1 files changed, 109 insertions, 56 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index cb5c13eee193..5bbb5612b207 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -154,11 +154,6 @@ static unsigned long long kvm_active_vms;
 
 static DEFINE_PER_CPU(cpumask_var_t, cpu_kick_mask);
 
-__weak void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
-						   unsigned long start, unsigned long end)
-{
-}
-
 __weak void kvm_arch_guest_memory_reclaimed(struct kvm *kvm)
 {
 }
@@ -521,18 +516,6 @@ static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
 	return container_of(mn, struct kvm, mmu_notifier);
 }
 
-static void kvm_mmu_notifier_invalidate_range(struct mmu_notifier *mn,
-					      struct mm_struct *mm,
-					      unsigned long start, unsigned long end)
-{
-	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	int idx;
-
-	idx = srcu_read_lock(&kvm->srcu);
-	kvm_arch_mmu_notifier_invalidate_range(kvm, start, end);
-	srcu_read_unlock(&kvm->srcu, idx);
-}
-
 typedef bool (*hva_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
 
 typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start,
@@ -686,6 +669,24 @@ 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 +708,7 @@ 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,
@@ -892,7 +893,6 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
 }
 
 static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
-	.invalidate_range	= kvm_mmu_notifier_invalidate_range,
 	.invalidate_range_start	= kvm_mmu_notifier_invalidate_range_start,
 	.invalidate_range_end	= kvm_mmu_notifier_invalidate_range_end,
 	.clear_flush_young	= kvm_mmu_notifier_clear_flush_young,
@@ -2477,7 +2477,7 @@ 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 +2578,7 @@ 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 +2602,16 @@ 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 +2629,7 @@ 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;
 
@@ -3870,7 +3873,10 @@ static int create_vcpu_fd(struct kvm_vcpu *vcpu)
 static int vcpu_get_pid(void *data, u64 *val)
 {
 	struct kvm_vcpu *vcpu = data;
-	*val = pid_nr(rcu_access_pointer(vcpu->pid));
+
+	rcu_read_lock();
+	*val = pid_nr(rcu_dereference(vcpu->pid));
+	rcu_read_unlock();
 	return 0;
 }
 
@@ -3962,18 +3968,19 @@ 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 +3995,9 @@ 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);
@@ -4025,8 +4035,17 @@ static ssize_t kvm_vcpu_stats_read(struct file *file, char __user *user_buffer,
 			sizeof(vcpu->stat), user_buffer, size, offset);
 }
 
+static int kvm_vcpu_stats_release(struct inode *inode, struct file *file)
+{
+	struct kvm_vcpu *vcpu = file->private_data;
+
+	kvm_put_kvm(vcpu->kvm);
+	return 0;
+}
+
 static const struct file_operations kvm_vcpu_stats_fops = {
 	.read = kvm_vcpu_stats_read,
+	.release = kvm_vcpu_stats_release,
 	.llseek = noop_llseek,
 };
 
@@ -4047,6 +4066,9 @@ static int kvm_vcpu_ioctl_get_stats_fd(struct kvm_vcpu *vcpu)
 		put_unused_fd(fd);
 		return PTR_ERR(file);
 	}
+
+	kvm_get_kvm(vcpu->kvm);
+
 	file->f_mode |= FMODE_PREAD;
 	fd_install(fd, file);
 
@@ -4598,7 +4620,7 @@ int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 	return -EINVAL;
 }
 
-static bool kvm_are_all_memslots_empty(struct kvm *kvm)
+bool kvm_are_all_memslots_empty(struct kvm *kvm)
 {
 	int i;
 
@@ -4611,6 +4633,7 @@ static bool kvm_are_all_memslots_empty(struct kvm *kvm)
 
 	return true;
 }
+EXPORT_SYMBOL_GPL(kvm_are_all_memslots_empty);
 
 static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
 					   struct kvm_enable_cap *cap)
@@ -4690,8 +4713,17 @@ static ssize_t kvm_vm_stats_read(struct file *file, char __user *user_buffer,
 				sizeof(kvm->stat), user_buffer, size, offset);
 }
 
+static int kvm_vm_stats_release(struct inode *inode, struct file *file)
+{
+	struct kvm *kvm = file->private_data;
+
+	kvm_put_kvm(kvm);
+	return 0;
+}
+
 static const struct file_operations kvm_vm_stats_fops = {
 	.read = kvm_vm_stats_read,
+	.release = kvm_vm_stats_release,
 	.llseek = noop_llseek,
 };
 
@@ -4710,6 +4742,9 @@ static int kvm_vm_ioctl_get_stats_fd(struct kvm *kvm)
 		put_unused_fd(fd);
 		return PTR_ERR(file);
 	}
+
+	kvm_get_kvm(kvm);
+
 	file->f_mode |= FMODE_PREAD;
 	fd_install(fd, file);
 
@@ -5184,7 +5219,20 @@ 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 +5245,8 @@ 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 +5263,24 @@ 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 +5311,7 @@ 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)
@@ -5276,6 +5325,12 @@ static void hardware_disable_all(void)
 }
 #endif /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */
 
+static void kvm_iodevice_destructor(struct kvm_io_device *dev)
+{
+	if (dev->ops->destructor)
+		dev->ops->destructor(dev);
+}
+
 static void kvm_io_bus_destroy(struct kvm_io_bus *bus)
 {
 	int i;
@@ -5499,7 +5554,7 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 			      struct kvm_io_device *dev)
 {
-	int i, j;
+	int i;
 	struct kvm_io_bus *new_bus, *bus;
 
 	lockdep_assert_held(&kvm->slots_lock);
@@ -5529,18 +5584,19 @@ int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
 	synchronize_srcu_expedited(&kvm->srcu);
 
-	/* Destroy the old bus _after_ installing the (null) bus. */
+	/*
+	 * If NULL bus is installed, destroy the old bus, including all the
+	 * attached devices. Otherwise, destroy the caller's device only.
+	 */
 	if (!new_bus) {
 		pr_err("kvm: failed to shrink bus, removing it completely\n");
-		for (j = 0; j < bus->dev_count; j++) {
-			if (j == i)
-				continue;
-			kvm_iodevice_destructor(bus->range[j].dev);
-		}
+		kvm_io_bus_destroy(bus);
+		return -ENOMEM;
 	}
 
+	kvm_iodevice_destructor(dev);
 	kfree(bus);
-	return new_bus ? 0 : -ENOMEM;
+	return 0;
 }
 
 struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
@@ -5967,7 +6023,6 @@ 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 +6094,6 @@ 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 +6119,6 @@ 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();