x86 architecture defines differences between the reset and INIT sequences. INIT does not initialize the FPU (including MMX, XMM, YMM, etc.), TSC, PMU, MSRs (in general), MTRRs machine-check, APIC ID, APIC arbitration ID and BSP. References (from Intel SDM): "If the MP protocol has completed and a BSP is chosen, subsequent INITs (either to a specific processor or system wide) do not cause the MP protocol to be repeated." [8.4.2: MP Initialization Protocol Requirements and Restrictions] [Table 9-1. IA-32 Processor States Following Power-up, Reset, or INIT] "If the processor is reset by asserting the INIT# pin, the x87 FPU state is not changed." [9.2: X87 FPU INITIALIZATION] "The state of the local APIC following an INIT reset is the same as it is after a power-up or hardware reset, except that the APIC ID and arbitration ID registers are not affected." [10.4.7.3: Local APIC State After an INIT Reset (“Wait-for-SIPI” State)] Signed-off-by: Nadav Amit <namit@xxxxxxxxxxxxxxxxx> --- arch/x86/include/asm/kvm_host.h | 6 +++--- arch/x86/kvm/lapic.c | 11 ++++++----- arch/x86/kvm/lapic.h | 2 +- arch/x86/kvm/svm.c | 2 +- arch/x86/kvm/vmx.c | 33 +++++++++++++++++++-------------- arch/x86/kvm/x86.c | 17 ++++++++++------- 6 files changed, 40 insertions(+), 31 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index bf5a160..59f4374 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -701,7 +701,7 @@ struct kvm_x86_ops { /* Create, but do not attach this VCPU */ struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id); void (*vcpu_free)(struct kvm_vcpu *vcpu); - void (*vcpu_reset)(struct kvm_vcpu *vcpu); + void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event); void (*prepare_guest_switch)(struct kvm_vcpu *vcpu); void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); @@ -989,7 +989,7 @@ void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id); void kvm_inject_nmi(struct kvm_vcpu *vcpu); -int fx_init(struct kvm_vcpu *vcpu); +int fx_init(struct kvm_vcpu *vcpu, bool init_event); void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, int bytes); @@ -1134,7 +1134,7 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); -void kvm_vcpu_reset(struct kvm_vcpu *vcpu); +void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu); void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, unsigned long address); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index bd4e34d..17da6fc 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1534,7 +1534,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) } -void kvm_lapic_reset(struct kvm_vcpu *vcpu) +void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) { struct kvm_lapic *apic; int i; @@ -1548,7 +1548,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu) /* Stop the timer in case it's a reset to an active apic */ hrtimer_cancel(&apic->lapic_timer.timer); - kvm_apic_set_id(apic, vcpu->vcpu_id); + if (!init_event) + kvm_apic_set_id(apic, vcpu->vcpu_id); kvm_apic_set_version(apic->vcpu); for (i = 0; i < APIC_LVT_NUM; i++) @@ -1689,7 +1690,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE); static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */ - kvm_lapic_reset(vcpu); + kvm_lapic_reset(vcpu, false); kvm_iodevice_init(&apic->dev, &apic_mmio_ops); return 0; @@ -2023,8 +2024,8 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) pe = xchg(&apic->pending_events, 0); if (test_bit(KVM_APIC_INIT, &pe)) { - kvm_lapic_reset(vcpu); - kvm_vcpu_reset(vcpu); + kvm_lapic_reset(vcpu, true); + kvm_vcpu_reset(vcpu, true); if (kvm_vcpu_is_bsp(apic->vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 0bc6c65..e4c82dc 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -48,7 +48,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu); int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu); int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu); void kvm_apic_accept_events(struct kvm_vcpu *vcpu); -void kvm_lapic_reset(struct kvm_vcpu *vcpu); +void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event); u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu); void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8); void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 155534c..1ef4c0d 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1195,7 +1195,7 @@ static void init_vmcb(struct vcpu_svm *svm) enable_gif(svm); } -static void svm_vcpu_reset(struct kvm_vcpu *vcpu) +static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct vcpu_svm *svm = to_svm(vcpu); u32 dummy; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index fdd9f8b..8aee6db 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -4694,7 +4694,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) return 0; } -static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) +static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct msr_data apic_base_msr; @@ -4705,11 +4705,15 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); kvm_set_cr8(&vmx->vcpu, 0); - apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; - if (kvm_vcpu_is_bsp(&vmx->vcpu)) - apic_base_msr.data |= MSR_IA32_APICBASE_BSP; - apic_base_msr.host_initiated = true; - kvm_set_apic_base(&vmx->vcpu, &apic_base_msr); + + if (!init_event) { + apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | + MSR_IA32_APICBASE_ENABLE; + if (kvm_vcpu_is_bsp(&vmx->vcpu)) + apic_base_msr.data |= MSR_IA32_APICBASE_BSP; + apic_base_msr.host_initiated = true; + kvm_set_apic_base(&vmx->vcpu, &apic_base_msr); + } vmx_segment_cache_clear(vmx); @@ -4733,9 +4737,12 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_LDTR_LIMIT, 0xffff); vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082); - vmcs_write32(GUEST_SYSENTER_CS, 0); - vmcs_writel(GUEST_SYSENTER_ESP, 0); - vmcs_writel(GUEST_SYSENTER_EIP, 0); + if (!init_event) { + vmcs_write32(GUEST_SYSENTER_CS, 0); + vmcs_writel(GUEST_SYSENTER_ESP, 0); + vmcs_writel(GUEST_SYSENTER_EIP, 0); + vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + } vmcs_writel(GUEST_RFLAGS, 0x02); kvm_rip_write(vcpu, 0xfff0); @@ -4750,14 +4757,11 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0); - /* Special registers */ - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); - setup_msrs(vmx); vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); /* 22.2.1 */ - if (cpu_has_vmx_tpr_shadow()) { + if (cpu_has_vmx_tpr_shadow() && !init_event) { vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); if (vm_need_tpr_shadow(vmx->vcpu.kvm)) vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, @@ -4776,7 +4780,8 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmx->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; vmx_set_cr0(&vmx->vcpu, kvm_read_cr0(vcpu)); /* enter rmode */ vmx_set_cr4(&vmx->vcpu, 0); - vmx_set_efer(&vmx->vcpu, 0); + if (!init_event) + vmx_set_efer(&vmx->vcpu, 0); vmx_fpu_activate(&vmx->vcpu); update_exception_bitmap(&vmx->vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cc2c759..324e639 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6961,7 +6961,7 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) return 0; } -int fx_init(struct kvm_vcpu *vcpu) +int fx_init(struct kvm_vcpu *vcpu, bool init_event) { int err; @@ -6969,7 +6969,9 @@ int fx_init(struct kvm_vcpu *vcpu) if (err) return err; - fpu_finit(&vcpu->arch.guest_fpu); + if (!init_event) + fpu_finit(&vcpu->arch.guest_fpu); + if (cpu_has_xsaves) vcpu->arch.guest_fpu.state->xsave.xsave_hdr.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED; @@ -7049,7 +7051,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) r = vcpu_load(vcpu); if (r) return r; - kvm_vcpu_reset(vcpu); + kvm_vcpu_reset(vcpu, false); kvm_mmu_setup(vcpu); vcpu_put(vcpu); @@ -7087,7 +7089,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvm_x86_ops->vcpu_free(vcpu); } -void kvm_vcpu_reset(struct kvm_vcpu *vcpu) +void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { atomic_set(&vcpu->arch.nmi_queued, 0); vcpu->arch.nmi_pending = 0; @@ -7111,13 +7113,14 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu) kvm_async_pf_hash_reset(vcpu); vcpu->arch.apf.halted = false; - kvm_pmu_reset(vcpu); + if (!init_event) + kvm_pmu_reset(vcpu); memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); vcpu->arch.regs_avail = ~0; vcpu->arch.regs_dirty = ~0; - kvm_x86_ops->vcpu_reset(vcpu); + kvm_x86_ops->vcpu_reset(vcpu, init_event); } void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) @@ -7299,7 +7302,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) goto fail_free_mce_banks; } - r = fx_init(vcpu); + r = fx_init(vcpu, false); if (r) goto fail_free_wbinvd_dirty_mask; -- 1.9.1 -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html