diff options
Diffstat (limited to 'arch/x86/kvm/vmx.c')
| -rw-r--r-- | arch/x86/kvm/vmx.c | 738 |
1 files changed, 490 insertions, 248 deletions
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a06f101ef64..801332edefc 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; @@ -349,6 +354,7 @@ struct vmcs02_list { struct nested_vmx { /* Has the level1 guest done vmxon? */ bool vmxon; + gpa_t vmxon_ptr; /* The guest-physical address of the current VMCS L1 keeps for L2 */ gpa_t current_vmptr; @@ -374,6 +380,9 @@ 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 @@ -405,7 +414,6 @@ struct vcpu_vmx { struct kvm_vcpu vcpu; unsigned long host_rsp; u8 fail; - u8 cpl; bool nmi_known_unmasked; u32 exit_intr_info; u32 idt_vectoring_info; @@ -441,6 +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; @@ -494,7 +503,7 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) [number##_HIGH] = VMCS12_OFFSET(name)+4 -static const unsigned long shadow_read_only_fields[] = { +static unsigned long shadow_read_only_fields[] = { /* * We do NOT shadow fields that are modified when L0 * traps and emulates any vmx instruction (e.g. VMPTRLD, @@ -517,10 +526,10 @@ static const unsigned long shadow_read_only_fields[] = { GUEST_LINEAR_ADDRESS, GUEST_PHYSICAL_ADDRESS }; -static const int max_shadow_read_only_fields = +static int max_shadow_read_only_fields = ARRAY_SIZE(shadow_read_only_fields); -static const unsigned long shadow_read_write_fields[] = { +static unsigned long shadow_read_write_fields[] = { GUEST_RIP, GUEST_RSP, GUEST_CR0, @@ -533,6 +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, @@ -548,7 +558,7 @@ static const unsigned long shadow_read_write_fields[] = { HOST_FS_SELECTOR, HOST_GS_SELECTOR }; -static const int max_shadow_read_write_fields = +static int max_shadow_read_write_fields = ARRAY_SIZE(shadow_read_write_fields); static const unsigned short vmcs_field_to_offset_table[] = { @@ -588,6 +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), @@ -718,6 +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); @@ -728,6 +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); @@ -1047,6 +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); @@ -1710,6 +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, @@ -1747,6 +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. @@ -2248,9 +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 @@ -2260,20 +2283,18 @@ static __init void nested_vmx_setup_ctls_msrs(void) rdmsr(MSR_IA32_VMX_EXIT_CTLS, nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high); nested_vmx_exit_ctls_low = VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR; - /* Note that guest use of VM_EXIT_ACK_INTR_ON_EXIT is not supported. */ + nested_vmx_exit_ctls_high &= #ifdef CONFIG_X86_64 VM_EXIT_HOST_ADDR_SPACE_SIZE | #endif - 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_SAVE_IA32_EFER); + 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 | VM_EXIT_ACK_INTR_ON_EXIT; + + if (vmx_mpx_supported()) + nested_vmx_exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS; /* entry controls */ rdmsr(MSR_IA32_VMX_ENTRY_CTLS, @@ -2287,6 +2308,8 @@ 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, @@ -2331,20 +2354,19 @@ static __init void nested_vmx_setup_ctls_msrs(void) VMX_EPT_INVEPT_BIT; nested_vmx_ept_caps &= vmx_capability.ept; /* - * Since invept is completely emulated we support both global - * and context invalidation independent of what host cpu - * supports + * For nested guests, we don't do anything specific + * for single context invalidation. Hence, only advertise + * support for global context invalidation. */ - nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT | - VMX_EPT_EXTENT_CONTEXT_BIT; + nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT; } else nested_vmx_ept_caps = 0; /* 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_ACTIVITY_HLT; + 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; } @@ -2479,6 +2501,11 @@ 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; @@ -2547,6 +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; @@ -2832,12 +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; @@ -2853,8 +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; @@ -2977,6 +3009,41 @@ static void free_kvm_area(void) } } +static void init_vmcs_shadow_fields(void) +{ + int i, j; + + /* No checks for read only fields yet */ + + for (i = j = 0; i < max_shadow_read_write_fields; i++) { + switch (shadow_read_write_fields[i]) { + case GUEST_BNDCFGS: + if (!vmx_mpx_supported()) + continue; + break; + default: + break; + } + + if (j < i) + shadow_read_write_fields[j] = + shadow_read_write_fields[i]; + j++; + } + max_shadow_read_write_fields = j; + + /* shadowed fields guest access without vmexit */ + for (i = 0; i < max_shadow_read_write_fields; i++) { + clear_bit(shadow_read_write_fields[i], + vmx_vmwrite_bitmap); + clear_bit(shadow_read_write_fields[i], + vmx_vmread_bitmap); + } + for (i = 0; i < max_shadow_read_only_fields; i++) + clear_bit(shadow_read_only_fields[i], + vmx_vmread_bitmap); +} + static __init int alloc_kvm_area(void) { int cpu; @@ -3007,6 +3074,8 @@ static __init int hardware_setup(void) enable_vpid = 0; if (!cpu_has_vmx_shadow_vmcs()) enable_shadow_vmcs = 0; + if (enable_shadow_vmcs) + init_vmcs_shadow_fields(); if (!cpu_has_vmx_ept() || !cpu_has_vmx_ept_4levels()) { @@ -3117,10 +3186,6 @@ static void enter_pmode(struct kvm_vcpu *vcpu) fix_pmode_seg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]); fix_pmode_seg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]); fix_pmode_seg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]); - - /* CPL is always 0 when CPU enters protected mode */ - __set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); - vmx->cpl = 0; } static void fix_rmode_seg(int seg, struct kvm_segment *save) @@ -3452,13 +3517,14 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) hw_cr4 &= ~X86_CR4_PAE; hw_cr4 |= X86_CR4_PSE; /* - * SMEP is disabled if CPU is in non-paging mode in - * hardware. However KVM always uses paging mode to + * SMEP/SMAP is disabled if CPU is in non-paging mode + * in hardware. However KVM always uses paging mode to * emulate guest non-paging mode with TDP. - * To emulate this behavior, SMEP needs to be manually - * disabled when guest switches to non-paging mode. + * To emulate this behavior, SMEP/SMAP needs to be + * manually disabled when guest switches to non-paging + * mode. */ - hw_cr4 &= ~X86_CR4_SMEP; + hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP); } else if (!(cr4 & X86_CR4_PAE)) { hw_cr4 &= ~X86_CR4_PAE; } @@ -3521,22 +3587,14 @@ static int vmx_get_cpl(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!is_protmode(vcpu)) + if (unlikely(vmx->rmode.vm86_active)) return 0; - - if (!is_long_mode(vcpu) - && (kvm_get_rflags(vcpu) & X86_EFLAGS_VM)) /* if virtual 8086 */ - return 3; - - if (!test_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail)) { - __set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); - vmx->cpl = vmx_read_guest_seg_selector(vmx, VCPU_SREG_CS) & 3; + else { + int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS); + return AR_DPL(ar); } - - return vmx->cpl; } - static u32 vmx_segment_access_rights(struct kvm_segment *var) { u32 ar; @@ -3564,8 +3622,6 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; vmx_segment_cache_clear(vmx); - if (seg == VCPU_SREG_CS) - __clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) { vmx->rmode.segs[seg] = *var; @@ -4223,6 +4279,10 @@ 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 @@ -4490,45 +4550,44 @@ static bool nested_exit_on_intr(struct kvm_vcpu *vcpu) PIN_BASED_EXT_INTR_MASK; } +/* + * In nested virtualization, check if L1 has set + * VM_EXIT_ACK_INTR_ON_EXIT + */ +static bool nested_exit_intr_ack_set(struct kvm_vcpu *vcpu) +{ + return get_vmcs12(vcpu)->vm_exit_controls & + VM_EXIT_ACK_INTR_ON_EXIT; +} + static bool nested_exit_on_nmi(struct kvm_vcpu *vcpu) { return get_vmcs12(vcpu)->pin_based_vm_exec_control & 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) @@ -4620,22 +4679,8 @@ 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)) { - if (to_vmx(vcpu)->nested.nested_run_pending) - return 0; - if (nested_exit_on_nmi(vcpu)) { - 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 (to_vmx(vcpu)->nested.nested_run_pending) + return 0; if (!cpu_has_virtual_nmis() && to_vmx(vcpu)->soft_vnmi_blocked) return 0; @@ -4647,19 +4692,8 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) { - if (is_guest_mode(vcpu)) { - if (to_vmx(vcpu)->nested.nested_run_pending) - return 0; - if (nested_exit_on_intr(vcpu)) { - nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, - 0, 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)); } @@ -4840,6 +4874,9 @@ static int handle_exception(struct kvm_vcpu *vcpu) (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { vcpu->arch.dr6 &= ~15; vcpu->arch.dr6 |= dr6; + if (!(dr6 & ~DR6_RESERVED)) /* icebp */ + skip_emulated_instruction(vcpu); + kvm_queue_exception(vcpu, DB_VECTOR); return 1; } @@ -5102,6 +5139,22 @@ 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); @@ -5112,7 +5165,7 @@ static int handle_dr(struct kvm_vcpu *vcpu) return 1; kvm_register_write(vcpu, reg, val); } else - if (kvm_set_dr(vcpu, dr, vcpu->arch.regs[reg])) + if (kvm_set_dr(vcpu, dr, kvm_register_read(vcpu, reg))) return 1; skip_emulated_instruction(vcpu); @@ -5128,6 +5181,24 @@ 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); @@ -5367,7 +5438,7 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) } /* clear all local breakpoint enable flags */ - vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~55); + vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~0x55); /* * TODO: What about debug traps on tss switch? @@ -5493,6 +5564,10 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) gpa_t gpa; gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); + if (!kvm_io_bus_write(vcpu->kvm, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { + skip_emulated_instruction(vcpu); + return 1; + } ret = handle_mmio_page_fault_common(vcpu, gpa, true); if (likely(ret == RET_MMIO_PF_EMULATE)) @@ -5597,12 +5672,24 @@ static int handle_pause(struct kvm_vcpu *vcpu) return 1; } -static int handle_invalid_op(struct kvm_vcpu *vcpu) +static int handle_nop(struct kvm_vcpu *vcpu) { - kvm_queue_exception(vcpu, UD_VECTOR); + skip_emulated_instruction(vcpu); return 1; } +static int handle_mwait(struct kvm_vcpu *vcpu) +{ + printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n"); + return handle_nop(vcpu); +} + +static int handle_monitor(struct kvm_vcpu *vcpu) +{ + printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n"); + return handle_nop(vcpu); +} + /* * To run an L2 guest, we need a vmcs02 based on the L1-specified vmcs12. * We could reuse a single VMCS for all the L2 guests, but we also want the @@ -5727,6 +5814,166 @@ 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; +} + +/* + * Decode the memory-address operand of a vmx instruction, as recorded on an + * exit caused by such an instruction (run by a guest hypervisor). + * On success, returns 0. When the operand is invalid, returns 1 and throws + * #UD or #GP. + */ +static int get_vmx_mem_address(struct kvm_vcpu *vcpu, + unsigned long exit_qualification, + u32 vmx_instruction_info, gva_t *ret) +{ + /* + * According to Vol. 3B, "Information for VM Exits Due to Instruction + * Execution", on an exit, vmx_instruction_info holds most of the + * addressing components of the operand. Only the displacement part + * is put in exit_qualification (see 3B, "Basic VM-Exit Information"). + * For how an actual address is calculated from all these components, + * refer to Vol. 1, "Operand Addressing". + */ + int scaling = vmx_instruction_info & 3; + int addr_size = (vmx_instruction_info >> 7) & 7; + bool is_reg = vmx_instruction_info & (1u << 10); + int seg_reg = (vmx_instruction_info >> 15) & 7; + int index_reg = (vmx_instruction_info >> 18) & 0xf; + bool index_is_valid = !(vmx_instruction_info & (1u << 22)); + int base_reg = (vmx_instruction_info >> 23) & 0xf; + bool base_is_valid = !(vmx_instruction_info & (1u << 27)); + + if (is_reg) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + + /* Addr = segment_base + offset */ + /* offset = base + [index * scale] + displacement */ + *ret = vmx_get_segment_base(vcpu, seg_reg); + if (base_is_valid) + *ret += kvm_register_read(vcpu, base_reg); + if (index_is_valid) + *ret += kvm_register_read(vcpu, index_reg)<<scaling; + *ret += exit_qualification; /* holds the displacement */ + + if (addr_size == 1) /* 32 bit */ + *ret &= 0xffffffff; + + /* + * TODO: throw #GP (and return 1) in various cases that the VM* + * instructions require it - e.g., offset beyond segment limit, + * unusable or unreadable/unwritable segment, non-canonical 64-bit + * address, and so on. Currently these are not checked. + */ + return 0; +} + +/* + * This function performs the various checks including + * - if it's 4KB aligned + * - No bits beyond the physical address width are set + * - Returns 0 on success or else 1 + * (Intel SDM Section 30.3) + */ +static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, + gpa_t *vmpointer) +{ + gva_t gva; + gpa_t vmptr; + struct x86_exception e; + struct page *page; + struct vcpu_vmx *vmx = to_vmx(vcpu); + int maxphyaddr = cpuid_maxphyaddr(vcpu); + + if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), + vmcs_read32(VMX_INSTRUCTION_INFO), &gva)) + return 1; + + if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr, + sizeof(vmptr), &e)) { + kvm_inject_page_fault(vcpu, &e); + return 1; + } + + switch (exit_reason) { + case EXIT_REASON_VMON: + /* + * SDM 3: 24.11.5 + * The first 4 bytes of VMXON region contain the supported + * VMCS revision identifier + * + * Note - IA32_VMX_BASIC[48] will never be 1 + * for the nested case; + * which replaces physical address width with 32 + * + */ + if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) { + nested_vmx_failInvalid(vcpu); + skip_emulated_instruction(vcpu); + return 1; + } + + page = nested_get_page(vcpu, vmptr); + if (page == NULL || + *(u32 *)kmap(page) != VMCS12_REVISION) { + nested_vmx_failInvalid(vcpu); + kunmap(page); + skip_emulated_instruction(vcpu); + return 1; + } + kunmap(page); + vmx->nested.vmxon_ptr = vmptr; + break; + case EXIT_REASON_VMCLEAR: + if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) { + nested_vmx_failValid(vcpu, + VMXERR_VMCLEAR_INVALID_ADDRESS); + skip_emulated_instruction(vcpu); + return 1; + } + + if (vmptr == vmx->nested.vmxon_ptr) { + nested_vmx_failValid(vcpu, + VMXERR_VMCLEAR_VMXON_POINTER); + skip_emulated_instruction(vcpu); + return 1; + } + break; + case EXIT_REASON_VMPTRLD: + if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) { + nested_vmx_failValid(vcpu, + VMXERR_VMPTRLD_INVALID_ADDRESS); + skip_emulated_instruction(vcpu); + return 1; + } + + if (vmptr == vmx->nested.vmxon_ptr) { + nested_vmx_failValid(vcpu, + VMXERR_VMCLEAR_VMXON_POINTER); + skip_emulated_instruction(vcpu); + return 1; + } + break; + default: + return 1; /* shouldn't happen */ + } + + if (vmpointer) + *vmpointer = vmptr; + return 0; +} + /* * Emulate the VMXON instruction. * Currently, we just remember that VMX is active, and do not save or even @@ -5765,6 +6012,10 @@ static int handle_vmon(struct kvm_vcpu *vcpu) kvm_inject_gp(vcpu, 0); return 1; } + + if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMON, NULL)) + return 1; + if (vmx->nested.vmxon) { nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION); skip_emulated_instruction(vcpu); @@ -5791,6 +6042,10 @@ 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); @@ -5883,87 +6138,19 @@ static int handle_vmoff(struct kvm_vcpu *vcpu) return 1; } -/* - * Decode the memory-address operand of a vmx instruction, as recorded on an - * exit caused by such an instruction (run by a guest hypervisor). - * On success, returns 0. When the operand is invalid, returns 1 and throws - * #UD or #GP. - */ -static int get_vmx_mem_address(struct kvm_vcpu *vcpu, - unsigned long exit_qualification, - u32 vmx_instruction_info, gva_t *ret) -{ - /* - * According to Vol. 3B, "Information for VM Exits Due to Instruction - * Execution", on an exit, vmx_instruction_info holds most of the - * addressing components of the operand. Only the displacement part - * is put in exit_qualification (see 3B, "Basic VM-Exit Information"). - * For how an actual address is calculated from all these components, - * refer to Vol. 1, "Operand Addressing". - */ - int scaling = vmx_instruction_info & 3; - int addr_size = (vmx_instruction_info >> 7) & 7; - bool is_reg = vmx_instruction_info & (1u << 10); - int seg_reg = (vmx_instruction_info >> 15) & 7; - int index_reg = (vmx_instruction_info >> 18) & 0xf; - bool index_is_valid = !(vmx_instruction_info & (1u << 22)); - int base_reg = (vmx_instruction_info >> 23) & 0xf; - bool base_is_valid = !(vmx_instruction_info & (1u << 27)); - - if (is_reg) { - kvm_queue_exception(vcpu, UD_VECTOR); - return 1; - } - - /* Addr = segment_base + offset */ - /* offset = base + [index * scale] + displacement */ - *ret = vmx_get_segment_base(vcpu, seg_reg); - if (base_is_valid) - *ret += kvm_register_read(vcpu, base_reg); - if (index_is_valid) - *ret += kvm_register_read(vcpu, index_reg)<<scaling; - *ret += exit_qualification; /* holds the displacement */ - - if (addr_size == 1) /* 32 bit */ - *ret &= 0xffffffff; - - /* - * TODO: throw #GP (and return 1) in various cases that the VM* - * instructions require it - e.g., offset beyond segment limit, - * unusable or unreadable/unwritable segment, non-canonical 64-bit - * address, and so on. Currently these are not checked. - */ - return 0; -} - /* Emulate the VMCLEAR instruction */ static int handle_vmclear(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - gva_t gva; gpa_t vmptr; struct vmcs12 *vmcs12; struct page *page; - struct x86_exception e; if (!nested_vmx_check_permission(vcpu)) return 1; - if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), - vmcs_read32(VMX_INSTRUCTION_INFO), &gva)) - return 1; - - if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr, - sizeof(vmptr), &e)) { - kvm_inject_page_fault(vcpu, &e); + if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMCLEAR, &vmptr)) return 1; - } - - if (!IS_ALIGNED(vmptr, PAGE_SIZE)) { - nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS); - skip_emulated_instruction(vcpu); - return 1; - } if (vmptr == vmx->nested.current_vmptr) { nested_release_vmcs12(vmx); @@ -6284,29 +6471,14 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) static int handle_vmptrld(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - gva_t gva; gpa_t vmptr; - struct x86_exception e; u32 exec_control; if (!nested_vmx_check_permission(vcpu)) return 1; - if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), - vmcs_read32(VMX_INSTRUCTION_INFO), &gva)) - return 1; - - if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr, - sizeof(vmptr), &e)) { - kvm_inject_page_fault(vcpu, &e); - return 1; - } - - if (!IS_ALIGNED(vmptr, PAGE_SIZE)) { - nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS); - skip_emulated_instruction(vcpu); + if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMPTRLD, &vmptr)) return 1; - } if (vmx->nested.current_vmptr != vmptr) { struct vmcs12 *new_vmcs12; @@ -6383,7 +6555,6 @@ static int handle_invept(struct kvm_vcpu *vcpu) struct { u64 eptp, gpa; } operand; - u64 eptp_mask = ((1ull << 51) - 1) & PAGE_MASK; if (!(nested_vmx_secondary_ctls_high & SECONDARY_EXEC_ENABLE_EPT) || !(nested_vmx_ept_caps & VMX_EPT_INVEPT_BIT)) { @@ -6423,16 +6594,13 @@ static int handle_invept(struct kvm_vcpu *vcpu) } switch (type) { - case VMX_EPT_EXTENT_CONTEXT: - if ((operand.eptp & eptp_mask) != - (nested_ept_get_cr3(vcpu) & eptp_mask)) - break; case VMX_EPT_EXTENT_GLOBAL: kvm_mmu_sync_roots(vcpu); kvm_mmu_flush_tlb(vcpu); nested_vmx_succeed(vcpu); break; default: + /* Trap single context invalidation invept calls */ BUG_ON(1); break; } @@ -6483,8 +6651,8 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation, [EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig, [EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause, - [EXIT_REASON_MWAIT_INSTRUCTION] = handle_invalid_op, - [EXIT_REASON_MONITOR_INSTRUCTION] = handle_invalid_op, + [EXIT_REASON_MWAIT_INSTRUCTION] = handle_mwait, + [EXIT_REASON_MONITOR_INSTRUCTION] = handle_monitor, [EXIT_REASON_INVEPT] = handle_invept, }; @@ -6688,7 +6856,7 @@ 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)); @@ -6767,9 +6935,6 @@ 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: @@ -6785,27 +6950,6 @@ 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. @@ -7052,6 +7196,12 @@ 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; @@ -7218,8 +7368,6 @@ 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 */ @@ -7345,7 +7493,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP) | (1 << VCPU_EXREG_RFLAGS) - | (1 << VCPU_EXREG_CPL) | (1 << VCPU_EXREG_PDPTR) | (1 << VCPU_EXREG_SEGMENTS) | (1 << VCPU_EXREG_CR3)); @@ -7616,6 +7763,28 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, 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 @@ -7629,7 +7798,6 @@ 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); @@ -7687,13 +7855,15 @@ 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 | + PIN_BASED_POSTED_INTR); + 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 @@ -7721,11 +7891,13 @@ 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 */ - exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | + SECONDARY_EXEC_APIC_REGISTER_VIRT); if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) exec_control |= vmcs12->secondary_vm_exec_control; @@ -7808,10 +7980,7 @@ 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; - vm_exit_controls_init(vmx, 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. @@ -7830,6 +7999,9 @@ 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); @@ -8155,6 +8327,58 @@ 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), @@ -8225,10 +8449,13 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, 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 @@ -8260,6 +8487,8 @@ 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: */ @@ -8369,6 +8598,10 @@ 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; @@ -8447,6 +8680,14 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info, exit_qualification); + if ((exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) + && nested_exit_intr_ack_set(vcpu)) { + int irq = kvm_cpu_get_interrupt(vcpu); + WARN_ON(irq < 0); + vmcs12->vm_exit_intr_info = irq | + INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR; + } + trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason, vmcs12->exit_qualification, vmcs12->idt_vectoring_info_field, @@ -8495,6 +8736,9 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, 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; } /* @@ -8573,6 +8817,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .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, @@ -8634,6 +8879,9 @@ 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) @@ -8682,14 +8930,6 @@ static int __init vmx_init(void) memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE); memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE); - /* shadowed read/write fields */ - for (i = 0; i < max_shadow_read_write_fields; i++) { - clear_bit(shadow_read_write_fields[i], vmx_vmwrite_bitmap); - clear_bit(shadow_read_write_fields[i], vmx_vmread_bitmap); - } - /* shadowed read only fields */ - for (i = 0; i < max_shadow_read_only_fields; i++) - clear_bit(shadow_read_only_fields[i], vmx_vmread_bitmap); /* * Allow direct access to the PC debug port (it is often used for I/O @@ -8721,6 +8961,8 @@ 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, |