btrfs: zoned: activate block group only for extent allocation

In btrfs_make_block_group(), we activate the allocated block group,
expecting that the block group is soon used for allocation. However, the
chunk allocation from flush_space() context broke the assumption. There
can be a large time gap between the chunk allocation time and the extent
allocation time from the chunk.

Activating the empty block groups pre-allocated from flush_space()
context can exhaust the active zone counter of a device. Once we use all
the active zone counts for empty pre-allocated block groups, we cannot
activate new block group for the other things: metadata, tree-log, or
data relocation block group.  That failure results in a fake -ENOSPC.

This patch introduces CHUNK_ALLOC_FORCE_FOR_EXTENT to distinguish the
chunk allocation from find_free_extent(). Now, the new block group is
activated only in that context.

Fixes: eb66a010 ("btrfs: zoned: activate new block group")
CC: stable@vger.kernel.org # 5.16+
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Tested-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/block-group.c

@@ -2503,12 +2503,6 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran
 		return ERR_PTR(ret);
 	}
 
-	/*
-	 * New block group is likely to be used soon. Try to activate it now.
-	 * Failure is OK for now.
-	 */
-	btrfs_zone_activate(cache);
-
 	ret = exclude_super_stripes(cache);
 	if (ret) {
 		/* We may have excluded something, so call this just in case */
@@ -3660,8 +3654,14 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 	struct btrfs_block_group *ret_bg;
 	bool wait_for_alloc = false;
 	bool should_alloc = false;
+	bool from_extent_allocation = false;
 	int ret = 0;
 
+	if (force == CHUNK_ALLOC_FORCE_FOR_EXTENT) {
+		from_extent_allocation = true;
+		force = CHUNK_ALLOC_FORCE;
+	}
+
 	/* Don't re-enter if we're already allocating a chunk */
 	if (trans->allocating_chunk)
 		return -ENOSPC;
@@ -3754,9 +3754,17 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 	ret_bg = do_chunk_alloc(trans, flags);
 	trans->allocating_chunk = false;
 
-	if (IS_ERR(ret_bg))
+	if (IS_ERR(ret_bg)) {
 		ret = PTR_ERR(ret_bg);
-	else
+	} else if (from_extent_allocation) {
+		/*
+		 * New block group is likely to be used soon. Try to activate
+		 * it now. Failure is OK for now.
+		 */
+		btrfs_zone_activate(ret_bg);
+	}
+
+	if (!ret)
 		btrfs_put_block_group(ret_bg);
 
 	spin_lock(&space_info->lock);

fs/btrfs/block-group.h

@@ -35,11 +35,15 @@ enum btrfs_discard_state {
  * the FS with empty chunks
  *
  * CHUNK_ALLOC_FORCE means it must try to allocate one
+ *
+ * CHUNK_ALLOC_FORCE_FOR_EXTENT like CHUNK_ALLOC_FORCE but called from
+ * find_free_extent() that also activaes the zone
  */
 enum btrfs_chunk_alloc_enum {
 	CHUNK_ALLOC_NO_FORCE,
 	CHUNK_ALLOC_LIMITED,
 	CHUNK_ALLOC_FORCE,
+	CHUNK_ALLOC_FORCE_FOR_EXTENT,
 };
 
 struct btrfs_caching_control {

fs/btrfs/extent-tree.c

@@ -4082,7 +4082,7 @@ static int find_free_extent_update_loop(struct btrfs_fs_info *fs_info,
 			}
 
 			ret = btrfs_chunk_alloc(trans, ffe_ctl->flags,
-						CHUNK_ALLOC_FORCE);
+						CHUNK_ALLOC_FORCE_FOR_EXTENT);
 
 			/* Do not bail out on ENOSPC since we can do more. */
 			if (ret == -ENOSPC)