diff options
Diffstat (limited to 'virt')
-rw-r--r-- | virt/kvm/async_pf.c | 3 | ||||
-rw-r--r-- | virt/kvm/kvm_main.c | 92 |
2 files changed, 65 insertions, 30 deletions
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 9bfe1d6f6529..e033c79d528e 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -61,8 +61,7 @@ static void async_pf_execute(struct work_struct *work) * access remotely. */ mmap_read_lock(mm); - get_user_pages_remote(mm, addr, 1, FOLL_WRITE, NULL, NULL, - &locked); + get_user_pages_remote(mm, addr, 1, FOLL_WRITE, NULL, &locked); if (locked) mmap_read_unlock(mm); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index cb5c13eee193..19f301ef23c9 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -686,6 +686,24 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn return __kvm_handle_hva_range(kvm, &range); } + +static bool kvm_change_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) +{ + /* + * Skipping invalid memslots is correct if and only change_pte() is + * surrounded by invalidate_range_{start,end}(), which is currently + * guaranteed by the primary MMU. If that ever changes, KVM needs to + * unmap the memslot instead of skipping the memslot to ensure that KVM + * doesn't hold references to the old PFN. + */ + WARN_ON_ONCE(!READ_ONCE(kvm->mn_active_invalidate_count)); + + if (range->slot->flags & KVM_MEMSLOT_INVALID) + return false; + + return kvm_set_spte_gfn(kvm, range); +} + static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long address, @@ -707,7 +725,7 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn, if (!READ_ONCE(kvm->mmu_invalidate_in_progress)) return; - kvm_handle_hva_range(mn, address, address + 1, pte, kvm_set_spte_gfn); + kvm_handle_hva_range(mn, address, address + 1, pte, kvm_change_spte_gfn); } void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start, @@ -2477,7 +2495,7 @@ static inline int check_user_page_hwpoison(unsigned long addr) { int rc, flags = FOLL_HWPOISON | FOLL_WRITE; - rc = get_user_pages(addr, 1, flags, NULL, NULL); + rc = get_user_pages(addr, 1, flags, NULL); return rc == -EHWPOISON; } @@ -2578,6 +2596,7 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma, { kvm_pfn_t pfn; pte_t *ptep; + pte_t pte; spinlock_t *ptl; int r; @@ -2601,14 +2620,16 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma, return r; } - if (write_fault && !pte_write(*ptep)) { + pte = ptep_get(ptep); + + if (write_fault && !pte_write(pte)) { pfn = KVM_PFN_ERR_RO_FAULT; goto out; } if (writable) - *writable = pte_write(*ptep); - pfn = pte_pfn(*ptep); + *writable = pte_write(pte); + pfn = pte_pfn(pte); /* * Get a reference here because callers of *hva_to_pfn* and @@ -2626,7 +2647,7 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma, * tail pages of non-compound higher order allocations, which * would then underflow the refcount when the caller does the * required put_page. Don't allow those pages here. - */ + */ if (!kvm_try_get_pfn(pfn)) r = -EFAULT; @@ -3962,18 +3983,19 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) } vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); - r = xa_insert(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, GFP_KERNEL_ACCOUNT); - BUG_ON(r == -EBUSY); + r = xa_reserve(&kvm->vcpu_array, vcpu->vcpu_idx, GFP_KERNEL_ACCOUNT); if (r) goto unlock_vcpu_destroy; /* Now it's all set up, let userspace reach it */ kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); - if (r < 0) { - xa_erase(&kvm->vcpu_array, vcpu->vcpu_idx); - kvm_put_kvm_no_destroy(kvm); - goto unlock_vcpu_destroy; + if (r < 0) + goto kvm_put_xa_release; + + if (KVM_BUG_ON(!!xa_store(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, 0), kvm)) { + r = -EINVAL; + goto kvm_put_xa_release; } /* @@ -3988,6 +4010,9 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) kvm_create_vcpu_debugfs(vcpu); return r; +kvm_put_xa_release: + kvm_put_kvm_no_destroy(kvm); + xa_release(&kvm->vcpu_array, vcpu->vcpu_idx); unlock_vcpu_destroy: mutex_unlock(&kvm->lock); kvm_dirty_ring_free(&vcpu->dirty_ring); @@ -5184,7 +5209,20 @@ static void hardware_disable_all(void) static int hardware_enable_all(void) { atomic_t failed = ATOMIC_INIT(0); - int r = 0; + int r; + + /* + * Do not enable hardware virtualization if the system is going down. + * If userspace initiated a forced reboot, e.g. reboot -f, then it's + * possible for an in-flight KVM_CREATE_VM to trigger hardware enabling + * after kvm_reboot() is called. Note, this relies on system_state + * being set _before_ kvm_reboot(), which is why KVM uses a syscore ops + * hook instead of registering a dedicated reboot notifier (the latter + * runs before system_state is updated). + */ + if (system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || + system_state == SYSTEM_RESTART) + return -EBUSY; /* * When onlining a CPU, cpu_online_mask is set before kvm_online_cpu() @@ -5197,6 +5235,8 @@ static int hardware_enable_all(void) cpus_read_lock(); mutex_lock(&kvm_lock); + r = 0; + kvm_usage_count++; if (kvm_usage_count == 1) { on_each_cpu(hardware_enable_nolock, &failed, 1); @@ -5213,26 +5253,24 @@ static int hardware_enable_all(void) return r; } -static int kvm_reboot(struct notifier_block *notifier, unsigned long val, - void *v) +static void kvm_shutdown(void) { /* - * Some (well, at least mine) BIOSes hang on reboot if - * in vmx root mode. - * - * And Intel TXT required VMX off for all cpu when system shutdown. + * Disable hardware virtualization and set kvm_rebooting to indicate + * that KVM has asynchronously disabled hardware virtualization, i.e. + * that relevant errors and exceptions aren't entirely unexpected. + * Some flavors of hardware virtualization need to be disabled before + * transferring control to firmware (to perform shutdown/reboot), e.g. + * on x86, virtualization can block INIT interrupts, which are used by + * firmware to pull APs back under firmware control. Note, this path + * is used for both shutdown and reboot scenarios, i.e. neither name is + * 100% comprehensive. */ pr_info("kvm: exiting hardware virtualization\n"); kvm_rebooting = true; on_each_cpu(hardware_disable_nolock, NULL, 1); - return NOTIFY_OK; } -static struct notifier_block kvm_reboot_notifier = { - .notifier_call = kvm_reboot, - .priority = 0, -}; - static int kvm_suspend(void) { /* @@ -5263,6 +5301,7 @@ static void kvm_resume(void) static struct syscore_ops kvm_syscore_ops = { .suspend = kvm_suspend, .resume = kvm_resume, + .shutdown = kvm_shutdown, }; #else /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ static int hardware_enable_all(void) @@ -5967,7 +6006,6 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) if (r) return r; - register_reboot_notifier(&kvm_reboot_notifier); register_syscore_ops(&kvm_syscore_ops); #endif @@ -6039,7 +6077,6 @@ err_cpu_kick_mask: err_vcpu_cache: #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING unregister_syscore_ops(&kvm_syscore_ops); - unregister_reboot_notifier(&kvm_reboot_notifier); cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); #endif return r; @@ -6065,7 +6102,6 @@ void kvm_exit(void) kvm_async_pf_deinit(); #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING unregister_syscore_ops(&kvm_syscore_ops); - unregister_reboot_notifier(&kvm_reboot_notifier); cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); #endif kvm_irqfd_exit(); |