diff options
Diffstat (limited to 'arch/x86/kvm/vmx.c')
| -rw-r--r-- | arch/x86/kvm/vmx.c | 476 |
1 files changed, 314 insertions, 162 deletions
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 2b2fce1b2009..5c8879127cfa 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -418,6 +418,8 @@ struct vcpu_vmx { u64 msr_host_kernel_gs_base; u64 msr_guest_kernel_gs_base; #endif + u32 vm_entry_controls_shadow; + u32 vm_exit_controls_shadow; /* * loaded_vmcs points to the VMCS currently used in this vcpu. For a * non-nested (L1) guest, it always points to vmcs01. For a nested @@ -1056,7 +1058,9 @@ static inline bool is_exception(u32 intr_info) == (INTR_TYPE_HARD_EXCEPTION | INTR_INFO_VALID_MASK); } -static void nested_vmx_vmexit(struct kvm_vcpu *vcpu); +static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, + u32 exit_intr_info, + unsigned long exit_qualification); static void nested_vmx_entry_failure(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, u32 reason, unsigned long qualification); @@ -1326,6 +1330,62 @@ static void vmcs_set_bits(unsigned long field, u32 mask) vmcs_writel(field, vmcs_readl(field) | mask); } +static inline void vm_entry_controls_init(struct vcpu_vmx *vmx, u32 val) +{ + vmcs_write32(VM_ENTRY_CONTROLS, val); + vmx->vm_entry_controls_shadow = val; +} + +static inline void vm_entry_controls_set(struct vcpu_vmx *vmx, u32 val) +{ + if (vmx->vm_entry_controls_shadow != val) + vm_entry_controls_init(vmx, val); +} + +static inline u32 vm_entry_controls_get(struct vcpu_vmx *vmx) +{ + return vmx->vm_entry_controls_shadow; +} + + +static inline void vm_entry_controls_setbit(struct vcpu_vmx *vmx, u32 val) +{ + vm_entry_controls_set(vmx, vm_entry_controls_get(vmx) | val); +} + +static inline void vm_entry_controls_clearbit(struct vcpu_vmx *vmx, u32 val) +{ + vm_entry_controls_set(vmx, vm_entry_controls_get(vmx) & ~val); +} + +static inline void vm_exit_controls_init(struct vcpu_vmx *vmx, u32 val) +{ + vmcs_write32(VM_EXIT_CONTROLS, val); + vmx->vm_exit_controls_shadow = val; +} + +static inline void vm_exit_controls_set(struct vcpu_vmx *vmx, u32 val) +{ + if (vmx->vm_exit_controls_shadow != val) + vm_exit_controls_init(vmx, val); +} + +static inline u32 vm_exit_controls_get(struct vcpu_vmx *vmx) +{ + return vmx->vm_exit_controls_shadow; +} + + +static inline void vm_exit_controls_setbit(struct vcpu_vmx *vmx, u32 val) +{ + vm_exit_controls_set(vmx, vm_exit_controls_get(vmx) | val); +} + +static inline void vm_exit_controls_clearbit(struct vcpu_vmx *vmx, u32 val) +{ + vm_exit_controls_set(vmx, vm_exit_controls_get(vmx) & ~val); +} + static void vmx_segment_cache_clear(struct vcpu_vmx *vmx) { vmx->segment_cache.bitmask = 0; @@ -1410,11 +1470,11 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) vmcs_write32(EXCEPTION_BITMAP, eb); } -static void clear_atomic_switch_msr_special(unsigned long entry, - unsigned long exit) +static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, + unsigned long entry, unsigned long exit) { - vmcs_clear_bits(VM_ENTRY_CONTROLS, entry); - vmcs_clear_bits(VM_EXIT_CONTROLS, exit); + vm_entry_controls_clearbit(vmx, entry); + vm_exit_controls_clearbit(vmx, exit); } static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr) @@ -1425,14 +1485,15 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr) switch (msr) { case MSR_EFER: if (cpu_has_load_ia32_efer) { - clear_atomic_switch_msr_special(VM_ENTRY_LOAD_IA32_EFER, + clear_atomic_switch_msr_special(vmx, + VM_ENTRY_LOAD_IA32_EFER, VM_EXIT_LOAD_IA32_EFER); return; } break; case MSR_CORE_PERF_GLOBAL_CTRL: if (cpu_has_load_perf_global_ctrl) { - clear_atomic_switch_msr_special( + clear_atomic_switch_msr_special(vmx, VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL, VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL); return; @@ -1453,14 +1514,15 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr) vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr); } -static void add_atomic_switch_msr_special(unsigned long entry, - unsigned long exit, unsigned long guest_val_vmcs, - unsigned long host_val_vmcs, u64 guest_val, u64 host_val) +static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx, + unsigned long entry, unsigned long exit, + unsigned long guest_val_vmcs, unsigned long host_val_vmcs, + u64 guest_val, u64 host_val) { vmcs_write64(guest_val_vmcs, guest_val); vmcs_write64(host_val_vmcs, host_val); - vmcs_set_bits(VM_ENTRY_CONTROLS, entry); - vmcs_set_bits(VM_EXIT_CONTROLS, exit); + vm_entry_controls_setbit(vmx, entry); + vm_exit_controls_setbit(vmx, exit); } static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, @@ -1472,7 +1534,8 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, switch (msr) { case MSR_EFER: if (cpu_has_load_ia32_efer) { - add_atomic_switch_msr_special(VM_ENTRY_LOAD_IA32_EFER, + add_atomic_switch_msr_special(vmx, + VM_ENTRY_LOAD_IA32_EFER, VM_EXIT_LOAD_IA32_EFER, GUEST_IA32_EFER, HOST_IA32_EFER, @@ -1482,7 +1545,7 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, break; case MSR_CORE_PERF_GLOBAL_CTRL: if (cpu_has_load_perf_global_ctrl) { - add_atomic_switch_msr_special( + add_atomic_switch_msr_special(vmx, VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL, VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL, GUEST_IA32_PERF_GLOBAL_CTRL, @@ -1498,7 +1561,7 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, break; if (i == NR_AUTOLOAD_MSRS) { - printk_once(KERN_WARNING"Not enough mst switch entries. " + printk_once(KERN_WARNING "Not enough msr switch entries. " "Can't add msr %x\n", msr); return; } else if (i == m->nr) { @@ -1898,19 +1961,17 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) /* * KVM wants to inject page-faults which it got to the guest. This function * checks whether in a nested guest, we need to inject them to L1 or L2. - * This function assumes it is called with the exit reason in vmcs02 being - * a #PF exception (this is the only case in which KVM injects a #PF when L2 - * is running). */ -static int nested_pf_handled(struct kvm_vcpu *vcpu) +static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - /* TODO: also check PFEC_MATCH/MASK, not just EB.PF. */ - if (!(vmcs12->exception_bitmap & (1u << PF_VECTOR))) + if (!(vmcs12->exception_bitmap & (1u << nr))) return 0; - nested_vmx_vmexit(vcpu); + nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason, + vmcs_read32(VM_EXIT_INTR_INFO), + vmcs_readl(EXIT_QUALIFICATION)); return 1; } @@ -1921,8 +1982,8 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, struct vcpu_vmx *vmx = to_vmx(vcpu); u32 intr_info = nr | INTR_INFO_VALID_MASK; - if (nr == PF_VECTOR && is_guest_mode(vcpu) && - !vmx->nested.nested_run_pending && nested_pf_handled(vcpu)) + if (!reinject && is_guest_mode(vcpu) && + nested_vmx_check_exception(vcpu, nr)) return; if (has_error_code) { @@ -2204,9 +2265,15 @@ static __init void nested_vmx_setup_ctls_msrs(void) #ifdef CONFIG_X86_64 VM_EXIT_HOST_ADDR_SPACE_SIZE | #endif - VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT; + VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT | + VM_EXIT_SAVE_VMX_PREEMPTION_TIMER; + if (!(nested_vmx_pinbased_ctls_high & PIN_BASED_VMX_PREEMPTION_TIMER) || + !(nested_vmx_exit_ctls_high & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER)) { + nested_vmx_exit_ctls_high &= ~VM_EXIT_SAVE_VMX_PREEMPTION_TIMER; + nested_vmx_pinbased_ctls_high &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + } nested_vmx_exit_ctls_high |= (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | - VM_EXIT_LOAD_IA32_EFER); + VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER); /* entry controls */ rdmsr(MSR_IA32_VMX_ENTRY_CTLS, @@ -2226,7 +2293,8 @@ static __init void nested_vmx_setup_ctls_msrs(void) nested_vmx_procbased_ctls_low, nested_vmx_procbased_ctls_high); nested_vmx_procbased_ctls_low = 0; nested_vmx_procbased_ctls_high &= - CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_USE_TSC_OFFSETING | + CPU_BASED_VIRTUAL_INTR_PENDING | + CPU_BASED_VIRTUAL_NMI_PENDING | CPU_BASED_USE_TSC_OFFSETING | CPU_BASED_HLT_EXITING | CPU_BASED_INVLPG_EXITING | CPU_BASED_MWAIT_EXITING | CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING | @@ -2252,13 +2320,15 @@ static __init void nested_vmx_setup_ctls_msrs(void) nested_vmx_secondary_ctls_low = 0; nested_vmx_secondary_ctls_high &= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_UNRESTRICTED_GUEST | SECONDARY_EXEC_WBINVD_EXITING; if (enable_ept) { /* nested EPT: emulate EPT also to L1 */ nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT; nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT | - VMX_EPTP_WB_BIT | VMX_EPT_INVEPT_BIT; + VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT | + VMX_EPT_INVEPT_BIT; nested_vmx_ept_caps &= vmx_capability.ept; /* * Since invept is completely emulated we support both global @@ -2274,6 +2344,7 @@ static __init void nested_vmx_setup_ctls_msrs(void) rdmsr(MSR_IA32_VMX_MISC, nested_vmx_misc_low, nested_vmx_misc_high); nested_vmx_misc_low &= VMX_MISC_PREEMPTION_TIMER_RATE_MASK | VMX_MISC_SAVE_EFER_LMA; + nested_vmx_misc_low |= VMX_MISC_ACTIVITY_HLT; nested_vmx_misc_high = 0; } @@ -2290,32 +2361,10 @@ static inline u64 vmx_control_msr(u32 low, u32 high) return low | ((u64)high << 32); } -/* - * If we allow our guest to use VMX instructions (i.e., nested VMX), we should - * also let it use VMX-specific MSRs. - * vmx_get_vmx_msr() and vmx_set_vmx_msr() return 1 when we handled a - * VMX-specific MSR, or 0 when we haven't (and the caller should handle it - * like all other MSRs). - */ +/* Returns 0 on success, non-0 otherwise. */ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) { - if (!nested_vmx_allowed(vcpu) && msr_index >= MSR_IA32_VMX_BASIC && - msr_index <= MSR_IA32_VMX_TRUE_ENTRY_CTLS) { - /* - * According to the spec, processors which do not support VMX - * should throw a #GP(0) when VMX capability MSRs are read. - */ - kvm_queue_exception_e(vcpu, GP_VECTOR, 0); - return 1; - } - switch (msr_index) { - case MSR_IA32_FEATURE_CONTROL: - if (nested_vmx_allowed(vcpu)) { - *pdata = to_vmx(vcpu)->nested.msr_ia32_feature_control; - break; - } - return 0; case MSR_IA32_VMX_BASIC: /* * This MSR reports some information about VMX support. We @@ -2382,34 +2431,9 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) *pdata = nested_vmx_ept_caps; break; default: - return 0; - } - - return 1; -} - -static int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) -{ - u32 msr_index = msr_info->index; - u64 data = msr_info->data; - bool host_initialized = msr_info->host_initiated; - - if (!nested_vmx_allowed(vcpu)) - return 0; - - if (msr_index == MSR_IA32_FEATURE_CONTROL) { - if (!host_initialized && - to_vmx(vcpu)->nested.msr_ia32_feature_control - & FEATURE_CONTROL_LOCKED) - return 0; - to_vmx(vcpu)->nested.msr_ia32_feature_control = data; return 1; } - /* - * No need to treat VMX capability MSRs specially: If we don't handle - * them, handle_wrmsr will #GP(0), which is correct (they are readonly) - */ return 0; } @@ -2455,13 +2479,20 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) case MSR_IA32_SYSENTER_ESP: data = vmcs_readl(GUEST_SYSENTER_ESP); break; + case MSR_IA32_FEATURE_CONTROL: + if (!nested_vmx_allowed(vcpu)) + return 1; + data = to_vmx(vcpu)->nested.msr_ia32_feature_control; + break; + case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: + if (!nested_vmx_allowed(vcpu)) + return 1; + return vmx_get_vmx_msr(vcpu, msr_index, pdata); case MSR_TSC_AUX: if (!to_vmx(vcpu)->rdtscp_enabled) return 1; /* Otherwise falls through */ default: - if (vmx_get_vmx_msr(vcpu, msr_index, pdata)) - return 0; msr = find_msr_entry(to_vmx(vcpu), msr_index); if (msr) { data = msr->data; @@ -2474,6 +2505,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) return 0; } +static void vmx_leave_nested(struct kvm_vcpu *vcpu); + /* * Writes msr value into into the appropriate "register". * Returns 0 on success, non-0 otherwise. @@ -2528,6 +2561,17 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_TSC_ADJUST: ret = kvm_set_msr_common(vcpu, msr_info); break; + case MSR_IA32_FEATURE_CONTROL: + if (!nested_vmx_allowed(vcpu) || + (to_vmx(vcpu)->nested.msr_ia32_feature_control & + FEATURE_CONTROL_LOCKED && !msr_info->host_initiated)) + return 1; + vmx->nested.msr_ia32_feature_control = data; + if (msr_info->host_initiated && data == 0) + vmx_leave_nested(vcpu); + break; + case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: + return 1; /* they are read-only */ case MSR_TSC_AUX: if (!vmx->rdtscp_enabled) return 1; @@ -2536,8 +2580,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; /* Otherwise falls through */ default: - if (vmx_set_vmx_msr(vcpu, msr_info)) - break; msr = find_msr_entry(vmx, msr_index); if (msr) { msr->data = data; @@ -3177,14 +3219,10 @@ static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) vmx_load_host_state(to_vmx(vcpu)); vcpu->arch.efer = efer; if (efer & EFER_LMA) { - vmcs_write32(VM_ENTRY_CONTROLS, - vmcs_read32(VM_ENTRY_CONTROLS) | - VM_ENTRY_IA32E_MODE); + vm_entry_controls_setbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE); msr->data = efer; } else { - vmcs_write32(VM_ENTRY_CONTROLS, - vmcs_read32(VM_ENTRY_CONTROLS) & - ~VM_ENTRY_IA32E_MODE); + vm_entry_controls_clearbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE); msr->data = efer & ~EFER_LME; } @@ -3212,9 +3250,7 @@ static void enter_lmode(struct kvm_vcpu *vcpu) static void exit_lmode(struct kvm_vcpu *vcpu) { - vmcs_write32(VM_ENTRY_CONTROLS, - vmcs_read32(VM_ENTRY_CONTROLS) - & ~VM_ENTRY_IA32E_MODE); + vm_entry_controls_clearbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE); vmx_set_efer(vcpu, vcpu->arch.efer & ~EFER_LMA); } @@ -3380,8 +3416,10 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) if (enable_ept) { eptp = construct_eptp(cr3); vmcs_write64(EPT_POINTER, eptp); - guest_cr3 = is_paging(vcpu) ? kvm_read_cr3(vcpu) : - vcpu->kvm->arch.ept_identity_map_addr; + if (is_paging(vcpu) || is_guest_mode(vcpu)) + guest_cr3 = kvm_read_cr3(vcpu); + else + guest_cr3 = vcpu->kvm->arch.ept_identity_map_addr; ept_load_pdptrs(vcpu); } @@ -4339,10 +4377,11 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) ++vmx->nmsrs; } - vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl); + + vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl); /* 22.2.1, 20.8.1 */ - vmcs_write32(VM_ENTRY_CONTROLS, vmcs_config.vmentry_ctrl); + vm_entry_controls_init(vmx, vmcs_config.vmentry_ctrl); vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL); set_cr4_guest_host_mask(vmx); @@ -4581,15 +4620,12 @@ static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu)) { - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - if (to_vmx(vcpu)->nested.nested_run_pending) return 0; if (nested_exit_on_nmi(vcpu)) { - nested_vmx_vmexit(vcpu); - vmcs12->vm_exit_reason = EXIT_REASON_EXCEPTION_NMI; - vmcs12->vm_exit_intr_info = NMI_VECTOR | - INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK; + nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, + NMI_VECTOR | INTR_TYPE_NMI_INTR | + INTR_INFO_VALID_MASK, 0); /* * The NMI-triggered VM exit counts as injection: * clear this one and block further NMIs. @@ -4611,15 +4647,11 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu)) { - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - if (to_vmx(vcpu)->nested.nested_run_pending) return 0; if (nested_exit_on_intr(vcpu)) { - nested_vmx_vmexit(vcpu); - vmcs12->vm_exit_reason = - EXIT_REASON_EXTERNAL_INTERRUPT; - vmcs12->vm_exit_intr_info = 0; + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, + 0, 0); /* * fall through to normal code, but now in L1, not L2 */ @@ -4805,7 +4837,8 @@ static int handle_exception(struct kvm_vcpu *vcpu) dr6 = vmcs_readl(EXIT_QUALIFICATION); if (!(vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { - vcpu->arch.dr6 = dr6 | DR6_FIXED_1; + vcpu->arch.dr6 &= ~15; + vcpu->arch.dr6 |= dr6; kvm_queue_exception(vcpu, DB_VECTOR); return 1; } @@ -4879,6 +4912,17 @@ vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) hypercall[2] = 0xc1; } +static bool nested_cr0_valid(struct vmcs12 *vmcs12, unsigned long val) +{ + unsigned long always_on = VMXON_CR0_ALWAYSON; + + if (nested_vmx_secondary_ctls_high & + SECONDARY_EXEC_UNRESTRICTED_GUEST && + nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST)) + always_on &= ~(X86_CR0_PE | X86_CR0_PG); + return (val & always_on) == always_on; +} + /* called to set cr0 as appropriate for a mov-to-cr0 exit. */ static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val) { @@ -4897,9 +4941,7 @@ static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val) val = (val & ~vmcs12->cr0_guest_host_mask) | (vmcs12->guest_cr0 & vmcs12->cr0_guest_host_mask); - /* TODO: will have to take unrestricted guest mode into - * account */ - if ((val & VMXON_CR0_ALWAYSON) != VMXON_CR0_ALWAYSON) + if (!nested_cr0_valid(vmcs12, val)) return 1; if (kvm_set_cr0(vcpu, val)) @@ -5064,14 +5106,27 @@ static int handle_dr(struct kvm_vcpu *vcpu) reg = DEBUG_REG_ACCESS_REG(exit_qualification); if (exit_qualification & TYPE_MOV_FROM_DR) { unsigned long val; - if (!kvm_get_dr(vcpu, dr, &val)) - kvm_register_write(vcpu, reg, val); + + if (kvm_get_dr(vcpu, dr, &val)) + return 1; + kvm_register_write(vcpu, reg, val); } else - kvm_set_dr(vcpu, dr, vcpu->arch.regs[reg]); + if (kvm_set_dr(vcpu, dr, vcpu->arch.regs[reg])) + return 1; + skip_emulated_instruction(vcpu); return 1; } +static u64 vmx_get_dr6(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.dr6; +} + +static void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val) +{ +} + static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) { vmcs_writel(GUEST_DR7, val); @@ -6444,11 +6499,8 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, int size; u8 b; - if (nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING)) - return 1; - if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) - return 0; + return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); exit_qualification = vmcs_readl(EXIT_QUALIFICATION); @@ -6612,6 +6664,13 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) struct vmcs12 *vmcs12 = get_vmcs12(vcpu); u32 exit_reason = vmx->exit_reason; + trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason, + vmcs_readl(EXIT_QUALIFICATION), + vmx->idt_vectoring_info, + intr_info, + vmcs_read32(VM_EXIT_INTR_ERROR_CODE), + KVM_ISA_VMX); + if (vmx->nested.nested_run_pending) return 0; @@ -6627,6 +6686,9 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) return 0; else if (is_page_fault(intr_info)) return enable_ept; + else if (is_no_device(intr_info) && + !(nested_read_cr0(vmcs12) & X86_CR0_TS)) + return 0; return vmcs12->exception_bitmap & (1u << (intr_info & INTR_INFO_VECTOR_MASK)); case EXIT_REASON_EXTERNAL_INTERRUPT: @@ -6722,6 +6784,27 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2) *info2 = vmcs_read32(VM_EXIT_INTR_INFO); } +static void nested_adjust_preemption_timer(struct kvm_vcpu *vcpu) +{ + u64 delta_tsc_l1; + u32 preempt_val_l1, preempt_val_l2, preempt_scale; + + if (!(get_vmcs12(vcpu)->pin_based_vm_exec_control & + PIN_BASED_VMX_PREEMPTION_TIMER)) + return; + preempt_scale = native_read_msr(MSR_IA32_VMX_MISC) & + MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE; + preempt_val_l2 = vmcs_read32(VMX_PREEMPTION_TIMER_VALUE); + delta_tsc_l1 = vmx_read_l1_tsc(vcpu, native_read_tsc()) + - vcpu->arch.last_guest_tsc; + preempt_val_l1 = delta_tsc_l1 >> preempt_scale; + if (preempt_val_l2 <= preempt_val_l1) + preempt_val_l2 = 0; + else + preempt_val_l2 -= preempt_val_l1; + vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, preempt_val_l2); +} + /* * The guest has exited. See if we can fix it or if we need userspace * assistance. @@ -6736,22 +6819,10 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) if (vmx->emulation_required) return handle_invalid_guest_state(vcpu); - /* - * the KVM_REQ_EVENT optimization bit is only on for one entry, and if - * we did not inject a still-pending event to L1 now because of - * nested_run_pending, we need to re-enable this bit. - */ - if (vmx->nested.nested_run_pending) - kvm_make_request(KVM_REQ_EVENT, vcpu); - - if (!is_guest_mode(vcpu) && (exit_reason == EXIT_REASON_VMLAUNCH || - exit_reason == EXIT_REASON_VMRESUME)) - vmx->nested.nested_run_pending = 1; - else - vmx->nested.nested_run_pending = 0; - if (is_guest_mode(vcpu) && nested_vmx_exit_handled(vcpu)) { - nested_vmx_vmexit(vcpu); + nested_vmx_vmexit(vcpu, exit_reason, + vmcs_read32(VM_EXIT_INTR_INFO), + vmcs_readl(EXIT_QUALIFICATION)); return 1; } @@ -7061,9 +7132,9 @@ static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu, case INTR_TYPE_HARD_EXCEPTION: if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) { u32 err = vmcs_read32(error_code_field); - kvm_queue_exception_e(vcpu, vector, err); + kvm_requeue_exception_e(vcpu, vector, err); } else - kvm_queue_exception(vcpu, vector); + kvm_requeue_exception(vcpu, vector); break; case INTR_TYPE_SOFT_INTR: vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); @@ -7146,6 +7217,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) atomic_switch_perf_msrs(vmx); debugctlmsr = get_debugctlmsr(); + if (is_guest_mode(vcpu) && !vmx->nested.nested_run_pending) + nested_adjust_preemption_timer(vcpu); vmx->__launched = vmx->loaded_vmcs->launched; asm( /* Store host registers */ @@ -7284,6 +7357,16 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->exit_reason = vmcs_read32(VM_EXIT_REASON); trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX); + /* + * the KVM_REQ_EVENT optimization bit is only on for one entry, and if + * we did not inject a still-pending event to L1 now because of + * nested_run_pending, we need to re-enable this bit. + */ + if (vmx->nested.nested_run_pending) + kvm_make_request(KVM_REQ_EVENT, vcpu); + + vmx->nested.nested_run_pending = 0; + vmx_complete_atomic_exit(vmx); vmx_recover_nmi_blocking(vmx); vmx_complete_interrupts(vmx); @@ -7294,8 +7377,8 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); free_vpid(vmx); - free_nested(vmx); free_loaded_vmcs(vmx->loaded_vmcs); + free_nested(vmx); kfree(vmx->guest_msrs); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, vmx); @@ -7410,8 +7493,7 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) */ if (is_mmio) ret = MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT; - else if (vcpu->kvm->arch.iommu_domain && - !(vcpu->kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY)) + else if (kvm_arch_has_noncoherent_dma(vcpu->kvm)) ret = kvm_get_guest_memory_type(vcpu, gfn) << VMX_EPT_MT_EPTE_SHIFT; else @@ -7481,15 +7563,14 @@ static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { - struct vmcs12 *vmcs12; - nested_vmx_vmexit(vcpu); - vmcs12 = get_vmcs12(vcpu); + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + u32 exit_reason; if (fault->error_code & PFERR_RSVD_MASK) - vmcs12->vm_exit_reason = EXIT_REASON_EPT_MISCONFIG; + exit_reason = EXIT_REASON_EPT_MISCONFIG; else - vmcs12->vm_exit_reason = EXIT_REASON_EPT_VIOLATION; - vmcs12->exit_qualification = vcpu->arch.exit_qualification; + exit_reason = EXIT_REASON_EPT_VIOLATION; + nested_vmx_vmexit(vcpu, exit_reason, 0, vcpu->arch.exit_qualification); vmcs12->guest_physical_address = fault->address; } @@ -7501,9 +7582,9 @@ static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu) return get_vmcs12(vcpu)->ept_pointer; } -static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu) +static void nested_ept_init_mmu_context(struct kvm_vcpu *vcpu) { - int r = kvm_init_shadow_ept_mmu(vcpu, &vcpu->arch.mmu, + kvm_init_shadow_ept_mmu(vcpu, &vcpu->arch.mmu, nested_vmx_ept_caps & VMX_EPT_EXECUTE_ONLY_BIT); vcpu->arch.mmu.set_cr3 = vmx_set_cr3; @@ -7511,8 +7592,6 @@ static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu) vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault; vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu; - - return r; } static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu) @@ -7520,6 +7599,22 @@ static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu) vcpu->arch.walk_mmu = &vcpu->arch.mmu; } +static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, + struct x86_exception *fault) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + + WARN_ON(!is_guest_mode(vcpu)); + + /* TODO: also check PFEC_MATCH/MASK, not just EB.PF. */ + if (vmcs12->exception_bitmap & (1u << PF_VECTOR)) + nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason, + vmcs_read32(VM_EXIT_INTR_INFO), + vmcs_readl(EXIT_QUALIFICATION)); + else + kvm_inject_page_fault(vcpu, fault); +} + /* * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it @@ -7533,6 +7628,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 exec_control; + u32 exit_control; vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector); vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector); @@ -7656,6 +7752,11 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) else vmcs_write64(APIC_ACCESS_ADDR, page_to_phys(vmx->nested.apic_access_page)); + } else if (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm)) { + exec_control |= + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + vmcs_write64(APIC_ACCESS_ADDR, + page_to_phys(vcpu->kvm->arch.apic_access_page)); } vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); @@ -7706,12 +7807,15 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER * bits are further modified by vmx_set_efer() below. */ - vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl); + exit_control = vmcs_config.vmexit_ctrl; + if (vmcs12->pin_based_vm_exec_control & PIN_BASED_VMX_PREEMPTION_TIMER) + exit_control |= VM_EXIT_SAVE_VMX_PREEMPTION_TIMER; + vm_exit_controls_init(vmx, exit_control); /* vmcs12's VM_ENTRY_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE are * emulated by vmx_set_efer(), below. */ - vmcs_write32(VM_ENTRY_CONTROLS, + vm_entry_controls_init(vmx, (vmcs12->vm_entry_controls & ~VM_ENTRY_LOAD_IA32_EFER & ~VM_ENTRY_IA32E_MODE) | (vmcs_config.vmentry_ctrl & ~VM_ENTRY_IA32E_MODE)); @@ -7773,6 +7877,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) kvm_set_cr3(vcpu, vmcs12->guest_cr3); kvm_mmu_reset_context(vcpu); + if (!enable_ept) + vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested; + /* * L1 may access the L2's PDPTR, so save them to construct vmcs12 */ @@ -7826,7 +7933,8 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) return 1; } - if (vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE) { + if (vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE && + vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT) { nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); return 1; } @@ -7876,7 +7984,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) return 1; } - if (((vmcs12->guest_cr0 & VMXON_CR0_ALWAYSON) != VMXON_CR0_ALWAYSON) || + if (!nested_cr0_valid(vmcs12, vmcs12->guest_cr0) || ((vmcs12->guest_cr4 & VMXON_CR4_ALWAYSON) != VMXON_CR4_ALWAYSON)) { nested_vmx_entry_failure(vcpu, vmcs12, EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT); @@ -7953,6 +8061,11 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) prepare_vmcs02(vcpu, vmcs12); + if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) + return kvm_emulate_halt(vcpu); + + vmx->nested.nested_run_pending = 1; + /* * Note no nested_vmx_succeed or nested_vmx_fail here. At this point * we are no longer running L1, and VMLAUNCH/VMRESUME has not yet @@ -8005,7 +8118,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu, u32 idt_vectoring; unsigned int nr; - if (vcpu->arch.exception.pending) { + if (vcpu->arch.exception.pending && vcpu->arch.exception.reinject) { nr = vcpu->arch.exception.nr; idt_vectoring = nr | VECTORING_INFO_VALID_MASK; @@ -8023,7 +8136,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu, } vmcs12->idt_vectoring_info_field = idt_vectoring; - } else if (vcpu->arch.nmi_pending) { + } else if (vcpu->arch.nmi_injected) { vmcs12->idt_vectoring_info_field = INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR; } else if (vcpu->arch.interrupt.pending) { @@ -8052,7 +8165,9 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu, * exit-information fields only. Other fields are modified by L1 with VMWRITE, * which already writes to vmcs12 directly. */ -static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) +static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, + u32 exit_reason, u32 exit_intr_info, + unsigned long exit_qualification) { /* update guest state fields: */ vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12); @@ -8104,6 +8219,15 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); vmcs12->guest_pending_dbg_exceptions = vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS); + if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) + vmcs12->guest_activity_state = GUEST_ACTIVITY_HLT; + else + vmcs12->guest_activity_state = GUEST_ACTIVITY_ACTIVE; + + if ((vmcs12->pin_based_vm_exec_control & PIN_BASED_VMX_PREEMPTION_TIMER) && + (vmcs12->vm_exit_controls & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER)) + vmcs12->vmx_preemption_timer_value = + vmcs_read32(VMX_PREEMPTION_TIMER_VALUE); /* * In some cases (usually, nested EPT), L2 is allowed to change its @@ -8123,23 +8247,25 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->vm_entry_controls = (vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) | - (vmcs_read32(VM_ENTRY_CONTROLS) & VM_ENTRY_IA32E_MODE); + (vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE); /* TODO: These cannot have changed unless we have MSR bitmaps and * the relevant bit asks not to trap the change */ vmcs12->guest_ia32_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_PAT) vmcs12->guest_ia32_pat = vmcs_read64(GUEST_IA32_PAT); + if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_EFER) + vmcs12->guest_ia32_efer = vcpu->arch.efer; vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS); vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP); vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP); /* update exit information fields: */ - vmcs12->vm_exit_reason = to_vmx(vcpu)->exit_reason; - vmcs12->exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + vmcs12->vm_exit_reason = exit_reason; + vmcs12->exit_qualification = exit_qualification; - vmcs12->vm_exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); + vmcs12->vm_exit_intr_info = exit_intr_info; if ((vmcs12->vm_exit_intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) == (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) @@ -8201,7 +8327,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * fpu_active (which may have changed). * Note that vmx_set_cr0 refers to efer set above. */ - kvm_set_cr0(vcpu, vmcs12->host_cr0); + vmx_set_cr0(vcpu, vmcs12->host_cr0); /* * If we did fpu_activate()/fpu_deactivate() during L2's run, we need * to apply the same changes to L1's vmcs. We just set cr0 correctly, @@ -8218,12 +8344,14 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); kvm_set_cr4(vcpu, vmcs12->host_cr4); - if (nested_cpu_has_ept(vmcs12)) - nested_ept_uninit_mmu_context(vcpu); + nested_ept_uninit_mmu_context(vcpu); kvm_set_cr3(vcpu, vmcs12->host_cr3); kvm_mmu_reset_context(vcpu); + if (!enable_ept) + vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault; + if (enable_vpid) { /* * Trivially support vpid by letting L2s share their parent @@ -8303,7 +8431,9 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * and modify vmcs12 to make it see what it would expect to see there if * L2 was its real guest. Must only be called when in L2 (is_guest_mode()) */ -static void nested_vmx_vmexit(struct kvm_vcpu *vcpu) +static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, + u32 exit_intr_info, + unsigned long exit_qualification) { struct vcpu_vmx *vmx = to_vmx(vcpu); int cpu; @@ -8313,7 +8443,15 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu) WARN_ON_ONCE(vmx->nested.nested_run_pending); leave_guest_mode(vcpu); - prepare_vmcs12(vcpu, vmcs12); + prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info, + exit_qualification); + + trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason, + vmcs12->exit_qualification, + vmcs12->idt_vectoring_info_field, + vmcs12->vm_exit_intr_info, + vmcs12->vm_exit_intr_error_code, + KVM_ISA_VMX); cpu = get_cpu(); vmx->loaded_vmcs = &vmx->vmcs01; @@ -8322,6 +8460,8 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu) vcpu->cpu = cpu; put_cpu(); + vm_entry_controls_init(vmx, vmcs_read32(VM_ENTRY_CONTROLS)); + vm_exit_controls_init(vmx, vmcs_read32(VM_EXIT_CONTROLS)); vmx_segment_cache_clear(vmx); /* if no vmcs02 cache requested, remove the one we used */ @@ -8357,6 +8497,16 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu) } /* + * Forcibly leave nested mode in order to be able to reset the VCPU later on. + */ +static void vmx_leave_nested(struct kvm_vcpu *vcpu) +{ + if (is_guest_mode(vcpu)) + nested_vmx_vmexit(vcpu, -1, 0, 0); + free_nested(to_vmx(vcpu)); +} + +/* * L1's failure to enter L2 is a subset of a normal exit, as explained in * 23.7 "VM-entry failures during or after loading guest state" (this also * lists the acceptable exit-reason and exit-qualification parameters). @@ -8419,6 +8569,8 @@ static struct kvm_x86_ops vmx_x86_ops = { .set_idt = vmx_set_idt, .get_gdt = vmx_get_gdt, .set_gdt = vmx_set_gdt, + .get_dr6 = vmx_get_dr6, + .set_dr6 = vmx_set_dr6, .set_dr7 = vmx_set_dr7, .cache_reg = vmx_cache_reg, .get_rflags = vmx_get_rflags, |