diff options
Diffstat (limited to 'arch/x86/kvm/vmx.c')
| -rw-r--r-- | arch/x86/kvm/vmx.c | 820 |
1 files changed, 445 insertions, 375 deletions
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 263e56059fd5..c51aaac953b4 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -33,6 +33,7 @@ #include <linux/slab.h> #include <linux/tboot.h> #include <linux/hrtimer.h> +#include <linux/nospec.h> #include "kvm_cache_regs.h" #include "x86.h" @@ -48,6 +49,7 @@ #include <asm/kexec.h> #include <asm/apic.h> #include <asm/irq_remapping.h> +#include <asm/nospec-branch.h> #include "trace.h" #include "pmu.h" @@ -108,6 +110,14 @@ static u64 __read_mostly host_xss; static bool __read_mostly enable_pml = 1; module_param_named(pml, enable_pml, bool, S_IRUGO); +#define MSR_TYPE_R 1 +#define MSR_TYPE_W 2 +#define MSR_TYPE_RW 3 + +#define MSR_BITMAP_MODE_X2APIC 1 +#define MSR_BITMAP_MODE_X2APIC_APICV 2 +#define MSR_BITMAP_MODE_LM 4 + #define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL /* Guest_tsc -> host_tsc conversion requires 64-bit division. */ @@ -132,6 +142,12 @@ module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO); #define VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE 5 +#define VMX_VPID_EXTENT_SUPPORTED_MASK \ + (VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT | \ + VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT | \ + VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT | \ + VMX_VPID_EXTENT_SINGLE_NON_GLOBAL_BIT) + /* * These 2 parameters are used to config the controls for Pause-Loop Exiting: * ple_gap: upper bound on the amount of time between two successive @@ -172,7 +188,6 @@ module_param(ple_window_max, int, S_IRUGO); extern const ulong vmx_return; #define NR_AUTOLOAD_MSRS 8 -#define VMCS02_POOL_SIZE 1 struct vmcs { u32 revision_id; @@ -190,6 +205,7 @@ struct loaded_vmcs { struct vmcs *shadow_vmcs; int cpu; int launched; + unsigned long *msr_bitmap; struct list_head loaded_vmcss_on_cpu_link; }; @@ -206,7 +222,7 @@ struct shared_msr_entry { * stored in guest memory specified by VMPTRLD, but is opaque to the guest, * which must access it using VMREAD/VMWRITE/VMCLEAR instructions. * More than one of these structures may exist, if L1 runs multiple L2 guests. - * nested_vmx_run() will use the data here to build a vmcs02: a VMCS for the + * nested_vmx_run() will use the data here to build the vmcs02: a VMCS for the * underlying hardware which will be used to run L2. * This structure is packed to ensure that its layout is identical across * machines (necessary for live migration). @@ -385,13 +401,6 @@ struct __packed vmcs12 { */ #define VMCS12_SIZE 0x1000 -/* Used to remember the last vmcs02 used for some recently used vmcs12s */ -struct vmcs02_list { - struct list_head list; - gpa_t vmptr; - struct loaded_vmcs vmcs02; -}; - /* * The nested_vmx structure is part of vcpu_vmx, and holds information we need * for correct emulation of VMX (i.e., nested VMX) on this vcpu. @@ -418,15 +427,15 @@ struct nested_vmx { */ bool sync_shadow_vmcs; - /* vmcs02_list cache of VMCSs recently used to run L2 guests */ - struct list_head vmcs02_pool; - int vmcs02_num; bool change_vmcs01_virtual_x2apic_mode; /* L2 must run next, and mustn't decide to exit to L1. */ bool nested_run_pending; + + struct loaded_vmcs vmcs02; + /* - * Guest pages referred to in vmcs02 with host-physical pointers, so - * we must keep them pinned while L2 runs. + * Guest pages referred to in the vmcs02 with host-physical + * pointers, so we must keep them pinned while L2 runs. */ struct page *apic_access_page; struct page *virtual_apic_page; @@ -435,8 +444,6 @@ struct nested_vmx { bool pi_pending; u16 posted_intr_nv; - unsigned long *msr_bitmap; - struct hrtimer preemption_timer; bool preemption_timer_expired; @@ -537,6 +544,7 @@ struct vcpu_vmx { unsigned long host_rsp; u8 fail; bool nmi_known_unmasked; + u8 msr_bitmap_mode; u32 exit_intr_info; u32 idt_vectoring_info; ulong rflags; @@ -548,6 +556,10 @@ struct vcpu_vmx { u64 msr_host_kernel_gs_base; u64 msr_guest_kernel_gs_base; #endif + + u64 arch_capabilities; + u64 spec_ctrl; + u32 vm_entry_controls_shadow; u32 vm_exit_controls_shadow; /* @@ -855,13 +867,18 @@ static const unsigned short vmcs_field_to_offset_table[] = { static inline short vmcs_field_to_offset(unsigned long field) { - BUILD_BUG_ON(ARRAY_SIZE(vmcs_field_to_offset_table) > SHRT_MAX); + const size_t size = ARRAY_SIZE(vmcs_field_to_offset_table); + unsigned short offset; - if (field >= ARRAY_SIZE(vmcs_field_to_offset_table) || - vmcs_field_to_offset_table[field] == 0) + BUILD_BUG_ON(size > SHRT_MAX); + if (field >= size) return -ENOENT; - return vmcs_field_to_offset_table[field]; + field = array_index_nospec(field, size); + offset = vmcs_field_to_offset_table[field]; + if (offset == 0) + return -ENOENT; + return offset; } static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) @@ -903,6 +920,9 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var); static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx); static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx); static int alloc_identity_pagetable(struct kvm *kvm); +static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu); +static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -922,12 +942,6 @@ static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock); static unsigned long *vmx_io_bitmap_a; static unsigned long *vmx_io_bitmap_b; -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_msr_bitmap_legacy_x2apic_apicv_inactive; -static unsigned long *vmx_msr_bitmap_longmode_x2apic_apicv_inactive; static unsigned long *vmx_vmread_bitmap; static unsigned long *vmx_vmwrite_bitmap; @@ -1844,6 +1858,52 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) vmcs_write32(EXCEPTION_BITMAP, eb); } +/* + * Check if MSR is intercepted for currently loaded MSR bitmap. + */ +static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) +{ + unsigned long *msr_bitmap; + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return true; + + msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap; + + if (msr <= 0x1fff) { + return !!test_bit(msr, msr_bitmap + 0x800 / f); + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + return !!test_bit(msr, msr_bitmap + 0xc00 / f); + } + + return true; +} + +/* + * Check if MSR is intercepted for L01 MSR bitmap. + */ +static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr) +{ + unsigned long *msr_bitmap; + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return true; + + msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap; + + if (msr <= 0x1fff) { + return !!test_bit(msr, msr_bitmap + 0x800 / f); + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + return !!test_bit(msr, msr_bitmap + 0xc00 / f); + } + + return true; +} + static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit) { @@ -2253,6 +2313,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) { per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs; vmcs_load(vmx->loaded_vmcs->vmcs); + indirect_branch_prediction_barrier(); } if (!already_loaded) { @@ -2521,36 +2582,6 @@ static void move_msr_up(struct vcpu_vmx *vmx, int from, int to) vmx->guest_msrs[from] = tmp; } -static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu) -{ - unsigned long *msr_bitmap; - - if (is_guest_mode(vcpu)) - msr_bitmap = to_vmx(vcpu)->nested.msr_bitmap; - else if (cpu_has_secondary_exec_ctrls() && - (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { - if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode_x2apic; - else - msr_bitmap = vmx_msr_bitmap_legacy_x2apic; - } else { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode_x2apic_apicv_inactive; - else - msr_bitmap = vmx_msr_bitmap_legacy_x2apic_apicv_inactive; - } - } else { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode; - else - msr_bitmap = vmx_msr_bitmap_legacy; - } - - vmcs_write64(MSR_BITMAP, __pa(msr_bitmap)); -} - /* * Set up the vmcs to automatically save and restore system * msrs. Don't touch the 64-bit msrs if the guest is in legacy @@ -2591,7 +2622,7 @@ static void setup_msrs(struct vcpu_vmx *vmx) vmx->save_nmsrs = save_nmsrs; if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(&vmx->vcpu); + vmx_update_msr_bitmap(&vmx->vcpu); } /* @@ -2814,8 +2845,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) */ if (enable_vpid) vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT | - VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT | - VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT; + VMX_VPID_EXTENT_SUPPORTED_MASK; else vmx->nested.nested_vmx_vpid_caps = 0; @@ -2980,6 +3010,19 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_TSC: msr_info->data = guest_read_tsc(vcpu); break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has_ibrs(vcpu)) + return 1; + + msr_info->data = to_vmx(vcpu)->spec_ctrl; + break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated && + !guest_cpuid_has_arch_capabilities(vcpu)) + return 1; + msr_info->data = to_vmx(vcpu)->arch_capabilities; + break; case MSR_IA32_SYSENTER_CS: msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); break; @@ -3084,6 +3127,68 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr_info); break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has_ibrs(vcpu)) + return 1; + + /* The STIBP bit doesn't fault even if it's not advertised */ + if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP)) + return 1; + + vmx->spec_ctrl = data; + + if (!data) + break; + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_vmx_merge_msr_bitmap. We should not touch the + * vmcs02.msr_bitmap here since it gets completely overwritten + * in the merging. We update the vmcs01 here for L1 as well + * since it will end up touching the MSR anyway now. + */ + vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, + MSR_IA32_SPEC_CTRL, + MSR_TYPE_RW); + break; + case MSR_IA32_PRED_CMD: + if (!msr_info->host_initiated && + !guest_cpuid_has_ibpb(vcpu)) + return 1; + + if (data & ~PRED_CMD_IBPB) + return 1; + + if (!data) + break; + + wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_vmx_merge_msr_bitmap. We should not touch the + * vmcs02.msr_bitmap here since it gets completely overwritten + * in the merging. + */ + vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD, + MSR_TYPE_W); + break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated) + return 1; + vmx->arch_capabilities = data; + 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)) @@ -3523,11 +3628,6 @@ static struct vmcs *alloc_vmcs_cpu(int cpu) return vmcs; } -static struct vmcs *alloc_vmcs(void) -{ - return alloc_vmcs_cpu(raw_smp_processor_id()); -} - static void free_vmcs(struct vmcs *vmcs) { free_pages((unsigned long)vmcs, vmcs_config.order); @@ -3543,9 +3643,38 @@ static void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) loaded_vmcs_clear(loaded_vmcs); free_vmcs(loaded_vmcs->vmcs); loaded_vmcs->vmcs = NULL; + if (loaded_vmcs->msr_bitmap) + free_page((unsigned long)loaded_vmcs->msr_bitmap); WARN_ON(loaded_vmcs->shadow_vmcs != NULL); } +static struct vmcs *alloc_vmcs(void) +{ + return alloc_vmcs_cpu(raw_smp_processor_id()); +} + +static int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) +{ + loaded_vmcs->vmcs = alloc_vmcs(); + if (!loaded_vmcs->vmcs) + return -ENOMEM; + + loaded_vmcs->shadow_vmcs = NULL; + loaded_vmcs_init(loaded_vmcs); + + if (cpu_has_vmx_msr_bitmap()) { + loaded_vmcs->msr_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); + if (!loaded_vmcs->msr_bitmap) + goto out_vmcs; + memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE); + } + return 0; + +out_vmcs: + free_loaded_vmcs(loaded_vmcs); + return -ENOMEM; +} + static void free_kvm_area(void) { int cpu; @@ -4552,10 +4681,8 @@ static void free_vpid(int vpid) spin_unlock(&vmx_vpid_lock); } -#define MSR_TYPE_R 1 -#define MSR_TYPE_W 2 -static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, - u32 msr, int type) +static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type) { int f = sizeof(unsigned long); @@ -4589,8 +4716,8 @@ static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, } } -static void __vmx_enable_intercept_for_msr(unsigned long *msr_bitmap, - u32 msr, int type) +static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type) { int f = sizeof(unsigned long); @@ -4624,6 +4751,15 @@ static void __vmx_enable_intercept_for_msr(unsigned long *msr_bitmap, } } +static void __always_inline vmx_set_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type, bool value) +{ + if (value) + vmx_enable_intercept_for_msr(msr_bitmap, msr, type); + else + vmx_disable_intercept_for_msr(msr_bitmap, msr, type); +} + /* * If a msr is allowed by L0, we should check whether it is allowed by L1. * The corresponding bit will be cleared unless both of L0 and L1 allow it. @@ -4670,58 +4806,68 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1, } } -static void vmx_disable_intercept_for_msr(u32 msr, bool longmode_only) +static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu) { - if (!longmode_only) - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy, - msr, MSR_TYPE_R | MSR_TYPE_W); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode, - msr, MSR_TYPE_R | MSR_TYPE_W); -} + u8 mode = 0; -static void vmx_enable_intercept_msr_read_x2apic(u32 msr, bool apicv_active) -{ - if (apicv_active) { - __vmx_enable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, - msr, MSR_TYPE_R); - __vmx_enable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, - msr, MSR_TYPE_R); - } else { - __vmx_enable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv_inactive, - msr, MSR_TYPE_R); - __vmx_enable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv_inactive, - msr, MSR_TYPE_R); + if (cpu_has_secondary_exec_ctrls() && + (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { + mode |= MSR_BITMAP_MODE_X2APIC; + if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) + mode |= MSR_BITMAP_MODE_X2APIC_APICV; } + + if (is_long_mode(vcpu)) + mode |= MSR_BITMAP_MODE_LM; + + return mode; } -static void vmx_disable_intercept_msr_read_x2apic(u32 msr, bool apicv_active) +#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) + +static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap, + u8 mode) { - if (apicv_active) { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, - msr, MSR_TYPE_R); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, - msr, MSR_TYPE_R); - } else { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv_inactive, - msr, MSR_TYPE_R); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv_inactive, - msr, MSR_TYPE_R); + int msr; + + for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { + unsigned word = msr / BITS_PER_LONG; + msr_bitmap[word] = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0; + msr_bitmap[word + (0x800 / sizeof(long))] = ~0; + } + + if (mode & MSR_BITMAP_MODE_X2APIC) { + /* + * TPR reads and writes can be virtualized even if virtual interrupt + * delivery is not in use. + */ + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW); + if (mode & MSR_BITMAP_MODE_X2APIC_APICV) { + vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_R); + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_EOI), MSR_TYPE_W); + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W); + } } } -static void vmx_disable_intercept_msr_write_x2apic(u32 msr, bool apicv_active) +static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu) { - if (apicv_active) { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, - msr, MSR_TYPE_W); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, - msr, MSR_TYPE_W); - } else { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv_inactive, - msr, MSR_TYPE_W); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv_inactive, - msr, MSR_TYPE_W); - } + struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; + u8 mode = vmx_msr_bitmap_mode(vcpu); + u8 changed = mode ^ vmx->msr_bitmap_mode; + + if (!changed) + return; + + vmx_set_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW, + !(mode & MSR_BITMAP_MODE_LM)); + + if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV)) + vmx_update_msr_bitmap_x2apic(msr_bitmap, mode); + + vmx->msr_bitmap_mode = mode; } static bool vmx_get_enable_apicv(void) @@ -4729,30 +4875,45 @@ static bool vmx_get_enable_apicv(void) return enable_apicv; } -static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) +static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + gfn_t gfn; + + /* + * Don't need to mark the APIC access page dirty; it is never + * written to by the CPU during APIC virtualization. + */ + + if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) { + gfn = vmcs12->virtual_apic_page_addr >> PAGE_SHIFT; + kvm_vcpu_mark_page_dirty(vcpu, gfn); + } + + if (nested_cpu_has_posted_intr(vmcs12)) { + gfn = vmcs12->posted_intr_desc_addr >> PAGE_SHIFT; + kvm_vcpu_mark_page_dirty(vcpu, gfn); + } +} + + +static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); int max_irr; void *vapic_page; u16 status; - if (vmx->nested.pi_desc && - vmx->nested.pi_pending) { - vmx->nested.pi_pending = false; - if (!pi_test_and_clear_on(vmx->nested.pi_desc)) - return 0; - - max_irr = find_last_bit( - (unsigned long *)vmx->nested.pi_desc->pir, 256); + if (!vmx->nested.pi_desc || !vmx->nested.pi_pending) + return; - if (max_irr == 256) - return 0; + vmx->nested.pi_pending = false; + if (!pi_test_and_clear_on(vmx->nested.pi_desc)) + return; + max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256); + if (max_irr != 256) { vapic_page = kmap(vmx->nested.virtual_apic_page); - if (!vapic_page) { - WARN_ON(1); - return -ENOMEM; - } __kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page); kunmap(vmx->nested.virtual_apic_page); @@ -4763,7 +4924,8 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) vmcs_write16(GUEST_INTR_STATUS, status); } } - return 0; + + nested_mark_vmcs12_pages_dirty(vcpu); } static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu) @@ -4810,14 +4972,15 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, if (is_guest_mode(vcpu) && vector == vmx->nested.posted_intr_nv) { - /* the PIR and ON have been set by L1. */ - kvm_vcpu_trigger_posted_interrupt(vcpu); /* * If a posted intr is not recognized by hardware, * we will accomplish it in the next vmentry. */ vmx->nested.pi_pending = true; kvm_make_request(KVM_REQ_EVENT, vcpu); + /* the PIR and ON have been set by L1. */ + if (!kvm_vcpu_trigger_posted_interrupt(vcpu)) + kvm_vcpu_kick(vcpu); return 0; } return -1; @@ -4950,7 +5113,7 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) } if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); } static u32 vmx_exec_control(struct vcpu_vmx *vmx) @@ -5039,7 +5202,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) 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(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap)); vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */ @@ -5113,6 +5276,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) ++vmx->nmsrs; } + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, vmx->arch_capabilities); vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl); @@ -5141,6 +5306,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u64 cr0; vmx->rmode.vm86_active = 0; + vmx->spec_ctrl = 0; vmx->soft_vnmi_blocked = 0; @@ -5185,7 +5351,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmcs_write64(GUEST_IA32_DEBUGCTL, 0); } - vmcs_writel(GUEST_RFLAGS, 0x02); + kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); kvm_rip_write(vcpu, 0xfff0); vmcs_writel(GUEST_GDTR_BASE, 0); @@ -6248,7 +6414,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (test_bit(KVM_REQ_EVENT, &vcpu->requests)) return 1; - err = emulate_instruction(vcpu, EMULTYPE_NO_REEXECUTE); + err = emulate_instruction(vcpu, 0); if (err == EMULATE_USER_EXIT) { ++vcpu->stat.mmio_exits; @@ -6370,7 +6536,7 @@ static void wakeup_handler(void) static __init int hardware_setup(void) { - int r = -ENOMEM, i, msr; + int r = -ENOMEM, i; rdmsrl_safe(MSR_EFER, &host_efer); @@ -6385,41 +6551,13 @@ static __init int hardware_setup(void) if (!vmx_io_bitmap_b) goto out; - vmx_msr_bitmap_legacy = (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_legacy) - goto out1; - - vmx_msr_bitmap_legacy_x2apic = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_legacy_x2apic) - goto out2; - - vmx_msr_bitmap_legacy_x2apic_apicv_inactive = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_legacy_x2apic_apicv_inactive) - goto out3; - - vmx_msr_bitmap_longmode = (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_longmode) - goto out4; - - vmx_msr_bitmap_longmode_x2apic = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_longmode_x2apic) - goto out5; - - vmx_msr_bitmap_longmode_x2apic_apicv_inactive = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_longmode_x2apic_apicv_inactive) - goto out6; - vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_vmread_bitmap) - goto out7; + goto out1; vmx_vmwrite_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_vmwrite_bitmap) - goto out8; + goto out2; memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE); memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE); @@ -6428,12 +6566,9 @@ static __init int hardware_setup(void) memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE); - memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE); - memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE); - if (setup_vmcs_config(&vmcs_config) < 0) { r = -EIO; - goto out9; + goto out3; } if (boot_cpu_has(X86_FEATURE_NX)) @@ -6490,47 +6625,8 @@ static __init int hardware_setup(void) kvm_tsc_scaling_ratio_frac_bits = 48; } - vmx_disable_intercept_for_msr(MSR_FS_BASE, false); - vmx_disable_intercept_for_msr(MSR_GS_BASE, false); - vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false); - - memcpy(vmx_msr_bitmap_legacy_x2apic, - vmx_msr_bitmap_legacy, PAGE_SIZE); - memcpy(vmx_msr_bitmap_longmode_x2apic, - vmx_msr_bitmap_longmode, PAGE_SIZE); - memcpy(vmx_msr_bitmap_legacy_x2apic_apicv_inactive, - vmx_msr_bitmap_legacy, PAGE_SIZE); - memcpy(vmx_msr_bitmap_longmode_x2apic_apicv_inactive, - vmx_msr_bitmap_longmode, PAGE_SIZE); - set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ - /* - * enable_apicv && kvm_vcpu_apicv_active() - */ - for (msr = 0x800; msr <= 0x8ff; msr++) - vmx_disable_intercept_msr_read_x2apic(msr, true); - - /* TMCCT */ - vmx_enable_intercept_msr_read_x2apic(0x839, true); - /* TPR */ - vmx_disable_intercept_msr_write_x2apic(0x808, true); - /* EOI */ - vmx_disable_intercept_msr_write_x2apic(0x80b, true); - /* SELF-IPI */ - vmx_disable_intercept_msr_write_x2apic(0x83f, true); - - /* - * (enable_apicv && !kvm_vcpu_apicv_active()) || - * !enable_apicv - */ - /* TPR */ - vmx_disable_intercept_msr_read_x2apic(0x808, false); - vmx_disable_intercept_msr_write_x2apic(0x808, false); - if (enable_ept) { kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK, (enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull, @@ -6576,22 +6672,10 @@ static __init int hardware_setup(void) return alloc_kvm_area(); -out9: - free_page((unsigned long)vmx_vmwrite_bitmap); -out8: - free_page((unsigned long)vmx_vmread_bitmap); -out7: - free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic_apicv_inactive); -out6: - free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic); -out5: - free_page((unsigned long)vmx_msr_bitmap_longmode); -out4: - free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic_apicv_inactive); out3: - free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic); + free_page((unsigned long)vmx_vmwrite_bitmap); out2: - free_page((unsigned long)vmx_msr_bitmap_legacy); + free_page((unsigned long)vmx_vmread_bitmap); out1: free_page((unsigned long)vmx_io_bitmap_b); out: @@ -6602,12 +6686,6 @@ out: static __exit void hardware_unsetup(void) { - free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic); - free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic_apicv_inactive); - free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic); - free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic_apicv_inactive); - free_page((unsigned long)vmx_msr_bitmap_legacy); - 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); @@ -6655,94 +6733,6 @@ static int handle_monitor(struct kvm_vcpu *vcpu) } /* - * To run an L2 guest, we need a vmcs02 based on the L1-specified vmcs12. - * We could reuse a single VMCS for all the L2 guests, but we also want the - * option to allocate a separate vmcs02 for each separate loaded vmcs12 - this - * allows keeping them loaded on the processor, and in the future will allow - * optimizations where prepare_vmcs02 doesn't need to set all the fields on - * every entry if they never change. - * So we keep, in vmx->nested.vmcs02_pool, a cache of size VMCS02_POOL_SIZE - * (>=0) with a vmcs02 for each recently loaded vmcs12s, most recent first. - * - * The following functions allocate and free a vmcs02 in this pool. - */ - -/* Get a VMCS from the pool to use as vmcs02 for the current vmcs12. */ -static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx) -{ - struct vmcs02_list *item; - list_for_each_entry(item, &vmx->nested.vmcs02_pool, list) - if (item->vmptr == vmx->nested.current_vmptr) { - list_move(&item->list, &vmx->nested.vmcs02_pool); - return &item->vmcs02; - } - - if (vmx->nested.vmcs02_num >= max(VMCS02_POOL_SIZE, 1)) { - /* Recycle the least recently used VMCS. */ - item = list_last_entry(&vmx->nested.vmcs02_pool, - struct vmcs02_list, list); - item->vmptr = vmx->nested.current_vmptr; - list_move(&item->list, &vmx->nested.vmcs02_pool); - return &item->vmcs02; - } - - /* Create a new VMCS */ - item = kmalloc(sizeof(struct vmcs02_list), GFP_KERNEL); - if (!item) - return NULL; - item->vmcs02.vmcs = alloc_vmcs(); - item->vmcs02.shadow_vmcs = NULL; - if (!item->vmcs02.vmcs) { - kfree(item); - return NULL; - } - loaded_vmcs_init(&item->vmcs02); - item->vmptr = vmx->nested.current_vmptr; - list_add(&(item->list), &(vmx->nested.vmcs02_pool)); - vmx->nested.vmcs02_num++; - return &item->vmcs02; -} - -/* Free and remove from pool a vmcs02 saved for a vmcs12 (if there is one) */ -static void nested_free_vmcs02(struct vcpu_vmx *vmx, gpa_t vmptr) -{ - struct vmcs02_list *item; - list_for_each_entry(item, &vmx->nested.vmcs02_pool, list) - if (item->vmptr == vmptr) { - free_loaded_vmcs(&item->vmcs02); - list_del(&item->list); - kfree(item); - vmx->nested.vmcs02_num--; - return; - } -} - -/* - * Free all VMCSs saved for this vcpu, except the one pointed by - * 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) { - /* - * 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--; - } -} - -/* * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(), * set the success or error code of an emulated VMX instruction, as specified * by Vol 2B, VMX Instruction Reference, "Conventions". @@ -7016,6 +7006,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu) struct vmcs *shadow_vmcs; const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; + int r; /* The Intel VMX Instruction Reference lists a bunch of bits that * are prerequisite to running VMXON, most notably cr4.VMXE must be @@ -7055,12 +7046,9 @@ static int handle_vmon(struct kvm_vcpu *vcpu) return 1; } - if (cpu_has_vmx_msr_bitmap()) { - vmx->nested.msr_bitmap = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx->nested.msr_bitmap) - goto out_msr_bitmap; - } + r = alloc_loaded_vmcs(&vmx->nested.vmcs02); + if (r < 0) + goto out_vmcs02; vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL); if (!vmx->nested.cached_vmcs12) @@ -7077,9 +7065,6 @@ static int handle_vmon(struct kvm_vcpu *vcpu) vmx->vmcs01.shadow_vmcs = shadow_vmcs; } - INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool)); - vmx->nested.vmcs02_num = 0; - hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; @@ -7094,9 +7079,9 @@ out_shadow_vmcs: kfree(vmx->nested.cached_vmcs12); out_cached_vmcs12: - free_page((unsigned long)vmx->nested.msr_bitmap); + free_loaded_vmcs(&vmx->nested.vmcs02); -out_msr_bitmap: +out_vmcs02: return -ENOMEM; } @@ -7172,17 +7157,13 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->nested.vmxon = false; free_vpid(vmx->nested.vpid02); nested_release_vmcs12(vmx); - if (vmx->nested.msr_bitmap) { - free_page((unsigned long)vmx->nested.msr_bitmap); - vmx->nested.msr_bitmap = NULL; - } if (enable_shadow_vmcs) { vmcs_clear(vmx->vmcs01.shadow_vmcs); free_vmcs(vmx->vmcs01.shadow_vmcs); vmx->vmcs01.shadow_vmcs = NULL; } kfree(vmx->nested.cached_vmcs12); - /* Unpin physical memory we referred to in current vmcs02 */ + /* Unpin physical memory we referred to in the vmcs02 */ if (vmx->nested.apic_access_page) { nested_release_page(vmx->nested.apic_access_page); vmx->nested.apic_access_page = NULL; @@ -7198,7 +7179,7 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->nested.pi_desc = NULL; } - nested_free_all_saved_vmcss(vmx); + free_loaded_vmcs(&vmx->nested.vmcs02); } /* Emulate the VMXOFF instruction */ @@ -7232,8 +7213,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) vmptr + offsetof(struct vmcs12, launch_state), &zero, sizeof(zero)); - nested_free_vmcs02(vmx, vmptr); - skip_emulated_instruction(vcpu); nested_vmx_succeed(vcpu); return 1; @@ -7711,7 +7690,8 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf); - types = (vmx->nested.nested_vmx_vpid_caps >> 8) & 0x7; + types = (vmx->nested.nested_vmx_vpid_caps & + VMX_VPID_EXTENT_SUPPORTED_MASK) >> 8; if (type >= 32 || !(types & (1 << type))) { nested_vmx_failValid(vcpu, @@ -7733,21 +7713,27 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) } switch (type) { + case VMX_VPID_EXTENT_INDIVIDUAL_ADDR: case VMX_VPID_EXTENT_SINGLE_CONTEXT: - /* - * Old versions of KVM use the single-context version so we - * have to support it; just treat it the same as all-context. - */ + case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL: + if (!vpid) { + nested_vmx_failValid(vcpu, + VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + skip_emulated_instruction(vcpu); + return 1; + } + break; case VMX_VPID_EXTENT_ALL_CONTEXT: - __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02); - nested_vmx_succeed(vcpu); break; default: - /* Trap individual address invalidation invvpid calls */ - BUG_ON(1); - break; + WARN_ON_ONCE(1); + skip_emulated_instruction(vcpu); + return 1; } + __vmx_flush_tlb(vcpu, vmx->nested.vpid02); + nested_vmx_succeed(vcpu); + skip_emulated_instruction(vcpu); return 1; } @@ -8020,6 +8006,19 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) vmcs_read32(VM_EXIT_INTR_ERROR_CODE), KVM_ISA_VMX); + /* + * The host physical addresses of some pages of guest memory + * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC + * Page). The CPU may write to these pages via their host + * physical address while L2 is running, bypassing any + * address-translation-based dirty tracking (e.g. EPT write + * protection). + * + * Mark them dirty on every exit from L2 to prevent them from + * getting out of sync with dirty tracking. + */ + nested_mark_vmcs12_pages_dirty(vcpu); + if (vmx->nested.nested_run_pending) return false; @@ -8511,7 +8510,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) } vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control); - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); } static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa) @@ -8667,14 +8666,14 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) #endif "pushf\n\t" __ASM_SIZE(push) " $%c[cs]\n\t" - "call *%[entry]\n\t" + CALL_NOSPEC : #ifdef CONFIG_X86_64 [sp]"=&r"(tmp), #endif "+r"(__sp) : - [entry]"r"(entry), + THUNK_TARGET(entry), [ss]"i"(__KERNEL_DS), [cs]"i"(__KERNEL_CS) ); @@ -8900,6 +8899,15 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_arm_hv_timer(vcpu); + /* + * If this vCPU has touched SPEC_CTRL, restore the guest's value if + * it's non-zero. Since vmentry is serialising on affected CPUs, there + * is no need to worry about the conditional branch over the wrmsr + * being speculatively taken. + */ + if (vmx->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + vmx->__launched = vmx->loaded_vmcs->launched; asm( /* Store host registers */ @@ -8948,6 +8956,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) /* Save guest registers, load host registers, keep flags */ "mov %0, %c[wordsize](%%" _ASM_SP ") \n\t" "pop %0 \n\t" + "setbe %c[fail](%0)\n\t" "mov %%" _ASM_AX ", %c[rax](%0) \n\t" "mov %%" _ASM_BX ", %c[rbx](%0) \n\t" __ASM_SIZE(pop) " %c[rcx](%0) \n\t" @@ -8964,12 +8973,23 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) "mov %%r13, %c[r13](%0) \n\t" "mov %%r14, %c[r14](%0) \n\t" "mov %%r15, %c[r15](%0) \n\t" + "xor %%r8d, %%r8d \n\t" + "xor %%r9d, %%r9d \n\t" + "xor %%r10d, %%r10d \n\t" + "xor %%r11d, %%r11d \n\t" + "xor %%r12d, %%r12d \n\t" + "xor %%r13d, %%r13d \n\t" + "xor %%r14d, %%r14d \n\t" + "xor %%r15d, %%r15d \n\t" #endif "mov %%cr2, %%" _ASM_AX " \n\t" "mov %%" _ASM_AX ", %c[cr2](%0) \n\t" + "xor %%eax, %%eax \n\t" + "xor %%ebx, %%ebx \n\t" + "xor %%esi, %%esi \n\t" + "xor %%edi, %%edi \n\t" "pop %%" _ASM_BP "; pop %%" _ASM_DX " \n\t" - "setbe %c[fail](%0) \n\t" ".pushsection .rodata \n\t" ".global vmx_return \n\t" "vmx_return: " _ASM_PTR " 2b \n\t" @@ -9006,6 +9026,30 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) #endif ); + /* + * We do not use IBRS in the kernel. If this vCPU has used the + * SPEC_CTRL MSR it may have left it on; save the value and + * turn it off. This is much more efficient than blindly adding + * it to the atomic save/restore list. Especially as the former + * (Saving guest MSRs on vmexit) doesn't even exist in KVM. + * + * For non-nested case: + * If the L01 MSR bitmap does not intercept the MSR, then we need to + * save it. + * + * For nested case: + * If the L02 MSR bitmap does not intercept the MSR, then we need to + * save it. + */ + if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) + rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + + if (vmx->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + + /* Eliminate branch target predictions from guest mode */ + vmexit_fill_RSB(); + /* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */ if (debugctlmsr) update_debugctlmsr(debugctlmsr); @@ -9116,6 +9160,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) { int err; struct vcpu_vmx *vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); + unsigned long *msr_bitmap; int cpu; if (!vmx) @@ -9148,17 +9193,24 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (!vmx->guest_msrs) goto free_pml; - vmx->loaded_vmcs = &vmx->vmcs01; - vmx->loaded_vmcs->vmcs = alloc_vmcs(); - vmx->loaded_vmcs->shadow_vmcs = NULL; - if (!vmx->loaded_vmcs->vmcs) - goto free_msrs; if (!vmm_exclusive) kvm_cpu_vmxon(__pa(per_cpu(vmxarea, raw_smp_processor_id()))); - loaded_vmcs_init(vmx->loaded_vmcs); + err = alloc_loaded_vmcs(&vmx->vmcs01); if (!vmm_exclusive) kvm_cpu_vmxoff(); + if (err < 0) + goto free_msrs; + + msr_bitmap = vmx->vmcs01.msr_bitmap; + vmx_disable_intercept_for_msr(msr_bitmap, MSR_FS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_GS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW); + vmx->msr_bitmap_mode = 0; + vmx->loaded_vmcs = &vmx->vmcs01; cpu = get_cpu(); vmx_vcpu_load(&vmx->vcpu, cpu); vmx->vcpu.cpu = cpu; @@ -9552,21 +9604,31 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, int msr; struct page *page; unsigned long *msr_bitmap_l1; - unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.msr_bitmap; + unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap; + /* + * pred_cmd & spec_ctrl are trying to verify two things: + * + * 1. L0 gave a permission to L1 to actually passthrough the MSR. This + * ensures that we do not accidentally generate an L02 MSR bitmap + * from the L12 MSR bitmap that is too permissive. + * 2. That L1 or L2s have actually used the MSR. This avoids + * unnecessarily merging of the bitmap if the MSR is unused. This + * works properly because we only update the L01 MSR bitmap lazily. + * So even if L0 should pass L1 these MSRs, the L01 bitmap is only + * updated to reflect this when L1 (or its L2s) actually write to + * the MSR. + */ + bool pred_cmd = !msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); + bool spec_ctrl = !msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL); - /* This shortcut is ok because we support only x2APIC MSRs so far. */ - if (!nested_cpu_has_virt_x2apic_mode(vmcs12)) + if (!nested_cpu_has_virt_x2apic_mode(vmcs12) && + !pred_cmd && !spec_ctrl) return false; page = nested_get_page(vcpu, vmcs12->msr_bitmap); if (!page) return false; msr_bitmap_l1 = (unsigned long *)kmap(page); - if (!msr_bitmap_l1) { - nested_release_page_clean(page); - WARN_ON(1); - return false; - } memset(msr_bitmap_l0, 0xff, PAGE_SIZE); @@ -9593,6 +9655,19 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, MSR_TYPE_W); } } + + if (spec_ctrl) + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_SPEC_CTRL, + MSR_TYPE_R | MSR_TYPE_W); + + if (pred_cmd) + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PRED_CMD, + MSR_TYPE_W); + kunmap(page); nested_release_page_clean(page); @@ -10072,6 +10147,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (kvm_has_tsc_control) decache_tsc_multiplier(vmx); + if (cpu_has_vmx_msr_bitmap()) + vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap)); + if (enable_vpid) { /* * There is no direct mapping between vpid02 and vpid12, the @@ -10167,7 +10245,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) struct vmcs12 *vmcs12; struct vcpu_vmx *vmx = to_vmx(vcpu); int cpu; - struct loaded_vmcs *vmcs02; bool ia32e; u32 msr_entry_idx; @@ -10307,17 +10384,13 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) * the nested entry. */ - vmcs02 = nested_get_current_vmcs02(vmx); - if (!vmcs02) - return -ENOMEM; - enter_guest_mode(vcpu); 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->loaded_vmcs = &vmx->nested.vmcs02; vmx_vcpu_put(vcpu); vmx_vcpu_load(vcpu, cpu); vcpu->cpu = cpu; @@ -10469,7 +10542,8 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) return 0; } - return vmx_complete_nested_posted_interrupt(vcpu); + vmx_complete_nested_posted_interrupt(vcpu); + return 0; } static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu) @@ -10780,7 +10854,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vmcs_write64(GUEST_IA32_DEBUGCTL, 0); if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr, vmcs12->vm_exit_msr_load_count)) @@ -10831,10 +10905,6 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vm_exit_controls_reset_shadow(vmx); 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); - load_vmcs12_host_state(vcpu, vmcs12); /* Update any VMCS fields that might have changed while L2 ran */ |