scsi: core: add support for request batching

This allows a list of requests to be issued, with the LLD only writing the
hardware doorbell when necessary, after the last request was prepared.
This is more efficient if we have lists of requests to issue, particularly
on virtualized hardware, where writing the doorbell is more expensive than
on real hardware.

The use case for this is plugged IO, where blk-mq flushes a batch of
requests all at once.

The API is the same as for blk-mq, just with blk-mq concepts tweaked to
fit the SCSI subsystem API: the "last" flag in blk_mq_queue_data becomes a
flag in scsi_cmnd, while the queue_num in the commit_rqs callback is
extracted from the hctx and passed as a parameter.

The only complication is that blk-mq uses different plugging heuristics
depending on whether commit_rqs is present or not.  So we have two
different sets of blk_mq_ops and pick one depending on whether the
scsi_host template uses commit_rqs or not.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 34 insertions, 3 deletions

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 9381171c2fc0..c72bce2f0cf1 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1666,10 +1666,11 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
 		blk_mq_start_request(req);
 	}
 
+	cmd->flags &= SCMD_PRESERVED_FLAGS;
 	if (sdev->simple_tags)
 		cmd->flags |= SCMD_TAGGED;
-	else
-		cmd->flags &= ~SCMD_TAGGED;
+	if (bd->last)
+		cmd->flags |= SCMD_LAST;
 
 	scsi_init_cmd_errh(cmd);
 	cmd->scsi_done = scsi_mq_done;
@@ -1807,10 +1808,37 @@ void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(__scsi_init_queue);
 
+static const struct blk_mq_ops scsi_mq_ops_no_commit = {
+	.get_budget	= scsi_mq_get_budget,
+	.put_budget	= scsi_mq_put_budget,
+	.queue_rq	= scsi_queue_rq,
+	.complete	= scsi_softirq_done,
+	.timeout	= scsi_timeout,
+#ifdef CONFIG_BLK_DEBUG_FS
+	.show_rq	= scsi_show_rq,
+#endif
+	.init_request	= scsi_mq_init_request,
+	.exit_request	= scsi_mq_exit_request,
+	.initialize_rq_fn = scsi_initialize_rq,
+	.busy		= scsi_mq_lld_busy,
+	.map_queues	= scsi_map_queues,
+};
+
+
+static void scsi_commit_rqs(struct blk_mq_hw_ctx *hctx)
+{
+	struct request_queue *q = hctx->queue;
+	struct scsi_device *sdev = q->queuedata;
+	struct Scsi_Host *shost = sdev->host;
+
+	shost->hostt->commit_rqs(shost, hctx->queue_num);
+}
+
 static const struct blk_mq_ops scsi_mq_ops = {
 	.get_budget	= scsi_mq_get_budget,
 	.put_budget	= scsi_mq_put_budget,
 	.queue_rq	= scsi_queue_rq,
+	.commit_rqs	= scsi_commit_rqs,
 	.complete	= scsi_softirq_done,
 	.timeout	= scsi_timeout,
 #ifdef CONFIG_BLK_DEBUG_FS
@@ -1846,7 +1874,10 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost)
 			sizeof(struct scatterlist) * SCSI_INLINE_PROT_SG_CNT;
 
 	memset(&shost->tag_set, 0, sizeof(shost->tag_set));
-	shost->tag_set.ops = &scsi_mq_ops;
+	if (shost->hostt->commit_rqs)
+		shost->tag_set.ops = &scsi_mq_ops;
+	else
+		shost->tag_set.ops = &scsi_mq_ops_no_commit;
 	shost->tag_set.nr_hw_queues = shost->nr_hw_queues ? : 1;
 	shost->tag_set.queue_depth = shost->can_queue;
 	shost->tag_set.cmd_size = cmd_size;