On 11/27/18 4:49 PM, Omar Sandoval wrote:
> On Mon, Nov 26, 2018 at 09:35:55AM -0700, Jens Axboe wrote:
>> If we are issuing a list of requests, we know if we're at the last one.
>> If we fail issuing, ensure that we call ->commits_rqs() to flush any
>> potential previous requests.
>
> One comment below, otherwise
>
> Reviewed-by: Omar Sandoval <[email protected]>
>> @@ -1260,6 +1260,14 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q,
>> struct list_head *list,
>> if (!list_empty(list)) {
>> bool needs_restart;
>>
>> + /*
>> + * If we didn't flush the entire list, we could have told
>> + * the driver there was more coming, but that turned out to
>> + * be a lie.
>> + */
>> + if (q->mq_ops->commit_rqs)
>> + q->mq_ops->commit_rqs(hctx);
>> +
>
> This hunk seems like it should go with the patch adding commit_rqs.
Agree, that would be better, since that also makes that patch fix an
actual issue instead of just being a prep patch. I'll shuffle that hunk
to that patch.
--
Jens Axboe
