scsi: core: Replace sdev->device_busy with sbitmap

SCSI currently uses an atomic variable to track queue depth for each
attached device. The queue depth depends on many factors such as transport
type and device implementation. In addition, the SCSI device queue depth is
not a static entity but changes over time as a result of congestion
management.

While blk-mq currently tracks queue depth for each hctx, it can't easily be
changed to accommodate the SCSI per-device requirement.

The current approach of using an atomic variable doesn't scale well when
there are lots of CPU cores and the disk is very fast. IOPS can be
substantially impacted by the atomic in the hot path.

Replace the atomic variable sdev->device_busy with an sbitmap for tracking
the SCSI device queue depth.

It has been observed that IOPS is improved ~30% by this patchset in the
following test:

1) test machine(32 logical CPU cores)
	Thread(s) per core:  2
	Core(s) per socket:  8
	Socket(s):           2
	NUMA node(s):        2
	Model name:          Intel(R) Xeon(R) Silver 4110 CPU @ 2.10GHz

2) setup scsi_debug:
modprobe scsi_debug virtual_gb=128 max_luns=1 submit_queues=32 delay=0 max_queue=256

3) fio script:
fio --rw=randread --size=128G --direct=1 --ioengine=libaio --iodepth=2048 \
	--numjobs=32 --bs=4k --group_reporting=1 --group_reporting=1 --runtime=60 \
	--loops=10000 --name=job1 --filename=/dev/sdN

[mkp: fix device_busy reference in mpt3sas]

Link: https://lore.kernel.org/r/20210122023317.687987-14-ming.lei@redhat.com
Link: https://lore.kernel.org/linux-block/20200119071432.18558-6-ming.lei@redhat.com/
Cc: Omar Sandoval <osandov@fb.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Sumanesh Samanta <sumanesh.samanta@broadcom.com>
Cc: Ewan D. Milne <emilne@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Tested-by: Sumanesh Samanta <sumanesh.samanta@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 18 insertions, 17 deletions

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 2f8578fb89ff..ffe824782647 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -328,7 +328,7 @@ void scsi_device_unbusy(struct scsi_device *sdev, struct scsi_cmnd *cmd)
 	if (starget->can_queue > 0)
 		atomic_dec(&starget->target_busy);
 
-	atomic_dec(&sdev->device_busy);
+	sbitmap_put(&sdev->budget_map, cmd->budget_token);
 	cmd->budget_token = -1;
 }
 
@@ -1257,19 +1257,20 @@ scsi_device_state_check(struct scsi_device *sdev, struct request *req)
 }
 
 /*
- * scsi_dev_queue_ready: if we can send requests to sdev, return 1 else
- * return 0.
- *
- * Called with the queue_lock held.
+ * scsi_dev_queue_ready: if we can send requests to sdev, assign one token
+ * and return the token else return -1.
  */
 static inline int scsi_dev_queue_ready(struct request_queue *q,
 				  struct scsi_device *sdev)
 {
-	unsigned int busy;
+	int token;
 
-	busy = atomic_inc_return(&sdev->device_busy) - 1;
+	token = sbitmap_get(&sdev->budget_map);
 	if (atomic_read(&sdev->device_blocked)) {
-		if (busy)
+		if (token < 0)
+			goto out;
+
+		if (scsi_device_busy(sdev) > 1)
 			goto out_dec;
 
 		/*
@@ -1281,13 +1282,12 @@ static inline int scsi_dev_queue_ready(struct request_queue *q,
 				   "unblocking device at zero depth\n"));
 	}
 
-	if (busy >= sdev->queue_depth)
-		goto out_dec;
-
-	return 1;
+	return token;
 out_dec:
-	atomic_dec(&sdev->device_busy);
-	return 0;
+	if (token >= 0)
+		sbitmap_put(&sdev->budget_map, token);
+out:
+	return -1;
 }
 
 /*
@@ -1612,15 +1612,16 @@ static void scsi_mq_put_budget(struct request_queue *q, int budget_token)
 {
 	struct scsi_device *sdev = q->queuedata;
 
-	atomic_dec(&sdev->device_busy);
+	sbitmap_put(&sdev->budget_map, budget_token);
 }
 
 static int scsi_mq_get_budget(struct request_queue *q)
 {
 	struct scsi_device *sdev = q->queuedata;
+	int token = scsi_dev_queue_ready(q, sdev);
 
-	if (scsi_dev_queue_ready(q, sdev))
-		return 0;
+	if (token >= 0)
+		return token;
 
 	atomic_inc(&sdev->restarts);