summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--block/blk-mq.c14
-rw-r--r--block/blk-softirq.c5
2 files changed, 16 insertions, 3 deletions
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 1dc157c85a83..89bd9cb9defc 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -568,6 +568,20 @@ static void __blk_mq_complete_request(struct request *rq)
if (!blk_mq_mark_complete(rq))
return;
+ /*
+ * Most of single queue controllers, there is only one irq vector
+ * for handling IO completion, and the only irq's affinity is set
+ * as all possible CPUs. On most of ARCHs, this affinity means the
+ * irq is handled on one specific CPU.
+ *
+ * So complete IO reqeust in softirq context in case of single queue
+ * for not degrading IO performance by irqsoff latency.
+ */
+ if (rq->q->nr_hw_queues == 1) {
+ __blk_complete_request(rq);
+ return;
+ }
+
if (!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) {
rq->q->softirq_done_fn(rq);
return;
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 15c1f5e12eb8..e47a2f751884 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -97,8 +97,8 @@ static int blk_softirq_cpu_dead(unsigned int cpu)
void __blk_complete_request(struct request *req)
{
- int ccpu, cpu;
struct request_queue *q = req->q;
+ int cpu, ccpu = q->mq_ops ? req->mq_ctx->cpu : req->cpu;
unsigned long flags;
bool shared = false;
@@ -110,8 +110,7 @@ void __blk_complete_request(struct request *req)
/*
* Select completion CPU
*/
- if (req->cpu != -1) {
- ccpu = req->cpu;
+ if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) && ccpu != -1) {
if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags))
shared = cpus_share_cache(cpu, ccpu);
} else