Merge tag 'ovl-update-6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/overlayfs/vfs

Pull overlayfs updates from Amir Goldstein:

 - Fix a syzbot reported NULL pointer deref with bfs lower layers

 - Fix a copy up failure of large file from lower fuse fs

 - Followup cleanup of backing_file API from Miklos

 - Introduction and use of revert/override_creds_light() helpers, that
   were suggested by Christian as a mitigation to cache line bouncing
   and false sharing of fields in overlayfs creator_cred long lived
   struct cred copy.

 - Store up to two backing file references (upper and lower) in an
   ovl_file container instead of storing a single backing file in
   file->private_data.

   This is used to avoid the practice of opening a short lived backing
   file for the duration of some file operations and to avoid the
   specialized use of FDPUT_FPUT in such occasions, that was getting in
   the way of Al's fd_file() conversions.

* tag 'ovl-update-6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/overlayfs/vfs:
  ovl: Filter invalid inodes with missing lookup function
  ovl: convert ovl_real_fdget() callers to ovl_real_file()
  ovl: convert ovl_real_fdget_path() callers to ovl_real_file_path()
  ovl: store upper real file in ovl_file struct
  ovl: allocate a container struct ovl_file for ovl private context
  ovl: do not open non-data lower file for fsync
  ovl: Optimize override/revert creds
  ovl: pass an explicit reference of creators creds to callers
  ovl: use wrapper ovl_revert_creds()
  fs/backing-file: Convert to revert/override_creds_light()
  cred: Add a light version of override/revert_creds()
  backing-file: clean up the API
  ovl: properly handle large files in ovl_security_fileattr

9 files changed, 282 insertions, 187 deletions

diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index ee2cbd044ce6..3601ddfeddc2 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -1259,7 +1259,7 @@ static int ovl_copy_up_flags(struct dentry *dentry, int flags)
 		dput(parent);
 		dput(next);
 	}
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 
 	return err;
 }
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index ab65e98a1def..08e683917d12 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -553,15 +553,17 @@ out_cleanup:
 	goto out_dput;
 }
 
-static int ovl_setup_cred_for_create(struct dentry *dentry, struct inode *inode,
-				     umode_t mode, const struct cred *old_cred)
+static const struct cred *ovl_setup_cred_for_create(struct dentry *dentry,
+						    struct inode *inode,
+						    umode_t mode,
+						    const struct cred *old_cred)
 {
 	int err;
 	struct cred *override_cred;
 
 	override_cred = prepare_creds();
 	if (!override_cred)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	override_cred->fsuid = inode->i_uid;
 	override_cred->fsgid = inode->i_gid;
@@ -569,19 +571,26 @@ static int ovl_setup_cred_for_create(struct dentry *dentry, struct inode *inode,
 					      old_cred, override_cred);
 	if (err) {
 		put_cred(override_cred);
-		return err;
+		return ERR_PTR(err);
 	}
-	put_cred(override_creds(override_cred));
-	put_cred(override_cred);
 
-	return 0;
+	/*
+	 * Caller is going to match this with revert_creds_light() and drop
+	 * referenec on the returned creds.
+	 * We must be called with creator creds already, otherwise we risk
+	 * leaking creds.
+	 */
+	old_cred = override_creds_light(override_cred);
+	WARN_ON_ONCE(old_cred != ovl_creds(dentry->d_sb));
+
+	return override_cred;
 }
 
 static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
 			      struct ovl_cattr *attr, bool origin)
 {
 	int err;
-	const struct cred *old_cred;
+	const struct cred *old_cred, *new_cred = NULL;
 	struct dentry *parent = dentry->d_parent;
 
 	old_cred = ovl_override_creds(dentry->d_sb);
@@ -610,9 +619,13 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
 		 * create a new inode, so just use the ovl mounter's
 		 * fs{u,g}id.
 		 */
-		err = ovl_setup_cred_for_create(dentry, inode, attr->mode, old_cred);
-		if (err)
+		new_cred = ovl_setup_cred_for_create(dentry, inode, attr->mode,
+						     old_cred);
+		err = PTR_ERR(new_cred);
+		if (IS_ERR(new_cred)) {
+			new_cred = NULL;
 			goto out_revert_creds;
+		}
 	}
 
 	if (!ovl_dentry_is_whiteout(dentry))
@@ -621,7 +634,8 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
 		err = ovl_create_over_whiteout(dentry, inode, attr);
 
 out_revert_creds:
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
+	put_cred(new_cred);
 	return err;
 }
 
@@ -702,7 +716,7 @@ static int ovl_set_link_redirect(struct dentry *dentry)
 
 	old_cred = ovl_override_creds(dentry->d_sb);
 	err = ovl_set_redirect(dentry, false);
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 
 	return err;
 }
@@ -912,7 +926,7 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir)
 		err = ovl_remove_upper(dentry, is_dir, &list);
 	else
 		err = ovl_remove_and_whiteout(dentry, &list);
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 	if (!err) {
 		if (is_dir)
 			clear_nlink(dentry->d_inode);
@@ -1292,7 +1306,7 @@ out_dput_old:
 out_unlock:
 	unlock_rename(new_upperdir, old_upperdir);
 out_revert_creds:
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 	if (update_nlink)
 		ovl_nlink_end(new);
 	else
@@ -1306,18 +1320,22 @@ out:
 static int ovl_create_tmpfile(struct file *file, struct dentry *dentry,
 			      struct inode *inode, umode_t mode)
 {
-	const struct cred *old_cred;
+	const struct cred *old_cred, *new_cred = NULL;
 	struct path realparentpath;
 	struct file *realfile;
+	struct ovl_file *of;
 	struct dentry *newdentry;
 	/* It's okay to set O_NOATIME, since the owner will be current fsuid */
 	int flags = file->f_flags | OVL_OPEN_FLAGS;
 	int err;
 
 	old_cred = ovl_override_creds(dentry->d_sb);
-	err = ovl_setup_cred_for_create(dentry, inode, mode, old_cred);
-	if (err)
+	new_cred = ovl_setup_cred_for_create(dentry, inode, mode, old_cred);
+	err = PTR_ERR(new_cred);
+	if (IS_ERR(new_cred)) {
+		new_cred = NULL;
 		goto out_revert_creds;
+	}
 
 	ovl_path_upper(dentry->d_parent, &realparentpath);
 	realfile = backing_tmpfile_open(&file->f_path, flags, &realparentpath,
@@ -1327,17 +1345,25 @@ static int ovl_create_tmpfile(struct file *file, struct dentry *dentry,
 	if (err)
 		goto out_revert_creds;
 
+	of = ovl_file_alloc(realfile);
+	if (!of) {
+		fput(realfile);
+		err = -ENOMEM;
+		goto out_revert_creds;
+	}
+
 	/* ovl_instantiate() consumes the newdentry reference on success */
 	newdentry = dget(realfile->f_path.dentry);
 	err = ovl_instantiate(dentry, inode, newdentry, false, file);
 	if (!err) {
-		file->private_data = realfile;
+		file->private_data = of;
 	} else {
 		dput(newdentry);
-		fput(realfile);
+		ovl_file_free(of);
 	}
 out_revert_creds:
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
+	put_cred(new_cred);
 	return err;
 }
 
@@ -1389,7 +1415,7 @@ static int ovl_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
 put_realfile:
 	/* Without FMODE_OPENED ->release() won't be called on @file */
 	if (!(file->f_mode & FMODE_OPENED))
-		fput(file->private_data);
+		ovl_file_free(file->private_data);
 put_inode:
 	iput(inode);
 drop_write:
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 4444c78e2e0c..969b458100fe 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -51,7 +51,7 @@ static struct file *ovl_open_realfile(const struct file *file,
 		realfile = backing_file_open(&file->f_path, flags, realpath,
 					     current_cred());
 	}
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 
 	pr_debug("open(%p[%pD2/%c], 0%o) -> (%p, 0%o)\n",
 		 file, file, ovl_whatisit(inode, realinode), file->f_flags,
@@ -89,56 +89,110 @@ static int ovl_change_flags(struct file *file, unsigned int flags)
 	return 0;
 }
 
-static int ovl_real_fdget_meta(const struct file *file, struct fd *real,
-			       bool allow_meta)
+struct ovl_file {
+	struct file *realfile;
+	struct file *upperfile;
+};
+
+struct ovl_file *ovl_file_alloc(struct file *realfile)
 {
-	struct dentry *dentry = file_dentry(file);
-	struct file *realfile = file->private_data;
-	struct path realpath;
-	int err;
+	struct ovl_file *of = kzalloc(sizeof(struct ovl_file), GFP_KERNEL);
 
-	real->word = (unsigned long)realfile;
+	if (unlikely(!of))
+		return NULL;
 
-	if (allow_meta) {
-		ovl_path_real(dentry, &realpath);
-	} else {
-		/* lazy lookup and verify of lowerdata */
-		err = ovl_verify_lowerdata(dentry);
-		if (err)
-			return err;
+	of->realfile = realfile;
+	return of;
+}
 
-		ovl_path_realdata(dentry, &realpath);
-	}
-	if (!realpath.dentry)
-		return -EIO;
+void ovl_file_free(struct ovl_file *of)
+{
+	fput(of->realfile);
+	if (of->upperfile)
+		fput(of->upperfile);
+	kfree(of);
+}
 
-	/* Has it been copied up since we'd opened it? */
-	if (unlikely(file_inode(realfile) != d_inode(realpath.dentry))) {
-		struct file *f = ovl_open_realfile(file, &realpath);
-		if (IS_ERR(f))
-			return PTR_ERR(f);
-		real->word = (unsigned long)f | FDPUT_FPUT;
-		return 0;
+static bool ovl_is_real_file(const struct file *realfile,
+			     const struct path *realpath)
+{
+	return file_inode(realfile) == d_inode(realpath->dentry);
+}
+
+static struct file *ovl_real_file_path(const struct file *file,
+				       struct path *realpath)
+{
+	struct ovl_file *of = file->private_data;
+	struct file *realfile = of->realfile;
+
+	if (WARN_ON_ONCE(!realpath->dentry))
+		return ERR_PTR(-EIO);
+
+	/*
+	 * If the realfile that we want is not where the data used to be at
+	 * open time, either we'd been copied up, or it's an fsync of a
+	 * metacopied file.  We need the upperfile either way, so see if it
+	 * is already opened and if it is not then open and store it.
+	 */
+	if (unlikely(!ovl_is_real_file(realfile, realpath))) {
+		struct file *upperfile = READ_ONCE(of->upperfile);
+		struct file *old;
+
+		if (!upperfile) { /* Nobody opened upperfile yet */
+			upperfile = ovl_open_realfile(file, realpath);
+			if (IS_ERR(upperfile))
+				return upperfile;
+
+			/* Store the upperfile for later */
+			old = cmpxchg_release(&of->upperfile, NULL, upperfile);
+			if (old) { /* Someone opened upperfile before us */
+				fput(upperfile);
+				upperfile = old;
+			}
+		}
+		/*
+		 * Stored file must be from the right inode, unless someone's
+		 * been corrupting the upper layer.
+		 */
+		if (WARN_ON_ONCE(!ovl_is_real_file(upperfile, realpath)))
+			return ERR_PTR(-EIO);
+
+		realfile = upperfile;
 	}
 
 	/* Did the flags change since open? */
-	if (unlikely((file->f_flags ^ realfile->f_flags) & ~OVL_OPEN_FLAGS))
-		return ovl_change_flags(realfile, file->f_flags);
+	if (unlikely((file->f_flags ^ realfile->f_flags) & ~OVL_OPEN_FLAGS)) {
+		int err = ovl_change_flags(realfile, file->f_flags);
 
-	return 0;
+		if (err)
+			return ERR_PTR(err);
+	}
+
+	return realfile;
 }
 
-static int ovl_real_fdget(const struct file *file, struct fd *real)
+static struct file *ovl_real_file(const struct file *file)
 {
-	if (d_is_dir(file_dentry(file))) {
+	struct dentry *dentry = file_dentry(file);
+	struct path realpath;
+	int err;
+
+	if (d_is_dir(dentry)) {
 		struct file *f = ovl_dir_real_file(file, false);
-		if (IS_ERR(f))
-			return PTR_ERR(f);
-		real->word = (unsigned long)f;
-		return 0;
+
+		if (WARN_ON_ONCE(!f))
+			return ERR_PTR(-EIO);
+		return f;
 	}
 
-	return ovl_real_fdget_meta(file, real, false);
+	/* lazy lookup and verify of lowerdata */
+	err = ovl_verify_lowerdata(dentry);
+	if (err)
+		return ERR_PTR(err);
+
+	ovl_path_realdata(dentry, &realpath);
+
+	return ovl_real_file_path(file, &realpath);
 }
 
 static int ovl_open(struct inode *inode, struct file *file)
@@ -146,6 +200,7 @@ static int ovl_open(struct inode *inode, struct file *file)
 	struct dentry *dentry = file_dentry(file);
 	struct file *realfile;
 	struct path realpath;
+	struct ovl_file *of;
 	int err;
 
 	/* lazy lookup and verify lowerdata */
@@ -168,22 +223,27 @@ static int ovl_open(struct inode *inode, struct file *file)
 	if (IS_ERR(realfile))
 		return PTR_ERR(realfile);
 
-	file->private_data = realfile;
+	of = ovl_file_alloc(realfile);
+	if (!of) {
+		fput(realfile);
+		return -ENOMEM;
+	}
+
+	file->private_data = of;
 
 	return 0;
 }
 
 static int ovl_release(struct inode *inode, struct file *file)
 {
-	fput(file->private_data);
-
+	ovl_file_free(file->private_data);
 	return 0;
 }
 
 static loff_t ovl_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file_inode(file);
-	struct fd real;
+	struct file *realfile;
 	const struct cred *old_cred;
 	loff_t ret;
 
@@ -199,9 +259,9 @@ static loff_t ovl_llseek(struct file *file, loff_t offset, int whence)
 			return vfs_setpos(file, 0, 0);
 	}
 
-	ret = ovl_real_fdget(file, &real);
-	if (ret)
-		return ret;
+	realfile = ovl_real_file(file);
+	if (IS_ERR(realfile))
+		return PTR_ERR(realfile);
 
 	/*
 	 * Overlay file f_pos is the master copy that is preserved
@@ -211,17 +271,15 @@ static loff_t ovl_llseek(struct file *file, loff_t offset, int whence)
 	 * files, so we use the real file to perform seeks.
 	 */
 	ovl_inode_lock(inode);
-	fd_file(real)->f_pos = file->f_pos;
+	realfile->f_pos = file->f_pos;
 
 	old_cred = ovl_override_creds(inode->i_sb);
-	ret = vfs_llseek(fd_file(real), offset, whence);
-	revert_creds(old_cred);
+	ret = vfs_llseek(realfile, offset, whence);
+	ovl_revert_creds(old_cred);
 
-	file->f_pos = fd_file(real)->f_pos;
+	file->f_pos = realfile->f_pos;
 	ovl_inode_unlock(inode);
 
-	fdput(real);
-
 	return ret;
 }
 
@@ -231,9 +289,9 @@ static void ovl_file_modified(struct file *file)
 	ovl_copyattr(file_inode(file));
 }
 
-static void ovl_file_end_write(struct file *file, loff_t pos, ssize_t ret)
+static void ovl_file_end_write(struct kiocb *iocb, ssize_t ret)
 {
-	ovl_file_modified(file);
+	ovl_file_modified(iocb->ki_filp);
 }
 
 static void ovl_file_accessed(struct file *file)
@@ -267,38 +325,32 @@ static void ovl_file_accessed(struct file *file)
 static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct file *file = iocb->ki_filp;
-	struct fd real;
-	ssize_t ret;
+	struct file *realfile;
 	struct backing_file_ctx ctx = {
 		.cred = ovl_creds(file_inode(file)->i_sb),
-		.user_file = file,
 		.accessed = ovl_file_accessed,
 	};
 
 	if (!iov_iter_count(iter))
 		return 0;
 
-	ret = ovl_real_fdget(file, &real);
-	if (ret)
-		return ret;
-
-	ret = backing_file_read_iter(fd_file(real), iter, iocb, iocb->ki_flags,
-				     &ctx);
-	fdput(real);
+	realfile = ovl_real_file(file);
+	if (IS_ERR(realfile))
+		return PTR_ERR(realfile);
 
-	return ret;
+	return backing_file_read_iter(realfile, iter, iocb, iocb->ki_flags,
+				      &ctx);
 }
 
 static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
-	struct fd real;
+	struct file *realfile;
 	ssize_t ret;
 	int ifl = iocb->ki_flags;
 	struct backing_file_ctx ctx = {
 		.cred = ovl_creds(inode->i_sb),
-		.user_file = file,
 		.end_write = ovl_file_end_write,
 	};
 
@@ -309,8 +361,9 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 	/* Update mode */
 	ovl_copyattr(inode);
 
-	ret = ovl_real_fdget(file, &real);
-	if (ret)
+	realfile = ovl_real_file(file);
+	ret = PTR_ERR(realfile);
+	if (IS_ERR(realfile))
 		goto out_unlock;
 
 	if (!ovl_should_sync(OVL_FS(inode->i_sb)))
@@ -321,8 +374,7 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 	 * this property in case it is set by the issuer.
 	 */
 	ifl &= ~IOCB_DIO_CALLER_COMP;
-	ret = backing_file_write_iter(fd_file(real), iter, iocb, ifl, &ctx);
-	fdput(real);
+	ret = backing_file_write_iter(realfile, iter, iocb, ifl, &ctx);
 
 out_unlock:
 	inode_unlock(inode);
@@ -334,20 +386,22 @@ static ssize_t ovl_splice_read(struct file *in, loff_t *ppos,
 			       struct pipe_inode_info *pipe, size_t len,
 			       unsigned int flags)
 {
-	struct fd real;
+	struct file *realfile;
 	ssize_t ret;
 	struct backing_file_ctx ctx = {
 		.cred = ovl_creds(file_inode(in)->i_sb),
-		.user_file = in,
 		.accessed = ovl_file_accessed,
 	};
+	struct kiocb iocb;
 
-	ret = ovl_real_fdget(in, &real);
-	if (ret)
-		return ret;
+	realfile = ovl_real_file(in);
+	if (IS_ERR(realfile))
+		return PTR_ERR(realfile);
 
-	ret = backing_file_splice_read(fd_file(real), ppos, pipe, len, flags, &ctx);
-	fdput(real);
+	init_sync_kiocb(&iocb, in);
+	iocb.ki_pos = *ppos;
+	ret = backing_file_splice_read(realfile, &iocb, pipe, len, flags, &ctx);
+	*ppos = iocb.ki_pos;
 
 	return ret;
 }
@@ -355,7 +409,7 @@ static ssize_t ovl_splice_read(struct file *in, loff_t *ppos,
 /*
  * Calling iter_file_splice_write() directly from overlay's f_op may deadlock
  * due to lock order inversion between pipe->mutex in iter_file_splice_write()
- * and file_start_write(fd_file(real)) in ovl_write_iter().
+ * and file_start_write(realfile) in ovl_write_iter().
  *
  * So do everything ovl_write_iter() does and call iter_file_splice_write() on
  * the real file.
@@ -363,25 +417,28 @@ static ssize_t ovl_splice_read(struct file *in, loff_t *ppos,
 static ssize_t ovl_splice_write(struct pipe_inode_info *pipe, struct file *out,
 				loff_t *ppos, size_t len, unsigned int flags)
 {
-	struct fd real;
+	struct file *realfile;
 	struct inode *inode = file_inode(out);
 	ssize_t ret;
 	struct backing_file_ctx ctx = {
 		.cred = ovl_creds(inode->i_sb),
-		.user_file = out,
 		.end_write = ovl_file_end_write,
 	};
+	struct kiocb iocb;
 
 	inode_lock(inode);
 	/* Update mode */
 	ovl_copyattr(inode);
 
-	ret = ovl_real_fdget(out, &real);
-	if (ret)
+	realfile = ovl_real_file(out);
+	ret = PTR_ERR(realfile);
+	if (IS_ERR(realfile))
 		goto out_unlock;
 
-	ret = backing_file_splice_write(pipe, fd_file(real), ppos, len, flags, &ctx);
-	fdput(real);
+	init_sync_kiocb(&iocb, out);
+	iocb.ki_pos = *ppos;
+	ret = backing_file_splice_write(pipe, realfile, &iocb, len, flags, &ctx);
+	*ppos = iocb.ki_pos;
 
 out_unlock:
 	inode_unlock(inode);
@@ -391,7 +448,10 @@ out_unlock:
 
 static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 {
-	struct fd real;
+	struct dentry *dentry = file_dentry(file);
+	enum ovl_path_type type;
+	struct path upperpath;
+	struct file *upperfile;
 	const struct cred *old_cred;
 	int ret;
 
@@ -399,38 +459,38 @@ static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	if (ret <= 0)
 		return ret;
 
-	ret = ovl_real_fdget_meta(file, &real, !datasync);
-	if (ret)
-		return ret;
-
 	/* Don't sync lower file for fear of receiving EROFS error */
-	if (file_inode(fd_file(real)) == ovl_inode_upper(file_inode(file))) {
-		old_cred = ovl_override_creds(file_inode(file)->i_sb);
-		ret = vfs_fsync_range(fd_file(real), start, end, datasync);
-		revert_creds(old_cred);
-	}
+	type = ovl_path_type(dentry);
+	if (!OVL_TYPE_UPPER(type) || (datasync && OVL_TYPE_MERGE(type)))
+		return 0;
 
-	fdput(real);
+	ovl_path_upper(dentry, &upperpath);
+	upperfile = ovl_real_file_path(file, &upperpath);
+	if (IS_ERR(upperfile))
+		return PTR_ERR(upperfile);
+
+	old_cred = ovl_override_creds(file_inode(file)->i_sb);
+	ret = vfs_fsync_range(upperfile, start, end, datasync);
+	ovl_revert_creds(old_cred);
 
 	return ret;
 }
 
 static int ovl_mmap(struct file *file, struct vm_area_struct *vma)
 {
-	struct file *realfile = file->private_data;
+	struct ovl_file *of = file->private_data;
 	struct backing_file_ctx ctx = {
 		.cred = ovl_creds(file_inode(file)->i_sb),
-		.user_file = file,
 		.accessed = ovl_file_accessed,
 	};
 
-	return backing_file_mmap(realfile, vma, &ctx);
+	return backing_file_mmap(of->realfile, vma, &ctx);
 }
 
 static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 {
 	struct inode *inode = file_inode(file);
-	struct fd real;
+	struct file *realfile;
 	const struct cred *old_cred;
 	int ret;
 
@@ -441,19 +501,18 @@ static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len
 	if (ret)
 		goto out_unlock;
 
-	ret = ovl_real_fdget(file, &real);
-	if (ret)
+	realfile = ovl_real_file(file);
+	ret = PTR_ERR(realfile);
+	if (IS_ERR(realfile))
 		goto out_unlock;
 
 	old_cred = ovl_override_creds(file_inode(file)->i_sb);
-	ret = vfs_fallocate(fd_file(real), mode, offset, len);
-	revert_creds(old_cred);
+	ret = vfs_fallocate(realfile, mode, offset, len);
+	ovl_revert_creds(old_cred);
 
 	/* Update size */
 	ovl_file_modified(file);
 
-	fdput(real);
-
 out_unlock:
 	inode_unlock(inode);
 
@@ -462,19 +521,17 @@ out_unlock:
 
 static int ovl_fadvise(struct file *file, loff_t offset, loff_t len, int advice)
 {
-	struct fd real;
+	struct file *realfile;
 	const struct cred *old_cred;
 	int ret;
 
-	ret = ovl_real_fdget(file, &real);
-	if (ret)
-		return ret;
+	realfile = ovl_real_file(file);
+	if (IS_ERR(realfile))
+		return PTR_ERR(realfile);
 
 	old_cred = ovl_override_creds(file_inode(file)->i_sb);
-	ret = vfs_fadvise(fd_file(real), offset, len, advice);
-	revert_creds(old_cred);
-
-	fdput(real);
+	ret = vfs_fadvise(realfile, offset, len, advice);
+	ovl_revert_creds(old_cred);
 
 	return ret;
 }
@@ -490,7 +547,7 @@ static loff_t ovl_copyfile(struct file *file_in, loff_t pos_in,
 			    loff_t len, unsigned int flags, enum ovl_copyop op)
 {
 	struct inode *inode_out = file_inode(file_out);
-	struct fd real_in, real_out;
+	struct file *realfile_in, *realfile_out;
 	const struct cred *old_cred;
 	loff_t ret;
 
@@ -503,42 +560,39 @@ static loff_t ovl_copyfile(struct file *file_in, loff_t pos_in,
 			goto out_unlock;
 	}
 
-	ret = ovl_real_fdget(file_out, &real_out);
-	if (ret)
+	realfile_out = ovl_real_file(file_out);
+	ret = PTR_ERR(realfile_out);
+	if (IS_ERR(realfile_out))
 		goto out_unlock;
 
-	ret = ovl_real_fdget(file_in, &real_in);
-	if (ret) {
-		fdput(real_out);
+	realfile_in = ovl_real_file(file_in);
+	ret = PTR_ERR(realfile_in);
+	if (IS_ERR(realfile_in))
 		goto out_unlock;
-	}
 
 	old_cred = ovl_override_creds(file_inode(file_out)->i_sb);
 	switch (op) {
 	case OVL_COPY:
-		ret = vfs_copy_file_range(fd_file(real_in), pos_in,
-					  fd_file(real_out), pos_out, len, flags);
+		ret = vfs_copy_file_range(realfile_in, pos_in,
+					  realfile_out, pos_out, len, flags);
 		break;
 
 	case OVL_CLONE:
-		ret = vfs_clone_file_range(fd_file(real_in), pos_in,
-					   fd_file(real_out), pos_out, len, flags);
+		ret = vfs_clone_file_range(realfile_in, pos_in,
+					   realfile_out, pos_out, len, flags);
 		break;
 
 	case OVL_DEDUPE:
-		ret = vfs_dedupe_file_range_one(fd_file(real_in), pos_in,
-						fd_file(real_out), pos_out, len,
+		ret = vfs_dedupe_file_range_one(realfile_in, pos_in,
+						realfile_out, pos_out, len,
 						flags);
 		break;
 	}
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 
 	/* Update size */
 	ovl_file_modified(file_out);
 
-	fdput(real_in);
-	fdput(real_out);
-
 out_unlock:
 	inode_unlock(inode_out);
 
@@ -582,20 +636,19 @@ static loff_t ovl_remap_file_range(struct file *file_in, loff_t pos_in,
 
 static int ovl_flush(struct file *file, fl_owner_t id)
 {
-	struct fd real;
+	struct file *realfile;
 	const struct cred *old_cred;
-	int err;
+	int err = 0;
 
-	err = ovl_real_fdget(file, &real);
-	if (err)
-		return err;
+	realfile = ovl_real_file(file);
+	if (IS_ERR(realfile))
+		return PTR_ERR(realfile);
 
-	if (fd_file(real)->f_op->flush) {
+	if (realfile->f_op->flush) {
 		old_cred = ovl_override_creds(file_inode(file)->i_sb);
-		err = fd_file(real)->f_op->flush(fd_file(real), id);
-		revert_creds(old_cred);
+		err = realfile->f_op->flush(realfile, id);
+		ovl_revert_creds(old_cred);
 	}
-	fdput(real);
 
 	return err;
 }
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 8b31f44c12cd..6f0e15f86c21 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -80,7 +80,7 @@ int ovl_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		inode_lock(upperdentry->d_inode);
 		old_cred = ovl_override_creds(dentry->d_sb);
 		err = ovl_do_notify_change(ofs, upperdentry, attr);
-		revert_creds(old_cred);
+		ovl_revert_creds(old_cred);
 		if (!err)
 			ovl_copyattr(dentry->d_inode);
 		inode_unlock(upperdentry->d_inode);
@@ -280,7 +280,7 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path,
 		stat->nlink = dentry->d_inode->i_nlink;
 
 out:
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 
 	return err;
 }
@@ -317,7 +317,7 @@ int ovl_permission(struct mnt_idmap *idmap,
 		mask |= MAY_READ;
 	}
 	err = inode_permission(mnt_idmap(realpath.mnt), realinode, mask);
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 
 	return err;
 }
@@ -334,7 +334,7 @@ static const char *ovl_get_link(struct dentry *dentry,
 
 	old_cred = ovl_override_creds(dentry->d_sb);
 	p = vfs_get_link(ovl_dentry_real(dentry), done);
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 	return p;
 }
 
@@ -469,7 +469,7 @@ struct posix_acl *do_ovl_get_acl(struct mnt_idmap *idmap,
 
 		old_cred = ovl_override_creds(inode->i_sb);
 		acl = ovl_get_acl_path(&realpath, posix_acl_xattr_name(type), noperm);
-		revert_creds(old_cred);
+		ovl_revert_creds(old_cred);
 	}
 
 	return acl;
@@ -498,7 +498,7 @@ static int ovl_set_or_remove_acl(struct dentry *dentry, struct inode *inode,
 		old_cred = ovl_override_creds(dentry->d_sb);
 		real_acl = vfs_get_acl(mnt_idmap(realpath.mnt), realdentry,
 				       acl_name);
-		revert_creds(old_cred);
+		ovl_revert_creds(old_cred);
 		if (IS_ERR(real_acl)) {
 			err = PTR_ERR(real_acl);
 			goto out;
@@ -523,7 +523,7 @@ static int ovl_set_or_remove_acl(struct dentry *dentry, struct inode *inode,
 		err = ovl_do_set_acl(ofs, realdentry, acl_name, acl);
 	else
 		err = ovl_do_remove_acl(ofs, realdentry, acl_name);
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 	ovl_drop_write(dentry);
 
 	/* copy c/mtime */
@@ -600,7 +600,7 @@ static int ovl_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 
 	old_cred = ovl_override_creds(inode->i_sb);
 	err = realinode->i_op->fiemap(realinode, fieinfo, start, len);
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 
 	return err;
 }
@@ -616,8 +616,13 @@ static int ovl_security_fileattr(const struct path *realpath, struct fileattr *f
 	struct file *file;
 	unsigned int cmd;
 	int err;
+	unsigned int flags;
+
+	flags = O_RDONLY;
+	if (force_o_largefile())
+		flags |= O_LARGEFILE;
 
-	file = dentry_open(realpath, O_RDONLY, current_cred());
+	file = dentry_open(realpath, flags, current_cred());
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
@@ -671,7 +676,7 @@ int ovl_fileattr_set(struct mnt_idmap *idmap,
 		err = ovl_set_protattr(inode, upperpath.dentry, fa);
 		if (!err)
 			err = ovl_real_fileattr_set(&upperpath, fa);
-		revert_creds(old_cred);
+		ovl_revert_creds(old_cred);
 		ovl_drop_write(dentry);
 
 		/*
@@ -733,7 +738,7 @@ int ovl_fileattr_get(struct dentry *dentry, struct fileattr *fa)
 	old_cred = ovl_override_creds(inode->i_sb);
 	err = ovl_real_fileattr_get(&realpath, fa);
 	ovl_fileattr_prot_flags(inode, fa);
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 
 	return err;
 }
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index 5764f91d283e..7e27b7d4adee 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -961,7 +961,7 @@ static int ovl_maybe_validate_verity(struct dentry *dentry)
 		if (err == 0)
 			ovl_set_flag(OVL_VERIFIED_DIGEST, inode);
 
-		revert_creds(old_cred);
+		ovl_revert_creds(old_cred);
 	}
 
 	ovl_inode_unlock(inode);
@@ -995,7 +995,7 @@ static int ovl_maybe_lookup_lowerdata(struct dentry *dentry)
 
 	old_cred = ovl_override_creds(dentry->d_sb);
 	err = ovl_lookup_data_layers(dentry, redirect, &datapath);
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 	if (err)
 		goto out_err;
 
@@ -1342,7 +1342,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 
 	ovl_dentry_init_reval(dentry, upperdentry, OVL_I_E(inode));
 
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 	if (origin_path) {
 		dput(origin_path->dentry);
 		kfree(origin_path);
@@ -1366,7 +1366,7 @@ out_put_upper:
 	kfree(upperredirect);
 out:
 	kfree(d.redirect);
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 	return ERR_PTR(err);
 }
 
@@ -1423,7 +1423,7 @@ bool ovl_lower_positive(struct dentry *dentry)
 			dput(this);
 		}
 	}
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 
 	return positive;
 }
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 910dbbb2bb7b..b361f35762be 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -421,6 +421,7 @@ int ovl_want_write(struct dentry *dentry);
 void ovl_drop_write(struct dentry *dentry);
 struct dentry *ovl_workdir(struct dentry *dentry);
 const struct cred *ovl_override_creds(struct super_block *sb);
+void ovl_revert_creds(const struct cred *old_cred);
 
 static inline const struct cred *ovl_creds(struct super_block *sb)
 {
@@ -854,6 +855,9 @@ int ovl_real_fileattr_set(const struct path *realpath, struct fileattr *fa);
 int ovl_fileattr_get(struct dentry *dentry, struct fileattr *fa);
 int ovl_fileattr_set(struct mnt_idmap *idmap,
 		     struct dentry *dentry, struct fileattr *fa);
+struct ovl_file;
+struct ovl_file *ovl_file_alloc(struct file *realfile);
+void ovl_file_free(struct ovl_file *of);
 
 /* copy_up.c */
 int ovl_copy_up(struct dentry *dentry);
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 0ca8af060b0c..881ec5592da5 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -290,7 +290,7 @@ static int ovl_check_whiteouts(const struct path *path, struct ovl_readdir_data
 		}
 		inode_unlock(dir->d_inode);
 	}
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 
 	return err;
 }
@@ -808,7 +808,7 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx)
 	}
 	err = 0;
 out:
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 	return err;
 }
 
@@ -860,7 +860,7 @@ static struct file *ovl_dir_open_realfile(const struct file *file,
 
 	old_cred = ovl_override_creds(file_inode(file)->i_sb);
 	res = ovl_path_open(realpath, O_RDONLY | (file->f_flags & O_LARGEFILE));
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 
 	return res;
 }
@@ -987,7 +987,7 @@ int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list)
 
 	old_cred = ovl_override_creds(dentry->d_sb);
 	err = ovl_dir_read_merged(dentry, list, &root);
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 	if (err)
 		return err;
 
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index edc9216f6e27..9aa7493b1e10 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -65,7 +65,12 @@ const struct cred *ovl_override_creds(struct super_block *sb)
 {
 	struct ovl_fs *ofs = OVL_FS(sb);
 
-	return override_creds(ofs->creator_cred);
+	return override_creds_light(ofs->creator_cred);
+}
+
+void ovl_revert_creds(const struct cred *old_cred)
+{
+	revert_creds_light(old_cred);
 }
 
 /*
@@ -197,6 +202,9 @@ void ovl_dentry_init_flags(struct dentry *dentry, struct dentry *upperdentry,
 
 bool ovl_dentry_weird(struct dentry *dentry)
 {
+	if (!d_can_lookup(dentry) && !d_is_file(dentry) && !d_is_symlink(dentry))
+		return true;
+
 	return dentry->d_flags & (DCACHE_NEED_AUTOMOUNT |
 				  DCACHE_MANAGE_TRANSIT |
 				  DCACHE_OP_HASH |
@@ -1178,7 +1186,7 @@ int ovl_nlink_start(struct dentry *dentry)
 	 * value relative to the upper inode nlink in an upper inode xattr.
 	 */
 	err = ovl_set_nlink_upper(dentry);
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 	if (err)
 		goto out_drop_write;
 
@@ -1203,7 +1211,7 @@ void ovl_nlink_end(struct dentry *dentry)
 
 		old_cred = ovl_override_creds(dentry->d_sb);
 		ovl_cleanup_index(dentry);
-		revert_creds(old_cred);
+		ovl_revert_creds(old_cred);
 	}
 
 	ovl_inode_unlock(inode);
diff --git a/fs/overlayfs/xattrs.c b/fs/overlayfs/xattrs.c
index 383978e4663c..88055deca936 100644
--- a/fs/overlayfs/xattrs.c
+++ b/fs/overlayfs/xattrs.c
@@ -47,7 +47,7 @@ static int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char
 		ovl_path_lower(dentry, &realpath);
 		old_cred = ovl_override_creds(dentry->d_sb);
 		err = vfs_getxattr(mnt_idmap(realpath.mnt), realdentry, name, NULL, 0);
-		revert_creds(old_cred);
+		ovl_revert_creds(old_cred);
 		if (err < 0)
 			goto out;
 	}
@@ -72,7 +72,7 @@ static int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char
 		WARN_ON(flags != XATTR_REPLACE);
 		err = ovl_do_removexattr(ofs, realdentry, name);
 	}
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 	ovl_drop_write(dentry);
 
 	/* copy c/mtime */
@@ -91,7 +91,7 @@ static int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char
 	ovl_i_path_real(inode, &realpath);
 	old_cred = ovl_override_creds(dentry->d_sb);
 	res = vfs_getxattr(mnt_idmap(realpath.mnt), realpath.dentry, name, value, size);
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 	return res;
 }
 
@@ -121,7 +121,7 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
 
 	old_cred = ovl_override_creds(dentry->d_sb);
 	res = vfs_listxattr(realdentry, list, size);
-	revert_creds(old_cred);
+	ovl_revert_creds(old_cred);
 	if (res <= 0 || size == 0)
 		return res;
 
@@ -268,4 +268,3 @@ const struct xattr_handler * const *ovl_xattr_handlers(struct ovl_fs *ofs)
 	return ofs->config.userxattr ? ovl_user_xattr_handlers :
 		ovl_trusted_xattr_handlers;
 }
-