scsi: convert device_busy to atomic_t

Avoid taking the queue_lock to check the per-device queue limit. Instead
we do an atomic_inc_return early on to grab our slot in the queue,
and if necessary decrement it after finishing all checks.

Unlike the host and target busy counters this doesn't allow us to avoid the
queue_lock in the request_fn due to the way the interface works, but it'll
allow us to prepare for using the blk-mq code, which doesn't use the
queue_lock at all, and it at least avoids a queue_lock round trip in
scsi_device_unbusy, which is still important given how busy the queue_lock
is.

Signed-off-by: Christoph Hellwig <[e-mail]>
Reviewed-by: Hannes Reinecke <[e-mail]>
Reviewed-by: Webb Scales <[e-mail]>
Acked-by: Jens Axboe <[e-mail]>
Tested-by: Bart Van Assche <[e-mail]>
Tested-by: Robert Elliott <[e-mail]>

drivers/message/fusion/mptsas.c

···
 						printk(MYIOC_s_DEBUG_FMT
 						"SDEV OUTSTANDING CMDS"
 						"%d\n", ioc->name,
-						sdev->device_busy));
+						atomic_read(&sdev->device_busy)));
 				}
 
 			}

drivers/scsi/scsi_lib.c

···
 		spin_unlock_irqrestore(shost->host_lock, flags);
 	}
 
-	spin_lock_irqsave(sdev->request_queue->queue_lock, flags);
-	sdev->device_busy--;
-	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
+	atomic_dec(&sdev->device_busy);
 }
 
 /*
···
 
 static inline int scsi_device_is_busy(struct scsi_device *sdev)
 {
-	if (sdev->device_busy >= sdev->queue_depth || sdev->device_blocked)
+	if (atomic_read(&sdev->device_busy) >= sdev->queue_depth ||
+	    sdev->device_blocked)
 		return 1;
-
 	return 0;
 }
 
···
 		 * queue must be restarted, so we schedule a callback to happen
 		 * shortly.
 		 */
-		if (sdev->device_busy == 0)
+		if (atomic_read(&sdev->device_busy) == 0)
 			blk_delay_queue(q, SCSI_QUEUE_DELAY);
 		break;
 	default:
···
 static inline int scsi_dev_queue_ready(struct request_queue *q,
 				  struct scsi_device *sdev)
 {
-	if (sdev->device_busy == 0 && sdev->device_blocked) {
+	unsigned int busy;
+
+	busy = atomic_inc_return(&sdev->device_busy) - 1;
+	if (sdev->device_blocked) {
+		if (busy)
+			goto out_dec;
+
 		/*
 		 * unblock after device_blocked iterates to zero
 		 */
-		if (--sdev->device_blocked == 0) {
-			SCSI_LOG_MLQUEUE(3,
-				   sdev_printk(KERN_INFO, sdev,
-				   "unblocking device at zero depth\n"));
-		} else {
+		if (--sdev->device_blocked != 0) {
 			blk_delay_queue(q, SCSI_QUEUE_DELAY);
-			return 0;
+			goto out_dec;
 		}
+		SCSI_LOG_MLQUEUE(3, sdev_printk(KERN_INFO, sdev,
+				   "unblocking device at zero depth\n"));
 	}
-	if (scsi_device_is_busy(sdev))
-		return 0;
+
+	if (busy >= sdev->queue_depth)
+		goto out_dec;
 
 	return 1;
+out_dec:
+	atomic_dec(&sdev->device_busy);
+	return 0;
 }
-
 
 /*
  * scsi_target_queue_ready: checks if there we can send commands to target
···
 	 * bump busy counts.  To bump the counters, we need to dance
 	 * with the locks as normal issue path does.
 	 */
-	sdev->device_busy++;
+	atomic_inc(&sdev->device_busy);
 	atomic_inc(&shost->host_busy);
 	atomic_inc(&starget->target_busy);
 
···
 		 * accept it.
 		 */
 		req = blk_peek_request(q);
-		if (!req || !scsi_dev_queue_ready(q, sdev))
+		if (!req)
 			break;
 
 		if (unlikely(!scsi_device_online(sdev))) {
···
 			continue;
 		}
 
+		if (!scsi_dev_queue_ready(q, sdev))
+			break;
 
 		/*
 		 * Remove the request from the request list.
 		 */
 		if (!(blk_queue_tagged(q) && !blk_queue_start_tag(q, req)))
 			blk_start_request(req);
-		sdev->device_busy++;
 
 		spin_unlock_irq(q->queue_lock);
 		cmd = req->special;
···
 	 */
 	spin_lock_irq(q->queue_lock);
 	blk_requeue_request(q, req);
-	sdev->device_busy--;
+	atomic_dec(&sdev->device_busy);
 out_delay:
-	if (sdev->device_busy == 0 && !scsi_device_blocked(sdev))
+	if (atomic_read(&sdev->device_busy) && !scsi_device_blocked(sdev))
 		blk_delay_queue(q, SCSI_QUEUE_DELAY);
 }
 
···
 		return err;
 
 	scsi_run_queue(sdev->request_queue);
-	while (sdev->device_busy) {
+	while (atomic_read(&sdev->device_busy)) {
 		msleep_interruptible(200);
 		scsi_run_queue(sdev->request_queue);
 	}

drivers/scsi/scsi_sysfs.c

···
  * Create the actual show/store functions and data structures.
  */
 sdev_rd_attr (device_blocked, "%d\n");
-sdev_rd_attr (device_busy, "%d\n");
 sdev_rd_attr (type, "%d\n");
 sdev_rd_attr (scsi_level, "%d\n");
 sdev_rd_attr (vendor, "%.8s\n");
 sdev_rd_attr (model, "%.16s\n");
 sdev_rd_attr (rev, "%.4s\n");
+
+static ssize_t
+sdev_show_device_busy(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	struct scsi_device *sdev = to_scsi_device(dev);
+	return snprintf(buf, 20, "%d\n", atomic_read(&sdev->device_busy));
+}
+static DEVICE_ATTR(device_busy, S_IRUGO, sdev_show_device_busy, NULL);
 
 /*
  * TODO: can we make these symlinks to the block layer ones?

drivers/scsi/sg.c

···
 			      scsidp->id, scsidp->lun, (int) scsidp->type,
 			      1,
 			      (int) scsidp->queue_depth,
-			      (int) scsidp->device_busy,
+			      (int) atomic_read(&scsidp->device_busy),
 			      (int) scsi_device_online(scsidp));
 	}
 	read_unlock_irqrestore(&sg_index_lock, iflags);

include/scsi/scsi_device.h

···
 	struct list_head    siblings;   /* list of all devices on this host */
 	struct list_head    same_target_siblings; /* just the devices sharing same target id */
 
-	/* this is now protected by the request_queue->queue_lock */
-	unsigned int device_busy;	/* commands actually active on
-					 * low-level. protected by queue_lock. */
+	atomic_t device_busy;		/* commands actually active on LLDD */
 	spinlock_t list_lock;
 	struct list_head cmd_list;	/* queue of in use SCSI Command structures */
 	struct list_head starved_entry;