1 files changed, 97 insertions, 10 deletions

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index d31a0c4f56be..ef9c55bc7907 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -27,6 +27,7 @@
 #include "backref.h"
 #include "hash.h"
 #include "compression.h"
+#include "qgroup.h"
 
 /* magic values for the inode_only field in btrfs_log_inode:
  *
@@ -680,6 +681,21 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 		ins.type = BTRFS_EXTENT_ITEM_KEY;
 		offset = key->offset - btrfs_file_extent_offset(eb, item);
 
+		/*
+		 * Manually record dirty extent, as here we did a shallow
+		 * file extent item copy and skip normal backref update,
+		 * but modifying extent tree all by ourselves.
+		 * So need to manually record dirty extent for qgroup,
+		 * as the owner of the file extent changed from log tree
+		 * (doesn't affect qgroup) to fs/file tree(affects qgroup)
+		 */
+		ret = btrfs_qgroup_insert_dirty_extent(trans, root->fs_info,
+				btrfs_file_extent_disk_bytenr(eb, item),
+				btrfs_file_extent_disk_num_bytes(eb, item),
+				GFP_NOFS);
+		if (ret < 0)
+			goto out;
+
 		if (ins.objectid > 0) {
 			u64 csum_start;
 			u64 csum_end;
@@ -2807,7 +2823,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	 */
 	mutex_unlock(&root->log_mutex);
 
-	btrfs_init_log_ctx(&root_log_ctx);
+	btrfs_init_log_ctx(&root_log_ctx, NULL);
 
 	mutex_lock(&log_root_tree->log_mutex);
 	atomic_inc(&log_root_tree->log_batch);
@@ -2851,6 +2867,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 
 	if (log_root_tree->log_transid_committed >= root_log_ctx.log_transid) {
 		blk_finish_plug(&plug);
+		list_del_init(&root_log_ctx.list);
 		mutex_unlock(&log_root_tree->log_mutex);
 		ret = root_log_ctx.log_ret;
 		goto out;
@@ -4469,7 +4486,8 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans,
 static int btrfs_check_ref_name_override(struct extent_buffer *eb,
 					 const int slot,
 					 const struct btrfs_key *key,
-					 struct inode *inode)
+					 struct inode *inode,
+					 u64 *other_ino)
 {
 	int ret;
 	struct btrfs_path *search_path;
@@ -4528,7 +4546,16 @@ static int btrfs_check_ref_name_override(struct extent_buffer *eb,
 					   search_path, parent,
 					   name, this_name_len, 0);
 		if (di && !IS_ERR(di)) {
-			ret = 1;
+			struct btrfs_key di_key;
+
+			btrfs_dir_item_key_to_cpu(search_path->nodes[0],
+						  di, &di_key);
+			if (di_key.type == BTRFS_INODE_ITEM_KEY) {
+				ret = 1;
+				*other_ino = di_key.objectid;
+			} else {
+				ret = -EAGAIN;
+			}
 			goto out;
 		} else if (IS_ERR(di)) {
 			ret = PTR_ERR(di);
@@ -4722,16 +4749,72 @@ again:
 		if ((min_key.type == BTRFS_INODE_REF_KEY ||
 		     min_key.type == BTRFS_INODE_EXTREF_KEY) &&
 		    BTRFS_I(inode)->generation == trans->transid) {
+			u64 other_ino = 0;
+
 			ret = btrfs_check_ref_name_override(path->nodes[0],
 							    path->slots[0],
-							    &min_key, inode);
+							    &min_key, inode,
+							    &other_ino);
 			if (ret < 0) {
 				err = ret;
 				goto out_unlock;
-			} else if (ret > 0) {
-				err = 1;
-				btrfs_set_log_full_commit(root->fs_info, trans);
-				goto out_unlock;
+			} else if (ret > 0 && ctx &&
+				   other_ino != btrfs_ino(ctx->inode)) {
+				struct btrfs_key inode_key;
+				struct inode *other_inode;
+
+				if (ins_nr > 0) {
+					ins_nr++;
+				} else {
+					ins_nr = 1;
+					ins_start_slot = path->slots[0];
+				}
+				ret = copy_items(trans, inode, dst_path, path,
+						 &last_extent, ins_start_slot,
+						 ins_nr, inode_only,
+						 logged_isize);
+				if (ret < 0) {
+					err = ret;
+					goto out_unlock;
+				}
+				ins_nr = 0;
+				btrfs_release_path(path);
+				inode_key.objectid = other_ino;
+				inode_key.type = BTRFS_INODE_ITEM_KEY;
+				inode_key.offset = 0;
+				other_inode = btrfs_iget(root->fs_info->sb,
+							 &inode_key, root,
+							 NULL);
+				/*
+				 * If the other inode that had a conflicting dir
+				 * entry was deleted in the current transaction,
+				 * we don't need to do more work nor fallback to
+				 * a transaction commit.
+				 */
+				if (IS_ERR(other_inode) &&
+				    PTR_ERR(other_inode) == -ENOENT) {
+					goto next_key;
+				} else if (IS_ERR(other_inode)) {
+					err = PTR_ERR(other_inode);
+					goto out_unlock;
+				}
+				/*
+				 * We are safe logging the other inode without
+				 * acquiring its i_mutex as long as we log with
+				 * the LOG_INODE_EXISTS mode. We're safe against
+				 * concurrent renames of the other inode as well
+				 * because during a rename we pin the log and
+				 * update the log with the new name before we
+				 * unpin it.
+				 */
+				err = btrfs_log_inode(trans, root, other_inode,
+						      LOG_INODE_EXISTS,
+						      0, LLONG_MAX, ctx);
+				iput(other_inode);
+				if (err)
+					goto out_unlock;
+				else
+					goto next_key;
 			}
 		}
 
@@ -4799,7 +4882,7 @@ next_slot:
 			ins_nr = 0;
 		}
 		btrfs_release_path(path);
-
+next_key:
 		if (min_key.offset < (u64)-1) {
 			min_key.offset++;
 		} else if (min_key.type < max_key.type) {
@@ -4993,8 +5076,12 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
 		if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
 			break;
 
-		if (IS_ROOT(parent))
+		if (IS_ROOT(parent)) {
+			inode = d_inode(parent);
+			if (btrfs_must_commit_transaction(trans, inode))
+				ret = 1;
 			break;
+		}
 
 		parent = dget_parent(parent);
 		dput(old_parent);