blk-mq: remove the get_cpu/put_cpu pair in blk_mq_complete_request

We don't really care if we get migrated during the I/O completion.
In the worth case we either perform an IPI that wasn't required, or
complete the request on a CPU which we just migrated off.

Reviewed-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit is contained in:
Christoph Hellwig 2020-06-11 08:44:48 +02:00 committed by Jens Axboe
parent 15f73f5b3e
commit 4c8fc19686
1 changed files with 1 additions and 2 deletions

View File

@ -685,7 +685,7 @@ void blk_mq_complete_request(struct request *rq)
return; return;
} }
cpu = get_cpu(); cpu = raw_smp_processor_id();
if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags)) if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags))
shared = cpus_share_cache(cpu, ctx->cpu); shared = cpus_share_cache(cpu, ctx->cpu);
@ -697,7 +697,6 @@ void blk_mq_complete_request(struct request *rq)
} else { } else {
__blk_mq_complete_request(rq); __blk_mq_complete_request(rq);
} }
put_cpu();
} }
EXPORT_SYMBOL(blk_mq_complete_request); EXPORT_SYMBOL(blk_mq_complete_request);