Merge tag 'for-6.2-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:
 "Another batch of fixes, dealing with fallouts from 6.1 reported by
  users:

   - tree-log fixes:
       - fix directory logging due to race with concurrent index key
         deletion
       - fix missing error handling when logging directory items
       - handle case of conflicting inodes being added to the log
       - remove transaction aborts for not so serious errors

   - fix qgroup accounting warning when rescan can be started at time
     with temporarily disable accounting

   - print more specific errors to system log when device scan ioctl
     fails

   - disable space overcommit for ZNS devices, causing heavy performance
     drop"

* tag 'for-6.2-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: do not abort transaction on failure to update log root
  btrfs: do not abort transaction on failure to write log tree when syncing log
  btrfs: add missing setup of log for full commit at add_conflicting_inode()
  btrfs: fix directory logging due to race with concurrent index key deletion
  btrfs: fix missing error handling when logging directory items
  btrfs: zoned: enable metadata over-commit for non-ZNS setup
  btrfs: qgroup: do not warn on record without old_roots populated
  btrfs: add extra error messages to cover non-ENOMEM errors from device_add_list()

7 files changed, 71 insertions, 21 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 8aeaada1fcae..3aa04224315e 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -367,7 +367,14 @@ error:
 	btrfs_print_tree(eb, 0);
 	btrfs_err(fs_info, "block=%llu write time tree block corruption detected",
 		  eb->start);
-	WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
+	/*
+	 * Be noisy if this is an extent buffer from a log tree. We don't abort
+	 * a transaction in case there's a bad log tree extent buffer, we just
+	 * fallback to a transaction commit. Still we want to know when there is
+	 * a bad log tree extent buffer, as that may signal a bug somewhere.
+	 */
+	WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG) ||
+		btrfs_header_owner(eb) == BTRFS_TREE_LOG_OBJECTID);
 	return ret;
 }
 
diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h
index a749367e5ae2..37b86acfcbcf 100644
--- a/fs/btrfs/fs.h
+++ b/fs/btrfs/fs.h
@@ -119,6 +119,12 @@ enum {
 	/* Indicate that we want to commit the transaction. */
 	BTRFS_FS_NEED_TRANS_COMMIT,
 
+	/*
+	 * Indicate metadata over-commit is disabled. This is set when active
+	 * zone tracking is needed.
+	 */
+	BTRFS_FS_NO_OVERCOMMIT,
+
 #if BITS_PER_LONG == 32
 	/* Indicate if we have error/warn message printed on 32bit systems */
 	BTRFS_FS_32BIT_ERROR,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index d275bf24b250..00851c86aa8a 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2765,9 +2765,19 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
 
 			/*
 			 * Old roots should be searched when inserting qgroup
-			 * extent record
+			 * extent record.
+			 *
+			 * But for INCONSISTENT (NO_ACCOUNTING) -> rescan case,
+			 * we may have some record inserted during
+			 * NO_ACCOUNTING (thus no old_roots populated), but
+			 * later we start rescan, which clears NO_ACCOUNTING,
+			 * leaving some inserted records without old_roots
+			 * populated.
+			 *
+			 * Those cases are rare and should not cause too much
+			 * time spent during commit_transaction().
 			 */
-			if (WARN_ON(!record->old_roots)) {
+			if (!record->old_roots) {
 				/* Search commit root to find old_roots */
 				ret = btrfs_find_all_roots(&ctx, false);
 				if (ret < 0)
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index d28ee4e36f3d..69c09508afb5 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -407,7 +407,8 @@ int btrfs_can_overcommit(struct btrfs_fs_info *fs_info,
 		return 0;
 
 	used = btrfs_space_info_used(space_info, true);
-	if (btrfs_is_zoned(fs_info) && (space_info->flags & BTRFS_BLOCK_GROUP_METADATA))
+	if (test_bit(BTRFS_FS_NO_OVERCOMMIT, &fs_info->flags) &&
+	    (space_info->flags & BTRFS_BLOCK_GROUP_METADATA))
 		avail = 0;
 	else
 		avail = calc_available_free_space(fs_info, space_info, flush);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index fb52aa060093..d43261545264 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2980,7 +2980,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 		ret = 0;
 	if (ret) {
 		blk_finish_plug(&plug);
-		btrfs_abort_transaction(trans, ret);
 		btrfs_set_log_full_commit(trans);
 		mutex_unlock(&root->log_mutex);
 		goto out;
@@ -3045,15 +3044,12 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 
 		blk_finish_plug(&plug);
 		btrfs_set_log_full_commit(trans);
-
-		if (ret != -ENOSPC) {
-			btrfs_abort_transaction(trans, ret);
-			mutex_unlock(&log_root_tree->log_mutex);
-			goto out;
-		}
+		if (ret != -ENOSPC)
+			btrfs_err(fs_info,
+				  "failed to update log for root %llu ret %d",
+				  root->root_key.objectid, ret);
 		btrfs_wait_tree_log_extents(log, mark);
 		mutex_unlock(&log_root_tree->log_mutex);
-		ret = BTRFS_LOG_FORCE_COMMIT;
 		goto out;
 	}
 
@@ -3112,7 +3108,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 		goto out_wake_log_root;
 	} else if (ret) {
 		btrfs_set_log_full_commit(trans);
-		btrfs_abort_transaction(trans, ret);
 		mutex_unlock(&log_root_tree->log_mutex);
 		goto out_wake_log_root;
 	}
@@ -3826,7 +3821,10 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 					      path->slots[0]);
 			if (tmp.type == BTRFS_DIR_INDEX_KEY)
 				last_old_dentry_offset = tmp.offset;
+		} else if (ret < 0) {
+			err = ret;
 		}
+
 		goto done;
 	}
 
@@ -3846,19 +3844,34 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 		 */
 		if (tmp.type == BTRFS_DIR_INDEX_KEY)
 			last_old_dentry_offset = tmp.offset;
+	} else if (ret < 0) {
+		err = ret;
+		goto done;
 	}
+
 	btrfs_release_path(path);
 
 	/*
-	 * Find the first key from this transaction again.  See the note for
-	 * log_new_dir_dentries, if we're logging a directory recursively we
-	 * won't be holding its i_mutex, which means we can modify the directory
-	 * while we're logging it.  If we remove an entry between our first
-	 * search and this search we'll not find the key again and can just
-	 * bail.
+	 * Find the first key from this transaction again or the one we were at
+	 * in the loop below in case we had to reschedule. We may be logging the
+	 * directory without holding its VFS lock, which happen when logging new
+	 * dentries (through log_new_dir_dentries()) or in some cases when we
+	 * need to log the parent directory of an inode. This means a dir index
+	 * key might be deleted from the inode's root, and therefore we may not
+	 * find it anymore. If we can't find it, just move to the next key. We
+	 * can not bail out and ignore, because if we do that we will simply
+	 * not log dir index keys that come after the one that was just deleted
+	 * and we can end up logging a dir index range that ends at (u64)-1
+	 * (@last_offset is initialized to that), resulting in removing dir
+	 * entries we should not remove at log replay time.
 	 */
 search:
 	ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0);
+	if (ret > 0)
+		ret = btrfs_next_item(root, path);
+	if (ret < 0)
+		err = ret;
+	/* If ret is 1, there are no more keys in the inode's root. */
 	if (ret != 0)
 		goto done;
 
@@ -5580,8 +5593,10 @@ static int add_conflicting_inode(struct btrfs_trans_handle *trans,
 	 * LOG_INODE_EXISTS mode) and slow down other fsyncs or transaction
 	 * commits.
 	 */
-	if (ctx->num_conflict_inodes >= MAX_CONFLICT_INODES)
+	if (ctx->num_conflict_inodes >= MAX_CONFLICT_INODES) {
+		btrfs_set_log_full_commit(trans);
 		return BTRFS_LOG_FORCE_COMMIT;
+	}
 
 	inode = btrfs_iget(root->fs_info->sb, ino, root);
 	/*
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index aa25fa335d3e..bf0decaac7f3 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -768,8 +768,11 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 					BTRFS_SUPER_FLAG_CHANGING_FSID_V2);
 
 	error = lookup_bdev(path, &path_devt);
-	if (error)
+	if (error) {
+		btrfs_err(NULL, "failed to lookup block device for path %s: %d",
+			  path, error);
 		return ERR_PTR(error);
+	}
 
 	if (fsid_change_in_progress) {
 		if (!has_metadata_uuid)
@@ -836,6 +839,9 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		unsigned int nofs_flag;
 
 		if (fs_devices->opened) {
+			btrfs_err(NULL,
+		"device %s belongs to fsid %pU, and the fs is already mounted",
+				  path, fs_devices->fsid);
 			mutex_unlock(&fs_devices->device_list_mutex);
 			return ERR_PTR(-EBUSY);
 		}
@@ -905,6 +911,9 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 			 * generation are equal.
 			 */
 			mutex_unlock(&fs_devices->device_list_mutex);
+			btrfs_err(NULL,
+"device %s already registered with a higher generation, found %llu expect %llu",
+				  path, found_transid, device->generation);
 			return ERR_PTR(-EEXIST);
 		}
 
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index a759668477bb..1f503e8e42d4 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -539,6 +539,8 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache)
 		}
 		atomic_set(&zone_info->active_zones_left,
 			   max_active_zones - nactive);
+		/* Overcommit does not work well with active zone tacking. */
+		set_bit(BTRFS_FS_NO_OVERCOMMIT, &fs_info->flags);
 	}
 
 	/* Validate superblock log */