5 files changed, 118 insertions, 105 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/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c
index 5ef88f5a0864..1b90acb6e3fe 100644
--- a/virt/kvm/coalesced_mmio.c
+++ b/virt/kvm/coalesced_mmio.c
@@ -186,15 +186,10 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
 		    coalesced_mmio_in_range(dev, zone->addr, zone->size)) {
 			r = kvm_io_bus_unregister_dev(kvm,
 				zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, &dev->dev);
-
-			kvm_iodevice_destructor(&dev->dev);
-
 			/*
 			 * On failure, unregister destroys all devices on the
-			 * bus _except_ the target device, i.e. coalesced_zones
-			 * has been modified.  Bail after destroying the target
-			 * device, there's no need to restart the walk as there
-			 * aren't any zones left.
+			 * bus, including the target device. There's no need
+			 * to restart the walk as there aren't any zones left.
 			 */
 			if (r)
 				break;
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index b0af834ffa95..89912a17f5d5 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -889,9 +889,9 @@ static int kvm_assign_ioeventfd_idx(struct kvm *kvm,
 
 unlock_fail:
 	mutex_unlock(&kvm->slots_lock);
+	kfree(p);
 
 fail:
-	kfree(p);
 	eventfd_ctx_put(eventfd);
 
 	return ret;
@@ -901,7 +901,7 @@ static int
 kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx,
 			   struct kvm_ioeventfd *args)
 {
-	struct _ioeventfd        *p, *tmp;
+	struct _ioeventfd        *p;
 	struct eventfd_ctx       *eventfd;
 	struct kvm_io_bus	 *bus;
 	int                       ret = -ENOENT;
@@ -915,8 +915,7 @@ kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx,
 
 	mutex_lock(&kvm->slots_lock);
 
-	list_for_each_entry_safe(p, tmp, &kvm->ioeventfds, list) {
-
+	list_for_each_entry(p, &kvm->ioeventfds, list) {
 		if (p->bus_idx != bus_idx ||
 		    p->eventfd != eventfd  ||
 		    p->addr != args->addr  ||
@@ -931,7 +930,6 @@ kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx,
 		bus = kvm_get_bus(kvm, bus_idx);
 		if (bus)
 			bus->ioeventfd_count--;
-		ioeventfd_release(p);
 		ret = 0;
 		break;
 	}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 65f94f592ff8..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,
@@ -910,7 +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,
@@ -2495,7 +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;
 }
 
@@ -2596,6 +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;
 
@@ -2619,14 +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
@@ -2644,7 +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;
 
@@ -3888,7 +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;
 }
 
@@ -3990,7 +3978,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 	if (r < 0)
 		goto kvm_put_xa_release;
 
-	if (KVM_BUG_ON(!!xa_store(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, 0), kvm)) {
+	if (KVM_BUG_ON(xa_store(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, 0), kvm)) {
 		r = -EINVAL;
 		goto kvm_put_xa_release;
 	}
@@ -4047,8 +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,
 };
 
@@ -4069,6 +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);
 
@@ -4620,7 +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;
 
@@ -4633,6 +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)
@@ -4712,8 +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,
 };
 
@@ -4732,6 +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);
 
@@ -5312,6 +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;
@@ -5535,7 +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);
@@ -5565,18 +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,
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index 9584eb57e0ed..365d30779768 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -21,7 +21,7 @@
 #include <asm/kvm_ppc.h>
 #endif
 
-struct kvm_vfio_group {
+struct kvm_vfio_file {
 	struct list_head node;
 	struct file *file;
 #ifdef CONFIG_SPAPR_TCE_IOMMU
@@ -30,7 +30,7 @@ struct kvm_vfio_group {
 };
 
 struct kvm_vfio {
-	struct list_head group_list;
+	struct list_head file_list;
 	struct mutex lock;
 	bool noncoherent;
 };
@@ -98,34 +98,35 @@ static struct iommu_group *kvm_vfio_file_iommu_group(struct file *file)
 }
 
 static void kvm_spapr_tce_release_vfio_group(struct kvm *kvm,
-					     struct kvm_vfio_group *kvg)
+					     struct kvm_vfio_file *kvf)
 {
-	if (WARN_ON_ONCE(!kvg->iommu_group))
+	if (WARN_ON_ONCE(!kvf->iommu_group))
 		return;
 
-	kvm_spapr_tce_release_iommu_group(kvm, kvg->iommu_group);
-	iommu_group_put(kvg->iommu_group);
-	kvg->iommu_group = NULL;
+	kvm_spapr_tce_release_iommu_group(kvm, kvf->iommu_group);
+	iommu_group_put(kvf->iommu_group);
+	kvf->iommu_group = NULL;
 }
 #endif
 
 /*
- * Groups can use the same or different IOMMU domains.  If the same then
- * adding a new group may change the coherency of groups we've previously
- * been told about.  We don't want to care about any of that so we retest
- * each group and bail as soon as we find one that's noncoherent.  This
- * means we only ever [un]register_noncoherent_dma once for the whole device.
+ * Groups/devices can use the same or different IOMMU domains. If the same
+ * then adding a new group/device may change the coherency of groups/devices
+ * we've previously been told about. We don't want to care about any of
+ * that so we retest each group/device and bail as soon as we find one that's
+ * noncoherent.  This means we only ever [un]register_noncoherent_dma once
+ * for the whole device.
  */
 static void kvm_vfio_update_coherency(struct kvm_device *dev)
 {
 	struct kvm_vfio *kv = dev->private;
 	bool noncoherent = false;
-	struct kvm_vfio_group *kvg;
+	struct kvm_vfio_file *kvf;
 
 	mutex_lock(&kv->lock);
 
-	list_for_each_entry(kvg, &kv->group_list, node) {
-		if (!kvm_vfio_file_enforced_coherent(kvg->file)) {
+	list_for_each_entry(kvf, &kv->file_list, node) {
+		if (!kvm_vfio_file_enforced_coherent(kvf->file)) {
 			noncoherent = true;
 			break;
 		}
@@ -143,10 +144,10 @@ static void kvm_vfio_update_coherency(struct kvm_device *dev)
 	mutex_unlock(&kv->lock);
 }
 
-static int kvm_vfio_group_add(struct kvm_device *dev, unsigned int fd)
+static int kvm_vfio_file_add(struct kvm_device *dev, unsigned int fd)
 {
 	struct kvm_vfio *kv = dev->private;
-	struct kvm_vfio_group *kvg;
+	struct kvm_vfio_file *kvf;
 	struct file *filp;
 	int ret;
 
@@ -162,27 +163,27 @@ static int kvm_vfio_group_add(struct kvm_device *dev, unsigned int fd)
 
 	mutex_lock(&kv->lock);
 
-	list_for_each_entry(kvg, &kv->group_list, node) {
-		if (kvg->file == filp) {
+	list_for_each_entry(kvf, &kv->file_list, node) {
+		if (kvf->file == filp) {
 			ret = -EEXIST;
 			goto err_unlock;
 		}
 	}
 
-	kvg = kzalloc(sizeof(*kvg), GFP_KERNEL_ACCOUNT);
-	if (!kvg) {
+	kvf = kzalloc(sizeof(*kvf), GFP_KERNEL_ACCOUNT);
+	if (!kvf) {
 		ret = -ENOMEM;
 		goto err_unlock;
 	}
 
-	kvg->file = filp;
-	list_add_tail(&kvg->node, &kv->group_list);
+	kvf->file = filp;
+	list_add_tail(&kvf->node, &kv->file_list);
 
 	kvm_arch_start_assignment(dev->kvm);
+	kvm_vfio_file_set_kvm(kvf->file, dev->kvm);
 
 	mutex_unlock(&kv->lock);
 
-	kvm_vfio_file_set_kvm(kvg->file, dev->kvm);
 	kvm_vfio_update_coherency(dev);
 
 	return 0;
@@ -193,10 +194,10 @@ err_fput:
 	return ret;
 }
 
-static int kvm_vfio_group_del(struct kvm_device *dev, unsigned int fd)
+static int kvm_vfio_file_del(struct kvm_device *dev, unsigned int fd)
 {
 	struct kvm_vfio *kv = dev->private;
-	struct kvm_vfio_group *kvg;
+	struct kvm_vfio_file *kvf;
 	struct fd f;
 	int ret;
 
@@ -208,18 +209,18 @@ static int kvm_vfio_group_del(struct kvm_device *dev, unsigned int fd)
 
 	mutex_lock(&kv->lock);
 
-	list_for_each_entry(kvg, &kv->group_list, node) {
-		if (kvg->file != f.file)
+	list_for_each_entry(kvf, &kv->file_list, node) {
+		if (kvf->file != f.file)
 			continue;
 
-		list_del(&kvg->node);
+		list_del(&kvf->node);
 		kvm_arch_end_assignment(dev->kvm);
 #ifdef CONFIG_SPAPR_TCE_IOMMU
-		kvm_spapr_tce_release_vfio_group(dev->kvm, kvg);
+		kvm_spapr_tce_release_vfio_group(dev->kvm, kvf);
 #endif
-		kvm_vfio_file_set_kvm(kvg->file, NULL);
-		fput(kvg->file);
-		kfree(kvg);
+		kvm_vfio_file_set_kvm(kvf->file, NULL);
+		fput(kvf->file);
+		kfree(kvf);
 		ret = 0;
 		break;
 	}
@@ -234,12 +235,12 @@ static int kvm_vfio_group_del(struct kvm_device *dev, unsigned int fd)
 }
 
 #ifdef CONFIG_SPAPR_TCE_IOMMU
-static int kvm_vfio_group_set_spapr_tce(struct kvm_device *dev,
-					void __user *arg)
+static int kvm_vfio_file_set_spapr_tce(struct kvm_device *dev,
+				       void __user *arg)
 {
 	struct kvm_vfio_spapr_tce param;
 	struct kvm_vfio *kv = dev->private;
-	struct kvm_vfio_group *kvg;
+	struct kvm_vfio_file *kvf;
 	struct fd f;
 	int ret;
 
@@ -254,20 +255,20 @@ static int kvm_vfio_group_set_spapr_tce(struct kvm_device *dev,
 
 	mutex_lock(&kv->lock);
 
-	list_for_each_entry(kvg, &kv->group_list, node) {
-		if (kvg->file != f.file)
+	list_for_each_entry(kvf, &kv->file_list, node) {
+		if (kvf->file != f.file)
 			continue;
 
-		if (!kvg->iommu_group) {
-			kvg->iommu_group = kvm_vfio_file_iommu_group(kvg->file);
-			if (WARN_ON_ONCE(!kvg->iommu_group)) {
+		if (!kvf->iommu_group) {
+			kvf->iommu_group = kvm_vfio_file_iommu_group(kvf->file);
+			if (WARN_ON_ONCE(!kvf->iommu_group)) {
 				ret = -EIO;
 				goto err_fdput;
 			}
 		}
 
 		ret = kvm_spapr_tce_attach_iommu_group(dev->kvm, param.tablefd,
-						       kvg->iommu_group);
+						       kvf->iommu_group);
 		break;
 	}
 
@@ -278,8 +279,8 @@ err_fdput:
 }
 #endif
 
-static int kvm_vfio_set_group(struct kvm_device *dev, long attr,
-			      void __user *arg)
+static int kvm_vfio_set_file(struct kvm_device *dev, long attr,
+			     void __user *arg)
 {
 	int32_t __user *argp = arg;
 	int32_t fd;
@@ -288,16 +289,16 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr,
 	case KVM_DEV_VFIO_GROUP_ADD:
 		if (get_user(fd, argp))
 			return -EFAULT;
-		return kvm_vfio_group_add(dev, fd);
+		return kvm_vfio_file_add(dev, fd);
 
 	case KVM_DEV_VFIO_GROUP_DEL:
 		if (get_user(fd, argp))
 			return -EFAULT;
-		return kvm_vfio_group_del(dev, fd);
+		return kvm_vfio_file_del(dev, fd);
 
 #ifdef CONFIG_SPAPR_TCE_IOMMU
 	case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE:
-		return kvm_vfio_group_set_spapr_tce(dev, arg);
+		return kvm_vfio_file_set_spapr_tce(dev, arg);
 #endif
 	}
 
@@ -309,8 +310,8 @@ static int kvm_vfio_set_attr(struct kvm_device *dev,
 {
 	switch (attr->group) {
 	case KVM_DEV_VFIO_GROUP:
-		return kvm_vfio_set_group(dev, attr->attr,
-					  u64_to_user_ptr(attr->addr));
+		return kvm_vfio_set_file(dev, attr->attr,
+					 u64_to_user_ptr(attr->addr));
 	}
 
 	return -ENXIO;
@@ -339,16 +340,16 @@ static int kvm_vfio_has_attr(struct kvm_device *dev,
 static void kvm_vfio_release(struct kvm_device *dev)
 {
 	struct kvm_vfio *kv = dev->private;
-	struct kvm_vfio_group *kvg, *tmp;
+	struct kvm_vfio_file *kvf, *tmp;
 
-	list_for_each_entry_safe(kvg, tmp, &kv->group_list, node) {
+	list_for_each_entry_safe(kvf, tmp, &kv->file_list, node) {
 #ifdef CONFIG_SPAPR_TCE_IOMMU
-		kvm_spapr_tce_release_vfio_group(dev->kvm, kvg);
+		kvm_spapr_tce_release_vfio_group(dev->kvm, kvf);
 #endif
-		kvm_vfio_file_set_kvm(kvg->file, NULL);
-		fput(kvg->file);
-		list_del(&kvg->node);
-		kfree(kvg);
+		kvm_vfio_file_set_kvm(kvf->file, NULL);
+		fput(kvf->file);
+		list_del(&kvf->node);
+		kfree(kvf);
 		kvm_arch_end_assignment(dev->kvm);
 	}
 
@@ -382,7 +383,7 @@ static int kvm_vfio_create(struct kvm_device *dev, u32 type)
 	if (!kv)
 		return -ENOMEM;
 
-	INIT_LIST_HEAD(&kv->group_list);
+	INIT_LIST_HEAD(&kv->file_list);
 	mutex_init(&kv->lock);
 
 	dev->private = kv;