diff options
Diffstat (limited to 'arch/x86/kvm/vmx')
| -rw-r--r-- | arch/x86/kvm/vmx/capabilities.h | 28 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/nested.c | 143 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/pmu_intel.c | 294 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/posted_intr.c | 6 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/vmenter.S | 2 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/vmx.c | 394 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/vmx.h | 58 |
7 files changed, 644 insertions, 281 deletions
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 3a1861403d73..d1d77985e889 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -19,6 +19,9 @@ extern int __read_mostly pt_mode; #define PT_MODE_HOST_GUEST 1 #define PMU_CAP_FW_WRITES (1ULL << 13) +#define PMU_CAP_LBR_FMT 0x3f + +#define DEBUGCTLMSR_LBR_MASK (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) struct nested_vmx_msrs { /* @@ -262,6 +265,12 @@ static inline bool cpu_has_vmx_tsc_scaling(void) SECONDARY_EXEC_TSC_SCALING; } +static inline bool cpu_has_vmx_bus_lock_detection(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_BUS_LOCK_DETECTION; +} + static inline bool cpu_has_vmx_apicv(void) { return cpu_has_vmx_apic_register_virt() && @@ -371,11 +380,28 @@ static inline bool vmx_pt_mode_is_host_guest(void) static inline u64 vmx_get_perf_capabilities(void) { + u64 perf_cap = 0; + + if (boot_cpu_has(X86_FEATURE_PDCM)) + rdmsrl(MSR_IA32_PERF_CAPABILITIES, perf_cap); + + perf_cap &= PMU_CAP_LBR_FMT; + /* * Since counters are virtualized, KVM would support full * width counting unconditionally, even if the host lacks it. */ - return PMU_CAP_FW_WRITES; + return PMU_CAP_FW_WRITES | perf_cap; +} + +static inline u64 vmx_supported_debugctl(void) +{ + u64 debugctl = 0; + + if (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT) + debugctl |= DEBUGCTLMSR_LBR_MASK; + + return debugctl; } #endif /* __KVM_X86_VMX_CAPS_H */ diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index f2b9bfb58206..bcca0b80e0d0 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -12,6 +12,7 @@ #include "nested.h" #include "pmu.h" #include "trace.h" +#include "vmx.h" #include "x86.h" static bool __read_mostly enable_shadow_vmcs = 1; @@ -411,8 +412,8 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned long *exit if (nr == DB_VECTOR) { if (!has_payload) { payload = vcpu->arch.dr6; - payload &= ~(DR6_FIXED_1 | DR6_BT); - payload ^= DR6_RTM; + payload &= ~DR6_BT; + payload ^= DR6_ACTIVE_LOW; } *exit_qual = payload; } else @@ -744,8 +745,7 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu, (CC(!nested_cpu_has_vid(vmcs12)) || CC(!nested_exit_intr_ack_set(vcpu)) || CC((vmcs12->posted_intr_nv & 0xff00)) || - CC((vmcs12->posted_intr_desc_addr & 0x3f)) || - CC((vmcs12->posted_intr_desc_addr >> cpuid_maxphyaddr(vcpu))))) + CC(!kvm_vcpu_is_legal_aligned_gpa(vcpu, vmcs12->posted_intr_desc_addr, 64)))) return -EINVAL; /* tpr shadow is needed by all apicv features. */ @@ -758,13 +758,11 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu, static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu, u32 count, u64 addr) { - int maxphyaddr; - if (count == 0) return 0; - maxphyaddr = cpuid_maxphyaddr(vcpu); - if (!IS_ALIGNED(addr, 16) || addr >> maxphyaddr || - (addr + count * sizeof(struct vmx_msr_entry) - 1) >> maxphyaddr) + + if (!kvm_vcpu_is_legal_aligned_gpa(vcpu, addr, 16) || + !kvm_vcpu_is_legal_gpa(vcpu, (addr + count * sizeof(struct vmx_msr_entry) - 1))) return -EINVAL; return 0; @@ -1062,14 +1060,6 @@ static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu, } } -static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val) -{ - unsigned long invalid_mask; - - invalid_mask = (~0ULL) << cpuid_maxphyaddr(vcpu); - return (val & invalid_mask) == 0; -} - /* * Returns true if the MMU needs to be sync'd on nested VM-Enter/VM-Exit. * tl;dr: the MMU needs a sync if L0 is using shadow paging and L1 didn't @@ -1121,7 +1111,7 @@ static bool nested_vmx_transition_mmu_sync(struct kvm_vcpu *vcpu) static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept, enum vm_entry_failure_code *entry_failure_code) { - if (CC(!nested_cr3_valid(vcpu, cr3))) { + if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3))) { *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; } @@ -2177,15 +2167,13 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx) vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap)); /* - * The PML address never changes, so it is constant in vmcs02. - * Conceptually we want to copy the PML index from vmcs01 here, - * and then back to vmcs01 on nested vmexit. But since we flush - * the log and reset GUEST_PML_INDEX on each vmexit, the PML - * index is also effectively constant in vmcs02. + * PML is emulated for L2, but never enabled in hardware as the MMU + * handles A/D emulation. Disabling PML for L2 also avoids having to + * deal with filtering out L2 GPAs from the buffer. */ if (enable_pml) { - vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); - vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); + vmcs_write64(PML_ADDRESS, 0); + vmcs_write16(GUEST_PML_INDEX, -1); } if (cpu_has_vmx_encls_vmexit()) @@ -2220,7 +2208,7 @@ static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx, static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) { - u32 exec_control, vmcs12_exec_ctrl; + u32 exec_control; u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12); if (vmx->nested.dirty_vmcs12 || vmx->nested.hv_evmcs) @@ -2294,11 +2282,11 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_ENABLE_VMFUNC); if (nested_cpu_has(vmcs12, - CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) { - vmcs12_exec_ctrl = vmcs12->secondary_vm_exec_control & - ~SECONDARY_EXEC_ENABLE_PML; - exec_control |= vmcs12_exec_ctrl; - } + CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) + exec_control |= vmcs12->secondary_vm_exec_control; + + /* PML is emulated and never enabled in hardware for L2. */ + exec_control &= ~SECONDARY_EXEC_ENABLE_PML; /* VMCS shadowing for L2 is emulated for now */ exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; @@ -2532,7 +2520,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * bitwise-or of what L1 wants to trap for L2, and what we want to * trap. Note that CR0.TS also needs updating - we do this later. */ - update_exception_bitmap(vcpu); + vmx_update_exception_bitmap(vcpu); vcpu->arch.cr0_guest_owned_bits &= ~vmcs12->cr0_guest_host_mask; vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits); @@ -2635,7 +2623,6 @@ static int nested_vmx_check_nmi_controls(struct vmcs12 *vmcs12) static bool nested_vmx_check_eptp(struct kvm_vcpu *vcpu, u64 new_eptp) { struct vcpu_vmx *vmx = to_vmx(vcpu); - int maxphyaddr = cpuid_maxphyaddr(vcpu); /* Check for memory type validity */ switch (new_eptp & VMX_EPTP_MT_MASK) { @@ -2666,7 +2653,7 @@ static bool nested_vmx_check_eptp(struct kvm_vcpu *vcpu, u64 new_eptp) } /* Reserved bits should not be set */ - if (CC(new_eptp >> maxphyaddr || ((new_eptp >> 7) & 0x1f))) + if (CC(kvm_vcpu_is_illegal_gpa(vcpu, new_eptp) || ((new_eptp >> 7) & 0x1f))) return false; /* AD, if set, should be supported */ @@ -2850,7 +2837,7 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, if (CC(!nested_host_cr0_valid(vcpu, vmcs12->host_cr0)) || CC(!nested_host_cr4_valid(vcpu, vmcs12->host_cr4)) || - CC(!nested_cr3_valid(vcpu, vmcs12->host_cr3))) + CC(kvm_vcpu_is_illegal_gpa(vcpu, vmcs12->host_cr3))) return -EINVAL; if (CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu)) || @@ -3057,35 +3044,8 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->host_state.cr4 = cr4; } - asm( - "sub $%c[wordsize], %%" _ASM_SP "\n\t" /* temporarily adjust RSP for CALL */ - "cmp %%" _ASM_SP ", %c[host_state_rsp](%[loaded_vmcs]) \n\t" - "je 1f \n\t" - __ex("vmwrite %%" _ASM_SP ", %[HOST_RSP]") "\n\t" - "mov %%" _ASM_SP ", %c[host_state_rsp](%[loaded_vmcs]) \n\t" - "1: \n\t" - "add $%c[wordsize], %%" _ASM_SP "\n\t" /* un-adjust RSP */ - - /* Check if vmlaunch or vmresume is needed */ - "cmpb $0, %c[launched](%[loaded_vmcs])\n\t" - - /* - * VMLAUNCH and VMRESUME clear RFLAGS.{CF,ZF} on VM-Exit, set - * RFLAGS.CF on VM-Fail Invalid and set RFLAGS.ZF on VM-Fail - * Valid. vmx_vmenter() directly "returns" RFLAGS, and so the - * results of VM-Enter is captured via CC_{SET,OUT} to vm_fail. - */ - "call vmx_vmenter\n\t" - - CC_SET(be) - : ASM_CALL_CONSTRAINT, CC_OUT(be) (vm_fail) - : [HOST_RSP]"r"((unsigned long)HOST_RSP), - [loaded_vmcs]"r"(vmx->loaded_vmcs), - [launched]"i"(offsetof(struct loaded_vmcs, launched)), - [host_state_rsp]"i"(offsetof(struct loaded_vmcs, host_state.rsp)), - [wordsize]"i"(sizeof(ulong)) - : "memory" - ); + vm_fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs, + vmx->loaded_vmcs->launched); if (vmx->msr_autoload.host.nr) vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); @@ -3330,7 +3290,11 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12 = get_vmcs12(vcpu); enum vm_entry_failure_code entry_failure_code; bool evaluate_pending_interrupts; - u32 exit_reason, failed_index; + union vmx_exit_reason exit_reason = { + .basic = EXIT_REASON_INVALID_STATE, + .failed_vmentry = 1, + }; + u32 failed_index; if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) kvm_vcpu_flush_tlb_current(vcpu); @@ -3382,7 +3346,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, if (nested_vmx_check_guest_state(vcpu, vmcs12, &entry_failure_code)) { - exit_reason = EXIT_REASON_INVALID_STATE; + exit_reason.basic = EXIT_REASON_INVALID_STATE; vmcs12->exit_qualification = entry_failure_code; goto vmentry_fail_vmexit; } @@ -3393,7 +3357,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, vcpu->arch.tsc_offset += vmcs12->tsc_offset; if (prepare_vmcs02(vcpu, vmcs12, &entry_failure_code)) { - exit_reason = EXIT_REASON_INVALID_STATE; + exit_reason.basic = EXIT_REASON_INVALID_STATE; vmcs12->exit_qualification = entry_failure_code; goto vmentry_fail_vmexit_guest_mode; } @@ -3403,7 +3367,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, vmcs12->vm_entry_msr_load_addr, vmcs12->vm_entry_msr_load_count); if (failed_index) { - exit_reason = EXIT_REASON_MSR_LOAD_FAIL; + exit_reason.basic = EXIT_REASON_MSR_LOAD_FAIL; vmcs12->exit_qualification = failed_index; goto vmentry_fail_vmexit_guest_mode; } @@ -3471,7 +3435,7 @@ vmentry_fail_vmexit: return NVMX_VMENTRY_VMEXIT; load_vmcs12_host_state(vcpu, vmcs12); - vmcs12->vm_exit_reason = exit_reason | VMX_EXIT_REASONS_FAILED_VMENTRY; + vmcs12->vm_exit_reason = exit_reason.full; if (enable_shadow_vmcs || vmx->nested.hv_evmcs) vmx->nested.need_vmcs12_to_shadow_sync = true; return NVMX_VMENTRY_VMEXIT; @@ -4234,9 +4198,6 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &ignored)) nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL); - if (!enable_ept) - vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault; - nested_vmx_transition_tlb_flush(vcpu, vmcs12, false); vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs); @@ -4529,6 +4490,11 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, vmx_set_virtual_apic_mode(vcpu); } + if (vmx->nested.update_vmcs01_cpu_dirty_logging) { + vmx->nested.update_vmcs01_cpu_dirty_logging = false; + vmx_update_cpu_dirty_logging(vcpu); + } + /* Unpin physical memory we referred to in vmcs02 */ if (vmx->nested.apic_access_page) { kvm_release_page_clean(vmx->nested.apic_access_page); @@ -5559,7 +5525,12 @@ static int handle_vmfunc(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); fail: - nested_vmx_vmexit(vcpu, vmx->exit_reason, + /* + * This is effectively a reflected VM-Exit, as opposed to a synthesized + * nested VM-Exit. Pass the original exit reason, i.e. don't hardcode + * EXIT_REASON_VMFUNC as the exit reason. + */ + nested_vmx_vmexit(vcpu, vmx->exit_reason.full, vmx_get_intr_info(vcpu), vmx_get_exit_qual(vcpu)); return 1; @@ -5627,7 +5598,8 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, * MSR bitmap. This may be the case even when L0 doesn't use MSR bitmaps. */ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12, u32 exit_reason) + struct vmcs12 *vmcs12, + union vmx_exit_reason exit_reason) { u32 msr_index = kvm_rcx_read(vcpu); gpa_t bitmap; @@ -5641,7 +5613,7 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, * First we need to figure out which of the four to use: */ bitmap = vmcs12->msr_bitmap; - if (exit_reason == EXIT_REASON_MSR_WRITE) + if (exit_reason.basic == EXIT_REASON_MSR_WRITE) bitmap += 2048; if (msr_index >= 0xc0000000) { msr_index -= 0xc0000000; @@ -5778,11 +5750,12 @@ static bool nested_vmx_exit_handled_mtf(struct vmcs12 *vmcs12) * Return true if L0 wants to handle an exit from L2 regardless of whether or not * L1 wants the exit. Only call this when in is_guest_mode (L2). */ -static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, u32 exit_reason) +static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, + union vmx_exit_reason exit_reason) { u32 intr_info; - switch ((u16)exit_reason) { + switch ((u16)exit_reason.basic) { case EXIT_REASON_EXCEPTION_NMI: intr_info = vmx_get_intr_info(vcpu); if (is_nmi(intr_info)) @@ -5820,7 +5793,10 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, u32 exit_reason) case EXIT_REASON_PREEMPTION_TIMER: return true; case EXIT_REASON_PML_FULL: - /* We emulate PML support to L1. */ + /* + * PML is emulated for an L1 VMM and should never be enabled in + * vmcs02, always "handle" PML_FULL by exiting to userspace. + */ return true; case EXIT_REASON_VMFUNC: /* VM functions are emulated through L2->L0 vmexits. */ @@ -5838,12 +5814,13 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, u32 exit_reason) * Return 1 if L1 wants to intercept an exit from L2. Only call this when in * is_guest_mode (L2). */ -static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu, u32 exit_reason) +static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu, + union vmx_exit_reason exit_reason) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); u32 intr_info; - switch ((u16)exit_reason) { + switch ((u16)exit_reason.basic) { case EXIT_REASON_EXCEPTION_NMI: intr_info = vmx_get_intr_info(vcpu); if (is_nmi(intr_info)) @@ -5962,7 +5939,7 @@ static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu, u32 exit_reason) bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 exit_reason = vmx->exit_reason; + union vmx_exit_reason exit_reason = vmx->exit_reason; unsigned long exit_qual; u32 exit_intr_info; @@ -5981,7 +5958,7 @@ bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu) goto reflect_vmexit; } - trace_kvm_nested_vmexit(exit_reason, vcpu, KVM_ISA_VMX); + trace_kvm_nested_vmexit(exit_reason.full, vcpu, KVM_ISA_VMX); /* If L0 (KVM) wants the exit, it trumps L1's desires. */ if (nested_vmx_l0_wants_exit(vcpu, exit_reason)) @@ -6007,7 +5984,7 @@ bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu) exit_qual = vmx_get_exit_qual(vcpu); reflect_vmexit: - nested_vmx_vmexit(vcpu, exit_reason, exit_intr_info, exit_qual); + nested_vmx_vmexit(vcpu, exit_reason.full, exit_intr_info, exit_qual); return true; } diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index cdf5f34518f4..9efc1a6b8693 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -152,12 +152,17 @@ static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, return &counters[array_index_nospec(idx, num_counters)]; } -static inline bool fw_writes_is_enabled(struct kvm_vcpu *vcpu) +static inline u64 vcpu_get_perf_capabilities(struct kvm_vcpu *vcpu) { if (!guest_cpuid_has(vcpu, X86_FEATURE_PDCM)) - return false; + return 0; - return vcpu->arch.perf_capabilities & PMU_CAP_FW_WRITES; + return vcpu->arch.perf_capabilities; +} + +static inline bool fw_writes_is_enabled(struct kvm_vcpu *vcpu) +{ + return (vcpu_get_perf_capabilities(vcpu) & PMU_CAP_FW_WRITES) != 0; } static inline struct kvm_pmc *get_fw_gp_pmc(struct kvm_pmu *pmu, u32 msr) @@ -168,6 +173,41 @@ static inline struct kvm_pmc *get_fw_gp_pmc(struct kvm_pmu *pmu, u32 msr) return get_gp_pmc(pmu, msr, MSR_IA32_PMC0); } +bool intel_pmu_lbr_is_compatible(struct kvm_vcpu *vcpu) +{ + /* + * As a first step, a guest could only enable LBR feature if its + * cpu model is the same as the host because the LBR registers + * would be pass-through to the guest and they're model specific. + */ + return boot_cpu_data.x86_model == guest_cpuid_model(vcpu); +} + +bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu) +{ + struct x86_pmu_lbr *lbr = vcpu_to_lbr_records(vcpu); + + return lbr->nr && (vcpu_get_perf_capabilities(vcpu) & PMU_CAP_LBR_FMT); +} + +static bool intel_pmu_is_valid_lbr_msr(struct kvm_vcpu *vcpu, u32 index) +{ + struct x86_pmu_lbr *records = vcpu_to_lbr_records(vcpu); + bool ret = false; + + if (!intel_pmu_lbr_is_enabled(vcpu)) + return ret; + + ret = (index == MSR_LBR_SELECT) || (index == MSR_LBR_TOS) || + (index >= records->from && index < records->from + records->nr) || + (index >= records->to && index < records->to + records->nr); + + if (!ret && records->info) + ret = (index >= records->info && index < records->info + records->nr); + + return ret; +} + static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -183,7 +223,8 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) default: ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0) || get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0) || - get_fixed_pmc(pmu, msr) || get_fw_gp_pmc(pmu, msr); + get_fixed_pmc(pmu, msr) || get_fw_gp_pmc(pmu, msr) || + intel_pmu_is_valid_lbr_msr(vcpu, msr); break; } @@ -202,6 +243,111 @@ static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr) return pmc; } +static inline void intel_pmu_release_guest_lbr_event(struct kvm_vcpu *vcpu) +{ + struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); + + if (lbr_desc->event) { + perf_event_release_kernel(lbr_desc->event); + lbr_desc->event = NULL; + vcpu_to_pmu(vcpu)->event_count--; + } +} + +int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu) +{ + struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct perf_event *event; + + /* + * The perf_event_attr is constructed in the minimum efficient way: + * - set 'pinned = true' to make it task pinned so that if another + * cpu pinned event reclaims LBR, the event->oncpu will be set to -1; + * - set '.exclude_host = true' to record guest branches behavior; + * + * - set '.config = INTEL_FIXED_VLBR_EVENT' to indicates host perf + * schedule the event without a real HW counter but a fake one; + * check is_guest_lbr_event() and __intel_get_event_constraints(); + * + * - set 'sample_type = PERF_SAMPLE_BRANCH_STACK' and + * 'branch_sample_type = PERF_SAMPLE_BRANCH_CALL_STACK | + * PERF_SAMPLE_BRANCH_USER' to configure it as a LBR callstack + * event, which helps KVM to save/restore guest LBR records + * during host context switches and reduces quite a lot overhead, + * check branch_user_callstack() and intel_pmu_lbr_sched_task(); + */ + struct perf_event_attr attr = { + .type = PERF_TYPE_RAW, + .size = sizeof(attr), + .config = INTEL_FIXED_VLBR_EVENT, + .sample_type = PERF_SAMPLE_BRANCH_STACK, + .pinned = true, + .exclude_host = true, + .branch_sample_type = PERF_SAMPLE_BRANCH_CALL_STACK | + PERF_SAMPLE_BRANCH_USER, + }; + + if (unlikely(lbr_desc->event)) { + __set_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use); + return 0; + } + + event = perf_event_create_kernel_counter(&attr, -1, + current, NULL, NULL); + if (IS_ERR(event)) { + pr_debug_ratelimited("%s: failed %ld\n", + __func__, PTR_ERR(event)); + return PTR_ERR(event); + } + lbr_desc->event = event; + pmu->event_count++; + __set_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use); + return 0; +} + +/* + * It's safe to access LBR msrs from guest when they have not + * been passthrough since the host would help restore or reset + * the LBR msrs records when the guest LBR event is scheduled in. + */ +static bool intel_pmu_handle_lbr_msrs_access(struct kvm_vcpu *vcpu, + struct msr_data *msr_info, bool read) +{ + struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); + u32 index = msr_info->index; + + if (!intel_pmu_is_valid_lbr_msr(vcpu, index)) + return false; + + if (!lbr_desc->event && intel_pmu_create_guest_lbr_event(vcpu) < 0) + goto dummy; + + /* + * Disable irq to ensure the LBR feature doesn't get reclaimed by the + * host at the time the value is read from the msr, and this avoids the + * host LBR value to be leaked to the guest. If LBR has been reclaimed, + * return 0 on guest reads. + */ + local_irq_disable(); + if (lbr_desc->event->state == PERF_EVENT_STATE_ACTIVE) { + if (read) + rdmsrl(index, msr_info->data); + else + wrmsrl(index, msr_info->data); + __set_bit(INTEL_PMC_IDX_FIXED_VLBR, vcpu_to_pmu(vcpu)->pmc_in_use); + local_irq_enable(); + return true; + } + clear_bit(INTEL_PMC_IDX_FIXED_VLBR, vcpu_to_pmu(vcpu)->pmc_in_use); + local_irq_enable(); + +dummy: + if (read) + msr_info->data = 0; + return true; +} + static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -236,7 +382,8 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { msr_info->data = pmc->eventsel; return 0; - } + } else if (intel_pmu_handle_lbr_msrs_access(vcpu, msr_info, true)) + return 0; } return 1; @@ -307,7 +454,8 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) reprogram_gp_counter(pmc, data); return 0; } - } + } else if (intel_pmu_handle_lbr_msrs_access(vcpu, msr_info, false)) + return 0; } return 1; @@ -316,6 +464,8 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) static void intel_pmu_refresh(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); + struct x86_pmu_capability x86_pmu; struct kvm_cpuid_entry2 *entry; union cpuid10_eax eax; @@ -327,7 +477,6 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->counter_bitmask[KVM_PMC_FIXED] = 0; pmu->version = 0; pmu->reserved_bits = 0xffffffff00200000ull; - vcpu->arch.perf_capabilities = 0; entry = kvm_find_cpuid_entry(vcpu, 0xa, 0); if (!entry) @@ -340,8 +489,6 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) return; perf_get_x86_pmu_capability(&x86_pmu); - if (guest_cpuid_has(vcpu, X86_FEATURE_PDCM)) - vcpu->arch.perf_capabilities = vmx_get_perf_capabilities(); pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters, x86_pmu.num_counters_gp); @@ -385,12 +532,21 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) INTEL_PMC_MAX_GENERIC, pmu->nr_arch_fixed_counters); nested_vmx_pmu_entry_exit_ctls_update(vcpu); + + if (intel_pmu_lbr_is_compatible(vcpu)) + x86_perf_get_lbr(&lbr_desc->records); + else + lbr_desc->records.nr = 0; + + if (lbr_desc->records.nr) + bitmap_set(pmu->all_valid_pmc_idx, INTEL_PMC_IDX_FIXED_VLBR, 1); } static void intel_pmu_init(struct kvm_vcpu *vcpu) { int i; struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { pmu->gp_counters[i].type = KVM_PMC_GP; @@ -405,6 +561,11 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu) pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED; pmu->fixed_counters[i].current_config = 0; } + + vcpu->arch.perf_capabilities = vmx_get_perf_capabilities(); + lbr_desc->records.nr = 0; + lbr_desc->event = NULL; + lbr_desc->msr_passthrough = false; } static void intel_pmu_reset(struct kvm_vcpu *vcpu) @@ -429,6 +590,119 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu) pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = pmu->global_ovf_ctrl = 0; + + intel_pmu_release_guest_lbr_event(vcpu); +} + +/* + * Emulate LBR_On_PMI behavior for 1 < pmu.version < 4. + * + * If Freeze_LBR_On_PMI = 1, the LBR is frozen on PMI and + * the KVM emulates to clear the LBR bit (bit 0) in IA32_DEBUGCTL. + * + * Guest needs to re-enable LBR to resume branches recording. + */ +static void intel_pmu_legacy_freezing_lbrs_on_pmi(struct kvm_vcpu *vcpu) +{ + u64 data = vmcs_read64(GUEST_IA32_DEBUGCTL); + + if (data & DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) { + data &= ~DEBUGCTLMSR_LBR; + vmcs_write64(GUEST_IA32_DEBUGCTL, data); + } +} + +static void intel_pmu_deliver_pmi(struct kvm_vcpu *vcpu) +{ + u8 version = vcpu_to_pmu(vcpu)->version; + + if (!intel_pmu_lbr_is_enabled(vcpu)) + return; + + if (version > 1 && version < 4) + intel_pmu_legacy_freezing_lbrs_on_pmi(vcpu); +} + +static void vmx_update_intercept_for_lbr_msrs(struct kvm_vcpu *vcpu, bool set) +{ + struct x86_pmu_lbr *lbr = vcpu_to_lbr_records(vcpu); + int i; + + for (i = 0; i < lbr->nr; i++) { + vmx_set_intercept_for_msr(vcpu, lbr->from + i, MSR_TYPE_RW, set); + vmx_set_intercept_for_msr(vcpu, lbr->to + i, MSR_TYPE_RW, set); + if (lbr->info) + vmx_set_intercept_for_msr(vcpu, lbr->info + i, MSR_TYPE_RW, set); + } + + vmx_set_intercept_for_msr(vcpu, MSR_LBR_SELECT, MSR_TYPE_RW, set); + vmx_set_intercept_for_msr(vcpu, MSR_LBR_TOS, MSR_TYPE_RW, set); +} + +static inline void vmx_disable_lbr_msrs_passthrough(struct kvm_vcpu *vcpu) +{ + struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); + + if (!lbr_desc->msr_passthrough) + return; + + vmx_update_intercept_for_lbr_msrs(vcpu, true); + lbr_desc->msr_passthrough = false; +} + +static inline void vmx_enable_lbr_msrs_passthrough(struct kvm_vcpu *vcpu) +{ + struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); + + if (lbr_desc->msr_passthrough) + return; + + vmx_update_intercept_for_lbr_msrs(vcpu, false); + lbr_desc->msr_passthrough = true; +} + +/* + * Higher priority host perf events (e.g. cpu pinned) could reclaim the + * pmu resources (e.g. LBR) that were assigned to the guest. This is + * usually done via ipi calls (more details in perf_install_in_context). + * + * Before entering the non-root mode (with irq disabled here), double + * confirm that the pmu features enabled to the guest are not reclaimed + * by higher priority host events. Otherwise, disallow vcpu's access to + * the reclaimed features. + */ +void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); + + if (!lbr_desc->event) { + vmx_disable_lbr_msrs_passthrough(vcpu); + if (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR) + goto warn; + if (test_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use)) + goto warn; + return; + } + + if (lbr_desc->event->state < PERF_EVENT_STATE_ACTIVE) { + vmx_disable_lbr_msrs_passthrough(vcpu); + __clear_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use); + goto warn; + } else + vmx_enable_lbr_msrs_passthrough(vcpu); + + return; + +warn: + pr_warn_ratelimited("kvm: vcpu-%d: fail to passthrough LBR.\n", + vcpu->vcpu_id); +} + +static void intel_pmu_cleanup(struct kvm_vcpu *vcpu) +{ + if (!(vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR)) + intel_pmu_release_guest_lbr_event(vcpu); } struct kvm_pmu_ops intel_pmu_ops = { @@ -445,4 +719,6 @@ struct kvm_pmu_ops intel_pmu_ops = { .refresh = intel_pmu_refresh, .init = intel_pmu_init, .reset = intel_pmu_reset, + .deliver_pmi = intel_pmu_deliver_pmi, + .cleanup = intel_pmu_cleanup, }; diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index f02962dcc72c..4831bc44ce66 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -54,7 +54,7 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) dest = cpu_physical_id(cpu); - if (x2apic_enabled()) + if (x2apic_mode) new.ndst = dest; else new.ndst = (dest << 8) & 0xFF00; @@ -104,7 +104,7 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) dest = cpu_physical_id(vcpu->cpu); - if (x2apic_enabled()) + if (x2apic_mode) new.ndst = dest; else new.ndst = (dest << 8) & 0xFF00; @@ -174,7 +174,7 @@ int pi_pre_block(struct kvm_vcpu *vcpu) */ dest = cpu_physical_id(vcpu->pre_pcpu); - if (x2apic_enabled()) + if (x2apic_mode) new.ndst = dest; else new.ndst = (dest << 8) & 0xFF00; diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index e85aa5faa22d..3a6461694fc2 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -44,7 +44,7 @@ * they VM-Fail, whereas a successful VM-Enter + VM-Exit will jump * to vmx_vmexit. */ -SYM_FUNC_START(vmx_vmenter) +SYM_FUNC_START_LOCAL(vmx_vmenter) /* EFLAGS.ZF is set if VMCS.LAUNCHED == 0 */ je 2f diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index eb69fef57485..50810d471462 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -50,6 +50,7 @@ #include "capabilities.h" #include "cpuid.h" #include "evmcs.h" +#include "hyperv.h" #include "irq.h" #include "kvm_cache_regs.h" #include "lapic.h" @@ -552,7 +553,7 @@ static int hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) { struct hv_enlightened_vmcs *evmcs; struct hv_partition_assist_pg **p_hv_pa_pg = - &vcpu->kvm->arch.hyperv.hv_pa_pg; + &to_kvm_hv(vcpu->kvm)->hv_pa_pg; /* * Synthetic VM-Exit is not enabled in current code and so All * evmcs in singe VM shares same assist page. @@ -658,6 +659,14 @@ static bool is_valid_passthrough_msr(u32 msr) case MSR_IA32_RTIT_CR3_MATCH: case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: /* PT MSRs. These are handled in pt_update_intercept_for_msr() */ + case MSR_LBR_SELECT: + case MSR_LBR_TOS: + case MSR_LBR_INFO_0 ... MSR_LBR_INFO_0 + 31: + case MSR_LBR_NHM_FROM ... MSR_LBR_NHM_FROM + 31: + case MSR_LBR_NHM_TO ... MSR_LBR_NHM_TO + 31: + case MSR_LBR_CORE_FROM ... MSR_LBR_CORE_FROM + 8: + case MSR_LBR_CORE_TO ... MSR_LBR_CORE_TO + 8: + /* LBR MSRs. These are handled in vmx_update_intercept_for_lbr_msrs() */ return true; } @@ -806,7 +815,7 @@ static u32 vmx_read_guest_seg_ar(struct vcpu_vmx *vmx, unsigned seg) return *p; } -void update_exception_bitmap(struct kvm_vcpu *vcpu) +void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu) { u32 eb; @@ -1102,7 +1111,7 @@ static inline bool pt_can_write_msr(struct vcpu_vmx *vmx) static inline bool pt_output_base_valid(struct kvm_vcpu *vcpu, u64 base) { /* The base must be 128-byte aligned and a legal physical address. */ - return !kvm_vcpu_is_illegal_gpa(vcpu, base) && !(base & 0x7f); + return kvm_vcpu_is_legal_aligned_gpa(vcpu, base, 128); } static inline void pt_load_msr(struct pt_ctx *ctx, u32 addr_range) @@ -1577,7 +1586,7 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) * i.e. we end up advancing IP with some random value. */ if (!static_cpu_has(X86_FEATURE_HYPERVISOR) || - to_vmx(vcpu)->exit_reason != EXIT_REASON_EPT_MISCONFIG) { + to_vmx(vcpu)->exit_reason.basic != EXIT_REASON_EPT_MISCONFIG) { orig_rip = kvm_rip_read(vcpu); rip = orig_rip + vmcs_read32(VM_EXIT_INSTRUCTION_LEN); #ifdef CONFIG_X86_64 @@ -1924,6 +1933,9 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) return 1; goto find_uret_msr; + case MSR_IA32_DEBUGCTLMSR: + msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL); + break; default: find_uret_msr: msr = vmx_find_uret_msr(vmx, msr_info->index); @@ -1947,6 +1959,16 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu, return (unsigned long)data; } +static u64 vcpu_supported_debugctl(struct kvm_vcpu *vcpu) +{ + u64 debugctl = vmx_supported_debugctl(); + + if (!intel_pmu_lbr_is_enabled(vcpu)) + debugctl &= ~DEBUGCTLMSR_LBR_MASK; + + return debugctl; +} + /* * Writes msr value into the appropriate "register". * Returns 0 on success, non-0 otherwise. @@ -1997,14 +2019,29 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } vmcs_writel(GUEST_SYSENTER_ESP, data); break; - case MSR_IA32_DEBUGCTLMSR: + case MSR_IA32_DEBUGCTLMSR: { + u64 invalid = data & ~vcpu_supported_debugctl(vcpu); + if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) { + if (report_ignored_msrs) + vcpu_unimpl(vcpu, "%s: BTF|LBR in IA32_DEBUGCTLMSR 0x%llx, nop\n", + __func__, data); + data &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); + invalid &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); + } + + if (invalid) + return 1; + if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) get_vmcs12(vcpu)->guest_ia32_debugctl = data; - ret = kvm_set_msr_common(vcpu, msr_info); - break; - + vmcs_write64(GUEST_IA32_DEBUGCTL, data); + if (intel_pmu_lbr_is_enabled(vcpu) && !to_vmx(vcpu)->lbr_desc.event && + (data & DEBUGCTLMSR_LBR)) + intel_pmu_create_guest_lbr_event(vcpu); + return 0; + } case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated && @@ -2196,6 +2233,18 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if ((data >> 32) != 0) return 1; goto find_uret_msr; + case MSR_IA32_PERF_CAPABILITIES: + if (data && !vcpu_to_pmu(vcpu)->version) + return 1; + if (data & PMU_CAP_LBR_FMT) { + if ((data & PMU_CAP_LBR_FMT) != + (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT)) + return 1; + if (!intel_pmu_lbr_is_compatible(vcpu)) + return 1; + } + ret = kvm_set_msr_common(vcpu, msr_info); + break; default: find_uret_msr: @@ -2265,7 +2314,6 @@ static int kvm_cpu_vmxon(u64 vmxon_pointer) u64 msr; cr4_set_bits(X86_CR4_VMXE); - intel_pt_handle_vmx(1); asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t" _ASM_EXTABLE(1b, %l[fault]) @@ -2276,7 +2324,6 @@ static int kvm_cpu_vmxon(u64 vmxon_pointer) fault: WARN_ONCE(1, "VMXON faulted, MSR_IA32_FEAT_CTL (0x3a) = 0x%llx\n", rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr); - intel_pt_handle_vmx(0); cr4_clear_bits(X86_CR4_VMXE); return -EFAULT; @@ -2299,9 +2346,13 @@ static int hardware_enable(void) !hv_get_vp_assist_page(cpu)) return -EFAULT; + intel_pt_handle_vmx(1); + r = kvm_cpu_vmxon(phys_addr); - if (r) + if (r) { + intel_pt_handle_vmx(0); return r; + } if (enable_ept) ept_sync_global(); @@ -2319,22 +2370,14 @@ static void vmclear_local_loaded_vmcss(void) __loaded_vmcs_clear(v); } - -/* Just like cpu_vmxoff(), but with the __kvm_handle_fault_on_reboot() - * tricks. - */ -static void kvm_cpu_vmxoff(void) -{ - asm volatile (__ex("vmxoff")); - - intel_pt_handle_vmx(0); - cr4_clear_bits(X86_CR4_VMXE); -} - static void hardware_disable(void) { vmclear_local_loaded_vmcss(); - kvm_cpu_vmxoff(); + + if (cpu_vmxoff()) + kvm_spurious_fault(); + + intel_pt_handle_vmx(0); } /* @@ -2428,7 +2471,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | SECONDARY_EXEC_PT_USE_GPA | SECONDARY_EXEC_PT_CONCEAL_VMX | - SECONDARY_EXEC_ENABLE_VMFUNC; + SECONDARY_EXEC_ENABLE_VMFUNC | + SECONDARY_EXEC_BUS_LOCK_DETECTION; if (cpu_has_sgx()) opt2 |= SECONDARY_EXEC_ENCLS_EXITING; if (adjust_vmx_controls(min2, opt2, @@ -2739,7 +2783,7 @@ static void enter_pmode(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) | (vmcs_readl(CR4_READ_SHADOW) & X86_CR4_VME)); - update_exception_bitmap(vcpu); + vmx_update_exception_bitmap(vcpu); fix_pmode_seg(vcpu, VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]); fix_pmode_seg(vcpu, VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]); @@ -2819,7 +2863,7 @@ static void enter_rmode(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_RFLAGS, flags); vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | X86_CR4_VME); - update_exception_bitmap(vcpu); + vmx_update_exception_bitmap(vcpu); fix_rmode_seg(VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]); fix_rmode_seg(VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]); @@ -3774,7 +3818,7 @@ static __always_inline void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, vmx_set_msr_bitmap_write(msr_bitmap, msr); } -static __always_inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, +void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool value) { if (value) @@ -4233,7 +4277,12 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) */ exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; - if (!enable_pml) + /* + * PML is enabled/disabled when dirty logging of memsmlots changes, but + * it needs to be set here when dirty logging is already active, e.g. + * if this vCPU was created after dirty logging was enabled. + */ + if (!vcpu->kvm->arch.cpu_dirty_logging_count) exec_control &= ~SECONDARY_EXEC_ENABLE_PML; if (cpu_has_vmx_xsaves()) { @@ -4251,24 +4300,17 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) } vmx_adjust_sec_exec_feature(vmx, &exec_control, rdtscp, RDTSCP); - - /* - * Expose INVPCID if and only if PCID is also exposed to the guest. - * INVPCID takes a #UD when it's disabled in the VMCS, but a #GP or #PF - * if CR4.PCIDE=0. Enumerating CPUID.INVPCID=1 would lead to incorrect - * behavior from the guest perspective (it would expect #GP or #PF). - */ - if (!guest_cpuid_has(vcpu, X86_FEATURE_PCID)) - guest_cpuid_clear(vcpu, X86_FEATURE_INVPCID); vmx_adjust_sec_exec_feature(vmx, &exec_control, invpcid, INVPCID); - vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdrand, RDRAND); vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdseed, RDSEED); vmx_adjust_sec_exec_control(vmx, &exec_control, waitpkg, WAITPKG, ENABLE_USR_WAIT_PAUSE, false); + if (!vcpu->kvm->arch.bus_lock_detection_enabled) + exec_control &= ~SECONDARY_EXEC_BUS_LOCK_DETECTION; + vmx->secondary_exec_control = exec_control; } @@ -4467,23 +4509,23 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmx_set_cr4(vcpu, 0); vmx_set_efer(vcpu, 0); - update_exception_bitmap(vcpu); + vmx_update_exception_bitmap(vcpu); vpid_sync_context(vmx->vpid); if (init_event) vmx_clear_hlt(vcpu); } -static void enable_irq_window(struct kvm_vcpu *vcpu) +static void vmx_enable_irq_window(struct kvm_vcpu *vcpu) { exec_controls_setbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); } -static void enable_nmi_window(struct kvm_vcpu *vcpu) +static void vmx_enable_nmi_window(struct kvm_vcpu *vcpu) { if (!enable_vnmi || vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) { - enable_irq_window(vcpu); + vmx_enable_irq_window(vcpu); return; } @@ -4824,7 +4866,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) kvm_queue_exception_p(vcpu, DB_VECTOR, dr6); return 1; } - kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1 | DR6_RTM; + kvm_run->debug.arch.dr6 = dr6 | DR6_ACTIVE_LOW; kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7); fallthrough; case BP_VECTOR: @@ -5049,6 +5091,7 @@ static int handle_dr(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; int dr, dr7, reg; + int err = 1; exit_qualification = vmx_get_exit_qual(vcpu); dr = exit_qualification & DEBUG_REG_ACCESS_NUM; @@ -5057,9 +5100,9 @@ static int handle_dr(struct kvm_vcpu *vcpu) if (!kvm_require_dr(vcpu, dr)) return 1; - /* Do not handle if the CPL > 0, will trigger GP on re-entry */ - if (!kvm_require_cpl(vcpu, 0)) - return 1; + if (kvm_x86_ops.get_cpl(vcpu) > 0) + goto out; + dr7 = vmcs_readl(GUEST_DR7); if (dr7 & DR7_GD) { /* @@ -5068,7 +5111,7 @@ static int handle_dr(struct kvm_vcpu *vcpu) * guest debugging itself. */ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { - vcpu->run->debug.arch.dr6 = DR6_BD | DR6_RTM | DR6_FIXED_1; + vcpu->run->debug.arch.dr6 = DR6_BD | DR6_ACTIVE_LOW; vcpu->run->debug.arch.dr7 = dr7; vcpu->run->debug.arch.pc = kvm_get_linear_rip(vcpu); vcpu->run->debug.arch.exception = DB_VECTOR; @@ -5096,14 +5139,15 @@ static int handle_dr(struct kvm_vcpu *vcpu) if (exit_qualification & TYPE_MOV_FROM_DR) { unsigned long val; - if (kvm_get_dr(vcpu, dr, &val)) - return 1; + kvm_get_dr(vcpu, dr, &val); kvm_register_write(vcpu, reg, val); - } else - if (kvm_set_dr(vcpu, dr, kvm_register_readl(vcpu, reg))) - return 1; + err = 0; + } else { + err = kvm_set_dr(vcpu, dr, kvm_register_readl(vcpu, reg)); + } - return kvm_skip_emulated_instruction(vcpu); +out: + return kvm_complete_insn_gp(vcpu, err); } static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) @@ -5177,9 +5221,8 @@ static int handle_xsetbv(struct kvm_vcpu *vcpu) u64 new_bv = kvm_read_edx_eax(vcpu); u32 index = kvm_rcx_read(vcpu); - if (kvm_set_xcr(vcpu, index, new_bv) == 0) - return kvm_skip_emulated_instruction(vcpu); - return 1; + int err = kvm_set_xcr(vcpu, index, new_bv); + return kvm_complete_insn_gp(vcpu, err); } static int handle_apic_access(struct kvm_vcpu *vcpu) @@ -5600,6 +5643,13 @@ static int handle_encls(struct kvm_vcpu *vcpu) return 1; } +static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu) +{ + vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK; + vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK; + return 0; +} + /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs @@ -5656,6 +5706,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_VMFUNC] = handle_vmx_instruction, [EXIT_REASON_PREEMPTION_TIMER] = handle_preemption_timer, [EXIT_REASON_ENCLS] = handle_encls, + [EXIT_REASON_BUS_LOCK] = handle_bus_lock_vmexit, }; static const int kvm_vmx_max_exit_handlers = @@ -5667,7 +5718,7 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2, struct vcpu_vmx *vmx = to_vmx(vcpu); *info1 = vmx_get_exit_qual(vcpu); - if (!(vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) { + if (!(vmx->exit_reason.failed_vmentry)) { *info2 = vmx->idt_vectoring_info; *intr_info = vmx_get_intr_info(vcpu); if (is_exception_with_error_code(*intr_info)) @@ -5720,24 +5771,6 @@ static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu) vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); } -/* - * Flush all vcpus' PML buffer and update logged GPAs to dirty_bitmap. - * Called before reporting dirty_bitmap to userspace. - */ -static void kvm_flush_pml_buffers(struct kvm *kvm) -{ - int i; - struct kvm_vcpu *vcpu; - /* - * We only need to kick vcpu out of guest mode here, as PML buffer - * is flushed at beginning of all VMEXITs, and it's obvious that only - * vcpus running in guest are possible to have unflushed GPAs in PML - * buffer. - */ - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vcpu_kick(vcpu); -} - static void vmx_dump_sel(char *name, uint32_t sel) { pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n", @@ -5908,20 +5941,22 @@ void dump_vmcs(void) * The guest has exited. See if we can fix it or if we need userspace * assistance. */ -static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) +static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) { struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 exit_reason = vmx->exit_reason; + union vmx_exit_reason exit_reason = vmx->exit_reason; u32 vectoring_info = vmx->idt_vectoring_info; + u16 exit_handler_index; /* * Flush logged GPAs PML buffer, this will make dirty_bitmap more * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before * querying dirty_bitmap, we only need to kick all vcpus out of guest * mode as if vcpus is in root mode, the PML buffer must has been - * flushed already. + * flushed already. Note, PML is never enabled in hardware while + * running L2. */ - if (enable_pml) + if (enable_pml && !is_guest_mode(vcpu)) vmx_flush_pml_buffer(vcpu); /* @@ -5938,6 +5973,13 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) if (is_guest_mode(vcpu)) { /* + * PML is never enabled when running L2, bail immediately if a + * PML full exit occurs as something is horribly wrong. + */ + if (exit_reason.basic == EXIT_REASON_PML_FULL) + goto unexpected_vmexit; + + /* * The host physical addresses of some pages of guest memory * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC * Page). The CPU may write to these pages via their host @@ -5954,11 +5996,11 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) return 1; } - if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) { + if (exit_reason.failed_vmentry) { dump_vmcs(); vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; vcpu->run->fail_entry.hardware_entry_failure_reason - = exit_reason; + = exit_reason.full; vcpu->run->fail_entry.cpu = vcpu->arch.last_vmentry_cpu; return 0; } @@ -5980,18 +6022,18 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) * will cause infinite loop. */ if ((vectoring_info & VECTORING_INFO_VALID_MASK) && - (exit_reason != EXIT_REASON_EXCEPTION_NMI && - exit_reason != EXIT_REASON_EPT_VIOLATION && - exit_reason != EXIT_REASON_PML_FULL && - exit_reason != EXIT_REASON_APIC_ACCESS && - exit_reason != EXIT_REASON_TASK_SWITCH)) { + (exit_reason.basic != EXIT_REASON_EXCEPTION_NMI && + exit_reason.basic != EXIT_REASON_EPT_VIOLATION && + exit_reason.basic != EXIT_REASON_PML_FULL && + exit_reason.basic != EXIT_REASON_APIC_ACCESS && + exit_reason.basic != EXIT_REASON_TASK_SWITCH)) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; vcpu->run->internal.ndata = 3; vcpu->run->internal.data[0] = vectoring_info; - vcpu->run->internal.data[1] = exit_reason; + vcpu->run->internal.data[1] = exit_reason.full; vcpu->run->internal.data[2] = vcpu->arch.exit_qualification; - if (exit_reason == EXIT_REASON_EPT_MISCONFIG) { + if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) { vcpu->run->internal.ndata++; vcpu->run->internal.data[3] = vmcs_read64(GUEST_PHYSICAL_ADDRESS); @@ -6023,42 +6065,62 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) if (exit_fastpath != EXIT_FASTPATH_NONE) return 1; - if (exit_reason >= kvm_vmx_max_exit_handlers) + if (exit_reason.basic >= kvm_vmx_max_exit_handlers) goto unexpected_vmexit; #ifdef CONFIG_RETPOLINE - if (exit_reason == EXIT_REASON_MSR_WRITE) + if (exit_reason.basic == EXIT_REASON_MSR_WRITE) return kvm_emulate_wrmsr(vcpu); - else if (exit_reason == EXIT_REASON_PREEMPTION_TIMER) + else if (exit_reason.basic == EXIT_REASON_PREEMPTION_TIMER) return handle_preemption_timer(vcpu); - else if (exit_reason == EXIT_REASON_INTERRUPT_WINDOW) + else if (exit_reason.basic == EXIT_REASON_INTERRUPT_WINDOW) return handle_interrupt_window(vcpu); - else if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) + else if (exit_reason.basic == EXIT_REASON_EXTERNAL_INTERRUPT) return handle_external_interrupt(vcpu); - else if (exit_reason == EXIT_REASON_HLT) + else if (exit_reason.basic == EXIT_REASON_HLT) return kvm_emulate_halt(vcpu); - else if (exit_reason == EXIT_REASON_EPT_MISCONFIG) + else if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) return handle_ept_misconfig(vcpu); #endif - exit_reason = array_index_nospec(exit_reason, - kvm_vmx_max_exit_handlers); - if (!kvm_vmx_exit_handlers[exit_reason]) + exit_handler_index = array_index_nospec((u16)exit_reason.basic, + kvm_vmx_max_exit_handlers); + if (!kvm_vmx_exit_handlers[exit_handler_index]) goto unexpected_vmexit; - return kvm_vmx_exit_handlers[exit_reason](vcpu); + return kvm_vmx_exit_handlers[exit_handler_index](vcpu); unexpected_vmexit: - vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", exit_reason); + vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", + exit_reason.full); dump_vmcs(); vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; vcpu->run->internal.ndata = 2; - vcpu->run->internal.data[0] = exit_reason; + vcpu->run->internal.data[0] = exit_reason.full; vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; return 0; } +static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) +{ + int ret = __vmx_handle_exit(vcpu, exit_fastpath); + + /* + * Even when current exit reason is handled by KVM internally, we + * still need to exit to user space when bus lock detected to inform + * that there is a bus lock in guest. + */ + if (to_vmx(vcpu)->exit_reason.bus_lock_detected) { + if (ret > 0) + vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK; + + vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK; + return 0; + } + return ret; +} + /* * Software based L1D cache flush which is used when microcode providing * the cache control MSR is not loaded. @@ -6129,7 +6191,7 @@ static noinstr void vmx_l1d_flush(struct kvm_vcpu *vcpu) : "eax", "ebx", "ecx", "edx"); } -static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) +static void vmx_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); int tpr_threshold; @@ -6373,9 +6435,9 @@ static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (vmx->exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) + if (vmx->exit_reason.basic == EXIT_REASON_EXTERNAL_INTERRUPT) handle_external_interrupt_irqoff(vcpu); - else if (vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI) + else if (vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI) handle_exception_nmi_irqoff(vmx); } @@ -6567,7 +6629,7 @@ void noinstr vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp) static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) { - switch (to_vmx(vcpu)->exit_reason) { + switch (to_vmx(vcpu)->exit_reason.basic) { case EXIT_REASON_MSR_WRITE: return handle_fastpath_set_msr_irqoff(vcpu); case EXIT_REASON_PREEMPTION_TIMER: @@ -6577,8 +6639,6 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) } } -bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, bool launched); - static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) { @@ -6638,11 +6698,9 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) { - fastpath_t exit_fastpath; struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long cr3, cr4; -reenter_guest: /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!enable_vnmi && vmx->loaded_vmcs->soft_vnmi_blocked)) @@ -6696,6 +6754,8 @@ reenter_guest: pt_guest_enter(vmx); atomic_switch_perf_msrs(vmx); + if (intel_pmu_lbr_is_enabled(vcpu)) + vmx_passthrough_lbr_msrs(vcpu); if (enable_preemption_timer) vmx_update_hv_timer(vcpu); @@ -6734,12 +6794,12 @@ reenter_guest: x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0); /* All fields are clean at this point */ - if (static_branch_unlikely(&enable_evmcs)) + if (static_branch_unlikely(&enable_evmcs)) { current_evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; - if (static_branch_unlikely(&enable_evmcs)) - current_evmcs->hv_vp_id = vcpu->arch.hyperv.vp_index; + current_evmcs->hv_vp_id = kvm_hv_get_vpindex(vcpu); + } /* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */ if (vmx->host_debugctlmsr) @@ -6768,21 +6828,23 @@ reenter_guest: vmx->idt_vectoring_info = 0; if (unlikely(vmx->fail)) { - vmx->exit_reason = 0xdead; + vmx->exit_reason.full = 0xdead; return EXIT_FASTPATH_NONE; } - vmx->exit_reason = vmcs_read32(VM_EXIT_REASON); - if (unlikely((u16)vmx->exit_reason == EXIT_REASON_MCE_DURING_VMENTRY)) + vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON); + if (unlikely((u16)vmx->exit_reason.basic == EXIT_REASON_MCE_DURING_VMENTRY)) kvm_machine_check(); - trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX); + if (likely(!vmx->exit_reason.failed_vmentry)) + vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); + + trace_kvm_exit(vmx->exit_reason.full, vcpu, KVM_ISA_VMX); - if (unlikely(vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) + if (unlikely(vmx->exit_reason.failed_vmentry)) return EXIT_FASTPATH_NONE; vmx->loaded_vmcs->launched = 1; - vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); vmx_recover_nmi_blocking(vmx); vmx_complete_interrupts(vmx); @@ -6790,22 +6852,7 @@ reenter_guest: if (is_guest_mode(vcpu)) return EXIT_FASTPATH_NONE; - exit_fastpath = vmx_exit_handlers_fastpath(vcpu); - if (exit_fastpath == EXIT_FASTPATH_REENTER_GUEST) { - if (!kvm_vcpu_exit_request(vcpu)) { - /* - * FIXME: this goto should be a loop in vcpu_enter_guest, - * but it would incur the cost of a retpoline for now. - * Revisit once static calls are available. - */ - if (vcpu->arch.apicv_active) - vmx_sync_pir_to_irr(vcpu); - goto reenter_guest; - } - exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED; - } - - return exit_fastpath; + return vmx_exit_handlers_fastpath(vcpu); } static void vmx_free_vcpu(struct kvm_vcpu *vcpu) @@ -7256,7 +7303,7 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) set_cr4_guest_host_mask(vmx); /* Refresh #PF interception to account for MAXPHYADDR changes. */ - update_exception_bitmap(vcpu); + vmx_update_exception_bitmap(vcpu); } static __init void vmx_set_cpu_caps(void) @@ -7270,8 +7317,8 @@ static __init void vmx_set_cpu_caps(void) /* CPUID 0x7 */ if (kvm_mpx_supported()) kvm_cpu_cap_check_and_set(X86_FEATURE_MPX); - if (cpu_has_vmx_invpcid()) - kvm_cpu_cap_check_and_set(X86_FEATURE_INVPCID); + if (!cpu_has_vmx_invpcid()) + kvm_cpu_cap_clear(X86_FEATURE_INVPCID); if (vmx_pt_mode_is_host_guest()) kvm_cpu_cap_check_and_set(X86_FEATURE_INTEL_PT); @@ -7449,30 +7496,24 @@ static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu) shrink_ple_window(vcpu); } -static void vmx_slot_enable_log_dirty(struct kvm *kvm, - struct kvm_memory_slot *slot) -{ - if (!kvm_dirty_log_manual_protect_and_init_set(kvm)) - kvm_mmu_slot_leaf_clear_dirty(kvm, slot); - kvm_mmu_slot_largepage_remove_write_access(kvm, slot); -} - -static void vmx_slot_disable_log_dirty(struct kvm *kvm, - struct kvm_memory_slot *slot) +void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu) { - kvm_mmu_slot_set_dirty(kvm, slot); -} + struct vcpu_vmx *vmx = to_vmx(vcpu); -static void vmx_flush_log_dirty(struct kvm *kvm) -{ - kvm_flush_pml_buffers(kvm); -} + if (is_guest_mode(vcpu)) { + vmx->nested.update_vmcs01_cpu_dirty_logging = true; + return; + } -static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm, - struct kvm_memory_slot *memslot, - gfn_t offset, unsigned long mask) -{ - kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask); + /* + * Note, cpu_dirty_logging_count can be changed concurrent with this + * code, but in that case another update request will be made and so + * the guest will never run with a stale PML value. + */ + if (vcpu->kvm->arch.cpu_dirty_logging_count) + secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_ENABLE_PML); + else + secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_ENABLE_PML); } static int vmx_pre_block(struct kvm_vcpu *vcpu) @@ -7546,7 +7587,7 @@ static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) return 0; } -static void enable_smi_window(struct kvm_vcpu *vcpu) +static void vmx_enable_smi_window(struct kvm_vcpu *vcpu) { /* RSM will cause a vmexit anyway. */ } @@ -7582,11 +7623,6 @@ static bool vmx_check_apicv_inhibit_reasons(ulong bit) return supported & BIT(bit); } -static int vmx_cpu_dirty_log_size(void) -{ - return enable_pml ? PML_ENTITY_NUM : 0; -} - static struct kvm_x86_ops vmx_x86_ops __initdata = { .hardware_unsetup = hardware_unsetup, @@ -7606,7 +7642,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .vcpu_load = vmx_vcpu_load, .vcpu_put = vmx_vcpu_put, - .update_exception_bitmap = update_exception_bitmap, + .update_exception_bitmap = vmx_update_exception_bitmap, .get_msr_feature = vmx_get_msr_feature, .get_msr = vmx_get_msr, .set_msr = vmx_set_msr, @@ -7649,9 +7685,9 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .nmi_allowed = vmx_nmi_allowed, .get_nmi_mask = vmx_get_nmi_mask, .set_nmi_mask = vmx_set_nmi_mask, - .enable_nmi_window = enable_nmi_window, - .enable_irq_window = enable_irq_window, - .update_cr8_intercept = update_cr8_intercept, + .enable_nmi_window = vmx_enable_nmi_window, + .enable_irq_window = vmx_enable_irq_window, + .update_cr8_intercept = vmx_update_cr8_intercept, .set_virtual_apic_mode = vmx_set_virtual_apic_mode, .set_apic_access_page_addr = vmx_set_apic_access_page_addr, .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, @@ -7686,10 +7722,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .sched_in = vmx_sched_in, - .slot_enable_log_dirty = vmx_slot_enable_log_dirty, - .slot_disable_log_dirty = vmx_slot_disable_log_dirty, - .flush_log_dirty = vmx_flush_log_dirty, - .enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked, + .cpu_dirty_log_size = PML_ENTITY_NUM, + .update_cpu_dirty_logging = vmx_update_cpu_dirty_logging, .pre_block = vmx_pre_block, .post_block = vmx_post_block, @@ -7709,7 +7743,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .smi_allowed = vmx_smi_allowed, .pre_enter_smm = vmx_pre_enter_smm, .pre_leave_smm = vmx_pre_leave_smm, - .enable_smi_window = enable_smi_window, + .enable_smi_window = vmx_enable_smi_window, .can_emulate_instruction = vmx_can_emulate_instruction, .apic_init_signal_blocked = vmx_apic_init_signal_blocked, @@ -7717,7 +7751,6 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .msr_filter_changed = vmx_msr_filter_changed, .complete_emulated_msr = kvm_complete_insn_gp, - .cpu_dirty_log_size = vmx_cpu_dirty_log_size, .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, }; @@ -7810,6 +7843,8 @@ static __init int hardware_setup(void) kvm_tsc_scaling_ratio_frac_bits = 48; } + kvm_has_bus_lock_exit = cpu_has_vmx_bus_lock_detection(); + set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ if (enable_ept) @@ -7832,13 +7867,8 @@ static __init int hardware_setup(void) if (!enable_ept || !enable_ept_ad_bits || !cpu_has_vmx_pml()) enable_pml = 0; - if (!enable_pml) { - vmx_x86_ops.slot_enable_log_dirty = NULL; - vmx_x86_ops.slot_disable_log_dirty = NULL; - vmx_x86_ops.flush_log_dirty = NULL; - vmx_x86_ops.enable_log_dirty_pt_masked = NULL; - vmx_x86_ops.cpu_dirty_log_size = NULL; - } + if (!enable_pml) + vmx_x86_ops.cpu_dirty_log_size = 0; if (!cpu_has_vmx_preemption_timer()) enable_preemption_timer = false; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 9d3a557949ac..89da5e1251f1 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -70,6 +70,54 @@ struct pt_desc { struct pt_ctx guest; }; +union vmx_exit_reason { + struct { + u32 basic : 16; + u32 reserved16 : 1; + u32 reserved17 : 1; + u32 reserved18 : 1; + u32 reserved19 : 1; + u32 reserved20 : 1; + u32 reserved21 : 1; + u32 reserved22 : 1; + u32 reserved23 : 1; + u32 reserved24 : 1; + u32 reserved25 : 1; + u32 bus_lock_detected : 1; + u32 enclave_mode : 1; + u32 smi_pending_mtf : 1; + u32 smi_from_vmx_root : 1; + u32 reserved30 : 1; + u32 failed_vmentry : 1; + }; + u32 full; +}; + +#define vcpu_to_lbr_desc(vcpu) (&to_vmx(vcpu)->lbr_desc) +#define vcpu_to_lbr_records(vcpu) (&to_vmx(vcpu)->lbr_desc.records) + +bool intel_pmu_lbr_is_compatible(struct kvm_vcpu *vcpu); +bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu); + +int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu); +void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu); + +struct lbr_desc { + /* Basic info about guest LBR records. */ + struct x86_pmu_lbr records; + + /* + * Emulate LBR feature via passthrough LBR registers when the + * per-vcpu guest LBR event is scheduled on the current pcpu. + * + * The records may be inaccurate if the host reclaims the LBR. + */ + struct perf_event *event; + + /* True if LBRs are marked as not intercepted in the MSR bitmap */ + bool msr_passthrough; +}; + /* * The nested_vmx structure is part of vcpu_vmx, and holds information we need * for correct emulation of VMX (i.e., nested VMX) on this vcpu. @@ -117,6 +165,7 @@ struct nested_vmx { bool change_vmcs01_virtual_apic_mode; bool reload_vmcs01_apic_access_page; + bool update_vmcs01_cpu_dirty_logging; /* * Enlightened VMCS has been enabled. It does not mean that L1 has to @@ -244,7 +293,7 @@ struct vcpu_vmx { int vpid; bool emulation_required; - u32 exit_reason; + union vmx_exit_reason exit_reason; /* Posted interrupt descriptor */ struct pi_desc pi_desc; @@ -279,6 +328,7 @@ struct vcpu_vmx { u64 ept_pointer; struct pt_desc pt_desc; + struct lbr_desc lbr_desc; /* Save desired MSR intercept (read: pass-through) state */ #define MAX_POSSIBLE_PASSTHROUGH_MSRS 13 @@ -329,7 +379,7 @@ void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa, int root_level); -void update_exception_bitmap(struct kvm_vcpu *vcpu); +void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu); void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu); bool vmx_nmi_blocked(struct kvm_vcpu *vcpu); bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu); @@ -339,8 +389,12 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu); struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr); void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu); void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp); +bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, bool launched); int vmx_find_loadstore_msr_slot(struct vmx_msrs *m, u32 msr); void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu); +void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, + u32 msr, int type, bool value); +void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu); static inline u8 vmx_get_rvi(void) { |