diff options
Diffstat (limited to 'arch/x86/kvm/x86.c')
| -rw-r--r-- | arch/x86/kvm/x86.c | 418 |
1 files changed, 289 insertions, 129 deletions
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 47e021bdcc94..cebdaa1e3cf5 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -75,6 +75,7 @@ #include <asm/tlbflush.h> #include <asm/intel_pt.h> #include <asm/emulate_prefix.h> +#include <asm/sgx.h> #include <clocksource/hyperv_timer.h> #define CREATE_TRACE_POINTS @@ -156,9 +157,9 @@ module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); /* * lapic timer advance (tscdeadline mode only) in nanoseconds. '-1' enables - * adaptive tuning starting from default advancment of 1000ns. '0' disables + * adaptive tuning starting from default advancement of 1000ns. '0' disables * advancement entirely. Any other value is used as-is and disables adaptive - * tuning, i.e. allows priveleged userspace to set an exact advancement time. + * tuning, i.e. allows privileged userspace to set an exact advancement time. */ static int __read_mostly lapic_timer_advance_ns = -1; module_param(lapic_timer_advance_ns, int, S_IRUGO | S_IWUSR); @@ -245,6 +246,9 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { VCPU_STAT("l1d_flush", l1d_flush), VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns), VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns), + VCPU_STAT("nested_run", nested_run), + VCPU_STAT("directed_yield_attempted", directed_yield_attempted), + VCPU_STAT("directed_yield_successful", directed_yield_successful), VM_STAT("mmu_shadow_zapped", mmu_shadow_zapped), VM_STAT("mmu_pte_write", mmu_pte_write), VM_STAT("mmu_pde_zapped", mmu_pde_zapped), @@ -271,8 +275,7 @@ static struct kmem_cache *x86_emulator_cache; * When called, it means the previous get/set msr reached an invalid msr. * Return true if we want to ignore/silent this failed msr access. */ -static bool kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr, - u64 data, bool write) +static bool kvm_msr_ignored_check(u32 msr, u64 data, bool write) { const char *op = write ? "wrmsr" : "rdmsr"; @@ -544,8 +547,6 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, if (!vcpu->arch.exception.pending && !vcpu->arch.exception.injected) { queue: - if (has_error && !is_protmode(vcpu)) - has_error = false; if (reinject) { /* * On vmentry, vcpu->arch.exception.pending is only @@ -984,14 +985,17 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) return 0; } -int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) +int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu) { - if (static_call(kvm_x86_get_cpl)(vcpu) == 0) - return __kvm_set_xcr(vcpu, index, xcr); + if (static_call(kvm_x86_get_cpl)(vcpu) != 0 || + __kvm_set_xcr(vcpu, kvm_rcx_read(vcpu), kvm_read_edx_eax(vcpu))) { + kvm_inject_gp(vcpu, 0); + return 1; + } - return 1; + return kvm_skip_emulated_instruction(vcpu); } -EXPORT_SYMBOL_GPL(kvm_set_xcr); +EXPORT_SYMBOL_GPL(kvm_emulate_xsetbv); bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { @@ -1073,10 +1077,15 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) return 0; } - if (is_long_mode(vcpu) && kvm_vcpu_is_illegal_gpa(vcpu, cr3)) + /* + * Do not condition the GPA check on long mode, this helper is used to + * stuff CR3, e.g. for RSM emulation, and there is no guarantee that + * the current vCPU mode is accurate. + */ + if (kvm_vcpu_is_illegal_gpa(vcpu, cr3)) return 1; - else if (is_pae_paging(vcpu) && - !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) + + if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) return 1; kvm_mmu_new_pgd(vcpu, cr3, skip_tlb_flush, skip_tlb_flush); @@ -1192,20 +1201,21 @@ void kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) } EXPORT_SYMBOL_GPL(kvm_get_dr); -bool kvm_rdpmc(struct kvm_vcpu *vcpu) +int kvm_emulate_rdpmc(struct kvm_vcpu *vcpu) { u32 ecx = kvm_rcx_read(vcpu); u64 data; - int err; - err = kvm_pmu_rdpmc(vcpu, ecx, &data); - if (err) - return err; + if (kvm_pmu_rdpmc(vcpu, ecx, &data)) { + kvm_inject_gp(vcpu, 0); + return 1; + } + kvm_rax_write(vcpu, (u32)data); kvm_rdx_write(vcpu, data >> 32); - return err; + return kvm_skip_emulated_instruction(vcpu); } -EXPORT_SYMBOL_GPL(kvm_rdpmc); +EXPORT_SYMBOL_GPL(kvm_emulate_rdpmc); /* * List of msr numbers which we expose to userspace through KVM_GET_MSRS @@ -1288,7 +1298,7 @@ static const u32 emulated_msrs_all[] = { MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK, MSR_IA32_TSC_ADJUST, - MSR_IA32_TSCDEADLINE, + MSR_IA32_TSC_DEADLINE, MSR_IA32_ARCH_CAPABILITIES, MSR_IA32_PERF_CAPABILITIES, MSR_IA32_MISC_ENABLE, @@ -1373,7 +1383,7 @@ static u64 kvm_get_arch_capabilities(void) /* * If nx_huge_pages is enabled, KVM's shadow paging will ensure that * the nested hypervisor runs with NX huge pages. If it is not, - * L1 is anyway vulnerable to ITLB_MULTIHIT explots from other + * L1 is anyway vulnerable to ITLB_MULTIHIT exploits from other * L1 guests, so it need not worry about its own (L2) guests. */ data |= ARCH_CAP_PSCHANGE_MC_NO; @@ -1445,7 +1455,7 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data) if (r == KVM_MSR_RET_INVALID) { /* Unconditionally clear the output for simplicity */ *data = 0; - if (kvm_msr_ignored_check(vcpu, index, 0, false)) + if (kvm_msr_ignored_check(index, 0, false)) r = 0; } @@ -1526,35 +1536,44 @@ EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type) { + struct kvm_x86_msr_filter *msr_filter; + struct msr_bitmap_range *ranges; struct kvm *kvm = vcpu->kvm; - struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges; - u32 count = kvm->arch.msr_filter.count; - u32 i; - bool r = kvm->arch.msr_filter.default_allow; + bool allowed; int idx; + u32 i; - /* MSR filtering not set up or x2APIC enabled, allow everything */ - if (!count || (index >= 0x800 && index <= 0x8ff)) + /* x2APIC MSRs do not support filtering. */ + if (index >= 0x800 && index <= 0x8ff) return true; - /* Prevent collision with set_msr_filter */ idx = srcu_read_lock(&kvm->srcu); - for (i = 0; i < count; i++) { + msr_filter = srcu_dereference(kvm->arch.msr_filter, &kvm->srcu); + if (!msr_filter) { + allowed = true; + goto out; + } + + allowed = msr_filter->default_allow; + ranges = msr_filter->ranges; + + for (i = 0; i < msr_filter->count; i++) { u32 start = ranges[i].base; u32 end = start + ranges[i].nmsrs; u32 flags = ranges[i].flags; unsigned long *bitmap = ranges[i].bitmap; if ((index >= start) && (index < end) && (flags & type)) { - r = !!test_bit(index - start, bitmap); + allowed = !!test_bit(index - start, bitmap); break; } } +out: srcu_read_unlock(&kvm->srcu, idx); - return r; + return allowed; } EXPORT_SYMBOL_GPL(kvm_msr_allowed); @@ -1611,7 +1630,7 @@ static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu, int ret = __kvm_set_msr(vcpu, index, data, host_initiated); if (ret == KVM_MSR_RET_INVALID) - if (kvm_msr_ignored_check(vcpu, index, data, true)) + if (kvm_msr_ignored_check(index, data, true)) ret = 0; return ret; @@ -1649,7 +1668,7 @@ static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu, if (ret == KVM_MSR_RET_INVALID) { /* Unconditionally clear *data for simplicity */ *data = 0; - if (kvm_msr_ignored_check(vcpu, index, 0, false)) + if (kvm_msr_ignored_check(index, 0, false)) ret = 0; } @@ -1783,6 +1802,40 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr); +int kvm_emulate_as_nop(struct kvm_vcpu *vcpu) +{ + return kvm_skip_emulated_instruction(vcpu); +} +EXPORT_SYMBOL_GPL(kvm_emulate_as_nop); + +int kvm_emulate_invd(struct kvm_vcpu *vcpu) +{ + /* Treat an INVD instruction as a NOP and just skip it. */ + return kvm_emulate_as_nop(vcpu); +} +EXPORT_SYMBOL_GPL(kvm_emulate_invd); + +int kvm_emulate_mwait(struct kvm_vcpu *vcpu) +{ + pr_warn_once("kvm: MWAIT instruction emulated as NOP!\n"); + return kvm_emulate_as_nop(vcpu); +} +EXPORT_SYMBOL_GPL(kvm_emulate_mwait); + +int kvm_handle_invalid_op(struct kvm_vcpu *vcpu) +{ + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; +} +EXPORT_SYMBOL_GPL(kvm_handle_invalid_op); + +int kvm_emulate_monitor(struct kvm_vcpu *vcpu) +{ + pr_warn_once("kvm: MONITOR instruction emulated as NOP!\n"); + return kvm_emulate_as_nop(vcpu); +} +EXPORT_SYMBOL_GPL(kvm_emulate_monitor); + static inline bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu) { xfer_to_guest_mode_prepare(); @@ -1841,7 +1894,7 @@ fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu) ret = EXIT_FASTPATH_EXIT_HANDLED; } break; - case MSR_IA32_TSCDEADLINE: + case MSR_IA32_TSC_DEADLINE: data = kvm_read_edx_eax(vcpu); if (!handle_fastpath_set_tscdeadline(vcpu, data)) { kvm_skip_emulated_instruction(vcpu); @@ -2320,7 +2373,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) kvm_vcpu_write_tsc_offset(vcpu, offset); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); - spin_lock(&kvm->arch.pvclock_gtod_sync_lock); + spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags); if (!matched) { kvm->arch.nr_vcpus_matched_tsc = 0; } else if (!already_matched) { @@ -2328,7 +2381,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) } kvm_track_tsc_matching(vcpu); - spin_unlock(&kvm->arch.pvclock_gtod_sync_lock); + spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags); } static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, @@ -2550,11 +2603,16 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) int i; struct kvm_vcpu *vcpu; struct kvm_arch *ka = &kvm->arch; + unsigned long flags; + + kvm_hv_invalidate_tsc_page(kvm); - spin_lock(&ka->pvclock_gtod_sync_lock); kvm_make_mclock_inprogress_request(kvm); + /* no guest entries from this point */ + spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); pvclock_update_vm_gtod_copy(kvm); + spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); kvm_for_each_vcpu(i, vcpu, kvm) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -2562,8 +2620,6 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) /* guest entries allowed */ kvm_for_each_vcpu(i, vcpu, kvm) kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu); - - spin_unlock(&ka->pvclock_gtod_sync_lock); #endif } @@ -2571,17 +2627,18 @@ u64 get_kvmclock_ns(struct kvm *kvm) { struct kvm_arch *ka = &kvm->arch; struct pvclock_vcpu_time_info hv_clock; + unsigned long flags; u64 ret; - spin_lock(&ka->pvclock_gtod_sync_lock); + spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); if (!ka->use_master_clock) { - spin_unlock(&ka->pvclock_gtod_sync_lock); + spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); return get_kvmclock_base_ns() + ka->kvmclock_offset; } hv_clock.tsc_timestamp = ka->master_cycle_now; hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; - spin_unlock(&ka->pvclock_gtod_sync_lock); + spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); /* both __this_cpu_read() and rdtsc() should be on the same cpu */ get_cpu(); @@ -2675,13 +2732,13 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) * If the host uses TSC clock, then passthrough TSC as stable * to the guest. */ - spin_lock(&ka->pvclock_gtod_sync_lock); + spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); use_master_clock = ka->use_master_clock; if (use_master_clock) { host_tsc = ka->master_cycle_now; kernel_ns = ka->master_kernel_ns; } - spin_unlock(&ka->pvclock_gtod_sync_lock); + spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); @@ -3075,7 +3132,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return kvm_set_apic_base(vcpu, msr_info); case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_write(vcpu, msr, data); - case MSR_IA32_TSCDEADLINE: + case MSR_IA32_TSC_DEADLINE: kvm_set_lapic_tscdeadline_msr(vcpu, data); break; case MSR_IA32_TSC_ADJUST: @@ -3370,6 +3427,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 0; break; case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5: + if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) + return kvm_pmu_get_msr(vcpu, msr_info); + if (!msr_info->host_initiated) + return 1; + msr_info->data = 0; + break; case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: @@ -3437,7 +3500,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data); - case MSR_IA32_TSCDEADLINE: + case MSR_IA32_TSC_DEADLINE: msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu); break; case MSR_IA32_TSC_ADJUST: @@ -3759,8 +3822,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_X86_USER_SPACE_MSR: case KVM_CAP_X86_MSR_FILTER: case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: +#ifdef CONFIG_X86_SGX_KVM + case KVM_CAP_SGX_ATTRIBUTE: +#endif + case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM: r = 1; break; + case KVM_CAP_SET_GUEST_DEBUG2: + return KVM_GUESTDBG_VALID_MASK; #ifdef CONFIG_KVM_XEN case KVM_CAP_XEN_HVM: r = KVM_XEN_HVM_CONFIG_HYPERCALL_MSR | @@ -4013,7 +4082,6 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) { struct kvm_host_map map; struct kvm_steal_time *st; - int idx; if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -4021,15 +4089,9 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) if (vcpu->arch.st.preempted) return; - /* - * Take the srcu lock as memslots will be accessed to check the gfn - * cache generation against the memslots generation. - */ - idx = srcu_read_lock(&vcpu->kvm->srcu); - if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map, &vcpu->arch.st.cache, true)) - goto out; + return; st = map.hva + offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); @@ -4037,20 +4099,25 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true); - -out: - srcu_read_unlock(&vcpu->kvm->srcu, idx); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { + int idx; + if (vcpu->preempted && !vcpu->arch.guest_state_protected) vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu); + /* + * Take the srcu lock as memslots will be accessed to check the gfn + * cache generation against the memslots generation. + */ + idx = srcu_read_lock(&vcpu->kvm->srcu); if (kvm_xen_msr_enabled(vcpu->kvm)) kvm_xen_runstate_set_preempted(vcpu); else kvm_steal_time_set_preempted(vcpu); + srcu_read_unlock(&vcpu->kvm->srcu, idx); static_call(kvm_x86_vcpu_put)(vcpu); vcpu->arch.last_host_tsc = rdtsc(); @@ -4663,7 +4730,6 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, kvm_update_pv_runtime(vcpu); return 0; - default: return -EINVAL; } @@ -5345,6 +5411,28 @@ split_irqchip_unlock: kvm->arch.bus_lock_detection_enabled = true; r = 0; break; +#ifdef CONFIG_X86_SGX_KVM + case KVM_CAP_SGX_ATTRIBUTE: { + unsigned long allowed_attributes = 0; + + r = sgx_set_attribute(&allowed_attributes, cap->args[0]); + if (r) + break; + + /* KVM only supports the PROVISIONKEY privileged attribute. */ + if ((allowed_attributes & SGX_ATTR_PROVISIONKEY) && + !(allowed_attributes & ~SGX_ATTR_PROVISIONKEY)) + kvm->arch.sgx_provisioning_allowed = true; + else + r = -EINVAL; + break; + } +#endif + case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM: + r = -EINVAL; + if (kvm_x86_ops.vm_copy_enc_context_from) + r = kvm_x86_ops.vm_copy_enc_context_from(kvm, cap->args[0]); + return r; default: r = -EINVAL; break; @@ -5352,25 +5440,34 @@ split_irqchip_unlock: return r; } -static void kvm_clear_msr_filter(struct kvm *kvm) +static struct kvm_x86_msr_filter *kvm_alloc_msr_filter(bool default_allow) +{ + struct kvm_x86_msr_filter *msr_filter; + + msr_filter = kzalloc(sizeof(*msr_filter), GFP_KERNEL_ACCOUNT); + if (!msr_filter) + return NULL; + + msr_filter->default_allow = default_allow; + return msr_filter; +} + +static void kvm_free_msr_filter(struct kvm_x86_msr_filter *msr_filter) { u32 i; - u32 count = kvm->arch.msr_filter.count; - struct msr_bitmap_range ranges[16]; - mutex_lock(&kvm->lock); - kvm->arch.msr_filter.count = 0; - memcpy(ranges, kvm->arch.msr_filter.ranges, count * sizeof(ranges[0])); - mutex_unlock(&kvm->lock); - synchronize_srcu(&kvm->srcu); + if (!msr_filter) + return; + + for (i = 0; i < msr_filter->count; i++) + kfree(msr_filter->ranges[i].bitmap); - for (i = 0; i < count; i++) - kfree(ranges[i].bitmap); + kfree(msr_filter); } -static int kvm_add_msr_filter(struct kvm *kvm, struct kvm_msr_filter_range *user_range) +static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, + struct kvm_msr_filter_range *user_range) { - struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges; struct msr_bitmap_range range; unsigned long *bitmap = NULL; size_t bitmap_size; @@ -5404,11 +5501,9 @@ static int kvm_add_msr_filter(struct kvm *kvm, struct kvm_msr_filter_range *user goto err; } - /* Everything ok, add this range identifier to our global pool */ - ranges[kvm->arch.msr_filter.count] = range; - /* Make sure we filled the array before we tell anyone to walk it */ - smp_wmb(); - kvm->arch.msr_filter.count++; + /* Everything ok, add this range identifier. */ + msr_filter->ranges[msr_filter->count] = range; + msr_filter->count++; return 0; err: @@ -5419,10 +5514,11 @@ err: static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) { struct kvm_msr_filter __user *user_msr_filter = argp; + struct kvm_x86_msr_filter *new_filter, *old_filter; struct kvm_msr_filter filter; bool default_allow; - int r = 0; bool empty = true; + int r = 0; u32 i; if (copy_from_user(&filter, user_msr_filter, sizeof(filter))) @@ -5435,25 +5531,32 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) if (empty && !default_allow) return -EINVAL; - kvm_clear_msr_filter(kvm); + new_filter = kvm_alloc_msr_filter(default_allow); + if (!new_filter) + return -ENOMEM; - kvm->arch.msr_filter.default_allow = default_allow; - - /* - * Protect from concurrent calls to this function that could trigger - * a TOCTOU violation on kvm->arch.msr_filter.count. - */ - mutex_lock(&kvm->lock); for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) { - r = kvm_add_msr_filter(kvm, &filter.ranges[i]); - if (r) - break; + r = kvm_add_msr_filter(new_filter, &filter.ranges[i]); + if (r) { + kvm_free_msr_filter(new_filter); + return r; + } } + mutex_lock(&kvm->lock); + + /* The per-VM filter is protected by kvm->lock... */ + old_filter = srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1); + + rcu_assign_pointer(kvm->arch.msr_filter, new_filter); + synchronize_srcu(&kvm->srcu); + + kvm_free_msr_filter(old_filter); + kvm_make_all_cpus_request(kvm, KVM_REQ_MSR_FILTER_CHANGED); mutex_unlock(&kvm->lock); - return r; + return 0; } long kvm_arch_vm_ioctl(struct file *filp, @@ -5700,6 +5803,7 @@ set_pit2_out: } #endif case KVM_SET_CLOCK: { + struct kvm_arch *ka = &kvm->arch; struct kvm_clock_data user_ns; u64 now_ns; @@ -5718,8 +5822,22 @@ set_pit2_out: * pvclock_update_vm_gtod_copy(). */ kvm_gen_update_masterclock(kvm); - now_ns = get_kvmclock_ns(kvm); - kvm->arch.kvmclock_offset += user_ns.clock - now_ns; + + /* + * This pairs with kvm_guest_time_update(): when masterclock is + * in use, we use master_kernel_ns + kvmclock_offset to set + * unsigned 'system_time' so if we use get_kvmclock_ns() (which + * is slightly ahead) here we risk going negative on unsigned + * 'system_time' when 'user_ns.clock' is very small. + */ + spin_lock_irq(&ka->pvclock_gtod_sync_lock); + if (kvm->arch.use_master_clock) + now_ns = ka->master_kernel_ns; + else + now_ns = get_kvmclock_base_ns(); + ka->kvmclock_offset = user_ns.clock - now_ns; + spin_unlock_irq(&ka->pvclock_gtod_sync_lock); + kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE); break; } @@ -5959,6 +6077,7 @@ gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); } +EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_read); gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) @@ -5975,6 +6094,7 @@ gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, access |= PFERR_WRITE_MASK; return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); } +EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_write); /* uses this to access any guest's mapped memory without checking CPL */ gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, @@ -6603,7 +6723,7 @@ static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu) int cpu = get_cpu(); cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); - smp_call_function_many(vcpu->arch.wbinvd_dirty_mask, + on_each_cpu_mask(vcpu->arch.wbinvd_dirty_mask, wbinvd_ipi, NULL, 1); put_cpu(); cpumask_clear(vcpu->arch.wbinvd_dirty_mask); @@ -6894,12 +7014,12 @@ static bool emulator_guest_has_fxsr(struct x86_emulate_ctxt *ctxt) static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg) { - return kvm_register_read(emul_to_vcpu(ctxt), reg); + return kvm_register_read_raw(emul_to_vcpu(ctxt), reg); } static void emulator_write_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg, ulong val) { - kvm_register_write(emul_to_vcpu(ctxt), reg, val); + kvm_register_write_raw(emul_to_vcpu(ctxt), reg, val); } static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked) @@ -7698,6 +7818,7 @@ static void kvm_hyperv_tsc_notifier(void) struct kvm *kvm; struct kvm_vcpu *vcpu; int cpu; + unsigned long flags; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) @@ -7713,17 +7834,15 @@ static void kvm_hyperv_tsc_notifier(void) list_for_each_entry(kvm, &vm_list, vm_list) { struct kvm_arch *ka = &kvm->arch; - spin_lock(&ka->pvclock_gtod_sync_lock); - + spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); pvclock_update_vm_gtod_copy(kvm); + spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); kvm_for_each_vcpu(cpu, vcpu, kvm) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); kvm_for_each_vcpu(cpu, vcpu, kvm) kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu); - - spin_unlock(&ka->pvclock_gtod_sync_lock); } mutex_unlock(&kvm_lock); } @@ -8004,9 +8123,6 @@ int kvm_arch_init(void *opaque) if (r) goto out_free_percpu; - kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, - PT_DIRTY_MASK, PT64_NX_MASK, 0, - PT_PRESENT_MASK, 0, sme_me_mask); kvm_timer_init(); perf_register_guest_info_callbacks(&kvm_guest_cbs); @@ -8166,21 +8282,35 @@ void kvm_apicv_init(struct kvm *kvm, bool enable) } EXPORT_SYMBOL_GPL(kvm_apicv_init); -static void kvm_sched_yield(struct kvm *kvm, unsigned long dest_id) +static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) { struct kvm_vcpu *target = NULL; struct kvm_apic_map *map; + vcpu->stat.directed_yield_attempted++; + rcu_read_lock(); - map = rcu_dereference(kvm->arch.apic_map); + map = rcu_dereference(vcpu->kvm->arch.apic_map); if (likely(map) && dest_id <= map->max_apic_id && map->phys_map[dest_id]) target = map->phys_map[dest_id]->vcpu; rcu_read_unlock(); - if (target && READ_ONCE(target->ready)) - kvm_vcpu_yield_to(target); + if (!target || !READ_ONCE(target->ready)) + goto no_yield; + + /* Ignore requests to yield to self */ + if (vcpu == target) + goto no_yield; + + if (kvm_vcpu_yield_to(target) <= 0) + goto no_yield; + + vcpu->stat.directed_yield_successful++; + +no_yield: + return; } int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) @@ -8227,7 +8357,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) break; kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1); - kvm_sched_yield(vcpu->kvm, a1); + kvm_sched_yield(vcpu, a1); ret = 0; break; #ifdef CONFIG_X86_64 @@ -8245,7 +8375,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) if (!guest_pv_has(vcpu, KVM_FEATURE_PV_SCHED_YIELD)) break; - kvm_sched_yield(vcpu->kvm, a0); + kvm_sched_yield(vcpu, a0); ret = 0; break; default: @@ -8328,6 +8458,27 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) static_call(kvm_x86_update_cr8_intercept)(vcpu, tpr, max_irr); } + +int kvm_check_nested_events(struct kvm_vcpu *vcpu) +{ + if (WARN_ON_ONCE(!is_guest_mode(vcpu))) + return -EIO; + + if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { + kvm_x86_ops.nested_ops->triple_fault(vcpu); + return 1; + } + + return kvm_x86_ops.nested_ops->check_events(vcpu); +} + +static void kvm_inject_exception(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.exception.error_code && !is_protmode(vcpu)) + vcpu->arch.exception.error_code = false; + static_call(kvm_x86_queue_exception)(vcpu); +} + static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) { int r; @@ -8336,7 +8487,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit /* try to reinject previous events if any */ if (vcpu->arch.exception.injected) { - static_call(kvm_x86_queue_exception)(vcpu); + kvm_inject_exception(vcpu); can_inject = false; } /* @@ -8373,7 +8524,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit * from L2 to L1. */ if (is_guest_mode(vcpu)) { - r = kvm_x86_ops.nested_ops->check_events(vcpu); + r = kvm_check_nested_events(vcpu); if (r < 0) goto busy; } @@ -8399,7 +8550,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit } } - static_call(kvm_x86_queue_exception)(vcpu); + kvm_inject_exception(vcpu); can_inject = false; } @@ -8548,7 +8699,7 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf) put_smstate(u32, buf, 0x7ff0, kvm_rip_read(vcpu)); for (i = 0; i < 8; i++) - put_smstate(u32, buf, 0x7fd0 + i * 4, kvm_register_read(vcpu, i)); + put_smstate(u32, buf, 0x7fd0 + i * 4, kvm_register_read_raw(vcpu, i)); kvm_get_dr(vcpu, 6, &val); put_smstate(u32, buf, 0x7fcc, (u32)val); @@ -8594,7 +8745,7 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf) int i; for (i = 0; i < 16; i++) - put_smstate(u64, buf, 0x7ff8 - i * 8, kvm_register_read(vcpu, i)); + put_smstate(u64, buf, 0x7ff8 - i * 8, kvm_register_read_raw(vcpu, i)); put_smstate(u64, buf, 0x7f78, kvm_rip_read(vcpu)); put_smstate(u32, buf, 0x7f70, kvm_get_rflags(vcpu)); @@ -8936,10 +9087,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto out; } if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { - vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; - vcpu->mmio_needed = 0; - r = 0; - goto out; + if (is_guest_mode(vcpu)) { + kvm_x86_ops.nested_ops->triple_fault(vcpu); + } else { + vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; + vcpu->mmio_needed = 0; + r = 0; + goto out; + } } if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) { /* Page is swapped out. Do synthetic halt */ @@ -9237,7 +9392,7 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu)) - kvm_x86_ops.nested_ops->check_events(vcpu); + kvm_check_nested_events(vcpu); return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && !vcpu->arch.apf.halted); @@ -10634,8 +10789,6 @@ void kvm_arch_pre_destroy_vm(struct kvm *kvm) void kvm_arch_destroy_vm(struct kvm *kvm) { - u32 i; - if (current->mm == kvm->mm) { /* * Free memory regions allocated on behalf of userspace, @@ -10651,8 +10804,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) mutex_unlock(&kvm->slots_lock); } static_call_cond(kvm_x86_vm_destroy)(kvm); - for (i = 0; i < kvm->arch.msr_filter.count; i++) - kfree(kvm->arch.msr_filter.ranges[i].bitmap); + kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1)); kvm_pic_destroy(kvm); kvm_ioapic_destroy(kvm); kvm_free_vcpus(kvm); @@ -10966,6 +11118,14 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu); } +bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.apicv_active && static_call(kvm_x86_dy_apicv_has_pending_interrupt)(vcpu)) + return true; + + return false; +} + bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) { if (READ_ONCE(vcpu->arch.pv.pv_unhalted)) @@ -10976,14 +11136,14 @@ bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) kvm_test_request(KVM_REQ_EVENT, vcpu)) return true; - if (vcpu->arch.apicv_active && static_call(kvm_x86_dy_apicv_has_pending_interrupt)(vcpu)) - return true; - - return false; + return kvm_arch_dy_has_pending_interrupt(vcpu); } bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) { + if (vcpu->arch.guest_state_protected) + return true; + return vcpu->arch.preempted_in_kernel; } @@ -11254,7 +11414,7 @@ bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu) if (!kvm_pv_async_pf_enabled(vcpu)) return true; else - return apf_pageready_slot_free(vcpu); + return kvm_lapic_enabled(vcpu) && apf_pageready_slot_free(vcpu); } void kvm_arch_start_assignment(struct kvm *kvm) @@ -11503,7 +11663,7 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) fallthrough; case INVPCID_TYPE_ALL_INCL_GLOBAL: - kvm_mmu_unload(vcpu); + kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); return kvm_skip_emulated_instruction(vcpu); default: |