btrfs: zoned: redirty released extent buffers

Tree manipulating operations like merging nodes often release
once-allocated tree nodes. Such nodes are cleaned so that pages in the
node are not uselessly written out. On zoned volumes, however, such
optimization blocks the following IOs as the cancellation of the write
out of the freed blocks breaks the sequential write sequence expected by
the device.

Introduce a list of clean and unwritten extent buffers that have been
released in a transaction. Redirty the buffers so that
btree_write_cache_pages() can send proper bios to the devices.

Besides it clears the entire content of the extent buffer not to confuse
raw block scanners e.g. 'btrfs check'. By clearing the content,
csum_dirty_buffer() complains about bytenr mismatch, so avoid the
checking and checksum using newly introduced buffer flag
EXTENT_BUFFER_NO_CHECK.

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, 37 insertions, 0 deletions

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index c5f9f4c6f20b..1de67d789b83 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -10,6 +10,7 @@
 #include "rcu-string.h"
 #include "disk-io.h"
 #include "block-group.h"
+#include "transaction.h"
 
 /* Maximum number of zones to report per blkdev_report_zones() call */
 #define BTRFS_REPORT_NR_ZONES   4096
@@ -1181,3 +1182,39 @@ void btrfs_calc_zone_unusable(struct btrfs_block_group *cache)
 	/* Should not have any excluded extents. Just in case, though */
 	btrfs_free_excluded_extents(cache);
 }
+
+void btrfs_redirty_list_add(struct btrfs_transaction *trans,
+			    struct extent_buffer *eb)
+{
+	struct btrfs_fs_info *fs_info = eb->fs_info;
+
+	if (!btrfs_is_zoned(fs_info) ||
+	    btrfs_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN) ||
+	    !list_empty(&eb->release_list))
+		return;
+
+	set_extent_buffer_dirty(eb);
+	set_extent_bits_nowait(&trans->dirty_pages, eb->start,
+			       eb->start + eb->len - 1, EXTENT_DIRTY);
+	memzero_extent_buffer(eb, 0, eb->len);
+	set_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags);
+
+	spin_lock(&trans->releasing_ebs_lock);
+	list_add_tail(&eb->release_list, &trans->releasing_ebs);
+	spin_unlock(&trans->releasing_ebs_lock);
+	atomic_inc(&eb->refs);
+}
+
+void btrfs_free_redirty_list(struct btrfs_transaction *trans)
+{
+	spin_lock(&trans->releasing_ebs_lock);
+	while (!list_empty(&trans->releasing_ebs)) {
+		struct extent_buffer *eb;
+
+		eb = list_first_entry(&trans->releasing_ebs,
+				      struct extent_buffer, release_list);
+		list_del_init(&eb->release_list);
+		free_extent_buffer(eb);
+	}
+	spin_unlock(&trans->releasing_ebs_lock);
+}