diff options
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r-- | arch/x86/kvm/cpuid.c | 20 | ||||
-rw-r--r-- | arch/x86/kvm/cpuid.h | 8 | ||||
-rw-r--r-- | arch/x86/kvm/emulate.c | 87 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 121 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.h | 2 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.c | 162 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.h | 3 | ||||
-rw-r--r-- | arch/x86/kvm/mmutrace.h | 6 | ||||
-rw-r--r-- | arch/x86/kvm/paging_tmpl.h | 35 | ||||
-rw-r--r-- | arch/x86/kvm/pmu_intel.c | 2 | ||||
-rw-r--r-- | arch/x86/kvm/svm.c | 126 | ||||
-rw-r--r-- | arch/x86/kvm/vmx.c | 260 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 131 |
13 files changed, 575 insertions, 388 deletions
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index a181ae76c71c..59ca2eea522c 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -780,18 +780,20 @@ out: static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i) { struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i]; - int j, nent = vcpu->arch.cpuid_nent; + struct kvm_cpuid_entry2 *ej; + int j = i; + int nent = vcpu->arch.cpuid_nent; e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT; /* when no next entry is found, the current entry[i] is reselected */ - for (j = i + 1; ; j = (j + 1) % nent) { - struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j]; - if (ej->function == e->function) { - ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; - return j; - } - } - return 0; /* silence gcc, even though control never reaches here */ + do { + j = (j + 1) % nent; + ej = &vcpu->arch.cpuid_entries[j]; + } while (ej->function != e->function); + + ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; + + return j; } /* find an entry with matching function, matching index (if needed), and that diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index a6fd40aade7c..da6728383052 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -144,6 +144,14 @@ static inline bool guest_cpuid_has_rtm(struct kvm_vcpu *vcpu) return best && (best->ebx & bit(X86_FEATURE_RTM)); } +static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->ebx & bit(X86_FEATURE_MPX)); +} + static inline bool guest_cpuid_has_rdtscp(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index c25cfaf584e7..fb0055953fbc 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -900,7 +900,7 @@ static __always_inline int do_insn_fetch_bytes(struct x86_emulate_ctxt *ctxt, if (rc != X86EMUL_CONTINUE) \ goto done; \ ctxt->_eip += sizeof(_type); \ - _x = *(_type __aligned(1) *) ctxt->fetch.ptr; \ + memcpy(&_x, ctxt->fetch.ptr, sizeof(_type)); \ ctxt->fetch.ptr += sizeof(_type); \ _x; \ }) @@ -2742,6 +2742,7 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt) ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF); } + ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0; return X86EMUL_CONTINUE; } @@ -3941,6 +3942,25 @@ static int check_fxsr(struct x86_emulate_ctxt *ctxt) } /* + * Hardware doesn't save and restore XMM 0-7 without CR4.OSFXSR, but does save + * and restore MXCSR. + */ +static size_t __fxstate_size(int nregs) +{ + return offsetof(struct fxregs_state, xmm_space[0]) + nregs * 16; +} + +static inline size_t fxstate_size(struct x86_emulate_ctxt *ctxt) +{ + bool cr4_osfxsr; + if (ctxt->mode == X86EMUL_MODE_PROT64) + return __fxstate_size(16); + + cr4_osfxsr = ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR; + return __fxstate_size(cr4_osfxsr ? 8 : 0); +} + +/* * FXSAVE and FXRSTOR have 4 different formats depending on execution mode, * 1) 16 bit mode * 2) 32 bit mode @@ -3961,7 +3981,6 @@ static int check_fxsr(struct x86_emulate_ctxt *ctxt) static int em_fxsave(struct x86_emulate_ctxt *ctxt) { struct fxregs_state fx_state; - size_t size; int rc; rc = check_fxsr(ctxt); @@ -3977,68 +3996,42 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR) - size = offsetof(struct fxregs_state, xmm_space[8 * 16/4]); - else - size = offsetof(struct fxregs_state, xmm_space[0]); - - return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state, size); -} - -static int fxrstor_fixup(struct x86_emulate_ctxt *ctxt, - struct fxregs_state *new) -{ - int rc = X86EMUL_CONTINUE; - struct fxregs_state old; - - rc = asm_safe("fxsave %[fx]", , [fx] "+m"(old)); - if (rc != X86EMUL_CONTINUE) - return rc; - - /* - * 64 bit host will restore XMM 8-15, which is not correct on non-64 - * bit guests. Load the current values in order to preserve 64 bit - * XMMs after fxrstor. - */ -#ifdef CONFIG_X86_64 - /* XXX: accessing XMM 8-15 very awkwardly */ - memcpy(&new->xmm_space[8 * 16/4], &old.xmm_space[8 * 16/4], 8 * 16); -#endif - - /* - * Hardware doesn't save and restore XMM 0-7 without CR4.OSFXSR, but - * does save and restore MXCSR. - */ - if (!(ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR)) - memcpy(new->xmm_space, old.xmm_space, 8 * 16); - - return rc; + return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state, + fxstate_size(ctxt)); } static int em_fxrstor(struct x86_emulate_ctxt *ctxt) { struct fxregs_state fx_state; int rc; + size_t size; rc = check_fxsr(ctxt); if (rc != X86EMUL_CONTINUE) return rc; - rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, 512); - if (rc != X86EMUL_CONTINUE) - return rc; + ctxt->ops->get_fpu(ctxt); - if (fx_state.mxcsr >> 16) - return emulate_gp(ctxt, 0); + size = fxstate_size(ctxt); + if (size < __fxstate_size(16)) { + rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state)); + if (rc != X86EMUL_CONTINUE) + goto out; + } - ctxt->ops->get_fpu(ctxt); + rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, size); + if (rc != X86EMUL_CONTINUE) + goto out; - if (ctxt->mode < X86EMUL_MODE_PROT64) - rc = fxrstor_fixup(ctxt, &fx_state); + if (fx_state.mxcsr >> 16) { + rc = emulate_gp(ctxt, 0); + goto out; + } if (rc == X86EMUL_CONTINUE) rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state)); +out: ctxt->ops->put_fpu(ctxt); return rc; @@ -4173,7 +4166,7 @@ static int check_dr_write(struct x86_emulate_ctxt *ctxt) static int check_svme(struct x86_emulate_ctxt *ctxt) { - u64 efer; + u64 efer = 0; ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index c329d2894905..2819d4c123eb 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1495,31 +1495,65 @@ EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use); static void cancel_hv_timer(struct kvm_lapic *apic) { + WARN_ON(!apic->lapic_timer.hv_timer_in_use); + preempt_disable(); kvm_x86_ops->cancel_hv_timer(apic->vcpu); apic->lapic_timer.hv_timer_in_use = false; + preempt_enable(); } static bool start_hv_timer(struct kvm_lapic *apic) { - u64 tscdeadline = apic->lapic_timer.tscdeadline; + struct kvm_timer *ktimer = &apic->lapic_timer; + int r; - if ((atomic_read(&apic->lapic_timer.pending) && - !apic_lvtt_period(apic)) || - kvm_x86_ops->set_hv_timer(apic->vcpu, tscdeadline)) { - if (apic->lapic_timer.hv_timer_in_use) - cancel_hv_timer(apic); - } else { - apic->lapic_timer.hv_timer_in_use = true; - hrtimer_cancel(&apic->lapic_timer.timer); + if (!kvm_x86_ops->set_hv_timer) + return false; + + if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending)) + return false; - /* In case the sw timer triggered in the window */ - if (atomic_read(&apic->lapic_timer.pending) && - !apic_lvtt_period(apic)) - cancel_hv_timer(apic); + r = kvm_x86_ops->set_hv_timer(apic->vcpu, ktimer->tscdeadline); + if (r < 0) + return false; + + ktimer->hv_timer_in_use = true; + hrtimer_cancel(&ktimer->timer); + + /* + * Also recheck ktimer->pending, in case the sw timer triggered in + * the window. For periodic timer, leave the hv timer running for + * simplicity, and the deadline will be recomputed on the next vmexit. + */ + if (!apic_lvtt_period(apic) && (r || atomic_read(&ktimer->pending))) { + if (r) + apic_timer_expired(apic); + return false; } - trace_kvm_hv_timer_state(apic->vcpu->vcpu_id, - apic->lapic_timer.hv_timer_in_use); - return apic->lapic_timer.hv_timer_in_use; + + trace_kvm_hv_timer_state(apic->vcpu->vcpu_id, true); + return true; +} + +static void start_sw_timer(struct kvm_lapic *apic) +{ + struct kvm_timer *ktimer = &apic->lapic_timer; + if (apic->lapic_timer.hv_timer_in_use) + cancel_hv_timer(apic); + if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending)) + return; + + if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) + start_sw_period(apic); + else if (apic_lvtt_tscdeadline(apic)) + start_sw_tscdeadline(apic); + trace_kvm_hv_timer_state(apic->vcpu->vcpu_id, false); +} + +static void restart_apic_timer(struct kvm_lapic *apic) +{ + if (!start_hv_timer(apic)) + start_sw_timer(apic); } void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) @@ -1533,19 +1567,14 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) if (apic_lvtt_period(apic) && apic->lapic_timer.period) { advance_periodic_target_expiration(apic); - if (!start_hv_timer(apic)) - start_sw_period(apic); + restart_apic_timer(apic); } } EXPORT_SYMBOL_GPL(kvm_lapic_expired_hv_timer); void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu) { - struct kvm_lapic *apic = vcpu->arch.apic; - - WARN_ON(apic->lapic_timer.hv_timer_in_use); - - start_hv_timer(apic); + restart_apic_timer(vcpu->arch.apic); } EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_hv_timer); @@ -1554,33 +1583,28 @@ void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu) struct kvm_lapic *apic = vcpu->arch.apic; /* Possibly the TSC deadline timer is not enabled yet */ - if (!apic->lapic_timer.hv_timer_in_use) - return; - - cancel_hv_timer(apic); + if (apic->lapic_timer.hv_timer_in_use) + start_sw_timer(apic); +} +EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer); - if (atomic_read(&apic->lapic_timer.pending)) - return; +void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; - if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) - start_sw_period(apic); - else if (apic_lvtt_tscdeadline(apic)) - start_sw_tscdeadline(apic); + WARN_ON(!apic->lapic_timer.hv_timer_in_use); + restart_apic_timer(apic); } -EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer); static void start_apic_timer(struct kvm_lapic *apic) { atomic_set(&apic->lapic_timer.pending, 0); - if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) { - if (set_target_expiration(apic) && - !(kvm_x86_ops->set_hv_timer && start_hv_timer(apic))) - start_sw_period(apic); - } else if (apic_lvtt_tscdeadline(apic)) { - if (!(kvm_x86_ops->set_hv_timer && start_hv_timer(apic))) - start_sw_tscdeadline(apic); - } + if ((apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) + && !set_target_expiration(apic)) + return; + + restart_apic_timer(apic); } static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val) @@ -1811,16 +1835,6 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu) * LAPIC interface *---------------------------------------------------------------------- */ -u64 kvm_get_lapic_target_expiration_tsc(struct kvm_vcpu *vcpu) -{ - struct kvm_lapic *apic = vcpu->arch.apic; - - if (!lapic_in_kernel(vcpu)) - return 0; - - return apic->lapic_timer.tscdeadline; -} - u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; @@ -1934,7 +1948,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) for (i = 0; i < KVM_APIC_LVT_NUM; i++) kvm_lapic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED); apic_update_lvtt(apic); - if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED)) + if (kvm_vcpu_is_reset_bsp(vcpu) && + kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED)) kvm_lapic_set_reg(apic, APIC_LVT0, SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT)); apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0)); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index bcbe811f3b97..29caa2c3dff9 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -87,7 +87,6 @@ int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu); -u64 kvm_get_lapic_target_expiration_tsc(struct kvm_vcpu *vcpu); u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu); void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data); @@ -216,4 +215,5 @@ void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu); void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu); void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu); bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu); +void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu); #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 5d3376f67794..aafd399cf8c6 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -183,13 +183,13 @@ static u64 __read_mostly shadow_user_mask; static u64 __read_mostly shadow_accessed_mask; static u64 __read_mostly shadow_dirty_mask; static u64 __read_mostly shadow_mmio_mask; +static u64 __read_mostly shadow_mmio_value; static u64 __read_mostly shadow_present_mask; /* - * The mask/value to distinguish a PTE that has been marked not-present for - * access tracking purposes. - * The mask would be either 0 if access tracking is disabled, or - * SPTE_SPECIAL_MASK|VMX_EPT_RWX_MASK if access tracking is enabled. + * SPTEs used by MMUs without A/D bits are marked with shadow_acc_track_value. + * Non-present SPTEs with shadow_acc_track_value set are in place for access + * tracking. */ static u64 __read_mostly shadow_acc_track_mask; static const u64 shadow_acc_track_value = SPTE_SPECIAL_MASK; @@ -207,16 +207,40 @@ static const u64 shadow_acc_track_saved_bits_shift = PT64_SECOND_AVAIL_BITS_SHIF static void mmu_spte_set(u64 *sptep, u64 spte); static void mmu_free_roots(struct kvm_vcpu *vcpu); -void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask) +void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value) { + BUG_ON((mmio_mask & mmio_value) != mmio_value); + shadow_mmio_value = mmio_value | SPTE_SPECIAL_MASK; shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK; } EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask); +static inline bool sp_ad_disabled(struct kvm_mmu_page *sp) +{ + return sp->role.ad_disabled; +} + +static inline bool spte_ad_enabled(u64 spte) +{ + MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value); + return !(spte & shadow_acc_track_value); +} + +static inline u64 spte_shadow_accessed_mask(u64 spte) +{ + MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value); + return spte_ad_enabled(spte) ? shadow_accessed_mask : 0; +} + +static inline u64 spte_shadow_dirty_mask(u64 spte) +{ + MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value); + return spte_ad_enabled(spte) ? shadow_dirty_mask : 0; +} + static inline bool is_access_track_spte(u64 spte) { - /* Always false if shadow_acc_track_mask is zero. */ - return (spte & shadow_acc_track_mask) == shadow_acc_track_value; + return !spte_ad_enabled(spte) && (spte & shadow_acc_track_mask) == 0; } /* @@ -270,7 +294,7 @@ static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, u64 mask = generation_mmio_spte_mask(gen); access &= ACC_WRITE_MASK | ACC_USER_MASK; - mask |= shadow_mmio_mask | access | gfn << PAGE_SHIFT; + mask |= shadow_mmio_value | access | gfn << PAGE_SHIFT; trace_mark_mmio_spte(sptep, gfn, access, gen); mmu_spte_set(sptep, mask); @@ -278,7 +302,7 @@ static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, static bool is_mmio_spte(u64 spte) { - return (spte & shadow_mmio_mask) == shadow_mmio_mask; + return (spte & shadow_mmio_mask) == shadow_mmio_value; } static gfn_t get_mmio_spte_gfn(u64 spte) @@ -315,12 +339,20 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte) return likely(kvm_gen == spte_gen); } +/* + * Sets the shadow PTE masks used by the MMU. + * + * Assumptions: + * - Setting either @accessed_mask or @dirty_mask requires setting both + * - At least one of @accessed_mask or @acc_track_mask must be set + */ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask, u64 acc_track_mask) { - if (acc_track_mask != 0) - acc_track_mask |= SPTE_SPECIAL_MASK; + BUG_ON(!dirty_mask != !accessed_mask); + BUG_ON(!accessed_mask && !acc_track_mask); + BUG_ON(acc_track_mask & shadow_acc_track_value); shadow_user_mask = user_mask; shadow_accessed_mask = accessed_mask; @@ -329,7 +361,6 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, shadow_x_mask = x_mask; shadow_present_mask = p_mask; shadow_acc_track_mask = acc_track_mask; - WARN_ON(shadow_accessed_mask != 0 && shadow_acc_track_mask != 0); } EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); @@ -549,7 +580,7 @@ static bool spte_has_volatile_bits(u64 spte) is_access_track_spte(spte)) return true; - if (shadow_accessed_mask) { + if (spte_ad_enabled(spte)) { if ((spte & shadow_accessed_mask) == 0 || (is_writable_pte(spte) && (spte & shadow_dirty_mask) == 0)) return true; @@ -560,14 +591,17 @@ static bool spte_has_volatile_bits(u64 spte) static bool is_accessed_spte(u64 spte) { - return shadow_accessed_mask ? spte & shadow_accessed_mask - : !is_access_track_spte(spte); + u64 accessed_mask = spte_shadow_accessed_mask(spte); + + return accessed_mask ? spte & accessed_mask + : !is_access_track_spte(spte); } static bool is_dirty_spte(u64 spte) { - return shadow_dirty_mask ? spte & shadow_dirty_mask - : spte & PT_WRITABLE_MASK; + u64 dirty_mask = spte_shadow_dirty_mask(spte); + + return dirty_mask ? spte & dirty_mask : spte & PT_WRITABLE_MASK; } /* Rules for using mmu_spte_set: @@ -707,10 +741,10 @@ static u64 mmu_spte_get_lockless(u64 *sptep) static u64 mark_spte_for_access_track(u64 spte) { - if (shadow_accessed_mask != 0) + if (spte_ad_enabled(spte)) return spte & ~shadow_accessed_mask; - if (shadow_acc_track_mask == 0 || is_access_track_spte(spte)) + if (is_access_track_spte(spte)) return spte; /* @@ -729,7 +763,6 @@ static u64 mark_spte_for_access_track(u64 spte) spte |= (spte & shadow_acc_track_saved_bits_mask) << shadow_acc_track_saved_bits_shift; spte &= ~shadow_acc_track_mask; - spte |= shadow_acc_track_value; return spte; } @@ -741,6 +774,7 @@ static u64 restore_acc_track_spte(u64 spte) u64 saved_bits = (spte >> shadow_acc_track_saved_bits_shift) & shadow_acc_track_saved_bits_mask; + WARN_ON_ONCE(spte_ad_enabled(spte)); WARN_ON_ONCE(!is_access_track_spte(spte)); new_spte &= ~shadow_acc_track_mask; @@ -759,7 +793,7 @@ static bool mmu_spte_age(u64 *sptep) if (!is_accessed_spte(spte)) return false; - if (shadow_accessed_mask) { + if (spte_ad_enabled(spte)) { clear_bit((ffs(shadow_accessed_mask) - 1), (unsigned long *)sptep); } else { @@ -1390,6 +1424,22 @@ static bool spte_clear_dirty(u64 *sptep) return mmu_spte_update(sptep, spte); } +static bool wrprot_ad_disabled_spte(u64 *sptep) +{ + bool was_writable = test_and_clear_bit(PT_WRITABLE_SHIFT, + (unsigned long *)sptep); + if (was_writable) + kvm_set_pfn_dirty(spte_to_pfn(*sptep)); + + return was_writable; +} + +/* + * Gets the GFN ready for another round of dirty logging by clearing the + * - D bit on ad-enabled SPTEs, and + * - W bit on ad-disabled SPTEs. + * Returns true iff any D or W bits were cleared. + */ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) { u64 *sptep; @@ -1397,7 +1447,10 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) bool flush = false; for_each_rmap_spte(rmap_head, &iter, sptep) - flush |= spte_clear_dirty(sptep); + if (spte_ad_enabled(*sptep)) + flush |= spte_clear_dirty(sptep); + else + flush |= wrprot_ad_disabled_spte(sptep); return flush; } @@ -1420,7 +1473,8 @@ static bool __rmap_set_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) bool flush = false; for_each_rmap_spte(rmap_head, &iter, sptep) - flush |= spte_set_dirty(sptep); + if (spte_ad_enabled(*sptep)) + flush |= spte_set_dirty(sptep); return flush; } @@ -1452,7 +1506,8 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, } /** - * kvm_mmu_clear_dirty_pt_masked - clear MMU D-bit for PT level pages + * kvm_mmu_clear_dirty_pt_masked - clear MMU D-bit for PT level pages, or write + * protect the page if the D-bit isn't supported. * @kvm: kvm instance * @slot: slot to clear D-bit * @gfn_offset: start of the BITS_PER_LONG pages we care about @@ -1766,18 +1821,9 @@ static int kvm_test_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, u64 *sptep; struct rmap_iterator iter; - /* - * If there's no access bit in the secondary pte set by the hardware and - * fast access tracking is also not enabled, it's up to gup-fast/gup to - * set the access bit in the primary pte or in the page structure. - */ - if (!shadow_accessed_mask && !shadow_acc_track_mask) - goto out; - for_each_rmap_spte(rmap_head, &iter, sptep) if (is_accessed_spte(*sptep)) return 1; -out: return 0; } @@ -1798,18 +1844,6 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end) { - /* - * In case of absence of EPT Access and Dirty Bits supports, - * emulate the accessed bit for EPT, by checking if this page has - * an EPT mapping, and clearing it if it does. On the next access, - * a new EPT mapping will be established. - * This has some overhead, but not as much as the cost of swapping - * out actively used pages or breaking up actively used hugepages. - */ - if (!shadow_accessed_mask && !shadow_acc_track_mask) - return kvm_handle_hva_range(kvm, start, end, 0, - kvm_unmap_rmapp); - return kvm_handle_hva_range(kvm, start, end, 0, kvm_age_rmapp); } @@ -2398,7 +2432,12 @@ static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep, BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK); spte = __pa(sp->spt) | shadow_present_mask | PT_WRITABLE_MASK | - shadow_user_mask | shadow_x_mask | shadow_accessed_mask; + shadow_user_mask | shadow_x_mask; + + if (sp_ad_disabled(sp)) + spte |= shadow_acc_track_value; + else + spte |= shadow_accessed_mask; mmu_spte_set(sptep, spte); @@ -2666,10 +2705,15 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, { u64 spte = 0; int ret = 0; + struct kvm_mmu_page *sp; if (set_mmio_spte(vcpu, sptep, gfn, pfn, pte_access)) return 0; + sp = page_header(__pa(sptep)); + if (sp_ad_disabled(sp)) + spte |= shadow_acc_track_value; + /* * For the EPT case, shadow_present_mask is 0 if hardware * supports exec-only page table entries. In that case, @@ -2678,7 +2722,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, */ spte |= shadow_present_mask; if (!speculative) - spte |= shadow_accessed_mask; + spte |= spte_shadow_accessed_mask(spte); if (pte_access & ACC_EXEC_MASK) spte |= shadow_x_mask; @@ -2735,7 +2779,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (pte_access & ACC_WRITE_MASK) { kvm_vcpu_mark_page_dirty(vcpu, gfn); - spte |= shadow_dirty_mask; + spte |= spte_shadow_dirty_mask(spte); } if (speculative) @@ -2877,16 +2921,16 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) { struct kvm_mmu_page *sp; + sp = page_header(__pa(sptep)); + /* - * Since it's no accessed bit on EPT, it's no way to - * distinguish between actually accessed translations - * and prefetched, so disable pte prefetch if EPT is - * enabled. + * Without accessed bits, there's no way to distinguish between + * actually accessed translations and prefetched, so disable pte + * prefetch if accessed bits aren't available. */ - if (!shadow_accessed_mask) + if (sp_ad_disabled(sp)) return; - sp = page_header(__pa(sptep)); if (sp->role.level > PT_PAGE_TABLE_LEVEL) return; @@ -3698,12 +3742,15 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); } -static bool can_do_async_pf(struct kvm_vcpu *vcpu) +bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) { if (unlikely(!lapic_in_kernel(vcpu) || kvm_event_needs_reinjection(vcpu))) return false; + if (is_guest_mode(vcpu)) + return false; + return kvm_x86_ops->interrupt_allowed(vcpu); } @@ -3719,7 +3766,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, if (!async) return false; /* *pfn has correct page already */ - if (!prefault && can_do_async_pf(vcpu)) { + if (!prefault && kvm_can_do_async_pf(vcpu)) { trace_kvm_try_async_get_page(gva, gfn); if (kvm_find_async_pf_gfn(vcpu, gfn)) { trace_kvm_async_pf_doublefault(gva, gfn); @@ -4287,6 +4334,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->base_role.word = 0; context->base_role.smm = is_smm(vcpu); + context->base_role.ad_disabled = (shadow_accessed_mask == 0); context->page_fault = tdp_page_fault; context->sync_page = nonpaging_sync_page; context->invlpg = nonpaging_invlpg; @@ -4374,6 +4422,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, context->root_level = context->shadow_root_level; context->root_hpa = INVALID_PAGE; context->direct_map = false; + context->base_role.ad_disabled = !accessed_dirty; update_permission_bitmask(vcpu, context, true); update_pkru_bitmask(vcpu, context, true); @@ -4633,6 +4682,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, mask.smep_andnot_wp = 1; mask.smap_andnot_wp = 1; mask.smm = 1; + mask.ad_disabled = 1; /* * If we don't have indirect shadow pages, it means no page is diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 27975807cc64..a276834950c1 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -51,7 +51,7 @@ static inline u64 rsvd_bits(int s, int e) return ((1ULL << (e - s + 1)) - 1) << s; } -void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask); +void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value); void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context); @@ -76,6 +76,7 @@ int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct); void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, bool accessed_dirty); +bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm) { diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index 5a24b846a1cb..8b97a6cba8d1 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -30,8 +30,9 @@ \ role.word = __entry->role; \ \ - trace_seq_printf(p, "sp gen %lx gfn %llx %u%s q%u%s %s%s" \ - " %snxe root %u %s%c", __entry->mmu_valid_gen, \ + trace_seq_printf(p, "sp gen %lx gfn %llx l%u%s q%u%s %s%s" \ + " %snxe %sad root %u %s%c", \ + __entry->mmu_valid_gen, \ __entry->gfn, role.level, \ role.cr4_pae ? " pae" : "", \ role.quadrant, \ @@ -39,6 +40,7 @@ access_str[role.access], \ role.invalid ? " invalid" : "", \ role.nxe ? "" : "!", \ + role.ad_disabled ? "!" : "", \ __entry->root_count, \ __entry->unsync ? "unsync" : "sync", 0); \ saved_ptr; \ diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 56241746abbd..b0454c7e4cff 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -283,11 +283,13 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, pt_element_t pte; pt_element_t __user *uninitialized_var(ptep_user); gfn_t table_gfn; - unsigned index, pt_access, pte_access, accessed_dirty, pte_pkey; + u64 pt_access, pte_access; + unsigned index, accessed_dirty, pte_pkey; unsigned nested_access; gpa_t pte_gpa; bool have_ad; int offset; + u64 walk_nx_mask = 0; const int write_fault = access & PFERR_WRITE_MASK; const int user_fault = access & PFERR_USER_MASK; const int fetch_fault = access & PFERR_FETCH_MASK; @@ -302,6 +304,7 @@ retry_walk: have_ad = PT_HAVE_ACCESSED_DIRTY(mmu); #if PTTYPE == 64 + walk_nx_mask = 1ULL << PT64_NX_SHIFT; if (walker->level == PT32E_ROOT_LEVEL) { pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3); trace_kvm_mmu_paging_element(pte, walker->level); @@ -313,8 +316,6 @@ retry_walk: walker->max_level = walker->level; ASSERT(!(is_long_mode(vcpu) && !is_pae(vcpu))); - accessed_dirty = have_ad ? PT_GUEST_ACCESSED_MASK : 0; - /* * FIXME: on Intel processors, loads of the PDPTE registers for PAE paging * by the MOV to CR instruction are treated as reads and do not cause the @@ -322,14 +323,14 @@ retry_walk: */ nested_access = (have_ad ? PFERR_WRITE_MASK : 0) | PFERR_USER_MASK; - pt_access = pte_access = ACC_ALL; + pte_access = ~0; ++walker->level; do { gfn_t real_gfn; unsigned long host_addr; - pt_access &= pte_access; + pt_access = pte_access; --walker->level; index = PT_INDEX(addr, walker->level); @@ -371,6 +372,12 @@ retry_walk: trace_kvm_mmu_paging_element(pte, walker->level); + /* + * Inverting the NX it lets us AND it like other + * permission bits. + */ + pte_access = pt_access & (pte ^ walk_nx_mask); + if (unlikely(!FNAME(is_present_gpte)(pte))) goto error; @@ -379,14 +386,16 @@ retry_walk: goto error; } - accessed_dirty &= pte; - pte_access = pt_access & FNAME(gpte_access)(vcpu, pte); - walker->ptes[walker->level - 1] = pte; } while (!is_last_gpte(mmu, walker->level, pte)); pte_pkey = FNAME(gpte_pkeys)(vcpu, pte); - errcode = permission_fault(vcpu, mmu, pte_access, pte_pkey, access); + accessed_dirty = have_ad ? pte_access & PT_GUEST_ACCESSED_MASK : 0; + + /* Convert to ACC_*_MASK flags for struct guest_walker. */ + walker->pt_access = FNAME(gpte_access)(vcpu, pt_access ^ walk_nx_mask); + walker->pte_access = FNAME(gpte_access)(vcpu, pte_access ^ walk_nx_mask); + errcode = permission_fault(vcpu, mmu, walker->pte_access, pte_pkey, access); if (unlikely(errcode)) goto error; @@ -403,7 +412,7 @@ retry_walk: walker->gfn = real_gpa >> PAGE_SHIFT; if (!write_fault) - FNAME(protect_clean_gpte)(mmu, &pte_access, pte); + FNAME(protect_clean_gpte)(mmu, &walker->pte_access, pte); else /* * On a write fault, fold the dirty bit into accessed_dirty. @@ -421,10 +430,8 @@ retry_walk: goto retry_walk; } - walker->pt_access = pt_access; - walker->pte_access = pte_access; pgprintk("%s: pte %llx pte_access %x pt_access %x\n", - __func__, (u64)pte, pte_access, pt_access); + __func__, (u64)pte, walker->pte_access, walker->pt_access); return 1; error: @@ -452,7 +459,7 @@ error: */ if (!(errcode & PFERR_RSVD_MASK)) { vcpu->arch.exit_qualification &= 0x187; - vcpu->arch.exit_qualification |= ((pt_access & pte) & 0x7) << 3; + vcpu->arch.exit_qualification |= (pte_access & 0x7) << 3; } #endif walker->fault.address = addr; diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/pmu_intel.c index 9d4a8504a95a..5ab4a364348e 100644 --- a/arch/x86/kvm/pmu_intel.c +++ b/arch/x86/kvm/pmu_intel.c @@ -294,7 +294,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) ((u64)1 << edx.split.bit_width_fixed) - 1; } - pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) | + pmu->global_ctrl = ((1ull << pmu->nr_arch_gp_counters) - 1) | (((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED); pmu->global_ctrl_mask = ~pmu->global_ctrl; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index c27ac6923a18..905ea6052517 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -36,6 +36,7 @@ #include <linux/slab.h> #include <linux/amd-iommu.h> #include <linux/hashtable.h> +#include <linux/frame.h> #include <asm/apic.h> #include <asm/perf_event.h> @@ -189,6 +190,7 @@ struct vcpu_svm { struct nested_state nested; bool nmi_singlestep; + u64 nmi_singlestep_guest_rflags; unsigned int3_injected; unsigned long int3_rip; @@ -963,6 +965,18 @@ static void svm_disable_lbrv(struct vcpu_svm *svm) set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0); } +static void disable_nmi_singlestep(struct vcpu_svm *svm) +{ + svm->nmi_singlestep = false; + if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) { + /* Clear our flags if they were not set by the guest */ + if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF)) + svm->vmcb->save.rflags &= ~X86_EFLAGS_TF; + if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_RF)) + svm->vmcb->save.rflags &= ~X86_EFLAGS_RF; + } +} + /* Note: * This hash table is used to map VM_ID to a struct kvm_arch, * when handling AMD IOMMU GALOG notification to schedule in @@ -1272,7 +1286,8 @@ static void init_vmcb(struct vcpu_svm *svm) } -static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, int index) +static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, + unsigned int index) { u64 *avic_physical_id_table; struct kvm_arch *vm_data = &vcpu->kvm->arch; @@ -1711,11 +1726,24 @@ static void svm_vcpu_unblocking(struct kvm_vcpu *vcpu) static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) { - return to_svm(vcpu)->vmcb->save.rflags; + struct vcpu_svm *svm = to_svm(vcpu); + unsigned long rflags = svm->vmcb->save.rflags; + + if (svm->nmi_singlestep) { + /* Hide our flags if they were not set by the guest */ + if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF)) + rflags &= ~X86_EFLAGS_TF; + if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_RF)) + rflags &= ~X86_EFLAGS_RF; + } + return rflags; } static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { + if (to_svm(vcpu)->nmi_singlestep) + rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); + /* * Any change of EFLAGS.VM is accompanied by a reload of SS * (caused by either a task switch or an inter-privilege IRET), @@ -1806,7 +1834,7 @@ static void svm_get_segment(struct kvm_vcpu *vcpu, * AMD's VMCB does not have an explicit unusable field, so emulate it * for cross vendor migration purposes by "not present" */ - var->unusable = !var->present || (var->type == 0); + var->unusable = !var->present; switch (seg) { case VCPU_SREG_TR: @@ -1839,6 +1867,7 @@ static void svm_get_segment(struct kvm_vcpu *vcpu, */ if (var->unusable) var->db = 0; + /* This is symmetric with svm_set_segment() */ var->dpl = to_svm(vcpu)->vmcb->save.cpl; break; } @@ -1979,18 +2008,14 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, s->base = var->base; s->limit = var->limit; s->selector = var->selector; - if (var->unusable) - s->attrib = 0; - else { - s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK); - s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT; - s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT; - s->attrib |= (var->present & 1) << SVM_SELECTOR_P_SHIFT; - s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT; - s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT; - s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT; - s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT; - } + s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK); + s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT; + s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT; + s->attrib |= ((var->present & 1) && !var->unusable) << SVM_SELECTOR_P_SHIFT; + s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT; + s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT; + s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT; + s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT; /* * This is always accurate, except if SYSRET returned to a segment @@ -1999,7 +2024,8 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, * would entail passing the CPL to userspace and back. */ if (seg == VCPU_SREG_SS) - svm->vmcb->save.cpl = (s->attrib >> SVM_SELECTOR_DPL_SHIFT) & 3; + /* This is symmetric with svm_get_segment() */ + svm->vmcb->save.cpl = (var->dpl & 3); mark_dirty(svm->vmcb, VMCB_SEG); } @@ -2112,10 +2138,7 @@ static int db_interception(struct vcpu_svm *svm) } if (svm->nmi_singlestep) { - svm->nmi_singlestep = false; - if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) - svm->vmcb->save.rflags &= - ~(X86_EFLAGS_TF | X86_EFLAGS_RF); + disable_nmi_singlestep(svm); } if (svm->vcpu.guest_debug & @@ -2370,8 +2393,8 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu) static int nested_svm_check_permissions(struct vcpu_svm *svm) { - if (!(svm->vcpu.arch.efer & EFER_SVME) - || !is_paging(&svm->vcpu)) { + if (!(svm->vcpu.arch.efer & EFER_SVME) || + !is_paging(&svm->vcpu)) { kvm_queue_exception(&svm->vcpu, UD_VECTOR); return 1; } @@ -2381,7 +2404,7 @@ static int nested_svm_check_permissions(struct vcpu_svm *svm) return 1; } - return 0; + return 0; } static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, @@ -2534,6 +2557,31 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; } +/* DB exceptions for our internal use must not cause vmexit */ +static int nested_svm_intercept_db(struct vcpu_svm *svm) +{ + unsigned long dr6; + + /* if we're not singlestepping, it's not ours */ + if (!svm->nmi_singlestep) + return NESTED_EXIT_DONE; + + /* if it's not a singlestep exception, it's not ours */ + if (kvm_get_dr(&svm->vcpu, 6, &dr6)) + return NESTED_EXIT_DONE; + if (!(dr6 & DR6_BS)) + return NESTED_EXIT_DONE; + + /* if the guest is singlestepping, it should get the vmexit */ + if (svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF) { + disable_nmi_singlestep(svm); + return NESTED_EXIT_DONE; + } + + /* it's ours, the nested hypervisor must not see this one */ + return NESTED_EXIT_HOST; +} + static int nested_svm_exit_special(struct vcpu_svm *svm) { u32 exit_code = svm->vmcb->control.exit_code; @@ -2589,8 +2637,12 @@ static int nested_svm_intercept(struct vcpu_svm *svm) } case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: { u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE); - if (svm->nested.intercept_exceptions & excp_bits) - vmexit = NESTED_EXIT_DONE; + if (svm->nested.intercept_exceptions & excp_bits) { + if (exit_code == SVM_EXIT_EXCP_BASE + DB_VECTOR) + vmexit = nested_svm_intercept_db(svm); + else + vmexit = NESTED_EXIT_DONE; + } /* async page fault always cause vmexit */ else if ((exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) && svm->apf_reason != 0) @@ -4627,10 +4679,17 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) == HF_NMI_MASK) return; /* IRET will cause a vm exit */ + if ((svm->vcpu.arch.hflags & HF_GIF_MASK) == 0) + return; /* STGI will cause a vm exit */ + + if (svm->nested.exit_required) + return; /* we're not going to run the guest yet */ + /* * Something prevents NMI from been injected. Single step over possible * problem (IRET or exception injection or interrupt shadow) */ + svm->nmi_singlestep_guest_rflags = svm_get_rflags(vcpu); svm->nmi_singlestep = true; svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); } @@ -4771,6 +4830,22 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(svm->nested.exit_required)) return; + /* + * Disable singlestep if we're injecting an interrupt/exception. + * We don't want our modified rflags to be pushed on the stack where + * we might not be able to easily reset them if we disabled NMI + * singlestep later. + */ + if (svm->nmi_singlestep && svm->vmcb->control.event_inj) { + /* + * Event injection happens before external interrupts cause a + * vmexit and interrupts are disabled here, so smp_send_reschedule + * is enough to force an immediate vmexit. + */ + disable_nmi_singlestep(svm); + smp_send_reschedule(vcpu->cpu); + } + pre_svm_run(svm); sync_lapic_to_cr8(vcpu); @@ -4907,6 +4982,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) mark_all_clean(svm->vmcb); } +STACK_FRAME_NON_STANDARD(svm_vcpu_run); static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root) { diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index c6f4ad44aa95..f76efad248ab 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/frame.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/mmu_context.h> #include "trace.h" #include "pmu.h" @@ -596,6 +598,7 @@ struct vcpu_vmx { int gs_ldt_reload_needed; int fs_reload_needed; u64 msr_host_bndcfgs; + unsigned long vmcs_host_cr3; /* May not match real cr3 */ unsigned long vmcs_host_cr4; /* May not match real cr4 */ } host_state; struct { @@ -910,8 +913,9 @@ static void nested_release_page_clean(struct page *page) kvm_release_page_clean(page); } +static bool nested_ept_ad_enabled(struct kvm_vcpu *vcpu); static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu); -static u64 construct_eptp(unsigned long root_hpa); +static u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa); static bool vmx_xsaves_supported(void); static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); static void vmx_set_segment(struct kvm_vcpu *vcpu, @@ -2425,7 +2429,7 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr) if (!(vmcs12->exception_bitmap & (1u << nr))) return 0; - nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason, + nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, vmcs_read32(VM_EXIT_INTR_INFO), vmcs_readl(EXIT_QUALIFICATION)); return 1; @@ -2769,7 +2773,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) if (enable_ept_ad_bits) { vmx->nested.nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_PML; - vmx->nested.nested_vmx_ept_caps |= VMX_EPT_AD_BIT; + vmx->nested.nested_vmx_ept_caps |= VMX_EPT_AD_BIT; } } else vmx->nested.nested_vmx_ept_caps = 0; @@ -3195,7 +3199,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP); break; case MSR_IA32_BNDCFGS: - if (!kvm_mpx_supported()) + if (!kvm_mpx_supported() || + (!msr_info->host_initiated && !guest_cpuid_has_mpx(vcpu))) return 1; msr_info->data = vmcs_read64(GUEST_BNDCFGS); break; @@ -3277,7 +3282,11 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmcs_writel(GUEST_SYSENTER_ESP, data); break; case MSR_IA32_BNDCFGS: - if (!kvm_mpx_supported()) + if (!kvm_mpx_supported() || + (!msr_info->host_initiated && !guest_cpuid_has_mpx(vcpu))) + return 1; + if (is_noncanonical_address(data & PAGE_MASK) || + (data & MSR_IA32_BNDCFGS_RSVD)) return 1; vmcs_write64(GUEST_BNDCFGS, data); break; @@ -4010,7 +4019,7 @@ static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid) if (enable_ept) { if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) return; - ept_sync_context(construct_eptp(vcpu->arch.mmu.root_hpa)); + ept_sync_context(construct_eptp(vcpu, vcpu->arch.mmu.root_hpa)); } else { vpid_sync_context(vpid); } @@ -4185,14 +4194,15 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) vmx->emulation_required = emulation_required(vcpu); } -static u64 construct_eptp(unsigned long root_hpa) +static u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa) { u64 eptp; /* TODO write the value reading from MSR */ eptp = VMX_EPT_DEFAULT_MT | VMX_EPT_DEFAULT_GAW << VMX_EPT_GAW_EPTP_SHIFT; - if (enable_ept_ad_bits) + if (enable_ept_ad_bits && + (!is_guest_mode(vcpu) || nested_ept_ad_enabled(vcpu))) eptp |= VMX_EPT_AD_ENABLE_BIT; eptp |= (root_hpa & PAGE_MASK); @@ -4206,7 +4216,7 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) guest_cr3 = cr3; if (enable_ept) { - eptp = construct_eptp(cr3); + eptp = construct_eptp(vcpu, cr3); vmcs_write64(EPT_POINTER, eptp); if (is_paging(vcpu) || is_guest_mode(vcpu)) guest_cr3 = kvm_read_cr3(vcpu); @@ -5012,12 +5022,19 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx) u32 low32, high32; unsigned long tmpl; struct desc_ptr dt; - unsigned long cr0, cr4; + unsigned long cr0, cr3, cr4; cr0 = read_cr0(); WARN_ON(cr0 & X86_CR0_TS); vmcs_writel(HOST_CR0, cr0); /* 22.2.3 */ - vmcs_writel(HOST_CR3, read_cr3()); /* 22.2.3 FIXME: shadow tables */ + + /* + * Save the most likely value for this task's CR3 in the VMCS. + * We can't use __get_current_cr3_fast() because we're not atomic. + */ + cr3 = __read_cr3(); + vmcs_writel(HOST_CR3, cr3); /* 22.2.3 FIXME: shadow tables */ + vmx->host_state.vmcs_host_cr3 = cr3; /* Save the most likely value for this task's CR4 in the VMCS. */ cr4 = cr4_read_shadow(); @@ -5160,7 +5177,8 @@ static void ept_set_mmio_spte_mask(void) * EPT Misconfigurations can be generated if the value of bits 2:0 * of an EPT paging-structure entry is 110b (write/execute). */ - kvm_mmu_set_mmio_spte_mask(VMX_EPT_MISCONFIG_WX_VALUE); + kvm_mmu_set_mmio_spte_mask(VMX_EPT_RWX_MASK, + VMX_EPT_MISCONFIG_WX_VALUE); } #define VMX_XSS_EXIT_BITMAP 0 @@ -6210,17 +6228,6 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - if (is_guest_mode(vcpu) - && !(exit_qualification & EPT_VIOLATION_GVA_TRANSLATED)) { - /* - * Fix up exit_qualification according to whether guest - * page table accesses are reads or writes. - */ - u64 eptp = nested_ept_get_cr3(vcpu); - if (!(eptp & VMX_EPT_AD_ENABLE_BIT)) - exit_qualification &= ~EPT_VIOLATION_ACC_WRITE; - } - /* * EPT violation happened while executing iret from NMI, * "blocked by NMI" bit has to be set before next VM entry. @@ -6443,7 +6450,7 @@ void vmx_enable_tdp(void) enable_ept_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull, 0ull, VMX_EPT_EXECUTABLE_MASK, cpu_has_vmx_ept_execute_only() ? 0ull : VMX_EPT_READABLE_MASK, - enable_ept_ad_bits ? 0ull : VMX_EPT_RWX_MASK); + VMX_EPT_RWX_MASK); ept_set_mmio_spte_mask(); kvm_enable_tdp(); @@ -6504,7 +6511,7 @@ static __init int hardware_setup(void) enable_ept_ad_bits = 0; } - if (!cpu_has_vmx_ept_ad_bits()) + if (!cpu_has_vmx_ept_ad_bits() || !enable_ept) enable_ept_ad_bits = 0; if (!cpu_has_vmx_unrestricted_guest()) @@ -6547,7 +6554,6 @@ static __init int hardware_setup(void) 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); - vmx_disable_intercept_for_msr(MSR_IA32_BNDCFGS, true); memcpy(vmx_msr_bitmap_legacy_x2apic_apicv, vmx_msr_bitmap_legacy, PAGE_SIZE); @@ -6914,97 +6920,21 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, return 0; } -/* - * This function performs the various checks including - * - if it's 4KB aligned - * - No bits beyond the physical address width are set - * - Returns 0 on success or else 1 - * (Intel SDM Section 30.3) - */ -static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, - gpa_t *vmpointer) +static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer) { gva_t gva; - gpa_t vmptr; struct x86_exception e; - struct page *page; - struct vcpu_vmx *vmx = to_vmx(vcpu); - int maxphyaddr = cpuid_maxphyaddr(vcpu); if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva)) return 1; - if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr, - sizeof(vmptr), &e)) { + if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, vmpointer, + sizeof(*vmpointer), &e)) { kvm_inject_page_fault(vcpu, &e); return 1; } - switch (exit_reason) { - case EXIT_REASON_VMON: - /* - * SDM 3: 24.11.5 - * The first 4 bytes of VMXON region contain the supported - * VMCS revision identifier - * - * Note - IA32_VMX_BASIC[48] will never be 1 - * for the nested case; - * which replaces physical address width with 32 - * - */ - if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) { - nested_vmx_failInvalid(vcpu); - return kvm_skip_emulated_instruction(vcpu); - } - - page = nested_get_page(vcpu, vmptr); - if (page == NULL) { - nested_vmx_failInvalid(vcpu); - return kvm_skip_emulated_instruction(vcpu); - } - if (*(u32 *)kmap(page) != VMCS12_REVISION) { - kunmap(page); - nested_release_page_clean(page); - nested_vmx_failInvalid(vcpu); - return kvm_skip_emulated_instruction(vcpu); - } - kunmap(page); - nested_release_page_clean(page); - vmx->nested.vmxon_ptr = vmptr; - break; - case EXIT_REASON_VMCLEAR: - if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) { - nested_vmx_failValid(vcpu, - VMXERR_VMCLEAR_INVALID_ADDRESS); - return kvm_skip_emulated_instruction(vcpu); - } - - if (vmptr == vmx->nested.vmxon_ptr) { - nested_vmx_failValid(vcpu, - VMXERR_VMCLEAR_VMXON_POINTER); - return kvm_skip_emulated_instruction(vcpu); - } - break; - case EXIT_REASON_VMPTRLD: - if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) { - nested_vmx_failValid(vcpu, - VMXERR_VMPTRLD_INVALID_ADDRESS); - return kvm_skip_emulated_instruction(vcpu); - } - - if (vmptr == vmx->nested.vmxon_ptr) { - nested_vmx_failValid(vcpu, - VMXERR_VMPTRLD_VMXON_POINTER); - return kvm_skip_emulated_instruction(vcpu); - } - break; - default: - return 1; /* shouldn't happen */ - } - - if (vmpointer) - *vmpointer = vmptr; return 0; } @@ -7066,6 +6996,8 @@ out_msr_bitmap: static int handle_vmon(struct kvm_vcpu *vcpu) { int ret; + gpa_t vmptr; + struct page *page; struct vcpu_vmx *vmx = to_vmx(vcpu); const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; @@ -7095,9 +7027,37 @@ static int handle_vmon(struct kvm_vcpu *vcpu) return 1; } - if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMON, NULL)) + if (nested_vmx_get_vmptr(vcpu, &vmptr)) return 1; - + + /* + * SDM 3: 24.11.5 + * The first 4 bytes of VMXON region contain the supported + * VMCS revision identifier + * + * Note - IA32_VMX_BASIC[48] will never be 1 for the nested case; + * which replaces physical address width with 32 + */ + if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) { + nested_vmx_failInvalid(vcpu); + return kvm_skip_emulated_instruction(vcpu); + } + + page = nested_get_page(vcpu, vmptr); + if (page == NULL) { + nested_vmx_failInvalid(vcpu); + return kvm_skip_emulated_instruction(vcpu); + } + if (*(u32 *)kmap(page) != VMCS12_REVISION) { + kunmap(page); + nested_release_page_clean(page); + nested_vmx_failInvalid(vcpu); + return kvm_skip_emulated_instruction(vcpu); + } + kunmap(page); + nested_release_page_clean(page); + + vmx->nested.vmxon_ptr = vmptr; ret = enter_vmx_operation(vcpu); if (ret) return ret; @@ -7213,9 +7173,19 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) if (!nested_vmx_check_permission(vcpu)) return 1; - if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMCLEAR, &vmptr)) + if (nested_vmx_get_vmptr(vcpu, &vmptr)) return 1; + if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) { + nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS); + return kvm_skip_emulated_instruction(vcpu); + } + + if (vmptr == vmx->nested.vmxon_ptr) { + nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_VMXON_POINTER); + return kvm_skip_emulated_instruction(vcpu); + } + if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vmx); @@ -7545,9 +7515,19 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) if (!nested_vmx_check_permission(vcpu)) return 1; - if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMPTRLD, &vmptr)) + if (nested_vmx_get_vmptr(vcpu, &vmptr)) return 1; + if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) { + nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS); + return kvm_skip_emulated_instruction(vcpu); + } + + if (vmptr == vmx->nested.vmxon_ptr) { + nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_VMXON_POINTER); + return kvm_skip_emulated_instruction(vcpu); + } + if (vmx->nested.current_vmptr != vmptr) { struct vmcs12 *new_vmcs12; struct page *page; @@ -7677,7 +7657,10 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) unsigned long type, types; gva_t gva; struct x86_exception e; - int vpid; + struct { + u64 vpid; + u64 gla; + } operand; if (!(vmx->nested.nested_vmx_secondary_ctls_high & SECONDARY_EXEC_ENABLE_VPID) || @@ -7707,17 +7690,28 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), vmx_instruction_info, false, &gva)) return 1; - if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vpid, - sizeof(u32), &e)) { + if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand, + sizeof(operand), &e)) { kvm_inject_page_fault(vcpu, &e); return 1; } + if (operand.vpid >> 16) { + nested_vmx_failValid(vcpu, + VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + return kvm_skip_emulated_instruction(vcpu); + } switch (type) { case VMX_VPID_EXTENT_INDIVIDUAL_ADDR: + if (is_noncanonical_address(operand.gla)) { + nested_vmx_failValid(vcpu, + VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + return kvm_skip_emulated_instruction(vcpu); + } + /* fall through */ case VMX_VPID_EXTENT_SINGLE_CONTEXT: case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL: - if (!vpid) { + if (!operand.vpid) { nested_vmx_failValid(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); return kvm_skip_emulated_instruction(vcpu); @@ -7913,11 +7907,13 @@ 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_readl(vcpu, reg); + int reg; + unsigned long val; switch ((exit_qualification >> 4) & 3) { case 0: /* mov to cr */ + reg = (exit_qualification >> 8) & 15; + val = kvm_register_readl(vcpu, reg); switch (cr) { case 0: if (vmcs12->cr0_guest_host_mask & @@ -7972,6 +7968,7 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, * lmsw can change bits 1..3 of cr0, and only set bit 0 of * cr0. Other attempted changes are ignored, with no exit. */ + val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f; if (vmcs12->cr0_guest_host_mask & 0xe & (val ^ vmcs12->cr0_read_shadow)) return true; @@ -8675,6 +8672,7 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) ); } } +STACK_FRAME_NON_STANDARD(vmx_handle_external_intr); static bool vmx_has_high_real_mode_segbase(void) { @@ -8843,7 +8841,7 @@ static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu) static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long debugctlmsr, cr4; + unsigned long debugctlmsr, cr3, cr4; /* Don't enter VMX if guest state is invalid, let the exit handler start emulation until we arrive back to a valid state */ @@ -8865,6 +8863,12 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty)) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); + cr3 = __get_current_cr3_fast(); + if (unlikely(cr3 != vmx->host_state.vmcs_host_cr3)) { + vmcs_writel(HOST_CR3, cr3); + vmx->host_state.vmcs_host_cr3 = cr3; + } + cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) { vmcs_writel(HOST_CR4, cr4); @@ -9051,6 +9055,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_recover_nmi_blocking(vmx); vmx_complete_interrupts(vmx); } +STACK_FRAME_NON_STANDARD(vmx_vcpu_run); static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) { @@ -9399,6 +9404,11 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, vmcs12->guest_physical_address = fault->address; } +static bool nested_ept_ad_enabled(struct kvm_vcpu *vcpu) +{ + return nested_ept_get_cr3(vcpu) & VMX_EPT_AD_ENABLE_BIT; +} + /* Callbacks for nested_ept_init_mmu_context: */ static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu) @@ -9409,18 +9419,18 @@ static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu) static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu) { - u64 eptp; + bool wants_ad; WARN_ON(mmu_is_nested(vcpu)); - eptp = nested_ept_get_cr3(vcpu); - if ((eptp & VMX_EPT_AD_ENABLE_BIT) && !enable_ept_ad_bits) + wants_ad = nested_ept_ad_enabled(vcpu); + if (wants_ad && !enable_ept_ad_bits) return 1; kvm_mmu_unload(vcpu); kvm_init_shadow_ept_mmu(vcpu, to_vmx(vcpu)->nested.nested_vmx_ept_caps & VMX_EPT_EXECUTE_ONLY_BIT, - eptp & VMX_EPT_AD_ENABLE_BIT); + wants_ad); vcpu->arch.mmu.set_cr3 = vmx_set_cr3; vcpu->arch.mmu.get_cr3 = nested_ept_get_cr3; vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault; @@ -10733,8 +10743,7 @@ static void sync_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_pdptr3 = vmcs_read64(GUEST_PDPTR3); } - if (nested_cpu_has_ept(vmcs12)) - vmcs12->guest_linear_address = vmcs_readl(GUEST_LINEAR_ADDRESS); + vmcs12->guest_linear_address = vmcs_readl(GUEST_LINEAR_ADDRESS); if (nested_cpu_has_vid(vmcs12)) vmcs12->guest_intr_status = vmcs_read16(GUEST_INTR_STATUS); @@ -10759,8 +10768,6 @@ static void sync_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP); if (kvm_mpx_supported()) vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); - if (nested_cpu_has_xsaves(vmcs12)) - vmcs12->xss_exit_bitmap = vmcs_read64(XSS_EXIT_BITMAP); } /* @@ -11157,7 +11164,8 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc) vmx->hv_deadline_tsc = tscl + delta_tsc; vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, PIN_BASED_VMX_PREEMPTION_TIMER); - return 0; + + return delta_tsc == 0; } static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu) @@ -11213,7 +11221,7 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu) if (!nested_cpu_has_pml(vmcs12)) return 0; - if (vmcs12->guest_pml_index > PML_ENTITY_NUM) { + if (vmcs12->guest_pml_index >= PML_ENTITY_NUM) { vmx->nested.pml_full = true; return 1; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 464da936c53d..6c7266f7766d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1763,6 +1763,7 @@ u64 get_kvmclock_ns(struct kvm *kvm) { struct kvm_arch *ka = &kvm->arch; struct pvclock_vcpu_time_info hv_clock; + u64 ret; spin_lock(&ka->pvclock_gtod_sync_lock); if (!ka->use_master_clock) { @@ -1774,10 +1775,17 @@ u64 get_kvmclock_ns(struct kvm *kvm) hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; spin_unlock(&ka->pvclock_gtod_sync_lock); + /* both __this_cpu_read() and rdtsc() should be on the same cpu */ + get_cpu(); + kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL, &hv_clock.tsc_shift, &hv_clock.tsc_to_system_mul); - return __pvclock_read_cycles(&hv_clock, rdtsc()); + ret = __pvclock_read_cycles(&hv_clock, rdtsc()); + + put_cpu(); + + return ret; } static void kvm_setup_pvclock_page(struct kvm_vcpu *v) @@ -2833,10 +2841,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_vcpu_write_tsc_offset(vcpu, offset); vcpu->arch.tsc_catchup = 1; } - if (kvm_lapic_hv_timer_in_use(vcpu) && - kvm_x86_ops->set_hv_timer(vcpu, - kvm_get_lapic_target_expiration_tsc(vcpu))) - kvm_lapic_switch_to_sw_timer(vcpu); + + if (kvm_lapic_hv_timer_in_use(vcpu)) + kvm_lapic_restart_hv_timer(vcpu); + /* * On a host with synchronized TSC, there is no need to update * kvmclock on vcpu->cpu migration @@ -3288,11 +3296,14 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, } } +#define XSAVE_MXCSR_OFFSET 24 + static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { u64 xstate_bv = *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)]; + u32 mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)]; if (boot_cpu_has(X86_FEATURE_XSAVE)) { /* @@ -3300,11 +3311,13 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, * CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility * with old userspace. */ - if (xstate_bv & ~kvm_supported_xcr0()) + if (xstate_bv & ~kvm_supported_xcr0() || + mxcsr & ~mxcsr_feature_mask) return -EINVAL; load_xsave(vcpu, (u8 *)guest_xsave->region); } else { - if (xstate_bv & ~XFEATURE_MASK_FPSSE) + if (xstate_bv & ~XFEATURE_MASK_FPSSE || + mxcsr & ~mxcsr_feature_mask) return -EINVAL; memcpy(&vcpu->arch.guest_fpu.state.fxsave, guest_xsave->region, sizeof(struct fxregs_state)); @@ -4818,16 +4831,20 @@ emul_write: static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) { - /* TODO: String I/O for in kernel device */ - int r; + int r = 0, i; - if (vcpu->arch.pio.in) - r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port, - vcpu->arch.pio.size, pd); - else - r = kvm_io_bus_write(vcpu, KVM_PIO_BUS, - vcpu->arch.pio.port, vcpu->arch.pio.size, - pd); + for (i = 0; i < vcpu->arch.pio.count; i++) { + if (vcpu->arch.pio.in) + r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port, + vcpu->arch.pio.size, pd); + else + r = kvm_io_bus_write(vcpu, KVM_PIO_BUS, + vcpu->arch.pio.port, vcpu->arch.pio.size, + pd); + if (r) + break; + pd += vcpu->arch.pio.size; + } return r; } @@ -4865,6 +4882,8 @@ static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, if (vcpu->arch.pio.count) goto data_avail; + memset(vcpu->arch.pio_data, 0, size * count); + ret = emulator_pio_in_out(vcpu, size, port, val, count, true); if (ret) { data_avail: @@ -5048,6 +5067,8 @@ static bool emulator_get_segment(struct x86_emulate_ctxt *ctxt, u16 *selector, if (var.unusable) { memset(desc, 0, sizeof(*desc)); + if (base3) + *base3 = 0; return false; } @@ -5292,6 +5313,8 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); ctxt->eflags = kvm_get_rflags(vcpu); + ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0; + ctxt->eip = kvm_rip_read(vcpu); ctxt->mode = (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL : (ctxt->eflags & X86_EFLAGS_VM) ? X86EMUL_MODE_VM86 : @@ -5507,36 +5530,25 @@ static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7, return dr6; } -static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, unsigned long rflags, int *r) +static void kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu, int *r) { struct kvm_run *kvm_run = vcpu->run; - /* - * rflags is the old, "raw" value of the flags. The new value has - * not been saved yet. - * - * This is correct even for TF set by the guest, because "the - * processor will not generate this exception after the instruction - * that sets the TF flag". - */ - if (unlikely(rflags & X86_EFLAGS_TF)) { - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { - kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 | - DR6_RTM; - kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip; - kvm_run->debug.arch.exception = DB_VECTOR; - kvm_run->exit_reason = KVM_EXIT_DEBUG; - *r = EMULATE_USER_EXIT; - } else { - /* - * "Certain debug exceptions may clear bit 0-3. The - * remaining contents of the DR6 register are never - * cleared by the processor". - */ - vcpu->arch.dr6 &= ~15; - vcpu->arch.dr6 |= DR6_BS | DR6_RTM; - kvm_queue_exception(vcpu, DB_VECTOR); - } + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { + kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 | DR6_RTM; + kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip; + kvm_run->debug.arch.exception = DB_VECTOR; + kvm_run->exit_reason = KVM_EXIT_DEBUG; + *r = EMULATE_USER_EXIT; + } else { + /* + * "Certain debug exceptions may clear bit 0-3. The + * remaining contents of the DR6 register are never + * cleared by the processor". + */ + vcpu->arch.dr6 &= ~15; + vcpu->arch.dr6 |= DR6_BS | DR6_RTM; + kvm_queue_exception(vcpu, DB_VECTOR); } } @@ -5546,7 +5558,17 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) int r = EMULATE_DONE; kvm_x86_ops->skip_emulated_instruction(vcpu); - kvm_vcpu_check_singlestep(vcpu, rflags, &r); + + /* + * rflags is the old, "raw" value of the flags. The new value has + * not been saved yet. + * + * This is correct even for TF set by the guest, because "the + * processor will not generate this exception after the instruction + * that sets the TF flag". + */ + if (unlikely(rflags & X86_EFLAGS_TF)) + kvm_vcpu_do_singlestep(vcpu, &r); return r == EMULATE_DONE; } EXPORT_SYMBOL_GPL(kvm_skip_emulated_instruction); @@ -5705,8 +5727,9 @@ restart: toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; kvm_rip_write(vcpu, ctxt->eip); - if (r == EMULATE_DONE) - kvm_vcpu_check_singlestep(vcpu, rflags, &r); + if (r == EMULATE_DONE && + (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) + kvm_vcpu_do_singlestep(vcpu, &r); if (!ctxt->have_exception || exception_type(ctxt->exception.vector) == EXCPT_TRAP) __kvm_set_rflags(vcpu, ctxt->eflags); @@ -5988,7 +6011,7 @@ static void kvm_set_mmio_spte_mask(void) mask &= ~1ull; #endif - kvm_mmu_set_mmio_spte_mask(mask); + kvm_mmu_set_mmio_spte_mask(mask, mask); } #ifdef CONFIG_X86_64 @@ -6710,7 +6733,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) bool req_immediate_exit = false; - if (vcpu->requests) { + if (kvm_request_pending(vcpu)) { if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) kvm_mmu_unload(vcpu); if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu)) @@ -6874,7 +6897,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_x86_ops->sync_pir_to_irr(vcpu); } - if (vcpu->mode == EXITING_GUEST_MODE || vcpu->requests + if (vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu) || need_resched() || signal_pending(current)) { vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); @@ -8373,10 +8396,13 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) if (vcpu->arch.pv.pv_unhalted) return true; - if (atomic_read(&vcpu->arch.nmi_queued)) + if (kvm_test_request(KVM_REQ_NMI, vcpu) || + (vcpu->arch.nmi_pending && + kvm_x86_ops->nmi_allowed(vcpu))) return true; - if (kvm_test_request(KVM_REQ_SMI, vcpu)) + if (kvm_test_request(KVM_REQ_SMI, vcpu) || + (vcpu->arch.smi_pending && !is_smm(vcpu))) return true; if (kvm_arch_interrupt_allowed(vcpu) && @@ -8583,8 +8609,7 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED)) return true; else - return !kvm_event_needs_reinjection(vcpu) && - kvm_x86_ops->interrupt_allowed(vcpu); + return kvm_can_do_async_pf(vcpu); } void kvm_arch_start_assignment(struct kvm *kvm) |