diff options
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r-- | arch/x86/kvm/cpuid.c | 9 | ||||
-rw-r--r-- | arch/x86/kvm/emulate.c | 67 | ||||
-rw-r--r-- | arch/x86/kvm/hyperv.c | 10 | ||||
-rw-r--r-- | arch/x86/kvm/i8259.c | 6 | ||||
-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/kvm_cache_regs.h | 2 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 27 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.h | 5 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.c | 157 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.h | 9 | ||||
-rw-r--r-- | arch/x86/kvm/mmutrace.h | 12 | ||||
-rw-r--r-- | arch/x86/kvm/mtrr.c | 8 | ||||
-rw-r--r-- | arch/x86/kvm/paging_tmpl.h | 34 | ||||
-rw-r--r-- | arch/x86/kvm/pmu.h | 18 | ||||
-rw-r--r-- | arch/x86/kvm/svm.c | 101 | ||||
-rw-r--r-- | arch/x86/kvm/trace.h | 19 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/capabilities.h | 6 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/nested.c | 78 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/nested.h | 5 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/pmu_intel.c | 24 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/vmenter.S | 3 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/vmx.c | 368 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/vmx.h | 2 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 330 | ||||
-rw-r--r-- | arch/x86/kvm/x86.h | 2 |
26 files changed, 881 insertions, 438 deletions
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 4992e7c99588..e8e7d053c7b4 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -333,6 +333,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0; unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0; unsigned f_la57 = 0; + unsigned f_pku = kvm_x86_ops->pku_supported() ? F(PKU) : 0; /* cpuid 1.edx */ const u32 kvm_cpuid_1_edx_x86_features = @@ -399,7 +400,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 7.0.ecx*/ const u32 kvm_cpuid_7_0_ecx_x86_features = - F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | + F(AVX512VBMI) | F(LA57) | 0 /*PKU*/ | 0 /*OSPKE*/ | F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B); @@ -415,7 +416,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, r = -E2BIG; - if (*nent >= maxnent) + if (WARN_ON(*nent >= maxnent)) goto out; do_cpuid_1_ent(entry, function, index); @@ -494,6 +495,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* Set LA57 based on hardware capability. */ entry->ecx |= f_la57; entry->ecx |= f_umip; + entry->ecx |= f_pku; /* PKU is not yet implemented for shadow paging. */ if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) entry->ecx &= ~F(PKU); @@ -733,6 +735,9 @@ 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/emulate.c b/arch/x86/kvm/emulate.c index 2fe9912aeed7..5560ac478135 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -22,6 +22,7 @@ #include "kvm_cache_regs.h" #include <asm/kvm_emulate.h> #include <linux/stringify.h> +#include <asm/fpu/api.h> #include <asm/debugreg.h> #include <asm/nospec-branch.h> @@ -1057,8 +1058,23 @@ static void fetch_register_operand(struct operand *op) } } +static void emulator_get_fpu(void) +{ + fpregs_lock(); + + fpregs_assert_state_consistent(); + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + switch_fpu_return(); +} + +static void emulator_put_fpu(void) +{ + fpregs_unlock(); +} + static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg) { + emulator_get_fpu(); switch (reg) { case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break; case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break; @@ -1080,11 +1096,13 @@ static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg) #endif default: BUG(); } + emulator_put_fpu(); } static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg) { + emulator_get_fpu(); switch (reg) { case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break; case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break; @@ -1106,10 +1124,12 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, #endif default: BUG(); } + emulator_put_fpu(); } static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) { + emulator_get_fpu(); switch (reg) { case 0: asm("movq %%mm0, %0" : "=m"(*data)); break; case 1: asm("movq %%mm1, %0" : "=m"(*data)); break; @@ -1121,10 +1141,12 @@ static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) case 7: asm("movq %%mm7, %0" : "=m"(*data)); break; default: BUG(); } + emulator_put_fpu(); } static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) { + emulator_get_fpu(); switch (reg) { case 0: asm("movq %0, %%mm0" : : "m"(*data)); break; case 1: asm("movq %0, %%mm1" : : "m"(*data)); break; @@ -1136,6 +1158,7 @@ static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) case 7: asm("movq %0, %%mm7" : : "m"(*data)); break; default: BUG(); } + emulator_put_fpu(); } static int em_fninit(struct x86_emulate_ctxt *ctxt) @@ -1143,7 +1166,9 @@ static int em_fninit(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); + emulator_get_fpu(); asm volatile("fninit"); + emulator_put_fpu(); return X86EMUL_CONTINUE; } @@ -1154,7 +1179,9 @@ static int em_fnstcw(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); + emulator_get_fpu(); asm volatile("fnstcw %0": "+m"(fcw)); + emulator_put_fpu(); ctxt->dst.val = fcw; @@ -1168,7 +1195,9 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); + emulator_get_fpu(); asm volatile("fnstsw %0": "+m"(fsw)); + emulator_put_fpu(); ctxt->dst.val = fsw; @@ -4076,8 +4105,12 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; + emulator_get_fpu(); + rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state)); + emulator_put_fpu(); + if (rc != X86EMUL_CONTINUE) return rc; @@ -4120,6 +4153,8 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; + emulator_get_fpu(); + if (size < __fxstate_size(16)) { rc = fxregs_fixup(&fx_state, size); if (rc != X86EMUL_CONTINUE) @@ -4135,6 +4170,8 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt) rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state)); out: + emulator_put_fpu(); + return rc; } @@ -5121,6 +5158,7 @@ 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 { @@ -5173,16 +5211,28 @@ 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) @@ -5266,10 +5316,15 @@ 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) @@ -5411,7 +5466,9 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt) { int rc; + emulator_get_fpu(); rc = asm_safe("fwait"); + emulator_put_fpu(); if (unlikely(rc != X86EMUL_CONTINUE)) return emulate_exception(ctxt, MF_VECTOR, 0, false); diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 72200998687c..2d4c1fe5f380 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -808,11 +808,12 @@ 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; } @@ -851,11 +852,12 @@ 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/i8259.c b/arch/x86/kvm/i8259.c index 8b38bb4868a6..629a09ca9860 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -460,10 +460,14 @@ static int picdev_write(struct kvm_pic *s, switch (addr) { case 0x20: case 0x21: + pic_lock(s); + pic_ioport_write(&s->pics[0], addr, data); + pic_unlock(s); + break; case 0xa0: case 0xa1: pic_lock(s); - pic_ioport_write(&s->pics[addr >> 7], addr, data); + pic_ioport_write(&s->pics[1], addr, data); pic_unlock(s); break; case 0x4d0: diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 1add1bc881e2..9446613625e1 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 : @@ -297,6 +299,7 @@ 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 924b3bd5a7b7..e3ab10d6b12e 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -416,7 +416,7 @@ 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/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 1cc6c47dc77e..341f58a01de0 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -7,7 +7,7 @@ #define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS #define KVM_POSSIBLE_CR4_GUEST_BITS \ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ - | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE) + | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE | X86_CR4_TSD) #define BUILD_KVM_GPR_ACCESSORS(lname, uname) \ static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 8d22c79f5333..9483b9da8864 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -59,9 +59,6 @@ #define APIC_VERSION (0x14UL | ((KVM_APIC_LVT_NUM - 1) << 16)) #define LAPIC_MMIO_LENGTH (1 << 12) /* followed define is not in apicdef.h */ -#define APIC_SHORT_MASK 0xc0000 -#define APIC_DEST_NOSHORT 0x0 -#define APIC_DEST_MASK 0x800 #define MAX_APIC_VECTOR 256 #define APIC_VECTORS_PER_REG 32 @@ -635,9 +632,11 @@ 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; } @@ -1063,11 +1062,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, apic_clear_vector(vector, apic->regs + APIC_TMR); } - if (vcpu->arch.apicv_active) - kvm_x86_ops->deliver_posted_interrupt(vcpu, vector); - else { + if (kvm_x86_ops->deliver_posted_interrupt(vcpu, vector)) { kvm_lapic_set_irr(vector, apic); - kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); } @@ -1918,15 +1914,20 @@ 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)) @@ -2086,7 +2087,7 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data) { struct kvm_lapic *apic = vcpu->arch.apic; - if (!lapic_in_kernel(vcpu) || apic_lvtt_oneshot(apic) || + if (!kvm_apic_present(vcpu) || apic_lvtt_oneshot(apic) || apic_lvtt_period(apic)) return; diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index d6d049ba3045..29980b4cc57b 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -10,8 +10,9 @@ #define KVM_APIC_SIPI 1 #define KVM_APIC_LVT_NUM 6 -#define KVM_APIC_SHORT_MASK 0xc0000 -#define KVM_APIC_DEST_MASK 0x800 +#define APIC_SHORT_MASK 0xc0000 +#define APIC_DEST_NOSHORT 0x0 +#define APIC_DEST_MASK 0x800 #define APIC_BUS_CYCLE_NS 1 #define APIC_BUS_FREQUENCY (1000000000ULL / APIC_BUS_CYCLE_NS) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 35348302a6e0..bc5154c57b4e 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -154,11 +154,6 @@ module_param(dbg, bool, 0644); #define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \ | shadow_x_mask | shadow_nx_mask | shadow_me_mask) -#define ACC_EXEC_MASK 1 -#define ACC_WRITE_MASK PT_WRITABLE_MASK -#define ACC_USER_MASK PT_USER_MASK -#define ACC_ALL (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK) - /* The mask for the R/X bits in EPT PTEs */ #define PT64_EPT_READABLE_MASK 0x1ull #define PT64_EPT_EXECUTABLE_MASK 0x4ull @@ -242,6 +237,7 @@ static u64 __read_mostly shadow_accessed_mask; static u64 __read_mostly shadow_dirty_mask; static u64 __read_mostly shadow_mmio_mask; static u64 __read_mostly shadow_mmio_value; +static u64 __read_mostly shadow_mmio_access_mask; static u64 __read_mostly shadow_present_mask; static u64 __read_mostly shadow_me_mask; @@ -284,6 +280,11 @@ static const u64 shadow_nonpresent_or_rsvd_mask_len = 5; */ static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; +/* + * The number of non-reserved physical address bits irrespective of features + * that repurpose legal bits, e.g. MKTME. + */ +u8 __read_mostly shadow_phys_bits; static void mmu_spte_set(u64 *sptep, u64 spte); static union kvm_mmu_page_role @@ -318,11 +319,15 @@ static void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, kvm_flush_remote_tlbs_with_range(kvm, &range); } -void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value) +void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask) { + BUG_ON((u64)(unsigned)access_mask != access_mask); BUG_ON((mmio_mask & mmio_value) != mmio_value); + WARN_ON(mmio_value & (shadow_nonpresent_or_rsvd_mask << shadow_nonpresent_or_rsvd_mask_len)); + WARN_ON(mmio_value & shadow_nonpresent_or_rsvd_lower_gfn_mask); shadow_mmio_value = mmio_value | SPTE_SPECIAL_MASK; shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK; + shadow_mmio_access_mask = access_mask; } EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask); @@ -413,7 +418,7 @@ static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, u64 mask = generation_mmio_spte_mask(gen); u64 gpa = gfn << PAGE_SHIFT; - access &= ACC_WRITE_MASK | ACC_USER_MASK; + access &= shadow_mmio_access_mask; mask |= shadow_mmio_value | access; mask |= gpa | shadow_nonpresent_or_rsvd_mask; mask |= (gpa & shadow_nonpresent_or_rsvd_mask) @@ -440,8 +445,7 @@ static gfn_t get_mmio_spte_gfn(u64 spte) static unsigned get_mmio_spte_access(u64 spte) { - u64 mask = generation_mmio_spte_mask(MMIO_SPTE_GEN_MASK) | shadow_mmio_mask; - return (spte & ~mask) & ~PAGE_MASK; + return spte & shadow_mmio_access_mask; } static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, @@ -496,6 +500,25 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, } EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); +static u8 kvm_get_shadow_phys_bits(void) +{ + /* + * boot_cpu_data.x86_phys_bits is reduced when MKTME or SME are detected + * in CPU detection code, but the processor treats those reduced bits as + * 'keyID' thus they are not reserved bits. Therefore KVM needs to look at + * the physical address bits reported by CPUID. + */ + if (likely(boot_cpu_data.extended_cpuid_level >= 0x80000008)) + return cpuid_eax(0x80000008) & 0xff; + + /* + * Quite weird to have VMX or SVM but not MAXPHYADDR; probably a VM with + * custom CPUID. Proceed with whatever the kernel found since these features + * aren't virtualizable (SME/SEV also require CPUIDs higher than 0x80000008). + */ + return boot_cpu_data.x86_phys_bits; +} + static void kvm_mmu_reset_all_pte_masks(void) { u8 low_phys_bits; @@ -509,6 +532,8 @@ static void kvm_mmu_reset_all_pte_masks(void) shadow_present_mask = 0; shadow_acc_track_mask = 0; + shadow_phys_bits = kvm_get_shadow_phys_bits(); + /* * If the CPU has 46 or less physical address bits, then set an * appropriate mask to guard against L1TF attacks. Otherwise, it is @@ -520,16 +545,15 @@ static void kvm_mmu_reset_all_pte_masks(void) * the most significant bits of legal physical address space. */ shadow_nonpresent_or_rsvd_mask = 0; - low_phys_bits = boot_cpu_data.x86_cache_bits; - if (boot_cpu_data.x86_cache_bits < - 52 - shadow_nonpresent_or_rsvd_mask_len) { + low_phys_bits = boot_cpu_data.x86_phys_bits; + if (boot_cpu_has_bug(X86_BUG_L1TF) && + !WARN_ON_ONCE(boot_cpu_data.x86_cache_bits >= + 52 - shadow_nonpresent_or_rsvd_mask_len)) { + low_phys_bits = boot_cpu_data.x86_cache_bits + - shadow_nonpresent_or_rsvd_mask_len; shadow_nonpresent_or_rsvd_mask = - rsvd_bits(boot_cpu_data.x86_cache_bits - - shadow_nonpresent_or_rsvd_mask_len, - boot_cpu_data.x86_cache_bits - 1); - low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len; - } else - WARN_ON_ONCE(boot_cpu_has_bug(X86_BUG_L1TF)); + rsvd_bits(low_phys_bits, boot_cpu_data.x86_cache_bits - 1); + } shadow_nonpresent_or_rsvd_lower_gfn_mask = GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT); @@ -1220,12 +1244,12 @@ static bool mmu_gfn_lpage_is_disallowed(struct kvm_vcpu *vcpu, gfn_t gfn, return __mmu_gfn_lpage_is_disallowed(gfn, level, slot); } -static int host_mapping_level(struct kvm *kvm, gfn_t gfn) +static int host_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn) { unsigned long page_size; int i, ret = 0; - page_size = kvm_host_page_size(kvm, gfn); + page_size = kvm_host_page_size(vcpu, gfn); for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { if (page_size >= KVM_HPAGE_SIZE(i)) @@ -1275,7 +1299,7 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn, if (unlikely(*force_pt_level)) return PT_PAGE_TABLE_LEVEL; - host_level = host_mapping_level(vcpu->kvm, large_gfn); + host_level = host_mapping_level(vcpu, large_gfn); if (host_level == PT_PAGE_TABLE_LEVEL) return host_level; @@ -1747,10 +1771,10 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, * Emulate arch specific page modification logging for the * nested hypervisor */ -int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu) +int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa) { if (kvm_x86_ops->write_log_dirty) - return kvm_x86_ops->write_log_dirty(vcpu); + return kvm_x86_ops->write_log_dirty(vcpu, l2_gpa); return 0; } @@ -3363,7 +3387,8 @@ static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, } if (unlikely(is_noslot_pfn(pfn))) - vcpu_cache_mmio_info(vcpu, gva, gfn, access); + vcpu_cache_mmio_info(vcpu, gva, gfn, + access & shadow_mmio_access_mask); return false; } @@ -3457,7 +3482,7 @@ static bool is_access_allowed(u32 fault_err_code, u64 spte) * - true: let the vcpu to access on the same address again. * - false: let the real page fault path to fix it. */ -static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, +static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int level, u32 error_code) { struct kvm_shadow_walk_iterator iterator; @@ -3477,7 +3502,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, do { u64 new_spte; - for_each_shadow_entry_lockless(vcpu, gva, iterator, spte) + for_each_shadow_entry_lockless(vcpu, cr2_or_gpa, iterator, spte) if (!is_shadow_present_pte(spte) || iterator.level < level) break; @@ -3555,7 +3580,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, } while (true); - trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep, + trace_fast_page_fault(vcpu, cr2_or_gpa, error_code, iterator.sptep, spte, fault_handled); walk_shadow_page_lockless_end(vcpu); @@ -3563,10 +3588,11 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable); + gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write, + bool *writable); static int make_mmu_pages_available(struct kvm_vcpu *vcpu); -static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, +static int nonpaging_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, gfn_t gfn, bool prefault) { int r; @@ -3592,16 +3618,16 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); } - if (fast_page_fault(vcpu, v, level, error_code)) + if (fast_page_fault(vcpu, gpa, level, error_code)) return RET_PF_RETRY; mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); - if (try_async_pf(vcpu, prefault, gfn, v, &pfn, write, &map_writable)) + if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable)) return RET_PF_RETRY; - if (handle_abnormal_pfn(vcpu, v, gfn, pfn, ACC_ALL, &r)) + if (handle_abnormal_pfn(vcpu, gpa, gfn, pfn, ACC_ALL, &r)) return r; spin_lock(&vcpu->kvm->mmu_lock); @@ -3611,7 +3637,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, goto out_unlock; if (likely(!force_pt_level)) transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); - r = __direct_map(vcpu, v, write, map_writable, level, pfn, + r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, prefault, false); spin_unlock(&vcpu->kvm->mmu_lock); @@ -3912,7 +3938,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots); -static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr, +static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) { if (exception) @@ -3920,7 +3946,7 @@ static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr, return vaddr; } -static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr, +static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) { @@ -4080,13 +4106,14 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr) walk_shadow_page_lockless_end(vcpu); } -static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, +static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, bool prefault) { - gfn_t gfn = gva >> PAGE_SHIFT; + gfn_t gfn = gpa >> PAGE_SHIFT; int r; - pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code); + /* Note, paging is disabled, ergo gva == gpa. */ + pgprintk("%s: gva %lx error %x\n", __func__, gpa, error_code); if (page_fault_handle_page_track(vcpu, error_code, gfn)) return RET_PF_EMULATE; @@ -4098,11 +4125,12 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa)); - return nonpaging_map(vcpu, gva & PAGE_MASK, + return nonpaging_map(vcpu, gpa & PAGE_MASK, error_code, gfn, prefault); } -static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) +static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + gfn_t gfn) { struct kvm_arch_async_pf arch; @@ -4111,7 +4139,8 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) arch.direct_map = vcpu->arch.mmu->direct_map; arch.cr3 = vcpu->arch.mmu->get_cr3(vcpu); - return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); + return kvm_setup_async_pf(vcpu, cr2_or_gpa, + kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); } bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) @@ -4128,7 +4157,8 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable) + gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write, + bool *writable) { struct kvm_memory_slot *slot; bool async; @@ -4148,12 +4178,12 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, return false; /* *pfn has correct page already */ if (!prefault && kvm_can_do_async_pf(vcpu)) { - trace_kvm_try_async_get_page(gva, gfn); + trace_kvm_try_async_get_page(cr2_or_gpa, gfn); if (kvm_find_async_pf_gfn(vcpu, gfn)) { - trace_kvm_async_pf_doublefault(gva, gfn); + trace_kvm_async_pf_doublefault(cr2_or_gpa, gfn); kvm_make_request(KVM_REQ_APF_HALT, vcpu); return true; - } else if (kvm_arch_setup_async_pf(vcpu, gva, gfn)) + } else if (kvm_arch_setup_async_pf(vcpu, cr2_or_gpa, gfn)) return true; } @@ -4166,6 +4196,12 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, { int r = 1; +#ifndef CONFIG_X86_64 + /* A 64-bit CR2 should be impossible on 32-bit KVM. */ + if (WARN_ON_ONCE(fault_address >> 32)) + return -EFAULT; +#endif + vcpu->arch.l1tf_flush_l1d = true; switch (vcpu->arch.apf.host_apf_reason) { default: @@ -4203,7 +4239,7 @@ check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level) return kvm_mtrr_check_gfn_range_consistency(vcpu, gfn, page_num); } -static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, +static int tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, bool prefault) { kvm_pfn_t pfn; @@ -4510,7 +4546,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, nonleaf_bit8_rsvd | rsvd_bits(7, 7) | rsvd_bits(maxphyaddr, 51); rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd | - nonleaf_bit8_rsvd | gbpages_bit_rsvd | + gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51); rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51); @@ -4603,7 +4639,7 @@ reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) */ shadow_zero_check = &context->shadow_zero_check; __reset_rsvds_bits_mask(vcpu, shadow_zero_check, - boot_cpu_data.x86_phys_bits, + shadow_phys_bits, context->shadow_root_level, uses_nx, guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES), is_pse(vcpu), true); @@ -4640,13 +4676,13 @@ reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, if (boot_cpu_is_amd()) __reset_rsvds_bits_mask(vcpu, shadow_zero_check, - boot_cpu_data.x86_phys_bits, + shadow_phys_bits, context->shadow_root_level, false, boot_cpu_has(X86_FEATURE_GBPAGES), true, true); else __reset_rsvds_bits_mask_ept(shadow_zero_check, - boot_cpu_data.x86_phys_bits, + shadow_phys_bits, false); if (!shadow_me_mask) @@ -4667,7 +4703,7 @@ 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, - boot_cpu_data.x86_phys_bits, execonly); + shadow_phys_bits, execonly); } #define BYTE_MASK(access) \ @@ -5462,7 +5498,7 @@ static int make_mmu_pages_available(struct kvm_vcpu *vcpu) return 0; } -int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, +int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len) { int r, emulation_type = 0; @@ -5472,18 +5508,18 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, /* With shadow page tables, fault_address contains a GVA or nGPA. */ if (vcpu->arch.mmu->direct_map) { vcpu->arch.gpa_available = true; - vcpu->arch.gpa_val = cr2; + vcpu->arch.gpa_val = cr2_or_gpa; } r = RET_PF_INVALID; if (unlikely(error_code & PFERR_RSVD_MASK)) { - r = handle_mmio_page_fault(vcpu, cr2, direct); + r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct); if (r == RET_PF_EMULATE) goto emulate; } if (r == RET_PF_INVALID) { - r = vcpu->arch.mmu->page_fault(vcpu, cr2, + r = vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa, lower_32_bits(error_code), false); WARN_ON(r == RET_PF_INVALID); @@ -5503,7 +5539,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, */ if (vcpu->arch.mmu->direct_map && (error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) { - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2)); + kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2_or_gpa)); return 1; } @@ -5518,7 +5554,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, * explicitly shadowing L1's page tables, i.e. unprotecting something * for L1 isn't going to magically fix whatever issue cause L2 to fail. */ - if (!mmio_info_in_cache(vcpu, cr2, direct) && !is_guest_mode(vcpu)) + if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu)) emulation_type = EMULTYPE_ALLOW_RETRY; emulate: /* @@ -5533,7 +5569,7 @@ emulate: return 1; } - er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len); + er = x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn, insn_len); switch (er) { case EMULATE_DONE: @@ -6189,14 +6225,13 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) if (new_val != old_val) { struct kvm *kvm; - int idx; spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { - idx = srcu_read_lock(&kvm->srcu); + mutex_lock(&kvm->slots_lock); kvm_mmu_zap_all_fast(kvm); - srcu_read_unlock(&kvm->srcu, idx); + mutex_unlock(&kvm->slots_lock); wake_up_process(kvm->arch.nx_lpage_recovery_thread); } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 4610230ddaea..b0fefb3ccc87 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -43,6 +43,11 @@ #define PT32_ROOT_LEVEL 2 #define PT32E_ROOT_LEVEL 3 +#define ACC_EXEC_MASK 1 +#define ACC_WRITE_MASK PT_WRITABLE_MASK +#define ACC_USER_MASK PT_USER_MASK +#define ACC_ALL (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK) + static inline u64 rsvd_bits(int s, int e) { if (e < s) @@ -51,7 +56,7 @@ static inline u64 rsvd_bits(int s, int e) return ((1ULL << (e - s + 1)) - 1) << s; } -void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value); +void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask); void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context); @@ -209,7 +214,7 @@ 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_arch_write_log_dirty(struct kvm_vcpu *vcpu); +int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa); int kvm_mmu_post_init_vm(struct kvm *kvm); void kvm_mmu_pre_destroy_vm(struct kvm *kvm); diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index dd30dccd2ad5..c2cabd4c6678 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -246,13 +246,13 @@ TRACE_EVENT( TRACE_EVENT( fast_page_fault, - TP_PROTO(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code, + TP_PROTO(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 error_code, u64 *sptep, u64 old_spte, bool retry), - TP_ARGS(vcpu, gva, error_code, sptep, old_spte, retry), + TP_ARGS(vcpu, cr2_or_gpa, error_code, sptep, old_spte, retry), TP_STRUCT__entry( __field(int, vcpu_id) - __field(gva_t, gva) + __field(gpa_t, cr2_or_gpa) __field(u32, error_code) __field(u64 *, sptep) __field(u64, old_spte) @@ -262,7 +262,7 @@ TRACE_EVENT( TP_fast_assign( __entry->vcpu_id = vcpu->vcpu_id; - __entry->gva = gva; + __entry->cr2_or_gpa = cr2_or_gpa; __entry->error_code = error_code; __entry->sptep = sptep; __entry->old_spte = old_spte; @@ -270,9 +270,9 @@ TRACE_EVENT( __entry->retry = retry; ), - TP_printk("vcpu %d gva %lx error_code %s sptep %p old %#llx" + TP_printk("vcpu %d gva %llx error_code %s sptep %p old %#llx" " new %llx spurious %d fixed %d", __entry->vcpu_id, - __entry->gva, __print_flags(__entry->error_code, "|", + __entry->cr2_or_gpa, __print_flags(__entry->error_code, "|", kvm_mmu_trace_pferr_flags), __entry->sptep, __entry->old_spte, __entry->new_spte, __spte_satisfied(old_spte), __spte_satisfied(new_spte) diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 25ce3edd1872..7f0059aa30e1 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -192,11 +192,15 @@ static bool fixed_msr_to_seg_unit(u32 msr, int *seg, int *unit) break; case MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000: *seg = 1; - *unit = msr - MSR_MTRRfix16K_80000; + *unit = array_index_nospec( + msr - MSR_MTRRfix16K_80000, + MSR_MTRRfix16K_A0000 - MSR_MTRRfix16K_80000 + 1); break; case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000: *seg = 2; - *unit = msr - MSR_MTRRfix4K_C0000; + *unit = array_index_nospec( + msr - MSR_MTRRfix4K_C0000, + MSR_MTRRfix4K_F8000 - MSR_MTRRfix4K_C0000 + 1); break; default: return false; diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 4a906f7111ce..7f64d44735f9 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -33,7 +33,7 @@ #define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT #define PT_HAVE_ACCESSED_DIRTY(mmu) true #ifdef CONFIG_X86_64 - #define PT_MAX_FULL_LEVELS 4 + #define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL #define CMPXCHG cmpxchg #else #define CMPXCHG cmpxchg64 @@ -220,7 +220,7 @@ static inline unsigned FNAME(gpte_access)(u64 gpte) static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, struct guest_walker *walker, - int write_fault) + gpa_t addr, int write_fault) { unsigned level, index; pt_element_t pte, orig_pte; @@ -245,7 +245,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, !(pte & PT_GUEST_DIRTY_MASK)) { trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte)); #if PTTYPE == PTTYPE_EPT - if (kvm_arch_write_log_dirty(vcpu)) + if (kvm_arch_write_log_dirty(vcpu, addr)) return -EINVAL; #endif pte |= PT_GUEST_DIRTY_MASK; @@ -291,11 +291,11 @@ static inline unsigned FNAME(gpte_pkeys)(struct kvm_vcpu *vcpu, u64 gpte) } /* - * Fetch a guest pte for a guest virtual address + * Fetch a guest pte for a guest virtual address, or for an L2's GPA. */ static int FNAME(walk_addr_generic)(struct guest_walker *walker, struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - gva_t addr, u32 access) + gpa_t addr, u32 access) { int ret; pt_element_t pte; @@ -442,7 +442,8 @@ retry_walk: (PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT); if (unlikely(!accessed_dirty)) { - ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault); + ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, + addr, write_fault); if (unlikely(ret < 0)) goto error; else if (ret) @@ -496,7 +497,7 @@ error: } static int FNAME(walk_addr)(struct guest_walker *walker, - struct kvm_vcpu *vcpu, gva_t addr, u32 access) + struct kvm_vcpu *vcpu, gpa_t addr, u32 access) { return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr, access); @@ -610,7 +611,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, * If the guest tries to write a write-protected page, we need to * emulate this operation, return 1 to indicate this case. */ -static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, +static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, struct guest_walker *gw, int write_fault, int hlevel, kvm_pfn_t pfn, bool map_writable, bool prefault, @@ -763,7 +764,7 @@ FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu, * Returns: 1 if we need to emulate the instruction, 0 otherwise, or * a negative value on error. */ -static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, +static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, bool prefault) { int write_fault = error_code & PFERR_WRITE_MASK; @@ -945,18 +946,19 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) spin_unlock(&vcpu->kvm->mmu_lock); } -static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access, +/* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */ +static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t addr, u32 access, struct x86_exception *exception) { struct guest_walker walker; gpa_t gpa = UNMAPPED_GVA; int r; - r = FNAME(walk_addr)(&walker, vcpu, vaddr, access); + r = FNAME(walk_addr)(&walker, vcpu, addr, access); if (r) { gpa = gfn_to_gpa(walker.gfn); - gpa |= vaddr & ~PAGE_MASK; + gpa |= addr & ~PAGE_MASK; } else if (exception) *exception = walker.fault; @@ -964,7 +966,8 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access, } #if PTTYPE != PTTYPE_EPT -static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr, +/* Note, gva_to_gpa_nested() is only used to translate L2 GVAs. */ +static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) { @@ -972,6 +975,11 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr, gpa_t gpa = UNMAPPED_GVA; int r; +#ifndef CONFIG_X86_64 + /* A 64-bit GVA should be impossible on 32-bit KVM. */ + WARN_ON_ONCE(vaddr >> 32); +#endif + r = FNAME(walk_addr_nested)(&walker, vcpu, vaddr, access); if (r) { diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 22dff661145a..7b4828e50ab3 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -2,6 +2,8 @@ #ifndef __KVM_X86_PMU_H #define __KVM_X86_PMU_H +#include <linux/nospec.h> + #define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu) #define pmu_to_vcpu(pmu) (container_of((pmu), struct kvm_vcpu, arch.pmu)) #define pmc_to_pmu(pmc) (&(pmc)->vcpu->arch.pmu) @@ -86,8 +88,12 @@ static inline bool pmc_is_enabled(struct kvm_pmc *pmc) static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr, u32 base) { - if (msr >= base && msr < base + pmu->nr_arch_gp_counters) - return &pmu->gp_counters[msr - base]; + if (msr >= base && msr < base + pmu->nr_arch_gp_counters) { + u32 index = array_index_nospec(msr - base, + pmu->nr_arch_gp_counters); + + return &pmu->gp_counters[index]; + } return NULL; } @@ -97,8 +103,12 @@ 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/svm.c b/arch/x86/kvm/svm.c index 68f63d9684a6..bf0d805e75c9 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -996,33 +996,32 @@ static void svm_cpu_uninit(int cpu) static int svm_cpu_init(int cpu) { struct svm_cpu_data *sd; - int r; sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL); if (!sd) return -ENOMEM; sd->cpu = cpu; - r = -ENOMEM; sd->save_area = alloc_page(GFP_KERNEL); if (!sd->save_area) - goto err_1; + goto free_cpu_data; if (svm_sev_enabled()) { - r = -ENOMEM; sd->sev_vmcbs = kmalloc_array(max_sev_asid + 1, sizeof(void *), GFP_KERNEL); if (!sd->sev_vmcbs) - goto err_1; + goto free_save_area; } per_cpu(svm_data, cpu) = sd; return 0; -err_1: +free_save_area: + __free_page(sd->save_area); +free_cpu_data: kfree(sd); - return r; + return -ENOMEM; } @@ -1296,6 +1295,47 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu) control->pause_filter_count, old); } +/* + * The default MMIO mask is a single bit (excluding the present bit), + * which could conflict with the memory encryption bit. Check for + * memory encryption support and override the default MMIO mask if + * memory encryption is enabled. + */ +static __init void svm_adjust_mmio_mask(void) +{ + unsigned int enc_bit, mask_bit; + u64 msr, mask; + + /* If there is no memory encryption support, use existing mask */ + if (cpuid_eax(0x80000000) < 0x8000001f) + return; + + /* If memory encryption is not enabled, use existing mask */ + rdmsrl(MSR_K8_SYSCFG, msr); + if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) + return; + + enc_bit = cpuid_ebx(0x8000001f) & 0x3f; + mask_bit = boot_cpu_data.x86_phys_bits; + + /* Increment the mask bit if it is the same as the encryption bit */ + if (enc_bit == mask_bit) + mask_bit++; + + /* + * If the mask bit location is below 52, then some bits above the + * physical addressing limit will always be reserved, so use the + * rsvd_bits() function to generate the mask. This mask, along with + * the present bit, will be used to generate a page fault with + * PFER.RSV = 1. + * + * If the mask bit location is 52 (or above), then clear the mask. + */ + mask = (mask_bit < 52) ? rsvd_bits(mask_bit, 51) | PT_PRESENT_MASK : 0; + + kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK); +} + static __init int svm_hardware_setup(void) { int cpu; @@ -1350,6 +1390,8 @@ static __init int svm_hardware_setup(void) } } + svm_adjust_mmio_mask(); + for_each_possible_cpu(cpu) { r = svm_cpu_init(cpu); if (r) @@ -1811,7 +1853,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, return NULL; /* Pin the user virtual address. */ - npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages); + npinned = get_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages); if (npinned != npages) { pr_err("SEV: Failure locking %lu pages.\n", npages); goto err; @@ -1876,6 +1918,10 @@ static struct kvm *svm_vm_alloc(void) struct kvm_svm *kvm_svm = __vmalloc(sizeof(struct kvm_svm), GFP_KERNEL_ACCOUNT | __GFP_ZERO, PAGE_KERNEL); + + if (!kvm_svm) + return NULL; + return &kvm_svm->kvm; } @@ -2140,12 +2186,20 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) goto out; } + svm->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, + GFP_KERNEL_ACCOUNT); + if (!svm->vcpu.arch.user_fpu) { + printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n"); + err = -ENOMEM; + goto free_partial_svm; + } + svm->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, GFP_KERNEL_ACCOUNT); if (!svm->vcpu.arch.guest_fpu) { printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n"); err = -ENOMEM; - goto free_partial_svm; + goto free_user_fpu; } err = kvm_vcpu_init(&svm->vcpu, kvm, id); @@ -2208,6 +2262,8 @@ uninit: kvm_vcpu_uninit(&svm->vcpu); free_svm: kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu); +free_user_fpu: + kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu); free_partial_svm: kmem_cache_free(kvm_vcpu_cache, svm); out: @@ -2238,6 +2294,7 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) __free_page(virt_to_page(svm->nested.hsave)); __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); kvm_vcpu_uninit(vcpu); + kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu); kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu); kmem_cache_free(kvm_vcpu_cache, svm); } @@ -3171,8 +3228,8 @@ static int nested_svm_exit_special(struct vcpu_svm *svm) return NESTED_EXIT_HOST; break; case SVM_EXIT_EXCP_BASE + PF_VECTOR: - /* When we're shadowing, trap PFs, but not async PF */ - if (!npt_enabled && svm->vcpu.arch.apf.host_apf_reason == 0) + /* Trap async PF even if not shadowing */ + if (!npt_enabled || svm->vcpu.arch.apf.host_apf_reason) return NESTED_EXIT_HOST; break; default: @@ -3261,7 +3318,7 @@ static inline void copy_vmcb_control_area(struct vmcb *dst_vmcb, struct vmcb *fr 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; + /* 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; @@ -4537,9 +4594,9 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm) */ kvm_for_each_vcpu(i, vcpu, kvm) { bool m = kvm_apic_match_dest(vcpu, apic, - icrl & KVM_APIC_SHORT_MASK, + icrl & APIC_SHORT_MASK, GET_APIC_DEST_FIELD(icrh), - icrl & KVM_APIC_DEST_MASK); + icrl & APIC_DEST_MASK); if (m && !avic_vcpu_is_running(vcpu)) kvm_vcpu_wake_up(vcpu); @@ -5161,8 +5218,11 @@ static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) return; } -static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) +static int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) { + if (!vcpu->arch.apicv_active) + return -1; + kvm_lapic_set_irr(vec, vcpu->arch.apic); smp_mb__after_atomic(); @@ -5171,6 +5231,8 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) kvm_cpu_get_apicid(vcpu->cpu)); else kvm_vcpu_wake_up(vcpu); + + return 0; } static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) @@ -5905,6 +5967,9 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && + boot_cpu_has(X86_FEATURE_XSAVES); + /* Update nrips enabled cache */ svm->nrips_enabled = !!guest_cpuid_has(&svm->vcpu, X86_FEATURE_NRIPS); @@ -5991,6 +6056,11 @@ static bool svm_has_wbinvd_exit(void) return true; } +static bool svm_pku_supported(void) +{ + return false; +} + #define PRE_EX(exit) { .exit_code = (exit), \ .stage = X86_ICPT_PRE_EXCEPT, } #define POST_EX(exit) { .exit_code = (exit), \ @@ -7280,6 +7350,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .xsaves_supported = svm_xsaves_supported, .umip_emulated = svm_umip_emulated, .pt_supported = svm_pt_supported, + .pku_supported = svm_pku_supported, .set_supported_cpuid = svm_set_supported_cpuid, diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 4d47a2631d1f..e11689b876d7 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -1462,6 +1462,25 @@ TRACE_EVENT(kvm_hv_send_ipi_ex, __entry->vector, __entry->format, __entry->valid_bank_mask) ); + +TRACE_EVENT(kvm_pv_tlb_flush, + TP_PROTO(unsigned int vcpu_id, bool need_flush_tlb), + TP_ARGS(vcpu_id, need_flush_tlb), + + TP_STRUCT__entry( + __field( unsigned int, vcpu_id ) + __field( bool, need_flush_tlb ) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->need_flush_tlb = need_flush_tlb; + ), + + TP_printk("vcpu %u need_flush_tlb %s", __entry->vcpu_id, + __entry->need_flush_tlb ? "true" : "false") +); + #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index d6664ee3d127..7cd3f8683b8c 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -12,6 +12,7 @@ extern bool __read_mostly enable_ept; extern bool __read_mostly enable_unrestricted_guest; extern bool __read_mostly enable_ept_ad_bits; extern bool __read_mostly enable_pml; +extern bool __read_mostly enable_apicv; extern int __read_mostly pt_mode; #define PT_MODE_SYSTEM 0 @@ -145,6 +146,11 @@ static inline bool vmx_umip_emulated(void) SECONDARY_EXEC_DESC; } +static inline bool vmx_pku_supported(void) +{ + return boot_cpu_has(X86_FEATURE_PKU); +} + static inline bool cpu_has_vmx_rdtscp(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 22437ad335b0..c6deeed854f1 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2384,6 +2384,16 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, entry_failure_code)) return -EINVAL; + /* + * Immediately write vmcs02.GUEST_CR3. It will be propagated to vmcs12 + * on nested VM-Exit, which can occur without actually running L2 and + * thus without hitting vmx_set_cr3(), e.g. if L1 is entering L2 with + * vmcs12.GUEST_ACTIVITYSTATE=HLT, in which case KVM will intercept the + * transition to HLT instead of running L2. + */ + if (enable_ept) + vmcs_writel(GUEST_CR3, vmcs12->guest_cr3); + if (!enable_ept) vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested; @@ -3357,7 +3367,7 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu, nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual); } -static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) +static int vmx_check_nested_events(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long exit_qual; @@ -3395,8 +3405,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) return 0; } - if ((kvm_cpu_has_interrupt(vcpu) || external_intr) && - nested_exit_on_intr(vcpu)) { + if (kvm_cpu_has_interrupt(vcpu) && nested_exit_on_intr(vcpu)) { if (block_nested_events) return -EBUSY; nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0); @@ -3970,17 +3979,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; if (likely(!vmx->fail)) { - /* - * TODO: SDM says that with acknowledge interrupt on - * exit, bit 31 of the VM-exit interrupt information - * (valid interrupt) is always set to 1 on - * EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't - * need kvm_cpu_has_interrupt(). See the commit - * message for details. - */ - if (nested_exit_intr_ack_set(vcpu) && - exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && - kvm_cpu_has_interrupt(vcpu)) { + if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && + nested_exit_intr_ack_set(vcpu)) { int irq = kvm_cpu_get_interrupt(vcpu); WARN_ON(irq < 0); vmcs12->vm_exit_intr_info = irq | @@ -4452,8 +4452,10 @@ static int handle_vmread(struct kvm_vcpu *vcpu) vmx_instruction_info, true, len, &gva)) return 1; /* _system ok, nested_vmx_check_permission has verified cpl=0 */ - if (kvm_write_guest_virt_system(vcpu, gva, &field_value, len, &e)) + if (kvm_write_guest_virt_system(vcpu, gva, &field_value, len, &e)) { kvm_inject_page_fault(vcpu, &e); + return 1; + } } return nested_vmx_succeed(vcpu); @@ -4882,24 +4884,17 @@ fail: return 1; } - -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; @@ -4926,6 +4921,24 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, return false; } +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); +} + /* * Return 1 if we should exit from L2 to L1 to handle an MSR access access, * rather than handle it ourselves in L0. I.e., check whether L1 expressed @@ -5112,7 +5125,7 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) vmcs_read32(VM_EXIT_INTR_ERROR_CODE), KVM_ISA_VMX); - switch (exit_reason) { + switch ((u16)exit_reason) { case EXIT_REASON_EXCEPTION_NMI: if (is_nmi(intr_info)) return false; @@ -5546,8 +5559,7 @@ void nested_vmx_vcpu_setup(void) * bit in the high half is on if the corresponding bit in the control field * may be on. See also vmx_control_verify(). */ -void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, - bool apicv) +void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) { /* * Note that as a general rule, the high half of the MSRs (bits in @@ -5574,7 +5586,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING | PIN_BASED_VIRTUAL_NMIS | - (apicv ? PIN_BASED_POSTED_INTR : 0); + (enable_apicv ? PIN_BASED_POSTED_INTR : 0); msrs->pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | PIN_BASED_VMX_PREEMPTION_TIMER; diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index 29d205bb4e4f..161c305de3f3 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -7,8 +7,7 @@ #include "vmx.h" void vmx_leave_nested(struct kvm_vcpu *vcpu); -void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, - bool apicv); +void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps); void nested_vmx_hardware_unsetup(void); __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)); void nested_vmx_vcpu_setup(void); @@ -22,6 +21,8 @@ int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata); int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, u32 vmx_instruction_info, bool wr, int len, gva_t *ret); +bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, + int size); static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) { diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 68d231d49c7a..cb3d9872a88d 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -84,10 +84,14 @@ 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. */ @@ -128,16 +132,20 @@ 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; *mask &= pmu->counter_bitmask[fixed ? KVM_PMC_FIXED : KVM_PMC_GP]; - - return &counters[idx]; + return &counters[array_index_nospec(idx, num_counters)]; } static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index d4cb1945b2e3..f83368b5af87 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -86,6 +86,9 @@ ENTRY(vmx_vmexit) /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + /* Clear RFLAGS.CF and RFLAGS.ZF to preserve VM-Exit, i.e. !VM-Fail. */ + or $1, %_ASM_AX + pop %_ASM_AX .Lvmexit_skip_rsb: #endif diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index ea5040117fbb..b177e25e3786 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -95,7 +95,7 @@ module_param(emulate_invalid_guest_state, bool, S_IRUGO); static bool __read_mostly fasteoi = 1; module_param(fasteoi, bool, S_IRUGO); -static bool __read_mostly enable_apicv = 1; +bool __read_mostly enable_apicv = 1; module_param(enable_apicv, bool, S_IRUGO); /* @@ -402,6 +402,7 @@ const u32 vmx_msr_index[] = { MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, #endif MSR_EFER, MSR_TSC_AUX, MSR_STAR, + MSR_IA32_TSX_CTRL, }; #if IS_ENABLED(CONFIG_HYPERV) @@ -565,6 +566,23 @@ struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) return NULL; } +static int vmx_set_guest_msr(struct vcpu_vmx *vmx, struct shared_msr_entry *msr, u64 data) +{ + int ret = 0; + + u64 old_msr_data = msr->data; + msr->data = data; + if (msr - vmx->guest_msrs < vmx->save_nmsrs) { + preempt_disable(); + ret = kvm_set_shared_msr(msr->index, msr->data, + msr->mask); + preempt_enable(); + if (ret) + msr->data = old_msr_data; + } + return ret; +} + void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs) { vmcs_clear(loaded_vmcs->vmcs); @@ -575,43 +593,15 @@ void loaded_vmcs_init(struct loaded_vmcs *loaded_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) @@ -623,19 +613,24 @@ 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; } void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) @@ -1229,18 +1224,17 @@ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (!already_loaded) { loaded_vmcs_clear(vmx->loaded_vmcs); 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(); } @@ -1284,7 +1278,6 @@ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) decache_tsc_multiplier(vmx); vmx_vcpu_pi_load(vcpu, cpu); - vmx->host_pkru = read_pkru(); vmx->host_debugctlmsr = get_debugctlmsr(); } @@ -1569,6 +1562,9 @@ static void setup_msrs(struct vcpu_vmx *vmx) index = __find_msr_index(vmx, MSR_TSC_AUX); if (index >= 0 && guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP)) move_msr_up(vmx, index, save_nmsrs++); + index = __find_msr_index(vmx, MSR_IA32_TSX_CTRL); + if (index >= 0) + move_msr_up(vmx, index, save_nmsrs++); vmx->save_nmsrs = save_nmsrs; vmx->guest_msrs_dirty = true; @@ -1668,6 +1664,11 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) #endif case MSR_EFER: return kvm_get_msr_common(vcpu, msr_info); + case MSR_IA32_TSX_CTRL: + if (!msr_info->host_initiated && + !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR)) + return 1; + goto find_shared_msr; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) @@ -1710,10 +1711,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, &msr_info->data); case MSR_IA32_XSS: - if (!vmx_xsaves_supported() || - (!msr_info->host_initiated && - !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)))) + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) return 1; msr_info->data = vcpu->arch.ia32_xss; break; @@ -1767,8 +1766,9 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) return 1; - /* Else, falls through */ + goto find_shared_msr; default: + find_shared_msr: msr = find_msr_entry(vmx, msr_info->index); if (msr) { msr_info->data = msr->data; @@ -1863,6 +1863,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) MSR_IA32_SPEC_CTRL, MSR_TYPE_RW); break; + case MSR_IA32_TSX_CTRL: + if (!msr_info->host_initiated && + !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR)) + return 1; + if (data & ~(TSX_CTRL_RTM_DISABLE | TSX_CTRL_CPUID_CLEAR)) + return 1; + goto find_shared_msr; case MSR_IA32_PRED_CMD: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) @@ -1928,10 +1935,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; return vmx_set_vmx_msr(vcpu, msr_index, data); case MSR_IA32_XSS: - if (!vmx_xsaves_supported() || - (!msr_info->host_initiated && - !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)))) + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) return 1; /* * The only supported bit as of Skylake is bit 8, but @@ -1940,11 +1945,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data != 0) return 1; vcpu->arch.ia32_xss = data; - if (vcpu->arch.ia32_xss != host_xss) - add_atomic_switch_msr(vmx, MSR_IA32_XSS, - vcpu->arch.ia32_xss, host_xss, false); - else - clear_atomic_switch_msr(vmx, MSR_IA32_XSS); + if (vcpu->arch.xsaves_enabled) { + if (vcpu->arch.ia32_xss != host_xss) + add_atomic_switch_msr(vmx, MSR_IA32_XSS, + vcpu->arch.ia32_xss, host_xss, false); + else + clear_atomic_switch_msr(vmx, MSR_IA32_XSS); + } break; case MSR_IA32_RTIT_CTL: if ((pt_mode != PT_MODE_HOST_GUEST) || @@ -1998,6 +2005,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) (index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_num_address_ranges))) return 1; + if (is_noncanonical_address(data, vcpu)) + return 1; if (index % 2) vmx->pt_desc.guest.addr_b[index / 2] = data; else @@ -2010,23 +2019,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) /* Check reserved bit, higher 32 bits should be zero */ if ((data >> 32) != 0) return 1; - /* Else, falls through */ + goto find_shared_msr; + default: + find_shared_msr: msr = find_msr_entry(vmx, msr_index); - if (msr) { - u64 old_msr_data = msr->data; - msr->data = data; - if (msr - vmx->guest_msrs < vmx->save_nmsrs) { - preempt_disable(); - ret = kvm_set_shared_msr(msr->index, msr->data, - msr->mask); - preempt_enable(); - if (ret) - msr->data = old_msr_data; - } - break; - } - ret = kvm_set_msr_common(vcpu, msr_info); + if (msr) + ret = vmx_set_guest_msr(vmx, msr, data); + else + ret = kvm_set_msr_common(vcpu, msr_info); } return ret; @@ -2108,21 +2109,6 @@ static int hardware_enable(void) !hv_get_vp_assist_page(cpu)) return -EFAULT; - 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; @@ -2829,6 +2815,9 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) static int get_ept_level(struct kvm_vcpu *vcpu) { + /* Nested EPT currently only supports 4-level walks. */ + if (is_guest_mode(vcpu) && nested_cpu_has_ept(get_vmcs12(vcpu))) + return 4; if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48)) return 5; return 4; @@ -2851,6 +2840,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa) void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { struct kvm *kvm = vcpu->kvm; + bool update_guest_cr3 = true; unsigned long guest_cr3; u64 eptp; @@ -2867,15 +2857,17 @@ void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock); } - if (enable_unrestricted_guest || is_paging(vcpu) || - is_guest_mode(vcpu)) - guest_cr3 = kvm_read_cr3(vcpu); - else + if (!enable_unrestricted_guest && !is_paging(vcpu)) guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr; + else if (test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) + guest_cr3 = vcpu->arch.cr3; + else /* vmcs01.GUEST_CR3 is already up-to-date. */ + update_guest_cr3 = false; ept_load_pdptrs(vcpu); } - vmcs_writel(GUEST_CR3, guest_cr3); + if (update_guest_cr3) + vmcs_writel(GUEST_CR3, guest_cr3); } int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) @@ -3700,24 +3692,29 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, * 2. If target vcpu isn't running(root mode), kick it to pick up the * interrupt from PIR in next vmentry. */ -static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) +static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) { struct vcpu_vmx *vmx = to_vmx(vcpu); int r; r = vmx_deliver_nested_posted_interrupt(vcpu, vector); if (!r) - return; + return 0; + + if (!vcpu->arch.apicv_active) + return -1; if (pi_test_and_set_pir(vector, &vmx->pi_desc)) - return; + return 0; /* If a previous notification has sent the IPI, nothing to do. */ if (pi_test_and_set_on(&vmx->pi_desc)) - return; + return 0; if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false)) kvm_vcpu_kick(vcpu); + + return 0; } /* @@ -3788,6 +3785,8 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) { + BUILD_BUG_ON(KVM_CR4_GUEST_OWNED_BITS & ~KVM_POSSIBLE_CR4_GUEST_BITS); + vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS; if (enable_ept) vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE; @@ -3904,6 +3903,8 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && guest_cpuid_has(vcpu, X86_FEATURE_XSAVES); + vcpu->arch.xsaves_enabled = xsaves_enabled; + if (!xsaves_enabled) exec_control &= ~SECONDARY_EXEC_XSAVES; @@ -3993,7 +3994,7 @@ static void ept_set_mmio_spte_mask(void) * of an EPT paging-structure entry is 110b (write/execute). */ kvm_mmu_set_mmio_spte_mask(VMX_EPT_RWX_MASK, - VMX_EPT_MISCONFIG_WX_VALUE); + VMX_EPT_MISCONFIG_WX_VALUE, 0); } #define VMX_XSS_EXIT_BITMAP 0 @@ -4076,7 +4077,20 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) continue; vmx->guest_msrs[j].index = i; vmx->guest_msrs[j].data = 0; - vmx->guest_msrs[j].mask = -1ull; + + switch (index) { + case MSR_IA32_TSX_CTRL: + /* + * No need to pass TSX_CTRL_CPUID_CLEAR through, so + * let's avoid changing CPUID bits under the host + * kernel's feet. + */ + vmx->guest_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; + break; + default: + vmx->guest_msrs[j].mask = -1ull; + break; + } ++vmx->nmsrs; } @@ -4334,8 +4348,13 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) { - return (!to_vmx(vcpu)->nested.nested_run_pending && - vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && + if (to_vmx(vcpu)->nested.nested_run_pending) + return false; + + if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) + return true; + + return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); } @@ -4429,7 +4448,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, */ static void kvm_machine_check(void) { -#if defined(CONFIG_X86_MCE) && defined(CONFIG_X86_64) +#if defined(CONFIG_X86_MCE) struct pt_regs regs = { .cs = 3, /* Fake ring 3 no matter what the guest ran on */ .flags = X86_EFLAGS_IF, @@ -6090,7 +6109,11 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) { - return pi_test_on(vcpu_to_pi_desc(vcpu)); + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + + return pi_test_on(pi_desc) || + (pi_test_sn(pi_desc) && + !bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS)); } static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) @@ -6429,11 +6452,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) kvm_load_guest_xcr0(vcpu); - if (static_cpu_has(X86_FEATURE_PKU) && - kvm_read_cr4_bits(vcpu, X86_CR4_PKE) && - vcpu->arch.pkru != vmx->host_pkru) - __write_pkru(vcpu->arch.pkru); - pt_guest_enter(vmx); atomic_switch_perf_msrs(vmx); @@ -6513,18 +6531,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) pt_guest_exit(vmx); - /* - * eager fpu is enabled if PKEY is supported and CR4 is switched - * back on host, so it is safe to read guest PKRU from current - * XSAVE. - */ - if (static_cpu_has(X86_FEATURE_PKU) && - kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) { - vcpu->arch.pkru = rdpkru(); - if (vcpu->arch.pkru != vmx->host_pkru) - __write_pkru(vmx->host_pkru); - } - kvm_put_guest_xcr0(vcpu); vmx->nested.nested_run_pending = 0; @@ -6550,6 +6556,10 @@ static struct kvm *vmx_vm_alloc(void) struct kvm_vmx *kvm_vmx = __vmalloc(sizeof(struct kvm_vmx), GFP_KERNEL_ACCOUNT | __GFP_ZERO, PAGE_KERNEL); + + if (!kvm_vmx) + return NULL; + return &kvm_vmx->kvm; } @@ -6569,6 +6579,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) free_loaded_vmcs(vmx->loaded_vmcs); kfree(vmx->guest_msrs); kvm_vcpu_uninit(vcpu); + kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); kmem_cache_free(kvm_vcpu_cache, vmx); } @@ -6584,12 +6595,20 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (!vmx) return ERR_PTR(-ENOMEM); + vmx->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, + GFP_KERNEL_ACCOUNT); + if (!vmx->vcpu.arch.user_fpu) { + printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n"); + err = -ENOMEM; + goto free_partial_vcpu; + } + vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, GFP_KERNEL_ACCOUNT); if (!vmx->vcpu.arch.guest_fpu) { printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n"); err = -ENOMEM; - goto free_partial_vcpu; + goto free_user_fpu; } vmx->vpid = allocate_vpid(); @@ -6654,8 +6673,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (nested) nested_vmx_setup_ctls_msrs(&vmx->nested.msrs, - vmx_capability.ept, - kvm_vcpu_apicv_active(&vmx->vcpu)); + vmx_capability.ept); else memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs)); @@ -6686,6 +6704,8 @@ uninit_vcpu: free_vcpu: free_vpid(vmx->vpid); kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); +free_user_fpu: + kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); free_partial_vcpu: kmem_cache_free(kvm_vcpu_cache, vmx); return ERR_PTR(err); @@ -6736,8 +6756,7 @@ static void __init vmx_check_processor_compat(void *rtn) if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) *(int *)rtn = -EIO; if (nested) - nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept, - enable_apicv); + nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept); if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) { printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n", smp_processor_id()); @@ -6949,6 +6968,9 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + /* xsaves_enabled is recomputed in vmx_compute_secondary_exec_control(). */ + vcpu->arch.xsaves_enabled = false; + if (cpu_has_secondary_exec_ctrls()) { vmx_compute_secondary_exec_control(vmx); vmcs_set_secondary_exec_control(vmx->secondary_exec_control); @@ -6969,6 +6991,15 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) if (boot_cpu_has(X86_FEATURE_INTEL_PT) && guest_cpuid_has(vcpu, X86_FEATURE_INTEL_PT)) update_intel_pt_cfg(vcpu); + + if (boot_cpu_has(X86_FEATURE_RTM)) { + struct shared_msr_entry *msr; + msr = find_msr_entry(vmx, MSR_IA32_TSX_CTRL); + if (msr) { + bool enabled = guest_cpuid_has(vcpu, X86_FEATURE_RTM); + vmx_set_guest_msr(vmx, msr, enabled ? 0 : TSX_CTRL_RTM_DISABLE); + } + } } static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) @@ -6982,6 +7013,40 @@ static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) to_vmx(vcpu)->req_immediate_exit = 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); + + /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ + 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) @@ -6989,19 +7054,45 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, 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. */ - if (info->intercept == x86_intercept_rdtscp && - !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) { - ctxt->exception.vector = UD_VECTOR; - ctxt->exception.error_code_valid = false; - return X86EMUL_PROPAGATE_FAULT; - } + 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); + + case x86_intercept_lgdt: + case x86_intercept_lidt: + case x86_intercept_lldt: + case x86_intercept_ltr: + case x86_intercept_sgdt: + case x86_intercept_sidt: + case x86_intercept_sldt: + case x86_intercept_str: + if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC)) + return X86EMUL_CONTINUE; + + /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ + break; /* TODO: check more intercepts... */ - return X86EMUL_CONTINUE; + default: + break; + } + + return X86EMUL_UNHANDLEABLE; } #ifdef CONFIG_X86_64 @@ -7096,11 +7187,11 @@ static void vmx_flush_log_dirty(struct kvm *kvm) kvm_flush_pml_buffers(kvm); } -static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu) +static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa) { struct vmcs12 *vmcs12; struct vcpu_vmx *vmx = to_vmx(vcpu); - gpa_t gpa, dst; + gpa_t dst; if (is_guest_mode(vcpu)) { WARN_ON_ONCE(vmx->nested.pml_full); @@ -7119,7 +7210,7 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu) return 1; } - gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull; + gpa &= ~0xFFFull; dst = vmcs12->pml_address + sizeof(u64) * vmcs12->guest_pml_index; if (kvm_write_guest_page(vcpu->kvm, gpa_to_gfn(dst), &gpa, @@ -7560,7 +7651,7 @@ static __init int hardware_setup(void) if (nested) { nested_vmx_setup_ctls_msrs(&vmcs_config.nested, - vmx_capability.ept, enable_apicv); + vmx_capability.ept); r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers); if (r) @@ -7694,6 +7785,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .xsaves_supported = vmx_xsaves_supported, .umip_emulated = vmx_umip_emulated, .pt_supported = vmx_pt_supported, + .pku_supported = vmx_pku_supported, .request_immediate_exit = vmx_request_immediate_exit, @@ -7780,7 +7872,7 @@ module_exit(vmx_exit); static int __init vmx_init(void) { - int r; + int r, cpu; #if IS_ENABLED(CONFIG_HYPERV) /* @@ -7831,6 +7923,12 @@ 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/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 61128b48c503..6935eff28122 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -256,8 +256,6 @@ struct vcpu_vmx { u64 current_tsc_ratio; - u32 host_pkru; - unsigned long host_debugctlmsr; u64 msr_ia32_power_ctl; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cfd880ab841d..df6f6df902c6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -90,6 +90,8 @@ u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA)); static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #endif +static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; + #define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ #define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ @@ -295,13 +297,14 @@ 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); @@ -437,6 +440,14 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu) * for #DB exceptions under VMX. */ vcpu->arch.dr6 ^= payload & DR6_RTM; + + /* + * The #DB payload is defined as compatible with the 'pending + * debug exceptions' field under VMX, not DR6. While bit 12 is + * defined in the 'pending debug exceptions' field (enabled + * breakpoint), it is reserved and must be zero in DR6. + */ + vcpu->arch.dr6 &= ~BIT(12); break; case PF_VECTOR: vcpu->arch.cr2 = payload; @@ -816,11 +827,25 @@ void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); vcpu->guest_xcr0_loaded = 1; } + + if (static_cpu_has(X86_FEATURE_PKU) && + (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) || + (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU)) && + vcpu->arch.pkru != vcpu->arch.host_pkru) + __write_pkru(vcpu->arch.pkru); } EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0); void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) { + if (static_cpu_has(X86_FEATURE_PKU) && + (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) || + (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU))) { + vcpu->arch.pkru = rdpkru(); + if (vcpu->arch.pkru != vcpu->arch.host_pkru) + __write_pkru(vcpu->arch.host_pkru); + } + if (vcpu->guest_xcr0_loaded) { if (vcpu->arch.xcr0 != host_xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0); @@ -880,9 +905,38 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) } EXPORT_SYMBOL_GPL(kvm_set_xcr); +static u64 kvm_host_cr4_reserved_bits(struct cpuinfo_x86 *c) +{ + u64 reserved_bits = CR4_RESERVED_BITS; + + if (!cpu_has(c, X86_FEATURE_XSAVE)) + reserved_bits |= X86_CR4_OSXSAVE; + + if (!cpu_has(c, X86_FEATURE_SMEP)) + reserved_bits |= X86_CR4_SMEP; + + if (!cpu_has(c, X86_FEATURE_SMAP)) + reserved_bits |= X86_CR4_SMAP; + + if (!cpu_has(c, X86_FEATURE_FSGSBASE)) + reserved_bits |= X86_CR4_FSGSBASE; + + if (!cpu_has(c, X86_FEATURE_PKU)) + reserved_bits |= X86_CR4_PKE; + + if (!cpu_has(c, X86_FEATURE_LA57) && + !(cpuid_ecx(0x7) & bit(X86_FEATURE_LA57))) + reserved_bits |= X86_CR4_LA57; + + if (!cpu_has(c, X86_FEATURE_UMIP) && !kvm_x86_ops->umip_emulated()) + reserved_bits |= X86_CR4_UMIP; + + return reserved_bits; +} + static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { - if (cr4 & CR4_RESERVED_BITS) + if (cr4 & cr4_reserved_bits) return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE)) @@ -921,6 +975,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (is_long_mode(vcpu)) { if (!(cr4 & X86_CR4_PAE)) return 1; + 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, @@ -1048,9 +1104,11 @@ 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; @@ -1087,9 +1145,11 @@ 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 */ @@ -1250,27 +1310,18 @@ u64 kvm_get_arch_capabilities(void) data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH; /* - * 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. + * On TAA affected systems: + * - nothing to do if TSX is disabled on the host. + * - we emulate TSX_CTRL if present on the host. + * This lets the guest use VERW to clear CPU buffers. */ - if (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM) && - (data & ARCH_CAP_TSX_CTRL_MSR)) - data &= ~ARCH_CAP_MDS_NO; + if (!boot_cpu_has(X86_FEATURE_RTM)) + data &= ~(ARCH_CAP_TAA_NO | ARCH_CAP_TSX_CTRL_MSR); + else if (!boot_cpu_has_bug(X86_BUG_TAA)) + data |= ARCH_CAP_TAA_NO; return data; } -EXPORT_SYMBOL_GPL(kvm_get_arch_capabilities); static int kvm_get_msr_feature(struct kvm_msr_entry *msr) { @@ -2372,7 +2423,10 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info) default: if (msr >= MSR_IA32_MC0_CTL && msr < MSR_IA32_MCx_CTL(bank_num)) { - u32 offset = msr - MSR_IA32_MC0_CTL; + u32 offset = array_index_nospec( + msr - MSR_IA32_MC0_CTL, + MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL); + /* only 0 or all 1s can be written to IA32_MCi_CTL * some Linux kernels though clear bit 10 in bank 4 to * workaround a BIOS/GART TBL issue on AMD K8s, ignore @@ -2467,43 +2521,47 @@ static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) static void record_steal_time(struct kvm_vcpu *vcpu) { + struct kvm_host_map map; + struct kvm_steal_time *st; + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)))) + /* -EAGAIN is returned in atomic context so we can just return. */ + if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, + &map, &vcpu->arch.st.cache, false)) return; + st = map.hva + + offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); + /* * Doing a TLB flush here, on the guest's behalf, can avoid * expensive IPIs. */ - if (xchg(&vcpu->arch.st.steal.preempted, 0) & KVM_VCPU_FLUSH_TLB) + trace_kvm_pv_tlb_flush(vcpu->vcpu_id, + st->preempted & KVM_VCPU_FLUSH_TLB); + if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB) kvm_vcpu_flush_tlb(vcpu, false); - if (vcpu->arch.st.steal.version & 1) - vcpu->arch.st.steal.version += 1; /* first time write, random junk */ + vcpu->arch.st.preempted = 0; - vcpu->arch.st.steal.version += 1; + if (st->version & 1) + st->version += 1; /* first time write, random junk */ - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); + st->version += 1; smp_wmb(); - vcpu->arch.st.steal.steal += current->sched_info.run_delay - + st->steal += current->sched_info.run_delay - vcpu->arch.st.last_steal; vcpu->arch.st.last_steal = current->sched_info.run_delay; - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); - smp_wmb(); - vcpu->arch.st.steal.version += 1; + st->version += 1; - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); + kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, false); } int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) @@ -2570,7 +2628,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return kvm_mtrr_set_msr(vcpu, msr, data); case MSR_IA32_APICBASE: return kvm_set_apic_base(vcpu, msr_info); - case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_write(vcpu, msr, data); case MSR_IA32_TSCDEADLINE: kvm_set_lapic_tscdeadline_msr(vcpu, data); @@ -2648,11 +2706,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & KVM_STEAL_RESERVED_MASK) return 1; - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime, - data & KVM_STEAL_VALID_BITS, - sizeof(struct kvm_steal_time))) - return 1; - vcpu->arch.st.msr_val = data; if (!(data & KVM_MSR_ENABLED)) @@ -2792,7 +2845,10 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) default: if (msr >= MSR_IA32_MC0_CTL && msr < MSR_IA32_MCx_CTL(bank_num)) { - u32 offset = msr - MSR_IA32_MC0_CTL; + u32 offset = array_index_nospec( + msr - MSR_IA32_MC0_CTL, + MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL); + data = vcpu->arch.mce_banks[offset]; break; } @@ -2869,7 +2925,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_APICBASE: msr_info->data = kvm_get_apic_base(vcpu); break; - case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data); break; case MSR_IA32_TSCDEADLINE: @@ -3305,9 +3361,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_x86_ops->vcpu_load(vcpu, cpu); - fpregs_assert_state_consistent(); - if (test_thread_flag(TIF_NEED_FPU_LOAD)) - switch_fpu_return(); + /* Save host pkru register if supported */ + vcpu->arch.host_pkru = read_pkru(); /* Apply any externally detected TSC adjustments (due to suspend) */ if (unlikely(vcpu->arch.tsc_offset_adjustment)) { @@ -3348,15 +3403,25 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) { + struct kvm_host_map map; + struct kvm_steal_time *st; + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - vcpu->arch.st.steal.preempted = KVM_VCPU_PREEMPTED; + if (vcpu->arch.st.preempted) + return; - kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime, - &vcpu->arch.st.steal.preempted, - offsetof(struct kvm_steal_time, preempted), - sizeof(vcpu->arch.st.steal.preempted)); + if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map, + &vcpu->arch.st.cache, true)) + return; + + st = map.hva + + offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); + + st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; + + kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -3492,7 +3557,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, unsigned bank_num = mcg_cap & 0xff, bank; r = -EINVAL; - if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS) + if (!bank_num || bank_num > KVM_MAX_MCE_BANKS) goto out; if (mcg_cap & ~(kvm_mce_cap_supported | 0xff | 0xff0000)) goto out; @@ -4285,6 +4350,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, case KVM_SET_NESTED_STATE: { struct kvm_nested_state __user *user_kvm_nested_state = argp; struct kvm_nested_state kvm_state; + int idx; r = -EINVAL; if (!kvm_x86_ops->set_nested_state) @@ -4308,7 +4374,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, && !(kvm_state.flags & KVM_STATE_NESTED_GUEST_MODE)) break; + idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } case KVM_GET_SUPPORTED_HV_CPUID: { @@ -6214,11 +6282,11 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) return r; } -static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, +static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, bool write_fault_to_shadow_pgtable, int emulation_type) { - gpa_t gpa = cr2; + gpa_t gpa = cr2_or_gpa; kvm_pfn_t pfn; if (!(emulation_type & EMULTYPE_ALLOW_RETRY)) @@ -6232,7 +6300,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, * Write permission should be allowed since only * write access need to be emulated. */ - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); /* * If the mapping is invalid in guest, let cpu retry @@ -6289,10 +6357,10 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, } static bool retry_instruction(struct x86_emulate_ctxt *ctxt, - unsigned long cr2, int emulation_type) + gpa_t cr2_or_gpa, int emulation_type) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - unsigned long last_retry_eip, last_retry_addr, gpa = cr2; + unsigned long last_retry_eip, last_retry_addr, gpa = cr2_or_gpa; last_retry_eip = vcpu->arch.last_retry_eip; last_retry_addr = vcpu->arch.last_retry_addr; @@ -6321,14 +6389,14 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, if (x86_page_table_writing_insn(ctxt)) return false; - if (ctxt->eip == last_retry_eip && last_retry_addr == cr2) + if (ctxt->eip == last_retry_eip && last_retry_addr == cr2_or_gpa) return false; vcpu->arch.last_retry_eip = ctxt->eip; - vcpu->arch.last_retry_addr = cr2; + vcpu->arch.last_retry_addr = cr2_or_gpa; if (!vcpu->arch.mmu->direct_map) - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); @@ -6472,11 +6540,8 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt) return false; } -int x86_emulate_instruction(struct kvm_vcpu *vcpu, - unsigned long cr2, - int emulation_type, - void *insn, - int insn_len) +int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + int emulation_type, void *insn, int insn_len) { int r; struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; @@ -6519,8 +6584,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, if (r != EMULATION_OK) { if (emulation_type & EMULTYPE_TRAP_UD) return EMULATE_FAIL; - if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, - emulation_type)) + if (reexecute_instruction(vcpu, cr2_or_gpa, + write_fault_to_spt, + emulation_type)) return EMULATE_DONE; if (ctxt->have_exception) { /* @@ -6549,7 +6615,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, return EMULATE_DONE; } - if (retry_instruction(ctxt, cr2, emulation_type)) + if (retry_instruction(ctxt, cr2_or_gpa, emulation_type)) return EMULATE_DONE; /* this is needed for vmware backdoor interface to work since it @@ -6561,7 +6627,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, restart: /* Save the faulting GPA (cr2) in the address field */ - ctxt->exception.address = cr2; + ctxt->exception.address = cr2_or_gpa; r = x86_emulate_insn(ctxt); @@ -6569,7 +6635,7 @@ restart: return EMULATE_DONE; if (r == EMULATION_FAILED) { - if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, + if (reexecute_instruction(vcpu, cr2_or_gpa, write_fault_to_spt, emulation_type)) return EMULATE_DONE; @@ -6606,7 +6672,7 @@ restart: if (!ctxt->have_exception || exception_type(ctxt->exception.vector) == EXCPT_TRAP) { kvm_rip_write(vcpu, ctxt->eip); - if (r == EMULATE_DONE && ctxt->tf) + if (r == EMULATE_DONE && (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) kvm_vcpu_do_singlestep(vcpu, &r); __kvm_set_rflags(vcpu, ctxt->eflags); } @@ -6968,33 +7034,25 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = { .handle_intel_pt_intr = kvm_handle_intel_pt_intr, }; +extern u8 __read_mostly shadow_phys_bits; + static void kvm_set_mmio_spte_mask(void) { u64 mask; - int maxphyaddr = boot_cpu_data.x86_phys_bits; - - /* - * Set the reserved bits and the present bit of an paging-structure - * entry to generate page fault with PFER.RSV = 1. - */ /* - * Mask the uppermost physical address bit, which would be reserved as - * long as the supported physical address width is less than 52. + * Set a reserved PA bit in MMIO SPTEs to generate page faults with + * PFEC.RSVD=1 on MMIO accesses. 64-bit PTEs (PAE, x86-64, and EPT + * paging) support a maximum of 52 bits of PA, i.e. if the CPU supports + * 52-bit physical addresses then there are no reserved PA bits in the + * PTEs and so the reserved PA approach must be disabled. */ - mask = 1ull << 51; - - /* Set the present bit. */ - mask |= 1ull; - - /* - * If reserved bit is not supported, clear the present bit to disable - * mmio page fault. - */ - if (IS_ENABLED(CONFIG_X86_64) && maxphyaddr == 52) - mask &= ~1ull; + if (shadow_phys_bits < 52) + mask = BIT_ULL(51) | PT_PRESENT_MASK; + else + mask = 0; - kvm_mmu_set_mmio_spte_mask(mask, mask); + kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK); } #ifdef CONFIG_X86_64 @@ -7350,7 +7408,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr); } -static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) +static int inject_pending_event(struct kvm_vcpu *vcpu) { int r; @@ -7386,7 +7444,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) * from L2 to L1. */ if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) { - r = kvm_x86_ops->check_nested_events(vcpu, req_int_win); + r = kvm_x86_ops->check_nested_events(vcpu); if (r != 0) return r; } @@ -7448,7 +7506,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) * KVM_REQ_EVENT only on certain events and not unconditionally? */ if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) { - r = kvm_x86_ops->check_nested_events(vcpu, req_int_win); + r = kvm_x86_ops->check_nested_events(vcpu); if (r != 0) return r; } @@ -7759,9 +7817,8 @@ static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu) kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap); } -int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, - unsigned long start, unsigned long end, - bool blockable) +void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, + unsigned long start, unsigned long end) { unsigned long apic_address; @@ -7772,8 +7829,6 @@ int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, apic_address = gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); if (start <= apic_address && apic_address < end) kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); - - return 0; } void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) @@ -7921,7 +7976,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto out; } - if (inject_pending_event(vcpu, req_int_win) != 0) + if (inject_pending_event(vcpu) != 0) req_immediate_exit = true; else { /* Enable SMI/NMI/IRQ window open exits if needed. @@ -8016,8 +8071,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) wait_lapic_expire(vcpu); guest_enter_irqoff(); - /* The preempt notifier should have taken care of the FPU already. */ - WARN_ON_ONCE(test_thread_flag(TIF_NEED_FPU_LOAD)); + fpregs_assert_state_consistent(); + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + switch_fpu_return(); if (unlikely(vcpu->arch.switch_db_regs)) { set_debugreg(0, 7); @@ -8137,7 +8193,7 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) - kvm_x86_ops->check_nested_events(vcpu, false); + kvm_x86_ops->check_nested_events(vcpu); return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && !vcpu->arch.apf.halted); @@ -8274,12 +8330,26 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) return 0; } +static void kvm_save_current_fpu(struct fpu *fpu) +{ + /* + * If the target FPU state is not resident in the CPU registers, just + * memcpy() from current, else save CPU state directly to the target. + */ + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + memcpy(&fpu->state, ¤t->thread.fpu.state, + fpu_kernel_xstate_size); + else + copy_fpregs_to_fpstate(fpu); +} + /* Swap (qemu) user FPU context for the guest FPU context. */ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) { fpregs_lock(); - copy_fpregs_to_fpstate(&vcpu->arch.user_fpu); + kvm_save_current_fpu(vcpu->arch.user_fpu); + /* PKRU is separately restored in kvm_x86_ops->run. */ __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state, ~XFEATURE_MASK_PKRU); @@ -8295,8 +8365,9 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { fpregs_lock(); - copy_fpregs_to_fpstate(vcpu->arch.guest_fpu); - copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state); + kvm_save_current_fpu(vcpu->arch.guest_fpu); + + copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state); fpregs_mark_activate(); fpregs_unlock(); @@ -8517,6 +8588,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { vcpu_load(vcpu); + if (kvm_mpx_supported()) + kvm_load_guest_fpu(vcpu); kvm_apic_accept_events(vcpu); if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED && @@ -8525,6 +8598,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, else mp_state->mp_state = vcpu->arch.mp_state; + if (kvm_mpx_supported()) + kvm_put_guest_fpu(vcpu); vcpu_put(vcpu); return 0; } @@ -8881,6 +8956,9 @@ static void fx_init(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) { void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask; + struct gfn_to_pfn_cache *cache = &vcpu->arch.st.cache; + + kvm_release_pfn(cache->pfn, cache->dirty, cache); kvmclock_reset(vcpu); @@ -8941,13 +9019,7 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { - vcpu->arch.apf.msr_val = 0; - - vcpu_load(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) @@ -9139,6 +9211,8 @@ int kvm_arch_hardware_setup(void) if (r != 0) return r; + cr4_reserved_bits = kvm_host_cr4_reserved_bits(&boot_cpu_data); + if (kvm_has_tsc_control) { /* * Make sure the user can only configure tsc_khz values that @@ -9480,6 +9554,13 @@ 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; @@ -9542,11 +9623,18 @@ out_free: void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { + struct kvm_vcpu *vcpu; + int i; + /* * memslots->generation has been incremented. * mmio generation may have reached its maximum value. */ kvm_mmu_invalidate_mmio_sptes(kvm, gen); + + /* Force re-initialization of steal_time cache */ + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_vcpu_kick(vcpu); } int kvm_arch_prepare_memory_region(struct kvm *kvm, @@ -9554,6 +9642,10 @@ 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; } @@ -9793,7 +9885,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu)) return; - vcpu->arch.mmu->page_fault(vcpu, work->gva, 0, true); + vcpu->arch.mmu->page_fault(vcpu, work->cr2_or_gpa, 0, true); } static inline u32 kvm_async_pf_hash_fn(gfn_t gfn) @@ -9876,7 +9968,7 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, { struct x86_exception fault; - trace_kvm_async_pf_not_present(work->arch.token, work->gva); + trace_kvm_async_pf_not_present(work->arch.token, work->cr2_or_gpa); kvm_add_async_pf_gfn(vcpu, work->arch.gfn); if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) || @@ -9904,7 +9996,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, work->arch.token = ~0; /* broadcast wakeup */ else kvm_del_async_pf_gfn(vcpu, work->arch.gfn); - trace_kvm_async_pf_ready(work->arch.token, work->gva); + trace_kvm_async_pf_ready(work->arch.token, work->cr2_or_gpa); if (vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED && !apf_get_user(vcpu, &val)) { diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index a470ff0868c5..8c0b13cc3c6a 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -281,7 +281,7 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int page_num); bool kvm_vector_hashing_enabled(void); -int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, +int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type, void *insn, int insn_len); #define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ |