On 08/15/2014 10:36 AM, Jens Axboe wrote:
> On 08/15/2014 10:31 AM, Christoph Hellwig wrote:
>>> +static void loop_queue_work(struct work_struct *work)
>>
>> Offloading work straight to a workqueue dosn't make much sense
>> in the blk-mq model as we'll usually be called from one. If you
>> need to avoid the cases where we are called directly a flag for
>> the blk-mq code to always schedule a workqueue sounds like a much
>> better plan.
>
> That's a good point - would clean up this bit, and be pretty close to a
> one-liner to support in blk-mq for the drivers that always need blocking
> context.
Something like this should do the trick - totally untested. But with
that, loop would just need to add BLK_MQ_F_WQ_CONTEXT to it's tag set
flags and it could always do the work inline from ->queue_rq().
--
Jens Axboe
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 5189cb1e478a..a97eb9a4af60 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -803,6 +803,9 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
return;
+ if (hctx->flags & BLK_MQ_F_WQ_CONTEXT)
+ async = true;
+
if (!async && cpumask_test_cpu(smp_processor_id(), hctx->cpumask))
__blk_mq_run_hw_queue(hctx);
else if (hctx->queue->nr_hw_queues == 1)
@@ -1173,7 +1176,7 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
goto run_queue;
}
- if (is_sync) {
+ if (is_sync && !(data.hctx->flags & BLK_MQ_F_WQ_CONTEXT)) {
int ret;
blk_mq_bio_to_request(rq, bio);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index eb726b9c5762..c7a8c5fdd380 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -127,7 +127,8 @@ enum {
BLK_MQ_RQ_QUEUE_ERROR = 2, /* end IO with error */
BLK_MQ_F_SHOULD_MERGE = 1 << 0,
- BLK_MQ_F_SHOULD_SORT = 1 << 1,
+ BLK_MQ_F_WQ_CONTEXT = 1 << 1, /* ->queue_rq() must run from
+ * a blocking context */
BLK_MQ_F_TAG_SHARED = 1 << 2,
BLK_MQ_F_SG_MERGE = 1 << 3,
BLK_MQ_F_SYSFS_UP = 1 << 4,
