Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs update from Al Viro:

 - big one - consolidation of descriptor-related logics; almost all of
   that is moved to fs/file.c

   (BTW, I'm seriously tempted to rename the result to fd.c.  As it is,
   we have a situation when file_table.c is about handling of struct
   file and file.c is about handling of descriptor tables; the reasons
   are historical - file_table.c used to be about a static array of
   struct file we used to have way back).

   A lot of stray ends got cleaned up and converted to saner primitives,
   disgusting mess in android/binder.c is still disgusting, but at least
   doesn't poke so much in descriptor table guts anymore.  A bunch of
   relatively minor races got fixed in process, plus an ext4 struct file
   leak.

 - related thing - fget_light() partially unuglified; see fdget() in
   there (and yes, it generates the code as good as we used to have).

 - also related - bits of Cyrill's procfs stuff that got entangled into
   that work; _not_ all of it, just the initial move to fs/proc/fd.c and
   switch of fdinfo to seq_file.

 - Alex's fs/coredump.c spiltoff - the same story, had been easier to
   take that commit than mess with conflicts.  The rest is a separate
   pile, this was just a mechanical code movement.

 - a few misc patches all over the place.  Not all for this cycle,
   there'll be more (and quite a few currently sit in akpm's tree)."

Fix up trivial conflicts in the android binder driver, and some fairly
simple conflicts due to two different changes to the sock_alloc_file()
interface ("take descriptor handling from sock_alloc_file() to callers"
vs "net: Providing protocol type via system.sockprotoname xattr of
/proc/PID/fd entries" adding a dentry name to the socket)

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (72 commits)
  MAX_LFS_FILESIZE should be a loff_t
  compat: fs: Generic compat_sys_sendfile implementation
  fs: push rcu_barrier() from deactivate_locked_super() to filesystems
  btrfs: reada_extent doesn't need kref for refcount
  coredump: move core dump functionality into its own file
  coredump: prevent double-free on an error path in core dumper
  usb/gadget: fix misannotations
  fcntl: fix misannotations
  ceph: don't abuse d_delete() on failure exits
  hypfs: ->d_parent is never NULL or negative
  vfs: delete surplus inode NULL check
  switch simple cases of fget_light to fdget
  new helpers: fdget()/fdput()
  switch o2hb_region_dev_write() to fget_light()
  proc_map_files_readdir(): don't bother with grabbing files
  make get_file() return its argument
  vhost_set_vring(): turn pollstart/pollstop into bool
  switch prctl_set_mm_exe_file() to fget_light()
  switch xfs_find_handle() to fget_light()
  switch xfs_swapext() to fget_light()
  ...

4 files changed, 33 insertions, 28 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 4c87847..b08ea47 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -107,6 +107,12 @@ void extent_io_exit(void)
 		list_del(&eb->leak_list);
 		kmem_cache_free(extent_buffer_cache, eb);
 	}
+
+	/*
+	 * Make sure all delayed rcu free are flushed before we
+	 * destroy caches.
+	 */
+	rcu_barrier();
 	if (extent_state_cache)
 		kmem_cache_destroy(extent_state_cache);
 	if (extent_buffer_cache)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 2a028a5..a6ed694 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7076,6 +7076,11 @@ static void init_once(void *foo)
 
 void btrfs_destroy_cachep(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	if (btrfs_inode_cachep)
 		kmem_cache_destroy(btrfs_inode_cachep);
 	if (btrfs_trans_handle_cachep)
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 27bfce5..47127c1 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1397,7 +1397,6 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
 				u64 *transid, bool readonly,
 				struct btrfs_qgroup_inherit **inherit)
 {
-	struct file *src_file;
 	int namelen;
 	int ret = 0;
 
@@ -1421,25 +1420,24 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
 		ret = btrfs_mksubvol(&file->f_path, name, namelen,
 				     NULL, transid, readonly, inherit);
 	} else {
+		struct fd src = fdget(fd);
 		struct inode *src_inode;
-		src_file = fget(fd);
-		if (!src_file) {
+		if (!src.file) {
 			ret = -EINVAL;
 			goto out_drop_write;
 		}
 
-		src_inode = src_file->f_path.dentry->d_inode;
+		src_inode = src.file->f_path.dentry->d_inode;
 		if (src_inode->i_sb != file->f_path.dentry->d_inode->i_sb) {
 			printk(KERN_INFO "btrfs: Snapshot src from "
 			       "another FS\n");
 			ret = -EINVAL;
-			fput(src_file);
-			goto out_drop_write;
+		} else {
+			ret = btrfs_mksubvol(&file->f_path, name, namelen,
+					     BTRFS_I(src_inode)->root,
+					     transid, readonly, inherit);
 		}
-		ret = btrfs_mksubvol(&file->f_path, name, namelen,
-				     BTRFS_I(src_inode)->root,
-				     transid, readonly, inherit);
-		fput(src_file);
+		fdput(src);
 	}
 out_drop_write:
 	mnt_drop_write_file(file);
@@ -2341,7 +2339,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 {
 	struct inode *inode = fdentry(file)->d_inode;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct file *src_file;
+	struct fd src_file;
 	struct inode *src;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_path *path;
@@ -2376,24 +2374,24 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 	if (ret)
 		return ret;
 
-	src_file = fget(srcfd);
-	if (!src_file) {
+	src_file = fdget(srcfd);
+	if (!src_file.file) {
 		ret = -EBADF;
 		goto out_drop_write;
 	}
 
 	ret = -EXDEV;
-	if (src_file->f_path.mnt != file->f_path.mnt)
+	if (src_file.file->f_path.mnt != file->f_path.mnt)
 		goto out_fput;
 
-	src = src_file->f_dentry->d_inode;
+	src = src_file.file->f_dentry->d_inode;
 
 	ret = -EINVAL;
 	if (src == inode)
 		goto out_fput;
 
 	/* the src must be open for reading */
-	if (!(src_file->f_mode & FMODE_READ))
+	if (!(src_file.file->f_mode & FMODE_READ))
 		goto out_fput;
 
 	/* don't make the dst file partly checksummed */
@@ -2724,7 +2722,7 @@ out_unlock:
 	vfree(buf);
 	btrfs_free_path(path);
 out_fput:
-	fput(src_file);
+	fdput(src_file);
 out_drop_write:
 	mnt_drop_write_file(file);
 	return ret;
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 48a4882..a955669 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -68,7 +68,7 @@ struct reada_extent {
 	u32			blocksize;
 	int			err;
 	struct list_head	extctl;
-	struct kref		refcnt;
+	int 			refcnt;
 	spinlock_t		lock;
 	struct reada_zone	*zones[BTRFS_MAX_MIRRORS];
 	int			nzones;
@@ -126,7 +126,7 @@ static int __readahead_hook(struct btrfs_root *root, struct extent_buffer *eb,
 	spin_lock(&fs_info->reada_lock);
 	re = radix_tree_lookup(&fs_info->reada_tree, index);
 	if (re)
-		kref_get(&re->refcnt);
+		re->refcnt++;
 	spin_unlock(&fs_info->reada_lock);
 
 	if (!re)
@@ -336,7 +336,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 	spin_lock(&fs_info->reada_lock);
 	re = radix_tree_lookup(&fs_info->reada_tree, index);
 	if (re)
-		kref_get(&re->refcnt);
+		re->refcnt++;
 	spin_unlock(&fs_info->reada_lock);
 
 	if (re)
@@ -352,7 +352,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 	re->top = *top;
 	INIT_LIST_HEAD(&re->extctl);
 	spin_lock_init(&re->lock);
-	kref_init(&re->refcnt);
+	re->refcnt = 1;
 
 	/*
 	 * map block
@@ -398,7 +398,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 	if (ret == -EEXIST) {
 		re_exist = radix_tree_lookup(&fs_info->reada_tree, index);
 		BUG_ON(!re_exist);
-		kref_get(&re_exist->refcnt);
+		re_exist->refcnt++;
 		spin_unlock(&fs_info->reada_lock);
 		goto error;
 	}
@@ -465,10 +465,6 @@ error:
 	return re_exist;
 }
 
-static void reada_kref_dummy(struct kref *kr)
-{
-}
-
 static void reada_extent_put(struct btrfs_fs_info *fs_info,
 			     struct reada_extent *re)
 {
@@ -476,7 +472,7 @@ static void reada_extent_put(struct btrfs_fs_info *fs_info,
 	unsigned long index = re->logical >> PAGE_CACHE_SHIFT;
 
 	spin_lock(&fs_info->reada_lock);
-	if (!kref_put(&re->refcnt, reada_kref_dummy)) {
+	if (--re->refcnt) {
 		spin_unlock(&fs_info->reada_lock);
 		return;
 	}
@@ -671,7 +667,7 @@ static int reada_start_machine_dev(struct btrfs_fs_info *fs_info,
 		return 0;
 	}
 	dev->reada_next = re->logical + re->blocksize;
-	kref_get(&re->refcnt);
+	re->refcnt++;
 
 	spin_unlock(&fs_info->reada_lock);