blk-mq: Restore the zone write order when requeuing

Zoned writes may be requeued. This happens if a block driver returns
BLK_STS_RESOURCE, to handle SCSI unit attentions or by the SCSI error
handler after error handling has finished. A later patch enables write
pipelining and increases the number of pending writes per zone. If
multiple writes are pending per zone, write requests may be requeued in
another order than submitted. Restore the request order if requests are
requeued. Add RQF_DONTPREP to RQF_NOMERGE_FLAGS because this patch may
cause RQF_DONTPREP requests to be sent to the code that checks whether
a request can be merged and RQF_DONTPREP requests must not be merged.

Cc: Christoph Hellwig <[email protected]>
Cc: Damien Le Moal <[email protected]>
Cc: Yu Kuai <[email protected]>
Signed-off-by: Bart Van Assche <[email protected]>

Author: bvanassche

block/bfq-iosched.c

@@ -6276,6 +6276,8 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 
 	if (flags & BLK_MQ_INSERT_AT_HEAD) {
 		list_add(&rq->queuelist, &bfqd->dispatch);
+	} else if (flags & BLK_MQ_INSERT_ORDERED) {
+		blk_mq_insert_ordered(rq, &bfqd->dispatch);
 	} else if (!bfqq) {
 		list_add_tail(&rq->queuelist, &bfqd->dispatch);
 	} else {

block/blk-mq.c

@@ -1557,7 +1557,9 @@ static void blk_mq_requeue_work(struct work_struct *work)
 		 * already.  Insert it into the hctx dispatch list to avoid
 		 * block layer merges for the request.
 		 */
-		if (rq->rq_flags & RQF_DONTPREP)
+		if (blk_rq_is_seq_zoned_write(rq))
+			blk_mq_insert_request(rq, BLK_MQ_INSERT_ORDERED);
+		else if (rq->rq_flags & RQF_DONTPREP)
 			blk_mq_request_bypass_insert(rq, 0);
 		else
 			blk_mq_insert_request(rq, BLK_MQ_INSERT_AT_HEAD);
@@ -2590,6 +2592,20 @@ static void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx,
 	blk_mq_run_hw_queue(hctx, run_queue_async);
 }
 
+void blk_mq_insert_ordered(struct request *rq, struct list_head *list)
+{
+	struct request_queue *q = rq->q;
+	struct request *rq2;
+
+	list_for_each_entry(rq2, list, queuelist)
+		if (rq2->q == q && blk_rq_pos(rq2) > blk_rq_pos(rq))
+			break;
+
+	/* Insert rq before rq2. If rq2 is the list head, append at the end. */
+	list_add_tail(&rq->queuelist, &rq2->queuelist);
+}
+EXPORT_SYMBOL_GPL(blk_mq_insert_ordered);
+
 static void blk_mq_insert_request(struct request *rq, blk_insert_t flags)
 {
 	struct request_queue *q = rq->q;
@@ -2644,6 +2660,8 @@ static void blk_mq_insert_request(struct request *rq, blk_insert_t flags)
 		spin_lock(&ctx->lock);
 		if (flags & BLK_MQ_INSERT_AT_HEAD)
 			list_add(&rq->queuelist, &ctx->rq_lists[hctx->type]);
+		else if (flags & BLK_MQ_INSERT_ORDERED)
+			blk_mq_insert_ordered(rq, &ctx->rq_lists[hctx->type]);
 		else
 			list_add_tail(&rq->queuelist,
 				      &ctx->rq_lists[hctx->type]);

block/blk-mq.h

@@ -40,8 +40,10 @@ enum {
 
 typedef unsigned int __bitwise blk_insert_t;
 #define BLK_MQ_INSERT_AT_HEAD		((__force blk_insert_t)0x01)
+#define BLK_MQ_INSERT_ORDERED		((__force blk_insert_t)0x02)
 
 void blk_mq_submit_bio(struct bio *bio);
+void blk_mq_insert_ordered(struct request *rq, struct list_head *list);
 int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob,
 		unsigned int flags);
 void blk_mq_exit_queue(struct request_queue *q);

block/kyber-iosched.c

@@ -603,6 +603,8 @@ static void kyber_insert_requests(struct blk_mq_hw_ctx *hctx,
 		trace_block_rq_insert(rq);
 		if (flags & BLK_MQ_INSERT_AT_HEAD)
 			list_move(&rq->queuelist, head);
+		else if (flags & BLK_MQ_INSERT_ORDERED)
+			blk_mq_insert_ordered(rq, head);
 		else
 			list_move_tail(&rq->queuelist, head);
 		sbitmap_set_bit(&khd->kcq_map[sched_domain],

block/mq-deadline.c

@@ -710,7 +710,12 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 		 * set expire time and add to fifo list
 		 */
 		rq->fifo_time = jiffies + dd->fifo_expire[data_dir];
-		list_add_tail(&rq->queuelist, &per_prio->fifo_list[data_dir]);
+		if (flags & BLK_MQ_INSERT_ORDERED)
+			blk_mq_insert_ordered(rq,
+					      &per_prio->fifo_list[data_dir]);
+		else
+			list_add_tail(&rq->queuelist,
+				      &per_prio->fifo_list[data_dir]);
 	}
 }
 

include/linux/blk-mq.h

@@ -86,7 +86,7 @@ enum rqf_flags {
 
 /* flags that prevent us from merging requests: */
 #define RQF_NOMERGE_FLAGS \
-	(RQF_STARTED | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD)
+	(RQF_STARTED | RQF_FLUSH_SEQ | RQF_DONTPREP | RQF_SPECIAL_PAYLOAD)
 
 enum mq_rq_state {
 	MQ_RQ_IDLE		= 0,
@@ -1191,4 +1191,15 @@ static inline int blk_rq_map_sg(struct request *rq, struct scatterlist *sglist)
 }
 void blk_dump_rq_flags(struct request *, char *);
 
+static inline bool blk_rq_is_seq_zoned_write(struct request *rq)
+{
+	switch (req_op(rq)) {
+	case REQ_OP_WRITE:
+	case REQ_OP_WRITE_ZEROES:
+		return bdev_zone_is_seq(rq->q->disk->part0, blk_rq_pos(rq));
+	default:
+		return false;
+	}
+}
+
 #endif /* BLK_MQ_H */