Merge tag 'for-5.5-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:
 "A mix of regression fixes and regular fixes for stable trees:

   - fix swapped error messages for qgroup enable/rescan

   - fixes for NO_HOLES feature with clone range

   - fix deadlock between iget/srcu lock/synchronize srcu while freeing
     an inode

   - fix double lock on subvolume cross-rename

   - tree log fixes
      * fix missing data checksums after replaying a log tree
      * also teach tree-checker about this problem
      * skip log replay on orphaned roots

   - fix maximum devices constraints for RAID1C -3 and -4

   - send: don't print warning on read-only mount regarding orphan
     cleanup

   - error handling fixes"

* tag 'for-5.5-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: send: remove WARN_ON for readonly mount
  btrfs: do not leak reloc root if we fail to read the fs root
  btrfs: skip log replay on orphaned roots
  btrfs: handle ENOENT in btrfs_uuid_tree_iterate
  btrfs: abort transaction after failed inode updates in create_subvol
  Btrfs: fix hole extent items with a zero size after range cloning
  Btrfs: fix removal logic of the tree mod log that leads to use-after-free issues
  Btrfs: make tree checker detect checksum items with overlapping ranges
  Btrfs: fix missing data checksums after replaying a log tree
  btrfs: return error pointer from alloc_test_extent_buffer
  btrfs: fix devs_max constraints for raid1c3 and raid1c4
  btrfs: tree-checker: Fix error format string for size_t
  btrfs: don't double lock the subvol_sem for rename exchange
  btrfs: handle error in btrfs_cache_block_group
  btrfs: do not call synchronize_srcu() in inode_tree_del
  Btrfs: fix cloning range with a hole when using the NO_HOLES feature
  btrfs: Fix error messages in qgroup_rescan_init

1 files changed, 47 insertions, 5 deletions

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 6f757361db53..d3f115909ff0 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -808,7 +808,8 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 						struct btrfs_ordered_sum,
 						list);
 				if (!ret)
-					ret = btrfs_del_csums(trans, fs_info,
+					ret = btrfs_del_csums(trans,
+							      fs_info->csum_root,
 							      sums->bytenr,
 							      sums->len);
 				if (!ret)
@@ -3909,6 +3910,28 @@ static int log_inode_item(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
+static int log_csums(struct btrfs_trans_handle *trans,
+		     struct btrfs_root *log_root,
+		     struct btrfs_ordered_sum *sums)
+{
+	int ret;
+
+	/*
+	 * Due to extent cloning, we might have logged a csum item that covers a
+	 * subrange of a cloned extent, and later we can end up logging a csum
+	 * item for a larger subrange of the same extent or the entire range.
+	 * This would leave csum items in the log tree that cover the same range
+	 * and break the searches for checksums in the log tree, resulting in
+	 * some checksums missing in the fs/subvolume tree. So just delete (or
+	 * trim and adjust) any existing csum items in the log for this range.
+	 */
+	ret = btrfs_del_csums(trans, log_root, sums->bytenr, sums->len);
+	if (ret)
+		return ret;
+
+	return btrfs_csum_file_blocks(trans, log_root, sums);
+}
+
 static noinline int copy_items(struct btrfs_trans_handle *trans,
 			       struct btrfs_inode *inode,
 			       struct btrfs_path *dst_path,
@@ -4054,7 +4077,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 						   struct btrfs_ordered_sum,
 						   list);
 		if (!ret)
-			ret = btrfs_csum_file_blocks(trans, log, sums);
+			ret = log_csums(trans, log, sums);
 		list_del(&sums->list);
 		kfree(sums);
 	}
@@ -4274,7 +4297,7 @@ static int log_extent_csums(struct btrfs_trans_handle *trans,
 						   struct btrfs_ordered_sum,
 						   list);
 		if (!ret)
-			ret = btrfs_csum_file_blocks(trans, log_root, sums);
+			ret = log_csums(trans, log_root, sums);
 		list_del(&sums->list);
 		kfree(sums);
 	}
@@ -6294,9 +6317,28 @@ again:
 		wc.replay_dest = btrfs_read_fs_root_no_name(fs_info, &tmp_key);
 		if (IS_ERR(wc.replay_dest)) {
 			ret = PTR_ERR(wc.replay_dest);
+
+			/*
+			 * We didn't find the subvol, likely because it was
+			 * deleted.  This is ok, simply skip this log and go to
+			 * the next one.
+			 *
+			 * We need to exclude the root because we can't have
+			 * other log replays overwriting this log as we'll read
+			 * it back in a few more times.  This will keep our
+			 * block from being modified, and we'll just bail for
+			 * each subsequent pass.
+			 */
+			if (ret == -ENOENT)
+				ret = btrfs_pin_extent_for_log_replay(fs_info,
+							log->node->start,
+							log->node->len);
 			free_extent_buffer(log->node);
 			free_extent_buffer(log->commit_root);
 			kfree(log);
+
+			if (!ret)
+				goto next;
 			btrfs_handle_fs_error(fs_info, ret,
 				"Couldn't read target root for tree log recovery.");
 			goto error;
@@ -6328,7 +6370,6 @@ again:
 						  &root->highest_objectid);
 		}
 
-		key.offset = found_key.offset - 1;
 		wc.replay_dest->log_root = NULL;
 		free_extent_buffer(log->node);
 		free_extent_buffer(log->commit_root);
@@ -6336,9 +6377,10 @@ again:
 
 		if (ret)
 			goto error;
-
+next:
 		if (found_key.offset == 0)
 			break;
+		key.offset = found_key.offset - 1;
 	}
 	btrfs_release_path(path);