btrfs: zoned: track unusable bytes for zones

In a zoned filesystem a once written then freed region is not usable
until the underlying zone has been reset. So we need to distinguish such
unusable space from usable free space.

Therefore we need to introduce the "zone_unusable" field to the block
group structure, and "bytes_zone_unusable" to the space_info structure
to track the unusable space.

Pinned bytes are always reclaimed to the unusable space. But, when an
allocated region is returned before using e.g., the block group becomes
read-only between allocation time and reservation time, we can safely
return the region to the block group. For the situation, this commit
introduces "btrfs_add_free_space_unused". This behaves the same as
btrfs_add_free_space() on regular filesystem. On zoned filesystems, it
rewinds the allocation offset.

Because the read-only bytes tracks free but unusable bytes when the block
group is read-only, we need to migrate the zone_unusable bytes to
read-only bytes when a block group is marked read-only.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 67 insertions, 0 deletions

diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 6134e10a6e7f..b93ac31eca69 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -2477,6 +2477,8 @@ int __btrfs_add_free_space(struct btrfs_fs_info *fs_info,
 	int ret = 0;
 	u64 filter_bytes = bytes;
 
+	ASSERT(!btrfs_is_zoned(fs_info));
+
 	info = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS);
 	if (!info)
 		return -ENOMEM;
@@ -2534,11 +2536,49 @@ out:
 	return ret;
 }
 
+static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
+					u64 bytenr, u64 size, bool used)
+{
+	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
+	u64 offset = bytenr - block_group->start;
+	u64 to_free, to_unusable;
+
+	spin_lock(&ctl->tree_lock);
+	if (!used)
+		to_free = size;
+	else if (offset >= block_group->alloc_offset)
+		to_free = size;
+	else if (offset + size <= block_group->alloc_offset)
+		to_free = 0;
+	else
+		to_free = offset + size - block_group->alloc_offset;
+	to_unusable = size - to_free;
+
+	ctl->free_space += to_free;
+	block_group->zone_unusable += to_unusable;
+	spin_unlock(&ctl->tree_lock);
+	if (!used) {
+		spin_lock(&block_group->lock);
+		block_group->alloc_offset -= size;
+		spin_unlock(&block_group->lock);
+	}
+
+	/* All the region is now unusable. Mark it as unused and reclaim */
+	if (block_group->zone_unusable == block_group->length)
+		btrfs_mark_bg_unused(block_group);
+
+	return 0;
+}
+
 int btrfs_add_free_space(struct btrfs_block_group *block_group,
 			 u64 bytenr, u64 size)
 {
 	enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
 
+	if (btrfs_is_zoned(block_group->fs_info))
+		return __btrfs_add_free_space_zoned(block_group, bytenr, size,
+						    true);
+
 	if (btrfs_test_opt(block_group->fs_info, DISCARD_SYNC))
 		trim_state = BTRFS_TRIM_STATE_TRIMMED;
 
@@ -2547,6 +2587,16 @@ int btrfs_add_free_space(struct btrfs_block_group *block_group,
 				      bytenr, size, trim_state);
 }
 
+int btrfs_add_free_space_unused(struct btrfs_block_group *block_group,
+				u64 bytenr, u64 size)
+{
+	if (btrfs_is_zoned(block_group->fs_info))
+		return __btrfs_add_free_space_zoned(block_group, bytenr, size,
+						    false);
+
+	return btrfs_add_free_space(block_group, bytenr, size);
+}
+
 /*
  * This is a subtle distinction because when adding free space back in general,
  * we want it to be added as untrimmed for async. But in the case where we add
@@ -2557,6 +2607,10 @@ int btrfs_add_free_space_async_trimmed(struct btrfs_block_group *block_group,
 {
 	enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
 
+	if (btrfs_is_zoned(block_group->fs_info))
+		return __btrfs_add_free_space_zoned(block_group, bytenr, size,
+						    true);
+
 	if (btrfs_test_opt(block_group->fs_info, DISCARD_SYNC) ||
 	    btrfs_test_opt(block_group->fs_info, DISCARD_ASYNC))
 		trim_state = BTRFS_TRIM_STATE_TRIMMED;
@@ -2574,6 +2628,9 @@ int btrfs_remove_free_space(struct btrfs_block_group *block_group,
 	int ret;
 	bool re_search = false;
 
+	if (btrfs_is_zoned(block_group->fs_info))
+		return 0;
+
 	spin_lock(&ctl->tree_lock);
 
 again:
@@ -2668,6 +2725,16 @@ void btrfs_dump_free_space(struct btrfs_block_group *block_group,
 	struct rb_node *n;
 	int count = 0;
 
+	/*
+	 * Zoned btrfs does not use free space tree and cluster. Just print
+	 * out the free space after the allocation offset.
+	 */
+	if (btrfs_is_zoned(fs_info)) {
+		btrfs_info(fs_info, "free space %llu",
+			   block_group->length - block_group->alloc_offset);
+		return;
+	}
+
 	spin_lock(&ctl->tree_lock);
 	for (n = rb_first(&ctl->free_space_offset); n; n = rb_next(n)) {
 		info = rb_entry(n, struct btrfs_free_space, offset_index);