Merge branch 'work.open3' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs open-related updates from Al Viro:

 - "do we need fput() or put_filp()" rules are gone - it's always fput()
   now. We keep track of that state where it belongs - in ->f_mode.

 - int *opened mess killed - in finish_open(), in ->atomic_open()
   instances and in fs/namei.c code around do_last()/lookup_open()/atomic_open().

 - alloc_file() wrappers with saner calling conventions are introduced
   (alloc_file_clone() and alloc_file_pseudo()); callers converted, with
   much simplification.

 - while we are at it, saner calling conventions for path_init() and
   link_path_walk(), simplifying things inside fs/namei.c (both on
   open-related paths and elsewhere).

* 'work.open3' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (40 commits)
  few more cleanups of link_path_walk() callers
  allow link_path_walk() to take ERR_PTR()
  make path_init() unconditionally paired with terminate_walk()
  document alloc_file() changes
  make alloc_file() static
  do_shmat(): grab shp->shm_file earlier, switch to alloc_file_clone()
  new helper: alloc_file_clone()
  create_pipe_files(): switch the first allocation to alloc_file_pseudo()
  anon_inode_getfile(): switch to alloc_file_pseudo()
  hugetlb_file_setup(): switch to alloc_file_pseudo()
  ocxlflash_getfile(): switch to alloc_file_pseudo()
  cxl_getfile(): switch to alloc_file_pseudo()
  ... and switch shmem_file_setup() to alloc_file_pseudo()
  __shmem_file_setup(): reorder allocations
  new wrapper: alloc_file_pseudo()
  kill FILE_{CREATED,OPENED}
  switch atomic_open() and lookup_open() to returning 0 in all success cases
  document ->atomic_open() changes
  ->atomic_open(): return 0 in all success cases
  get rid of 'opened' in path_openat() and the helpers downstream
  ...

22 files changed, 252 insertions, 402 deletions

diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 42e102e2e74a..85ff859d3af5 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -859,8 +859,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 
 static int
 v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
-		     struct file *file, unsigned flags, umode_t mode,
-		     int *opened)
+		     struct file *file, unsigned flags, umode_t mode)
 {
 	int err;
 	u32 perm;
@@ -917,7 +916,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		v9inode->writeback_fid = (void *) inode_fid;
 	}
 	mutex_unlock(&v9inode->v_mutex);
-	err = finish_open(file, dentry, generic_file_open, opened);
+	err = finish_open(file, dentry, generic_file_open);
 	if (err)
 		goto error;
 
@@ -925,7 +924,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
 	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
 		v9fs_cache_inode_set_cookie(d_inode(dentry), file);
 
-	*opened |= FILE_CREATED;
+	file->f_mode |= FMODE_CREATED;
 out:
 	dput(res);
 	return err;
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 7f6ae21a27b3..4823e1c46999 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -241,8 +241,7 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
 
 static int
 v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
-			  struct file *file, unsigned flags, umode_t omode,
-			  int *opened)
+			  struct file *file, unsigned flags, umode_t omode)
 {
 	int err = 0;
 	kgid_t gid;
@@ -352,13 +351,13 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
 	}
 	mutex_unlock(&v9inode->v_mutex);
 	/* Since we are opening a file, assign the open fid to the file */
-	err = finish_open(file, dentry, generic_file_open, opened);
+	err = finish_open(file, dentry, generic_file_open);
 	if (err)
 		goto err_clunk_old_fid;
 	file->private_data = ofid;
 	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
 		v9fs_cache_inode_set_cookie(inode, file);
-	*opened |= FILE_CREATED;
+	file->f_mode |= FMODE_CREATED;
 out:
 	v9fs_put_acl(dacl, pacl);
 	dput(res);
diff --git a/fs/aio.c b/fs/aio.c
index 27454594e37a..16f1f25bfd89 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -202,9 +202,7 @@ static const struct address_space_operations aio_ctx_aops;
 
 static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 {
-	struct qstr this = QSTR_INIT("[aio]", 5);
 	struct file *file;
-	struct path path;
 	struct inode *inode = alloc_anon_inode(aio_mnt->mnt_sb);
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
@@ -213,31 +211,17 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 	inode->i_mapping->private_data = ctx;
 	inode->i_size = PAGE_SIZE * nr_pages;
 
-	path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this);
-	if (!path.dentry) {
+	file = alloc_file_pseudo(inode, aio_mnt, "[aio]",
+				O_RDWR, &aio_ring_fops);
+	if (IS_ERR(file))
 		iput(inode);
-		return ERR_PTR(-ENOMEM);
-	}
-	path.mnt = mntget(aio_mnt);
-
-	d_instantiate(path.dentry, inode);
-	file = alloc_file(&path, FMODE_READ | FMODE_WRITE, &aio_ring_fops);
-	if (IS_ERR(file)) {
-		path_put(&path);
-		return file;
-	}
-
-	file->f_flags = O_RDWR;
 	return file;
 }
 
 static struct dentry *aio_mount(struct file_system_type *fs_type,
 				int flags, const char *dev_name, void *data)
 {
-	static const struct dentry_operations ops = {
-		.d_dname	= simple_dname,
-	};
-	struct dentry *root = mount_pseudo(fs_type, "aio:", NULL, &ops,
+	struct dentry *root = mount_pseudo(fs_type, "aio:", NULL, NULL,
 					   AIO_RING_MAGIC);
 
 	if (!IS_ERR(root))
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 3168ee4e77f4..91262c34b797 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -71,8 +71,6 @@ struct file *anon_inode_getfile(const char *name,
 				const struct file_operations *fops,
 				void *priv, int flags)
 {
-	struct qstr this;
-	struct path path;
 	struct file *file;
 
 	if (IS_ERR(anon_inode_inode))
@@ -82,39 +80,23 @@ struct file *anon_inode_getfile(const char *name,
 		return ERR_PTR(-ENOENT);
 
 	/*
-	 * Link the inode to a directory entry by creating a unique name
-	 * using the inode sequence number.
-	 */
-	file = ERR_PTR(-ENOMEM);
-	this.name = name;
-	this.len = strlen(name);
-	this.hash = 0;
-	path.dentry = d_alloc_pseudo(anon_inode_mnt->mnt_sb, &this);
-	if (!path.dentry)
-		goto err_module;
-
-	path.mnt = mntget(anon_inode_mnt);
-	/*
 	 * We know the anon_inode inode count is always greater than zero,
 	 * so ihold() is safe.
 	 */
 	ihold(anon_inode_inode);
-
-	d_instantiate(path.dentry, anon_inode_inode);
-
-	file = alloc_file(&path, OPEN_FMODE(flags), fops);
+	file = alloc_file_pseudo(anon_inode_inode, anon_inode_mnt, name,
+				 flags & (O_ACCMODE | O_NONBLOCK), fops);
 	if (IS_ERR(file))
-		goto err_dput;
+		goto err;
+
 	file->f_mapping = anon_inode_inode->i_mapping;
 
-	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
 	file->private_data = priv;
 
 	return file;
 
-err_dput:
-	path_put(&path);
-err_module:
+err:
+	iput(anon_inode_inode);
 	module_put(fops->owner);
 	return file;
 }
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index 125e8bbd22a2..8035d2a44561 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -134,7 +134,7 @@ static int bad_inode_update_time(struct inode *inode, struct timespec64 *time,
 
 static int bad_inode_atomic_open(struct inode *inode, struct dentry *dentry,
 				 struct file *file, unsigned int open_flag,
-				 umode_t create_mode, int *opened)
+				 umode_t create_mode)
 {
 	return -EIO;
 }
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 4b5fff31ef27..aa4a7a23ff99 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -205,7 +205,7 @@ static int load_misc_binary(struct linux_binprm *bprm)
 		goto error;
 
 	if (fmt->flags & MISC_FMT_OPEN_FILE) {
-		interp_file = filp_clone_open(fmt->interp_file);
+		interp_file = file_clone_open(fmt->interp_file);
 		if (!IS_ERR(interp_file))
 			deny_write_access(interp_file);
 	} else {
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index ad0bed99b1d5..e2679e8a2535 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -429,8 +429,7 @@ out:
  * file or symlink, return 1 so the VFS can retry.
  */
 int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
-		     struct file *file, unsigned flags, umode_t mode,
-		     int *opened)
+		     struct file *file, unsigned flags, umode_t mode)
 {
 	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
@@ -507,9 +506,9 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 		dout("atomic_open finish_open on dn %p\n", dn);
 		if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
 			ceph_init_inode_acls(d_inode(dentry), &acls);
-			*opened |= FILE_CREATED;
+			file->f_mode |= FMODE_CREATED;
 		}
-		err = finish_open(file, dentry, ceph_open, opened);
+		err = finish_open(file, dentry, ceph_open);
 	}
 out_req:
 	if (!req->r_err && req->r_target_inode)
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index a7077a0c989f..971328b99ede 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -1025,8 +1025,7 @@ extern const struct file_operations ceph_file_fops;
 extern int ceph_renew_caps(struct inode *inode);
 extern int ceph_open(struct inode *inode, struct file *file);
 extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
-			    struct file *file, unsigned flags, umode_t mode,
-			    int *opened);
+			    struct file *file, unsigned flags, umode_t mode);
 extern int ceph_release(struct inode *inode, struct file *filp);
 extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 				  char *data, size_t len);
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 5f0231803431..f3a78efc3109 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -65,8 +65,7 @@ extern struct inode *cifs_root_iget(struct super_block *);
 extern int cifs_create(struct inode *, struct dentry *, umode_t,
 		       bool excl);
 extern int cifs_atomic_open(struct inode *, struct dentry *,
-			    struct file *, unsigned, umode_t,
-			    int *);
+			    struct file *, unsigned, umode_t);
 extern struct dentry *cifs_lookup(struct inode *, struct dentry *,
 				  unsigned int);
 extern int cifs_unlink(struct inode *dir, struct dentry *dentry);
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index ddae52bd1993..3713d22b95a7 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -465,8 +465,7 @@ out_err:
 
 int
 cifs_atomic_open(struct inode *inode, struct dentry *direntry,
-		 struct file *file, unsigned oflags, umode_t mode,
-		 int *opened)
+		 struct file *file, unsigned oflags, umode_t mode)
 {
 	int rc;
 	unsigned int xid;
@@ -539,9 +538,9 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
 	}
 
 	if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
-		*opened |= FILE_CREATED;
+		file->f_mode |= FMODE_CREATED;
 
-	rc = finish_open(file, direntry, generic_file_open, opened);
+	rc = finish_open(file, direntry, generic_file_open);
 	if (rc) {
 		if (server->ops->close)
 			server->ops->close(xid, tcon, &fid);
diff --git a/fs/file_table.c b/fs/file_table.c
index 7ec0b3e5f05d..d6eccd04d703 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -51,6 +51,7 @@ static void file_free_rcu(struct rcu_head *head)
 
 static inline void file_free(struct file *f)
 {
+	security_file_free(f);
 	percpu_counter_dec(&nr_files);
 	call_rcu(&f->f_u.fu_rcuhead, file_free_rcu);
 }
@@ -100,9 +101,8 @@ int proc_nr_files(struct ctl_table *table, int write,
  * done, you will imbalance int the mount's writer count
  * and a warning at __fput() time.
  */
-struct file *get_empty_filp(void)
+struct file *alloc_empty_file(int flags, const struct cred *cred)
 {
-	const struct cred *cred = current_cred();
 	static long old_max;
 	struct file *f;
 	int error;
@@ -123,11 +123,10 @@ struct file *get_empty_filp(void)
 	if (unlikely(!f))
 		return ERR_PTR(-ENOMEM);
 
-	percpu_counter_inc(&nr_files);
 	f->f_cred = get_cred(cred);
 	error = security_file_alloc(f);
 	if (unlikely(error)) {
-		file_free(f);
+		file_free_rcu(&f->f_u.fu_rcuhead);
 		return ERR_PTR(error);
 	}
 
@@ -136,7 +135,10 @@ struct file *get_empty_filp(void)
 	spin_lock_init(&f->f_lock);
 	mutex_init(&f->f_pos_lock);
 	eventpoll_init_file(f);
+	f->f_flags = flags;
+	f->f_mode = OPEN_FMODE(flags);
 	/* f->f_version: 0 */
+	percpu_counter_inc(&nr_files);
 	return f;
 
 over:
@@ -152,15 +154,15 @@ over:
  * alloc_file - allocate and initialize a 'struct file'
  *
  * @path: the (dentry, vfsmount) pair for the new file
- * @mode: the mode with which the new file will be opened
+ * @flags: O_... flags with which the new file will be opened
  * @fop: the 'struct file_operations' for the new file
  */
-struct file *alloc_file(const struct path *path, fmode_t mode,
+static struct file *alloc_file(const struct path *path, int flags,
 		const struct file_operations *fop)
 {
 	struct file *file;
 
-	file = get_empty_filp();
+	file = alloc_empty_file(flags, current_cred());
 	if (IS_ERR(file))
 		return file;
 
@@ -168,19 +170,56 @@ struct file *alloc_file(const struct path *path, fmode_t mode,
 	file->f_inode = path->dentry->d_inode;
 	file->f_mapping = path->dentry->d_inode->i_mapping;
 	file->f_wb_err = filemap_sample_wb_err(file->f_mapping);
-	if ((mode & FMODE_READ) &&
+	if ((file->f_mode & FMODE_READ) &&
 	     likely(fop->read || fop->read_iter))
-		mode |= FMODE_CAN_READ;
-	if ((mode & FMODE_WRITE) &&
+		file->f_mode |= FMODE_CAN_READ;
+	if ((file->f_mode & FMODE_WRITE) &&
 	     likely(fop->write || fop->write_iter))
-		mode |= FMODE_CAN_WRITE;
-	file->f_mode = mode;
+		file->f_mode |= FMODE_CAN_WRITE;
+	file->f_mode |= FMODE_OPENED;
 	file->f_op = fop;
-	if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
+	if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_inc(path->dentry->d_inode);
 	return file;
 }
-EXPORT_SYMBOL(alloc_file);
+
+struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt,
+				const char *name, int flags,
+				const struct file_operations *fops)
+{
+	static const struct dentry_operations anon_ops = {
+		.d_dname = simple_dname
+	};
+	struct qstr this = QSTR_INIT(name, strlen(name));
+	struct path path;
+	struct file *file;
+
+	path.dentry = d_alloc_pseudo(mnt->mnt_sb, &this);
+	if (!path.dentry)
+		return ERR_PTR(-ENOMEM);
+	if (!mnt->mnt_sb->s_d_op)
+		d_set_d_op(path.dentry, &anon_ops);
+	path.mnt = mntget(mnt);
+	d_instantiate(path.dentry, inode);
+	file = alloc_file(&path, flags, fops);
+	if (IS_ERR(file)) {
+		ihold(inode);
+		path_put(&path);
+	}
+	return file;
+}
+EXPORT_SYMBOL(alloc_file_pseudo);
+
+struct file *alloc_file_clone(struct file *base, int flags,
+				const struct file_operations *fops)
+{
+	struct file *f = alloc_file(&base->f_path, flags, fops);
+	if (!IS_ERR(f)) {
+		path_get(&f->f_path);
+		f->f_mapping = base->f_mapping;
+	}
+	return f;
+}
 
 /* the real guts of fput() - releasing the last reference to file
  */
@@ -190,6 +229,9 @@ static void __fput(struct file *file)
 	struct vfsmount *mnt = file->f_path.mnt;
 	struct inode *inode = file->f_inode;
 
+	if (unlikely(!(file->f_mode & FMODE_OPENED)))
+		goto out;
+
 	might_sleep();
 
 	fsnotify_close(file);
@@ -207,7 +249,6 @@ static void __fput(struct file *file)
 	}
 	if (file->f_op->release)
 		file->f_op->release(inode, file);
-	security_file_free(file);
 	if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL &&
 		     !(file->f_mode & FMODE_PATH))) {
 		cdev_put(inode->i_cdev);
@@ -220,12 +261,10 @@ static void __fput(struct file *file)
 		put_write_access(inode);
 		__mnt_drop_write(mnt);
 	}
-	file->f_path.dentry = NULL;
-	file->f_path.mnt = NULL;
-	file->f_inode = NULL;
-	file_free(file);
 	dput(dentry);
 	mntput(mnt);
+out:
+	file_free(file);
 }
 
 static LLIST_HEAD(delayed_fput_list);
@@ -300,14 +339,6 @@ void __fput_sync(struct file *file)
 
 EXPORT_SYMBOL(fput);
 
-void put_filp(struct file *file)
-{
-	if (atomic_long_dec_and_test(&file->f_count)) {
-		security_file_free(file);
-		file_free(file);
-	}
-}
-
 void __init files_init(void)
 {
 	filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 56231b31f806..c979329311c8 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -399,7 +399,7 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
  */
 static int fuse_create_open(struct inode *dir, struct dentry *entry,
 			    struct file *file, unsigned flags,
-			    umode_t mode, int *opened)
+			    umode_t mode)
 {
 	int err;
 	struct inode *inode;
@@ -469,7 +469,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 	d_instantiate(entry, inode);
 	fuse_change_entry_timeout(entry, &outentry);
 	fuse_invalidate_attr(dir);
-	err = finish_open(file, entry, generic_file_open, opened);
+	err = finish_open(file, entry, generic_file_open);
 	if (err) {
 		fuse_sync_release(ff, flags);
 	} else {
@@ -489,7 +489,7 @@ out_err:
 static int fuse_mknod(struct inode *, struct dentry *, umode_t, dev_t);
 static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
 			    struct file *file, unsigned flags,
-			    umode_t mode, int *opened)
+			    umode_t mode)
 {
 	int err;
 	struct fuse_conn *fc = get_fuse_conn(dir);
@@ -508,12 +508,12 @@ static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
 		goto no_open;
 
 	/* Only creates */
-	*opened |= FILE_CREATED;
+	file->f_mode |= FMODE_CREATED;
 
 	if (fc->no_create)
 		goto mknod;
 
-	err = fuse_create_open(dir, entry, file, flags, mode, opened);
+	err = fuse_create_open(dir, entry, file, flags, mode);
 	if (err == -ENOSYS) {
 		fc->no_create = 1;
 		goto mknod;
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index feda55f67050..648f0ca1ad57 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -580,7 +580,7 @@ static int gfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
 static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 			     struct file *file,
 			     umode_t mode, dev_t dev, const char *symname,
-			     unsigned int size, int excl, int *opened)
+			     unsigned int size, int excl)
 {
 	const struct qstr *name = &dentry->d_name;
 	struct posix_acl *default_acl, *acl;
@@ -626,7 +626,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 		error = 0;
 		if (file) {
 			if (S_ISREG(inode->i_mode))
-				error = finish_open(file, dentry, gfs2_open_common, opened);
+				error = finish_open(file, dentry, gfs2_open_common);
 			else
 				error = finish_no_open(file, NULL);
 		}
@@ -767,8 +767,8 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	mark_inode_dirty(inode);
 	d_instantiate(dentry, inode);
 	if (file) {
-		*opened |= FILE_CREATED;
-		error = finish_open(file, dentry, gfs2_open_common, opened);
+		file->f_mode |= FMODE_CREATED;
+		error = finish_open(file, dentry, gfs2_open_common);
 	}
 	gfs2_glock_dq_uninit(ghs);
 	gfs2_glock_dq_uninit(ghs + 1);
@@ -822,7 +822,7 @@ fail:
 static int gfs2_create(struct inode *dir, struct dentry *dentry,
 		       umode_t mode, bool excl)
 {
-	return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, excl, NULL);
+	return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, excl);
 }
 
 /**
@@ -830,14 +830,13 @@ static int gfs2_create(struct inode *dir, struct dentry *dentry,
  * @dir: The directory inode
  * @dentry: The dentry of the new inode
  * @file: File to be opened
- * @opened: atomic_open flags
  *
  *
  * Returns: errno
  */
 
 static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry,
-				    struct file *file, int *opened)
+				    struct file *file)
 {
 	struct inode *inode;
 	struct dentry *d;
@@ -866,7 +865,7 @@ static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry,
 		return d;
 	}
 	if (file && S_ISREG(inode->i_mode))
-		error = finish_open(file, dentry, gfs2_open_common, opened);
+		error = finish_open(file, dentry, gfs2_open_common);
 
 	gfs2_glock_dq_uninit(&gh);
 	if (error) {
@@ -879,7 +878,7 @@ static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry,
 static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry,
 				  unsigned flags)
 {
-	return __gfs2_lookup(dir, dentry, NULL, NULL);
+	return __gfs2_lookup(dir, dentry, NULL);
 }
 
 /**
@@ -1189,7 +1188,7 @@ static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
 	if (size >= gfs2_max_stuffed_size(GFS2_I(dir)))
 		return -ENAMETOOLONG;
 
-	return gfs2_create_inode(dir, dentry, NULL, S_IFLNK | S_IRWXUGO, 0, symname, size, 0, NULL);
+	return gfs2_create_inode(dir, dentry, NULL, S_IFLNK | S_IRWXUGO, 0, symname, size, 0);
 }
 
 /**
@@ -1204,7 +1203,7 @@ static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
 static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 {
 	unsigned dsize = gfs2_max_stuffed_size(GFS2_I(dir));
-	return gfs2_create_inode(dir, dentry, NULL, S_IFDIR | mode, 0, NULL, dsize, 0, NULL);
+	return gfs2_create_inode(dir, dentry, NULL, S_IFDIR | mode, 0, NULL, dsize, 0);
 }
 
 /**
@@ -1219,7 +1218,7 @@ static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 static int gfs2_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
 		      dev_t dev)
 {
-	return gfs2_create_inode(dir, dentry, NULL, mode, dev, NULL, 0, 0, NULL);
+	return gfs2_create_inode(dir, dentry, NULL, mode, dev, NULL, 0, 0);
 }
 
 /**
@@ -1229,14 +1228,13 @@ static int gfs2_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
  * @file: The proposed new struct file
  * @flags: open flags
  * @mode: File mode
- * @opened: Flag to say whether the file has been opened or not
  *
  * Returns: error code or 0 for success
  */
 
 static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry,
 			    struct file *file, unsigned flags,
-			    umode_t mode, int *opened)
+			    umode_t mode)
 {
 	struct dentry *d;
 	bool excl = !!(flags & O_EXCL);
@@ -1244,13 +1242,13 @@ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry,
 	if (!d_in_lookup(dentry))
 		goto skip_lookup;
 
-	d = __gfs2_lookup(dir, dentry, file, opened);
+	d = __gfs2_lookup(dir, dentry, file);
 	if (IS_ERR(d))
 		return PTR_ERR(d);
 	if (d != NULL)
 		dentry = d;
 	if (d_really_is_positive(dentry)) {
-		if (!(*opened & FILE_OPENED))
+		if (!(file->f_mode & FMODE_OPENED))
 			return finish_no_open(file, d);
 		dput(d);
 		return 0;
@@ -1262,7 +1260,7 @@ skip_lookup:
 	if (!(flags & O_CREAT))
 		return -ENOENT;
 
-	return gfs2_create_inode(dir, dentry, file, S_IFREG | mode, 0, NULL, 0, excl, opened);
+	return gfs2_create_inode(dir, dentry, file, S_IFREG | mode, 0, NULL, 0, excl);
 }
 
 /*
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 40d4c66c7751..346a146c7617 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1310,10 +1310,6 @@ static int get_hstate_idx(int page_size_log)
 	return h - hstates;
 }
 
-static const struct dentry_operations anon_ops = {
-	.d_dname = simple_dname
-};
-
 /*
  * Note that size should be aligned to proper hugepage size in caller side,
  * otherwise hugetlb_reserve_pages reserves one less hugepages than intended.
@@ -1322,19 +1318,18 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 				vm_flags_t acctflag, struct user_struct **user,
 				int creat_flags, int page_size_log)
 {
-	struct file *file = ERR_PTR(-ENOMEM);
 	struct inode *inode;
-	struct path path;
-	struct super_block *sb;
-	struct qstr quick_string;
+	struct vfsmount *mnt;
 	int hstate_idx;
+	struct file *file;
 
 	hstate_idx = get_hstate_idx(page_size_log);
 	if (hstate_idx < 0)
 		return ERR_PTR(-ENODEV);
 
 	*user = NULL;
-	if (!hugetlbfs_vfsmount[hstate_idx])
+	mnt = hugetlbfs_vfsmount[hstate_idx];
+	if (!mnt)
 		return ERR_PTR(-ENOENT);
 
 	if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) {
@@ -1350,45 +1345,28 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 		}
 	}
 
-	sb = hugetlbfs_vfsmount[hstate_idx]->mnt_sb;
-	quick_string.name = name;
-	quick_string.len = strlen(quick_string.name);
-	quick_string.hash = 0;
-	path.dentry = d_alloc_pseudo(sb, &quick_string);
-	if (!path.dentry)
-		goto out_shm_unlock;
-
-	d_set_d_op(path.dentry, &anon_ops);
-	path.mnt = mntget(hugetlbfs_vfsmount[hstate_idx]);
 	file = ERR_PTR(-ENOSPC);
-	inode = hugetlbfs_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0);
+	inode = hugetlbfs_get_inode(mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0);
 	if (!inode)
-		goto out_dentry;
+		goto out;
 	if (creat_flags == HUGETLB_SHMFS_INODE)
 		inode->i_flags |= S_PRIVATE;
 
-	file = ERR_PTR(-ENOMEM);
-	if (hugetlb_reserve_pages(inode, 0,
-			size >> huge_page_shift(hstate_inode(inode)), NULL,
-			acctflag))
-		goto out_inode;
-
-	d_instantiate(path.dentry, inode);
 	inode->i_size = size;
 	clear_nlink(inode);
 
-	file = alloc_file(&path, FMODE_WRITE | FMODE_READ,
-			&hugetlbfs_file_operations);
-	if (IS_ERR(file))
-		goto out_dentry; /* inode is already attached */
-
-	return file;
+	if (hugetlb_reserve_pages(inode, 0,
+			size >> huge_page_shift(hstate_inode(inode)), NULL,
+			acctflag))
+		file = ERR_PTR(-ENOMEM);
+	else
+		file = alloc_file_pseudo(inode, mnt, name, O_RDWR,
+					&hugetlbfs_file_operations);
+	if (!IS_ERR(file))
+		return file;
 
-out_inode:
 	iput(inode);
-out_dentry:
-	path_put(&path);
-out_shm_unlock:
+out:
 	if (*user) {
 		user_shm_unlock(size, *user);
 		*user = NULL;
diff --git a/fs/internal.h b/fs/internal.h
index 5645b4ebf494..52a346903748 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -93,7 +93,7 @@ extern void chroot_fs_refs(const struct path *, const struct path *);
 /*
  * file_table.c
  */
-extern struct file *get_empty_filp(void);
+extern struct file *alloc_empty_file(int, const struct cred *);
 
 /*
  * super.c
@@ -125,8 +125,7 @@ int do_fchmodat(int dfd, const char __user *filename, umode_t mode);
 int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
 		int flag);
 
-extern int open_check_o_direct(struct file *f);
-extern int vfs_open(const struct path *, struct file *, const struct cred *);
+extern int vfs_open(const struct path *, struct file *);
 
 /*
  * inode.c
diff --git a/fs/namei.c b/fs/namei.c
index 734cef54fdf8..278e494bcbd2 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2028,6 +2028,8 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 {
 	int err;
 
+	if (IS_ERR(name))
+		return PTR_ERR(name);
 	while (*name=='/')
 		name++;
 	if (!*name)
@@ -2125,12 +2127,15 @@ OK:
 	}
 }
 
+/* must be paired with terminate_walk() */
 static const char *path_init(struct nameidata *nd, unsigned flags)
 {
 	const char *s = nd->name->name;
 
 	if (!*s)
 		flags &= ~LOOKUP_RCU;
+	if (flags & LOOKUP_RCU)
+		rcu_read_lock();
 
 	nd->last_type = LAST_ROOT; /* if there are only slashes... */
 	nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
@@ -2143,7 +2148,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 		nd->path = nd->root;
 		nd->inode = inode;
 		if (flags & LOOKUP_RCU) {
-			rcu_read_lock();
 			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
 			nd->root_seq = nd->seq;
 			nd->m_seq = read_seqbegin(&mount_lock);
@@ -2159,21 +2163,15 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 
 	nd->m_seq = read_seqbegin(&mount_lock);
 	if (*s == '/') {
-		if (flags & LOOKUP_RCU)
-			rcu_read_lock();
 		set_root(nd);
 		if (likely(!nd_jump_root(nd)))
 			return s;
-		nd->root.mnt = NULL;
-		rcu_read_unlock();
 		return ERR_PTR(-ECHILD);
 	} else if (nd->dfd == AT_FDCWD) {
 		if (flags & LOOKUP_RCU) {
 			struct fs_struct *fs = current->fs;
 			unsigned seq;
 
-			rcu_read_lock();
-
 			do {
 				seq = read_seqcount_begin(&fs->seq);
 				nd->path = fs->pwd;
@@ -2195,16 +2193,13 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 
 		dentry = f.file->f_path.dentry;
 
-		if (*s) {
-			if (!d_can_lookup(dentry)) {
-				fdput(f);
-				return ERR_PTR(-ENOTDIR);
-			}
+		if (*s && unlikely(!d_can_lookup(dentry))) {
+			fdput(f);
+			return ERR_PTR(-ENOTDIR);
 		}
 
 		nd->path = f.file->f_path;
 		if (flags & LOOKUP_RCU) {
-			rcu_read_lock();
 			nd->inode = nd->path.dentry->d_inode;
 			nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
 		} else {
@@ -2272,24 +2267,15 @@ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path
 	const char *s = path_init(nd, flags);
 	int err;
 
-	if (IS_ERR(s))
-		return PTR_ERR(s);
-
-	if (unlikely(flags & LOOKUP_DOWN)) {
+	if (unlikely(flags & LOOKUP_DOWN) && !IS_ERR(s)) {
 		err = handle_lookup_down(nd);
-		if (unlikely(err < 0)) {
-			terminate_walk(nd);
-			return err;
-		}
+		if (unlikely(err < 0))
+			s = ERR_PTR(err);
 	}
 
 	while (!(err = link_path_walk(s, nd))
 		&& ((err = lookup_last(nd)) > 0)) {
 		s = trailing_symlink(nd);
-		if (IS_ERR(s)) {
-			err = PTR_ERR(s);
-			break;
-		}
 	}
 	if (!err)
 		err = complete_walk(nd);
@@ -2336,10 +2322,7 @@ static int path_parentat(struct nameidata *nd, unsigned flags,
 				struct path *parent)
 {