Merge branch 'work.open3' of git://git.kernel.org/pub/scm/linux/kerne…

…l/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
  ...

Documentation/filesystems/Locking

@@ -64,7 +64,7 @@ prototypes:
 	void (*update_time)(struct inode *, struct timespec *, int);
 	int (*atomic_open)(struct inode *, struct dentry *,
 				struct file *, unsigned open_flag,
-				umode_t create_mode, int *opened);
+				umode_t create_mode);
 	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
 
 locking rules:

Documentation/filesystems/porting

@@ -602,3 +602,23 @@ in your dentry operations instead.
 	dentry separately, and it now has request_mask and query_flags arguments
 	to specify the fields and sync type requested by statx.  Filesystems not
 	supporting any statx-specific features may ignore the new arguments.
+--
+[mandatory]
+	->atomic_open() calling conventions have changed.  Gone is int *opened,
+	along with FILE_OPENED/FILE_CREATED.  In place of those we have
+	FMODE_OPENED/FMODE_CREATED, set in file->f_mode.  Additionally, return
+	value for 'called finish_no_open(), open it yourself' case has become
+	0, not 1.  Since finish_no_open() itself is returning 0 now, that part
+	does not need any changes in ->atomic_open() instances.
+--
+[mandatory]
+	alloc_file() has become static now; two wrappers are to be used instead.
+	alloc_file_pseudo(inode, vfsmount, name, flags, ops) is for the cases
+	when dentry needs to be created; that's the majority of old alloc_file()
+	users.  Calling conventions: on success a reference to new struct file
+	is returned and callers reference to inode is subsumed by that.  On
+	failure, ERR_PTR() is returned and no caller's references are affected,
+	so the caller needs to drop the inode reference it held.
+	alloc_file_clone(file, flags, ops) does not affect any caller's references.
+	On success you get a new struct file sharing the mount/dentry with the
+	original, on failure - ERR_PTR().

Documentation/filesystems/vfs.txt

@@ -386,7 +386,7 @@ struct inode_operations {
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	void (*update_time)(struct inode *, struct timespec *, int);
 	int (*atomic_open)(struct inode *, struct dentry *, struct file *,
-			unsigned open_flag, umode_t create_mode, int *opened);
+			unsigned open_flag, umode_t create_mode);
 	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
 };
 
@@ -496,13 +496,15 @@ otherwise noted.
 
   atomic_open: called on the last component of an open.  Using this optional
   	method the filesystem can look up, possibly create and open the file in
-  	one atomic operation.  If it cannot perform this (e.g. the file type
-  	turned out to be wrong) it may signal this by returning 1 instead of
-	usual 0 or -ve .  This method is only called if the last component is
-	negative or needs lookup.  Cached positive dentries are still handled by
-	f_op->open().  If the file was created, the FILE_CREATED flag should be
-	set in "opened".  In case of O_EXCL the method must only succeed if the
-	file didn't exist and hence FILE_CREATED shall always be set on success.
+	one atomic operation.  If it wants to leave actual opening to the
+	caller (e.g. if the file turned out to be a symlink, device, or just
+	something filesystem won't do atomic open for), it may signal this by
+	returning finish_no_open(file, dentry).  This method is only called if
+	the last component is negative or needs lookup.  Cached positive dentries
+	are still handled by f_op->open().  If the file was created,
+	FMODE_CREATED flag should be set in file->f_mode.  In case of O_EXCL
+	the method must only succeed if the file didn't exist and hence FMODE_CREATED
+	shall always be set on success.
 
   tmpfile: called in the end of O_TMPFILE open().  Optional, equivalent to
 	atomically creating, opening and unlinking a file in given directory.

drivers/gpu/drm/drm_lease.c

@@ -553,7 +553,7 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 
 	/* Clone the lessor file to create a new file for us */
 	DRM_DEBUG_LEASE("Allocating lease file\n");
-	lessee_file = filp_clone_open(lessor_file);
+	lessee_file = file_clone_open(lessor_file);
 	if (IS_ERR(lessee_file)) {
 		ret = PTR_ERR(lessee_file);
 		goto out_lessee;

drivers/misc/cxl/api.c

@@ -67,10 +67,8 @@ static struct file *cxl_getfile(const char *name,
 				const struct file_operations *fops,
 				void *priv, int flags)
 {
-	struct qstr this;
-	struct path path;
 	struct file *file;
-	struct inode *inode = NULL;
+	struct inode *inode;
 	int rc;
 
 	/* strongly inspired by anon_inode_getfile() */
@@ -91,23 +89,11 @@ static struct file *cxl_getfile(const char *name,
 		goto err_fs;
 	}
 
-	file = ERR_PTR(-ENOMEM);
-	this.name = name;
-	this.len = strlen(name);
-	this.hash = 0;
-	path.dentry = d_alloc_pseudo(cxl_vfs_mount->mnt_sb, &this);
-	if (!path.dentry)
+	file = alloc_file_pseudo(inode, cxl_vfs_mount, name,
+				 flags & (O_ACCMODE | O_NONBLOCK), fops);
+	if (IS_ERR(file))
 		goto err_inode;
 
-	path.mnt = mntget(cxl_vfs_mount);
-	d_instantiate(path.dentry, inode);
-
-	file = alloc_file(&path, OPEN_FMODE(flags), fops);
-	if (IS_ERR(file)) {
-		path_put(&path);
-		goto err_fs;
-	}
-	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
 	file->private_data = priv;
 
 	return file;

drivers/scsi/cxlflash/ocxl_hw.c

@@ -88,10 +88,8 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name,
 				      const struct file_operations *fops,
 				      void *priv, int flags)
 {
-	struct qstr this;
-	struct path path;
 	struct file *file;
-	struct inode *inode = NULL;
+	struct inode *inode;
 	int rc;
 
 	if (fops->owner && !try_module_get(fops->owner)) {
@@ -116,29 +114,15 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name,
 		goto err3;
 	}
 
-	this.name = name;
-	this.len = strlen(name);
-	this.hash = 0;
-	path.dentry = d_alloc_pseudo(ocxlflash_vfs_mount->mnt_sb, &this);
-	if (!path.dentry) {
-		dev_err(dev, "%s: d_alloc_pseudo failed\n", __func__);
-		rc = -ENOMEM;
-		goto err4;
-	}
-
-	path.mnt = mntget(ocxlflash_vfs_mount);
-	d_instantiate(path.dentry, inode);
-
-	file = alloc_file(&path, OPEN_FMODE(flags), fops);
+	file = alloc_file_pseudo(inode, ocxlflash_vfs_mount, name,
+				 flags & (O_ACCMODE | O_NONBLOCK), fops);
 	if (IS_ERR(file)) {
 		rc = PTR_ERR(file);
 		dev_err(dev, "%s: alloc_file failed rc=%d\n",
 			__func__, rc);
-		path_put(&path);
-		goto err3;
+		goto err4;
 	}
 
-	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
 	file->private_data = priv;
 out:
 	return file;

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;
@@ -917,15 +916,15 @@ 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;
 
 	file->private_data = fid;
 	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;

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);

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))

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))
@@ -81,40 +79,24 @@ struct file *anon_inode_getfile(const char *name,
 	if (fops->owner && !try_module_get(fops->owner))
 		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;
 }

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;
 }

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 {

fs/ceph/file.c

@@ -429,8 +429,7 @@ int ceph_open(struct inode *inode, struct file *file)
  * 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)

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);

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);

fs/cifs/dir.c

@@ -465,8 +465,7 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid,
 
 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);