btrfs: preallocate anon block device at first phase of snapshot creation

[BUG]
When the anonymous block device pool is exhausted, subvolume/snapshot
creation fails with EMFILE (Too many files open). This has been reported
by a user. The allocation happens in the second phase during transaction
commit where it's only way out is to abort the transaction

  BTRFS: Transaction aborted (error -24)
  WARNING: CPU: 17 PID: 17041 at fs/btrfs/transaction.c:1576 create_pending_snapshot+0xbc4/0xd10 [btrfs]
  RIP: 0010:create_pending_snapshot+0xbc4/0xd10 [btrfs]
  Call Trace:
   create_pending_snapshots+0x82/0xa0 [btrfs]
   btrfs_commit_transaction+0x275/0x8c0 [btrfs]
   btrfs_mksubvol+0x4b9/0x500 [btrfs]
   btrfs_ioctl_snap_create_transid+0x174/0x180 [btrfs]
   btrfs_ioctl_snap_create_v2+0x11c/0x180 [btrfs]
   btrfs_ioctl+0x11a4/0x2da0 [btrfs]
   do_vfs_ioctl+0xa9/0x640
   ksys_ioctl+0x67/0x90
   __x64_sys_ioctl+0x1a/0x20
   do_syscall_64+0x5a/0x110
   entry_SYSCALL_64_after_hwframe+0x44/0xa9
  ---[ end trace 33f2f83f3d5250e9 ]---
  BTRFS: error (device sda1) in create_pending_snapshot:1576: errno=-24 unknown
  BTRFS info (device sda1): forced readonly
  BTRFS warning (device sda1): Skipping commit of aborted transaction.
  BTRFS: error (device sda1) in cleanup_transaction:1831: errno=-24 unknown

[CAUSE]
When the global anonymous block device pool is exhausted, the following
call chain will fail, and lead to transaction abort:

 btrfs_ioctl_snap_create_v2()
 |- btrfs_ioctl_snap_create_transid()
    |- btrfs_mksubvol()
       |- btrfs_commit_transaction()
          |- create_pending_snapshot()
             |- btrfs_get_fs_root()
                |- btrfs_init_fs_root()
                   |- get_anon_bdev()

[FIX]
Although we can't enlarge the anonymous block device pool, at least we
can preallocate anon_dev for subvolume/snapshot in the first phase,
outside of transaction context and exactly at the moment the user calls
the creation ioctl.

Reported-by: Greed Rong <greedrong@gmail.com>
Link: https://lore.kernel.org/linux-btrfs/CA+UqX+NTrZ6boGnWHhSeZmEY5J76CTqmYjO2S+=tHJX7nb9DPw@mail.gmail.com/
CC: stable@vger.kernel.org # 4.4+
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 20 insertions, 1 deletions

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 4adfdfa28e53..ab34179d7cbc 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -566,6 +566,7 @@ static noinline int create_subvol(struct inode *dir,
 	struct inode *inode;
 	int ret;
 	int err;
+	dev_t anon_dev = 0;
 	u64 objectid;
 	u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID;
 	u64 index = 0;
@@ -578,6 +579,10 @@ static noinline int create_subvol(struct inode *dir,
 	if (ret)
 		goto fail_free;
 
+	ret = get_anon_bdev(&anon_dev);
+	if (ret < 0)
+		goto fail_free;
+
 	/*
 	 * Don't create subvolume whose level is not zero. Or qgroup will be
 	 * screwed up since it assumes subvolume qgroup's level to be 0.
@@ -660,12 +665,15 @@ static noinline int create_subvol(struct inode *dir,
 		goto fail;
 
 	key.offset = (u64)-1;
-	new_root = btrfs_get_fs_root(fs_info, objectid, true);
+	new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev);
 	if (IS_ERR(new_root)) {
+		free_anon_bdev(anon_dev);
 		ret = PTR_ERR(new_root);
 		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
+	/* Freeing will be done in btrfs_put_root() of new_root */
+	anon_dev = 0;
 
 	btrfs_record_root_in_trans(trans, new_root);
 
@@ -735,6 +743,8 @@ fail:
 	return ret;
 
 fail_free:
+	if (anon_dev)
+		free_anon_bdev(anon_dev);
 	kfree(root_item);
 	return ret;
 }
@@ -762,6 +772,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	if (!pending_snapshot)
 		return -ENOMEM;
 
+	ret = get_anon_bdev(&pending_snapshot->anon_dev);
+	if (ret < 0)
+		goto free_pending;
 	pending_snapshot->root_item = kzalloc(sizeof(struct btrfs_root_item),
 			GFP_KERNEL);
 	pending_snapshot->path = btrfs_alloc_path();
@@ -823,10 +836,16 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 
 	d_instantiate(dentry, inode);
 	ret = 0;
+	pending_snapshot->anon_dev = 0;
 fail:
+	/* Prevent double freeing of anon_dev */
+	if (ret && pending_snapshot->snap)
+		pending_snapshot->snap->anon_dev = 0;
 	btrfs_put_root(pending_snapshot->snap);
 	btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv);
 free_pending:
+	if (pending_snapshot->anon_dev)
+		free_anon_bdev(pending_snapshot->anon_dev);
 	kfree(pending_snapshot->root_item);
 	btrfs_free_path(pending_snapshot->path);
 	kfree(pending_snapshot);