blk-mq: make sure that correct hctx->next_cpu is set

Ming Lei · axboe · commit a1c735fb7907 · 2018-04-10T08:38:46.000-06:00
From commit 20e4d81 (blk-mq: simplify queue mapping & schedule with each possisble CPU), one hctx can be mapped from all offline CPUs, then hctx->next_cpu can be set as wrong. This patch fixes this issue by making hctx->next_cpu pointing to the first CPU in hctx->cpumask if all CPUs in hctx->cpumask are offline. 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> Fixes: 20e4d81 ("blk-mq: simplify queue mapping & schedule with each possisble CPU") Cc: stable@vger.kernel.org Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
diff --git a/block/blk-mq.c b/block/blk-mq.c
@@ -2431,6 +2431,8 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 		 */
 		hctx->next_cpu = cpumask_first_and(hctx->cpumask,
 				cpu_online_mask);
+		if (hctx->next_cpu >= nr_cpu_ids)
+			hctx->next_cpu = cpumask_first(hctx->cpumask);
 		hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
 	}
 }

Original file line number	Diff line number	Diff line change
`@@ -2431,6 +2431,8 @@ static void blk_mq_map_swqueue(struct request_queue *q)`
`2431`	`2431`	`*/`
`2432`	`2432`	`hctx->next_cpu = cpumask_first_and(hctx->cpumask,`
`2433`	`2433`	`cpu_online_mask);`
	`2434`	`+ if (hctx->next_cpu >= nr_cpu_ids)`
	`2435`	`+ hctx->next_cpu = cpumask_first(hctx->cpumask);`
`2434`	`2436`	`hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;`
`2435`	`2437`	`}`
`2436`	`2438`	`}`