[PATCH v10 15/41] btrfs: emulate write pointer for conventional zones

[Naohiro Aota <naohiro.aota@xxxxxxx>]

Conventional zones do not have a write pointer, so we cannot use it to
determine the allocation offset if a block group contains a conventional
zone.

But instead, we can consider the end of the last allocated extent in the
block group as an allocation offset.

Signed-off-by: Naohiro Aota <naohiro.aota@xxxxxxx>
---
 fs/btrfs/zoned.c | 80 ++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 74 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 69d3412c4fef..9bf40300e428 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -784,6 +784,61 @@ int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size)
 	return 0;
 }
 
+static int emulate_write_pointer(struct btrfs_block_group *cache,
+				 u64 *offset_ret)
+{
+	struct btrfs_fs_info *fs_info = cache->fs_info;
+	struct btrfs_root *root = fs_info->extent_root;
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	struct btrfs_key found_key;
+	int ret;
+	u64 length;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	key.objectid = cache->start + cache->length;
+	key.type = 0;
+	key.offset = 0;
+
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	/* We should not find the exact match */
+	if (ret <= 0) {
+		ret = -EUCLEAN;
+		goto out;
+	}
+
+	ret = btrfs_previous_extent_item(root, path, cache->start);
+	if (ret) {
+		if (ret == 1) {
+			ret = 0;
+			*offset_ret = 0;
+		}
+		goto out;
+	}
+
+	btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);
+
+	if (found_key.type == BTRFS_EXTENT_ITEM_KEY)
+		length = found_key.offset;
+	else
+		length = fs_info->nodesize;
+
+	if (!(found_key.objectid >= cache->start &&
+	       found_key.objectid + length <= cache->start + cache->length)) {
+		ret = -EUCLEAN;
+		goto out;
+	}
+	*offset_ret = found_key.objectid + length - cache->start;
+	ret = 0;
+
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
 int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
@@ -798,6 +853,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache)
 	int i;
 	unsigned int nofs_flag;
 	u64 *alloc_offsets = NULL;
+	u64 emulated_offset = 0;
 	u32 num_sequential = 0, num_conventional = 0;
 
 	if (!btrfs_is_zoned(fs_info))
@@ -899,12 +955,16 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache)
 	}
 
 	if (num_conventional > 0) {
-		/*
-		 * Since conventional zones do not have a write pointer, we
-		 * cannot determine alloc_offset from the pointer
-		 */
-		ret = -EINVAL;
-		goto out;
+		ret = emulate_write_pointer(cache, &emulated_offset);
+		if (ret || map->num_stripes == num_conventional) {
+			if (!ret)
+				cache->alloc_offset = emulated_offset;
+			else
+				btrfs_err(fs_info,
+			"zoned: failed to emulate write pointer of bg %llu",
+					  cache->start);
+			goto out;
+		}
 	}
 
 	switch (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
@@ -926,6 +986,14 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache)
 	}
 
 out:
+	/* An extent is allocated after the write pointer */
+	if (num_conventional && emulated_offset > cache->alloc_offset) {
+		btrfs_err(fs_info,
+			  "zoned: got wrong write pointer in BG %llu: %llu > %llu",
+			  logical, emulated_offset, cache->alloc_offset);
+		ret = -EIO;
+	}
+
 	kfree(alloc_offsets);
 	free_extent_map(em);
 
-- 
2.27.0