Writes in sequential write required zones must happen at the write
pointer. Even if the submitter of the write commands (e.g. a filesystem)
submits writes for sequential write required zones in order, the block
layer or the storage controller may reorder these write commands.
The zone locking mechanism in the mq-deadline I/O scheduler serializes
write commands for sequential zones. Some but not all storage controllers
require this serialization. Introduce a new request queue flag to allow
block drivers to indicate that they preserve the order of write commands
and thus do not require serialization of writes per zone.
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Damien Le Moal <dlemoal@xxxxxxxxxx>
Cc: Ming Lei <ming.lei@xxxxxxxxxx>
Signed-off-by: Bart Van Assche <bvanassche@xxxxxxx>
---
include/linux/blkdev.h | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 2f5371b8482c..de5e05cc34fa 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -534,6 +534,11 @@ struct request_queue {
#define QUEUE_FLAG_NONROT 6 /* non-rotational device (SSD) */
#define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */
#define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */
+/*
+ * Do not serialize sequential writes (REQ_OP_WRITE, REQ_OP_WRITE_ZEROES) sent
+ * to a sequential write required zone (BLK_ZONE_TYPE_SEQWRITE_REQ).
+ */
+#define QUEUE_FLAG_NO_ZONE_WRITE_LOCK 8
#define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */
#define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */
#define QUEUE_FLAG_SYNCHRONOUS 11 /* always completes in submit context */
@@ -597,6 +602,11 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
#define blk_queue_skip_tagset_quiesce(q) \
test_bit(QUEUE_FLAG_SKIP_TAGSET_QUIESCE, &(q)->queue_flags)
+static inline bool blk_queue_no_zone_write_lock(struct request_queue *q)
+{
+ return test_bit(QUEUE_FLAG_NO_ZONE_WRITE_LOCK, &q->queue_flags);
+}
+
extern void blk_set_pm_only(struct request_queue *q);
extern void blk_clear_pm_only(struct request_queue *q);
