btrfs: zoned: finish fully written block group

If we have written to the zone capacity, the device automatically
deactivates the zone. Sync up block group side (the active BG list and
zone_is_active flag) with it.

We need to do it both on data BGs and metadata BGs. On data side, we add a
hook to btrfs_finish_ordered_io(). On metadata side, we use
end_extent_buffer_writeback().

To reduce excess lookup of a block group, we mark the last extent buffer in
a block group with EXTENT_BUFFER_ZONE_FINISH flag. This cannot be done for
data (ordered_extent), because the address may change due to
REQ_OP_ZONE_APPEND.

Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>

5 files changed, 70 insertions, 2 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index fdc066cac572..5ad749e19ff3 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4159,6 +4159,9 @@ void wait_on_extent_buffer_writeback(struct extent_buffer *eb)
 
 static void end_extent_buffer_writeback(struct extent_buffer *eb)
 {
+	if (test_bit(EXTENT_BUFFER_ZONE_FINISH, &eb->bflags))
+		btrfs_zone_finish_endio(eb->fs_info, eb->start, eb->len);
+
 	clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
 	smp_mb__after_atomic();
 	wake_up_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK);
@@ -4760,8 +4763,13 @@ static int submit_eb_page(struct page *page, struct writeback_control *wbc,
 		free_extent_buffer(eb);
 		return ret;
 	}
-	if (cache)
+	if (cache) {
+		/* Impiles write in zoned mode */
 		btrfs_put_block_group(cache);
+		/* Mark the last eb in a block group */
+		if (cache->seq_zone && eb->start + eb->len == cache->zone_capacity)
+			set_bit(EXTENT_BUFFER_ZONE_FINISH, &eb->bflags);
+	}
 	ret = write_one_eb(eb, wbc, epd);
 	free_extent_buffer(eb);
 	if (ret < 0)
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 53abdc280451..9f3e0a45a5e4 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -32,6 +32,7 @@ enum {
 	/* write IO error */
 	EXTENT_BUFFER_WRITE_ERR,
 	EXTENT_BUFFER_NO_CHECK,
+	EXTENT_BUFFER_ZONE_FINISH,
 };
 
 /* these are flags for __process_pages_contig */
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 487533c35ddb..10efab2e3bd9 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3010,8 +3010,12 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 		goto out;
 	}
 
-	if (ordered_extent->bdev)
+	/* A valid bdev implies a write on a sequential zone */
+	if (ordered_extent->bdev) {
 		btrfs_rewrite_logical_zoned(ordered_extent);
+		btrfs_zone_finish_endio(fs_info, ordered_extent->disk_bytenr,
+					ordered_extent->disk_num_bytes);
+	}
 
 	btrfs_free_io_failure_record(inode, start, end);
 
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 798069484054..28a06c2d80ad 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1904,3 +1904,53 @@ bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, int raid_index
 
 	return ret;
 }
+
+void btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical, u64 length)
+{
+	struct btrfs_block_group *block_group;
+	struct map_lookup *map;
+	struct btrfs_device *device;
+	u64 physical;
+
+	if (!btrfs_is_zoned(fs_info))
+		return;
+
+	block_group = btrfs_lookup_block_group(fs_info, logical);
+	ASSERT(block_group);
+
+	if (logical + length < block_group->start + block_group->zone_capacity)
+		goto out;
+
+	spin_lock(&block_group->lock);
+
+	if (!block_group->zone_is_active) {
+		spin_unlock(&block_group->lock);
+		goto out;
+	}
+
+	block_group->zone_is_active = 0;
+	/* We should have consumed all the free space */
+	ASSERT(block_group->alloc_offset == block_group->zone_capacity);
+	ASSERT(block_group->free_space_ctl->free_space == 0);
+	btrfs_clear_treelog_bg(block_group);
+	spin_unlock(&block_group->lock);
+
+	map = block_group->physical_map;
+	device = map->stripes[0].dev;
+	physical = map->stripes[0].physical;
+
+	if (!device->zone_info->max_active_zones)
+		goto out;
+
+	btrfs_dev_clear_active_zone(device, physical);
+
+	spin_lock(&fs_info->zone_active_bgs_lock);
+	ASSERT(!list_empty(&block_group->active_bg_list));
+	list_del_init(&block_group->active_bg_list);
+	spin_unlock(&fs_info->zone_active_bgs_lock);
+
+	btrfs_put_block_group(block_group);
+
+out:
+	btrfs_put_block_group(block_group);
+}
diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h
index ade6588c4ccd..9c512402d7f4 100644
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -73,6 +73,8 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group);
 int btrfs_zone_finish(struct btrfs_block_group *block_group);
 bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices,
 			     int raid_index);
+void btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical,
+			     u64 length);
 #else /* CONFIG_BLK_DEV_ZONED */
 static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
 				     struct blk_zone *zone)
@@ -224,6 +226,9 @@ static inline bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices,
 	return true;
 }
 
+static inline void btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info,
+					   u64 logical, u64 length) { }
+
 #endif
 
 static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)