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, 64 insertions, 7 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index c90edf04a9db..9b307034d32c 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1391,7 +1391,12 @@ alloc_fail:
 	goto out;
 }
 
-static int btrfs_init_fs_root(struct btrfs_root *root)
+/*
+ * Initialize subvolume root in-memory structure
+ *
+ * @anon_dev:	anonymous device to attach to the root, if zero, allocate new
+ */
+static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev)
 {
 	int ret;
 	unsigned int nofs_flag;
@@ -1430,9 +1435,13 @@ static int btrfs_init_fs_root(struct btrfs_root *root)
 	 */
 	if (is_fstree(root->root_key.objectid) &&
 	    btrfs_root_refs(&root->root_item) > 0) {
-		ret = get_anon_bdev(&root->anon_dev);
-		if (ret)
-			goto fail;
+		if (!anon_dev) {
+			ret = get_anon_bdev(&root->anon_dev);
+			if (ret)
+				goto fail;
+		} else {
+			root->anon_dev = anon_dev;
+		}
 	}
 
 	mutex_lock(&root->objectid_mutex);
@@ -1537,8 +1546,27 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info)
 }
 
 
-struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
-				     u64 objectid, bool check_ref)
+/*
+ * Get an in-memory reference of a root structure.
+ *
+ * For essential trees like root/extent tree, we grab it from fs_info directly.
+ * For subvolume trees, we check the cached filesystem roots first. If not
+ * found, then read it from disk and add it to cached fs roots.
+ *
+ * Caller should release the root by calling btrfs_put_root() after the usage.
+ *
+ * NOTE: Reloc and log trees can't be read by this function as they share the
+ *	 same root objectid.
+ *
+ * @objectid:	root id
+ * @anon_dev:	preallocated anonymous block device number for new roots,
+ * 		pass 0 for new allocation.
+ * @check_ref:	whether to check root item references, If true, return -ENOENT
+ *		for orphan roots
+ */
+static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info,
+					     u64 objectid, dev_t anon_dev,
+					     bool check_ref)
 {
 	struct btrfs_root *root;
 	struct btrfs_path *path;
@@ -1567,6 +1595,8 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
 again:
 	root = btrfs_lookup_fs_root(fs_info, objectid);
 	if (root) {
+		/* Shouldn't get preallocated anon_dev for cached roots */
+		ASSERT(!anon_dev);
 		if (check_ref && btrfs_root_refs(&root->root_item) == 0) {
 			btrfs_put_root(root);
 			return ERR_PTR(-ENOENT);
@@ -1586,7 +1616,7 @@ again:
 		goto fail;
 	}
 
-	ret = btrfs_init_fs_root(root);
+	ret = btrfs_init_fs_root(root, anon_dev);
 	if (ret)
 		goto fail;
 
@@ -1619,6 +1649,33 @@ fail:
 	return ERR_PTR(ret);
 }
 
+/*
+ * Get in-memory reference of a root structure
+ *
+ * @objectid:	tree objectid
+ * @check_ref:	if set, verify that the tree exists and the item has at least
+ *		one reference
+ */
+struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
+				     u64 objectid, bool check_ref)
+{
+	return btrfs_get_root_ref(fs_info, objectid, 0, check_ref);
+}
+
+/*
+ * Get in-memory reference of a root structure, created as new, optionally pass
+ * the anonymous block device id
+ *
+ * @objectid:	tree objectid
+ * @anon_dev:	if zero, allocate a new anonymous block device or use the
+ *		parameter value
+ */
+struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
+					 u64 objectid, dev_t anon_dev)
+{
+	return btrfs_get_root_ref(fs_info, objectid, anon_dev, true);
+}
+
 static int btrfs_congested_fn(void *congested_data, int bdi_bits)
 {
 	struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data;