On Wed, Aug 18, 2021 at 10:44:28PM +0800, Ming Lei wrote:
> struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
> unsigned int op, blk_mq_req_flags_t flags, unsigned int hctx_idx)
> {
> @@ -468,7 +485,10 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
> data.hctx = q->queue_hw_ctx[hctx_idx];
> if (!blk_mq_hw_queue_mapped(data.hctx))
> goto out_queue_exit;
> - cpu = cpumask_first_and(data.hctx->cpumask, cpu_online_mask);
> +
> + WARN_ON_ONCE(blk_mq_hctx_use_managed_irq(data.hctx));
> +
> + cpu = blk_mq_first_mapped_cpu(data.hctx);
> data.ctx = __blk_mq_get_ctx(q, cpu);
I was pondering how we could address the issue that the qla2xxx driver
is using managed IRQs which makes nvme-fc depending as class on managed
IRQ.
blk_mq_alloc_request_hctx() is the only place where we really need to
distinguish between managed and !managed IRQs. As far I undertand the
situation, if all CPUs for a hctx are going offline, the driver wont use
this context. So there is only the case we end up in this code path is
when the driver tries to reconnect the queues, e.g. after
devloss. Couldn't we in this case not just return an error and go into
error recovery? Something like this:
diff --git a/block/blk-mq.c b/block/blk-mq.c
index a2db50886a26..52fc8592c72e 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -486,9 +486,13 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
if (!blk_mq_hw_queue_mapped(data.hctx))
goto out_queue_exit;
- WARN_ON_ONCE(blk_mq_hctx_use_managed_irq(data.hctx));
-
- cpu = blk_mq_first_mapped_cpu(data.hctx);
+ if (blk_mq_hctx_use_managed_irq(data.hctx)) {
+ cpu = cpumask_first_and(hctx->cpumask, cpu_online_mask);
+ if (cpu >= nr_cpu_ids)
+ return ERR_PTR(-EINVAL);
+ } else {
+ cpu = blk_mq_first_mapped_cpu(data.hctx);
+ }
data.ctx = __blk_mq_get_ctx(q, cpu);
