diff options
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r-- | arch/x86/kvm/cpuid.c | 34 | ||||
-rw-r--r-- | arch/x86/kvm/cpuid.h | 2 | ||||
-rw-r--r-- | arch/x86/kvm/emulate.c | 74 | ||||
-rw-r--r-- | arch/x86/kvm/hyperv.c | 11 | ||||
-rw-r--r-- | arch/x86/kvm/ioapic.c | 15 | ||||
-rw-r--r-- | arch/x86/kvm/irq_comm.c | 2 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 20 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.c | 460 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.h | 21 | ||||
-rw-r--r-- | arch/x86/kvm/mmutrace.h | 59 | ||||
-rw-r--r-- | arch/x86/kvm/mtrr.c | 9 | ||||
-rw-r--r-- | arch/x86/kvm/paging_tmpl.h | 79 | ||||
-rw-r--r-- | arch/x86/kvm/pmu.c | 4 | ||||
-rw-r--r-- | arch/x86/kvm/pmu.h | 18 | ||||
-rw-r--r-- | arch/x86/kvm/pmu_intel.c | 37 | ||||
-rw-r--r-- | arch/x86/kvm/svm.c | 37 | ||||
-rw-r--r-- | arch/x86/kvm/trace.h | 4 | ||||
-rw-r--r-- | arch/x86/kvm/vmx.c | 246 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 191 |
19 files changed, 960 insertions, 363 deletions
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index c17d3893ae60..63c3ff9e74d4 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -279,13 +279,18 @@ static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry, { switch (func) { case 0: - entry->eax = 1; /* only one leaf currently */ + entry->eax = 7; ++*nent; break; case 1: entry->ecx = F(MOVBE); ++*nent; break; + case 7: + entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + if (index == 0) + entry->ecx = F(RDPID); + ++*nent; default: break; } @@ -355,7 +360,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 0x80000008.ebx */ const u32 kvm_cpuid_8000_0008_ebx_x86_features = - F(AMD_IBPB) | F(AMD_IBRS) | F(VIRT_SSBD); + F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | + F(AMD_SSB_NO) | F(AMD_STIBP); /* cpuid 0xC0000001.edx */ const u32 kvm_cpuid_C000_0001_edx_x86_features = @@ -380,14 +386,15 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 7.0.edx*/ const u32 kvm_cpuid_7_0_edx_x86_features = - F(SPEC_CTRL) | F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES); + F(SPEC_CTRL) | F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | + F(INTEL_STIBP) | F(MD_CLEAR); /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); r = -E2BIG; - if (*nent >= maxnent) + if (WARN_ON(*nent >= maxnent)) goto out; do_cpuid_1_ent(entry, function, index); @@ -464,8 +471,17 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* PKU is not yet implemented for shadow paging. */ if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) entry->ecx &= ~F(PKU); + entry->edx &= kvm_cpuid_7_0_edx_x86_features; cpuid_mask(&entry->edx, CPUID_7_EDX); + if (boot_cpu_has(X86_FEATURE_IBPB) && + boot_cpu_has(X86_FEATURE_IBRS)) + entry->edx |= F(SPEC_CTRL); + if (boot_cpu_has(X86_FEATURE_STIBP)) + entry->edx |= F(INTEL_STIBP); + if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + boot_cpu_has(X86_FEATURE_AMD_SSBD)) + entry->edx |= F(SPEC_CTRL_SSBD); /* * We emulate ARCH_CAPABILITIES in software even * if the host doesn't support it. @@ -633,7 +649,12 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->ebx |= F(VIRT_SSBD); entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); - if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD)) + /* + * The preference is to use SPEC CTRL MSR instead of the + * VIRT_SPEC MSR. + */ + if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) && + !boot_cpu_has(X86_FEATURE_AMD_SSBD)) entry->ebx |= F(VIRT_SSBD); break; } @@ -676,6 +697,9 @@ out: static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func, u32 idx, int *nent, int maxnent, unsigned int type) { + if (*nent >= maxnent) + return -E2BIG; + if (type == KVM_GET_EMULATED_CPUID) return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 8a841b9d8f84..b2bf8e1d5782 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -176,7 +176,7 @@ static inline bool guest_cpuid_has_spec_ctrl(struct kvm_vcpu *vcpu) struct kvm_cpuid_entry2 *best; best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); - if (best && (best->ebx & bit(X86_FEATURE_AMD_IBRS))) + if (best && (best->ebx & (bit(X86_FEATURE_AMD_IBRS | bit(X86_FEATURE_AMD_SSBD))))) return true; best = kvm_find_cpuid_entry(vcpu, 7, 0); return best && (best->edx & (bit(X86_FEATURE_SPEC_CTRL) | bit(X86_FEATURE_SPEC_CTRL_SSBD))); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 510cfc06701a..da3cd734dee1 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -21,6 +21,7 @@ */ #include <linux/kvm_host.h> +#include <linux/nospec.h> #include "kvm_cache_regs.h" #include <asm/kvm_emulate.h> #include <linux/stringify.h> @@ -2579,15 +2580,13 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) * CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU * supports long mode. */ - cr4 = ctxt->ops->get_cr(ctxt, 4); if (emulator_has_longmode(ctxt)) { struct desc_struct cs_desc; /* Zero CR4.PCIDE before CR0.PG. */ - if (cr4 & X86_CR4_PCIDE) { + cr4 = ctxt->ops->get_cr(ctxt, 4); + if (cr4 & X86_CR4_PCIDE) ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE); - cr4 &= ~X86_CR4_PCIDE; - } /* A 32-bit code segment is required to clear EFER.LMA. */ memset(&cs_desc, 0, sizeof(cs_desc)); @@ -2601,13 +2600,16 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) if (cr0 & X86_CR0_PE) ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE)); - /* Now clear CR4.PAE (which must be done before clearing EFER.LME). */ - if (cr4 & X86_CR4_PAE) - ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE); + if (emulator_has_longmode(ctxt)) { + /* Clear CR4.PAE before clearing EFER.LME. */ + cr4 = ctxt->ops->get_cr(ctxt, 4); + if (cr4 & X86_CR4_PAE) + ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE); - /* And finally go back to 32-bit mode. */ - efer = 0; - ctxt->ops->set_msr(ctxt, MSR_EFER, efer); + /* And finally go back to 32-bit mode. */ + efer = 0; + ctxt->ops->set_msr(ctxt, MSR_EFER, efer); + } smbase = ctxt->ops->get_smbase(ctxt); if (emulator_has_longmode(ctxt)) @@ -3529,6 +3531,16 @@ static int em_cwd(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_rdpid(struct x86_emulate_ctxt *ctxt) +{ + u64 tsc_aux = 0; + + if (ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux)) + return emulate_gp(ctxt, 0); + ctxt->dst.val = tsc_aux; + return X86EMUL_CONTINUE; +} + static int em_rdtsc(struct x86_emulate_ctxt *ctxt) { u64 tsc = 0; @@ -4389,10 +4401,20 @@ static const struct opcode group8[] = { F(DstMem | SrcImmByte | Lock | PageTable, em_btc), }; +/* + * The "memory" destination is actually always a register, since we come + * from the register case of group9. + */ +static const struct gprefix pfx_0f_c7_7 = { + N, N, N, II(DstMem | ModRM | Op3264 | EmulateOnUD, em_rdpid, rdtscp), +}; + + static const struct group_dual group9 = { { N, I(DstMem64 | Lock | PageTable, em_cmpxchg8b), N, N, N, N, N, N, }, { - N, N, N, N, N, N, N, N, + N, N, N, N, N, N, N, + GP(0, &pfx_0f_c7_7), } }; static const struct opcode group11[] = { @@ -5000,6 +5022,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) ctxt->fetch.ptr = ctxt->fetch.data; ctxt->fetch.end = ctxt->fetch.data + insn_len; ctxt->opcode_len = 1; + ctxt->intercept = x86_intercept_none; if (insn_len > 0) memcpy(ctxt->fetch.data, insn, insn_len); else { @@ -5052,16 +5075,28 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) ctxt->ad_bytes = def_ad_bytes ^ 6; break; case 0x26: /* ES override */ + has_seg_override = true; + ctxt->seg_override = VCPU_SREG_ES; + break; case 0x2e: /* CS override */ + has_seg_override = true; + ctxt->seg_override = VCPU_SREG_CS; + break; case 0x36: /* SS override */ + has_seg_override = true; + ctxt->seg_override = VCPU_SREG_SS; + break; case 0x3e: /* DS override */ has_seg_override = true; - ctxt->seg_override = (ctxt->b >> 3) & 3; + ctxt->seg_override = VCPU_SREG_DS; break; case 0x64: /* FS override */ + has_seg_override = true; + ctxt->seg_override = VCPU_SREG_FS; + break; case 0x65: /* GS override */ has_seg_override = true; - ctxt->seg_override = ctxt->b & 7; + ctxt->seg_override = VCPU_SREG_GS; break; case 0x40 ... 0x4f: /* REX */ if (mode != X86EMUL_MODE_PROT64) @@ -5145,10 +5180,15 @@ done_prefixes: } break; case Escape: - if (ctxt->modrm > 0xbf) - opcode = opcode.u.esc->high[ctxt->modrm - 0xc0]; - else + if (ctxt->modrm > 0xbf) { + size_t size = ARRAY_SIZE(opcode.u.esc->high); + u32 index = array_index_nospec( + ctxt->modrm - 0xc0, size); + + opcode = opcode.u.esc->high[index]; + } else { opcode = opcode.u.esc->op[(ctxt->modrm >> 3) & 7]; + } break; case InstrDual: if ((ctxt->modrm >> 6) == 3) @@ -5256,6 +5296,8 @@ done_prefixes: ctxt->memopp->addr.mem.ea + ctxt->_eip); done: + if (rc == X86EMUL_PROPAGATE_FAULT) + ctxt->have_exception = true; return (rc != X86EMUL_CONTINUE) ? EMULATION_FAILED : EMULATION_OK; } diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 42b1c83741c8..5e837c96e93f 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -28,6 +28,7 @@ #include <linux/kvm_host.h> #include <linux/highmem.h> +#include <linux/nospec.h> #include <asm/apicdef.h> #include <trace/events/kvm.h> @@ -719,11 +720,12 @@ static int kvm_hv_msr_get_crash_data(struct kvm_vcpu *vcpu, u32 index, u64 *pdata) { struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + size_t size = ARRAY_SIZE(hv->hv_crash_param); - if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param))) + if (WARN_ON_ONCE(index >= size)) return -EINVAL; - *pdata = hv->hv_crash_param[index]; + *pdata = hv->hv_crash_param[array_index_nospec(index, size)]; return 0; } @@ -762,11 +764,12 @@ static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu, u32 index, u64 data) { struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + size_t size = ARRAY_SIZE(hv->hv_crash_param); - if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param))) + if (WARN_ON_ONCE(index >= size)) return -EINVAL; - hv->hv_crash_param[index] = data; + hv->hv_crash_param[array_index_nospec(index, size)] = data; return 0; } diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 5f810bb80802..aa34b16e62c2 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -36,6 +36,7 @@ #include <linux/io.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/nospec.h> #include <asm/processor.h> #include <asm/page.h> #include <asm/current.h> @@ -73,13 +74,14 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, default: { u32 redir_index = (ioapic->ioregsel - 0x10) >> 1; - u64 redir_content; + u64 redir_content = ~0ULL; - if (redir_index < IOAPIC_NUM_PINS) - redir_content = - ioapic->redirtbl[redir_index].bits; - else - redir_content = ~0ULL; + if (redir_index < IOAPIC_NUM_PINS) { + u32 index = array_index_nospec( + redir_index, IOAPIC_NUM_PINS); + + redir_content = ioapic->redirtbl[index].bits; + } result = (ioapic->ioregsel & 0x1) ? (redir_content >> 32) & 0xffffffff : @@ -299,6 +301,7 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) ioapic_debug("change redir index %x val %x\n", index, val); if (index >= IOAPIC_NUM_PINS) return; + index = array_index_nospec(index, IOAPIC_NUM_PINS); e = &ioapic->redirtbl[index]; mask_before = e->fields.mask; /* Preserve read-only fields */ diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 6c0191615f23..cf8b3c17657a 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -436,7 +436,7 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, kvm_set_msi_irq(vcpu->kvm, entry, &irq); - if (irq.level && kvm_apic_match_dest(vcpu, NULL, 0, + if (irq.trig_mode && kvm_apic_match_dest(vcpu, NULL, 0, irq.dest_id, irq.dest_mode)) __set_bit(irq.vector, ioapic_handled_vectors); } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index c8630569e392..3988e26af3b5 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -28,6 +28,7 @@ #include <linux/export.h> #include <linux/math64.h> #include <linux/slab.h> +#include <linux/nospec.h> #include <asm/processor.h> #include <asm/msr.h> #include <asm/page.h> @@ -531,9 +532,11 @@ static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu) static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu) { u8 val; - if (pv_eoi_get_user(vcpu, &val) < 0) + if (pv_eoi_get_user(vcpu, &val) < 0) { apic_debug("Can't read EOI MSR value: 0x%llx\n", (unsigned long long)vcpu->arch.pv_eoi.msr_val); + return false; + } return val & 0x1; } @@ -1587,15 +1590,20 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_LVTTHMR: case APIC_LVTPC: case APIC_LVT1: - case APIC_LVTERR: + case APIC_LVTERR: { /* TODO: Check vector */ + size_t size; + u32 index; + if (!kvm_apic_sw_enabled(apic)) val |= APIC_LVT_MASKED; - - val &= apic_lvt_mask[(reg - APIC_LVTT) >> 4]; + size = ARRAY_SIZE(apic_lvt_mask); + index = array_index_nospec( + (reg - APIC_LVTT) >> 4, size); + val &= apic_lvt_mask[index]; kvm_lapic_set_reg(apic, reg, val); - break; + } case APIC_LVTT: if (!kvm_apic_sw_enabled(apic)) @@ -1992,7 +2000,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) struct kvm_lapic *apic = vcpu->arch.apic; int highest_irr; - if (!apic_enabled(apic)) + if (!kvm_apic_hw_enabled(apic)) return -1; apic_update_ppr(apic); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 676edfc19a95..3a281a2decde 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -37,6 +37,7 @@ #include <linux/srcu.h> #include <linux/slab.h> #include <linux/uaccess.h> +#include <linux/kthread.h> #include <asm/page.h> #include <asm/cmpxchg.h> @@ -44,6 +45,30 @@ #include <asm/vmx.h> #include <asm/kvm_page_track.h> +extern bool itlb_multihit_kvm_mitigation; + +static int __read_mostly nx_huge_pages = -1; +static uint __read_mostly nx_huge_pages_recovery_ratio = 60; + +static int set_nx_huge_pages(const char *val, const struct kernel_param *kp); +static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp); + +static struct kernel_param_ops nx_huge_pages_ops = { + .set = set_nx_huge_pages, + .get = param_get_bool, +}; + +static struct kernel_param_ops nx_huge_pages_recovery_ratio_ops = { + .set = set_nx_huge_pages_recovery_ratio, + .get = param_get_uint, +}; + +module_param_cb(nx_huge_pages, &nx_huge_pages_ops, &nx_huge_pages, 0644); +__MODULE_PARM_TYPE(nx_huge_pages, "bool"); +module_param_cb(nx_huge_pages_recovery_ratio, &nx_huge_pages_recovery_ratio_ops, + &nx_huge_pages_recovery_ratio, 0644); +__MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint"); + /* * When setting this variable to true it enables Two-Dimensional-Paging * where the hardware walks 2 page tables: @@ -131,9 +156,6 @@ module_param(dbg, bool, 0644); #include <trace/events/kvm.h> -#define CREATE_TRACE_POINTS -#include "mmutrace.h" - #define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT) #define SPTE_MMU_WRITEABLE (1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1)) @@ -142,6 +164,20 @@ module_param(dbg, bool, 0644); /* make pte_list_desc fit well in cache line */ #define PTE_LIST_EXT 3 +/* + * Return values of handle_mmio_page_fault and mmu.page_fault: + * RET_PF_RETRY: let CPU fault again on the address. + * RET_PF_EMULATE: mmio page fault, emulate the instruction directly. + * + * For handle_mmio_page_fault only: + * RET_PF_INVALID: the spte is invalid, let the real page fault path update it. + */ +enum { + RET_PF_RETRY = 0, + RET_PF_EMULATE = 1, + RET_PF_INVALID = 2, +}; + struct pte_list_desc { u64 *sptes[PTE_LIST_EXT]; struct pte_list_desc *more; @@ -179,14 +215,23 @@ static u64 __read_mostly shadow_mmio_mask; static u64 __read_mostly shadow_present_mask; static void mmu_spte_set(u64 *sptep, u64 spte); +static bool is_executable_pte(u64 spte); static void mmu_free_roots(struct kvm_vcpu *vcpu); +#define CREATE_TRACE_POINTS +#include "mmutrace.h" + void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask) { shadow_mmio_mask = mmio_mask; } EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask); +static bool is_nx_huge_page_enabled(void) +{ + return READ_ONCE(nx_huge_pages); +} + /* * the low bit of the generation number is always presumed to be zero. * This disables mmio caching during memslot updates. The concept is @@ -324,6 +369,11 @@ static int is_last_spte(u64 pte, int level) return 0; } +static bool is_executable_pte(u64 spte) +{ + return (spte & (shadow_x_mask | shadow_nx_mask)) == shadow_x_mask; +} + static kvm_pfn_t spte_to_pfn(u64 pte) { return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; @@ -767,10 +817,16 @@ static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index) static void kvm_mmu_page_set_gfn(struct kvm_mmu_page *sp, int index, gfn_t gfn) { - if (sp->role.direct) - BUG_ON(gfn != kvm_mmu_page_get_gfn(sp, index)); - else + if (!sp->role.direct) { sp->gfns[index] = gfn; + return; + } + + if (WARN_ON(gfn != kvm_mmu_page_get_gfn(sp, index))) + pr_err_ratelimited("gfn mismatch under direct page %llx " + "(expected %llx, got %llx)\n", + sp->gfn, + kvm_mmu_page_get_gfn(sp, index), gfn); } /* @@ -829,6 +885,17 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_disallow_lpage(slot, gfn); } +static void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + if (sp->lpage_disallowed) + return; + + ++kvm->stat.nx_lpage_splits; + list_add_tail(&sp->lpage_disallowed_link, + &kvm->arch.lpage_disallowed_mmu_pages); + sp->lpage_disallowed = true; +} + static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) { struct kvm_memslots *slots; @@ -846,6 +913,13 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_allow_lpage(slot, gfn); } +static void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + --kvm->stat.nx_lpage_splits; + sp->lpage_disallowed = false; + list_del(&sp->lpage_disallowed_link); +} + static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level, struct kvm_memory_slot *slot) { @@ -2382,6 +2456,9 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, kvm_reload_remote_mmus(kvm); } + if (sp->lpage_disallowed) + unaccount_huge_nx_page(kvm, sp); + sp->role.invalid = 1; return ret; } @@ -2533,6 +2610,11 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (!speculative) spte |= shadow_accessed_mask; + if (level > PT_PAGE_TABLE_LEVEL && (pte_access & ACC_EXEC_MASK) && + is_nx_huge_page_enabled()) { + pte_access &= ~ACC_EXEC_MASK; + } + if (pte_access & ACC_EXEC_MASK) spte |= shadow_x_mask; else @@ -2598,13 +2680,13 @@ done: return ret; } -static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, - int write_fault, int level, gfn_t gfn, kvm_pfn_t pfn, - bool speculative, bool host_writable) +static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, + int write_fault, int level, gfn_t gfn, kvm_pfn_t pfn, + bool speculative, bool host_writable) { int was_rmapped = 0; int rmap_count; - bool emulate = false; + int ret = RET_PF_RETRY; pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__, *sptep, write_fault, gfn); @@ -2634,18 +2716,15 @@ static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, if (set_spte(vcpu, sptep, pte_access, level, gfn, pfn, speculative, true, host_writable)) { if (write_fault) - emulate = true; + ret = RET_PF_EMULATE; kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); } if (unlikely(is_mmio_spte(*sptep))) - emulate = true; + ret = RET_PF_EMULATE; pgprintk("%s: setting spte %llx\n", __func__, *sptep); - pgprintk("instantiating %s PTE (%s) at %llx (%llx) addr %p\n", - is_large_pte(*sptep)? "2MB" : "4kB", - *sptep & PT_PRESENT_MASK ?"RW":"R", gfn, - *sptep, sptep); + trace_kvm_mmu_set_spte(level, gfn, sptep); if (!was_rmapped && is_large_pte(*sptep)) ++vcpu->kvm->stat.lpages; @@ -2657,9 +2736,7 @@ static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, } } - kvm_release_pfn_clean(pfn); - - return emulate; + return ret; } static kvm_pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, @@ -2693,9 +2770,11 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, if (ret <= 0) return -1; - for (i = 0; i < ret; i++, gfn++, start++) + for (i = 0; i < ret; i++, gfn++, start++) { mmu_set_spte(vcpu, start, access, 0, sp->role.level, gfn, page_to_pfn(pages[i]), true, true); + put_page(pages[i]); + } return 0; } @@ -2743,40 +2822,71 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) __direct_pte_prefetch(vcpu, sp, sptep); } -static int __direct_map(struct kvm_vcpu *vcpu, int write, int map_writable, - int level, gfn_t gfn, kvm_pfn_t pfn, bool prefault) +static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it, + gfn_t gfn, kvm_pfn_t *pfnp, int *levelp) { - struct kvm_shadow_walk_iterator iterator; + int level = *levelp; + u64 spte = *it.sptep; + + if (it.level == level && level > PT_PAGE_TABLE_LEVEL && + is_nx_huge_page_enabled() && + is_shadow_present_pte(spte) && + !is_large_pte(spte)) { + /* + * A small SPTE exists for this pfn, but FNAME(fetch) + * and __direct_map would like to create a large PTE + * instead: just force them to go down another level, + * patching back for them into pfn the next 9 bits of + * the address. + */ + u64 page_mask = KVM_PAGES_PER_HPAGE(level) - KVM_PAGES_PER_HPAGE(level - 1); + *pfnp |= gfn & page_mask; + (*levelp)--; + } +} + +static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write, + int map_writable, int level, kvm_pfn_t pfn, + bool prefault, bool lpage_disallowed) +{ + struct kvm_shadow_walk_iterator it; struct kvm_mmu_page *sp; - int emulate = 0; - gfn_t pseudo_gfn; + int ret; + gfn_t gfn = gpa >> PAGE_SHIFT; + gfn_t base_gfn = gfn; if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) - return 0; + return RET_PF_RETRY; - for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) { - if (iterator.level == level) { - emulate = mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, - write, level, gfn, pfn, prefault, - map_writable); - direct_pte_prefetch(vcpu, iterator.sptep); - ++vcpu->stat.pf_fixed; - break; - } + trace_kvm_mmu_spte_requested(gpa, level, pfn); + for_each_shadow_entry(vcpu, gpa, it) { + /* + * We cannot overwrite existing page tables with an NX + * large page, as the leaf could be executable. + */ + disallowed_hugepage_adjust(it, gfn, &pfn, &level); - drop_large_spte(vcpu, iterator.sptep); - if (!is_shadow_present_pte(*iterator.sptep)) { - u64 base_addr = iterator.addr; + base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + if (it.level == level) + break; - base_addr &= PT64_LVL_ADDR_MASK(iterator.level); - pseudo_gfn = base_addr >> PAGE_SHIFT; - sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr, - iterator.level - 1, 1, ACC_ALL); + drop_large_spte(vcpu, it.sptep); + if (!is_shadow_present_pte(*it.sptep)) { + sp = kvm_mmu_get_page(vcpu, base_gfn, it.addr, + it.level - 1, true, ACC_ALL); - link_shadow_page(vcpu, iterator.sptep, sp); + link_shadow_page(vcpu, it.sptep, sp); + if (lpage_disallowed) + account_huge_nx_page(vcpu->kvm, sp); } } - return emulate; + + ret = mmu_set_spte(vcpu, it.sptep, ACC_ALL, + write, level, base_gfn, pfn, prefault, + map_writable); + direct_pte_prefetch(vcpu, it.sptep); + ++vcpu->stat.pf_fixed; + return ret; } static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *tsk) @@ -2798,25 +2908,23 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) * Do not cache the mmio info caused by writing the readonly gfn * into the spte otherwise read access on readonly gfn also can * caused mmio page fault and treat it as mmio access. - * Return 1 to tell kvm to emulate it. */ if (pfn == KVM_PFN_ERR_RO_FAULT) - return 1; + return RET_PF_EMULATE; if (pfn == KVM_PFN_ERR_HWPOISON) { kvm_send_hwpoison_signal(kvm_vcpu_gfn_to_hva(vcpu, gfn), current); - return 0; + return RET_PF_RETRY; } return -EFAULT; } static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, - gfn_t *gfnp, kvm_pfn_t *pfnp, + gfn_t gfn, kvm_pfn_t *pfnp, int *levelp) { kvm_pfn_t pfn = *pfnp; - gfn_t gfn = *gfnp; int level = *levelp; /* @@ -2826,7 +2934,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, * here. */ if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) && - level == PT_PAGE_TABLE_LEVEL && + !kvm_is_zone_device_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL && PageTransCompoundMap(pfn_to_page(pfn)) && !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) { unsigned long mask; @@ -2843,8 +2951,6 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, mask = KVM_PAGES_PER_HPAGE(level) - 1; VM_BUG_ON((gfn & mask) != (pfn & mask)); if (pfn & mask) { - gfn &= ~mask; - *gfnp = gfn; kvm_release_pfn_clean(pfn); pfn &= ~mask; kvm_get_pfn(pfn); @@ -3012,11 +3118,14 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, { int r; int level; - bool force_pt_level = false; + bool force_pt_level; kvm_pfn_t pfn; unsigned long mmu_seq; bool map_writable, write = error_code & PFERR_WRITE_MASK; + bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && + is_nx_huge_page_enabled(); + force_pt_level = lpage_disallowed; level = mapping_level(vcpu, gfn, &force_pt_level); if (likely(!force_pt_level)) { /* @@ -3031,32 +3140,30 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, } if (fast_page_fault(vcpu, v, level, error_code)) - return 0; + return RET_PF_RETRY; mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); if (try_async_pf(vcpu, prefault, gfn, v, &pfn, write, &map_writable)) - return 0; + return RET_PF_RETRY; if (handle_abnormal_pfn(vcpu, v, gfn, pfn, ACC_ALL, &r)) return r; + r = RET_PF_RETRY; spin_lock(&vcpu->kvm->mmu_lock); if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; make_mmu_pages_available(vcpu); if (likely(!force_pt_level)) - transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); - r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault); - spin_unlock(&vcpu->kvm->mmu_lock); - - return r; - + transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); + r = __direct_map(vcpu, v, write, map_writable, level, pfn, + prefault, false); out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); - return 0; + return r; } @@ -3383,38 +3490,38 @@ exit: return reserved; } -int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct) +static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct) { u64 spte; bool reserved; if (mmio_info_in_cache(vcpu, addr, direct)) - return RET_MMIO_PF_EMULATE; + return RET_PF_EMULATE; reserved = walk_shadow_page_get_mmio_spte(vcpu, addr, &spte); if (WARN_ON(reserved)) - return RET_MMIO_PF_BUG; + return -EINVAL; if (is_mmio_spte(spte)) { gfn_t gfn = get_mmio_spte_gfn(spte); unsigned access = get_mmio_spte_access(spte); if (!check_mmio_spte(vcpu, spte)) - return RET_MMIO_PF_INVALID; + return RET_PF_INVALID; if (direct) addr = 0; trace_handle_mmio_page_fault(addr, gfn, access); vcpu_cache_mmio_info(vcpu, addr, gfn, access); - return RET_MMIO_PF_EMULATE; + return RET_PF_EMULATE; } /* * If the page table is zapped by other cpus, let CPU fault again on * the address. */ - return RET_MMIO_PF_RETRY; + return RET_PF_RETRY; } EXPORT_SYMBOL_GPL(handle_mmio_page_fault); @@ -3464,7 +3571,7 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code); if (page_fault_handle_page_track(vcpu, error_code, gfn)) - return 1; + return RET_PF_EMULATE; r = mmu_topup_memory_caches(vcpu); if (r) @@ -3548,18 +3655,21 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, unsigned long mmu_seq; int write = error_code & PFERR_WRITE_MASK; bool map_writable; + bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && + is_nx_huge_page_enabled(); MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); if (page_fault_handle_page_track(vcpu, error_code, gfn)) - return 1; + return RET_PF_EMULATE; r = mmu_topup_memory_caches(vcpu); if (r) return r; - force_pt_level = !check_hugepage_cache_consistency(vcpu, gfn, - PT_DIRECTORY_LEVEL); + force_pt_level = + lpage_disallowed || + !check_hugepage_cache_consistency(vcpu, gfn, PT_DIRECTORY_LEVEL); level = mapping_level(vcpu, gfn, &force_pt_level); if (likely(!force_pt_level)) { if (level > PT_DIRECTORY_LEVEL && @@ -3569,32 +3679,30 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, } if (fast_page_fault(vcpu, gpa, level, error_code)) - return 0; + return RET_PF_RETRY; mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable)) - return 0; + return RET_PF_RETRY; if (handle_abnormal_pfn(vcpu, 0, gfn, pfn, ACC_ALL, &r)) return r; + r = RET_PF_RETRY; spin_lock(&vcpu->kvm->mmu_lock); if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; make_mmu_pages_available(vcpu); if (likely(!force_pt_level)) - transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); - r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault); - spin_unlock(&vcpu->kvm->mmu_lock); - - return r; - + transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); + r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, + prefault, lpage_disallowed); out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); - return 0; + return r; } static void nonpaging_init_context(struct kvm_vcpu *vcpu, @@ -4510,23 +4618,24 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code, enum emulation_result er; bool direct = vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu); + r = RET_PF_INVALID; if (unlikely(error_code & PFERR_RSVD_MASK)) { r = handle_mmio_page_fault(vcpu, cr2, direct); - if (r == RET_MMIO_PF_EMULATE) { + if (r == RET_PF_EMULATE) { emulation_type = 0; goto emulate; } - if (r == RET_MMIO_PF_RETRY) - return 1; - if (r < 0) - return r; } - r = vcpu->arch.mmu.page_fault(vcpu, cr2, error_code, false); + if (r == RET_PF_INVALID) { + r = vcpu->arch.mmu.page_fault(vcpu, cr2, error_code, false); + WARN_ON(r == RET_PF_INVALID); + } + + if (r == RET_PF_RETRY) + return 1; if (r < 0) return r; - if (!r) - return 1; if (mmio_info_in_cache(vcpu, cr2, direct)) emulation_type = 0; @@ -4781,9 +4890,9 @@ restart: * the guest, and the guest page table is using 4K page size * mapping if the indirect sp has level = 1. */ - if (sp->role.direct && - !kvm_is_reserved_pfn(pfn) && - PageTransCompoundMap(pfn_to_page(pfn))) { + if (sp->role.direct && !kvm_is_reserved_pfn(pfn) && + !kvm_is_zone_device_pfn(pfn) && + PageTransCompoundMap(pfn_to_page(pfn))) { drop_spte(kvm, sptep); need_tlb_flush = 1; goto restart; @@ -4965,7 +5074,7 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) int nr_to_scan = sc->nr_to_scan; unsigned long freed = 0; - spin_lock(&kvm_lock); + mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { int idx; @@ -5015,7 +5124,7 @@ unlock: break; } - spin_unlock(&kvm_lock); + mutex_unlock(&kvm_lock); return freed; } @@ -5039,8 +5148,58 @@ static void mmu_destroy_caches(void) kmem_cache_destroy(mmu_page_header_cache); } +static bool get_nx_auto_mode(void) +{ + /* Return true when CPU has the bug, and mitigations are ON */ + return boot_cpu_has_bug(X86_BUG_ITLB_MULTIHIT) && !cpu_mitigations_off(); +} + +static void __set_nx_huge_pages(bool val) +{ + nx_huge_pages = itlb_multihit_kvm_mitigation = val; +} + +static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) +{ + bool old_val = nx_huge_pages; + bool new_val; + + /* In "auto" mode deploy workaround only if CPU has the bug. */ + if (sysfs_streq(val, "off")) + new_val = 0; + else if (sysfs_streq(val, "force")) + new_val = 1; + else if (sysfs_streq(val, "auto")) + new_val = get_nx_auto_mode(); + else if (strtobool(val, &new_val) < 0) + return -EINVAL; + + __set_nx_huge_pages(new_val); + + if (new_val != old_val) { + struct kvm *kvm; + int idx; + + mutex_lock(&kvm_lock); + + list_for_each_entry(kvm, &vm_list, vm_list) { + idx = srcu_read_lock(&kvm->srcu); + kvm_mmu_invalidate_zap_all_pages(kvm); + srcu_read_unlock(&kvm->srcu, idx); + + wake_up_process(kvm->arch.nx_lpage_recovery_thread); + } + mutex_unlock(&kvm_lock); + } + + return 0; +} + int kvm_mmu_module_init(void) { + if (nx_huge_pages == -1) + __set_nx_huge_pages(get_nx_auto_mode()); + pte_list_desc_cache = kmem_cache_create("pte_list_desc", sizeof(struct pte_list_desc), 0, SLAB_ACCOUNT, NULL); @@ -5104,3 +5263,116 @@ void kvm_mmu_module_exit(void) unregister_shrinker(&mmu_shrinker); mmu_audit_disable(); } + +static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp) +{ + unsigned int old_val; + int err; + + old_val = nx_huge_pages_recovery_ratio; + err = param_set_uint(val, kp); + if (err) + return err; + + if (READ_ONCE(nx_huge_pages) && + !old_val && nx_huge_pages_recovery_ratio) { + struct kvm *kvm; + + mutex_lock(&kvm_lock); + + list_for_each_entry(kvm, &vm_list, vm_list) + wake_up_process(kvm->arch.nx_lpage_recovery_thread); + + mutex_unlock(&kvm_lock); + } + + return err; +} + +static void kvm_recover_nx_lpages(struct kvm *kvm) +{ + int rcu_idx; + struct kvm_mmu_page *sp; + unsigned int ratio; + LIST_HEAD(invalid_list); + ulong to_zap; + + rcu_idx = srcu_read_lock(&kvm->srcu); + spin_lock(&kvm->mmu_lock); + + ratio = READ_ONCE(nx_huge_pages_recovery_ratio); + to_zap = ratio ? DIV_ROUND_UP(kvm->stat.nx_lpage_splits, ratio) : 0; + while (to_zap && !list_empty(&kvm->arch.lpage_disallowed_mmu_pages)) { + /* + * We use a separate list instead of just using active_mmu_pages + * because the number of lpage_disallowed pages is expected to + * be relatively small compared to the total. + */ + sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages, + struct kvm_mmu_page, + lpage_disallowed_link); + WARN_ON_ONCE(!sp->lpage_disallowed); + kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); + WARN_ON_ONCE(sp->lpage_disallowed); + + if (!--to_zap || need_resched() || spin_needbreak(&kvm->mmu_lock)) { + kvm_mmu_commit_zap_page(kvm, &invalid_list); + if (to_zap) + cond_resched_lock(&kvm->mmu_lock); + } + } + + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, rcu_idx); +} + +static long get_nx_lpage_recovery_timeout(u64 start_time) +{ + return READ_ONCE(nx_huge_pages) && READ_ONCE(nx_huge_pages_recovery_ratio) + ? start_time + 60 * HZ - get_jiffies_64() + : MAX_SCHEDULE_TIMEOUT; +} + +static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data) +{ + u64 start_time; + long remaining_time; + + while (true) { + start_time = get_jiffies_64(); + remaining_time = get_nx_lpage_recovery_timeout(start_time); + + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop() && remaining_time > 0) { + schedule_timeout(remaining_time); + remaining_time = get_nx_lpage_recovery_timeout(start_time); + set_current_state(TASK_INTERRUPTIBLE); + } + + set_current_state(TASK_RUNNING); + + if (kthread_should_stop()) + return 0; + + kvm_recover_nx_lpages(kvm); + } +} + +int kvm_mmu_post_init_vm(struct kvm *kvm) +{ + int err; + + err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0, + "kvm-nx-lpage-recovery", + &kvm->arch.nx_lpage_recovery_thread); + if (!err) + kthread_unpark(kvm->arch.nx_lpage_recovery_thread); + + return err; +} + +void kvm_mmu_pre_destroy_vm(struct kvm *kvm) +{ + if (kvm->arch.nx_lpage_recovery_thread) + kthread_stop(kvm->arch.nx_lpage_recovery_thread); +} diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index c92834c55c59..e584689e7d46 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -56,23 +56,6 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask); void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context); -/* - * Return values of handle_mmio_page_fault: - * RET_MMIO_PF_EMULATE: it is a real mmio page fault, emulate the instruction - * directly. - * RET_MMIO_PF_INVALID: invalid spte is detected then let the real page - * fault path update the mmio spte. - * RET_MMIO_PF_RETRY: let CPU fault again on the address. - * RET_MMIO_PF_BUG: a bug was detected (and a WARN was printed). - */ -enum { - RET_MMIO_PF_EMULATE = 1, - RET_MMIO_PF_INVALID = 2, - RET_MMIO_PF_RETRY = 0, - RET_MMIO_PF_BUG = -1 -}; - -int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct); void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly); bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); @@ -202,4 +185,8 @@ void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn); + +int kvm_mmu_post_init_vm(struct kvm *kvm); +void kvm_mmu_pre_destroy_vm(struct kvm *kvm); + #endif diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index 5a24b846a1cb..756b14ecc957 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -322,6 +322,65 @@ TRACE_EVENT( __entry->kvm_gen == __entry->spte_gen ) ); + +TRACE_EVENT( + kvm_mmu_set_spte, + TP_PROTO(int level, gfn_t gfn, u64 *sptep), + TP_ARGS(level, gfn, sptep), + + TP_STRUCT__entry( + __field(u64, gfn) + __field(u64, spte) + __field(u64, sptep) + __field(u8, level) + /* These depend on page entry type, so compute them now. */ + __field(bool, r) + __field(bool, x) + __field(u8, u) + ), + + TP_fast_assign( + __entry->gfn = gfn; + __entry->spte = *sptep; + __entry->sptep = virt_to_phys(sptep); + __entry->level = level; + __entry->r = shadow_present_mask || (__entry->spte & PT_PRESENT_MASK); + __entry->x = is_executable_pte(__entry->spte); + __entry->u = shadow_user_mask ? !!(__entry->spte & shadow_user_mask) : -1; + ), + + TP_printk("gfn %llx spte %llx (%s%s%s%s) level %d at %llx", + __entry->gfn, __entry->spte, + __entry->r ? "r" : "-", + __entry->spte & PT_PRESENT_MASK ? "w" : "-", + __entry->x ? "x" : "-", + __entry->u == -1 ? "" : (__entry->u ? "u" : "-"), + __entry->level, __entry->sptep + ) +); + +TRACE_EVENT( + kvm_mmu_spte_requested, + TP_PROTO(gpa_t addr, int level, kvm_pfn_t pfn), + TP_ARGS(addr, level, pfn), + + TP_STRUCT__entry( + __field(u64, gfn) + __field(u64, pfn) + __field(u8, level) + ), + + TP_fast_assign( + __entry->gfn = addr >> PAGE_SHIFT; + __entry->pfn = pfn | (__entry->gfn & (KVM_PAGES_PER_HPAGE(level) - 1)); + __entry->level = level; + ), + + TP_printk("gfn %llx pfn %llx level %d", + __entry->gfn, __entry->pfn, __entry->level + ) +); + #endif /* _TRACE_KVMMMU_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 0149ac59c273..3e3016411020 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -17,6 +17,7 @@ */ #include <linux/kvm_host.h> +#include <linux/nospec.h> #include <asm/mtrr.h> #include "cpuid.h" @@ -202,11 +203,15 @@ static bool fixed_msr_to_seg_unit(u32 msr, int *seg, int *unit) break; case MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000: *seg = 1; - *unit = msr - MSR_MTRRfix16K_80000; + *unit = array_index_nospec( + msr - MSR_MTRRfix16K_80000, + MSR_MTRRfix16K_A0000 - MSR_MTRRfix16K_80000 + 1); break; case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000: *seg = 2; - *unit = msr - MSR_MTRRfix4K_C0000; + *unit = array_index_nospec( + msr - MSR_MTRRfix4K_C0000, + MSR_MTRRfix4K_F8000 - MSR_MTRRfix4K_C0000 + 1); break; default: return false; diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 37363900297d..e03225e707b2 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -499,6 +499,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, mmu_set_spte(vcpu, spte, pte_access, 0, PT_PAGE_TABLE_LEVEL, gfn, pfn, true, true); + kvm_release_pfn_clean(pfn); return true; } @@ -572,12 +573,14 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, struct guest_walker *gw, int write_fault, int hlevel, - kvm_pfn_t pfn, bool map_writable, bool prefault) + kvm_pfn_t pfn, bool map_writable, bool prefault, + bool lpage_disallowed) { struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; unsigned direct_access, access = gw->pt_access; - int top_level, emulate; + int top_level, ret; + gfn_t gfn, base_gfn; direct_access = gw->pte_access; @@ -622,36 +625,49 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, link_shadow_page(vcpu, it.sptep, sp); } - for (; - shadow_walk_okay(&it) && it.level > hlevel; - shadow_walk_next(&it)) { - gfn_t direct_gfn; + /* + * FNAME(page_fault) might have clobbered the bottom bits of + * gw->gfn, restore them from the virtual address. + */ + gfn = gw->gfn | ((addr & PT_LVL_OFFSET_MASK(gw->level)) >> PAGE_SHIFT); + base_gfn = gfn; + trace_kvm_mmu_spte_requested(addr, gw->level, pfn); + + for (; shadow_walk_okay(&it); shadow_walk_next(&it)) { clear_sp_write_flooding_count(it.sptep); - validate_direct_spte(vcpu, it.sptep, direct_access); - drop_large_spte(vcpu, it.sptep); + /* + * We cannot overwrite existing page tables with an NX + * large page, as the leaf could be executable. + */ + disallowed_hugepage_adjust(it, gfn, &pfn, &hlevel); - if (is_shadow_present_pte(*it.sptep)) - continue; + base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + if (it.level == hlevel) + break; - direct_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + validate_direct_spte(vcpu, it.sptep, direct_access); - sp = kvm_mmu_get_page(vcpu, direct_gfn, addr, it.level-1, - true, direct_access); - link_shadow_page(vcpu, it.sptep, sp); + drop_large_spte(vcpu, it.sptep); + + if (!is_shadow_present_pte(*it.sptep)) { + sp = kvm_mmu_get_page(vcpu, base_gfn, addr, + it.level - 1, true, direct_access); + link_shadow_page(vcpu, it.sptep, sp); + if (lpage_disallowed) + account_huge_nx_page(vcpu->kvm, sp); + } } - clear_sp_write_flooding_count(it.sptep); - emulate = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault, - it.level, gw->gfn, pfn, prefault, map_writable); + ret = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault, + it.level, base_gfn, pfn, prefault, map_writable); FNAME(pte_prefetch)(vcpu, gw, it.sptep); - - return emulate; + ++vcpu->stat.pf_fixed; + return ret; out_gpte_changed: - kvm_release_pfn_clean(pfn); - return 0; + return RET_PF_RETRY; } /* @@ -717,9 +733,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, int r; kvm_pfn_t pfn; int level = PT_PAGE_TABLE_LEVEL; - bool force_pt_level = false; unsigned long mmu_seq; bool map_writable, is_self_change_mapping; + bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && + is_nx_huge_page_enabled(); + bool force_pt_level = lpage_disallowed; pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code); @@ -746,12 +764,12 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, if (!prefault) inject_page_fault(vcpu, &walker.fault); - return 0; + return RET_PF_RETRY; } if (page_fault_handle_page_track(vcpu, error_code, walker.gfn)) { shadow_page_table_clear_flood(vcpu, addr); - return 1; + return RET_PF_EMULATE; } vcpu->arch.write_fault_to_shadow_pgtable = false; @@ -773,7 +791,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, if (try_async_pf(vcpu, prefault, walker.gfn, addr, &pfn, write_fault, &map_writable)) - return 0; + return RET_PF_RETRY; if (handle_abnormal_pfn(vcpu, mmu_is_nested(vcpu) ? 0 : addr, walker.gfn, pfn, walker.pte_access, &r)) @@ -799,6 +817,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, walker.pte_access &= ~ACC_EXEC_MASK; } + r = RET_PF_RETRY; spin_lock(&vcpu->kvm->mmu_lock); if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; @@ -806,19 +825,15 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT); make_mmu_pages_available(vcpu); if (!force_pt_level) - transparent_hugepage_adjust(vcpu, &walker.gfn, &pfn, &level); + transparent_hugepage_adjust(vcpu, walker.gfn, &pfn, &level); r = FNAME(fetch)(vcpu, addr, &walker, write_fault, - level, pfn, map_writable, prefault); - ++vcpu->stat.pf_fixed; + level, pfn, map_writable, prefault, lpage_disallowed); kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT); - spin_unlock(&vcpu->kvm->mmu_lock); - - return r; out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); - return 0; + return r; } static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp) diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 06ce377dcbc9..0827ee7d0e9b 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -124,8 +124,8 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, intr ? kvm_perf_overflow_intr : kvm_perf_overflow, pmc); if (IS_ERR(event)) { - printk_once("kvm_pmu: event creation failed %ld\n", - PTR_ERR(event)); + pr_debug_ratelimited("kvm_pmu: event creation failed %ld for pmc->idx = %d\n", + PTR_ERR(event), pmc->idx); return; } diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index f96e1f962587..fbf3d25af765 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -1,6 +1,8 @@ #ifndef __KVM_X86_PMU_H #define __KVM_X86_PMU_H +#include <linux/nospec.h> + #define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu) #define pmu_to_vcpu(pmu) (container_of((pmu), struct kvm_vcpu, arch.pmu)) #define pmc_to_pmu(pmc) (&(pmc)->vcpu->arch.pmu) @@ -80,8 +82,12 @@ static inline bool pmc_is_enabled(struct kvm_pmc *pmc) static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr, u32 base) { - if (msr >= base && msr < base + pmu->nr_arch_gp_counters) - return &pmu->gp_counters[msr - base]; + if (msr >= base && msr < base + pmu->nr_arch_gp_counters) { + u32 index = array_index_nospec(msr - base, + pmu->nr_arch_gp_counters); + + return &pmu->gp_counters[index]; + } return NULL; } @@ -91,8 +97,12 @@ static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr) { int base = MSR_CORE_PERF_FIXED_CTR0; - if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) - return &pmu->fixed_counters[msr - base]; + if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) { + u32 index = array_index_nospec(msr - base, + pmu->nr_arch_fixed_counters); + + return &pmu->fixed_counters[index]; + } return NULL; } diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/pmu_intel.c index 5ab4a364348e..84ae4dd261ca 100644 --- a/arch/x86/kvm/pmu_intel.c +++ b/arch/x86/kvm/pmu_intel.c @@ -87,10 +87,14 @@ static unsigned intel_find_arch_event(struct kvm_pmu *pmu, static unsigned intel_find_fixed_event(int idx) { - if (idx >= ARRAY_SIZE(fixed_pmc_events)) + u32 event; + size_t size = ARRAY_SIZE(fixed_pmc_events); + + if (idx >= size) return PERF_COUNT_HW_MAX; - return intel_arch_events[fixed_pmc_events[idx]].event_type; + event = fixed_pmc_events[array_index_nospec(idx, size)]; + return intel_arch_events[event].event_type; } /* check if a PMC is enabled by comparing it with globl_ctrl bits. */ @@ -131,15 +135,19 @@ static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu, struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); bool fixed = idx & (1u << 30); struct kvm_pmc *counters; + unsigned int num_counters; idx &= ~(3u << 30); - if (!fixed && idx >= pmu->nr_arch_gp_counters) - return NULL; - if (fixed && idx >= pmu->nr_arch_fixed_counters) + if (fixed) { + counters = pmu->fixed_counters; + num_counters = pmu->nr_arch_fixed_counters; + } else { + counters = pmu->gp_counters; + num_counters = pmu->nr_arch_gp_counters; + } + if (idx >= num_counters) return NULL; - counters = fixed ? pmu->fixed_counters : pmu->gp_counters; - - return &counters[idx]; + return &counters[array_index_nospec(idx, num_counters)]; } static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) @@ -235,11 +243,14 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } break; default: - if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || - (pmc = get_fixed_pmc(pmu, msr))) { - if (!msr_info->host_initiated) - data = (s64)(s32)data; - pmc->counter += data - pmc_read_counter(pmc); + if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0))) { + if (msr_info->host_initiated) + pmc->counter = data; + else + pmc->counter = (s32)data; + return 0; + } else if ((pmc = get_fixed_pmc(pmu, msr))) { + pmc->counter = data; return 0; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { if (data == pmc->eventsel) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 01eb0451b96d..1079228e4fef 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -590,8 +590,14 @@ static int get_npt_level(void) static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) { vcpu->arch.efer = efer; - if (!npt_enabled && !(efer & EFER_LMA)) - efer &= ~EFER_LME; + + if (!npt_enabled) { + /* Shadow paging assumes NX to be available. */ + efer |= EFER_NX; + + if (!(efer & EFER_LMA)) + efer &= ~EFER_LME; + } to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME; mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR); @@ -1518,7 +1524,11 @@ static void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (!kvm_vcpu_apicv_active(vcpu)) return; - if (WARN_ON(h_physical_id >= AVIC_MAX_PHYSICAL_ID_COUNT)) + /* + * Since the host physical APIC id is 8 bits, + * we can support host APIC ID upto 255. + */ + if (WARN_ON(h_physical_id > AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK)) return; entry = READ_ONCE(*(svm->avic_physical_id_cache)); @@ -3704,7 +3714,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) return 1; /* The STIBP bit doesn't fault even if it's not advertised */ - if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP)) + if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD)) return 1; svm->spec_ctrl = data; @@ -3940,14 +3950,25 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm) kvm_lapic_reg_write(apic, APIC_ICR, icrl); break; case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: { + int i; + struct kvm_vcpu *vcpu; + struct kvm *kvm = svm->vcpu.kvm; struct kvm_lapic *apic = svm->vcpu.arch.apic; /* - * Update ICR high and low, then emulate sending IPI, - * which is handled when writing APIC_ICR. + * At this point, we expect that the AVIC HW has already + * set the appropriate IRR bits on the valid target + * vcpus. So, we just need to kick the appropriate vcpu. */ - kvm_lapic_reg_write(apic, APIC_ICR2, icrh); - kvm_lapic_reg_write(apic, APIC_ICR, icrl); + kvm_for_each_vcpu(i, vcpu, kvm) { + bool m = kvm_apic_match_dest(vcpu, apic, + icrl & KVM_APIC_SHORT_MASK, + GET_APIC_DEST_FIELD(icrh), + icrl & KVM_APIC_DEST_MASK); + + if (m && !avic_vcpu_is_running(vcpu)) + kvm_vcpu_wake_up(vcpu); + } break; } case AVIC_IPI_FAILURE_INVALID_TARGET: diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 0a6cc6754ec5..ea618b713b6f 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -434,13 +434,13 @@ TRACE_EVENT(kvm_apic_ipi, ); TRACE_EVENT(kvm_apic_accept_irq, - TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec), + 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( __u8, tm ) + __field( __u16, tm ) __field( __u8, vec ) ), diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a34fb7284024..2ad59d8553a5 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -714,7 +714,6 @@ struct vcpu_vmx { u64 msr_guest_kernel_gs_base; #endif - u64 arch_capabilities; u64 spec_ctrl; u32 vm_entry_controls_shadow; @@ -1548,7 +1547,7 @@ static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr) return -1; } -static inline void __invvpid(int ext, u16 vpid, gva_t gva) +static inline void __invvpid(unsigned long ext, u16 vpid, gva_t gva) { struct { u64 vpid : 16; @@ -1562,7 +1561,7 @@ static inline void __invvpid(int ext, u16 vpid, gva_t gva) : : "a"(&operand), "c"(ext) : "cc", "memory"); } -static inline void __invept(int ext, u64 eptp, gpa_t gpa) +static inline void __invept(unsigned long ext, u64 eptp, gpa_t gpa) { struct { u64 eptp, gpa; @@ -1620,43 +1619,15 @@ static void vmcs_load(struct vmcs *vmcs) } #ifdef CONFIG_KEXEC_CORE -/* - * This bitmap is used to indicate whether the vmclear - * operation is enabled on all cpus. All disabled by - * default. - */ -static cpumask_t crash_vmclear_enabled_bitmap = CPU_MASK_NONE; - -static inline void crash_enable_local_vmclear(int cpu) -{ - cpumask_set_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - -static inline void crash_disable_local_vmclear(int cpu) -{ - cpumask_clear_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - -static inline int crash_local_vmclear_enabled(int cpu) -{ - return cpumask_test_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - static void crash_vmclear_local_loaded_vmcss(void) { int cpu = raw_smp_processor_id(); struct loaded_vmcs *v; - if (!crash_local_vmclear_enabled(cpu)) - return; - list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu), loaded_vmcss_on_cpu_link) vmcs_clear(v->vmcs); } -#else -static inline void crash_enable_local_vmclear(int cpu) { } -static inline void crash_disable_local_vmclear(int cpu) { } #endif /* CONFIG_KEXEC_CORE */ static void __loaded_vmcs_clear(void *arg) @@ -1668,19 +1639,24 @@ static void __loaded_vmcs_clear(void *arg) return; /* vcpu migration can race with cpu offline */ if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs) per_cpu(current_vmcs, cpu) = NULL; - crash_disable_local_vmclear(cpu); + + vmcs_clear(loaded_vmcs->vmcs); + if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched) + vmcs_clear(loaded_vmcs->shadow_vmcs); + list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link); /* - * we should ensure updating loaded_vmcs->loaded_vmcss_on_cpu_link - * is before setting loaded_vmcs->vcpu to -1 which is done in - * loaded_vmcs_init. Otherwise, other cpu can see vcpu = -1 fist - * then adds the vmcs into percpu list before it is deleted. + * Ensure all writes to loaded_vmcs, including deleting it from its + * current percpu list, complete before setting loaded_vmcs->vcpu to + * -1, otherwise a different cpu can see vcpu == -1 first and add + * loaded_vmcs to its percpu list before it's deleted from this cpu's + * list. Pairs with the smp_rmb() in vmx_vcpu_load_vmcs(). */ smp_wmb(); - loaded_vmcs_init(loaded_vmcs); - crash_enable_local_vmclear(cpu); + loaded_vmcs->cpu = -1; + loaded_vmcs->launched = 0; } static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) @@ -2220,17 +2196,9 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) u64 guest_efer = vmx->vcpu.arch.efer; u64 ignore_bits = 0; - if (!enable_ept) { - /* - * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing - * host CPUID is more efficient than testing guest CPUID - * or CR4. Host SMEP is anyway a requirement for guest SMEP. - */ - if (boot_cpu_has(X86_FEATURE_SMEP)) - guest_efer |= EFER_NX; - else if (!(guest_efer & EFER_NX)) - ignore_bits |= EFER_NX; - } + /* Shadow paging assumes NX to be available. */ + if (!enable_ept) + guest_efer |= EFER_NX; /* * LMA and LME handled by hardware; SCE meaningless outside long mode. @@ -2480,18 +2448,17 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (!already_loaded) { local_irq_disable(); - crash_disable_local_vmclear(cpu); /* - * Read loaded_vmcs->cpu should be before fetching - * loaded_vmcs->loaded_vmcss_on_cpu_link. - * See the comments in __loaded_vmcs_clear(). + * Ensure loaded_vmcs->cpu is read before adding loaded_vmcs to + * this cpu's percpu list, otherwise it may not yet be deleted + * from its previous cpu's percpu list. Pairs with the + * smb_wmb() in __loaded_vmcs_clear(). */ smp_rmb(); list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link, &per_cpu(loaded_vmcss_on_cpu, cpu)); - crash_enable_local_vmclear(cpu); local_irq_enable(); } @@ -3209,12 +3176,6 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = to_vmx(vcpu)->spec_ctrl; break; - case MSR_IA32_ARCH_CAPABILITIES: - if (!msr_info->host_initiated && - !guest_cpuid_has_arch_capabilities(vcpu)) - return 1; - msr_info->data = to_vmx(vcpu)->arch_capabilities; - break; case MSR_IA32_SYSENTER_CS: msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); break; @@ -3376,11 +3337,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD, MSR_TYPE_W); break; - case MSR_IA32_ARCH_CAPABILITIES: - if (!msr_info->host_initiated) - return 1; - vmx->arch_capabilities = data; - break; case MSR_IA32_CR_PAT: if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) @@ -3526,21 +3482,6 @@ static int hardware_enable(void) if (cr4_read_shadow() & X86_CR4_VMXE) return -EBUSY; - INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); - INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu)); - spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); - - /* - * Now we can enable the vmclear operation in kdump - * since the loaded_vmcss_on_cpu list on this cpu - * has been initialized. - * - * Though the cpu is not in VMX operation now, there - * is no problem to enable the vmclear operation - * for the loaded_vmcss_on_cpu list is empty! - */ - crash_enable_local_vmclear(cpu); - rdmsrl(MSR_IA32_FEATURE_CONTROL, old); test_bits = FEATURE_CONTROL_LOCKED; @@ -4661,6 +4602,26 @@ static bool cs_ss_rpl_check(struct kvm_vcpu *vcpu) (ss.selector & SEGMENT_RPL_MASK)); } +static bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, + unsigned int port, int size); +static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + unsigned long exit_qualification; + unsigned short port; + int size; + + if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) + return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); + + exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + + port = exit_qualification >> 16; + size = (exit_qualification & 7) + 1; + + return nested_vmx_check_io_bitmaps(vcpu, port, size); +} + /* * Check if guest state is valid. Returns true if valid, false if * not. @@ -5468,8 +5429,6 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) ++vmx->nmsrs; } - vmx->arch_capabilities = kvm_get_arch_capabilities(); - vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl); /* 22.2.1, 20.8.1 */ @@ -6566,20 +6525,13 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) return 1; } else - return x86_emulate_instruction(vcpu, gpa, EMULTYPE_SKIP, - NULL, 0) == EMULATE_DONE; + return emulate_instruction(vcpu, EMULTYPE_SKIP) == + EMULATE_DONE; } - ret = handle_mmio_page_fault(vcpu, gpa, true); - if (likely(ret == RET_MMIO_PF_EMULATE)) - return x86_emulate_instruction(vcpu, gpa, 0, NULL, 0) == - EMULATE_DONE; - - if (unlikely(ret == RET_MMIO_PF_INVALID)) - return kvm_mmu_page_fault(vcpu, gpa, 0, NULL, 0); - - if (unlikely(ret == RET_MMIO_PF_RETRY)) - return 1; + ret = kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0); + if (ret >= 0) + return ret; /* It is the real ept misconfig */ WARN_ON(1); @@ -7653,6 +7605,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu) unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); gva_t gva = 0; + struct x86_exception e; if (!nested_vmx_check_permission(vcpu) || !nested_vmx_check_vmcs12(vcpu)) @@ -7679,8 +7632,12 @@ static int handle_vmread(struct kvm_vcpu *vcpu) vmx_instruction_info, true, &gva)) return 1; /* _system ok, as nested_vmx_check_permission verified cpl=0 */ - kvm_write_guest_virt_system(vcpu, gva, &field_value, - (is_long_mode(vcpu) ? 8 : 4), NULL); + if (kvm_write_guest_virt_system(vcpu, gva, &field_value, + (is_long_mode(vcpu) ? 8 : 4), + &e)) { + kvm_inject_page_fault(vcpu, &e); + return 1; + } } nested_vmx_succeed(vcpu); @@ -8050,23 +8007,17 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { static const int kvm_vmx_max_exit_handlers = ARRAY_SIZE(kvm_vmx_exit_handlers); -static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12) +/* + * Return true if an IO instruction with the specified port and size should cause + * a VM-exit into L1. + */ +bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, + int size) { - unsigned long exit_qualification; + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); gpa_t bitmap, last_bitmap; - unsigned int port; - int size; u8 b; - if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) - return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); - - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - - port = exit_qualification >> 16; - size = (exit_qualification & 7) + 1; - last_bitmap = (gpa_t)-1; b = -1; @@ -9220,8 +9171,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->__launched = vmx->loaded_vmcs->launched; + /* L1D Flush includes CPU buffer clear to mitigate MDS */ if (static_branch_unlikely(&vmx_l1d_should_flush)) vmx_l1d_flush(vcpu); + else if (static_branch_unlikely(&mds_user_clear)) + mds_clear_cpu_buffers(); asm( /* Store host registers */ @@ -9580,8 +9534,8 @@ free_vcpu: return ERR_PTR(err); } -#define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n" -#define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n" +#define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" +#define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" static int vmx_vm_init(struct kvm *kvm) { @@ -11356,11 +11310,71 @@ static void nested_vmx_entry_failure(struct kvm_vcpu *vcpu, to_vmx(vcpu)->nested.sync_shadow_vmcs = true; } +static int vmx_check_intercept_io(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + unsigned short port; + bool intercept; + int size; + + if (info->intercept == x86_intercept_in || + info->intercept == x86_intercept_ins) { + port = info->src_val; + size = info->dst_bytes; + } else { + port = info->dst_val; + size = info->src_bytes; + } + + /* + * If the 'use IO bitmaps' VM-execution control is 0, IO instruction + * VM-exits depend on the 'unconditional IO exiting' VM-execution + * control. + * + * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps. + */ + if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) + intercept = nested_cpu_has(vmcs12, + CPU_BASED_UNCOND_IO_EXITING); + else + intercept = nested_vmx_check_io_bitmaps(vcpu, port, size); + + return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; +} + static int vmx_check_intercept(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, enum x86_intercept_stage stage) { - return X86EMUL_CONTINUE; + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + + switch (info->intercept) { + /* + * RDPID causes #UD if disabled through secondary execution controls. + * Because it is marked as EmulateOnUD, we need to intercept it here. + */ + case x86_intercept_rdtscp: + if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) { + ctxt->exception.vector = UD_VECTOR; + ctxt->exception.error_code_valid = false; + return X86EMUL_PROPAGATE_FAULT; + } + break; + + case x86_intercept_in: + case x86_intercept_ins: + case x86_intercept_out: + case x86_intercept_outs: + return vmx_check_intercept_io(vcpu, info); + + /* TODO: check more intercepts... */ + default: + break; + } + + return X86EMUL_UNHANDLEABLE; } #ifdef CONFIG_X86_64 @@ -11842,7 +11856,7 @@ module_exit(vmx_exit) static int __init vmx_init(void) { - int r; + int r, cpu; r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), __alignof__(struct vcpu_vmx), THIS_MODULE); @@ -11864,6 +11878,12 @@ static int __init vmx_init(void) } } + for_each_possible_cpu(cpu) { + INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); + INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu)); + spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); + } + #ifdef CONFIG_KEXEC_CORE rcu_assign_pointer(crash_vmclear_loaded_vmcss, crash_vmclear_local_loaded_vmcss); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a29df9ccbfde..314eb954bdee 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -54,6 +54,7 @@ #include <linux/pvclock_gtod.h> #include <linux/kvm_irqfd.h> #include <linux/irqbypass.h> +#include <linux/nospec.h> #include <trace/events/kvm.h> #include <asm/debugreg.h> @@ -191,6 +192,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "mmu_unsync", VM_STAT(mmu_unsync) }, { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, { "largepages", VM_STAT(lpages) }, + { "nx_largepages_splitted", VM_STAT(nx_lpage_splits) }, { NULL } }; @@ -272,13 +274,14 @@ int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); int err; - if (((value ^ smsr->values[slot].curr) & mask) == 0) + value = (value & mask) | (smsr->values[slot].host & ~mask); + if (value == smsr->values[slot].curr) return 0; - smsr->values[slot].curr = value; err = wrmsrl_safe(shared_msrs_global.msrs[slot], value); if (err) return 1; + smsr->values[slot].curr = value; if (!smsr->registered) { smsr->urn.on_user_return = kvm_on_user_return; user_return_notifier_register(&smsr->urn); @@ -535,8 +538,14 @@ static int kvm_read_nested_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, data, offset, len, access); } +static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) +{ + return rsvd_bits(cpuid_maxphyaddr(vcpu), 63) | rsvd_bits(5, 8) | + rsvd_bits(1, 2); +} + /* - * Load the pae pdptrs. Return true is they are all valid. + * Load the pae pdptrs. Return 1 if they are all valid, 0 otherwise. */ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) { @@ -555,8 +564,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) } for (i = 0; i < ARRAY_SIZE(pdpte); ++i) { if ((pdpte[i] & PT_PRESENT_MASK) && - (pdpte[i] & - vcpu->arch.mmu.guest_rsvd_check.rsvd_bits_mask[0][2])) { + (pdpte[i] & pdptr_rsvd_bits(vcpu))) { ret = 0; goto out; } @@ -582,7 +590,7 @@ static bool pdptrs_changed(struct kvm_vcpu *vcpu) gfn_t gfn; int r; - if (is_long_mode(vcpu) || !is_pae(vcpu)) + if (is_long_mode(vcpu) || !is_pae(vcpu) || !is_paging(vcpu)) return false; if (!test_bit(VCPU_EXREG_PDPTR, @@ -882,9 +890,11 @@ static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu) static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) { + size_t size = ARRAY_SIZE(vcpu->arch.db); + switch (dr) { case 0 ... 3: - vcpu->arch.db[dr] = val; + vcpu->arch.db[array_index_nospec(dr, size)] = val; if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) vcpu->arch.eff_db[dr] = val; break; @@ -921,9 +931,11 @@ EXPORT_SYMBOL_GPL(kvm_set_dr); int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) { + size_t size = ARRAY_SIZE(vcpu->arch.db); + switch (dr) { case 0 ... 3: - *val = vcpu->arch.db[dr]; + *val = vcpu->arch.db[array_index_nospec(dr, size)]; break; case 4: /* fall through */ @@ -1027,6 +1039,14 @@ u64 kvm_get_arch_capabilities(void) rdmsrl_safe(MSR_IA32_ARCH_CAPABILITIES, &data); /* + * If nx_huge_pages is enabled, KVM's shadow paging will ensure that + * the nested hypervisor runs with NX huge pages. If it is not, + * L1 is anyway vulnerable to ITLB_MULTIHIT explots from other + * L1 guests, so it need not worry about its own (L2) guests. + */ + data |= ARCH_CAP_PSCHANGE_MC_NO; + + /* * If we're doing cache flushes (either "always" or "cond") * we will do one whenever the guest does a vmlaunch/vmresume. * If an outer hypervisor is doing the cache flush for us @@ -1038,8 +1058,40 @@ u64 kvm_get_arch_capabilities(void) if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER) data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH; + if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + data |= ARCH_CAP_RDCL_NO; + if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + data |= ARCH_CAP_SSB_NO; + if (!boot_cpu_has_bug(X86_BUG_MDS)) + data |= ARCH_CAP_MDS_NO; + + /* + * On TAA affected systems, export MDS_NO=0 when: + * - TSX is enabled on the host, i.e. X86_FEATURE_RTM=1. + * - Updated microcode is present. This is detected by + * the presence of ARCH_CAP_TSX_CTRL_MSR and ensures + * that VERW clears CPU buffers. + * + * When MDS_NO=0 is exported, guests deploy clear CPU buffer + * mitigation and don't complain: + * + * "Vulnerable: Clear CPU buffers attempted, no microcode" + * + * If TSX is disabled on the system, guests are also mitigated against + * TAA and clear CPU buffer mitigation is not required for guests. + */ + if (!boot_cpu_has(X86_FEATURE_RTM)) + data &= ~ARCH_CAP_TAA_NO; + else if (!boot_cpu_has_bug(X86_BUG_TAA)) + data |= ARCH_CAP_TAA_NO; + else if (data & ARCH_CAP_TSX_CTRL_MSR) + data &= ~ARCH_CAP_MDS_NO; + + /* KVM does not emulate MSR_IA32_TSX_CTRL. */ + data &= ~ARCH_CAP_TSX_CTRL_MSR; return data; } + EXPORT_SYMBOL_GPL(kvm_get_arch_capabilities); static int kvm_get_msr_feature(struct kvm_msr_entry *msr) @@ -1073,11 +1125,8 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data) return 0; } -bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) +static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) { - if (efer & efer_reserved_bits) - return false; - if (efer & EFER_FFXSR) { struct kvm_cpuid_entry2 *feat; @@ -1095,19 +1144,33 @@ bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) } return true; + +} +bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) +{ + if (efer & efer_reserved_bits) + return false; + + return __kvm_valid_efer(vcpu, efer); } EXPORT_SYMBOL_GPL(kvm_valid_efer); -static int set_efer(struct kvm_vcpu *vcpu, u64 efer) +static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { u64 old_efer = vcpu->arch.efer; + u64 efer = msr_info->data; - if (!kvm_valid_efer(vcpu, efer)) + if (efer & efer_reserved_bits) return 1; - if (is_paging(vcpu) - && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) - return 1; + if (!msr_info->host_initiated) { + if (!__kvm_valid_efer(vcpu, efer)) + return 1; + + if (is_paging(vcpu) && + (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) + return 1; + } efer &= ~EFER_LMA; efer |= vcpu->arch.efer & EFER_LMA; @@ -1354,7 +1417,7 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) vcpu->arch.tsc_always_catchup = 1; return 0; } else { - WARN(1, "user requested TSC rate below hardware speed\n"); + pr_warn_ratelimited("user requested TSC rate below hardware speed\n"); return -1; } } @@ -1364,8 +1427,8 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) user_tsc_khz, tsc_khz); if (ratio == 0 || ratio >= kvm_max_tsc_scaling_ratio) { - WARN_ONCE(1, "Invalid TSC scaling ratio - virtual-tsc-khz=%u\n", - user_tsc_khz); + pr_warn_ratelimited("Invalid TSC scaling ratio - virtual-tsc-khz=%u\n", + user_tsc_khz); return -1; } @@ -2067,7 +2130,10 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data) default: if (msr >= MSR_IA32_MC0_CTL && msr < MSR_IA32_MCx_CTL(bank_num)) { - u32 offset = msr - MSR_IA32_MC0_CTL; + u32 offset = array_index_nospec( + msr - MSR_IA32_MC0_CTL, + MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL); + /* only 0 or all 1s can be written to IA32_MCi_CTL * some Linux kernels though clear bit 10 in bank 4 to * workaround a BIOS/GART TBL issue on AMD K8s, ignore @@ -2197,8 +2263,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (msr_info->host_initiated) vcpu->arch.microcode_version = data; break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated) + return 1; + vcpu->arch.arch_capabilities = data; + break; case MSR_EFER: - return set_efer(vcpu, data); + return set_efer(vcpu, msr_info); case MSR_K7_HWCR: data &= ~(u64)0x40; /* ignore flush filter disable */ data &= ~(u64)0x100; /* ignore ignne emulation enable */ @@ -2430,7 +2501,10 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) default: if (msr >= MSR_IA32_MC0_CTL && msr < MSR_IA32_MCx_CTL(bank_num)) { - u32 offset = msr - MSR_IA32_MC0_CTL; + u32 offset = array_index_nospec( + msr - MSR_IA32_MC0_CTL, + MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL); + data = vcpu->arch.mce_banks[offset]; break; } @@ -2473,6 +2547,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_UCODE_REV: msr_info->data = vcpu->arch.microcode_version; break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated && + !guest_cpuid_has_arch_capabilities(vcpu)) + return 1; + msr_info->data = vcpu->arch.arch_capabilities; + break; case MSR_MTRRcap: case 0x200 ... 0x2ff: return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data); @@ -4598,6 +4678,13 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val, /* kvm_write_guest_virt_system can pull in tons of pages. */ vcpu->arch.l1tf_flush_l1d = true; + /* + * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED + * is returned, but our callers are not ready for that and they blindly + * call kvm_inject_page_fault. Ensure that they at least do not leak + * uninitialized kernel stack memory into cr2 and error code. + */ + memset(exception, 0, sizeof(*exception)); return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, PFERR_WRITE_MASK, exception); } @@ -5735,8 +5822,16 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, emulation_type)) return EMULATE_DONE; - if (ctxt->have_exception && inject_emulated_exception(vcpu)) + if (ctxt->have_exception) { + /* + * #UD should result in just EMULATION_FAILED, and trap-like + * exception should not be encountered during decode. + */ + WARN_ON_ONCE(ctxt->exception.vector == UD_VECTOR || + exception_type(ctxt->exception.vector) == EXCPT_TRAP); + inject_emulated_exception(vcpu); return EMULATE_DONE; + } if (emulation_type & EMULTYPE_SKIP) return EMULATE_FAIL; return handle_emulation_failure(vcpu); @@ -5801,12 +5896,13 @@ restart: unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; - kvm_rip_write(vcpu, ctxt->eip); - if (r == EMULATE_DONE && ctxt->tf) - kvm_vcpu_do_singlestep(vcpu, &r); if (!ctxt->have_exception || - exception_type(ctxt->exception.vector) == EXCPT_TRAP) + exception_type(ctxt->exception.vector) == EXCPT_TRAP) { + kvm_rip_write(vcpu, ctxt->eip); + if (r == EMULATE_DONE && ctxt->tf) + kvm_vcpu_do_singlestep(vcpu, &r); __kvm_set_rflags(vcpu, ctxt->eflags); + } /* * For STI, interrupts are shadowed; so KVM_REQ_EVENT will @@ -5908,17 +6004,17 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1); - spin_lock(&kvm_lock); + mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->cpu != freq->cpu) continue; kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); - if (vcpu->cpu != smp_processor_id()) + if (vcpu->cpu != raw_smp_processor_id()) send_ipi = 1; } } - spin_unlock(&kvm_lock); + mutex_unlock(&kvm_lock); if (freq->old < freq->new && send_ipi) { /* @@ -6036,14 +6132,12 @@ static void kvm_set_mmio_spte_mask(void) /* Set the present bit. */ mask |= 1ull; -#ifdef CONFIG_X86_64 /* * If reserved bit is not supported, clear the present bit to disable * mmio page fault. */ if (maxphyaddr == 52) mask &= ~1ull; -#endif kvm_mmu_set_mmio_spte_mask(mask); } @@ -6056,12 +6150,12 @@ static void pvclock_gtod_update_fn(struct work_struct *work) struct kvm_vcpu *vcpu; int i; - spin_lock(&kvm_lock); + mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) kvm_for_each_vcpu(i, vcpu, kvm) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); atomic_set(&kvm_guest_has_master_clock, 0); - spin_unlock(&kvm_lock); + mutex_unlock(&kvm_lock); } static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn); @@ -7448,7 +7542,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, kvm_update_cpuid(vcpu); idx = srcu_read_lock(&vcpu->kvm->srcu); - if (!is_long_mode(vcpu) && is_pae(vcpu)) { + if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu)) { load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); mmu_reset_needed = 1; } @@ -7672,6 +7766,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { int r; + vcpu->arch.arch_capabilities = kvm_get_arch_capabilities(); kvm_vcpu_mtrr_init(vcpu); r = vcpu_load(vcpu); if (r) @@ -7712,7 +7807,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvm_mmu_unload(vcpu); vcpu_put(vcpu); - kvm_x86_ops->vcpu_free(vcpu); + kvm_arch_vcpu_free(vcpu); } void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) @@ -8028,6 +8123,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); + INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); atomic_set(&kvm->arch.noncoherent_dma_count, 0); @@ -8056,6 +8152,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) return 0; } +int kvm_arch_post_init_vm(struct kvm *kvm) +{ + return kvm_mmu_post_init_vm(kvm); +} + static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) { int r; @@ -8162,6 +8263,11 @@ int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) } EXPORT_SYMBOL_GPL(x86_set_memory_region); +void kvm_arch_pre_destroy_vm(struct kvm *kvm) +{ + kvm_mmu_pre_destroy_vm(kvm); +} + void kvm_arch_destroy_vm(struct kvm *kvm) { if (current->mm == kvm->mm) { @@ -8213,6 +8319,13 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, { int i; + /* + * Clear out the previous array pointers for the KVM_MR_MOVE case. The + * old arrays will be freed by __kvm_set_memory_region() if installing + * the new memslot is successful. + */ + memset(&slot->arch, 0, sizeof(slot->arch)); + for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { struct kvm_lpage_info *linfo; unsigned long ugfn; @@ -8286,6 +8399,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, enum kvm_mr_change change) { + if (change == KVM_MR_MOVE) + return kvm_arch_create_memslot(kvm, memslot, + mem->memory_size >> PAGE_SHIFT); + return 0; } |