[PATCH 1/2] Btrfs: use global reserve when deleting unused block group after ENOSPC

[fdmanana@kernel.org]

From: Filipe Manana <fdmanana@suse.com>

It's possible to reach a state where the cleaner kthread isn't able to
start a transaction to delete an unused block group due to lack of enough
free metadata space and due to lack of unallocated device space to allocate
a new metadata block group as well. If this happens try to use space from
the global block group reserve just like we do for unlink operations, so
that we don't reach a permanent state where starting a transaction for
filesystem operations (file creation, renames, etc) keeps failing with
-ENOSPC. Such an unfortunate state was observed on a machine where over
a dozen unused data block groups existed and the cleaner kthread was
failing to delete them due to ENOSPC error when attempting to start a
transaction, and even running balance with a -dusage=0 filter failed with
ENOSPC as well. Also unmounting and mounting again the filesystem didn't
help. Allowing the cleaner kthread to use the global block reserve to
delete the unused data block groups fixed the problem.

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Jeff Mahoney <jeffm@suse.com>
---
 fs/btrfs/ctree.h       |  2 ++
 fs/btrfs/extent-tree.c | 14 ++++++++++++--
 fs/btrfs/inode.c       | 24 +-----------------------
 fs/btrfs/transaction.c | 32 ++++++++++++++++++++++++++++++++
 fs/btrfs/transaction.h |  4 ++++
 fs/btrfs/volumes.c     |  2 +-
 6 files changed, 52 insertions(+), 26 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index a2e73f6..1573be6 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3479,6 +3479,8 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root, u64 bytes_used,
 			   u64 type, u64 chunk_objectid, u64 chunk_offset,
 			   u64 size);
+struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
+				struct btrfs_fs_info *fs_info);
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root, u64 group_start,
 			     struct extent_map *em);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index acf3ed1..7820093 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -10256,6 +10256,17 @@ out:
 	return ret;
 }
 
+struct btrfs_trans_handle *
+btrfs_start_trans_remove_block_group(struct btrfs_fs_info *fs_info)
+{
+	/*
+	 * 1 unit for adding the free space inode's orphan (located in the tree
+	 * of tree roots).
+	 */
+	return btrfs_start_transaction_fallback_global_rsv(fs_info->extent_root,
+							   1, 1);
+}
+
 /*
  * Process the unused_bgs list and remove any that don't have any allocated
  * space inside of them.
@@ -10322,8 +10333,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		 * Want to do this before we do anything else so we can recover
 		 * properly if we fail to join the transaction.
 		 */
-		/* 1 for btrfs_orphan_reserve_metadata() */
-		trans = btrfs_start_transaction(root, 1);
+		trans = btrfs_start_trans_remove_block_group(fs_info);
 		if (IS_ERR(trans)) {
 			btrfs_dec_block_group_ro(root, block_group);
 			ret = PTR_ERR(trans);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 6e93349..f82d1f4 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4046,9 +4046,7 @@ int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
  */
 static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir)
 {
-	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
-	int ret;
 
 	/*
 	 * 1 for the possible orphan item
@@ -4057,27 +4055,7 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir)
 	 * 1 for the inode ref
 	 * 1 for the inode
 	 */
-	trans = btrfs_start_transaction(root, 5);
-	if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC)
-		return trans;
-
-	if (PTR_ERR(trans) == -ENOSPC) {
-		u64 num_bytes = btrfs_calc_trans_metadata_size(root, 5);
-
-		trans = btrfs_start_transaction(root, 0);
-		if (IS_ERR(trans))
-			return trans;
-		ret = btrfs_cond_migrate_bytes(root->fs_info,
-					       &root->fs_info->trans_block_rsv,
-					       num_bytes, 5);
-		if (ret) {
-			btrfs_end_transaction(trans, root);
-			return ERR_PTR(ret);
-		}
-		trans->block_rsv = &root->fs_info->trans_block_rsv;
-		trans->bytes_reserved = num_bytes;
-	}
-	return trans;
+	return btrfs_start_transaction_fallback_global_rsv(root, 5, 5);
 }
 
 static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 418c6a2..3367a3c 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -592,6 +592,38 @@ struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
 	return start_transaction(root, num_items, TRANS_START,
 				 BTRFS_RESERVE_FLUSH_ALL);
 }
+struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
+					struct btrfs_root *root,
+					unsigned int num_items,
+					int min_factor)
+{
+	struct btrfs_trans_handle *trans;
+	u64 num_bytes;
+	int ret;
+
+	trans = btrfs_start_transaction(root, num_items);
+	if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC)
+		return trans;
+
+	trans = btrfs_start_transaction(root, 0);
+	if (IS_ERR(trans))
+		return trans;
+
+	num_bytes = btrfs_calc_trans_metadata_size(root, num_items);
+	ret = btrfs_cond_migrate_bytes(root->fs_info,
+				       &root->fs_info->trans_block_rsv,
+				       num_bytes,
+				       min_factor);
+	if (ret) {
+		btrfs_end_transaction(trans, root);
+		return ERR_PTR(ret);
+	}
+
+	trans->block_rsv = &root->fs_info->trans_block_rsv;
+	trans->bytes_reserved = num_bytes;
+
+	return trans;
+}
 
 struct btrfs_trans_handle *btrfs_start_transaction_lflush(
 					struct btrfs_root *root,
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index b05b2f6..0da21ca 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -185,6 +185,10 @@ int btrfs_end_transaction(struct btrfs_trans_handle *trans,
 			  struct btrfs_root *root);
 struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
 						   unsigned int num_items);
+struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
+					struct btrfs_root *root,
+					unsigned int num_items,
+					int min_factor);
 struct btrfs_trans_handle *btrfs_start_transaction_lflush(
 					struct btrfs_root *root,
 					unsigned int num_items);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index d198dd3..e0bd364 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2853,7 +2853,7 @@ static int btrfs_relocate_chunk(struct btrfs_root *root, u64 chunk_offset)
 	if (ret)
 		return ret;
 
-	trans = btrfs_start_transaction(root, 0);
+	trans = btrfs_start_trans_remove_block_group(root->fs_info);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
 		btrfs_std_error(root->fs_info, ret, NULL);
-- 
2.1.3