btrfs: zoned: don't zone append to conventional zone

In case of a zoned RAID, it can happen that a data write is targeting a
sequential write required zone and a conventional zone. In this case the
bio will be marked as REQ_OP_ZONE_APPEND but for the conventional zone,
this needs to be REQ_OP_WRITE.

The setting of REQ_OP_ZONE_APPEND is deferred to the last possible time in
btrfs_submit_dev_bio(), but the decision if we can use zone append is
cached in btrfs_bio.

CC: Naohiro Aota <naohiro.aota@wdc.com>
Fixes: e9b9b911e03c ("btrfs: add raid stripe tree to features enabled with debug config")
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>

2 files changed, 12 insertions, 10 deletions

diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index fa1d321a2fb8..e4d382d3a7ae 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -480,6 +480,8 @@ static void btrfs_clone_write_end_io(struct bio *bio)
 
 static void btrfs_submit_dev_bio(struct btrfs_device *dev, struct bio *bio)
 {
+	u64 physical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
+
 	if (!dev || !dev->bdev ||
 	    test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) ||
 	    (btrfs_op(bio) == BTRFS_MAP_WRITE &&
@@ -494,12 +496,13 @@ static void btrfs_submit_dev_bio(struct btrfs_device *dev, struct bio *bio)
 	 * For zone append writing, bi_sector must point the beginning of the
 	 * zone
 	 */
-	if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
-		u64 physical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
+	if (btrfs_bio(bio)->can_use_append && btrfs_dev_is_sequential(dev, physical)) {
 		u64 zone_start = round_down(physical, dev->fs_info->zone_size);
 
 		ASSERT(btrfs_dev_is_sequential(dev, physical));
 		bio->bi_iter.bi_sector = zone_start >> SECTOR_SHIFT;
+		bio->bi_opf &= ~REQ_OP_WRITE;
+		bio->bi_opf |= REQ_OP_ZONE_APPEND;
 	}
 	btrfs_debug(dev->fs_info,
 	"%s: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u",
@@ -747,7 +750,6 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
 	u64 logical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
 	u64 length = bio->bi_iter.bi_size;
 	u64 map_length = length;
-	bool use_append = btrfs_use_zone_append(bbio);
 	struct btrfs_io_context *bioc = NULL;
 	struct btrfs_io_stripe smap;
 	blk_status_t status;
@@ -775,8 +777,10 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
 	if (bio_op(bio) == REQ_OP_WRITE && is_data_bbio(bbio))
 		bbio->orig_logical = logical;
 
+	bbio->can_use_append = btrfs_use_zone_append(bbio);
+
 	map_length = min(map_length, length);
-	if (use_append)
+	if (bbio->can_use_append)
 		map_length = btrfs_append_map_length(bbio, map_length);
 
 	if (map_length < length) {
@@ -805,11 +809,6 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
 	}
 
 	if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
-		if (use_append) {
-			bio->bi_opf &= ~REQ_OP_WRITE;
-			bio->bi_opf |= REQ_OP_ZONE_APPEND;
-		}
-
 		if (is_data_bbio(bbio) && bioc && bioc->use_rst) {
 			/*
 			 * No locking for the list update, as we only add to
@@ -836,7 +835,7 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
 			status = errno_to_blk_status(ret);
 			if (status)
 				goto fail;
-		} else if (use_append ||
+		} else if (bbio->can_use_append ||
 			   (btrfs_is_zoned(fs_info) && inode &&
 			    inode->flags & BTRFS_INODE_NODATASUM)) {
 			ret = btrfs_alloc_dummy_sum(bbio);
diff --git a/fs/btrfs/bio.h b/fs/btrfs/bio.h
index 1be74209f0b8..246c7519dff3 100644
--- a/fs/btrfs/bio.h
+++ b/fs/btrfs/bio.h
@@ -92,6 +92,9 @@ struct btrfs_bio {
 	/* Whether the csum generation for data write is async. */
 	bool async_csum;
 
+	/* Whether the bio is written using zone append. */
+	bool can_use_append;
+
 	/*
 	 * This member must come last, bio_alloc_bioset will allocate enough
 	 * bytes for entire btrfs_bio but relies on bio being last.