1 files changed, 33 insertions, 66 deletions

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index ac9a4e65ca49..87a13a7c8270 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -294,10 +294,13 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
 	 * pmd_trans_unstable) of the pmd.
 	 */
 	_pmd = READ_ONCE(*pmd);
-	if (!pmd_present(_pmd))
+	if (pmd_none(_pmd))
 		goto out;
 
 	ret = false;
+	if (!pmd_present(_pmd))
+		goto out;
+
 	if (pmd_trans_huge(_pmd))
 		goto out;
 
@@ -570,11 +573,14 @@ out:
 static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 					      struct userfaultfd_wait_queue *ewq)
 {
+	struct userfaultfd_ctx *release_new_ctx;
+
 	if (WARN_ON_ONCE(current->flags & PF_EXITING))
 		goto out;
 
 	ewq->ctx = ctx;
 	init_waitqueue_entry(&ewq->wq, current);
+	release_new_ctx = NULL;
 
 	spin_lock(&ctx->event_wqh.lock);
 	/*
@@ -601,8 +607,7 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 				new = (struct userfaultfd_ctx *)
 					(unsigned long)
 					ewq->msg.arg.reserved.reserved1;
-
-				userfaultfd_ctx_put(new);
+				release_new_ctx = new;
 			}
 			break;
 		}
@@ -617,6 +622,20 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 	__set_current_state(TASK_RUNNING);
 	spin_unlock(&ctx->event_wqh.lock);
 
+	if (release_new_ctx) {
+		struct vm_area_struct *vma;
+		struct mm_struct *mm = release_new_ctx->mm;
+
+		/* the various vma->vm_userfaultfd_ctx still points to it */
+		down_write(&mm->mmap_sem);
+		for (vma = mm->mmap; vma; vma = vma->vm_next)
+			if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx)
+				vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
+		up_write(&mm->mmap_sem);
+
+		userfaultfd_ctx_put(release_new_ctx);
+	}
+
 	/*
 	 * ctx may go away after this if the userfault pseudo fd is
 	 * already released.
@@ -921,10 +940,10 @@ static inline struct userfaultfd_wait_queue *find_userfault_evt(
 	return find_userfault_in(&ctx->event_wqh);
 }
 
-static unsigned int userfaultfd_poll(struct file *file, poll_table *wait)
+static __poll_t userfaultfd_poll(struct file *file, poll_table *wait)
 {
 	struct userfaultfd_ctx *ctx = file->private_data;
-	unsigned int ret;
+	__poll_t ret;
 
 	poll_wait(file, &ctx->fd_wqh, wait);
 
@@ -969,24 +988,14 @@ static int resolve_userfault_fork(struct userfaultfd_ctx *ctx,
 				  struct uffd_msg *msg)
 {
 	int fd;
-	struct file *file;
-	unsigned int flags = new->flags & UFFD_SHARED_FCNTL_FLAGS;
 
-	fd = get_unused_fd_flags(flags);
+	fd = anon_inode_getfd("[userfaultfd]", &userfaultfd_fops, new,
+			      O_RDWR | (new->flags & UFFD_SHARED_FCNTL_FLAGS));
 	if (fd < 0)
 		return fd;
 
-	file = anon_inode_getfile("[userfaultfd]", &userfaultfd_fops, new,
-				  O_RDWR | flags);
-	if (IS_ERR(file)) {
-		put_unused_fd(fd);
-		return PTR_ERR(file);
-	}
-
-	fd_install(fd, file);
 	msg->arg.reserved.reserved1 = 0;
 	msg->arg.fork.ufd = fd;
-
 	return 0;
 }
 
@@ -1868,24 +1877,10 @@ static void init_once_userfaultfd_ctx(void *mem)
 	seqcount_init(&ctx->refile_seq);
 }
 
-/**
- * userfaultfd_file_create - Creates a userfaultfd file pointer.
- * @flags: Flags for the userfaultfd file.
- *
- * This function creates a userfaultfd file pointer, w/out installing
- * it into the fd table. This is useful when the userfaultfd file is
- * used during the initialization of data structures that require
- * extra setup after the userfaultfd creation. So the userfaultfd
- * creation is split into the file pointer creation phase, and the
- * file descriptor installation phase.  In this way races with
- * userspace closing the newly installed file descriptor can be
- * avoided.  Returns a userfaultfd file pointer, or a proper error
- * pointer.
- */
-static struct file *userfaultfd_file_create(int flags)
+SYSCALL_DEFINE1(userfaultfd, int, flags)
 {
-	struct file *file;
 	struct userfaultfd_ctx *ctx;
+	int fd;
 
 	BUG_ON(!current->mm);
 
@@ -1893,14 +1888,12 @@ static struct file *userfaultfd_file_create(int flags)
 	BUILD_BUG_ON(UFFD_CLOEXEC != O_CLOEXEC);
 	BUILD_BUG_ON(UFFD_NONBLOCK != O_NONBLOCK);
 
-	file = ERR_PTR(-EINVAL);
 	if (flags & ~UFFD_SHARED_FCNTL_FLAGS)
-		goto out;
+		return -EINVAL;
 
-	file = ERR_PTR(-ENOMEM);
 	ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL);
 	if (!ctx)
-		goto out;
+		return -ENOMEM;
 
 	atomic_set(&ctx->refcount, 1);
 	ctx->flags = flags;
@@ -1911,39 +1904,13 @@ static struct file *userfaultfd_file_create(int flags)
 	/* prevent the mm struct to be freed */
 	mmgrab(ctx->mm);
 
-	file = anon_inode_getfile("[userfaultfd]", &userfaultfd_fops, ctx,
-				  O_RDWR | (flags & UFFD_SHARED_FCNTL_FLAGS));
-	if (IS_ERR(file)) {
+	fd = anon_inode_getfd("[userfaultfd]", &userfaultfd_fops, ctx,
+			      O_RDWR | (flags & UFFD_SHARED_FCNTL_FLAGS));
+	if (fd < 0) {
 		mmdrop(ctx->mm);
 		kmem_cache_free(userfaultfd_ctx_cachep, ctx);
 	}
-out:
-	return file;
-}
-
-SYSCALL_DEFINE1(userfaultfd, int, flags)
-{
-	int fd, error;
-	struct file *file;
-
-	error = get_unused_fd_flags(flags & UFFD_SHARED_FCNTL_FLAGS);
-	if (error < 0)
-		return error;
-	fd = error;
-
-	file = userfaultfd_file_create(flags);
-	if (IS_ERR(file)) {
-		error = PTR_ERR(file);
-		goto err_put_unused_fd;
-	}
-	fd_install(fd, file);
-
 	return fd;
-
-err_put_unused_fd:
-	put_unused_fd(fd);
-
-	return error;
 }
 
 static int __init userfaultfd_init(void)