diff options
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r-- | arch/x86/kvm/Makefile | 2 | ||||
-rw-r--r-- | arch/x86/kvm/cpuid.c | 6 | ||||
-rw-r--r-- | arch/x86/kvm/emulate.c | 133 | ||||
-rw-r--r-- | arch/x86/kvm/hyperv.c | 20 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 17 | ||||
-rw-r--r-- | arch/x86/kvm/pmu.c | 2 | ||||
-rw-r--r-- | arch/x86/kvm/pmu_amd.c | 8 | ||||
-rw-r--r-- | arch/x86/kvm/svm.c | 13 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/pmu_intel.c (renamed from arch/x86/kvm/pmu_intel.c) | 0 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/vmx.c (renamed from arch/x86/kvm/vmx.c) | 209 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/vmx_evmcs.h (renamed from arch/x86/kvm/vmx_evmcs.h) | 0 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/vmx_shadow_fields.h (renamed from arch/x86/kvm/vmx_shadow_fields.h) | 0 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 18 |
13 files changed, 327 insertions, 101 deletions
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index dc4f2fdf5e57..13fd54de5449 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -16,7 +16,7 @@ kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ hyperv.o page_track.o debugfs.o -kvm-intel-y += vmx.o pmu_intel.o +kvm-intel-y += vmx/vmx.o vmx/pmu_intel.o kvm-amd-y += svm.o pmu_amd.o obj-$(CONFIG_KVM) += kvm.o diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 097eef712cdc..768a765c49b0 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -532,6 +532,11 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, union cpuid10_eax eax; union cpuid10_edx edx; + if (!static_cpu_has(X86_FEATURE_ARCH_PERFMON)) { + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; + break; + } + perf_get_x86_pmu_capability(&cap); /* @@ -675,6 +680,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); + entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8)); entry->edx = 0; /* * IBRS, IBPB and VIRT_SSBD aren't necessarily present in diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 3e182c7ae771..0cb75d29e67b 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -759,8 +759,7 @@ static int linearize(struct x86_emulate_ctxt *ctxt, ctxt->mode, linear); } -static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst, - enum x86emul_mode mode) +static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst) { ulong linear; int rc; @@ -770,41 +769,71 @@ static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst, if (ctxt->op_bytes != sizeof(unsigned long)) addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1); - rc = __linearize(ctxt, addr, &max_size, 1, false, true, mode, &linear); + rc = __linearize(ctxt, addr, &max_size, 1, false, true, ctxt->mode, &linear); if (rc == X86EMUL_CONTINUE) ctxt->_eip = addr.ea; return rc; } +static inline int emulator_recalc_and_set_mode(struct x86_emulate_ctxt *ctxt) +{ + u64 efer; + struct desc_struct cs; + u16 selector; + u32 base3; + + ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); + + if (!(ctxt->ops->get_cr(ctxt, 0) & X86_CR0_PE)) { + /* Real mode. cpu must not have long mode active */ + if (efer & EFER_LMA) + return X86EMUL_UNHANDLEABLE; + ctxt->mode = X86EMUL_MODE_REAL; + return X86EMUL_CONTINUE; + } + + if (ctxt->eflags & X86_EFLAGS_VM) { + /* Protected/VM86 mode. cpu must not have long mode active */ + if (efer & EFER_LMA) + return X86EMUL_UNHANDLEABLE; + ctxt->mode = X86EMUL_MODE_VM86; + return X86EMUL_CONTINUE; + } + + if (!ctxt->ops->get_segment(ctxt, &selector, &cs, &base3, VCPU_SREG_CS)) + return X86EMUL_UNHANDLEABLE; + + if (efer & EFER_LMA) { + if (cs.l) { + /* Proper long mode */ + ctxt->mode = X86EMUL_MODE_PROT64; + } else if (cs.d) { + /* 32 bit compatibility mode*/ + ctxt->mode = X86EMUL_MODE_PROT32; + } else { + ctxt->mode = X86EMUL_MODE_PROT16; + } + } else { + /* Legacy 32 bit / 16 bit mode */ + ctxt->mode = cs.d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; + } + + return X86EMUL_CONTINUE; +} + static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst) { - return assign_eip(ctxt, dst, ctxt->mode); + return assign_eip(ctxt, dst); } -static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst, - const struct desc_struct *cs_desc) +static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst) { - enum x86emul_mode mode = ctxt->mode; - int rc; + int rc = emulator_recalc_and_set_mode(ctxt); -#ifdef CONFIG_X86_64 - if (ctxt->mode >= X86EMUL_MODE_PROT16) { - if (cs_desc->l) { - u64 efer = 0; + if (rc != X86EMUL_CONTINUE) + return rc; - ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); - if (efer & EFER_LMA) - mode = X86EMUL_MODE_PROT64; - } else - mode = X86EMUL_MODE_PROT32; /* temporary value */ - } -#endif - if (mode == X86EMUL_MODE_PROT16 || mode == X86EMUL_MODE_PROT32) - mode = cs_desc->d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - rc = assign_eip(ctxt, dst, mode); - if (rc == X86EMUL_CONTINUE) - ctxt->mode = mode; - return rc; + return assign_eip(ctxt, dst); } static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) @@ -1669,11 +1698,6 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, goto exception; } - if (!seg_desc.p) { - err_vec = (seg == VCPU_SREG_SS) ? SS_VECTOR : NP_VECTOR; - goto exception; - } - dpl = seg_desc.dpl; switch (seg) { @@ -1713,12 +1737,6 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, case VCPU_SREG_TR: if (seg_desc.s || (seg_desc.type != 1 && seg_desc.type != 9)) goto exception; - old_desc = seg_desc; - seg_desc.type |= 2; /* busy */ - ret = ctxt->ops->cmpxchg_emulated(ctxt, desc_addr, &old_desc, &seg_desc, - sizeof(seg_desc), &ctxt->exception); - if (ret != X86EMUL_CONTINUE) - return ret; break; case VCPU_SREG_LDTR: if (seg_desc.s || seg_desc.type != 2) @@ -1737,6 +1755,11 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, break; } + if (!seg_desc.p) { + err_vec = (seg == VCPU_SREG_SS) ? SS_VECTOR : NP_VECTOR; + goto exception; + } + if (seg_desc.s) { /* mark segment as accessed */ if (!(seg_desc.type & 1)) { @@ -1751,8 +1774,17 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, if (ret != X86EMUL_CONTINUE) return ret; if (emul_is_noncanonical_address(get_desc_base(&seg_desc) | - ((u64)base3 << 32), ctxt)) - return emulate_gp(ctxt, 0); + ((u64)base3 << 32), ctxt)) + return emulate_gp(ctxt, err_code); + } + + if (seg == VCPU_SREG_TR) { + old_desc = seg_desc; + seg_desc.type |= 2; /* busy */ + ret = ctxt->ops->cmpxchg_emulated(ctxt, desc_addr, &old_desc, &seg_desc, + sizeof(seg_desc), &ctxt->exception); + if (ret != X86EMUL_CONTINUE) + return ret; } load: ctxt->ops->set_segment(ctxt, selector, &seg_desc, base3, seg); @@ -1972,7 +2004,7 @@ static int em_pop_sreg(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - if (ctxt->modrm_reg == VCPU_SREG_SS) + if (seg == VCPU_SREG_SS) ctxt->interruptibility = KVM_X86_SHADOW_INT_MOV_SS; if (ctxt->op_bytes > 2) rsp_increment(ctxt, ctxt->op_bytes - 2); @@ -2189,7 +2221,7 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc); + rc = assign_eip_far(ctxt, ctxt->src.val); /* Error handling is not implemented. */ if (rc != X86EMUL_CONTINUE) return X86EMUL_UNHANDLEABLE; @@ -2270,7 +2302,7 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) &new_desc); if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, eip, &new_desc); + rc = assign_eip_far(ctxt, eip); /* Error handling is not implemented. */ if (rc != X86EMUL_CONTINUE) return X86EMUL_UNHANDLEABLE; @@ -2892,6 +2924,7 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); ctxt->_eip = rdx; + ctxt->mode = usermode; *reg_write(ctxt, VCPU_REGS_RSP) = rcx; return X86EMUL_CONTINUE; @@ -3488,7 +3521,7 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc); + rc = assign_eip_far(ctxt, ctxt->src.val); if (rc != X86EMUL_CONTINUE) goto fail; @@ -3635,11 +3668,25 @@ static int em_movbe(struct x86_emulate_ctxt *ctxt) static int em_cr_write(struct x86_emulate_ctxt *ctxt) { - if (ctxt->ops->set_cr(ctxt, ctxt->modrm_reg, ctxt->src.val)) + int cr_num = ctxt->modrm_reg; + int r; + + if (ctxt->ops->set_cr(ctxt, cr_num, ctxt->src.val)) return emulate_gp(ctxt, 0); /* Disable writeback. */ ctxt->dst.type = OP_NONE; + + if (cr_num == 0) { + /* + * CR0 write might have updated CR0.PE and/or CR0.PG + * which can affect the cpu's execution mode. + */ + r = emulator_recalc_and_set_mode(ctxt); + if (r != X86EMUL_CONTINUE) + return r; + } + return X86EMUL_CONTINUE; } diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 3fd6c4b2c2b7..2047edb5ff74 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -237,7 +237,7 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, struct kvm_vcpu *vcpu = synic_to_vcpu(synic); int ret; - if (!synic->active && !host) + if (!synic->active && (!host || data)) return 1; trace_kvm_hv_synic_set_msr(vcpu->vcpu_id, msr, data, host); @@ -283,6 +283,9 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, case HV_X64_MSR_EOM: { int i; + if (!synic->active) + break; + for (i = 0; i < ARRAY_SIZE(synic->sint); i++) kvm_hv_notify_acked_sint(vcpu, i); break; @@ -338,6 +341,9 @@ static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint) struct kvm_lapic_irq irq; int ret, vector; + if (KVM_BUG_ON(!lapic_in_kernel(vcpu), vcpu->kvm)) + return -EINVAL; + if (sint >= ARRAY_SIZE(synic->sint)) return -EINVAL; @@ -544,6 +550,12 @@ static int stimer_start(struct kvm_vcpu_hv_stimer *stimer) static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config, bool host) { + struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer); + struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu); + + if (!synic->active && (!host || config)) + return 1; + trace_kvm_hv_stimer_set_config(stimer_to_vcpu(stimer)->vcpu_id, stimer->index, config, host); @@ -558,6 +570,12 @@ static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config, static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count, bool host) { + struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer); + struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu); + + if (!synic->active && (!host || count)) + return 1; + trace_kvm_hv_stimer_set_count(stimer_to_vcpu(stimer)->vcpu_id, stimer->index, count, host); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 56a4b9762b0c..256b00f456e6 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -961,6 +961,10 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, *r = -1; if (irq->shorthand == APIC_DEST_SELF) { + if (KVM_BUG_ON(!src, kvm)) { + *r = 0; + return true; + } *r = kvm_apic_set_irq(src->vcpu, irq, dest_map); return true; } @@ -2045,10 +2049,7 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data) void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8) { - struct kvm_lapic *apic = vcpu->arch.apic; - - apic_set_tpr(apic, ((cr8 & 0x0f) << 4) - | (kvm_lapic_get_reg(apic, APIC_TASKPRI) & 4)); + apic_set_tpr(vcpu->arch.apic, (cr8 & 0x0f) << 4); } u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu) @@ -2200,13 +2201,17 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) { u32 reg = kvm_lapic_get_reg(apic, lvt_type); int vector, mode, trig_mode; + int r; if (kvm_apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) { vector = reg & APIC_VECTOR_MASK; mode = reg & APIC_MODE_MASK; trig_mode = reg & APIC_LVT_LEVEL_TRIGGER; - return __apic_accept_irq(apic, mode, vector, 1, trig_mode, - NULL); + + r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL); + if (r && lvt_type == APIC_LVTPC) + kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED); + return r; } return 0; } diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index acc8d217f656..ad3d39c00d7f 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -171,7 +171,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) } if (type == PERF_TYPE_RAW) - config = eventsel & X86_RAW_EVENT_MASK; + config = eventsel & AMD64_RAW_EVENT_MASK; pmc_reprogram_counter(pmc, type, config, !(eventsel & ARCH_PERFMON_EVENTSEL_USR), diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c index 41dff881e0f0..93a135f216b2 100644 --- a/arch/x86/kvm/pmu_amd.c +++ b/arch/x86/kvm/pmu_amd.c @@ -247,12 +247,10 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) /* MSR_EVNTSELn */ pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL); if (pmc) { - if (data == pmc->eventsel) - return 0; - if (!(data & pmu->reserved_bits)) { + data &= ~pmu->reserved_bits; + if (data != pmc->eventsel) reprogram_gp_counter(pmc, data); - return 0; - } + return 0; } return 1; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 85181457413e..cd3432df0d24 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -50,6 +50,7 @@ #include <asm/kvm_para.h> #include <asm/irq_remapping.h> #include <asm/spec-ctrl.h> +#include <asm/cpu_device_id.h> #include <asm/virtext.h> #include "trace.h" @@ -4154,9 +4155,9 @@ static int svm_get_msr_feature(struct kvm_msr_entry *msr) msr->data = 0; switch (msr->index) { - case MSR_F10H_DECFG: - if (boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) - msr->data |= MSR_F10H_DECFG_LFENCE_SERIALIZE; + case MSR_AMD64_DE_CFG: + if (cpu_feature_enabled(X86_FEATURE_LFENCE_RDTSC)) + msr->data |= MSR_AMD64_DE_CFG_LFENCE_SERIALIZE; break; default: return 1; @@ -4258,7 +4259,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 0x1E; } break; - case MSR_F10H_DECFG: + case MSR_AMD64_DE_CFG: msr_info->data = svm->msr_decfg; break; default: @@ -4445,7 +4446,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_VM_IGNNE: vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); break; - case MSR_F10H_DECFG: { + case MSR_AMD64_DE_CFG: { struct kvm_msr_entry msr_entry; msr_entry.index = msr->index; @@ -5142,8 +5143,6 @@ static void svm_set_irq(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - BUG_ON(!(gif_set(svm))); - trace_kvm_inj_virq(vcpu->arch.interrupt.nr); ++vcpu->stat.irq_injections; diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 611f9e60f815..611f9e60f815 100644 --- a/arch/x86/kvm/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx/vmx.c index 77b9ed5223f3..55e52064c4ec 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -41,6 +41,7 @@ #include <asm/asm.h> #include <asm/cpu.h> +#include <asm/cpu_device_id.h> #include <asm/io.h> #include <asm/desc.h> #include <asm/vmx.h> @@ -212,6 +213,9 @@ static const struct { #define L1D_CACHE_ORDER 4 static void *vmx_l1d_flush_pages; +/* Control for disabling CPU Fill buffer clear */ +static bool __read_mostly vmx_fb_clear_ctrl_available; + static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) { struct page *page; @@ -1045,6 +1049,8 @@ struct vcpu_vmx { u64 msr_ia32_feature_control; u64 msr_ia32_feature_control_valid_bits; u64 ept_pointer; + u64 msr_ia32_mcu_opt_ctrl; + bool disable_fb_clear; }; enum segment_cache_field { @@ -2056,6 +2062,12 @@ static inline bool nested_cpu_has_shadow_vmcs(struct vmcs12 *vmcs12) return nested_cpu_has2(vmcs12, SECONDARY_EXEC_SHADOW_VMCS); } +static inline bool nested_cpu_has_save_preemption_timer(struct vmcs12 *vmcs12) +{ + return vmcs12->vm_exit_controls & + VM_EXIT_SAVE_VMX_PREEMPTION_TIMER; +} + static inline bool is_nmi(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) @@ -2107,6 +2119,60 @@ static inline void __invept(unsigned long ext, u64 eptp, gpa_t gpa) BUG_ON(error); } +static void vmx_setup_fb_clear_ctrl(void) +{ + u64 msr; + + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES) && + !boot_cpu_has_bug(X86_BUG_MDS) && + !boot_cpu_has_bug(X86_BUG_TAA)) { + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr); + if (msr & ARCH_CAP_FB_CLEAR_CTRL) + vmx_fb_clear_ctrl_available = true; + } +} + +static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx) +{ + u64 msr; + + if (!vmx->disable_fb_clear) + return; + + msr = __rdmsr(MSR_IA32_MCU_OPT_CTRL); + msr |= FB_CLEAR_DIS; + native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr); + /* Cache the MSR value to avoid reading it later */ + vmx->msr_ia32_mcu_opt_ctrl = msr; +} + +static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) +{ + if (!vmx->disable_fb_clear) + return; + + vmx->msr_ia32_mcu_opt_ctrl &= ~FB_CLEAR_DIS; + native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl); +} + +static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) +{ + vmx->disable_fb_clear = vmx_fb_clear_ctrl_available; + + /* + * If guest will not execute VERW, there is no need to set FB_CLEAR_DIS + * at VMEntry. Skip the MSR read/write when a guest has no use case to + * execute VERW. + */ + if ((vcpu->arch.arch_capabilities & ARCH_CAP_FB_CLEAR) || + ((vcpu->arch.arch_capabilities & ARCH_CAP_MDS_NO) && + (vcpu->arch.arch_capabilities & ARCH_CAP_TAA_NO) && + (vcpu->arch.arch_capabilities & ARCH_CAP_PSDP_NO) && + (vcpu->arch.arch_capabilities & ARCH_CAP_FBSDP_NO) && + (vcpu->arch.arch_capabilities & ARCH_CAP_SBDR_SSDP_NO))) + vmx->disable_fb_clear = false; +} + static struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) { int i; @@ -4314,9 +4380,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } break; } - ret = kvm_set_msr_common(vcpu, msr_info); + ret = kvm_set_msr_common(vcpu, msr_info); } + /* FB_CLEAR may have changed, also update the FB_CLEAR_DIS behavior */ + if (msr_index == MSR_IA32_ARCH_CAPABILITIES) + vmx_update_fb_clear_dis(vcpu, vmx); + return ret; } @@ -4670,9 +4740,6 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) } } - if (boot_cpu_has(X86_FEATURE_XSAVES)) - rdmsrl(MSR_IA32_XSS, host_xss); - return 0; } @@ -5454,18 +5521,15 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var) { u32 ar; - if (var->unusable || !var->present) - ar = 1 << 16; - else { - ar = var->type & 15; - ar |= (var->s & 1) << 4; - ar |= (var->dpl & 3) << 5; - ar |= (var->present & 1) << 7; - ar |= (var->avl & 1) << 12; - ar |= (var->l & 1) << 13; - ar |= (var->db & 1) << 14; - ar |= (var->g & 1) << 15; - } + ar = var->type & 15; + ar |= (var->s & 1) << 4; + ar |= (var->dpl & 3) << 5; + ar |= (var->present & 1) << 7; + ar |= (var->avl & 1) << 12; + ar |= (var->l & 1) << 13; + ar |= (var->db & 1) << 14; + ar |= (var->g & 1) << 15; + ar |= (var->unusable || !var->present) << 16; return ar; } @@ -6761,6 +6825,8 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vpid_sync_context(vmx->vpid); if (init_event) vmx_clear_hlt(vcpu); + + vmx_update_fb_clear_dis(vcpu, vmx); } /* @@ -7885,6 +7951,9 @@ static __init int hardware_setup(void) WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost"); } + if (boot_cpu_has(X86_FEATURE_XSAVES)) + rdmsrl(MSR_IA32_XSS, host_xss); + if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() || !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global())) enable_vpid = 0; @@ -10694,10 +10763,35 @@ static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->hv_timer_armed = false; } +u64 __always_inline vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx) +{ + u64 guestval, hostval = this_cpu_read(x86_spec_ctrl_current); + + if (!cpu_feature_enabled(X86_FEATURE_MSR_SPEC_CTRL)) + return 0; + + guestval = __rdmsr(MSR_IA32_SPEC_CTRL); + + /* + * + * For legacy IBRS, the IBRS bit always needs to be written after + * transitioning from a less privileged predictor mode, regardless of + * whether the guest/host values differ. + */ + if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) || + guestval != hostval) + native_wrmsrl(MSR_IA32_SPEC_CTRL, hostval); + + barrier_nospec(); + + return guestval; +} + static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long cr3, cr4, evmcs_rsp; + u64 spec_ctrl; /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!enable_vnmi && @@ -10773,6 +10867,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_l1d_flush(vcpu); else if (static_branch_unlikely(&mds_user_clear)) mds_clear_cpu_buffers(); + else if (static_branch_unlikely(&mmio_stale_data_clear) && + kvm_arch_has_assigned_device(vcpu->kvm)) + mds_clear_cpu_buffers(); + + vmx_disable_fb_clear(vmx); asm volatile ( /* Store host registers */ @@ -10919,6 +11018,26 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) ); /* + * IMPORTANT: RSB filling and SPEC_CTRL handling must be done before + * the first unbalanced RET after vmexit! + * + * For retpoline or IBRS, RSB filling is needed to prevent poisoned RSB + * entries and (in some cases) RSB underflow. + * + * eIBRS has its own protection against poisoned RSB, so it doesn't + * need the RSB filling sequence. But it does need to be enabled, and a + * single call to retire, before the first unbalanced RET. + * + * So no RETs before vmx_spec_ctrl_restore_host() below. + */ + vmexit_fill_RSB(); + + /* Save this for below */ + spec_ctrl = vmx_spec_ctrl_restore_host(vmx); + + vmx_enable_fb_clear(vmx); + + /* * We do not use IBRS in the kernel. If this vCPU has used the * SPEC_CTRL MSR it may have left it on; save the value and * turn it off. This is much more efficient than blindly adding @@ -10934,12 +11053,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) * save it. */ if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) - vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); - - x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0); - - /* Eliminate branch target predictions from guest mode */ - vmexit_fill_RSB(); + vmx->spec_ctrl = spec_ctrl; /* All fields are clean at this point */ if (static_branch_unlikely(&enable_evmcs)) @@ -12498,6 +12612,10 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (nested_vmx_check_msr_switch_controls(vcpu, vmcs12)) return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + if (!nested_cpu_has_preemption_timer(vmcs12) && + nested_cpu_has_save_preemption_timer(vmcs12)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + if (nested_vmx_check_pml_controls(vcpu, vmcs12)) return VMXERR_ENTRY_INVALID_CONTROL_FIELD; @@ -12634,7 +12752,7 @@ static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu, static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, u32 *exit_qual) { - bool ia32e; + bool ia32e = !!(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE); *exit_qual = ENTRY_FAIL_DEFAULT; @@ -12647,6 +12765,13 @@ static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, return 1; } + if ((vmcs12->guest_cr0 & (X86_CR0_PG | X86_CR0_PE)) == X86_CR0_PG) + return 1; + + if ((ia32e && !(vmcs12->guest_cr4 & X86_CR4_PAE)) || + (ia32e && !(vmcs12->guest_cr0 & X86_CR0_PG))) + return 1; + /* * If the load IA32_EFER VM-entry control is 1, the following checks * are performed on the field for the IA32_EFER MSR: @@ -12658,7 +12783,6 @@ static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, */ if (to_vmx(vcpu)->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) { - ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0; if (!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer) || ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA) || ((vmcs12->guest_cr0 & X86_CR0_PG) && @@ -13204,14 +13328,6 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, */ vmcs12_save_pending_event(vcpu, vmcs12); } - - /* - * Drop what we picked up for L2 via vmx_complete_interrupts. It is - * preserved above and would only end up incorrectly in L1. - */ - vcpu->arch.nmi_injected = false; - kvm_clear_exception_queue(vcpu); - kvm_clear_interrupt_queue(vcpu); } /* @@ -13545,6 +13661,17 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, nested_vmx_abort(vcpu, VMX_ABORT_SAVE_GUEST_MSR_FAIL); } + /* + * Drop events/exceptions that were queued for re-injection to L2 + * (picked up via vmx_complete_interrupts()), as well as exceptions + * that were pending for L2. Note, this must NOT be hoisted above + * prepare_vmcs12(), events/exceptions queued for re-injection need to + * be captured in vmcs12 (see vmcs12_save_pending_event()). + */ + vcpu->arch.nmi_injected = false; + kvm_clear_exception_queue(vcpu); + kvm_clear_interrupt_queue(vcpu); + vmx_switch_vmcs(vcpu, &vmx->vmcs01); vm_entry_controls_reset_shadow(vmx); vm_exit_controls_reset_shadow(vmx); @@ -13751,6 +13878,21 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ break; + case x86_intercept_pause: + /* + * PAUSE is a single-byte NOP with a REPE prefix, i.e. collides + * with vanilla NOPs in the emulator. Apply the interception + * check only to actual PAUSE instructions. Don't check + * PAUSE-loop-exiting, software can't expect a given PAUSE to + * exit, i.e. KVM is within its rights to allow L2 to execute + * the PAUSE. + */ + if ((info->rep_prefix != REPE_PREFIX) || + !nested_cpu_has2(vmcs12, CPU_BASED_PAUSE_EXITING)) + return X86EMUL_CONTINUE; + + break; + /* TODO: check more intercepts... */ default: break; @@ -14623,8 +14765,11 @@ static int __init vmx_init(void) } } + vmx_setup_fb_clear_ctrl(); + 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)); } diff --git a/arch/x86/kvm/vmx_evmcs.h b/arch/x86/kvm/vmx/vmx_evmcs.h index 210a884090ad..210a884090ad 100644 --- a/arch/x86/kvm/vmx_evmcs.h +++ b/arch/x86/kvm/vmx/vmx_evmcs.h diff --git a/arch/x86/kvm/vmx_shadow_fields.h b/arch/x86/kvm/vmx/vmx_shadow_fields.h index cd0c75f6d037..cd0c75f6d037 100644 --- a/arch/x86/kvm/vmx_shadow_fields.h +++ b/arch/x86/kvm/vmx/vmx_shadow_fields.h diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 417abc9ba1ad..0548ae57826f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1156,7 +1156,7 @@ static u32 msr_based_features[] = { MSR_IA32_VMX_EPT_VPID_CAP, MSR_IA32_VMX_VMFUNC, - MSR_F10H_DECFG, + MSR_AMD64_DE_CFG, MSR_IA32_UCODE_REV, MSR_IA32_ARCH_CAPABILITIES, }; @@ -1220,6 +1220,13 @@ u64 kvm_get_arch_capabilities(void) /* KVM does not emulate MSR_IA32_TSX_CTRL. */ data &= ~ARCH_CAP_TSX_CTRL_MSR; + + /* Guests don't need to know "Fill buffer clear control" exists */ + data &= ~ARCH_CAP_FB_CLEAR_CTRL; + + if (!boot_cpu_has_bug(X86_BUG_GDS) || gds_ucode_mitigated()) + data |= ARCH_CAP_GDS_NO; + return data; } @@ -2453,6 +2460,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_PATCH_LOADER: case MSR_AMD64_BU_CFG2: case MSR_AMD64_DC_CFG: + case MSR_AMD64_TW_CFG: case MSR_F15H_EX_CFG: break; @@ -2756,6 +2764,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_BU_CFG2: case MSR_IA32_PERF_CTL: case MSR_AMD64_DC_CFG: + case MSR_AMD64_TW_CFG: case MSR_F15H_EX_CFG: msr_info->data = 0; break; @@ -3633,12 +3642,11 @@ static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, { unsigned long val; + memset(dbgregs, 0, sizeof(*dbgregs)); memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db)); kvm_get_dr(vcpu, 6, &val); dbgregs->dr6 = val; dbgregs->dr7 = vcpu->arch.dr7; - dbgregs->flags = 0; - memset(&dbgregs->reserved, 0, sizeof(dbgregs->reserved)); } static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, @@ -9732,9 +9740,9 @@ void kvm_arch_end_assignment(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_arch_end_assignment); -bool kvm_arch_has_assigned_device(struct kvm *kvm) +bool noinstr kvm_arch_has_assigned_device(struct kvm *kvm) { - return atomic_read(&kvm->arch.assigned_device_count); + return arch_atomic_read(&kvm->arch.assigned_device_count); } EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device); |