diff options
Diffstat (limited to 'arch/x86/kvm/vmx.c')
| -rw-r--r-- | arch/x86/kvm/vmx.c | 654 |
1 files changed, 431 insertions, 223 deletions
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index da7837e..1320e0f 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -31,6 +31,7 @@ #include <linux/ftrace_event.h> #include <linux/slab.h> #include <linux/tboot.h> +#include <linux/hrtimer.h> #include "kvm_cache_regs.h" #include "x86.h" @@ -42,6 +43,7 @@ #include <asm/i387.h> #include <asm/xcr.h> #include <asm/perf_event.h> +#include <asm/debugreg.h> #include <asm/kexec.h> #include "trace.h" @@ -110,6 +112,8 @@ module_param(nested, bool, S_IRUGO); #define RMODE_GUEST_OWNED_EFLAGS_BITS (~(X86_EFLAGS_IOPL | X86_EFLAGS_VM)) +#define VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE 5 + /* * These 2 parameters are used to config the controls for Pause-Loop Exiting: * ple_gap: upper bound on the amount of time between two successive @@ -202,6 +206,7 @@ struct __packed vmcs12 { u64 guest_pdptr1; u64 guest_pdptr2; u64 guest_pdptr3; + u64 guest_bndcfgs; u64 host_ia32_pat; u64 host_ia32_efer; u64 host_ia32_perf_global_ctrl; @@ -374,6 +379,9 @@ struct nested_vmx { */ struct page *apic_access_page; u64 msr_ia32_feature_control; + + struct hrtimer preemption_timer; + bool preemption_timer_expired; }; #define POSTED_INTR_ON 0 @@ -418,6 +426,8 @@ 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 @@ -439,6 +449,7 @@ struct vcpu_vmx { #endif int gs_ldt_reload_needed; int fs_reload_needed; + u64 msr_host_bndcfgs; } host_state; struct { int vm86_active; @@ -531,6 +542,7 @@ static const unsigned long shadow_read_write_fields[] = { GUEST_CS_LIMIT, GUEST_CS_BASE, GUEST_ES_BASE, + GUEST_BNDCFGS, CR0_GUEST_HOST_MASK, CR0_READ_SHADOW, CR4_READ_SHADOW, @@ -586,6 +598,7 @@ static const unsigned short vmcs_field_to_offset_table[] = { FIELD64(GUEST_PDPTR1, guest_pdptr1), FIELD64(GUEST_PDPTR2, guest_pdptr2), FIELD64(GUEST_PDPTR3, guest_pdptr3), + FIELD64(GUEST_BNDCFGS, guest_bndcfgs), FIELD64(HOST_IA32_PAT, host_ia32_pat), FIELD64(HOST_IA32_EFER, host_ia32_efer), FIELD64(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl), @@ -716,6 +729,7 @@ static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu); static u64 construct_eptp(unsigned long root_hpa); static void kvm_cpu_vmxon(u64 addr); static void kvm_cpu_vmxoff(void); +static bool vmx_mpx_supported(void); static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); @@ -726,6 +740,7 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var); static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu); static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx); static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx); +static bool vmx_mpx_supported(void); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -1045,6 +1060,12 @@ static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12) return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS; } +static inline bool nested_cpu_has_preemption_timer(struct vmcs12 *vmcs12) +{ + return vmcs12->pin_based_vm_exec_control & + PIN_BASED_VMX_PREEMPTION_TIMER; +} + static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12) { return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_EPT); @@ -1056,7 +1077,9 @@ 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 +1349,62 @@ 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 +1489,11 @@ 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 +1504,15 @@ 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 +1533,15 @@ 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 +1553,8 @@ 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 +1564,7 @@ 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, @@ -1647,6 +1729,8 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) if (is_long_mode(&vmx->vcpu)) wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); #endif + if (boot_cpu_has(X86_FEATURE_MPX)) + rdmsrl(MSR_IA32_BNDCFGS, vmx->host_state.msr_host_bndcfgs); for (i = 0; i < vmx->save_nmsrs; ++i) kvm_set_shared_msr(vmx->guest_msrs[i].index, vmx->guest_msrs[i].data, @@ -1684,6 +1768,8 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) #ifdef CONFIG_X86_64 wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); #endif + if (vmx->host_state.msr_host_bndcfgs) + wrmsrl(MSR_IA32_BNDCFGS, vmx->host_state.msr_host_bndcfgs); /* * If the FPU is not active (through the host task or * the guest vcpu), then restore the cr0.TS bit. @@ -1906,7 +1992,9 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr) 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; } @@ -2183,9 +2271,9 @@ static __init void nested_vmx_setup_ctls_msrs(void) */ nested_vmx_pinbased_ctls_low |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR; nested_vmx_pinbased_ctls_high &= PIN_BASED_EXT_INTR_MASK | - PIN_BASED_NMI_EXITING | PIN_BASED_VIRTUAL_NMIS | + PIN_BASED_NMI_EXITING | PIN_BASED_VIRTUAL_NMIS; + nested_vmx_pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | PIN_BASED_VMX_PREEMPTION_TIMER; - nested_vmx_pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR; /* * Exit controls @@ -2200,15 +2288,12 @@ 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; + nested_vmx_exit_ctls_high |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | + VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER | 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_SAVE_IA32_EFER); + if (vmx_mpx_supported()) + nested_vmx_exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS; /* entry controls */ rdmsr(MSR_IA32_VMX_ENTRY_CTLS, @@ -2222,6 +2307,8 @@ static __init void nested_vmx_setup_ctls_msrs(void) VM_ENTRY_LOAD_IA32_PAT; nested_vmx_entry_ctls_high |= (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER); + if (vmx_mpx_supported()) + nested_vmx_entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS; /* cpu-based controls */ rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, @@ -2277,8 +2364,9 @@ static __init void nested_vmx_setup_ctls_msrs(void) /* miscellaneous data */ 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_SAVE_EFER_LMA; + nested_vmx_misc_low |= VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE | + VMX_MISC_ACTIVITY_HLT; nested_vmx_misc_high = 0; } @@ -2295,32 +2383,10 @@ 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 @@ -2387,34 +2453,9 @@ 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; } @@ -2460,13 +2501,25 @@ 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_BNDCFGS: + if (!vmx_mpx_supported()) + return 1; + data = vmcs_read64(GUEST_BNDCFGS); + 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; @@ -2479,6 +2532,8 @@ 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. @@ -2519,6 +2574,11 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_SYSENTER_ESP: vmcs_writel(GUEST_SYSENTER_ESP, data); break; + case MSR_IA32_BNDCFGS: + if (!vmx_mpx_supported()) + return 1; + vmcs_write64(GUEST_BNDCFGS, data); + break; case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr_info); break; @@ -2533,6 +2593,17 @@ 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; @@ -2541,8 +2612,6 @@ 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; @@ -2795,12 +2864,12 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) vmx_capability.ept, vmx_capability.vpid); } - min = 0; + min = VM_EXIT_SAVE_DEBUG_CONTROLS; #ifdef CONFIG_X86_64 min |= VM_EXIT_HOST_ADDR_SPACE_SIZE; #endif opt = VM_EXIT_SAVE_IA32_PAT | VM_EXIT_LOAD_IA32_PAT | - VM_EXIT_ACK_INTR_ON_EXIT; + VM_EXIT_ACK_INTR_ON_EXIT | VM_EXIT_CLEAR_BNDCFGS; if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS, &_vmexit_control) < 0) return -EIO; @@ -2816,8 +2885,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) !(_vmexit_control & VM_EXIT_ACK_INTR_ON_EXIT)) _pin_based_exec_control &= ~PIN_BASED_POSTED_INTR; - min = 0; - opt = VM_ENTRY_LOAD_IA32_PAT; + min = VM_ENTRY_LOAD_DEBUG_CONTROLS; + opt = VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_BNDCFGS; if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS, &_vmentry_control) < 0) return -EIO; @@ -3182,14 +3251,10 @@ 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; } @@ -3217,9 +3282,7 @@ 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); } @@ -4192,6 +4255,10 @@ static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) static u32 vmx_exec_control(struct vcpu_vmx *vmx) { u32 exec_control = vmcs_config.cpu_based_exec_ctrl; + + if (vmx->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT) + exec_control &= ~CPU_BASED_MOV_DR_EXITING; + if (!vm_need_tpr_shadow(vmx->vcpu.kvm)) { exec_control &= ~CPU_BASED_TPR_SHADOW; #ifdef CONFIG_X86_64 @@ -4346,10 +4413,11 @@ 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); @@ -4360,7 +4428,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - u64 msr; + struct msr_data apic_base_msr; vmx->rmode.vm86_active = 0; @@ -4368,10 +4436,11 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); kvm_set_cr8(&vmx->vcpu, 0); - msr = 0xfee00000 | MSR_IA32_APICBASE_ENABLE; + apic_base_msr.data = 0xfee00000 | MSR_IA32_APICBASE_ENABLE; if (kvm_vcpu_is_bsp(&vmx->vcpu)) - msr |= MSR_IA32_APICBASE_BSP; - kvm_set_apic_base(&vmx->vcpu, msr); + apic_base_msr.data |= MSR_IA32_APICBASE_BSP; + apic_base_msr.host_initiated = true; + kvm_set_apic_base(&vmx->vcpu, &apic_base_msr); vmx_segment_cache_clear(vmx); @@ -4463,39 +4532,28 @@ static bool nested_exit_on_nmi(struct kvm_vcpu *vcpu) PIN_BASED_NMI_EXITING; } -static int enable_irq_window(struct kvm_vcpu *vcpu) +static void enable_irq_window(struct kvm_vcpu *vcpu) { u32 cpu_based_vm_exec_control; - if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) - /* - * We get here if vmx_interrupt_allowed() said we can't - * inject to L1 now because L2 must run. The caller will have - * to make L2 exit right after entry, so we can inject to L1 - * more promptly. - */ - return -EBUSY; - cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING; vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); - return 0; } -static int enable_nmi_window(struct kvm_vcpu *vcpu) +static void enable_nmi_window(struct kvm_vcpu *vcpu) { u32 cpu_based_vm_exec_control; - if (!cpu_has_virtual_nmis()) - return enable_irq_window(vcpu); - - if (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) - return enable_irq_window(vcpu); + if (!cpu_has_virtual_nmis() || + vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) { + enable_irq_window(vcpu); + return; + } cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_NMI_PENDING; vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); - return 0; } static void vmx_inject_irq(struct kvm_vcpu *vcpu) @@ -4587,25 +4645,8 @@ 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; - /* - * The NMI-triggered VM exit counts as injection: - * clear this one and block further NMIs. - */ - vcpu->arch.nmi_pending = 0; - vmx_set_nmi_mask(vcpu, true); - return 0; - } - } + if (to_vmx(vcpu)->nested.nested_run_pending) + return 0; if (!cpu_has_virtual_nmis() && to_vmx(vcpu)->soft_vnmi_blocked) return 0; @@ -4617,23 +4658,8 @@ 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; - /* - * fall through to normal code, but now in L1, not L2 - */ - } - } - - return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && + return (!to_vmx(vcpu)->nested.nested_run_pending && + vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); } @@ -4812,7 +4838,8 @@ 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; } @@ -5075,19 +5102,66 @@ static int handle_dr(struct kvm_vcpu *vcpu) } } + if (vcpu->guest_debug == 0) { + u32 cpu_based_vm_exec_control; + + cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); + cpu_based_vm_exec_control &= ~CPU_BASED_MOV_DR_EXITING; + vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); + + /* + * No more DR vmexits; force a reload of the debug registers + * and reenter on this instruction. The next vmexit will + * retrieve the full state of the debug registers. + */ + vcpu->arch.switch_db_regs |= KVM_DEBUGREG_WONT_EXIT; + return 1; + } + exit_qualification = vmcs_readl(EXIT_QUALIFICATION); dr = exit_qualification & DEBUG_REG_ACCESS_NUM; 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_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) +{ + u32 cpu_based_vm_exec_control; + + get_debugreg(vcpu->arch.db[0], 0); + get_debugreg(vcpu->arch.db[1], 1); + get_debugreg(vcpu->arch.db[2], 2); + get_debugreg(vcpu->arch.db[3], 3); + get_debugreg(vcpu->arch.dr6, 6); + vcpu->arch.dr7 = vmcs_readl(GUEST_DR7); + + vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT; + + cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); + cpu_based_vm_exec_control |= CPU_BASED_MOV_DR_EXITING; + vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); +} + static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) { vmcs_writel(GUEST_DR7, val); @@ -5687,6 +5761,18 @@ static void nested_vmx_failValid(struct kvm_vcpu *vcpu, */ } +static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer) +{ + struct vcpu_vmx *vmx = + container_of(timer, struct vcpu_vmx, nested.preemption_timer); + + vmx->nested.preemption_timer_expired = true; + kvm_make_request(KVM_REQ_EVENT, &vmx->vcpu); + kvm_vcpu_kick(&vmx->vcpu); + + return HRTIMER_NORESTART; +} + /* * Emulate the VMXON instruction. * Currently, we just remember that VMX is active, and do not save or even @@ -5751,6 +5837,10 @@ static int handle_vmon(struct kvm_vcpu *vcpu) INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool)); vmx->nested.vmcs02_num = 0; + hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); + vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; + vmx->nested.vmxon = true; skip_emulated_instruction(vcpu); @@ -6460,11 +6550,8 @@ 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); @@ -6628,6 +6715,13 @@ 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; @@ -6644,7 +6738,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) else if (is_page_fault(intr_info)) return enable_ept; else if (is_no_device(intr_info) && - !(nested_read_cr0(vmcs12) & X86_CR0_TS)) + !(vmcs12->guest_cr0 & X86_CR0_TS)) return 0; return vmcs12->exception_bitmap & (1u << (intr_info & INTR_INFO_VECTOR_MASK)); @@ -6723,9 +6817,6 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) * table is L0's fault. */ return 0; - case EXIT_REASON_PREEMPTION_TIMER: - return vmcs12->pin_based_vm_exec_control & - PIN_BASED_VMX_PREEMPTION_TIMER; case EXIT_REASON_WBINVD: return nested_cpu_has2(vmcs12, SECONDARY_EXEC_WBINVD_EXITING); case EXIT_REASON_XSETBV: @@ -6741,27 +6832,6 @@ 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. @@ -6777,7 +6847,9 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) return handle_invalid_guest_state(vcpu); 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; } @@ -7006,6 +7078,12 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) local_irq_enable(); } +static bool vmx_mpx_supported(void) +{ + return (vmcs_config.vmexit_ctrl & VM_EXIT_CLEAR_BNDCFGS) && + (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_BNDCFGS); +} + static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) { u32 exit_intr_info; @@ -7172,8 +7250,6 @@ 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 */ @@ -7332,8 +7408,8 @@ 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); @@ -7518,15 +7594,14 @@ 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; } @@ -7564,11 +7639,35 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, /* TODO: also check PFEC_MATCH/MASK, not just EB.PF. */ if (vmcs12->exception_bitmap & (1u << PF_VECTOR)) - nested_vmx_vmexit(vcpu); + 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); } +static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu) +{ + u64 preemption_timeout = get_vmcs12(vcpu)->vmx_preemption_timer_value; + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (vcpu->arch.virtual_tsc_khz == 0) + return; + + /* Make sure short timeouts reliably trigger an immediate vmexit. + * hrtimer_start does not guarantee this. */ + if (preemption_timeout <= 1) { + vmx_preemption_timer_fn(&vmx->nested.preemption_timer); + return; + } + + preemption_timeout <<= VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE; + preemption_timeout *= 1000000; + do_div(preemption_timeout, vcpu->arch.virtual_tsc_khz); + hrtimer_start(&vmx->nested.preemption_timer, + ns_to_ktime(preemption_timeout), HRTIMER_MODE_REL); +} + /* * 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 @@ -7582,7 +7681,6 @@ 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); @@ -7640,13 +7738,14 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs_write64(VMCS_LINK_POINTER, -1ull); - vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, - (vmcs_config.pin_based_exec_ctrl | - vmcs12->pin_based_vm_exec_control)); + exec_control = vmcs12->pin_based_vm_exec_control; + exec_control |= vmcs_config.pin_based_exec_ctrl; + exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, exec_control); - if (vmcs12->pin_based_vm_exec_control & PIN_BASED_VMX_PREEMPTION_TIMER) - vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, - vmcs12->vmx_preemption_timer_value); + vmx->nested.preemption_timer_expired = false; + if (nested_cpu_has_preemption_timer(vmcs12)) + vmx_start_preemption_timer(vcpu); /* * Whether page-faults are trapped is determined by a combination of @@ -7674,7 +7773,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) enable_ept ? vmcs12->page_fault_error_code_match : 0); if (cpu_has_secondary_exec_ctrls()) { - u32 exec_control = vmx_secondary_exec_control(vmx); + exec_control = vmx_secondary_exec_control(vmx); if (!vmx->rdtscp_enabled) exec_control &= ~SECONDARY_EXEC_RDTSCP; /* Take the following fields only from vmcs12 */ @@ -7706,6 +7805,11 @@ 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); @@ -7756,15 +7860,12 @@ 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. */ - 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; - vmcs_write32(VM_EXIT_CONTROLS, exit_control); + vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl); /* 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)); @@ -7778,6 +7879,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) set_cr4_guest_host_mask(vmx); + if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) + vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs); + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset); @@ -7882,7 +7986,8 @@ 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; } @@ -7994,8 +8099,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) enter_guest_mode(vcpu); - vmx->nested.nested_run_pending = 1; - vmx->nested.vmcs01_tsc_offset = vmcs_read64(TSC_OFFSET); cpu = get_cpu(); @@ -8011,6 +8114,11 @@ 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 @@ -8099,6 +8207,58 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu, } } +static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) && + vmx->nested.preemption_timer_expired) { + if (vmx->nested.nested_run_pending) + return -EBUSY; + nested_vmx_vmexit(vcpu, EXIT_REASON_PREEMPTION_TIMER, 0, 0); + return 0; + } + + if (vcpu->arch.nmi_pending && nested_exit_on_nmi(vcpu)) { + if (vmx->nested.nested_run_pending || + vcpu->arch.interrupt.pending) + return -EBUSY; + 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. + */ + vcpu->arch.nmi_pending = 0; + vmx_set_nmi_mask(vcpu, true); + return 0; + } + + if ((kvm_cpu_has_interrupt(vcpu) || external_intr) && + nested_exit_on_intr(vcpu)) { + if (vmx->nested.nested_run_pending) + return -EBUSY; + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0); + } + + return 0; +} + +static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu) +{ + ktime_t remaining = + hrtimer_get_remaining(&to_vmx(vcpu)->nested.preemption_timer); + u64 value; + + if (ktime_to_ns(remaining) <= 0) + return 0; + + value = ktime_to_ns(remaining) * vcpu->arch.virtual_tsc_khz; + do_div(value, 1000000); + return value >> VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE; +} + /* * prepare_vmcs12 is part of what we need to do when the nested L2 guest exits * and we want to prepare to run its L1 parent. L1 keeps a vmcs for L2 (vmcs12), @@ -8110,7 +8270,9 @@ 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); @@ -8162,11 +8324,18 @@ 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); + if (nested_cpu_has_preemption_timer(vmcs12)) { + if (vmcs12->vm_exit_controls & + VM_EXIT_SAVE_VMX_PREEMPTION_TIMER) + vmcs12->vmx_preemption_timer_value = + vmx_get_preemption_timer_value(vcpu); + hrtimer_cancel(&to_vmx(vcpu)->nested.preemption_timer); + } /* * In some cases (usually, nested EPT), L2 is allowed to change its @@ -8186,7 +8355,7 @@ 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 */ @@ -8198,13 +8367,15 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) 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); + if (vmx_mpx_supported()) + vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); /* 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)) @@ -8307,6 +8478,10 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vmcs_writel(GUEST_IDTR_BASE, vmcs12->host_idtr_base); vmcs_writel(GUEST_GDTR_BASE, vmcs12->host_gdtr_base); + /* If not VM_EXIT_CLEAR_BNDCFGS, the L2 value propagates to L1. */ + if (vmcs12->vm_exit_controls & VM_EXIT_CLEAR_BNDCFGS) + vmcs_write64(GUEST_BNDCFGS, 0); + if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) { vmcs_write64(GUEST_IA32_PAT, vmcs12->host_ia32_pat); vcpu->arch.pat = vmcs12->host_ia32_pat; @@ -8370,7 +8545,9 @@ 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; @@ -8380,7 +8557,15 @@ 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; @@ -8389,6 +8574,8 @@ 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 */ @@ -8421,6 +8608,19 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu) nested_vmx_succeed(vcpu); if (enable_shadow_vmcs) vmx->nested.sync_shadow_vmcs = true; + + /* in case we halted in L2 */ + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; +} + +/* + * 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)); } /* @@ -8486,7 +8686,10 @@ 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, + .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, .cache_reg = vmx_cache_reg, .get_rflags = vmx_get_rflags, .set_rflags = vmx_set_rflags, @@ -8548,6 +8751,9 @@ static struct kvm_x86_ops vmx_x86_ops = { .check_intercept = vmx_check_intercept, .handle_external_intr = vmx_handle_external_intr, + .mpx_supported = vmx_mpx_supported, + + .check_nested_events = vmx_check_nested_events, }; static int __init vmx_init(void) @@ -8635,6 +8841,8 @@ static int __init vmx_init(void) vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false); vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false); vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false); + vmx_disable_intercept_for_msr(MSR_IA32_BNDCFGS, true); + memcpy(vmx_msr_bitmap_legacy_x2apic, vmx_msr_bitmap_legacy, PAGE_SIZE); memcpy(vmx_msr_bitmap_longmode_x2apic, |
