scsi: fix the {host,target,device}_blocked counter mess

Seems like these counters are missing any sort of synchronization for
updates, as a over 10 year old comment from me noted.  Fix this by
using atomic counters, and while we're at it also make sure they are
in the same cacheline as the _busy counters and not needlessly stored
to in every I/O completion.

With the new model the _busy counters can temporarily go negative,
so all the readers are updated to check for > 0 values.  Longer
term every successful I/O completion will reset the counters to zero,
so the temporarily negative values will not cause any harm.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Webb Scales <webbnh@hp.com>
Acked-by: Jens Axboe <axboe@kernel.dk>
Tested-by: Bart Van Assche <bvanassche@acm.org>
Tested-by: Robert Elliott <elliott@hp.com>
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 1ddf0fb..69da4cb 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -99,14 +99,16 @@
 	 */
 	switch (reason) {
 	case SCSI_MLQUEUE_HOST_BUSY:
-		host->host_blocked = host->max_host_blocked;
+		atomic_set(&host->host_blocked, host->max_host_blocked);
 		break;
 	case SCSI_MLQUEUE_DEVICE_BUSY:
 	case SCSI_MLQUEUE_EH_RETRY:
-		device->device_blocked = device->max_device_blocked;
+		atomic_set(&device->device_blocked,
+			   device->max_device_blocked);
 		break;
 	case SCSI_MLQUEUE_TARGET_BUSY:
-		starget->target_blocked = starget->max_target_blocked;
+		atomic_set(&starget->target_blocked,
+			   starget->max_target_blocked);
 		break;
 	}
 }
@@ -351,29 +353,35 @@
 	spin_unlock_irqrestore(shost->host_lock, flags);
 }
 
-static inline int scsi_device_is_busy(struct scsi_device *sdev)
+static inline bool scsi_device_is_busy(struct scsi_device *sdev)
 {
-	if (atomic_read(&sdev->device_busy) >= sdev->queue_depth ||
-	    sdev->device_blocked)
-		return 1;
-	return 0;
+	if (atomic_read(&sdev->device_busy) >= sdev->queue_depth)
+		return true;
+	if (atomic_read(&sdev->device_blocked) > 0)
+		return true;
+	return false;
 }
 
-static inline int scsi_target_is_busy(struct scsi_target *starget)
+static inline bool scsi_target_is_busy(struct scsi_target *starget)
 {
-	return ((starget->can_queue > 0 &&
-		 atomic_read(&starget->target_busy) >= starget->can_queue) ||
-		 starget->target_blocked);
+	if (starget->can_queue > 0 &&
+	    atomic_read(&starget->target_busy) >= starget->can_queue)
+		return true;
+	if (atomic_read(&starget->target_blocked) > 0)
+		return true;
+	return false;
 }
 
-static inline int scsi_host_is_busy(struct Scsi_Host *shost)
+static inline bool scsi_host_is_busy(struct Scsi_Host *shost)
 {
-	if ((shost->can_queue > 0 &&
-	     atomic_read(&shost->host_busy) >= shost->can_queue) ||
-	    shost->host_blocked || shost->host_self_blocked)
-		return 1;
-
-	return 0;
+	if (shost->can_queue > 0 &&
+	    atomic_read(&shost->host_busy) >= shost->can_queue)
+		return true;
+	if (atomic_read(&shost->host_blocked) > 0)
+		return true;
+	if (shost->host_self_blocked)
+		return true;
+	return false;
 }
 
 static void scsi_starved_list_run(struct Scsi_Host *shost)
@@ -1256,14 +1264,14 @@
 	unsigned int busy;
 
 	busy = atomic_inc_return(&sdev->device_busy) - 1;
-	if (sdev->device_blocked) {
+	if (atomic_read(&sdev->device_blocked)) {
 		if (busy)
 			goto out_dec;
 
 		/*
 		 * unblock after device_blocked iterates to zero
 		 */
-		if (--sdev->device_blocked != 0) {
+		if (atomic_dec_return(&sdev->device_blocked) > 0) {
 			blk_delay_queue(q, SCSI_QUEUE_DELAY);
 			goto out_dec;
 		}
@@ -1302,19 +1310,15 @@
 	}
 
 	busy = atomic_inc_return(&starget->target_busy) - 1;
-	if (starget->target_blocked) {
+	if (atomic_read(&starget->target_blocked) > 0) {
 		if (busy)
 			goto starved;
 
 		/*
 		 * unblock after target_blocked iterates to zero
 		 */
-		spin_lock_irq(shost->host_lock);
-		if (--starget->target_blocked != 0) {
-			spin_unlock_irq(shost->host_lock);
+		if (atomic_dec_return(&starget->target_blocked) > 0)
 			goto out_dec;
-		}
-		spin_unlock_irq(shost->host_lock);
 
 		SCSI_LOG_MLQUEUE(3, starget_printk(KERN_INFO, starget,
 				 "unblocking target at zero depth\n"));
@@ -1349,19 +1353,15 @@
 		return 0;
 
 	busy = atomic_inc_return(&shost->host_busy) - 1;
-	if (shost->host_blocked) {
+	if (atomic_read(&shost->host_blocked) > 0) {
 		if (busy)
 			goto starved;
 
 		/*
 		 * unblock after host_blocked iterates to zero
 		 */
-		spin_lock_irq(shost->host_lock);
-		if (--shost->host_blocked != 0) {
-			spin_unlock_irq(shost->host_lock);
+		if (atomic_dec_return(&shost->host_blocked) > 0)
 			goto out_dec;
-		}
-		spin_unlock_irq(shost->host_lock);
 
 		SCSI_LOG_MLQUEUE(3,
 			shost_printk(KERN_INFO, shost,