diff options
Diffstat (limited to 'arch/x86/kvm/vmx.c')
| -rw-r--r-- | arch/x86/kvm/vmx.c | 1079 |
1 files changed, 835 insertions, 244 deletions
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 6667042714cc..25a791ed21c8 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -84,8 +84,11 @@ module_param(vmm_exclusive, bool, S_IRUGO); static bool __read_mostly fasteoi = 1; module_param(fasteoi, bool, S_IRUGO); -static bool __read_mostly enable_apicv_reg_vid; +static bool __read_mostly enable_apicv = 1; +module_param(enable_apicv, bool, S_IRUGO); +static bool __read_mostly enable_shadow_vmcs = 1; +module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO); /* * If nested=1, nested virtualization is supported, i.e., guests may use * VMX and be a hypervisor for its own guests. If nested=0, guests may not @@ -298,7 +301,8 @@ struct __packed vmcs12 { u32 guest_activity_state; u32 guest_sysenter_cs; u32 host_ia32_sysenter_cs; - u32 padding32[8]; /* room for future expansion */ + u32 vmx_preemption_timer_value; + u32 padding32[7]; /* room for future expansion */ u16 virtual_processor_id; u16 guest_es_selector; u16 guest_cs_selector; @@ -351,6 +355,12 @@ struct nested_vmx { /* The host-usable pointer to the above */ struct page *current_vmcs12_page; struct vmcs12 *current_vmcs12; + struct vmcs *current_shadow_vmcs; + /* + * Indicates if the shadow vmcs must be updated with the + * data hold by vmcs12 + */ + bool sync_shadow_vmcs; /* vmcs02_list cache of VMCSs recently used to run L2 guests */ struct list_head vmcs02_pool; @@ -365,6 +375,31 @@ struct nested_vmx { struct page *apic_access_page; }; +#define POSTED_INTR_ON 0 +/* Posted-Interrupt Descriptor */ +struct pi_desc { + u32 pir[8]; /* Posted interrupt requested */ + u32 control; /* bit 0 of control is outstanding notification bit */ + u32 rsvd[7]; +} __aligned(64); + +static bool pi_test_and_set_on(struct pi_desc *pi_desc) +{ + return test_and_set_bit(POSTED_INTR_ON, + (unsigned long *)&pi_desc->control); +} + +static bool pi_test_and_clear_on(struct pi_desc *pi_desc) +{ + return test_and_clear_bit(POSTED_INTR_ON, + (unsigned long *)&pi_desc->control); +} + +static int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) +{ + return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); +} + struct vcpu_vmx { struct kvm_vcpu vcpu; unsigned long host_rsp; @@ -377,6 +412,7 @@ struct vcpu_vmx { struct shared_msr_entry *guest_msrs; int nmsrs; int save_nmsrs; + unsigned long host_idt_base; #ifdef CONFIG_X86_64 u64 msr_host_kernel_gs_base; u64 msr_guest_kernel_gs_base; @@ -428,6 +464,9 @@ struct vcpu_vmx { bool rdtscp_enabled; + /* Posted interrupt descriptor */ + struct pi_desc pi_desc; + /* Support for a guest hypervisor (nested VMX) */ struct nested_vmx nested; }; @@ -451,6 +490,64 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) #define FIELD64(number, name) [number] = VMCS12_OFFSET(name), \ [number##_HIGH] = VMCS12_OFFSET(name)+4 + +static const 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, + * VMXON...) executed by L1. + * For example, VM_INSTRUCTION_ERROR is read + * by L1 if a vmx instruction fails (part of the error path). + * Note the code assumes this logic. If for some reason + * we start shadowing these fields then we need to + * force a shadow sync when L0 emulates vmx instructions + * (e.g. force a sync if VM_INSTRUCTION_ERROR is modified + * by nested_vmx_failValid) + */ + VM_EXIT_REASON, + VM_EXIT_INTR_INFO, + VM_EXIT_INSTRUCTION_LEN, + IDT_VECTORING_INFO_FIELD, + IDT_VECTORING_ERROR_CODE, + VM_EXIT_INTR_ERROR_CODE, + EXIT_QUALIFICATION, + GUEST_LINEAR_ADDRESS, + GUEST_PHYSICAL_ADDRESS +}; +static const int max_shadow_read_only_fields = + ARRAY_SIZE(shadow_read_only_fields); + +static const unsigned long shadow_read_write_fields[] = { + GUEST_RIP, + GUEST_RSP, + GUEST_CR0, + GUEST_CR3, + GUEST_CR4, + GUEST_INTERRUPTIBILITY_INFO, + GUEST_RFLAGS, + GUEST_CS_SELECTOR, + GUEST_CS_AR_BYTES, + GUEST_CS_LIMIT, + GUEST_CS_BASE, + GUEST_ES_BASE, + CR0_GUEST_HOST_MASK, + CR0_READ_SHADOW, + CR4_READ_SHADOW, + TSC_OFFSET, + EXCEPTION_BITMAP, + CPU_BASED_VM_EXEC_CONTROL, + VM_ENTRY_EXCEPTION_ERROR_CODE, + VM_ENTRY_INTR_INFO_FIELD, + VM_ENTRY_INSTRUCTION_LEN, + VM_ENTRY_EXCEPTION_ERROR_CODE, + HOST_FS_BASE, + HOST_GS_BASE, + HOST_FS_SELECTOR, + HOST_GS_SELECTOR +}; +static const int max_shadow_read_write_fields = + ARRAY_SIZE(shadow_read_write_fields); + static const unsigned short vmcs_field_to_offset_table[] = { FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id), FIELD(GUEST_ES_SELECTOR, guest_es_selector), @@ -537,6 +634,7 @@ static const unsigned short vmcs_field_to_offset_table[] = { FIELD(GUEST_ACTIVITY_STATE, guest_activity_state), FIELD(GUEST_SYSENTER_CS, guest_sysenter_cs), FIELD(HOST_IA32_SYSENTER_CS, host_ia32_sysenter_cs), + FIELD(VMX_PREEMPTION_TIMER_VALUE, vmx_preemption_timer_value), FIELD(CR0_GUEST_HOST_MASK, cr0_guest_host_mask), FIELD(CR4_GUEST_HOST_MASK, cr4_guest_host_mask), FIELD(CR0_READ_SHADOW, cr0_read_shadow), @@ -624,6 +722,9 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); static bool guest_state_valid(struct kvm_vcpu *vcpu); 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 DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -640,6 +741,8 @@ static unsigned long *vmx_msr_bitmap_legacy; static unsigned long *vmx_msr_bitmap_longmode; static unsigned long *vmx_msr_bitmap_legacy_x2apic; static unsigned long *vmx_msr_bitmap_longmode_x2apic; +static unsigned long *vmx_vmread_bitmap; +static unsigned long *vmx_vmwrite_bitmap; static bool cpu_has_load_ia32_efer; static bool cpu_has_load_perf_global_ctrl; @@ -782,6 +885,18 @@ static inline bool cpu_has_vmx_virtual_intr_delivery(void) SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY; } +static inline bool cpu_has_vmx_posted_intr(void) +{ + return vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR; +} + +static inline bool cpu_has_vmx_apicv(void) +{ + return cpu_has_vmx_apic_register_virt() && + cpu_has_vmx_virtual_intr_delivery() && + cpu_has_vmx_posted_intr(); +} + static inline bool cpu_has_vmx_flexpriority(void) { return cpu_has_vmx_tpr_shadow() && @@ -895,6 +1010,18 @@ static inline bool cpu_has_vmx_wbinvd_exit(void) SECONDARY_EXEC_WBINVD_EXITING; } +static inline bool cpu_has_vmx_shadow_vmcs(void) +{ + u64 vmx_msr; + rdmsrl(MSR_IA32_VMX_MISC, vmx_msr); + /* check if the cpu supports writing r/o exit information fields */ + if (!(vmx_msr & MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS)) + return false; + + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_SHADOW_VMCS; +} + static inline bool report_flexpriority(void) { return flexpriority_enabled; @@ -1790,7 +1917,7 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, u32 intr_info = nr | INTR_INFO_VALID_MASK; if (nr == PF_VECTOR && is_guest_mode(vcpu) && - nested_pf_handled(vcpu)) + !vmx->nested.nested_run_pending && nested_pf_handled(vcpu)) return; if (has_error_code) { @@ -2022,6 +2149,7 @@ static u32 nested_vmx_secondary_ctls_low, nested_vmx_secondary_ctls_high; static u32 nested_vmx_pinbased_ctls_low, nested_vmx_pinbased_ctls_high; static u32 nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high; static u32 nested_vmx_entry_ctls_low, nested_vmx_entry_ctls_high; +static u32 nested_vmx_misc_low, nested_vmx_misc_high; static __init void nested_vmx_setup_ctls_msrs(void) { /* @@ -2040,30 +2168,40 @@ static __init void nested_vmx_setup_ctls_msrs(void) */ /* pin-based controls */ + rdmsr(MSR_IA32_VMX_PINBASED_CTLS, + nested_vmx_pinbased_ctls_low, nested_vmx_pinbased_ctls_high); /* * According to the Intel spec, if bit 55 of VMX_BASIC is off (as it is * in our case), bits 1, 2 and 4 (i.e., 0x16) must be 1 in this MSR. */ - nested_vmx_pinbased_ctls_low = 0x16 ; - nested_vmx_pinbased_ctls_high = 0x16 | - PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING | - PIN_BASED_VIRTUAL_NMIS; + 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_VMX_PREEMPTION_TIMER; + nested_vmx_pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR; - /* exit controls */ - nested_vmx_exit_ctls_low = 0; + /* + * Exit controls + * If bit 55 of VMX_BASIC is off, bits 0-8 and 10, 11, 13, 14, 16 and + * 17 must be 1. + */ + 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. */ #ifdef CONFIG_X86_64 nested_vmx_exit_ctls_high = VM_EXIT_HOST_ADDR_SPACE_SIZE; #else nested_vmx_exit_ctls_high = 0; #endif + nested_vmx_exit_ctls_high |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR; /* entry controls */ rdmsr(MSR_IA32_VMX_ENTRY_CTLS, nested_vmx_entry_ctls_low, nested_vmx_entry_ctls_high); - nested_vmx_entry_ctls_low = 0; + /* If bit 55 of VMX_BASIC is off, bits 0-8 and 12 must be 1. */ + nested_vmx_entry_ctls_low = VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR; nested_vmx_entry_ctls_high &= VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_IA32E_MODE; + nested_vmx_entry_ctls_high |= VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR; /* cpu-based controls */ rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, @@ -2080,6 +2218,7 @@ static __init void nested_vmx_setup_ctls_msrs(void) CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING | CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_EXITING | CPU_BASED_RDPMC_EXITING | CPU_BASED_RDTSC_EXITING | + CPU_BASED_PAUSE_EXITING | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; /* * We can allow some features even when not supported by the @@ -2094,7 +2233,14 @@ static __init void nested_vmx_setup_ctls_msrs(void) nested_vmx_secondary_ctls_low, nested_vmx_secondary_ctls_high); nested_vmx_secondary_ctls_low = 0; nested_vmx_secondary_ctls_high &= - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_WBINVD_EXITING; + + /* 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_high = 0; } static inline bool vmx_control_verify(u32 control, u32 low, u32 high) @@ -2165,7 +2311,8 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) nested_vmx_entry_ctls_high); break; case MSR_IA32_VMX_MISC: - *pdata = 0; + *pdata = vmx_control_msr(nested_vmx_misc_low, + nested_vmx_misc_high); break; /* * These MSRs specify bits which the guest must keep fixed (on or off) @@ -2459,7 +2606,7 @@ static int hardware_enable(void *garbage) ept_sync_global(); } - store_gdt(&__get_cpu_var(host_gdt)); + native_store_gdt(&__get_cpu_var(host_gdt)); return 0; } @@ -2529,12 +2676,6 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) u32 _vmexit_control = 0; u32 _vmentry_control = 0; - min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING; - opt = PIN_BASED_VIRTUAL_NMIS; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS, - &_pin_based_exec_control) < 0) - return -EIO; - min = CPU_BASED_HLT_EXITING | #ifdef CONFIG_X86_64 CPU_BASED_CR8_LOAD_EXITING | @@ -2573,7 +2714,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY; + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | + SECONDARY_EXEC_SHADOW_VMCS; if (adjust_vmx_controls(min2, opt2, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) @@ -2605,11 +2747,23 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) #ifdef CONFIG_X86_64 min |= VM_EXIT_HOST_ADDR_SPACE_SIZE; #endif - opt = VM_EXIT_SAVE_IA32_PAT | VM_EXIT_LOAD_IA32_PAT; + opt = VM_EXIT_SAVE_IA32_PAT | VM_EXIT_LOAD_IA32_PAT | + VM_EXIT_ACK_INTR_ON_EXIT; if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS, &_vmexit_control) < 0) return -EIO; + min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING; + opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR; + if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS, + &_pin_based_exec_control) < 0) + return -EIO; + + if (!(_cpu_based_2nd_exec_control & + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) || + !(_vmexit_control & VM_EXIT_ACK_INTR_ON_EXIT)) + _pin_based_exec_control &= ~PIN_BASED_POSTED_INTR; + min = 0; opt = VM_ENTRY_LOAD_IA32_PAT; if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS, @@ -2762,6 +2916,8 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_vpid()) enable_vpid = 0; + if (!cpu_has_vmx_shadow_vmcs()) + enable_shadow_vmcs = 0; if (!cpu_has_vmx_ept() || !cpu_has_vmx_ept_4levels()) { @@ -2788,14 +2944,16 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_ple()) ple_gap = 0; - if (!cpu_has_vmx_apic_register_virt() || - !cpu_has_vmx_virtual_intr_delivery()) - enable_apicv_reg_vid = 0; + if (!cpu_has_vmx_apicv()) + enable_apicv = 0; - if (enable_apicv_reg_vid) + if (enable_apicv) kvm_x86_ops->update_cr8_intercept = NULL; - else + else { kvm_x86_ops->hwapic_irr_update = NULL; + kvm_x86_ops->deliver_posted_interrupt = NULL; + kvm_x86_ops->sync_pir_to_irr = vmx_sync_pir_to_irr_dummy; + } if (nested) nested_vmx_setup_ctls_msrs(); @@ -2876,22 +3034,6 @@ static void enter_pmode(struct kvm_vcpu *vcpu) vmx->cpl = 0; } -static gva_t rmode_tss_base(struct kvm *kvm) -{ - if (!kvm->arch.tss_addr) { - struct kvm_memslots *slots; - struct kvm_memory_slot *slot; - gfn_t base_gfn; - - slots = kvm_memslots(kvm); - slot = id_to_memslot(slots, 0); - base_gfn = slot->base_gfn + slot->npages - 3; - - return base_gfn << PAGE_SHIFT; - } - return kvm->arch.tss_addr; -} - static void fix_rmode_seg(int seg, struct kvm_segment *save) { const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; @@ -2942,19 +3084,15 @@ static void enter_rmode(struct kvm_vcpu *vcpu) /* * Very old userspace does not call KVM_SET_TSS_ADDR before entering - * vcpu. Call it here with phys address pointing 16M below 4G. + * vcpu. Warn the user that an update is overdue. */ - if (!vcpu->kvm->arch.tss_addr) { + if (!vcpu->kvm->arch.tss_addr) printk_once(KERN_WARNING "kvm: KVM_SET_TSS_ADDR need to be " "called before entering vcpu\n"); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - vmx_set_tss_addr(vcpu->kvm, 0xfeffd000); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - } vmx_segment_cache_clear(vmx); - vmcs_writel(GUEST_TR_BASE, rmode_tss_base(vcpu->kvm)); + vmcs_writel(GUEST_TR_BASE, vcpu->kvm->arch.tss_addr); vmcs_write32(GUEST_TR_LIMIT, RMODE_TSS_SIZE - 1); vmcs_write32(GUEST_TR_AR_BYTES, 0x008b); @@ -3214,7 +3352,9 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) */ if (!nested_vmx_allowed(vcpu)) return 1; - } else if (to_vmx(vcpu)->nested.vmxon) + } + if (to_vmx(vcpu)->nested.vmxon && + ((cr4 & VMXON_CR4_ALWAYSON) != VMXON_CR4_ALWAYSON)) return 1; vcpu->arch.cr4 = cr4; @@ -3550,7 +3690,7 @@ static bool guest_state_valid(struct kvm_vcpu *vcpu) return true; /* real mode guest state checks */ - if (!is_protmode(vcpu)) { + if (!is_protmode(vcpu) || (vmx_get_rflags(vcpu) & X86_EFLAGS_VM)) { if (!rmode_segment_valid(vcpu, VCPU_SREG_CS)) return false; if (!rmode_segment_valid(vcpu, VCPU_SREG_SS)) @@ -3599,7 +3739,7 @@ static int init_rmode_tss(struct kvm *kvm) int r, idx, ret = 0; idx = srcu_read_lock(&kvm->srcu); - fn = rmode_tss_base(kvm) >> PAGE_SHIFT; + fn = kvm->arch.tss_addr >> PAGE_SHIFT; r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE); if (r < 0) goto out; @@ -3692,7 +3832,7 @@ static int alloc_apic_access_page(struct kvm *kvm) kvm_userspace_mem.flags = 0; kvm_userspace_mem.guest_phys_addr = 0xfee00000ULL; kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, false); + r = __kvm_set_memory_region(kvm, &kvm_userspace_mem); if (r) goto out; @@ -3722,7 +3862,7 @@ static int alloc_identity_pagetable(struct kvm *kvm) kvm_userspace_mem.guest_phys_addr = kvm->arch.ept_identity_map_addr; kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, false); + r = __kvm_set_memory_region(kvm, &kvm_userspace_mem); if (r) goto out; @@ -3869,13 +4009,59 @@ static void vmx_disable_intercept_msr_write_x2apic(u32 msr) msr, MSR_TYPE_W); } +static int vmx_vm_has_apicv(struct kvm *kvm) +{ + return enable_apicv && irqchip_in_kernel(kvm); +} + +/* + * Send interrupt to vcpu via posted interrupt way. + * 1. If target vcpu is running(non-root mode), send posted interrupt + * notification to vcpu and hardware will sync PIR to vIRR atomically. + * 2. If target vcpu isn't running(root mode), kick it to pick up the + * interrupt from PIR in next vmentry. + */ +static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + int r; + + if (pi_test_and_set_pir(vector, &vmx->pi_desc)) + return; + + r = pi_test_and_set_on(&vmx->pi_desc); + kvm_make_request(KVM_REQ_EVENT, vcpu); +#ifdef CONFIG_SMP + if (!r && (vcpu->mode == IN_GUEST_MODE)) + apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), + POSTED_INTR_VECTOR); + else +#endif + kvm_vcpu_kick(vcpu); +} + +static void vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (!pi_test_and_clear_on(&vmx->pi_desc)) + return; + + kvm_apic_update_irr(vcpu, vmx->pi_desc.pir); +} + +static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu) +{ + return; +} + /* * Set up the vmcs's constant host-state fields, i.e., host-state fields that * will not change in the lifetime of the guest. * Note that host-state that does change is set elsewhere. E.g., host-state * that is set differently for each CPU is set in vmx_vcpu_load(), not here. */ -static void vmx_set_constant_host_state(void) +static void vmx_set_constant_host_state(struct vcpu_vmx *vmx) { u32 low32, high32; unsigned long tmpl; @@ -3903,6 +4089,7 @@ static void vmx_set_constant_host_state(void) native_store_idt(&dt); vmcs_writel(HOST_IDTR_BASE, dt.address); /* 22.2.4 */ + vmx->host_idt_base = dt.address; vmcs_writel(HOST_RIP, vmx_return); /* 22.2.5 */ @@ -3928,6 +4115,15 @@ static void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) vmcs_writel(CR4_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr4_guest_owned_bits); } +static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) +{ + u32 pin_based_exec_ctrl = vmcs_config.pin_based_exec_ctrl; + + if (!vmx_vm_has_apicv(vmx->vcpu.kvm)) + pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR; + return pin_based_exec_ctrl; +} + static u32 vmx_exec_control(struct vcpu_vmx *vmx) { u32 exec_control = vmcs_config.cpu_based_exec_ctrl; @@ -3945,11 +4141,6 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx) return exec_control; } -static int vmx_vm_has_apicv(struct kvm *kvm) -{ - return enable_apicv_reg_vid && irqchip_in_kernel(kvm); -} - static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) { u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl; @@ -3971,6 +4162,12 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; + /* SECONDARY_EXEC_SHADOW_VMCS is enabled when L1 executes VMPTRLD + (handle_vmptrld). + We can NOT enable shadow_vmcs here because we don't have yet + a current VMCS12 + */ + exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; return exec_control; } @@ -3999,14 +4196,17 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write64(IO_BITMAP_A, __pa(vmx_io_bitmap_a)); vmcs_write64(IO_BITMAP_B, __pa(vmx_io_bitmap_b)); + if (enable_shadow_vmcs) { + vmcs_write64(VMREAD_BITMAP, __pa(vmx_vmread_bitmap)); + vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap)); + } if (cpu_has_vmx_msr_bitmap()) vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_legacy)); vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */ /* Control */ - vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, - vmcs_config.pin_based_exec_ctrl); + vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_ctrl(vmx)); vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, vmx_exec_control(vmx)); @@ -4015,13 +4215,16 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmx_secondary_exec_control(vmx)); } - if (enable_apicv_reg_vid) { + if (vmx_vm_has_apicv(vmx->vcpu.kvm)) { vmcs_write64(EOI_EXIT_BITMAP0, 0); vmcs_write64(EOI_EXIT_BITMAP1, 0); vmcs_write64(EOI_EXIT_BITMAP2, 0); vmcs_write64(EOI_EXIT_BITMAP3, 0); vmcs_write16(GUEST_INTR_STATUS, 0); + + vmcs_write64(POSTED_INTR_NV, POSTED_INTR_VECTOR); + vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc))); } if (ple_gap) { @@ -4035,7 +4238,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write16(HOST_FS_SELECTOR, 0); /* 22.2.4 */ vmcs_write16(HOST_GS_SELECTOR, 0); /* 22.2.4 */ - vmx_set_constant_host_state(); + vmx_set_constant_host_state(vmx); #ifdef CONFIG_X86_64 rdmsrl(MSR_FS_BASE, a); vmcs_writel(HOST_FS_BASE, a); /* 22.2.4 */ @@ -4089,11 +4292,10 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) return 0; } -static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) +static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u64 msr; - int ret; vmx->rmode.vm86_active = 0; @@ -4109,12 +4311,8 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmx_segment_cache_clear(vmx); seg_setup(VCPU_SREG_CS); - if (kvm_vcpu_is_bsp(&vmx->vcpu)) - vmcs_write16(GUEST_CS_SELECTOR, 0xf000); - else { - vmcs_write16(GUEST_CS_SELECTOR, vmx->vcpu.arch.sipi_vector << 8); - vmcs_writel(GUEST_CS_BASE, vmx->vcpu.arch.sipi_vector << 12); - } + vmcs_write16(GUEST_CS_SELECTOR, 0xf000); + vmcs_write32(GUEST_CS_BASE, 0xffff0000); seg_setup(VCPU_SREG_DS); seg_setup(VCPU_SREG_ES); @@ -4137,10 +4335,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_SYSENTER_EIP, 0); vmcs_writel(GUEST_RFLAGS, 0x02); - if (kvm_vcpu_is_bsp(&vmx->vcpu)) - kvm_rip_write(vcpu, 0xfff0); - else - kvm_rip_write(vcpu, 0); + kvm_rip_write(vcpu, 0xfff0); vmcs_writel(GUEST_GDTR_BASE, 0); vmcs_write32(GUEST_GDTR_LIMIT, 0xffff); @@ -4171,23 +4366,20 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_write64(APIC_ACCESS_ADDR, page_to_phys(vmx->vcpu.kvm->arch.apic_access_page)); + if (vmx_vm_has_apicv(vcpu->kvm)) + memset(&vmx->pi_desc, 0, sizeof(struct pi_desc)); + if (vmx->vpid != 0) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); vmx->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); vmx_set_cr0(&vmx->vcpu, kvm_read_cr0(vcpu)); /* enter rmode */ - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); vmx_set_cr4(&vmx->vcpu, 0); vmx_set_efer(&vmx->vcpu, 0); vmx_fpu_activate(&vmx->vcpu); update_exception_bitmap(&vmx->vcpu); vpid_sync_context(vmx); - - ret = 0; - - return ret; } /* @@ -4200,40 +4392,45 @@ static bool nested_exit_on_intr(struct kvm_vcpu *vcpu) PIN_BASED_EXT_INTR_MASK; } -static void enable_irq_window(struct kvm_vcpu *vcpu) +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) { u32 cpu_based_vm_exec_control; - if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) { + + 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. Ask L2 to exit - * right after entry, so we can inject to L1 more promptly. + * 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. */ - kvm_make_request(KVM_REQ_IMMEDIATE_EXIT, vcpu); - return; - } + 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 void enable_nmi_window(struct kvm_vcpu *vcpu) +static int enable_nmi_window(struct kvm_vcpu *vcpu) { u32 cpu_based_vm_exec_control; - if (!cpu_has_virtual_nmis()) { - enable_irq_window(vcpu); - return; - } + 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 (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) @@ -4294,16 +4491,6 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu) INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR); } -static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) -{ - if (!cpu_has_virtual_nmis() && to_vmx(vcpu)->soft_vnmi_blocked) - return 0; - - return !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & - (GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_STI - | GUEST_INTR_STATE_NMI)); -} - static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu) { if (!cpu_has_virtual_nmis()) @@ -4333,18 +4520,52 @@ 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 (!cpu_has_virtual_nmis() && to_vmx(vcpu)->soft_vnmi_blocked) + return 0; + + return !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & + (GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_STI + | GUEST_INTR_STATE_NMI)); +} + static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) { - if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) { + if (is_guest_mode(vcpu)) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - if (to_vmx(vcpu)->nested.nested_run_pending || - (vmcs12->idt_vectoring_info_field & - VECTORING_INFO_VALID_MASK)) + + if (to_vmx(vcpu)->nested.nested_run_pending) return 0; - 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 */ + 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) && @@ -4362,7 +4583,7 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) .flags = 0, }; - ret = kvm_set_memory_region(kvm, &tss_mem, false); + ret = kvm_set_memory_region(kvm, &tss_mem); if (ret) return ret; kvm->arch.tss_addr = addr; @@ -4603,34 +4824,50 @@ vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) /* called to set cr0 as appropriate for a mov-to-cr0 exit. */ static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val) { - if (to_vmx(vcpu)->nested.vmxon && - ((val & VMXON_CR0_ALWAYSON) != VMXON_CR0_ALWAYSON)) - return 1; - if (is_guest_mode(vcpu)) { + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + unsigned long orig_val = val; + /* * We get here when L2 changed cr0 in a way that did not change * any of L1's shadowed bits (see nested_vmx_exit_handled_cr), - * but did change L0 shadowed bits. This can currently happen - * with the TS bit: L0 may want to leave TS on (for lazy fpu - * loading) while pretending to allow the guest to change it. + * but did change L0 shadowed bits. So we first calculate the + * effective cr0 value that L1 would like to write into the + * hardware. It consists of the L2-owned bits from the new + * value combined with the L1-owned bits from L1's guest_cr0. */ - if (kvm_set_cr0(vcpu, (val & vcpu->arch.cr0_guest_owned_bits) | - (vcpu->arch.cr0 & ~vcpu->arch.cr0_guest_owned_bits))) + 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) return 1; - vmcs_writel(CR0_READ_SHADOW, val); + + if (kvm_set_cr0(vcpu, val)) + return 1; + vmcs_writel(CR0_READ_SHADOW, orig_val); return 0; - } else + } else { + if (to_vmx(vcpu)->nested.vmxon && + ((val & VMXON_CR0_ALWAYSON) != VMXON_CR0_ALWAYSON)) + return 1; return kvm_set_cr0(vcpu, val); + } } static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val) { if (is_guest_mode(vcpu)) { - if (kvm_set_cr4(vcpu, (val & vcpu->arch.cr4_guest_owned_bits) | - (vcpu->arch.cr4 & ~vcpu->arch.cr4_guest_owned_bits))) + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + unsigned long orig_val = val; + + /* analogously to handle_set_cr0 */ + val = (val & ~vmcs12->cr4_guest_host_mask) | + (vmcs12->guest_cr4 & vmcs12->cr4_guest_host_mask); + if (kvm_set_cr4(vcpu, val)) return 1; - vmcs_writel(CR4_READ_SHADOW, val); + vmcs_writel(CR4_READ_SHADOW, orig_val); return 0; } else return kvm_set_cr4(vcpu, val); @@ -5183,7 +5420,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (test_bit(KVM_REQ_EVENT, &vcpu->requests)) return 1; - err = emulate_instruction(vcpu, 0); + err = emulate_instruction(vcpu, EMULTYPE_NO_REEXECUTE); if (err == EMULATE_DO_MMIO) { ret = 0; @@ -5259,8 +5496,7 @@ static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx) } /* Create a new VMCS */ - item = (struct vmcs02_list *) - kmalloc(sizeof(struct vmcs02_list), GFP_KERNEL); + item = kmalloc(sizeof(struct vmcs02_list), GFP_KERNEL); if (!item) return NULL; item->vmcs02.vmcs = alloc_vmcs(); @@ -5309,6 +5545,9 @@ static void nested_free_all_saved_vmcss(struct vcpu_vmx *vmx) free_loaded_vmcs(&vmx->vmcs01); } +static void nested_vmx_failValid(struct kvm_vcpu *vcpu, + u32 vm_instruction_error); + /* * Emulate the VMXON instruction. * Currently, we just remember that VMX is active, and do not save or even @@ -5321,6 +5560,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu) { struct kvm_segment cs; struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vmcs *shadow_vmcs; /* The Intel VMX Instruction Reference lists a bunch of bits that * are prerequisite to running VMXON, most notably cr4.VMXE must be @@ -5344,6 +5584,21 @@ static int handle_vmon(struct kvm_vcpu *vcpu) kvm_inject_gp(vcpu, 0); return 1; } + if (vmx->nested.vmxon) { + nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION); + skip_emulated_instruction(vcpu); + return 1; + } + if (enable_shadow_vmcs) { + shadow_vmcs = alloc_vmcs(); + if (!shadow_vmcs) + return -ENOMEM; + /* mark vmcs as shadow */ + shadow_vmcs->revision_id |= (1u << 31); + /* init shadow vmcs */ + vmcs_clear(shadow_vmcs); + vmx->nested.current_shadow_vmcs = shadow_vmcs; + } INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool)); vmx->nested.vmcs02_num = 0; @@ -5384,6 +5639,25 @@ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu) return 1; } +static inline void nested_release_vmcs12(struct vcpu_vmx *vmx) +{ + u32 exec_control; + if (enable_shadow_vmcs) { + if (vmx->nested.current_vmcs12 != NULL) { + /* copy to memory all shadowed fields in case + they were modified */ + copy_shadow_to_vmcs12(vmx); + vmx->nested.sync_shadow_vmcs = false; + exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; + vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); + vmcs_write64(VMCS_LINK_POINTER, -1ull); + } + } + kunmap(vmx->nested.current_vmcs12_page); + nested_release_page(vmx->nested.current_vmcs12_page); +} + /* * Free whatever needs to be freed from vmx->nested when L1 goes down, or * just stops using VMX. @@ -5394,11 +5668,12 @@ static void free_nested(struct vcpu_vmx *vmx) return; vmx->nested.vmxon = false; if (vmx->nested.current_vmptr != -1ull) { - kunmap(vmx->nested.current_vmcs12_page); - nested_release_page(vmx->nested.current_vmcs12_page); + nested_release_vmcs12(vmx); vmx->nested.current_vmptr = -1ull; vmx->nested.current_vmcs12 = NULL; } + if (enable_shadow_vmcs) + free_vmcs(vmx->nested.current_shadow_vmcs); /* Unpin physical memory we referred to in current vmcs02 */ if (vmx->nested.apic_access_page) { nested_release_page(vmx->nested.apic_access_page); @@ -5507,6 +5782,10 @@ static void nested_vmx_failValid(struct kvm_vcpu *vcpu, X86_EFLAGS_SF | X86_EFLAGS_OF)) | X86_EFLAGS_ZF); get_vmcs12(vcpu)->vm_instruction_error = vm_instruction_error; + /* + * We don't need to force a shadow sync because + * VM_INSTRUCTION_ERROR is not shadowed + */ } /* Emulate the VMCLEAR instruction */ @@ -5539,8 +5818,7 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) } if (vmptr == vmx->nested.current_vmptr) { - kunmap(vmx->nested.current_vmcs12_page); - nested_release_page(vmx->nested.current_vmcs12_page); + nested_release_vmcs12(vmx); vmx->nested.current_vmptr = -1ull; vmx->nested.current_vmcs12 = NULL; } @@ -5639,6 +5917,111 @@ static inline bool vmcs12_read_any(struct kvm_vcpu *vcpu, } } + +static inline bool vmcs12_write_any(struct kvm_vcpu *vcpu, + unsigned long field, u64 field_value){ + short offset = vmcs_field_to_offset(field); + char *p = ((char *) get_vmcs12(vcpu)) + offset; + if (offset < 0) + return false; + + switch (vmcs_field_type(field)) { + case VMCS_FIELD_TYPE_U16: + *(u16 *)p = field_value; + return true; + case VMCS_FIELD_TYPE_U32: + *(u32 *)p = field_value; + return true; + case VMCS_FIELD_TYPE_U64: + *(u64 *)p = field_value; + return true; + case VMCS_FIELD_TYPE_NATURAL_WIDTH: + *(natural_width *)p = field_value; + return true; + default: + return false; /* can never happen. */ + } + +} + +static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx) +{ + int i; + unsigned long field; + u64 field_value; + struct vmcs *shadow_vmcs = vmx->nested.current_shadow_vmcs; + unsigned long *fields = (unsigned long *)shadow_read_write_fields; + int num_fields = max_shadow_read_write_fields; + + vmcs_load(shadow_vmcs); + + for (i = 0; i < num_fields; i++) { + field = fields[i]; + switch (vmcs_field_type(field)) { + case VMCS_FIELD_TYPE_U16: + field_value = vmcs_read16(field); + break; + case VMCS_FIELD_TYPE_U32: + field_value = vmcs_read32(field); + break; + case VMCS_FIELD_TYPE_U64: + field_value = vmcs_read64(field); + break; + case VMCS_FIELD_TYPE_NATURAL_WIDTH: + field_value = vmcs_readl(field); + break; + } + vmcs12_write_any(&vmx->vcpu, field, field_value); + } + + vmcs_clear(shadow_vmcs); + vmcs_load(vmx->loaded_vmcs->vmcs); +} + +static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) +{ + unsigned long *fields[] = { + (unsigned long *)shadow_read_write_fields, + (unsigned long *)shadow_read_only_fields + }; + int num_lists = ARRAY_SIZE(fields); + int max_fields[] = { + max_shadow_read_write_fields, + max_shadow_read_only_fields + }; + int i, q; + unsigned long field; + u64 field_value = 0; + struct vmcs *shadow_vmcs = vmx->nested.current_shadow_vmcs; + + vmcs_load(shadow_vmcs); + + for (q = 0; q < num_lists; q++) { + for (i = 0; i < max_fields[q]; i++) { + field = fields[q][i]; + vmcs12_read_any(&vmx->vcpu, field, &field_value); + + switch (vmcs_field_type(field)) { + case VMCS_FIELD_TYPE_U16: + vmcs_write16(field, (u16)field_value); + break; + case VMCS_FIELD_TYPE_U32: + vmcs_write32(field, (u32)field_value); + break; + case VMCS_FIELD_TYPE_U64: + vmcs_write64(field, (u64)field_value); + break; + case VMCS_FIELD_TYPE_NATURAL_WIDTH: + vmcs_writel(field, (long)field_value); + break; + } + } + } + + vmcs_clear(shadow_vmcs); + vmcs_load(vmx->loaded_vmcs->vmcs); +} + /* * VMX instructions which assume a current vmcs12 (i.e., that VMPTRLD was * used before) all generate the same failure when it is missing. @@ -5703,8 +6086,6 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) gva_t gva; unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - char *p; - short offset; /* The value to write might be 32 or 64 bits, depending on L1's long * mode, and eventually we need to write that into a field of several * possible lengths. The code below first zero-extends the value to 64 @@ -5741,28 +6122,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) return 1; } - offset = vmcs_field_to_offset(field); - if (offset < 0) { - nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); - skip_emulated_instruction(vcpu); - return 1; - } - p = ((char *) get_vmcs12(vcpu)) + offset; - - switch (vmcs_field_type(field)) { - case VMCS_FIELD_TYPE_U16: - *(u16 *)p = field_value; - break; - case VMCS_FIELD_TYPE_U32: - *(u32 *)p = field_value; - break; - case VMCS_FIELD_TYPE_U64: - *(u64 *)p = field_value; - break; - case VMCS_FIELD_TYPE_NATURAL_WIDTH: - *(natural_width *)p = field_value; - break; - default: + if (!vmcs12_write_any(vcpu, field, field_value)) { nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); skip_emulated_instruction(vcpu); return 1; @@ -5780,6 +6140,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) gva_t gva; gpa_t vmptr; struct x86_exception e; + u32 exec_control; if (!nested_vmx_check_permission(vcpu)) return 1; @@ -5818,14 +6179,20 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) skip_emulated_instruction(vcpu); return 1; } - if (vmx->nested.current_vmptr != -1ull) { - kunmap(vmx->nested.current_vmcs12_page); - nested_release_page(vmx->nested.current_vmcs12_page); - } + if (vmx->nested.current_vmptr != -1ull) + nested_release_vmcs12(vmx); vmx->nested.current_vmptr = vmptr; vmx->nested.current_vmcs12 = new_vmcs12; vmx->nested.current_vmcs12_page = page; + if (enable_shadow_vmcs) { + exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + exec_control |= SECONDARY_EXEC_SHADOW_VMCS; + vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); + vmcs_write64(VMCS_LINK_POINTER, + __pa(vmx->nested.current_shadow_vmcs)); + vmx->nested.sync_shadow_vmcs = true; + } } nested_vmx_succeed(vcpu); @@ -5908,6 +6275,52 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { static const int kvm_vmx_max_exit_handlers = ARRAY_SIZE(kvm_vmx_exit_handlers); +static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + unsigned long exit_qualification; + gpa_t bitmap, last_bitmap; + unsigned int port; + 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; + + exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + + port = exit_qualification >> 16; + size = (exit_qualification & 7) + 1; + + last_bitmap = (gpa_t)-1; + b = -1; + + while (size > 0) { + if (port < 0x8000) + bitmap = vmcs12->io_bitmap_a; + else if (port < 0x10000) + bitmap = vmcs12->io_bitmap_b; + else + return 1; + bitmap += (port & 0x7fff) / 8; + + if (last_bitmap != bitmap) + if (kvm_read_guest(vcpu->kvm, bitmap, &b, 1)) + return 1; + if (b & (1 << (port & 7))) + return 1; + + port++; + size--; + last_bitmap = bitmap; + } + + return 0; +} + /* * Return 1 if we should exit from L2 to L1 to handle an MSR access access, * rather than handle it ourselves in L0. I.e., check whether L1 expressed @@ -5939,7 +6352,8 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, /* Then read the msr_index'th bit from this bitmap: */ if (msr_index < 1024*8) { unsigned char b; - kvm_read_guest(vcpu->kvm, bitmap + msr_index/8, &b, 1); + if (kvm_read_guest(vcpu->kvm, bitmap + msr_index/8, &b, 1)) + return 1; return 1 & (b >> (msr_index & 7)); } else return 1; /* let L1 handle the wrong parameter */ @@ -6033,10 +6447,10 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, */ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) { - u32 exit_reason = vmcs_read32(VM_EXIT_REASON); u32 intr_info = vmcs_read32(VM_EXIT_INTR_INFO); struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + u32 exit_reason = vmx->exit_reason; if (vmx->nested.nested_run_pending) return 0; @@ -6060,14 +6474,9 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_TRIPLE_FAULT: return 1; case EXIT_REASON_PENDING_INTERRUPT: + return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_INTR_PENDING); case EXIT_REASON_NMI_WINDOW: - /* - * prepare_vmcs02() set the CPU_BASED_VIRTUAL_INTR_PENDING bit - * (aka Interrupt Window Exiting) only when L1 turned it on, - * so if we got a PENDING_INTERRUPT exit, this must be for L1. - * Same for NMI Window Exiting. - */ - return 1; + return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING); case EXIT_REASON_TASK_SWITCH: return 1; case EXIT_REASON_CPUID: @@ -6097,8 +6506,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_DR_ACCESS: return nested_cpu_has(vmcs12, CPU_BASED_MOV_DR_EXITING); case EXIT_REASON_IO_INSTRUCTION: - /* TODO: support IO bitmaps */ - return 1; + return nested_vmx_exit_handled_io(vcpu, vmcs12); case EXIT_REASON_MSR_READ: case EXIT_REASON_MSR_WRITE: return nested_vmx_exit_handled_msr(vcpu, vmcs12, exit_reason); @@ -6122,6 +6530,9 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_EPT_VIOLATION: case EXIT_REASON_EPT_MISCONFIG: 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: @@ -6316,6 +6727,9 @@ static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { + if (!vmx_vm_has_apicv(vcpu->kvm)) + return; + vmcs_write64(EOI_EXIT_BITMAP0, eoi_exit_bitmap[0]); vmcs_write64(EOI_EXIT_BITMAP1, eoi_exit_bitmap[1]); vmcs_write64(EOI_EXIT_BITMAP2, eoi_exit_bitmap[2]); @@ -6346,6 +6760,52 @@ static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx) } } +static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) +{ + u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); + + /* + * If external interrupt exists, IF bit is set in rflags/eflags on the + * interrupt stack frame, and interrupt will be enabled on a return + * from interrupt handler. + */ + if ((exit_intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK)) + == (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR)) { + unsigned int vector; + unsigned long entry; + gate_desc *desc; + struct vcpu_vmx *vmx = to_vmx(vcpu); +#ifdef CONFIG_X86_64 + unsigned long tmp; +#endif + + vector = exit_intr_info & INTR_INFO_VECTOR_MASK; + desc = (gate_desc *)vmx->host_idt_base + vector; + entry = gate_offset(*desc); + asm volatile( +#ifdef CONFIG_X86_64 + "mov %%" _ASM_SP ", %[sp]\n\t" + "and $0xfffffffffffffff0, %%" _ASM_SP "\n\t" + "push $%c[ss]\n\t" + "push %[sp]\n\t" +#endif + "pushf\n\t" + "orl $0x200, (%%" _ASM_SP ")\n\t" + __ASM_SIZE(push) " $%c[cs]\n\t" + "call *%[entry]\n\t" + : +#ifdef CONFIG_X86_64 + [sp]"=&r"(tmp) +#endif + : + [entry]"r"(entry), + [ss]"i"(__KERNEL_DS), + [cs]"i"(__KERNEL_CS) + ); + } else + local_irq_enable(); +} + static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) { u32 exit_intr_info; @@ -6388,7 +6848,7 @@ static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) ktime_to_ns(ktime_sub(ktime_get(), vmx->entry_time)); } -static void __vmx_complete_interrupts(struct vcpu_vmx *vmx, +static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu, u32 idt_vectoring_info, int instr_len_field, int error_code_field) @@ -6399,46 +6859,43 @@ static void __vmx_complete_interrupts(struct vcpu_vmx *vmx, idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK; - vmx->vcpu.arch.nmi_injected = false; - kvm_clear_exception_queue(&vmx->vcpu); - kvm_clear_interrupt_queue(&vmx->vcpu); + vcpu->arch.nmi_injected = false; + kvm_clear_exception_queue(vcpu); + kvm_clear_interrupt_queue(vcpu); if (!idtv_info_valid) return; - kvm_make_request(KVM_REQ_EVENT, &vmx->vcpu); + kvm_make_request(KVM_REQ_EVENT, vcpu); vector = idt_vectoring_info & VECTORING_INFO_VECTOR_MASK; type = idt_vectoring_info & VECTORING_INFO_TYPE_MASK; switch (type) { case INTR_TYPE_NMI_INTR: - vmx->vcpu.arch.nmi_injected = true; + vcpu->arch.nmi_injected = true; /* * SDM 3: 27.7.1.2 (September 2008) * Clear bit "block by NMI" before VM entry if a NMI * delivery faulted. */ - vmx_set_nmi_mask(&vmx->vcpu, false); + vmx_set_nmi_mask(vcpu, false); break; case INTR_TYPE_SOFT_EXCEPTION: - vmx->vcpu.arch.event_exit_inst_len = - vmcs_read32(instr_len_field); + vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); /* fall through */ 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(&vmx->vcpu, vector, err); + kvm_queue_exception_e(vcpu, vector, err); } else - kvm_queue_exception(&vmx->vcpu, vector); + kvm_queue_exception(vcpu, vector); break; case INTR_TYPE_SOFT_INTR: - vmx->vcpu.arch.event_exit_inst_len = - vmcs_read32(instr_len_field); + vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); /* fall through */ case INTR_TYPE_EXT_INTR: - kvm_queue_interrupt(&vmx->vcpu, vector, - type == INTR_TYPE_SOFT_INTR); + kvm_queue_interrupt(vcpu, vector, type == INTR_TYPE_SOFT_INTR); break; default: break; @@ -6447,18 +6904,14 @@ static void __vmx_complete_interrupts(struct vcpu_vmx *vmx, static void vmx_complete_interrupts(struct vcpu_vmx *vmx) { - if (is_guest_mode(&vmx->vcpu)) - return; - __vmx_complete_interrupts(vmx, vmx->idt_vectoring_info, + __vmx_complete_interrupts(&vmx->vcpu, vmx->idt_vectoring_info, VM_EXIT_INSTRUCTION_LEN, IDT_VECTORING_ERROR_CODE); } static void vmx_cancel_injection(struct kvm_vcpu *vcpu) { - if (is_guest_mode(vcpu)) - return; - __vmx_complete_interrupts(to_vmx(vcpu), + __vmx_complete_interrupts(vcpu, vmcs_read32(VM_ENTRY_INTR_INFO_FIELD), VM_ENTRY_INSTRUCTION_LEN, VM_ENTRY_EXCEPTION_ERROR_CODE); @@ -6489,21 +6942,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long debugctlmsr; - if (is_guest_mode(vcpu) && !vmx->nested.nested_run_pending) { - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - if (vmcs12->idt_vectoring_info_field & - VECTORING_INFO_VALID_MASK) { - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, - vmcs12->idt_vectoring_info_field); - vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, - vmcs12->vm_exit_instruction_len); - if (vmcs12->idt_vectoring_info_field & - VECTORING_INFO_DELIVER_CODE_MASK) - vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, - vmcs12->idt_vectoring_error_code); - } - } - /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked)) vmx->entry_time = ktime_get(); @@ -6513,6 +6951,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vmx->emulation_required) return; + if (vmx->nested.sync_shadow_vmcs) { + copy_vmcs12_to_shadow(vmx); + vmx->nested.sync_shadow_vmcs = false; + } + if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty)) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty)) @@ -6662,17 +7105,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); - if (is_guest_mode(vcpu)) { - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - vmcs12->idt_vectoring_info_field = vmx->idt_vectoring_info; - if (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK) { - vmcs12->idt_vectoring_error_code = - vmcs_read32(IDT_VECTORING_ERROR_CODE); - vmcs12->vm_exit_instruction_len = - vmcs_read32(VM_EXIT_INSTRUCTION_LEN); - } - } - vmx->loaded_vmcs->launched = 1; vmx->exit_reason = vmcs_read32(VM_EXIT_REASON); @@ -6734,10 +7166,11 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) put_cpu(); if (err) goto free_vmcs; - if (vm_need_virtualize_apic_accesses(kvm)) + if (vm_need_virtualize_apic_accesses(kvm)) { err = alloc_apic_access_page(kvm); if (err) goto free_vmcs; + } if (enable_ept) { if (!kvm->arch.ept_identity_map_addr) @@ -6931,9 +7364,8 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->vm_entry_instruction_len); vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, vmcs12->guest_interruptibility_info); - vmcs_write32(GUEST_ACTIVITY_STATE, vmcs12->guest_activity_state); vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs); - vmcs_writel(GUEST_DR7, vmcs12->guest_dr7); + kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); vmcs_writel(GUEST_RFLAGS, vmcs12->guest_rflags); vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, vmcs12->guest_pending_dbg_exceptions); @@ -6946,6 +7378,10 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) (vmcs_config.pin_based_exec_ctrl | vmcs12->pin_based_vm_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); + /* * Whether page-faults are trapped is determined by a combination of * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF. @@ -7016,7 +7452,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) * Other fields are different per CPU, and will be set later when * vmx_vcpu_load() is called, and when vmx_save_host_state() is called. */ - vmx_set_constant_host_state(); + vmx_set_constant_host_state(vmx); /* * HOST_RSP is normally set correctly in vmx_vcpu_run() just before @@ -7082,7 +7518,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER) vcpu->arch.efer = vmcs12->guest_ia32_efer; - if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) + else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) vcpu->arch.efer |= (EFER_LMA | EFER_LME); else vcpu->arch.efer &= ~(EFER_LMA | EFER_LME); @@ -7121,6 +7557,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) struct vcpu_vmx *vmx = to_vmx(vcpu); int cpu; struct loaded_vmcs *vmcs02; + bool ia32e; if (!nested_vmx_check_permission(vcpu) || !nested_vmx_check_vmcs12(vcpu)) @@ -7129,6 +7566,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) skip_emulated_instruction(vcpu); vmcs12 = get_vmcs12(vcpu); + if (enable_shadow_vmcs) + copy_shadow_to_vmcs12(vmx); + /* * The nested entry process starts with enforcing various prerequisites * on vmcs12 as required by the Intel SDM, and act appropriately when @@ -7146,6 +7586,11 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) return 1; } + if (vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE) { + nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); + return 1; + } + if ((vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_MSR_BITMAPS) && !IS_ALIGNED(vmcs12->msr_bitmap, PAGE_SIZE)) { /*TODO: Also verify bits beyond physical address width are 0*/ @@ -7204,6 +7649,45 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) } /* + * If the load IA32_EFER VM-entry control is 1, the following checks + * are performed on the field for the IA32_EFER MSR: + * - Bits reserved in the IA32_EFER MSR must be 0. + * - Bit 10 (corresponding to IA32_EFER.LMA) must equal the value of + * the IA-32e mode guest VM-exit control. It must also be identical + * to bit 8 (LME) if bit 31 in the CR0 field (corresponding to + * CR0.PG) is 1. + */ + if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER) { + ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0; + if (!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer) || + ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA) || + ((vmcs12->guest_cr0 & X86_CR0_PG) && + ia32e != !!(vmcs12->guest_ia32_efer & EFER_LME))) { + nested_vmx_entry_failure(vcpu, vmcs12, + EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT); + return 1; + } + } + + /* + * If the load IA32_EFER VM-exit control is 1, bits reserved in the + * IA32_EFER MSR must be 0 in the field for that register. In addition, + * the values of the LMA and LME bits in the field must each be that of + * the host address-space size VM-exit control. + */ + if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) { + ia32e = (vmcs12->vm_exit_controls & + VM_EXIT_HOST_ADDR_SPACE_SIZE) != 0; + if (!kvm_valid_efer(vcpu, vmcs12->host_ia32_efer) || + ia32e != !!(vmcs12->host_ia32_efer & EFER_LMA) || + ia32e != !!(vmcs12->host_ia32_efer & EFER_LME)) { + nested_vmx_entry_failure(vcpu, vmcs12, + EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT); + return 1; + } + } + + /* * We're finally done with prerequisite checking, and can start with * the nested entry. */ @@ -7223,6 +7707,8 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) vcpu->cpu = cpu; put_cpu(); + vmx_segment_cache_clear(vmx); + vmcs12->launch_state = 1; prepare_vmcs02(vcpu, vmcs12); @@ -7273,6 +7759,48 @@ vmcs12_guest_cr4(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vcpu->arch.cr4_guest_owned_bits)); } +static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + u32 idt_vectoring; + unsigned int nr; + + if (vcpu->arch.exception.pending) { + nr = vcpu->arch.exception.nr; + idt_vectoring = nr | VECTORING_INFO_VALID_MASK; + + if (kvm_exception_is_soft(nr)) { + vmcs12->vm_exit_instruction_len = + vcpu->arch.event_exit_inst_len; + idt_vectoring |= INTR_TYPE_SOFT_EXCEPTION; + } else + idt_vectoring |= INTR_TYPE_HARD_EXCEPTION; + + if (vcpu->arch.exception.has_error_code) { + idt_vectoring |= VECTORING_INFO_DELIVER_CODE_MASK; + vmcs12->idt_vectoring_error_code = + vcpu->arch.exception.error_code; + } + + vmcs12->idt_vectoring_info_field = idt_vectoring; + } else if (vcpu->arch.nmi_pending) { + vmcs12->idt_vectoring_info_field = + INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR; + } else if (vcpu->arch.interrupt.pending) { + nr = vcpu->arch.interrupt.nr; + idt_vectoring = nr | VECTORING_INFO_VALID_MASK; + + if (vcpu->arch.interrupt.soft) { + idt_vectoring |= INTR_TYPE_SOFT_INTR; + vmcs12->vm_entry_instruction_len = + vcpu->arch.event_exit_inst_len; + } else + idt_vectoring |= INTR_TYPE_EXT_INTR; + + vmcs12->idt_vectoring_info_field = idt_vectoring; + } +} + /* * 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), @@ -7284,7 +7812,7 @@ vmcs12_guest_cr4(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) * exit-information fields only. Other fields are modified by L1 with VMWRITE, * which already writes to vmcs12 directly. */ -void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) +static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { /* update guest state fields: */ vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12); @@ -7332,16 +7860,19 @@ void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_gdtr_base = vmcs_readl(GUEST_GDTR_BASE); vmcs12->guest_idtr_base = vmcs_readl(GUEST_IDTR_BASE); - vmcs12->guest_activity_state = vmcs_read32(GUEST_ACTIVITY_STATE); vmcs12->guest_interruptibility_info = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); vmcs12->guest_pending_dbg_exceptions = vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS); + vmcs12->vm_entry_controls = + (vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) | + (vmcs_read32(VM_ENTRY_CONTROLS) & 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_entry_controls & VM_EXIT_SAVE_IA32_PAT) + if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_PAT) vmcs12->guest_ia32_pat = vmcs_read64(GUEST_IA32_PAT); vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS); vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP); @@ -7349,21 +7880,38 @@ void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) /* update exit information fields: */ - vmcs12->vm_exit_reason = vmcs_read32(VM_EXIT_REASON); + vmcs12->vm_exit_reason = to_vmx(vcpu)->exit_reason; vmcs12->exit_qualification = vmcs_readl(EXIT_QUALIFICATION); vmcs12->vm_exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - vmcs12->vm_exit_intr_error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); - vmcs12->idt_vectoring_info_field = - vmcs_read32(IDT_VECTORING_INFO_FIELD); - vmcs12->idt_vectoring_error_code = - vmcs_read32(IDT_VECTORING_ERROR_CODE); + if ((vmcs12->vm_exit_intr_info & + (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) == + (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) + vmcs12->vm_exit_intr_error_code = + vmcs_read32(VM_EXIT_INTR_ERROR_CODE); + vmcs12->idt_vectoring_info_field = 0; vmcs12->vm_exit_instruction_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - /* clear vm-entry fields which are to be cleared on exit */ - if (!(vmcs12->vm_exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) + if (!(vmcs12->vm_exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) { + /* vm_entry_intr_info_field is cleared on exit. Emulate this + * instead of reading the real value. */ vmcs12->vm_entry_intr_info_field &= ~INTR_INFO_VALID_MASK; + + /* + * Transfer the event that L0 or L1 may wanted to inject into + * L2 to IDT_VECTORING_INFO_FIELD. + */ + vmcs12_save_pending_event(vcpu, vmcs12); + } + + /* + * Drop what we picked up for L2 via vmx_complete_interrupts. It is + * preserved above and would only end up incorrectly in L1. + */ + vcpu->arch.nmi_injected = false; + kvm_clear_exception_queue(vcpu); + kvm_clear_interrupt_queue(vcpu); } /* @@ -7375,11 +7923,12 @@ void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) * Failures During or After Loading Guest State"). * This function should be called when the active VMCS is L1's (vmcs01). */ -void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) +static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) { if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) vcpu->arch.efer = vmcs12->host_ia32_efer; - if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) + else if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) vcpu->arch.efer |= (EFER_LMA | EFER_LME); else vcpu->arch.efer &= ~(EFER_LMA | EFER_LME); @@ -7387,6 +7936,7 @@ void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->host_rsp); kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->host_rip); + vmx_set_rflags(vcpu, X86_EFLAGS_BIT1); /* * Note that calling vmx_set_cr0 is important, even if cr0 hasn't * actually changed, because it depends on the current state of @@ -7445,6 +7995,9 @@ void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL, vmcs12->host_ia32_perf_global_ctrl); + + kvm_set_dr(vcpu, 7, 0x400); + vmcs_write64(GUEST_IA32_DEBUGCTL, 0); } /* @@ -7458,6 +8011,9 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu) int cpu; struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + /* trying to cancel vmlaunch/vmresume is a bug */ + WARN_ON_ONCE(vmx->nested.nested_run_pending); + leave_guest_mode(vcpu); prepare_vmcs12(vcpu, vmcs12); @@ -7468,6 +8024,8 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu) vcpu->cpu = cpu; put_cpu(); + vmx_segment_cache_clear(vmx); + /* if no vmcs02 cache requested, remove the one we used */ if (VMCS02_POOL_SIZE == 0) nested_free_vmcs02(vmx, vmx->nested.current_vmptr); @@ -7496,6 +8054,8 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu) nested_vmx_failValid(vcpu, vmcs_read32(VM_INSTRUCTION_ERROR)); } else nested_vmx_succeed(vcpu); + if (enable_shadow_vmcs) + vmx->nested.sync_shadow_vmcs = true; } /* @@ -7513,6 +8073,8 @@ static void nested_vmx_entry_failure(struct kvm_vcpu *vcpu, vmcs12->vm_exit_reason = reason | VMX_EXIT_REASONS_FAILED_VMENTRY; vmcs12->exit_qualification = qualification; nested_vmx_succeed(vcpu); + if (enable_shadow_vmcs) + to_vmx(vcpu)->nested.sync_shadow_vmcs = true; } static int vmx_check_intercept(struct kvm_vcpu *vcpu, @@ -7590,6 +8152,8 @@ static struct kvm_x86_ops vmx_x86_ops = { .load_eoi_exitmap = vmx_load_eoi_exitmap, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, + .sync_pir_to_irr = vmx_sync_pir_to_irr, + .deliver_posted_interrupt = vmx_deliver_posted_interrupt, .set_tss_addr = vmx_set_tss_addr, .get_tdp_level = get_ept_level, @@ -7618,6 +8182,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .set_tdp_cr3 = vmx_set_cr3, .check_intercept = vmx_check_intercept, + .handle_external_intr = vmx_handle_external_intr, }; static int __init vmx_init(void) @@ -7656,6 +8221,24 @@ static int __init vmx_init(void) (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_msr_bitmap_longmode_x2apic) goto out4; + vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); + if (!vmx_vmread_bitmap) + goto out5; + + vmx_vmwrite_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); + if (!vmx_vmwrite_bitmap) + goto out6; + + 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 @@ -7674,7 +8257,7 @@ static int __init vmx_init(void) r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), __alignof__(struct vcpu_vmx), THIS_MODULE); if (r) - goto out3; + goto out7; #ifdef CONFIG_KEXEC rcu_assign_pointer(crash_vmclear_loaded_vmcss, @@ -7692,7 +8275,7 @@ static int __init vmx_init(void) memcpy(vmx_msr_bitmap_longmode_x2apic, vmx_msr_bitmap_longmode, PAGE_SIZE); - if (enable_apicv_reg_vid) { + if (enable_apicv) { for (msr = 0x800; msr <= 0x8ff; msr++) vmx_disable_intercept_msr_read_x2apic(msr); @@ -7722,6 +8305,12 @@ static int __init vmx_init(void) return 0; +out7: + free_page((unsigned long)vmx_vmwrite_bitmap); +out6: + free_page((unsigned long)vmx_vmread_bitmap); +out5: + free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic); out4: free_page((unsigned long)vmx_msr_bitmap_longmode); out3: @@ -7743,6 +8332,8 @@ static void __exit vmx_exit(void) free_page((unsigned long)vmx_msr_bitmap_longmode); free_page((unsigned long)vmx_io_bitmap_b); free_page((unsigned long)vmx_io_bitmap_a); + free_page((unsigned long)vmx_vmwrite_bitmap); + free_page((unsigned long)vmx_vmread_bitmap); #ifdef CONFIG_KEXEC rcu_assign_pointer(crash_vmclear_loaded_vmcss, NULL); |