blk-mq: avoid to write intermediate result to hctx->next_cpu

This patch figures out the final selected CPU, then writes
it to hctx->next_cpu once, then we can avoid to intermediate
next cpu observed from other dispatch paths.

Cc: Stefan Haberland <sth@linux.vnet.ibm.com>
Tested-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-mq.c

@@ -1344,14 +1344,14 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
 {
 	bool tried = false;
+	int next_cpu = hctx->next_cpu;
 
 	if (hctx->queue->nr_hw_queues == 1)
 		return WORK_CPU_UNBOUND;
 
 	if (--hctx->next_cpu_batch <= 0) {
-		int next_cpu;
 select_cpu:
-		next_cpu = cpumask_next_and(hctx->next_cpu, hctx->cpumask,
+		next_cpu = cpumask_next_and(next_cpu, hctx->cpumask,
 				cpu_online_mask);
 		if (next_cpu >= nr_cpu_ids)
 			next_cpu = cpumask_first_and(hctx->cpumask, cpu_online_mask);
@@ -1361,9 +1361,7 @@ select_cpu:
 		 * is set correctly for not breaking workqueue.
 		 */
 		if (next_cpu >= nr_cpu_ids)
-			hctx->next_cpu = cpumask_first(hctx->cpumask);
-		else
-			hctx->next_cpu = next_cpu;
+			next_cpu = cpumask_first(hctx->cpumask);
 		hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
 	}
 
@@ -1371,7 +1369,7 @@ select_cpu:
 	 * Do unbound schedule if we can't find a online CPU for this hctx,
 	 * and it should only happen in the path of handling CPU DEAD.
 	 */
-	if (!cpu_online(hctx->next_cpu)) {
+	if (!cpu_online(next_cpu)) {
 		if (!tried) {
 			tried = true;
 			goto select_cpu;
@@ -1381,10 +1379,13 @@ select_cpu:
 		 * Make sure to re-select CPU next time once after CPUs
 		 * in hctx->cpumask become online again.
 		 */
+		hctx->next_cpu = next_cpu;
 		hctx->next_cpu_batch = 1;
 		return WORK_CPU_UNBOUND;
 	}
-	return hctx->next_cpu;
+
+	hctx->next_cpu = next_cpu;
+	return next_cpu;
 }
 
 static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,