Merge tag 'vfs-7.3-rc1.lookup' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs lookup updates from Christian Brauner:
 "This refactors lookup_open() and adds vfs_lookup_open() for nfsd.

  mnt_want_write() and parent locking are moved into lookup_open()
  itself.

  audit_inode_child() is also now called in lookup_open() on failure.
  That is the calling convention in vfs_create() and vfs_mkdir(), but
  lookup_open() made no such call when atomic_open() should have created
  a file and did not. And neither did the regular ->create() path fwiw.

  This also contains work to remove the unneeded excl argument from the
  ->create() inode op"

* tag 'vfs-7.3-rc1.lookup' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  fs/namei.c: fix coding style in atomic_open() and lookup_open()
  fs/namei.c: fix kerneldoc of atomic_open() and vfs_lookup_open()
  fs/namei.c: update stale comments in lookup_open()
  Remove excl arg to ->create inode_operation
  fs/namei.c: update kerneldoc of atomic_open()
  vfs: call audit_inode_child() in lookup_open() on failure
  vfs: move create error && negative dentry case in lookup_open() up
  VFS: add vfs_lookup_open() for nfsd
  VFS: move delegated_inode retry loop into lookup_open()
  VFS: move mnt_want_write() and locking into lookup_open()

Documentation/filesystems/locking.rst

@@ -61,7 +61,7 @@ inode_operations
 
 prototypes::
 
-	int (*create) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t, bool);
+	int (*create) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t);
 	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
 	int (*link) (struct dentry *,struct inode *,struct dentry *);
 	int (*unlink) (struct inode *,struct dentry *);

Documentation/filesystems/porting.rst

@@ -1401,3 +1401,11 @@ as with d_dispose_if_unused() these are not trivial; with this variant
 of API it's more explicit, since grabbing ->d_lock is caller-side, but
 d_dispose_if_unused() had all the same issues.  It's a low-level primitive;
 use only if you have no alternative.
+
+---
+
+**mandatory**
+
+The .create inode_operation no longer receives the 'excl' arg.  It must
+always assume the file does not already exist.  If the filesystem needs
+to be involved in non-exclusive create, it should provide atomic_open.

Documentation/filesystems/vfs.rst

@@ -415,7 +415,7 @@ As of kernel 2.6.22, the following members are defined:
 .. code-block:: c
 
 	struct inode_operations {
-		int (*create) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t, bool);
+		int (*create) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t);
 		struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
 		int (*link) (struct dentry *,struct inode *,struct dentry *);
 		int (*unlink) (struct inode *,struct dentry *);

fs/9p/vfs_inode.c

@@ -645,7 +645,6 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
  * @dir: The parent directory
  * @dentry: The name of file to be created
  * @mode: The UNIX file mode to set
- * @excl: True if the file must not yet exist
  *
  * open(.., O_CREAT) is handled in v9fs_vfs_atomic_open().  This is only called
  * for mknod(2).
@@ -654,7 +653,7 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 
 static int
 v9fs_vfs_create(struct mnt_idmap *idmap, struct inode *dir,
-		struct dentry *dentry, umode_t mode, bool excl)
+		struct dentry *dentry, umode_t mode)
 {
 	struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir);
 	u32 perm = unixmode2p9mode(v9ses, mode);

fs/9p/vfs_inode_dotl.c

@@ -213,12 +213,11 @@ int v9fs_open_to_dotl_flags(int flags)
  * @dir: directory inode that is being created
  * @dentry:  dentry that is being deleted
  * @omode: create permissions
- * @excl: True if the file must not yet exist
  *
  */
 static int
 v9fs_vfs_create_dotl(struct mnt_idmap *idmap, struct inode *dir,
-		     struct dentry *dentry, umode_t omode, bool excl)
+		     struct dentry *dentry, umode_t omode)
 {
 	return v9fs_vfs_mknod_dotl(idmap, dir, dentry, omode, 0);
 }

fs/affs/affs.h

@@ -169,7 +169,7 @@ extern int	affs_hash_name(struct super_block *sb, const u8 *name, unsigned int l
 extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int);
 extern int	affs_unlink(struct inode *dir, struct dentry *dentry);
 extern int	affs_create(struct mnt_idmap *idmap, struct inode *dir,
-			struct dentry *dentry, umode_t mode, bool);
+			struct dentry *dentry, umode_t mode);
 extern struct dentry *affs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 			struct dentry *dentry, umode_t mode);
 extern int	affs_rmdir(struct inode *dir, struct dentry *dentry);

fs/affs/namei.c

@@ -243,7 +243,7 @@ affs_unlink(struct inode *dir, struct dentry *dentry)
 
 int
 affs_create(struct mnt_idmap *idmap, struct inode *dir,
-	    struct dentry *dentry, umode_t mode, bool excl)
+	    struct dentry *dentry, umode_t mode)
 {
 	struct super_block *sb = dir->i_sb;
 	struct inode	*inode;

fs/afs/dir.c

@@ -34,7 +34,7 @@ static bool afs_lookup_filldir(struct dir_context *ctx, const char *name, int nl
 			       u64 ino, u32 uniquifier);
 #define AFS_LOOKUP ((filldir_t)0x137UL)
 static int afs_create(struct mnt_idmap *idmap, struct inode *dir,
-		      struct dentry *dentry, umode_t mode, bool excl);
+		      struct dentry *dentry, umode_t mode);
 static struct dentry *afs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 				struct dentry *dentry, umode_t mode);
 static int afs_rmdir(struct inode *dir, struct dentry *dentry);
@@ -1633,7 +1633,7 @@ static const struct afs_operation_ops afs_create_operation = {
  * create a regular file on an AFS filesystem
  */
 static int afs_create(struct mnt_idmap *idmap, struct inode *dir,
-		      struct dentry *dentry, umode_t mode, bool excl)
+		      struct dentry *dentry, umode_t mode)
 {
 	struct afs_operation *op;
 	struct afs_vnode *dvnode = AFS_FS_I(dir);

fs/bad_inode.c

@@ -29,7 +29,7 @@ static const struct file_operations bad_file_ops =
 
 static int bad_inode_create(struct mnt_idmap *idmap,
 			    struct inode *dir, struct dentry *dentry,
-			    umode_t mode, bool excl)
+			    umode_t mode)
 {
 	return -EIO;
 }

fs/bfs/dir.c

@@ -83,7 +83,7 @@ const struct file_operations bfs_dir_operations = {
 };
 
 static int bfs_create(struct mnt_idmap *idmap, struct inode *dir,
-		      struct dentry *dentry, umode_t mode, bool excl)
+		      struct dentry *dentry, umode_t mode)
 {
 	int err;
 	struct inode *inode;

fs/btrfs/inode.c

@@ -7007,7 +7007,7 @@ static int btrfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 }
 
 static int btrfs_create(struct mnt_idmap *idmap, struct inode *dir,
-			struct dentry *dentry, umode_t mode, bool excl)
+			struct dentry *dentry, umode_t mode)
 {
 	struct inode *inode;
 

fs/ceph/dir.c

@@ -983,7 +983,7 @@ static int ceph_mknod(struct mnt_idmap *idmap, struct inode *dir,
 }
 
 static int ceph_create(struct mnt_idmap *idmap, struct inode *dir,
-		       struct dentry *dentry, umode_t mode, bool excl)
+		       struct dentry *dentry, umode_t mode)
 {
 	return ceph_mknod(idmap, dir, dentry, mode, 0);
 }

fs/coda/dir.c

@@ -134,7 +134,7 @@ static inline void coda_dir_drop_nlink(struct inode *dir)
 
 /* creation routines: create, mknod, mkdir, link, symlink */
 static int coda_create(struct mnt_idmap *idmap, struct inode *dir,
-		       struct dentry *de, umode_t mode, bool excl)
+		       struct dentry *de, umode_t mode)
 {
 	int error;
 	const char *name=de->d_name.name;

fs/ecryptfs/inode.c

@@ -268,7 +268,7 @@ int ecryptfs_initialize_file(struct dentry *ecryptfs_dentry,
 static int
 ecryptfs_create(struct mnt_idmap *idmap,
 		struct inode *directory_inode, struct dentry *ecryptfs_dentry,
-		umode_t mode, bool excl)
+		umode_t mode)
 {
 	struct inode *ecryptfs_inode;
 	int rc;

fs/efivarfs/inode.c

@@ -75,7 +75,7 @@ static bool efivarfs_valid_name(const char *str, int len)
 }
 
 static int efivarfs_create(struct mnt_idmap *idmap, struct inode *dir,
-			   struct dentry *dentry, umode_t mode, bool excl)
+			   struct dentry *dentry, umode_t mode)
 {
 	struct inode *inode = NULL;
 	struct efivar_entry *var;

fs/exfat/namei.c

@@ -538,7 +538,7 @@ static int exfat_add_entry(struct inode *inode, const char *path,
 }
 
 static int exfat_create(struct mnt_idmap *idmap, struct inode *dir,
-			struct dentry *dentry, umode_t mode, bool excl)
+			struct dentry *dentry, umode_t mode)
 {
 	struct super_block *sb = dir->i_sb;
 	struct inode *inode;

fs/ext2/namei.c

@@ -99,7 +99,7 @@ struct dentry *ext2_get_parent(struct dentry *child)
  */
 static int ext2_create (struct mnt_idmap * idmap,
 			struct inode * dir, struct dentry * dentry,
-			umode_t mode, bool excl)
+			umode_t mode)
 {
 	struct inode *inode;
 	int err;

fs/ext4/namei.c

@@ -2811,7 +2811,7 @@ static int ext4_add_nondir(handle_t *handle,
  * with d_instantiate().
  */
 static int ext4_create(struct mnt_idmap *idmap, struct inode *dir,
-		       struct dentry *dentry, umode_t mode, bool excl)
+		       struct dentry *dentry, umode_t mode)
 {
 	handle_t *handle;
 	struct inode *inode;

fs/f2fs/namei.c

@@ -366,7 +366,7 @@ static struct inode *f2fs_new_inode(struct mnt_idmap *idmap,
 }
 
 static int f2fs_create(struct mnt_idmap *idmap, struct inode *dir,
-		       struct dentry *dentry, umode_t mode, bool excl)
+		       struct dentry *dentry, umode_t mode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
 	struct f2fs_lock_context lc;

fs/fat/namei_msdos.c

@@ -265,7 +265,7 @@ static int msdos_add_entry(struct inode *dir, const unsigned char *name,
 
 /***** Create a file */
 static int msdos_create(struct mnt_idmap *idmap, struct inode *dir,
-			struct dentry *dentry, umode_t mode, bool excl)
+			struct dentry *dentry, umode_t mode)
 {
 	struct super_block *sb = dir->i_sb;
 	struct inode *inode = NULL;

fs/fat/namei_vfat.c

@@ -755,7 +755,7 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
 }
 
 static int vfat_create(struct mnt_idmap *idmap, struct inode *dir,
-		       struct dentry *dentry, umode_t mode, bool excl)
+		       struct dentry *dentry, umode_t mode)
 {
 	struct super_block *sb = dir->i_sb;
 	struct inode *inode;

fs/fuse/dir.c

@@ -1084,7 +1084,7 @@ static int fuse_mknod(struct mnt_idmap *idmap, struct inode *dir,
 }
 
 static int fuse_create(struct mnt_idmap *idmap, struct inode *dir,
-		       struct dentry *entry, umode_t mode, bool excl)
+		       struct dentry *entry, umode_t mode)
 {
 	return fuse_mknod(idmap, dir, entry, mode, 0);
 }

fs/gfs2/inode.c

@@ -963,15 +963,14 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
  * @dir: The directory in which to create the file
  * @dentry: The dentry of the new file
  * @mode: The mode of the new file
- * @excl: Force fail if inode exists
  *
  * Returns: errno
  */
 
 static int gfs2_create(struct mnt_idmap *idmap, struct inode *dir,
-		       struct dentry *dentry, umode_t mode, bool excl)
+		       struct dentry *dentry, umode_t mode)
 {
-	return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, excl);
+	return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, 1);
 }
 
 /**

fs/hfs/dir.c

@@ -184,7 +184,7 @@ static int hfs_dir_release(struct inode *inode, struct file *file)
  * the directory and the name (and its length) of the new file.
  */
 static int hfs_create(struct mnt_idmap *idmap, struct inode *dir,
-		      struct dentry *dentry, umode_t mode, bool excl)
+		      struct dentry *dentry, umode_t mode)
 {
 	struct inode *inode;
 	int res;

fs/hfsplus/dir.c

@@ -562,7 +562,7 @@ static int hfsplus_mknod(struct mnt_idmap *idmap, struct inode *dir,
 }
 
 static int hfsplus_create(struct mnt_idmap *idmap, struct inode *dir,
-			  struct dentry *dentry, umode_t mode, bool excl)
+			  struct dentry *dentry, umode_t mode)
 {
 	return hfsplus_mknod(&nop_mnt_idmap, dir, dentry, mode, 0);
 }

fs/hostfs/hostfs_kern.c

@@ -593,7 +593,7 @@ static struct inode *hostfs_iget(struct super_block *sb, char *name)
 }
 
 static int hostfs_create(struct mnt_idmap *idmap, struct inode *dir,
-			 struct dentry *dentry, umode_t mode, bool excl)
+			 struct dentry *dentry, umode_t mode)
 {
 	struct inode *inode;
 	char *name;

fs/hpfs/namei.c

@@ -129,7 +129,7 @@ static struct dentry *hpfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 }
 
 static int hpfs_create(struct mnt_idmap *idmap, struct inode *dir,
-		       struct dentry *dentry, umode_t mode, bool excl)
+		       struct dentry *dentry, umode_t mode)
 {
 	const unsigned char *name = dentry->d_name.name;
 	unsigned len = dentry->d_name.len;

fs/hugetlbfs/inode.c

@@ -979,7 +979,7 @@ static struct dentry *hugetlbfs_mkdir(struct mnt_idmap *idmap, struct inode *dir
 
 static int hugetlbfs_create(struct mnt_idmap *idmap,
 			    struct inode *dir, struct dentry *dentry,
-			    umode_t mode, bool excl)
+			    umode_t mode)
 {
 	return hugetlbfs_mknod(idmap, dir, dentry, mode | S_IFREG, 0);
 }

fs/jffs2/dir.c

@@ -26,7 +26,7 @@
 static int jffs2_readdir (struct file *, struct dir_context *);
 
 static int jffs2_create (struct mnt_idmap *, struct inode *,
-		         struct dentry *, umode_t, bool);
+		         struct dentry *, umode_t);
 static struct dentry *jffs2_lookup (struct inode *,struct dentry *,
 				    unsigned int);
 static int jffs2_link (struct dentry *,struct inode *,struct dentry *);
@@ -163,7 +163,7 @@ static int jffs2_readdir(struct file *file, struct dir_context *ctx)
 
 
 static int jffs2_create(struct mnt_idmap *idmap, struct inode *dir_i,
-			struct dentry *dentry, umode_t mode, bool excl)
+			struct dentry *dentry, umode_t mode)
 {
 	struct jffs2_raw_inode *ri;
 	struct jffs2_inode_info *f, *dir_f;

fs/jfs/namei.c

@@ -61,7 +61,7 @@ static inline void free_ea_wmap(struct inode *inode)
  *
  */
 static int jfs_create(struct mnt_idmap *idmap, struct inode *dip,
-		      struct dentry *dentry, umode_t mode, bool excl)
+		      struct dentry *dentry, umode_t mode)
 {
 	int rc = 0;
 	tid_t tid;		/* transaction id */

fs/minix/namei.c

@@ -64,7 +64,7 @@ static int minix_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
 }
 
 static int minix_create(struct mnt_idmap *idmap, struct inode *dir,
-			struct dentry *dentry, umode_t mode, bool excl)
+			struct dentry *dentry, umode_t mode)
 {
 	return minix_mknod(&nop_mnt_idmap, dir, dentry, mode, 0);
 }

fs/namei.c

@@ -4199,7 +4199,7 @@ int vfs_create(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode,
 	error = try_break_deleg(dir, LEASE_BREAK_DIR_CREATE, di);
 	if (error)
 		return error;
-	error = dir->i_op->create(idmap, dir, dentry, mode, true);
+	error = dir->i_op->create(idmap, dir, dentry, mode);
 	if (!error)
 		fsnotify_create(dir, dentry);
 	return error;
@@ -4336,50 +4336,83 @@ static int may_o_create(struct mnt_idmap *idmap,
 	return security_inode_create(dir->dentry->d_inode, dentry, mode);
 }
 
-/*
- * Attempt to atomically look up, create and open a file from a negative
- * dentry.
+/**
+ * atomic_open() - atomically look up, create and open a file
+ * @path:          parent directory path
+ * @dentry:        child to ->atomic_open()
+ * @file:          file to attach child to
+ * @open_flag:     open flags
+ * @mode:          create mode
+ * @create_error:  return value from may_o_create()
  *
- * Returns 0 if successful.  The file will have been created and attached to
- * @file by the filesystem calling finish_open().
+ * Attempt to look up, create and open @dentry, which must be negative, in a
+ * single call into the filesystem.
  *
- * If the file was looked up only or didn't need creating, FMODE_OPENED won't
- * be set.  The caller will need to perform the open themselves.  @path will
- * have been updated to point to the new dentry.  This may be negative.
+ * If a non-error dentry is returned then: when FMODE_OPENED is set,
+ * the file will have been attached to @file by the filesystem calling
+ * finish_open(). If FMODE_OPENED isn't set, the filesystem instead called
+ * finish_no_open() and the caller will need to perform the open themselves.
  *
- * Returns an error code otherwise.
+ * FMODE_CREATED is set when the call to ->atomic_open() actually created
+ * the file.
+ *
+ * Returns: the opened or looked-up dentry, or ERR_PTR() on failure.  The
+ * reference to @dentry is consumed in either case.
  */
 static struct dentry *atomic_open(const struct path *path, struct dentry *dentry,
 				  struct file *file,
-				  int open_flag, umode_t mode)
+				  int open_flag, umode_t mode, int create_error)
 {
 	struct dentry *const DENTRY_NOT_SET = (void *) -1UL;
-	struct inode *dir =  path->dentry->d_inode;
+	struct inode *dir_inode = path->dentry->d_inode;
 	int error;
 
 	file->__f_path.dentry = DENTRY_NOT_SET;
 	file->__f_path.mnt = path->mnt;
-	error = dir->i_op->atomic_open(dir, dentry, file,
+	error = dir_inode->i_op->atomic_open(dir_inode, dentry, file,
 				       open_to_namei_flags(open_flag), mode);
 	d_lookup_done(dentry);
+
 	if (!error) {
 		if (file->f_mode & FMODE_OPENED) {
-			if (unlikely(dentry != file->f_path.dentry)) {
+			/* finish_open() called */
+			struct dentry *opened = file->f_path.dentry;
+
+			if (unlikely(opened != dentry)) {
 				dput(dentry);
-				dentry = dget(file->f_path.dentry);
+				dentry = dget(opened);
 			}
-		} else if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) {
-			error = -EIO;
-		} else {
-			if (file->f_path.dentry) {
+		} else if (likely(file->f_path.dentry != DENTRY_NOT_SET)) {
+			/* finish_no_open() called */
+			struct dentry *replaced = file->f_path.dentry;
+
+			if (replaced) {
 				dput(dentry);
-				dentry = file->f_path.dentry;
+				dentry = replaced;
 			}
 			if (unlikely(d_is_negative(dentry)))
 				error = -ENOENT;
+		} else {
+			const char *fsname = dentry->d_sb->s_type->name;
+
+			WARN(1, "%s: ->atomic_open() left file->f_path.dentry unset!\n",
+			     fsname);
+			error = -EIO;
 		}
 	}
+
 	if (error) {
+		if (unlikely(create_error) && error == -ENOENT) {
+			/*
+			 * Should have done a create, but errored before.
+			 * Some filesystems return -ENOENT directly instead of
+			 * calling finish_no_open() with a negative dentry;
+			 * either way it should only mean the child doesn't exist,
+			 * so a refused create is safe to record here.
+			 */
+			audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE);
+			error = create_error;
+		}
 		dput(dentry);
 		dentry = ERR_PTR(error);
 	}
@@ -4389,32 +4422,52 @@ static struct dentry *atomic_open(const struct path *path, struct dentry *dentry
 /*
  * Look up and maybe create and open the last component.
  *
- * Must be called with parent locked (exclusive in O_CREAT case).
+ * Takes the parent inode lock itself, exclusive if O_CREAT was requested and
+ * shared otherwise, and drops it again before returning.  The caller must not
+ * hold it.
  *
- * Returns 0 on success, that is, if
- *  the file was successfully atomically created (if necessary) and opened, or
- *  the file was not completely opened at this time, though lookups and
- *  creations were performed.
- * These case are distinguished by presence of FMODE_OPENED on file->f_mode.
- * In the latter case dentry returned in @path might be negative if O_CREAT
- * hadn't been specified.
+ * On success returns the dentry of the last component.  If FMODE_OPENED is set
+ * on file->f_mode the file was also opened and attached to @file; otherwise
+ * only lookup and creation were performed and the caller has to open it.  In
+ * the latter case the dentry may be negative if O_CREAT hadn't been specified.
  *
- * An error code is returned on failure.
+ * Returns ERR_PTR() on failure.
  */
 static struct dentry *lookup_open(struct nameidata *nd, struct file *file,
-				  const struct open_flags *op,
-				  bool got_write, struct delegated_inode *delegated_inode)
+				  const struct open_flags *op)
 {
+	struct delegated_inode delegated_inode = { };
 	struct mnt_idmap *idmap;
 	struct dentry *dir = nd->path.dentry;
 	struct inode *dir_inode = dir->d_inode;
-	int open_flag = op->open_flag;
+	int open_flag;
 	struct dentry *dentry;
-	int error, create_error = 0;
-	umode_t mode = op->mode;
+	int error, create_error;
+	umode_t mode;
+	bool got_write;
 
-	if (unlikely(IS_DEADDIR(dir_inode)))
-		return ERR_PTR(-ENOENT);
+retry:
+	open_flag = op->open_flag;
+	got_write = false;
+	mode = op->mode;
+	create_error = 0;
+
+	if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) {
+		got_write = !mnt_want_write(nd->path.mnt);
+		/*
+		 * do _not_ fail yet - we might not need that or fail with
+		 * a different error; we'll be dropping this one anyway.
+		 */
+	}
+	if (open_flag & O_CREAT)
+		inode_lock(dir_inode);
+	else
+		inode_lock_shared(dir_inode);
+
+	if (unlikely(IS_DEADDIR(dir_inode))) {
+		dentry = ERR_PTR(-ENOENT);
+		goto out;
+	}
 
 	file->f_mode &= ~FMODE_CREATED;
 	dentry = d_lookup(dir, &nd->last);
@@ -4422,7 +4475,7 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file,
 		if (!dentry) {
 			dentry = d_alloc_parallel(dir, &nd->last);
 			if (IS_ERR(dentry))
-				return dentry;
+				goto out;
 		}
 		if (d_in_lookup(dentry))
 			break;
@@ -4437,8 +4490,8 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file,
 		dentry = NULL;
 	}
 	if (dentry->d_inode) {
-		/* Cached positive dentry: will open in f_op->open */
-		return dentry;
+		/* Cached positive dentry: will open in do_open(). */
+		goto out;
 	}
 
 	if (open_flag & O_CREAT)
@@ -4459,7 +4512,7 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file,
 	if (open_flag & O_CREAT) {
 		if (open_flag & O_EXCL)
 			open_flag &= ~O_TRUNC;
-		mode = vfs_prepare_mode(idmap, dir->d_inode, mode, mode, mode);
+		mode = vfs_prepare_mode(idmap, dir_inode, mode, mode, mode);
 		if (likely(got_write))
 			create_error = may_o_create(idmap, &nd->path,
 						    dentry, mode);
@@ -4471,10 +4524,9 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file,
 	if (dir_inode->i_op->atomic_open) {
 		if (nd->flags & LOOKUP_DIRECTORY)
 			open_flag |= O_DIRECTORY;
-		dentry = atomic_open(&nd->path, dentry, file, open_flag, mode);
-		if (unlikely(create_error) && dentry == ERR_PTR(-ENOENT))
-			dentry = ERR_PTR(create_error);
-		return dentry;
+		dentry = atomic_open(&nd->path, dentry, file, open_flag, mode,
+				     create_error);
+		goto out;
 	}
 
 	if (d_in_lookup(dentry)) {
@@ -4490,37 +4542,164 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file,
 			dentry = res;
 		}
 	}
-
-	/* Negative dentry, just create the file */
-	if (!dentry->d_inode && (open_flag & O_CREAT)) {
-		/* but break the directory lease first! */
-		error = try_break_deleg(dir_inode, LEASE_BREAK_DIR_CREATE, delegated_inode);
-		if (error)
-			goto out_dput;
-
-		file->f_mode |= FMODE_CREATED;
-		audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE);
-		if (!dir_inode->i_op->create) {
-			error = -EACCES;
-			goto out_dput;
-		}
-
-		error = dir_inode->i_op->create(idmap, dir_inode, dentry,
-						mode, open_flag & O_EXCL);
-		if (error)
-			goto out_dput;
+	if (dentry->d_inode || !(op->open_flag & O_CREAT)) {
+		/*
+		 * No need to create a file.  If lookup returned a positive
+		 * dentry, the file will be opened in do_open().
+		 */
+		goto out;
 	}
-	if (unlikely(create_error) && !dentry->d_inode) {
+
+	/* Negative dentry with O_CREAT flag set */
+	audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE);
+
+	if (unlikely(create_error)) {
+		/* should have done a create, but we already errored */
 		error = create_error;
 		goto out_dput;
 	}
+
+	error = try_break_deleg(dir_inode, LEASE_BREAK_DIR_CREATE, &delegated_inode);
+	if (error)
+		goto out_dput;
+
+	file->f_mode |= FMODE_CREATED;
+	if (!dir_inode->i_op->create) {
+		error = -EACCES;
+		goto out_dput;
+	}
+
+	error = dir_inode->i_op->create(idmap, dir_inode, dentry, mode);
+	if (error)
+		goto out_dput;
+out:
+	if (!IS_ERR(dentry)) {
+		if (file->f_mode & FMODE_CREATED)
+			fsnotify_create(dir_inode, dentry);
+		if (file->f_mode & FMODE_OPENED)
+			fsnotify_open(file);
+	}
+	if ((open_flag & O_CREAT) || create_error)
+		inode_unlock(dir_inode);
+	else
+		inode_unlock_shared(dir_inode);
+
+	if (got_write)
+		mnt_drop_write(nd->path.mnt);
+
+	if (is_delegated(&delegated_inode)) {
+		/* Must have come through out_dput: dentry is an ERR_PTR() */
+		error = break_deleg_wait(&delegated_inode);
+
+		if (!error)
+			goto retry;
+		dentry = ERR_PTR(error);
+	}
+
 	return dentry;
 
 out_dput:
 	dput(dentry);
-	return ERR_PTR(error);
+	dentry = ERR_PTR(error);
+	goto out;
 }
 
+/**
+ * vfs_lookup_open - open and possibly create a regular file
+ * @parent: directory to contain file
+ * @last: final component of file name
+ * @open_flag: O_flags
+ * @mode: initial permissions for file
+ *
+ * Open a file after lookup and/or create.  This provides similar
+ * functionality to open_last_lookups() for non-VFS users, particularly
+ * nfsd.
+ * It uses ->atomic_open or ->lookup / ->create / ->open as appropriate.
+ *
+ * If the fs object found is not a regular file then an error is returned.
+ * In some cases, related errors are repurposed so that the caller can
+ * determine the type of file found from the error.
+ * -EISDIR : a directory was found
+ * -ELOOP  : a symlink was found
+ * -ENODEV : a block or character device special file was found
+ * -EFTYPE : any other non-regular file was found, such as FIFO or SOCK.
+ *           or ->atomic_open responded to __O_REGULAR.
+ *
+ * Returns: the opened struct file, or an error.
+ */
+struct file *vfs_lookup_open(struct path *parent, struct qstr *last,
+			     int open_flag, umode_t mode)
+{
+	struct file *file __free(fput) = NULL;
+	struct nameidata nd = {};
+	struct open_flags op = {};
+	struct dentry *dentry;
+	int error = 0;
+
+	WARN_ONCE(mode & ~S_IALLUGO, "mode must only have permission bits");
+	WARN_ONCE(open_flag & ~(O_ACCMODE|O_CREAT|O_EXCL|O_TRUNC|__O_REGULAR),
+		  "open_flag has unsupported flags");
+
+	mode |= S_IFREG;
+	open_flag |= __O_REGULAR;
+
+	error = lookup_noperm_common(last, parent->dentry);
+	if (error)
+		return ERR_PTR(error);
+
+	file = alloc_empty_file(open_flag, current_cred());
+	if (IS_ERR(file))
+		return file;
+
+	nd.path = *parent;
+	nd.last = *last;
+	nd.flags = LOOKUP_OPEN;
+	if (open_flag & O_CREAT) {
+		nd.flags |= LOOKUP_CREATE;
+		if (open_flag & O_EXCL)
+			nd.flags |= LOOKUP_EXCL;
+	}
+	op.open_flag = open_flag;
+	op.mode = mode;
+	dentry = lookup_open(&nd, file, &op);
+
+	if (IS_ERR(dentry))
+		return ERR_CAST(dentry);
+
+	if (d_really_is_negative(dentry)) {
+		error = -ENOENT;
+	} else if (!(file->f_mode & FMODE_CREATED) && (open_flag & O_EXCL)) {
+		error = -EEXIST;
+	} else if ((dentry->d_inode->i_mode & S_IFMT) != S_IFREG) {
+		switch (dentry->d_inode->i_mode & S_IFMT) {
+		case S_IFDIR:
+			error = -EISDIR;
+			break;
+		case S_IFLNK:
+			error = -ELOOP;
+			break;
+		case S_IFBLK:
+		case S_IFCHR:
+			error = -ENODEV;
+			break;
+		case S_IFIFO:
+		case S_IFSOCK:
+		default:
+			error = -EFTYPE;
+			break;
+		}
+	} else if (!(file->f_mode & FMODE_OPENED)) {
+		nd.path.dentry = dentry;
+		error = vfs_open(&nd.path, file);
+	}
+	dput(dentry);
+
+	if (error)
+		return ERR_PTR(error);
+	return no_free_ptr(file);
+}
+EXPORT_SYMBOL_FOR_MODULES(vfs_lookup_open, "nfsd");
+
 static inline bool trailing_slashes(struct nameidata *nd)
 {
 	return (bool)nd->last.name[nd->last.len];
@@ -4560,10 +4739,7 @@ static struct dentry *lookup_fast_for_open(struct nameidata *nd, int open_flag)
 static const char *open_last_lookups(struct nameidata *nd,
 		   struct file *file, const struct open_flags *op)
 {
-	struct delegated_inode delegated_inode = { };
-	struct dentry *dir = nd->path.dentry;
 	int open_flag = op->open_flag;
-	bool got_write = false;
 	struct dentry *dentry;
 	const char *res;
 
@@ -4592,44 +4768,10 @@ static const char *open_last_lookups(struct nameidata *nd,
 				return ERR_PTR(-ECHILD);
 		}
 	}
-retry:
-	if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) {
-		got_write = !mnt_want_write(nd->path.mnt);
-		/*
-		 * do _not_ fail yet - we might not need that or fail with
-		 * a different error; let lookup_open() decide; we'll be
-		 * dropping this one anyway.
-		 */
-	}
-	if (open_flag & O_CREAT)
-		inode_lock(dir->d_inode);
-	else
-		inode_lock_shared(dir->d_inode);
-	dentry = lookup_open(nd, file, op, got_write, &delegated_inode);
-	if (!IS_ERR(dentry)) {
-		if (file->f_mode & FMODE_CREATED)
-			fsnotify_create(dir->d_inode, dentry);
-		if (file->f_mode & FMODE_OPENED)
-			fsnotify_open(file);
-	}
-	if (open_flag & O_CREAT)
-		inode_unlock(dir->d_inode);
-	else
-		inode_unlock_shared(dir->d_inode);
 
-	if (got_write)
-		mnt_drop_write(nd->path.mnt);
-
-	if (IS_ERR(dentry)) {
-		if (is_delegated(&delegated_inode)) {
-			int error = break_deleg_wait(&delegated_inode);
-
-			if (!error)
-				goto retry;
-			return ERR_PTR(error);
-		}
+	dentry = lookup_open(nd, file, op);
+	if (IS_ERR(dentry))
 		return ERR_CAST(dentry);
-	}
 
 	if (file->f_mode & (FMODE_OPENED | FMODE_CREATED)) {
 		dput(nd->path.dentry);
@@ -5051,7 +5193,7 @@ struct file *dentry_create(struct path *path, int flags, umode_t mode,
 
 		/* atomic_open will dput(dentry) on error */
 		dget(orig_dentry);
-		dentry = atomic_open(path, dentry, file, flags, mode);
+		dentry = atomic_open(path, dentry, file, flags, mode, create_error);
 		error = PTR_ERR_OR_ZERO(dentry);
 
 		if (IS_ERR(dentry))
@@ -5061,9 +5203,6 @@ struct file *dentry_create(struct path *path, int flags, umode_t mode,
 			/* Drop the extra reference */
 			dput(orig_dentry);
 
-		if (unlikely(create_error) && error == -ENOENT)
-			error = create_error;
-
 		if (!error) {
 			if (file->f_mode & FMODE_CREATED)
 				fsnotify_create(dir->d_inode, dentry);

fs/nfs/dir.c

@@ -2427,9 +2427,9 @@ static int nfs_do_create(struct inode *dir, struct dentry *dentry,
 }
 
 int nfs_create(struct mnt_idmap *idmap, struct inode *dir,
-	       struct dentry *dentry, umode_t mode, bool excl)
+	       struct dentry *dentry, umode_t mode)
 {
-	return nfs_do_create(dir, dentry, mode, excl ? O_EXCL : 0);
+	return nfs_do_create(dir, dentry, mode, O_EXCL);
 }
 EXPORT_SYMBOL_GPL(nfs_create);
 

fs/nfs/internal.h

@@ -395,7 +395,7 @@ extern unsigned long nfs_access_cache_scan(struct shrinker *shrink,
 struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int);
 void nfs_d_prune_case_insensitive_aliases(struct inode *inode);
 int nfs_create(struct mnt_idmap *, struct inode *, struct dentry *,
-	       umode_t, bool);
+	       umode_t);
 struct dentry *nfs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *,
 			 umode_t);
 int nfs_rmdir(struct inode *, struct dentry *);

fs/nilfs2/namei.c

@@ -86,7 +86,7 @@ nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
  * with d_instantiate().
  */
 static int nilfs_create(struct mnt_idmap *idmap, struct inode *dir,
-			struct dentry *dentry, umode_t mode, bool excl)
+			struct dentry *dentry, umode_t mode)
 {
 	struct inode *inode;
 	struct nilfs_transaction_info ti;

fs/ntfs/namei.c

@@ -737,7 +737,7 @@ static struct ntfs_inode *__ntfs_create(struct mnt_idmap *idmap, struct inode *d
 }
 
 static int ntfs_create(struct mnt_idmap *idmap, struct inode *dir,
-		struct dentry *dentry, umode_t mode, bool excl)
+		struct dentry *dentry, umode_t mode)
 {
 	struct ntfs_volume *vol = NTFS_SB(dir->i_sb);
 	struct ntfs_inode *ni;

fs/ntfs3/namei.c

@@ -105,7 +105,7 @@ static struct dentry *ntfs_lookup(struct inode *dir, struct dentry *dentry,
  * ntfs_create - inode_operations::create
  */
 static int ntfs_create(struct mnt_idmap *idmap, struct inode *dir,
-		       struct dentry *dentry, umode_t mode, bool excl)
+		       struct dentry *dentry, umode_t mode)
 {
 	return ntfs_create_inode(idmap, dir, dentry, NULL, S_IFREG | mode, 0,
 				 NULL, 0, NULL);

fs/ocfs2/dlmfs/dlmfs.c

@@ -453,8 +453,7 @@ static struct dentry *dlmfs_mkdir(struct mnt_idmap * idmap,
 static int dlmfs_create(struct mnt_idmap *idmap,
 			struct inode *dir,
 			struct dentry *dentry,
-			umode_t mode,
-			bool excl)
+			umode_t mode)
 {
 	int status = 0;
 	struct inode *inode;

fs/ocfs2/namei.c

@@ -667,8 +667,7 @@ static struct dentry *ocfs2_mkdir(struct mnt_idmap *idmap,
 static int ocfs2_create(struct mnt_idmap *idmap,
 			struct inode *dir,
 			struct dentry *dentry,
-			umode_t mode,
-			bool excl)
+			umode_t mode)
 {
 	int ret;
 

fs/omfs/dir.c

@@ -286,7 +286,7 @@ static struct dentry *omfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 }
 
 static int omfs_create(struct mnt_idmap *idmap, struct inode *dir,
-		       struct dentry *dentry, umode_t mode, bool excl)
+		       struct dentry *dentry, umode_t mode)
 {
 	return omfs_add_node(dir, dentry, mode | S_IFREG);
 }

fs/orangefs/namei.c

@@ -18,8 +18,7 @@
 static int orangefs_create(struct mnt_idmap *idmap,
 			struct inode *dir,
 			struct dentry *dentry,
-			umode_t mode,
-			bool exclusive)
+			umode_t mode)
 {
 	struct orangefs_inode_s *parent = ORANGEFS_I(dir);
 	struct orangefs_kernel_op_s *new_op;

fs/overlayfs/dir.c

@@ -732,7 +732,7 @@ static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev,
 }
 
 static int ovl_create(struct mnt_idmap *idmap, struct inode *dir,
-		      struct dentry *dentry, umode_t mode, bool excl)
+		      struct dentry *dentry, umode_t mode)
 {
 	return ovl_create_object(dentry, (mode & 07777) | S_IFREG, 0, NULL);
 }

fs/ramfs/inode.c

@@ -128,7 +128,7 @@ static struct dentry *ramfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 }
 
 static int ramfs_create(struct mnt_idmap *idmap, struct inode *dir,
-			struct dentry *dentry, umode_t mode, bool excl)
+			struct dentry *dentry, umode_t mode)
 {
 	return ramfs_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFREG, 0);
 }

fs/smb/client/cifsfs.h

@@ -54,7 +54,7 @@ void cifs_sb_deactive(struct super_block *sb);
 extern const struct inode_operations cifs_dir_inode_ops;
 struct inode *cifs_root_iget(struct super_block *sb);
 int cifs_create(struct mnt_idmap *idmap, struct inode *dir,
-		struct dentry *direntry, umode_t mode, bool excl);
+		struct dentry *direntry, umode_t mode);
 int cifs_atomic_open(struct inode *dir, struct dentry *direntry,
 		     struct file *file, unsigned int oflags, umode_t mode);
 int cifs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,

fs/smb/client/dir.c

@@ -645,7 +645,7 @@ int cifs_atomic_open(struct inode *dir, struct dentry *direntry,
  * hashed-positive by calling d_instantiate().
  */
 int cifs_create(struct mnt_idmap *idmap, struct inode *dir,
-		struct dentry *direntry, umode_t mode, bool excl)
+		struct dentry *direntry, umode_t mode)
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(dir);
 	int rc;

fs/ubifs/dir.c

@@ -303,7 +303,7 @@ static int ubifs_prepare_create(struct inode *dir, struct dentry *dentry,
 }
 
 static int ubifs_create(struct mnt_idmap *idmap, struct inode *dir,
-			struct dentry *dentry, umode_t mode, bool excl)
+			struct dentry *dentry, umode_t mode)
 {
 	struct inode *inode;
 	struct ubifs_info *c = dir->i_sb->s_fs_info;

fs/udf/namei.c

@@ -371,7 +371,7 @@ static int udf_add_nondir(struct dentry *dentry, struct inode *inode)
 }
 
 static int udf_create(struct mnt_idmap *idmap, struct inode *dir,
-		      struct dentry *dentry, umode_t mode, bool excl)
+		      struct dentry *dentry, umode_t mode)
 {
 	struct inode *inode = udf_new_inode(dir, mode);
 

fs/ufs/namei.c

@@ -70,8 +70,7 @@ static struct dentry *ufs_lookup(struct inode * dir, struct dentry *dentry, unsi
  * with d_instantiate(). 
  */
 static int ufs_create (struct mnt_idmap * idmap,
-		struct inode * dir, struct dentry * dentry, umode_t mode,
-		bool excl)
+		struct inode * dir, struct dentry * dentry, umode_t mode)
 {
 	struct inode *inode;
 

fs/vboxsf/dir.c

@@ -298,9 +298,9 @@ static int vboxsf_dir_create(struct inode *parent, struct dentry *dentry,
 
 static int vboxsf_dir_mkfile(struct mnt_idmap *idmap,
 			     struct inode *parent, struct dentry *dentry,
-			     umode_t mode, bool excl)
+			     umode_t mode)
 {
-	return vboxsf_dir_create(parent, dentry, mode, false, excl, NULL);
+	return vboxsf_dir_create(parent, dentry, mode, false, true, NULL);
 }
 
 static struct dentry *vboxsf_dir_mkdir(struct mnt_idmap *idmap,

fs/xfs/xfs_iops.c

@@ -293,8 +293,7 @@ xfs_vn_create(
 	struct mnt_idmap	*idmap,
 	struct inode		*dir,
 	struct dentry		*dentry,
-	umode_t			mode,
-	bool			flags)
+	umode_t			mode)
 {
 	return xfs_generic_create(idmap, dir, dentry, mode, 0, NULL);
 }
@@ -338,7 +337,7 @@ STATIC struct dentry *
 xfs_vn_ci_lookup(
 	struct inode	*dir,
 	struct dentry	*dentry,
-	unsigned int flags)
+	unsigned int	flags)
 {
 	struct xfs_inode *ip;
 	struct xfs_name	xname;

include/linux/fs.h

@@ -2002,7 +2002,7 @@ struct inode_operations {
 	int (*readlink) (struct dentry *, char __user *,int);
 
 	int (*create) (struct mnt_idmap *, struct inode *,struct dentry *,
-		       umode_t, bool);
+		       umode_t);
 	int (*link) (struct dentry *,struct inode *,struct dentry *);
 	int (*unlink) (struct inode *,struct dentry *);
 	int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *,

include/linux/namei.h

@@ -97,6 +97,9 @@ struct dentry *start_creating_dentry(struct dentry *parent,
 struct dentry *start_removing_dentry(struct dentry *parent,
 				     struct dentry *child);
 
+struct file *vfs_lookup_open(struct path *parent, struct qstr *last,
+			     int open_flag, umode_t mode);
+
 /* end_creating - finish action started with start_creating
  * @child: dentry returned by start_creating() or vfs_mkdir()
  *

ipc/mqueue.c

@@ -608,7 +608,7 @@ static int mqueue_create_attr(struct dentry *dentry, umode_t mode, void *arg)
 }
 
 static int mqueue_create(struct mnt_idmap *idmap, struct inode *dir,
-			 struct dentry *dentry, umode_t mode, bool excl)
+			 struct dentry *dentry, umode_t mode)
 {
 	return mqueue_create_attr(dentry, mode, NULL);
 }

mm/shmem.c

@@ -3874,7 +3874,7 @@ static struct dentry *shmem_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 }
 
 static int shmem_create(struct mnt_idmap *idmap, struct inode *dir,
-			struct dentry *dentry, umode_t mode, bool excl)
+			struct dentry *dentry, umode_t mode)
 {
 	return shmem_mknod(idmap, dir, dentry, mode | S_IFREG, 0);
 }