diff options
Diffstat (limited to 'arch/x86/kvm/vmx.c')
| -rw-r--r-- | arch/x86/kvm/vmx.c | 616 |
1 files changed, 445 insertions, 171 deletions
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 801332edefc3..04fa1b8298c8 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -125,14 +125,32 @@ module_param(nested, bool, S_IRUGO); * Time is measured based on a counter that runs at the same rate as the TSC, * refer SDM volume 3b section 21.6.13 & 22.1.3. */ -#define KVM_VMX_DEFAULT_PLE_GAP 128 -#define KVM_VMX_DEFAULT_PLE_WINDOW 4096 +#define KVM_VMX_DEFAULT_PLE_GAP 128 +#define KVM_VMX_DEFAULT_PLE_WINDOW 4096 +#define KVM_VMX_DEFAULT_PLE_WINDOW_GROW 2 +#define KVM_VMX_DEFAULT_PLE_WINDOW_SHRINK 0 +#define KVM_VMX_DEFAULT_PLE_WINDOW_MAX \ + INT_MAX / KVM_VMX_DEFAULT_PLE_WINDOW_GROW + static int ple_gap = KVM_VMX_DEFAULT_PLE_GAP; module_param(ple_gap, int, S_IRUGO); static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW; module_param(ple_window, int, S_IRUGO); +/* Default doubles per-vcpu window every exit. */ +static int ple_window_grow = KVM_VMX_DEFAULT_PLE_WINDOW_GROW; +module_param(ple_window_grow, int, S_IRUGO); + +/* Default resets per-vcpu window every exit to ple_window. */ +static int ple_window_shrink = KVM_VMX_DEFAULT_PLE_WINDOW_SHRINK; +module_param(ple_window_shrink, int, S_IRUGO); + +/* Default is to compute the maximum so we can never overflow. */ +static int ple_window_actual_max = KVM_VMX_DEFAULT_PLE_WINDOW_MAX; +static int ple_window_max = KVM_VMX_DEFAULT_PLE_WINDOW_MAX; +module_param(ple_window_max, int, S_IRUGO); + extern const ulong vmx_return; #define NR_AUTOLOAD_MSRS 8 @@ -379,10 +397,14 @@ struct nested_vmx { * we must keep them pinned while L2 runs. */ struct page *apic_access_page; + struct page *virtual_apic_page; u64 msr_ia32_feature_control; struct hrtimer preemption_timer; bool preemption_timer_expired; + + /* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */ + u64 vmcs01_debugctl; }; #define POSTED_INTR_ON 0 @@ -481,6 +503,10 @@ struct vcpu_vmx { /* Support for a guest hypervisor (nested VMX) */ struct nested_vmx nested; + + /* Dynamic PLE window. */ + int ple_window; + bool ple_window_dirty; }; enum segment_cache_field { @@ -530,6 +556,7 @@ static int max_shadow_read_only_fields = ARRAY_SIZE(shadow_read_only_fields); static unsigned long shadow_read_write_fields[] = { + TPR_THRESHOLD, GUEST_RIP, GUEST_RSP, GUEST_CR0, @@ -740,7 +767,7 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var); static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu); static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx); static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx); -static bool vmx_mpx_supported(void); +static int alloc_identity_pagetable(struct kvm *kvm); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -820,7 +847,6 @@ static const u32 vmx_msr_index[] = { #endif MSR_EFER, MSR_TSC_AUX, MSR_STAR, }; -#define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index) static inline bool is_page_fault(u32 intr_info) { @@ -1940,7 +1966,7 @@ static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) vmcs_writel(GUEST_RFLAGS, rflags); } -static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) +static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu) { u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); int ret = 0; @@ -1950,7 +1976,7 @@ static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) if (interruptibility & GUEST_INTR_STATE_MOV_SS) ret |= KVM_X86_SHADOW_INT_MOV_SS; - return ret & mask; + return ret; } static void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) @@ -2134,7 +2160,7 @@ static u64 guest_read_tsc(void) * Like guest_read_tsc, but always returns L1's notion of the timestamp * counter, even if a nested guest (L2) is currently running. */ -u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) +static u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) { u64 tsc_offset; @@ -2239,10 +2265,13 @@ static inline bool nested_vmx_allowed(struct kvm_vcpu *vcpu) * or other means. */ static u32 nested_vmx_procbased_ctls_low, nested_vmx_procbased_ctls_high; +static u32 nested_vmx_true_procbased_ctls_low; 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_true_exit_ctls_low; static u32 nested_vmx_entry_ctls_low, nested_vmx_entry_ctls_high; +static u32 nested_vmx_true_entry_ctls_low; static u32 nested_vmx_misc_low, nested_vmx_misc_high; static u32 nested_vmx_ept_caps; static __init void nested_vmx_setup_ctls_msrs(void) @@ -2265,21 +2294,13 @@ 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 |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR; nested_vmx_pinbased_ctls_high &= PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING | PIN_BASED_VIRTUAL_NMIS; nested_vmx_pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | PIN_BASED_VMX_PREEMPTION_TIMER; - /* - * Exit controls - * If bit 55 of VMX_BASIC is off, bits 0-8 and 10, 11, 13, 14, 16 and - * 17 must be 1. - */ + /* exit controls */ rdmsr(MSR_IA32_VMX_EXIT_CTLS, nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high); nested_vmx_exit_ctls_low = VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR; @@ -2296,10 +2317,13 @@ static __init void nested_vmx_setup_ctls_msrs(void) if (vmx_mpx_supported()) nested_vmx_exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS; + /* We support free control of debug control saving. */ + nested_vmx_true_exit_ctls_low = nested_vmx_exit_ctls_low & + ~VM_EXIT_SAVE_DEBUG_CONTROLS; + /* entry controls */ rdmsr(MSR_IA32_VMX_ENTRY_CTLS, nested_vmx_entry_ctls_low, nested_vmx_entry_ctls_high); - /* 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 &= #ifdef CONFIG_X86_64 @@ -2311,10 +2335,14 @@ static __init void nested_vmx_setup_ctls_msrs(void) if (vmx_mpx_supported()) nested_vmx_entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS; + /* We support free control of debug control loading. */ + nested_vmx_true_entry_ctls_low = nested_vmx_entry_ctls_low & + ~VM_ENTRY_LOAD_DEBUG_CONTROLS; + /* cpu-based controls */ rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, nested_vmx_procbased_ctls_low, nested_vmx_procbased_ctls_high); - nested_vmx_procbased_ctls_low = 0; + nested_vmx_procbased_ctls_low = CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR; nested_vmx_procbased_ctls_high &= CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING | CPU_BASED_USE_TSC_OFFSETING | @@ -2327,7 +2355,7 @@ 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_PAUSE_EXITING | CPU_BASED_TPR_SHADOW | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; /* * We can allow some features even when not supported by the @@ -2335,7 +2363,12 @@ static __init void nested_vmx_setup_ctls_msrs(void) * can use it to avoid exits to L1 - even when L0 runs L2 * without MSR bitmaps. */ - nested_vmx_procbased_ctls_high |= CPU_BASED_USE_MSR_BITMAPS; + nested_vmx_procbased_ctls_high |= CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | + CPU_BASED_USE_MSR_BITMAPS; + + /* We support free control of CR3 access interception. */ + nested_vmx_true_procbased_ctls_low = nested_vmx_procbased_ctls_low & + ~(CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING); /* secondary cpu-based controls */ rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2, @@ -2394,7 +2427,7 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) * guest, and the VMCS structure we give it - not about the * VMX support of the underlying hardware. */ - *pdata = VMCS12_REVISION | + *pdata = VMCS12_REVISION | VMX_BASIC_TRUE_CTLS | ((u64)VMCS12_SIZE << VMX_BASIC_VMCS_SIZE_SHIFT) | (VMX_BASIC_MEM_TYPE_WB << VMX_BASIC_MEM_TYPE_SHIFT); break; @@ -2404,16 +2437,25 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) nested_vmx_pinbased_ctls_high); break; case MSR_IA32_VMX_TRUE_PROCBASED_CTLS: + *pdata = vmx_control_msr(nested_vmx_true_procbased_ctls_low, + nested_vmx_procbased_ctls_high); + break; case MSR_IA32_VMX_PROCBASED_CTLS: *pdata = vmx_control_msr(nested_vmx_procbased_ctls_low, nested_vmx_procbased_ctls_high); break; case MSR_IA32_VMX_TRUE_EXIT_CTLS: + *pdata = vmx_control_msr(nested_vmx_true_exit_ctls_low, + nested_vmx_exit_ctls_high); + break; case MSR_IA32_VMX_EXIT_CTLS: *pdata = vmx_control_msr(nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high); break; case MSR_IA32_VMX_TRUE_ENTRY_CTLS: + *pdata = vmx_control_msr(nested_vmx_true_entry_ctls_low, + nested_vmx_entry_ctls_high); + break; case MSR_IA32_VMX_ENTRY_CTLS: *pdata = vmx_control_msr(nested_vmx_entry_ctls_low, nested_vmx_entry_ctls_high); @@ -2442,7 +2484,7 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) *pdata = -1ULL; break; case MSR_IA32_VMX_VMCS_ENUM: - *pdata = 0x1f; + *pdata = 0x2e; /* highest index: VMX_PREEMPTION_TIMER_VALUE */ break; case MSR_IA32_VMX_PROCBASED_CTLS2: *pdata = vmx_control_msr(nested_vmx_secondary_ctls_low, @@ -2584,6 +2626,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_CR_PAT: if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { + if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) + return 1; vmcs_write64(GUEST_IA32_PAT, data); vcpu->arch.pat = data; break; @@ -2687,7 +2731,7 @@ static void kvm_cpu_vmxon(u64 addr) : "memory", "cc"); } -static int hardware_enable(void *garbage) +static int hardware_enable(void) { int cpu = raw_smp_processor_id(); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); @@ -2751,7 +2795,7 @@ static void kvm_cpu_vmxoff(void) asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc"); } -static void hardware_disable(void *garbage) +static void hardware_disable(void) { if (vmm_exclusive) { vmclear_local_loaded_vmcss(); @@ -3090,9 +3134,17 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_unrestricted_guest()) enable_unrestricted_guest = 0; - if (!cpu_has_vmx_flexpriority()) + if (!cpu_has_vmx_flexpriority()) { flexpriority_enabled = 0; + /* + * set_apic_access_page_addr() is used to reload apic access + * page upon invalidation. No need to do anything if the + * processor does not have the APIC_ACCESS_ADDR VMCS field. + */ + kvm_x86_ops->set_apic_access_page_addr = NULL; + } + if (!cpu_has_vmx_tpr_shadow()) kvm_x86_ops->update_cr8_intercept = NULL; @@ -3653,7 +3705,7 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(var)); out: - vmx->emulation_required |= emulation_required(vcpu); + vmx->emulation_required = emulation_required(vcpu); } static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) @@ -3888,7 +3940,7 @@ static int init_rmode_tss(struct kvm *kvm) { gfn_t fn; u16 data = 0; - int r, idx, ret = 0; + int idx, r; idx = srcu_read_lock(&kvm->srcu); fn = kvm->arch.tss_addr >> PAGE_SHIFT; @@ -3910,32 +3962,32 @@ static int init_rmode_tss(struct kvm *kvm) r = kvm_write_guest_page(kvm, fn, &data, RMODE_TSS_SIZE - 2 * PAGE_SIZE - 1, sizeof(u8)); - if (r < 0) - goto out; - - ret = 1; out: srcu_read_unlock(&kvm->srcu, idx); - return ret; + return r; } static int init_rmode_identity_map(struct kvm *kvm) { - int i, idx, r, ret; + int i, idx, r = 0; pfn_t identity_map_pfn; u32 tmp; if (!enable_ept) - return 1; - if (unlikely(!kvm->arch.ept_identity_pagetable)) { - printk(KERN_ERR "EPT: identity-mapping pagetable " - "haven't been allocated!\n"); return 0; - } + + /* Protect kvm->arch.ept_identity_pagetable_done. */ + mutex_lock(&kvm->slots_lock); + if (likely(kvm->arch.ept_identity_pagetable_done)) - return 1; - ret = 0; + goto out2; + identity_map_pfn = kvm->arch.ept_identity_map_addr >> PAGE_SHIFT; + + r = alloc_identity_pagetable(kvm); + if (r < 0) + goto out2; + idx = srcu_read_lock(&kvm->srcu); r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE); if (r < 0) @@ -3950,10 +4002,13 @@ static int init_rmode_identity_map(struct kvm *kvm) goto out; } kvm->arch.ept_identity_pagetable_done = true; - ret = 1; + out: srcu_read_unlock(&kvm->srcu, idx); - return ret; + +out2: + mutex_unlock(&kvm->slots_lock); + return r; } static void seg_setup(int seg) @@ -3978,23 +4033,28 @@ static int alloc_apic_access_page(struct kvm *kvm) int r = 0; mutex_lock(&kvm->slots_lock); - if (kvm->arch.apic_access_page) + if (kvm->arch.apic_access_page_done) goto out; kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT; kvm_userspace_mem.flags = 0; - kvm_userspace_mem.guest_phys_addr = 0xfee00000ULL; + kvm_userspace_mem.guest_phys_addr = APIC_DEFAULT_PHYS_BASE; kvm_userspace_mem.memory_size = PAGE_SIZE; r = __kvm_set_memory_region(kvm, &kvm_userspace_mem); if (r) goto out; - page = gfn_to_page(kvm, 0xfee00); + page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); if (is_error_page(page)) { r = -EFAULT; goto out; } - kvm->arch.apic_access_page = page; + /* + * Do not pin the page in memory, so that memory hot-unplug + * is able to migrate it. + */ + put_page(page); + kvm->arch.apic_access_page_done = true; out: mutex_unlock(&kvm->slots_lock); return r; @@ -4002,31 +4062,20 @@ out: static int alloc_identity_pagetable(struct kvm *kvm) { - struct page *page; + /* Called with kvm->slots_lock held. */ + struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; - mutex_lock(&kvm->slots_lock); - if (kvm->arch.ept_identity_pagetable) - goto out; + BUG_ON(kvm->arch.ept_identity_pagetable_done); + kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT; kvm_userspace_mem.flags = 0; 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); - if (r) - goto out; - - page = gfn_to_page(kvm, kvm->arch.ept_identity_map_addr >> PAGE_SHIFT); - if (is_error_page(page)) { - r = -EFAULT; - goto out; - } - kvm->arch.ept_identity_pagetable = page; -out: - mutex_unlock(&kvm->slots_lock); return r; } @@ -4385,7 +4434,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) if (ple_gap) { vmcs_write32(PLE_GAP, ple_gap); - vmcs_write32(PLE_WINDOW, ple_window); + vmx->ple_window = ple_window; + vmx->ple_window_dirty = true; } vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0); @@ -4422,7 +4472,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmx->vcpu.arch.pat = host_pat; } - for (i = 0; i < NR_VMX_MSR; ++i) { + for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) { u32 index = vmx_msr_index[i]; u32 data_low, data_high; int j = vmx->nmsrs; @@ -4460,7 +4510,7 @@ 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 = 0xfee00000 | MSR_IA32_APICBASE_ENABLE; + 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; @@ -4520,9 +4570,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_write32(TPR_THRESHOLD, 0); } - if (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm)) - vmcs_write64(APIC_ACCESS_ADDR, - page_to_phys(vmx->vcpu.kvm->arch.apic_access_page)); + kvm_vcpu_reload_apic_access_page(vcpu); if (vmx_vm_has_apicv(vcpu->kvm)) memset(&vmx->pi_desc, 0, sizeof(struct pi_desc)); @@ -4712,10 +4760,7 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) if (ret) return ret; kvm->arch.tss_addr = addr; - if (!init_rmode_tss(kvm)) - return -ENOMEM; - - return 0; + return init_rmode_tss(kvm); } static bool rmode_exception(struct kvm_vcpu *vcpu, int vec) @@ -4873,7 +4918,7 @@ static int handle_exception(struct kvm_vcpu *vcpu) if (!(vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { vcpu->arch.dr6 &= ~15; - vcpu->arch.dr6 |= dr6; + vcpu->arch.dr6 |= dr6 | DR6_RTM; if (!(dr6 & ~DR6_RESERVED)) /* icebp */ skip_emulated_instruction(vcpu); @@ -5039,7 +5084,7 @@ static int handle_cr(struct kvm_vcpu *vcpu) reg = (exit_qualification >> 8) & 15; switch ((exit_qualification >> 4) & 3) { case 0: /* mov to cr */ - val = kvm_register_read(vcpu, reg); + val = kvm_register_readl(vcpu, reg); trace_kvm_cr_write(cr, val); switch (cr) { case 0: @@ -5056,7 +5101,7 @@ static int handle_cr(struct kvm_vcpu *vcpu) return 1; case 8: { u8 cr8_prev = kvm_get_cr8(vcpu); - u8 cr8 = kvm_register_read(vcpu, reg); + u8 cr8 = (u8)val; err = kvm_set_cr8(vcpu, cr8); kvm_complete_insn_gp(vcpu, err); if (irqchip_in_kernel(vcpu->kvm)) @@ -5132,7 +5177,7 @@ static int handle_dr(struct kvm_vcpu *vcpu) return 0; } else { vcpu->arch.dr7 &= ~DR7_GD; - vcpu->arch.dr6 |= DR6_BD; + vcpu->arch.dr6 |= DR6_BD | DR6_RTM; vmcs_writel(GUEST_DR7, vcpu->arch.dr7); kvm_queue_exception(vcpu, DB_VECTOR); return 1; @@ -5165,7 +5210,7 @@ static int handle_dr(struct kvm_vcpu *vcpu) return 1; kvm_register_write(vcpu, reg, val); } else - if (kvm_set_dr(vcpu, dr, kvm_register_read(vcpu, reg))) + if (kvm_set_dr(vcpu, dr, kvm_register_readl(vcpu, reg))) return 1; skip_emulated_instruction(vcpu); @@ -5504,17 +5549,18 @@ static u64 ept_rsvd_mask(u64 spte, int level) for (i = 51; i > boot_cpu_data.x86_phys_bits; i--) mask |= (1ULL << i); - if (level > 2) + if (level == 4) /* bits 7:3 reserved */ mask |= 0xf8; - else if (level == 2) { - if (spte & (1ULL << 7)) - /* 2MB ref, bits 20:12 reserved */ - mask |= 0x1ff000; - else - /* bits 6:3 reserved */ - mask |= 0x78; - } + else if (spte & (1ULL << 7)) + /* + * 1GB/2MB page, bits 29:12 or 20:12 reserved respectively, + * level == 1 if the hypervisor is using the ignored bit 7. + */ + mask |= (PAGE_SIZE << ((level - 1) * 9)) - PAGE_SIZE; + else if (level > 1) + /* bits 6:3 reserved */ + mask |= 0x78; return mask; } @@ -5544,7 +5590,8 @@ static void ept_misconfig_inspect_spte(struct kvm_vcpu *vcpu, u64 spte, WARN_ON(1); } - if (level == 1 || (level == 2 && (spte & (1ULL << 7)))) { + /* bits 5:3 are _not_ reserved for large page or leaf page */ + if ((rsvd_bits & 0x38) == 0) { u64 ept_mem_type = (spte & 0x38) >> 3; if (ept_mem_type == 2 || ept_mem_type == 3 || @@ -5621,7 +5668,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) cpu_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); intr_window_requested = cpu_exec_ctrl & CPU_BASED_VIRTUAL_INTR_PENDING; - while (!guest_state_valid(vcpu) && count-- != 0) { + while (vmx->emulation_required && count-- != 0) { if (intr_window_requested && vmx_interrupt_allowed(vcpu)) return handle_interrupt_window(&vmx->vcpu); @@ -5655,17 +5702,89 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) schedule(); } - vmx->emulation_required = emulation_required(vcpu); out: return ret; } +static int __grow_ple_window(int val) +{ + if (ple_window_grow < 1) + return ple_window; + + val = min(val, ple_window_actual_max); + + if (ple_window_grow < ple_window) + val *= ple_window_grow; + else + val += ple_window_grow; + + return val; +} + +static int __shrink_ple_window(int val, int modifier, int minimum) +{ + if (modifier < 1) + return ple_window; + + if (modifier < ple_window) + val /= modifier; + else + val -= modifier; + + return max(val, minimum); +} + +static void grow_ple_window(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + int old = vmx->ple_window; + + vmx->ple_window = __grow_ple_window(old); + + if (vmx->ple_window != old) + vmx->ple_window_dirty = true; + + trace_kvm_ple_window_grow(vcpu->vcpu_id, vmx->ple_window, old); +} + +static void shrink_ple_window(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + int old = vmx->ple_window; + + vmx->ple_window = __shrink_ple_window(old, + ple_window_shrink, ple_window); + + if (vmx->ple_window != old) + vmx->ple_window_dirty = true; + + trace_kvm_ple_window_shrink(vcpu->vcpu_id, vmx->ple_window, old); +} + +/* + * ple_window_actual_max is computed to be one grow_ple_window() below + * ple_window_max. (See __grow_ple_window for the reason.) + * This prevents overflows, because ple_window_max is int. + * ple_window_max effectively rounded down to a multiple of ple_window_grow in + * this process. + * ple_window_max is also prevented from setting vmx->ple_window < ple_window. + */ +static void update_ple_window_actual_max(void) +{ + ple_window_actual_max = + __shrink_ple_window(max(ple_window_max, ple_window), + ple_window_grow, INT_MIN); +} + /* * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE * exiting, so only get here on cpu with PAUSE-Loop-Exiting. */ static int handle_pause(struct kvm_vcpu *vcpu) { + if (ple_gap) + grow_ple_window(vcpu); + skip_emulated_instruction(vcpu); kvm_vcpu_on_spin(vcpu); @@ -5754,22 +5873,27 @@ static void nested_free_vmcs02(struct vcpu_vmx *vmx, gpa_t vmptr) /* * Free all VMCSs saved for this vcpu, except the one pointed by - * vmx->loaded_vmcs. These include the VMCSs in vmcs02_pool (except the one - * currently used, if running L2), and vmcs01 when running L2. + * vmx->loaded_vmcs. We must be running L1, so vmx->loaded_vmcs + * must be &vmx->vmcs01. */ static void nested_free_all_saved_vmcss(struct vcpu_vmx *vmx) { struct vmcs02_list *item, *n; + + WARN_ON(vmx->loaded_vmcs != &vmx->vmcs01); list_for_each_entry_safe(item, n, &vmx->nested.vmcs02_pool, list) { - if (vmx->loaded_vmcs != &item->vmcs02) - free_loaded_vmcs(&item->vmcs02); + /* + * Something will leak if the above WARN triggers. Better than + * a use-after-free. + */ + if (vmx->loaded_vmcs == &item->vmcs02) + continue; + + free_loaded_vmcs(&item->vmcs02); list_del(&item->list); kfree(item); + vmx->nested.vmcs02_num--; } - vmx->nested.vmcs02_num = 0; - - if (vmx->loaded_vmcs != &vmx->vmcs01) - free_loaded_vmcs(&vmx->vmcs01); } /* @@ -5918,7 +6042,7 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, * which replaces physical address width with 32 * */ - if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) { + if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) { nested_vmx_failInvalid(vcpu); skip_emulated_instruction(vcpu); return 1; @@ -5936,7 +6060,7 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, vmx->nested.vmxon_ptr = vmptr; break; case EXIT_REASON_VMCLEAR: - if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) { + if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) { nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS); skip_emulated_instruction(vcpu); @@ -5951,7 +6075,7 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, } break; case EXIT_REASON_VMPTRLD: - if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) { + if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) { nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS); skip_emulated_instruction(vcpu); @@ -6086,20 +6210,27 @@ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu) static inline void nested_release_vmcs12(struct vcpu_vmx *vmx) { u32 exec_control; + if (vmx->nested.current_vmptr == -1ull) + return; + + /* current_vmptr and current_vmcs12 are always set/reset together */ + if (WARN_ON(vmx->nested.current_vmcs12 == NULL)) + return; + 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); - } + /* 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); + vmx->nested.current_vmptr = -1ull; + vmx->nested.current_vmcs12 = NULL; } /* @@ -6110,18 +6241,19 @@ static void free_nested(struct vcpu_vmx *vmx) { if (!vmx->nested.vmxon) return; + vmx->nested.vmxon = false; - if (vmx->nested.current_vmptr != -1ull) { - nested_release_vmcs12(vmx); - vmx->nested.current_vmptr = -1ull; - vmx->nested.current_vmcs12 = NULL; - } + nested_release_vmcs12(vmx); 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); - vmx->nested.apic_access_page = 0; + vmx->nested.apic_access_page = NULL; + } + if (vmx->nested.virtual_apic_page) { + nested_release_page(vmx->nested.virtual_apic_page); + vmx->nested.virtual_apic_page = NULL; } nested_free_all_saved_vmcss(vmx); @@ -6152,11 +6284,8 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMCLEAR, &vmptr)) return 1; - if (vmptr == vmx->nested.current_vmptr) { + if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vmx); - vmx->nested.current_vmptr = -1ull; - vmx->nested.current_vmcs12 = NULL; - } page = nested_get_page(vcpu, vmptr); if (page == NULL) { @@ -6384,7 +6513,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu) return 1; /* Decode instruction info and find the field to read */ - field = kvm_register_read(vcpu, (((vmx_instruction_info) >> 28) & 0xf)); + field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf)); /* Read the field, zero-extended to a u64 field_value */ if (!vmcs12_read_any(vcpu, field, &field_value)) { nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); @@ -6397,7 +6526,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu) * on the guest's mode (32 or 64 bit), not on the given field's length. */ if (vmx_instruction_info & (1u << 10)) { - kvm_register_write(vcpu, (((vmx_instruction_info) >> 3) & 0xf), + kvm_register_writel(vcpu, (((vmx_instruction_info) >> 3) & 0xf), field_value); } else { if (get_vmx_mem_address(vcpu, exit_qualification, @@ -6434,21 +6563,21 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) return 1; if (vmx_instruction_info & (1u << 10)) - field_value = kvm_register_read(vcpu, + field_value = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 3) & 0xf)); else { if (get_vmx_mem_address(vcpu, exit_qualification, vmx_instruction_info, &gva)) return 1; if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, - &field_value, (is_long_mode(vcpu) ? 8 : 4), &e)) { + &field_value, (is_64_bit_mode(vcpu) ? 8 : 4), &e)) { kvm_inject_page_fault(vcpu, &e); return 1; } } - field = kvm_register_read(vcpu, (((vmx_instruction_info) >> 28) & 0xf)); + field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf)); if (vmcs_field_readonly(field)) { nested_vmx_failValid(vcpu, VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT); @@ -6498,9 +6627,8 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) skip_emulated_instruction(vcpu); return 1; } - if (vmx->nested.current_vmptr != -1ull) - nested_release_vmcs12(vmx); + nested_release_vmcs12(vmx); vmx->nested.current_vmptr = vmptr; vmx->nested.current_vmcs12 = new_vmcs12; vmx->nested.current_vmcs12_page = page; @@ -6571,7 +6699,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) } vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf); + type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf); types = (nested_vmx_ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6; @@ -6596,7 +6724,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) switch (type) { case VMX_EPT_EXTENT_GLOBAL: kvm_mmu_sync_roots(vcpu); - kvm_mmu_flush_tlb(vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); nested_vmx_succeed(vcpu); break; default: @@ -6751,7 +6879,7 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); int cr = exit_qualification & 15; int reg = (exit_qualification >> 8) & 15; - unsigned long val = kvm_register_read(vcpu, reg); + unsigned long val = kvm_register_readl(vcpu, reg); switch ((exit_qualification >> 4) & 3) { case 0: /* mov to cr */ @@ -6871,6 +6999,8 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_TASK_SWITCH: return 1; case EXIT_REASON_CPUID: + if (kvm_register_read(vcpu, VCPU_REGS_RAX) == 0xa) + return 0; return 1; case EXIT_REASON_HLT: return nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING); @@ -6915,7 +7045,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_MCE_DURING_VMENTRY: return 0; case EXIT_REASON_TPR_BELOW_THRESHOLD: - return 1; + return nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW); case EXIT_REASON_APIC_ACCESS: return nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); @@ -7036,6 +7166,12 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + + if (is_guest_mode(vcpu) && + nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) + return; + if (irr == -1 || tpr < irr) { vmcs_write32(TPR_THRESHOLD, 0); return; @@ -7073,6 +7209,29 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) vmx_set_msr_bitmap(vcpu); } +static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + /* + * Currently we do not handle the nested case where L2 has an + * APIC access page of its own; that page is still pinned. + * Hence, we skip the case where the VCPU is in guest mode _and_ + * L1 prepared an APIC access page for L2. + * + * For the case where L1 and L2 share the same APIC access page + * (flexpriority=Y but SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES clear + * in the vmcs12), this function will only update either the vmcs01 + * or the vmcs02. If the former, the vmcs02 will be updated by + * prepare_vmcs02. If the latter, the vmcs01 will be updated in + * the next L2->L1 exit. + */ + if (!is_guest_mode(vcpu) || + !nested_cpu_has2(vmx->nested.current_vmcs12, + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) + vmcs_write64(APIC_ACCESS_ADDR, hpa); +} + static void vmx_hwapic_isr_update(struct kvm *kvm, int isr) { u16 status; @@ -7112,7 +7271,26 @@ static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) if (max_irr == -1) return; - vmx_set_rvi(max_irr); + /* + * If a vmexit is needed, vmx_check_nested_events handles it. + */ + if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) + return; + + if (!is_guest_mode(vcpu)) { + vmx_set_rvi(max_irr); + return; + } + + /* + * Fall back to pre-APICv interrupt injection since L2 + * is run without virtual interrupt delivery. + */ + if (!kvm_event_needs_reinjection(vcpu) && + vmx_interrupt_allowed(vcpu)) { + kvm_queue_interrupt(vcpu, max_irr, false); + vmx_inject_irq(vcpu); + } } static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) @@ -7347,6 +7525,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vmx->emulation_required) return; + if (vmx->ple_window_dirty) { + vmx->ple_window_dirty = false; + vmcs_write32(PLE_WINDOW, vmx->ple_window); + } + if (vmx->nested.sync_shadow_vmcs) { copy_vmcs12_to_shadow(vmx); vmx->nested.sync_shadow_vmcs = false; @@ -7520,13 +7703,31 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_complete_interrupts(vmx); } +static void vmx_load_vmcs01(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + int cpu; + + if (vmx->loaded_vmcs == &vmx->vmcs01) + return; + + cpu = get_cpu(); + vmx->loaded_vmcs = &vmx->vmcs01; + vmx_vcpu_put(vcpu); + vmx_vcpu_load(vcpu, cpu); + vcpu->cpu = cpu; + put_cpu(); +} + static void vmx_free_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); free_vpid(vmx); - free_loaded_vmcs(vmx->loaded_vmcs); + leave_guest_mode(vcpu); + vmx_load_vmcs01(vcpu); free_nested(vmx); + free_loaded_vmcs(vmx->loaded_vmcs); kfree(vmx->guest_msrs); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, vmx); @@ -7548,6 +7749,9 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) goto free_vcpu; vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL); + BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0]) + > PAGE_SIZE); + err = -ENOMEM; if (!vmx->guest_msrs) { goto uninit_vcpu; @@ -7581,10 +7785,8 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (!kvm->arch.ept_identity_map_addr) kvm->arch.ept_identity_map_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR; - err = -ENOMEM; - if (alloc_identity_pagetable(kvm) != 0) - goto free_vmcs; - if (!init_rmode_identity_map(kvm)) + err = init_rmode_identity_map(kvm); + if (err) goto free_vmcs; } @@ -7763,6 +7965,55 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, kvm_inject_page_fault(vcpu, fault); } +static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { + /* TODO: Also verify bits beyond physical address width are 0 */ + if (!PAGE_ALIGNED(vmcs12->apic_access_addr)) + return false; + + /* + * Translate L1 physical address to host physical + * address for vmcs02. Keep the page pinned, so this + * physical address remains valid. We keep a reference + * to it so we can release it later. + */ + if (vmx->nested.apic_access_page) /* shouldn't happen */ + nested_release_page(vmx->nested.apic_access_page); + vmx->nested.apic_access_page = + nested_get_page(vcpu, vmcs12->apic_access_addr); + } + + if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) { + /* TODO: Also verify bits beyond physical address width are 0 */ + if (!PAGE_ALIGNED(vmcs12->virtual_apic_page_addr)) + return false; + + if (vmx->nested.virtual_apic_page) /* shouldn't happen */ + nested_release_page(vmx->nested.virtual_apic_page); + vmx->nested.virtual_apic_page = + nested_get_page(vcpu, vmcs12->virtual_apic_page_addr); + + /* + * Failing the vm entry is _not_ what the processor does + * but it's basically the only possibility we have. + * We could still enter the guest if CR8 load exits are + * enabled, CR8 store exits are enabled, and virtualize APIC + * access is disabled; in this case the processor would never + * use the TPR shadow and we could simply clear the bit from + * the execution control. But such a configuration is useless, + * so let's keep the code simple. + */ + if (!vmx->nested.virtual_apic_page) + return false; + } + + return true; +} + static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu) { u64 preemption_timeout = get_vmcs12(vcpu)->vmx_preemption_timer_value; @@ -7788,7 +8039,7 @@ static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu) /* * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it - * with L0's requirements for its guest (a.k.a. vmsc01), so we can run the L2 + * with L0's requirements for its guest (a.k.a. vmcs01), so we can run the L2 * guest in a way that will both be appropriate to L1's requests, and our * needs. In addition to modifying the active vmcs (which is vmcs02), this * function also has additional necessary side-effects, like setting various @@ -7836,7 +8087,13 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base); vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base); - vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl); + if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) { + kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); + vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl); + } else { + kvm_set_dr(vcpu, 7, vcpu->arch.dr7); + vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.vmcs01_debugctl); + } vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, vmcs12->vm_entry_intr_info_field); vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, @@ -7846,7 +8103,6 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, vmcs12->guest_interruptibility_info); vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs); - kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); vmx_set_rflags(vcpu, vmcs12->guest_rflags); vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, vmcs12->guest_pending_dbg_exceptions); @@ -7904,16 +8160,6 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) { /* - * Translate L1 physical address to host physical - * address for vmcs02. Keep the page pinned, so this - * physical address remains valid. We keep a reference - * to it so we can release it later. - */ - if (vmx->nested.apic_access_page) /* shouldn't happen */ - nested_release_page(vmx->nested.apic_access_page); - vmx->nested.apic_access_page = - nested_get_page(vcpu, vmcs12->apic_access_addr); - /* * If translation failed, no matter: This feature asks * to exit when accessing the given address, and if it * can never be accessed, this feature won't do @@ -7928,8 +8174,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) } else if (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm)) { exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; - vmcs_write64(APIC_ACCESS_ADDR, - page_to_phys(vcpu->kvm->arch.apic_access_page)); + kvm_vcpu_reload_apic_access_page(vcpu); } vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); @@ -7958,6 +8203,13 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING; exec_control &= ~CPU_BASED_TPR_SHADOW; exec_control |= vmcs12->cpu_based_vm_exec_control; + + if (exec_control & CPU_BASED_TPR_SHADOW) { + vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, + page_to_phys(vmx->nested.virtual_apic_page)); + vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold); + } + /* * Merging of IO and MSR bitmaps not currently supported. * Rather, exit every time. @@ -8113,14 +8365,13 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) } if ((vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_MSR_BITMAPS) && - !IS_ALIGNED(vmcs12->msr_bitmap, PAGE_SIZE)) { + !PAGE_ALIGNED(vmcs12->msr_bitmap)) { /*TODO: Also verify bits beyond physical address width are 0*/ nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); return 1; } - if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) && - !IS_ALIGNED(vmcs12->apic_access_addr, PAGE_SIZE)) { + if (!nested_get_vmcs12_pages(vcpu, vmcs12)) { /*TODO: Also verify bits beyond physical address width are 0*/ nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); return 1; @@ -8136,15 +8387,18 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) } if (!vmx_control_verify(vmcs12->cpu_based_vm_exec_control, - nested_vmx_procbased_ctls_low, nested_vmx_procbased_ctls_high) || + nested_vmx_true_procbased_ctls_low, + nested_vmx_procbased_ctls_high) || !vmx_control_verify(vmcs12->secondary_vm_exec_control, nested_vmx_secondary_ctls_low, nested_vmx_secondary_ctls_high) || !vmx_control_verify(vmcs12->pin_based_vm_exec_control, nested_vmx_pinbased_ctls_low, nested_vmx_pinbased_ctls_high) || !vmx_control_verify(vmcs12->vm_exit_controls, - nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high) || + nested_vmx_true_exit_ctls_low, + nested_vmx_exit_ctls_high) || !vmx_control_verify(vmcs12->vm_entry_controls, - nested_vmx_entry_ctls_low, nested_vmx_entry_ctls_high)) + nested_vmx_true_entry_ctls_low, + nested_vmx_entry_ctls_high)) { nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); return 1; @@ -8221,6 +8475,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) vmx->nested.vmcs01_tsc_offset = vmcs_read64(TSC_OFFSET); + if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) + vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); + cpu = get_cpu(); vmx->loaded_vmcs = vmcs02; vmx_vcpu_put(vcpu); @@ -8398,7 +8655,6 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12); vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12); - kvm_get_dr(vcpu, 7, (unsigned long *)&vmcs12->guest_dr7); vmcs12->guest_rsp = kvm_register_read(vcpu, VCPU_REGS_RSP); vmcs12->guest_rip = kvm_register_read(vcpu, VCPU_REGS_RIP); vmcs12->guest_rflags = vmcs_readl(GUEST_RFLAGS); @@ -8477,9 +8733,13 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, (vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) | (vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE); + if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) { + kvm_get_dr(vcpu, 7, (unsigned long *)&vmcs12->guest_dr7); + vmcs12->guest_ia32_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); + } + /* 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_exit_controls & VM_EXIT_SAVE_IA32_PAT) vmcs12->guest_ia32_pat = vmcs_read64(GUEST_IA32_PAT); if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_EFER) @@ -8670,7 +8930,6 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, unsigned long exit_qualification) { struct vcpu_vmx *vmx = to_vmx(vcpu); - int cpu; struct vmcs12 *vmcs12 = get_vmcs12(vcpu); /* trying to cancel vmlaunch/vmresume is a bug */ @@ -8680,6 +8939,8 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info, exit_qualification); + vmx_load_vmcs01(vcpu); + if ((exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) && nested_exit_intr_ack_set(vcpu)) { int irq = kvm_cpu_get_interrupt(vcpu); @@ -8695,13 +8956,6 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vmcs12->vm_exit_intr_error_code, KVM_ISA_VMX); - cpu = get_cpu(); - vmx->loaded_vmcs = &vmx->vmcs01; - vmx_vcpu_put(vcpu); - vmx_vcpu_load(vcpu, cpu); - vcpu->cpu = cpu; - put_cpu(); - vm_entry_controls_init(vmx, vmcs_read32(VM_ENTRY_CONTROLS)); vm_exit_controls_init(vmx, vmcs_read32(VM_EXIT_CONTROLS)); vmx_segment_cache_clear(vmx); @@ -8721,10 +8975,20 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, /* Unpin physical memory we referred to in vmcs02 */ if (vmx->nested.apic_access_page) { nested_release_page(vmx->nested.apic_access_page); - vmx->nested.apic_access_page = 0; + vmx->nested.apic_access_page = NULL; + } + if (vmx->nested.virtual_apic_page) { + nested_release_page(vmx->nested.virtual_apic_page); + vmx->nested.virtual_apic_page = NULL; } /* + * We are now running in L2, mmu_notifier will force to reload the + * page's hpa for L2 vmcs. Need to reload it for L1 before entering L1. + */ + kvm_vcpu_reload_apic_access_page(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. @@ -8777,6 +9041,12 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, return X86EMUL_CONTINUE; } +static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu) +{ + if (ple_gap) + shrink_ple_window(vcpu); +} + static struct kvm_x86_ops vmx_x86_ops = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, @@ -8821,7 +9091,6 @@ static struct kvm_x86_ops vmx_x86_ops = { .cache_reg = vmx_cache_reg, .get_rflags = vmx_get_rflags, .set_rflags = vmx_set_rflags, - .fpu_activate = vmx_fpu_activate, .fpu_deactivate = vmx_fpu_deactivate, .tlb_flush = vmx_flush_tlb, @@ -8844,6 +9113,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, .set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode, + .set_apic_access_page_addr = vmx_set_apic_access_page_addr, .vm_has_apicv = vmx_vm_has_apicv, .load_eoi_exitmap = vmx_load_eoi_exitmap, .hwapic_irr_update = vmx_hwapic_irr_update, @@ -8882,6 +9152,8 @@ static struct kvm_x86_ops vmx_x86_ops = { .mpx_supported = vmx_mpx_supported, .check_nested_events = vmx_check_nested_events, + + .sched_in = vmx_sched_in, }; static int __init vmx_init(void) @@ -8890,7 +9162,7 @@ static int __init vmx_init(void) rdmsrl_safe(MSR_EFER, &host_efer); - for (i = 0; i < NR_VMX_MSR; ++i) + for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) kvm_define_shared_msr(i, vmx_msr_index[i]); vmx_io_bitmap_a = (unsigned long *)__get_free_page(GFP_KERNEL); @@ -8996,6 +9268,8 @@ static int __init vmx_init(void) } else kvm_disable_tdp(); + update_ple_window_actual_max(); + return 0; out7: @@ -9029,7 +9303,7 @@ static void __exit vmx_exit(void) free_page((unsigned long)vmx_vmread_bitmap); #ifdef CONFIG_KEXEC - rcu_assign_pointer(crash_vmclear_loaded_vmcss, NULL); + RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL); synchronize_rcu(); #endif |