[PATCH 1/2] blk-mq: not deactivate hctx if the device doesn't use managed irq

[Ming Lei]

On Tue, Jun 29, 2021 at 02:39:14PM +0200, Hannes Reinecke wrote:
> On 6/29/21 9:49 AM, Ming Lei wrote:
> > hctx is deactivated when all CPU in hctx->cpumask become offline by
> > draining all requests originated from this hctx and moving new
> > allocation to active hctx. This way is for avoiding inflight IO when
> > the managed irq is shutdown.
> > 
> > Some drivers(nvme fc, rdma, tcp, loop) doesn't use managed irq, so
> > they needn't to deactivate hctx. Also, they are the only user of
> > blk_mq_alloc_request_hctx() which is used for connecting io queue.
> > And their requirement is that the connect request can be submitted
> > via one specified hctx on which all CPU in its hctx->cpumask may have
> > become offline.
> > 
> 
> How can you submit a connect request for a hctx on which all CPUs are
> offline? That hctx will be unusable as it'll never be able to receive
> interrupts ...

I believe BLK_MQ_F_NOT_USE_MANAGED_IRQ is self-explanatory. And the
interrupt(non-managed) of this hctx will be migrated to online CPUs,
see migrate_one_irq().

For managed irq, we have to prevent new allocation if all CPUs of this
hctx is offline because genirq will shutdown the interrupt.

> 
> > Address the requirement for nvme fc/rdma/loop, so the reported kernel
> > panic on the following line in blk_mq_alloc_request_hctx() can be fixed.
> > 
> > 	data.ctx = __blk_mq_get_ctx(q, cpu)
> > 
> > Cc: Sagi Grimberg <sagi at grimberg.me>
> > Cc: Daniel Wagner <dwagner at suse.de>
> > Cc: Wen Xiong <wenxiong at us.ibm.com>
> > Cc: John Garry <john.garry at huawei.com>
> > Signed-off-by: Ming Lei <ming.lei at redhat.com>
> > ---
> >   block/blk-mq.c         | 6 +++++-
> >   include/linux/blk-mq.h | 1 +
> >   2 files changed, 6 insertions(+), 1 deletion(-)
> > 
> > diff --git a/block/blk-mq.c b/block/blk-mq.c
> > index df5dc3b756f5..74632f50d969 100644
> > --- a/block/blk-mq.c
> > +++ b/block/blk-mq.c
> > @@ -494,7 +494,7 @@ 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);
> > +	cpu = cpumask_first(data.hctx->cpumask);
> >   	data.ctx = __blk_mq_get_ctx(q, cpu);
> 
> I don't get it.
> Doesn't this allow us to allocate a request on a dead cpu, ie the very thing
> we try to prevent?

It is fine to allocate & dispatch one request to the hctx when all CPU on
its cpumask are offline if this hctx's interrupt isn't managed.


Thanks,
Ming