diff options
Diffstat (limited to 'arch/x86/kvm')
| -rw-r--r-- | arch/x86/kvm/Kconfig | 1 | ||||
| -rw-r--r-- | arch/x86/kvm/cpuid.h | 1 | ||||
| -rw-r--r-- | arch/x86/kvm/emulate.c | 17 | ||||
| -rw-r--r-- | arch/x86/kvm/lapic.c | 4 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu.c | 2 | ||||
| -rw-r--r-- | arch/x86/kvm/svm.c | 38 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx.c | 412 | ||||
| -rw-r--r-- | arch/x86/kvm/x86.c | 53 |
8 files changed, 304 insertions, 224 deletions
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 3ea624452f93..3c48bc8bf08c 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -23,6 +23,7 @@ config KVM depends on HIGH_RES_TIMERS # for TASKSTATS/TASK_DELAY_ACCT: depends on NET && MULTIUSER + depends on X86_LOCAL_APIC select PREEMPT_NOTIFIERS select MMU_NOTIFIER select ANON_INODES diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 1ea3c0e1e3a9..0bc5c1315708 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -59,7 +59,6 @@ static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned x86_feature) { unsigned x86_leaf = x86_feature / 32; - BUILD_BUG_ON(!__builtin_constant_p(x86_leaf)); BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid)); BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 16bf6655aa85..d90cdc77e077 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -425,8 +425,10 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)); #op " %al \n\t" \ FOP_RET -asm(".global kvm_fastop_exception \n" - "kvm_fastop_exception: xor %esi, %esi; ret"); +asm(".pushsection .fixup, \"ax\"\n" + ".global kvm_fastop_exception \n" + "kvm_fastop_exception: xor %esi, %esi; ret\n" + ".popsection"); FOP_START(setcc) FOP_SETCC(seto) @@ -4102,10 +4104,12 @@ static int check_cr_write(struct x86_emulate_ctxt *ctxt) ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); if (efer & EFER_LMA) { u64 maxphyaddr; - u32 eax = 0x80000008; + u32 eax, ebx, ecx, edx; - if (ctxt->ops->get_cpuid(ctxt, &eax, NULL, NULL, - NULL, false)) + eax = 0x80000008; + ecx = 0; + if (ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, + &edx, false)) maxphyaddr = eax & 0xff; else maxphyaddr = 36; @@ -5296,7 +5300,6 @@ static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt, static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) { - register void *__sp asm(_ASM_SP); ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF; if (!(ctxt->d & ByteOp)) @@ -5304,7 +5307,7 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n" : "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags), - [fastop]"+S"(fop), "+r"(__sp) + [fastop]"+S"(fop), ASM_CALL_CONSTRAINT : "c"(ctxt->src2.val)); ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index aaf10b6f5380..69c5612be786 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1324,6 +1324,10 @@ static void apic_timer_expired(struct kvm_lapic *apic) atomic_inc(&apic->lapic_timer.pending); kvm_set_pending_timer(vcpu); + /* + * For x86, the atomic_inc() is serialized, thus + * using swait_active() is safe. + */ if (swait_active(q)) swake_up(q); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index eca30c1eb1d9..106d4a029a8a 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3837,7 +3837,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, case KVM_PV_REASON_PAGE_NOT_PRESENT: vcpu->arch.apf.host_apf_reason = 0; local_irq_disable(); - kvm_async_pf_task_wait(fault_address); + kvm_async_pf_task_wait(fault_address, 0); local_irq_enable(); break; case KVM_PV_REASON_PAGE_READY: diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 2c1cfe68a9af..0e68f0b3cbf7 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1200,7 +1200,6 @@ static void avic_init_vmcb(struct vcpu_svm *svm) vmcb->control.avic_physical_id = ppa & AVIC_HPA_MASK; vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID_COUNT; vmcb->control.int_ctl |= AVIC_ENABLE_MASK; - svm->vcpu.arch.apicv_active = true; } static void init_vmcb(struct vcpu_svm *svm) @@ -1316,7 +1315,7 @@ static void init_vmcb(struct vcpu_svm *svm) set_intercept(svm, INTERCEPT_PAUSE); } - if (avic) + if (kvm_vcpu_apicv_active(&svm->vcpu)) avic_init_vmcb(svm); /* @@ -1600,6 +1599,23 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) avic_update_vapic_bar(svm, APIC_DEFAULT_PHYS_BASE); } +static int avic_init_vcpu(struct vcpu_svm *svm) +{ + int ret; + + if (!kvm_vcpu_apicv_active(&svm->vcpu)) + return 0; + + ret = avic_init_backing_page(&svm->vcpu); + if (ret) + return ret; + + INIT_LIST_HEAD(&svm->ir_list); + spin_lock_init(&svm->ir_list_lock); + + return ret; +} + static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) { struct vcpu_svm *svm; @@ -1636,14 +1652,9 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) if (!hsave_page) goto free_page3; - if (avic) { - err = avic_init_backing_page(&svm->vcpu); - if (err) - goto free_page4; - - INIT_LIST_HEAD(&svm->ir_list); - spin_lock_init(&svm->ir_list_lock); - } + err = avic_init_vcpu(svm); + if (err) + goto free_page4; /* We initialize this flag to true to make sure that the is_running * bit would be set the first time the vcpu is loaded. @@ -4395,9 +4406,9 @@ static void svm_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) return; } -static bool svm_get_enable_apicv(void) +static bool svm_get_enable_apicv(struct kvm_vcpu *vcpu) { - return avic; + return avic && irqchip_split(vcpu->kvm); } static void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) @@ -4414,7 +4425,7 @@ static void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb; - if (!avic) + if (!kvm_vcpu_apicv_active(&svm->vcpu)) return; vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK; @@ -5302,6 +5313,7 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu, */ if (info->rep_prefix != REPE_PREFIX) goto out; + break; case SVM_EXIT_IOIO: { u64 exit_info; u32 bytes; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 4253adef9044..a2b804e10c95 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -200,6 +200,8 @@ struct loaded_vmcs { int cpu; bool launched; bool nmi_known_unmasked; + unsigned long vmcs_host_cr3; /* May not match real cr3 */ + unsigned long vmcs_host_cr4; /* May not match real cr4 */ struct list_head loaded_vmcss_on_cpu_link; }; @@ -600,8 +602,6 @@ struct vcpu_vmx { int gs_ldt_reload_needed; int fs_reload_needed; u64 msr_host_bndcfgs; - unsigned long vmcs_host_cr3; /* May not match real cr3 */ - unsigned long vmcs_host_cr4; /* May not match real cr4 */ } host_state; struct { int vm86_active; @@ -2202,46 +2202,44 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) struct pi_desc old, new; unsigned int dest; - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + /* + * In case of hot-plug or hot-unplug, we may have to undo + * vmx_vcpu_pi_put even if there is no assigned device. And we + * always keep PI.NDST up to date for simplicity: it makes the + * code easier, and CPU migration is not a fast path. + */ + if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu) return; + /* + * First handle the simple case where no cmpxchg is necessary; just + * allow posting non-urgent interrupts. + * + * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change + * PI.NDST: pi_post_block will do it for us and the wakeup_handler + * expects the VCPU to be on the blocked_vcpu_list that matches + * PI.NDST. + */ + if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || + vcpu->cpu == cpu) { + pi_clear_sn(pi_desc); + return; + } + + /* The full case. */ do { old.control = new.control = pi_desc->control; - /* - * If 'nv' field is POSTED_INTR_WAKEUP_VECTOR, there - * are two possible cases: - * 1. After running 'pre_block', context switch - * happened. For this case, 'sn' was set in - * vmx_vcpu_put(), so we need to clear it here. - * 2. After running 'pre_block', we were blocked, - * and woken up by some other guy. For this case, - * we don't need to do anything, 'pi_post_block' - * will do everything for us. However, we cannot - * check whether it is case #1 or case #2 here - * (maybe, not needed), so we also clear sn here, - * I think it is not a big deal. - */ - if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR) { - if (vcpu->cpu != cpu) { - dest = cpu_physical_id(cpu); - - if (x2apic_enabled()) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; - } + dest = cpu_physical_id(cpu); - /* set 'NV' to 'notification vector' */ - new.nv = POSTED_INTR_VECTOR; - } + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; - /* Allow posting non-urgent interrupts */ new.sn = 0; - } while (cmpxchg(&pi_desc->control, old.control, - new.control) != old.control); + } while (cmpxchg64(&pi_desc->control, old.control, + new.control) != old.control); } static void decache_tsc_multiplier(struct vcpu_vmx *vmx) @@ -5012,7 +5010,7 @@ static void vmx_disable_intercept_msr_x2apic(u32 msr, int type, bool apicv_activ } } -static bool vmx_get_enable_apicv(void) +static bool vmx_get_enable_apicv(struct kvm_vcpu *vcpu) { return enable_apicv; } @@ -5077,21 +5075,30 @@ static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu, int pi_vec = nested ? POSTED_INTR_NESTED_VECTOR : POSTED_INTR_VECTOR; if (vcpu->mode == IN_GUEST_MODE) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - /* - * Currently, we don't support urgent interrupt, - * all interrupts are recognized as non-urgent - * interrupt, so we cannot post interrupts when - * 'SN' is set. + * The vector of interrupt to be delivered to vcpu had + * been set in PIR before this function. * - * If the vcpu is in guest mode, it means it is - * running instead of being scheduled out and - * waiting in the run queue, and that's the only - * case when 'SN' is set currently, warning if - * 'SN' is set. + * Following cases will be reached in this block, and + * we always send a notification event in all cases as + * explained below. + * + * Case 1: vcpu keeps in non-root mode. Sending a + * notification event posts the interrupt to vcpu. + * + * Case 2: vcpu exits to root mode and is still + * runnable. PIR will be synced to vIRR before the + * next vcpu entry. Sending a notification event in + * this case has no effect, as vcpu is not in root + * mode. + * + * Case 3: vcpu exits to root mode and is blocked. + * vcpu_block() has already synced PIR to vIRR and + * never blocks vcpu if vIRR is not cleared. Therefore, + * a blocked vcpu here does not wait for any requested + * interrupts in PIR, and sending a notification event + * which has no effect is safe here. */ - WARN_ON_ONCE(pi_test_sn(&vmx->pi_desc)); apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec); return true; @@ -5169,12 +5176,12 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx) */ cr3 = __read_cr3(); vmcs_writel(HOST_CR3, cr3); /* 22.2.3 FIXME: shadow tables */ - vmx->host_state.vmcs_host_cr3 = cr3; + vmx->loaded_vmcs->vmcs_host_cr3 = cr3; /* Save the most likely value for this task's CR4 in the VMCS. */ cr4 = cr4_read_shadow(); vmcs_writel(HOST_CR4, cr4); /* 22.2.3, 22.2.5 */ - vmx->host_state.vmcs_host_cr4 = cr4; + vmx->loaded_vmcs->vmcs_host_cr4 = cr4; vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */ #ifdef CONFIG_X86_64 @@ -5192,7 +5199,7 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx) vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS); /* 22.2.4 */ vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8); /* 22.2.4 */ - native_store_idt(&dt); + store_idt(&dt); vmcs_writel(HOST_IDTR_BASE, dt.address); /* 22.2.4 */ vmx->host_idt_base = dt.address; @@ -8344,12 +8351,14 @@ static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason, - vmcs_readl(EXIT_QUALIFICATION), - vmx->idt_vectoring_info, - intr_info, - vmcs_read32(VM_EXIT_INTR_ERROR_CODE), - KVM_ISA_VMX); + if (vmx->nested.nested_run_pending) + return false; + + if (unlikely(vmx->fail)) { + pr_info_ratelimited("%s failed vm entry %x\n", __func__, + vmcs_read32(VM_INSTRUCTION_ERROR)); + return true; + } /* * The host physical addresses of some pages of guest memory @@ -8363,14 +8372,12 @@ static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) */ nested_mark_vmcs12_pages_dirty(vcpu); - if (vmx->nested.nested_run_pending) - return false; - - if (unlikely(vmx->fail)) { - pr_info_ratelimited("%s failed vm entry %x\n", __func__, - vmcs_read32(VM_INSTRUCTION_ERROR)); - return true; - } + trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason, + vmcs_readl(EXIT_QUALIFICATION), + vmx->idt_vectoring_info, + intr_info, + vmcs_read32(VM_EXIT_INTR_ERROR_CODE), + KVM_ISA_VMX); switch (exit_reason) { case EXIT_REASON_EXCEPTION_NMI: @@ -9036,7 +9043,6 @@ 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); - register void *__sp asm(_ASM_SP); if ((exit_intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK)) == (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR)) { @@ -9065,7 +9071,7 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) #ifdef CONFIG_X86_64 [sp]"=&r"(tmp), #endif - "+r"(__sp) + ASM_CALL_CONSTRAINT : [entry]"r"(entry), [ss]"i"(__KERNEL_DS), @@ -9265,15 +9271,15 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); cr3 = __get_current_cr3_fast(); - if (unlikely(cr3 != vmx->host_state.vmcs_host_cr3)) { + if (unlikely(cr3 != vmx->loaded_vmcs->vmcs_host_cr3)) { vmcs_writel(HOST_CR3, cr3); - vmx->host_state.vmcs_host_cr3 = cr3; + vmx->loaded_vmcs->vmcs_host_cr3 = cr3; } cr4 = cr4_read_shadow(); - if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) { + if (unlikely(cr4 != vmx->loaded_vmcs->vmcs_host_cr4)) { vmcs_writel(HOST_CR4, cr4); - vmx->host_state.vmcs_host_cr4 = cr4; + vmx->loaded_vmcs->vmcs_host_cr4 = cr4; } /* When single-stepping over STI and MOV SS, we must clear the @@ -9424,12 +9430,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) | (1 << VCPU_EXREG_CR3)); vcpu->arch.regs_dirty = 0; - vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); - - vmx->loaded_vmcs->launched = 1; - - vmx->exit_reason = vmcs_read32(VM_EXIT_REASON); - /* * eager fpu is enabled if PKEY is supported and CR4 is switched * back on host, so it is safe to read guest PKRU from current @@ -9451,6 +9451,14 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); vmx->nested.nested_run_pending = 0; + vmx->idt_vectoring_info = 0; + + vmx->exit_reason = vmx->fail ? 0xdead : vmcs_read32(VM_EXIT_REASON); + if (vmx->fail || (vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) + return; + + vmx->loaded_vmcs->launched = 1; + vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); vmx_complete_atomic_exit(vmx); vmx_recover_nmi_blocking(vmx); @@ -9581,6 +9589,13 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED; + /* + * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR + * or POSTED_INTR_WAKEUP_VECTOR. + */ + vmx->pi_desc.nv = POSTED_INTR_VECTOR; + vmx->pi_desc.sn = 1; + return &vmx->vcpu; free_vmcs: @@ -9829,7 +9844,8 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, WARN_ON(!is_guest_mode(vcpu)); - if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) { + if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) && + !to_vmx(vcpu)->nested.nested_run_pending) { vmcs12->vm_exit_intr_error_code = fault->error_code; nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, PF_VECTOR | INTR_TYPE_HARD_EXCEPTION | @@ -10525,6 +10541,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (exec_control & CPU_BASED_TPR_SHADOW) { vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, -1ull); vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold); + } else { +#ifdef CONFIG_X86_64 + exec_control |= CPU_BASED_CR8_LOAD_EXITING | + CPU_BASED_CR8_STORE_EXITING; +#endif } /* @@ -11388,46 +11409,30 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - u32 vm_inst_error = 0; /* trying to cancel vmlaunch/vmresume is a bug */ WARN_ON_ONCE(vmx->nested.nested_run_pending); + /* + * The only expected VM-instruction error is "VM entry with + * invalid control field(s)." Anything else indicates a + * problem with L0. + */ + WARN_ON_ONCE(vmx->fail && (vmcs_read32(VM_INSTRUCTION_ERROR) != + VMXERR_ENTRY_INVALID_CONTROL_FIELD)); + leave_guest_mode(vcpu); - prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info, - exit_qualification); - if (nested_vmx_store_msr(vcpu, vmcs12->vm_exit_msr_store_addr, - vmcs12->vm_exit_msr_store_count)) - nested_vmx_abort(vcpu, VMX_ABORT_SAVE_GUEST_MSR_FAIL); + if (likely(!vmx->fail)) { + prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info, + exit_qualification); - if (unlikely(vmx->fail)) - vm_inst_error = vmcs_read32(VM_INSTRUCTION_ERROR); + if (nested_vmx_store_msr(vcpu, vmcs12->vm_exit_msr_store_addr, + vmcs12->vm_exit_msr_store_count)) + nested_vmx_abort(vcpu, VMX_ABORT_SAVE_GUEST_MSR_FAIL); + } vmx_switch_vmcs(vcpu, &vmx->vmcs01); - - /* - * TODO: SDM says that with acknowledge interrupt on exit, bit 31 of - * the VM-exit interrupt information (valid interrupt) is always set to - * 1 on EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't need - * kvm_cpu_has_interrupt(). See the commit message for details. - */ - if (nested_exit_intr_ack_set(vcpu) && - exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && - kvm_cpu_has_interrupt(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, - vmcs12->vm_exit_intr_info, - vmcs12->vm_exit_intr_error_code, - KVM_ISA_VMX); - vm_entry_controls_reset_shadow(vmx); vm_exit_controls_reset_shadow(vmx); vmx_segment_cache_clear(vmx); @@ -11436,8 +11441,6 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, if (VMCS02_POOL_SIZE == 0) nested_free_vmcs02(vmx, vmx->nested.current_vmptr); - load_vmcs12_host_state(vcpu, vmcs12); - /* Update any VMCS fields that might have changed while L2 ran */ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr); @@ -11486,21 +11489,57 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, */ kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); - /* - * Exiting from L2 to L1, we're now back to L1 which thinks it just - * finished a VMLAUNCH or VMRESUME instruction, so we need to set the - * success or failure flag accordingly. - */ - if (unlikely(vmx->fail)) { - vmx->fail = 0; - nested_vmx_failValid(vcpu, vm_inst_error); - } else - 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; + + if (likely(!vmx->fail)) { + /* + * TODO: SDM says that with acknowledge interrupt on + * exit, bit 31 of the VM-exit interrupt information + * (valid interrupt) is always set to 1 on + * EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't + * need kvm_cpu_has_interrupt(). See the commit + * message for details. + */ + if (nested_exit_intr_ack_set(vcpu) && + exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && + kvm_cpu_has_interrupt(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, + vmcs12->vm_exit_intr_info, + vmcs12->vm_exit_intr_error_code, + KVM_ISA_VMX); + + load_vmcs12_host_state(vcpu, vmcs12); + + return; + } + + /* + * After an early L2 VM-entry failure, we're now back + * in L1 which thinks it just finished a VMLAUNCH or + * VMRESUME instruction, so we need to set the failure + * flag and the VM-instruction error field of the VMCS + * accordingly. + */ + nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); + /* + * The emulated instruction was already skipped in + * nested_vmx_run, but the updated RIP was never + * written back to the vmcs01. + */ + skip_emulated_instruction(vcpu); + vmx->fail = 0; } /* @@ -11671,6 +11710,37 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask); } +static void __pi_post_block(struct kvm_vcpu *vcpu) +{ + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + struct pi_desc old, new; + unsigned int dest; + + do { + old.control = new.control = pi_desc->control; + WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR, + "Wakeup handler not enabled while the VCPU is blocked\n"); + + dest = cpu_physical_id(vcpu->cpu); + + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; + + /* set 'NV' to 'notification vector' */ + new.nv = POSTED_INTR_VECTOR; + } while (cmpxchg64(&pi_desc->control, old.control, + new.control) != old.control); + + if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) { + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + list_del(&vcpu->blocked_vcpu_list); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + vcpu->pre_pcpu = -1; + } +} + /* * This routine does the following things for vCPU which is going * to be blocked if VT-d PI is enabled. @@ -11686,7 +11756,6 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm, */ static int pi_pre_block(struct kvm_vcpu *vcpu) { - unsigned long flags; unsigned int dest; struct pi_desc old, new; struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); @@ -11696,34 +11765,20 @@ static int pi_pre_block(struct kvm_vcpu *vcpu) !kvm_vcpu_apicv_active(vcpu)) return 0; - vcpu->pre_pcpu = vcpu->cpu; - spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - list_add_tail(&vcpu->blocked_vcpu_list, - &per_cpu(blocked_vcpu_on_cpu, - vcpu->pre_pcpu)); - spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); + WARN_ON(irqs_disabled()); + local_irq_disable(); + if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) { + vcpu->pre_pcpu = vcpu->cpu; + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + list_add_tail(&vcpu->blocked_vcpu_list, + &per_cpu(blocked_vcpu_on_cpu, + vcpu->pre_pcpu)); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + } do { old.control = new.control = pi_desc->control; - /* - * We should not block the vCPU if - * an interrupt is posted for it. - */ - if (pi_test_on(pi_desc) == 1) { - spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - list_del(&vcpu->blocked_vcpu_list); - spin_unlock_irqrestore( - &per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - vcpu->pre_pcpu = -1; - - return 1; - } - WARN((pi_desc->sn == 1), "Warning: SN field of posted-interrupts " "is set before blocking\n"); @@ -11745,10 +11800,15 @@ static int pi_pre_block(struct kvm_vcpu *vcpu) /* set 'NV' to 'wakeup vector' */ new.nv = POSTED_INTR_WAKEUP_VECTOR; - } while (cmpxchg(&pi_desc->control, old.control, - new.control) != old.control); + } while (cmpxchg64(&pi_desc->control, old.control, + new.control) != old.control); - return 0; + /* We should not block the vCPU if an interrupt is posted for it. */ + if (pi_test_on(pi_desc) == 1) + __pi_post_block(vcpu); + + local_irq_enable(); + return (vcpu->pre_pcpu == -1); } static int vmx_pre_block(struct kvm_vcpu *vcpu) @@ -11764,44 +11824,13 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu) static void pi_post_block(struct kvm_vcpu *vcpu) { - struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - struct pi_desc old, new; - unsigned int dest; - unsigned long flags; - - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + if (vcpu->pre_pcpu == -1) return; - do { - old.control = new.control = pi_desc->control; - - dest = cpu_physical_id(vcpu->cpu); - - if (x2apic_enabled()) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; - - /* Allow posting non-urgent interrupts */ - new.sn = 0; - - /* set 'NV' to 'notification vector' */ - new.nv = POSTED_INTR_VECTOR; - } while (cmpxchg(&pi_desc->control, old.control, - new.control) != old.control); - - if(vcpu->pre_pcpu != -1) { - spin_lock_irqsave( - &per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - list_del(&vcpu->blocked_vcpu_list); - spin_unlock_irqrestore( - &per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - vcpu->pre_pcpu = -1; - } + WARN_ON(irqs_disabled()); + local_irq_disable(); + __pi_post_block(vcpu); + local_irq_enable(); } static void vmx_post_block(struct kvm_vcpu *vcpu) @@ -11829,7 +11858,7 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, struct kvm_lapic_irq irq; struct kvm_vcpu *vcpu; struct vcpu_data vcpu_info; - int idx, ret = -EINVAL; + int idx, ret = 0; if (!kvm_arch_has_assigned_device(kvm) || !irq_remapping_cap(IRQ_POSTING_CAP) || @@ -11838,7 +11867,12 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, idx = srcu_read_lock(&kvm->irq_srcu); irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); - BUG_ON(guest_irq >= irq_rt->nr_rt_entries); + if (guest_irq >= irq_rt->nr_rt_entries || + hlist_empty(&irq_rt->map[guest_irq])) { + pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n", + guest_irq, irq_rt->nr_rt_entries); + goto out; + } hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) { if (e->type != KVM_IRQ_ROUTING_MSI) @@ -11881,12 +11915,8 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, if (set) ret = irq_set_vcpu_affinity(host_irq, &vcpu_info); - else { - /* suppress notification event before unposting */ - pi_set_sn(vcpu_to_pi_desc(vcpu)); + else ret = irq_set_vcpu_affinity(host_irq, NULL); - pi_clear_sn(vcpu_to_pi_desc(vcpu)); - } if (ret < 0) { printk(KERN_INFO "%s: failed to update PI IRTE\n", diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6069af86da3b..03869eb7fcd6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7225,16 +7225,25 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) int r; sigset_t sigsaved; - fpu__activate_curr(fpu); + fpu__initialize(fpu); if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { + if (kvm_run->immediate_exit) { + r = -EINTR; + goto out; + } kvm_vcpu_block(vcpu); kvm_apic_accept_events(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); r = -EAGAIN; + if (signal_pending(current)) { + r = -EINTR; + vcpu->run->exit_reason = KVM_EXIT_INTR; + ++vcpu->stat.signal_exits; + } goto out; } @@ -7971,7 +7980,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) BUG_ON(vcpu->kvm == NULL); kvm = vcpu->kvm; - vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(); + vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu); vcpu->arch.pv.pv_unhalted = false; vcpu->arch.emulate_ctxt.ops = &emulate_ops; if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_reset_bsp(vcpu)) @@ -8452,6 +8461,9 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) if (vcpu->arch.pv.pv_unhalted) return true; + if (vcpu->arch.exception.pending) + return true; + if (kvm_test_request(KVM_REQ_NMI, vcpu) || (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu))) @@ -8619,6 +8631,13 @@ static int apf_put_user(struct kvm_vcpu *vcpu, u32 val) sizeof(val)); } +static int apf_get_user(struct kvm_vcpu *vcpu, u32 *val) +{ + + return kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, val, + sizeof(u32)); +} + void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) { @@ -8646,6 +8665,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) { struct x86_exception fault; + u32 val; if (work->wakeup_all) work->arch.token = ~0; /* broadcast wakeup */ @@ -8653,15 +8673,26 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, kvm_del_async_pf_gfn(vcpu, work->arch.gfn); trace_kvm_async_pf_ready(work->arch.token, work->gva); - if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) && - !apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) { - fault.vector = PF_VECTOR; - fault.error_code_valid = true; - fault.error_code = 0; - fault.nested_page_fault = false; - fault.address = work->arch.token; - fault.async_page_fault = true; - kvm_inject_page_fault(vcpu, &fault); + if (vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED && + !apf_get_user(vcpu, &val)) { + if (val == KVM_PV_REASON_PAGE_NOT_PRESENT && + vcpu->arch.exception.pending && + vcpu->arch.exception.nr == PF_VECTOR && + !apf_put_user(vcpu, 0)) { + vcpu->arch.exception.injected = false; + vcpu->arch.exception.pending = false; + vcpu->arch.exception.nr = 0; + vcpu->arch.exception.has_error_code = false; + vcpu->arch.exception.error_code = 0; + } else if (!apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) { + fault.vector = PF_VECTOR; + fault.error_code_valid = true; + fault.error_code = 0; + fault.nested_page_fault = false; + fault.address = work->arch.token; + fault.async_page_fault = true; + kvm_inject_page_fault(vcpu, &fault); + } } vcpu->arch.apf.halted = false; vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; |