From: Paolo Bonzini <pbonzini@xxxxxxxxxx> (cherry picked from commit 904e14fb7cb96401a7dc803ca2863fd5ba32ffe6) Place the MSR bitmap in struct loaded_vmcs, and update it in place every time the x2apic or APICv state can change. This is rare and the loop can handle 64 MSRs per iteration, in a similar fashion as nested_vmx_prepare_msr_bitmap. This prepares for choosing, on a per-VM basis, whether to intercept the SPEC_CTRL and PRED_CMD MSRs. Cc: stable@xxxxxxxxxxxxxxx # prereq for Spectre mitigation Suggested-by: Jim Mattson <jmattson@xxxxxxxxxx> Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx> Signed-off-by: David Woodhouse <dwmw@xxxxxxxxxxxx> Signed-off-by: Yi Sun <yi.y.sun@xxxxxxxxxxxxxxx> [v4.4 backport] Conflicts: arch/x86/kvm/vmx.c --- arch/x86/kvm/vmx.c | 301 +++++++++++++++++++++-------------------------------- 1 file changed, 120 insertions(+), 181 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index b3e71a5..20351a8 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -109,6 +109,13 @@ 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_LM 4 + #define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL #define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD) @@ -188,6 +195,7 @@ struct loaded_vmcs { struct vmcs *vmcs; int cpu; int launched; + unsigned long *msr_bitmap; struct list_head loaded_vmcss_on_cpu_link; }; @@ -523,6 +531,7 @@ 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; @@ -881,6 +890,7 @@ 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 int alloc_identity_pagetable(struct kvm *kvm); +static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -900,11 +910,6 @@ 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_nested; static unsigned long *vmx_vmread_bitmap; static unsigned long *vmx_vmwrite_bitmap; @@ -2343,27 +2348,6 @@ 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 = vmx_msr_bitmap_nested; - else if (vcpu->arch.apic_base & X2APIC_ENABLE) { - 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; - 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 @@ -2404,7 +2388,7 @@ 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); } /* @@ -3357,6 +3341,8 @@ 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); } static struct vmcs *alloc_vmcs(void) @@ -3371,7 +3357,18 @@ static int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) return -ENOMEM; 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) @@ -4370,10 +4367,8 @@ 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); @@ -4407,8 +4402,8 @@ 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); @@ -4442,6 +4437,15 @@ 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. @@ -4488,37 +4492,61 @@ 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) -{ - __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); + if (cpu_has_secondary_exec_ctrls() && + (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { + mode |= MSR_BITMAP_MODE_X2APIC; + } + + if (is_long_mode(vcpu)) + mode |= MSR_BITMAP_MODE_LM; + + return mode; } -static void vmx_disable_intercept_msr_read_x2apic(u32 msr) +#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) + +static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap, + u8 mode) { - __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); + int msr; + + for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { + unsigned word = msr / BITS_PER_LONG; + msr_bitmap[word] = ~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); + } } -static void vmx_disable_intercept_msr_write_x2apic(u32 msr) +static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu) { - __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); + 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)) + vmx_update_msr_bitmap_x2apic(msr_bitmap, mode); + + vmx->msr_bitmap_mode = mode; } static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu) @@ -4818,7 +4846,7 @@ 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 */ @@ -6153,7 +6181,7 @@ 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); @@ -6168,38 +6196,13 @@ 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_longmode = (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_longmode) - goto out3; - - vmx_msr_bitmap_longmode_x2apic = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_longmode_x2apic) - goto out4; - - if (nested) { - vmx_msr_bitmap_nested = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_nested) - goto out5; - } - vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_vmread_bitmap) - goto out6; + goto out1; vmx_vmwrite_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_vmwrite_bitmap) - goto out7; + goto out2; memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE); memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE); @@ -6208,14 +6211,9 @@ 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 (nested) - memset(vmx_msr_bitmap_nested, 0xff, PAGE_SIZE); - if (setup_vmcs_config(&vmcs_config) < 0) { r = -EIO; - goto out8; + goto out3; } if (boot_cpu_has(X86_FEATURE_NX)) @@ -6281,38 +6279,8 @@ static __init int hardware_setup(void) kvm_x86_ops->sync_pir_to_irr = vmx_sync_pir_to_irr_dummy; } - 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); - set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ - if (enable_apicv) { - for (msr = 0x800; msr <= 0x8ff; msr++) - vmx_disable_intercept_msr_read_x2apic(msr); - - /* According SDM, in x2apic mode, the whole id reg is used. - * But in KVM, it only use the highest eight bits. Need to - * intercept it */ - vmx_enable_intercept_msr_read_x2apic(0x802); - /* TMCCT */ - vmx_enable_intercept_msr_read_x2apic(0x839); - /* TPR */ - vmx_disable_intercept_msr_write_x2apic(0x808); - /* EOI */ - vmx_disable_intercept_msr_write_x2apic(0x80b); - /* SELF-IPI */ - vmx_disable_intercept_msr_write_x2apic(0x83f); - } - if (enable_ept) { kvm_mmu_set_mask_ptes(0ull, (enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull, @@ -6343,21 +6311,10 @@ static __init int hardware_setup(void) return alloc_kvm_area(); -out8: - free_page((unsigned long)vmx_vmwrite_bitmap); -out7: - free_page((unsigned long)vmx_vmread_bitmap); -out6: - if (nested) - free_page((unsigned long)vmx_msr_bitmap_nested); -out5: - free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic); -out4: - free_page((unsigned long)vmx_msr_bitmap_longmode); 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: @@ -6368,16 +6325,10 @@ out: static __exit void hardware_unsetup(void) { - free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic); - free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic); - 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); free_page((unsigned long)vmx_vmread_bitmap); - if (nested) - free_page((unsigned long)vmx_msr_bitmap_nested); free_kvm_area(); } @@ -8158,7 +8109,7 @@ 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) @@ -8738,6 +8689,7 @@ 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) @@ -8778,6 +8730,15 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) 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); @@ -9164,7 +9125,8 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, { int msr; struct page *page; - unsigned long *msr_bitmap; + unsigned long *msr_bitmap_l1; + unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap; if (!nested_cpu_has_virt_x2apic_mode(vmcs12)) return false; @@ -9174,58 +9136,32 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, WARN_ON(1); return false; } - msr_bitmap = (unsigned long *)kmap(page); + msr_bitmap_l1 = (unsigned long *)kmap(page); + + memset(msr_bitmap_l0, 0xff, PAGE_SIZE); if (nested_cpu_has_virt_x2apic_mode(vmcs12)) { if (nested_cpu_has_apic_reg_virt(vmcs12)) for (msr = 0x800; msr <= 0x8ff; msr++) nested_vmx_disable_intercept_for_msr( - msr_bitmap, - vmx_msr_bitmap_nested, + msr_bitmap_l1, msr_bitmap_l0, msr, MSR_TYPE_R); /* TPR is allowed */ - nested_vmx_disable_intercept_for_msr(msr_bitmap, - vmx_msr_bitmap_nested, + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, APIC_BASE_MSR + (APIC_TASKPRI >> 4), MSR_TYPE_R | MSR_TYPE_W); if (nested_cpu_has_vid(vmcs12)) { /* EOI and self-IPI are allowed */ nested_vmx_disable_intercept_for_msr( - msr_bitmap, - vmx_msr_bitmap_nested, + msr_bitmap_l1, msr_bitmap_l0, APIC_BASE_MSR + (APIC_EOI >> 4), MSR_TYPE_W); nested_vmx_disable_intercept_for_msr( - msr_bitmap, - vmx_msr_bitmap_nested, + msr_bitmap_l1, msr_bitmap_l0, APIC_BASE_MSR + (APIC_SELF_IPI >> 4), MSR_TYPE_W); } - } else { - /* - * Enable reading intercept of all the x2apic - * MSRs. We should not rely on vmcs12 to do any - * optimizations here, it may have been modified - * by L1. - */ - for (msr = 0x800; msr <= 0x8ff; msr++) - __vmx_enable_intercept_for_msr( - vmx_msr_bitmap_nested, - msr, - MSR_TYPE_R); - - __vmx_enable_intercept_for_msr( - vmx_msr_bitmap_nested, - APIC_BASE_MSR + (APIC_TASKPRI >> 4), - MSR_TYPE_W); - __vmx_enable_intercept_for_msr( - vmx_msr_bitmap_nested, - APIC_BASE_MSR + (APIC_EOI >> 4), - MSR_TYPE_W); - __vmx_enable_intercept_for_msr( - vmx_msr_bitmap_nested, - APIC_BASE_MSR + (APIC_SELF_IPI >> 4), - MSR_TYPE_W); } kunmap(page); nested_release_page_clean(page); @@ -9645,10 +9581,10 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) } if (cpu_has_vmx_msr_bitmap() && - exec_control & CPU_BASED_USE_MSR_BITMAPS) { - nested_vmx_merge_msr_bitmap(vcpu, vmcs12); - /* MSR_BITMAP will be set by following vmx_set_efer. */ - } else + exec_control & CPU_BASED_USE_MSR_BITMAPS && + nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) + ; /* MSR_BITMAP will be set by following vmx_set_efer. */ + else exec_control &= ~CPU_BASED_USE_MSR_BITMAPS; /* @@ -9700,6 +9636,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) else vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset); + 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 @@ -10400,7 +10339,7 @@ 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)) -- 1.8.3.1