linux-block.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Sagi Grimberg <sagi@grimberg.me>
To: Bart Van Assche <Bart.VanAssche@sandisk.com>,
	"linux-rdma@vger.kernel.org" <linux-rdma@vger.kernel.org>,
	"linux-block@vger.kernel.org" <linux-block@vger.kernel.org>,
	"linux-nvme@lists.infradead.org" <linux-nvme@lists.infradead.org>,
	"target-devel@vger.kernel.org" <target-devel@vger.kernel.org>
Subject: Re: [PATCH rfc 06/10] IB/cq: Don't force IB_POLL_DIRECT poll context for ib_process_cq_direct
Date: Mon, 13 Mar 2017 10:24:40 +0200	[thread overview]
Message-ID: <f4ade02b-9d17-20ae-f910-47c718f2a5bd@grimberg.me> (raw)
In-Reply-To: <1489077040.2597.3.camel@sandisk.com>


>> polling the completion queue directly does not interfere
>> with the existing polling logic, hence drop the requirement.
>>
>> This can be used for polling mode ULPs.
>>
>> Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
>> ---
>>  drivers/infiniband/core/cq.c | 2 --
>>  1 file changed, 2 deletions(-)
>>
>> diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c
>> index 21d1a38af489..7f6ae0ecb0c5 100644
>> --- a/drivers/infiniband/core/cq.c
>> +++ b/drivers/infiniband/core/cq.c
>> @@ -64,8 +64,6 @@ static int __ib_process_cq(struct ib_cq *cq, int budget)
>>   */
>>  int ib_process_cq_direct(struct ib_cq *cq, int budget)
>>  {
>> -	WARN_ON_ONCE(cq->poll_ctx != IB_POLL_DIRECT);
>> -
>>  	return __ib_process_cq(cq, budget);
>>  }
>>  EXPORT_SYMBOL(ib_process_cq_direct);
>
> Using ib_process_cq_direct() for queues that have another type than
> IB_POLL_DIRECT may trigger concurrent CQ processing.

Correct.

> Before this patch
> the completions from each CQ were processed sequentially. That's a big
> change so I think this should be mentioned clearly in the header above
> ib_process_cq_direct().

Note that I now see that the cq lock is not sufficient for mutual
exclusion here because we're referencing cq->wc array outside of it.

There are three options I see here:
1. we'll need to allocate a different wc array for polling mode,
perhaps a smaller one?
2. Export __ib_process_cq (in some form) with an option to pass in a wc
array.
3. Simply not support non-selective polling but it seems like a shame...

Any thoughts?

  reply	other threads:[~2017-03-13  8:24 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-03-09 13:16 [PATCH rfc 00/10] non selective polling block interface Sagi Grimberg
2017-03-09 13:16 ` [PATCH rfc 01/10] nvme-pci: Split __nvme_process_cq to poll and handle Sagi Grimberg
2017-03-09 13:57   ` Johannes Thumshirn
2017-03-22 19:07   ` Christoph Hellwig
2017-03-09 13:16 ` [PATCH rfc 02/10] nvme-pci: Add budget to __nvme_process_cq Sagi Grimberg
2017-03-09 13:46   ` Johannes Thumshirn
2017-03-22 19:08   ` Christoph Hellwig
2017-03-09 13:16 ` [PATCH rfc 03/10] nvme-pci: open-code polling logic in nvme_poll Sagi Grimberg
2017-03-09 13:56   ` Johannes Thumshirn
2017-03-22 19:09   ` Christoph Hellwig
2017-03-09 13:16 ` [PATCH rfc 04/10] block: Add a non-selective polling interface Sagi Grimberg
2017-03-09 13:44   ` Johannes Thumshirn
2017-03-10  3:04     ` Damien Le Moal
2017-03-13  8:26       ` Sagi Grimberg
2017-03-09 16:25   ` Bart Van Assche
2017-03-13  8:15     ` Sagi Grimberg
2017-03-14 21:21       ` Bart Van Assche
2017-03-09 13:16 ` [PATCH rfc 05/10] nvme-pci: Support blk_poll_batch Sagi Grimberg
2017-03-09 13:16 ` [PATCH rfc 06/10] IB/cq: Don't force IB_POLL_DIRECT poll context for ib_process_cq_direct Sagi Grimberg
2017-03-09 16:30   ` Bart Van Assche
2017-03-13  8:24     ` Sagi Grimberg [this message]
2017-03-14 21:32       ` Bart Van Assche
2017-03-09 13:16 ` [PATCH rfc 07/10] nvme-rdma: Don't rearm the CQ when polling directly Sagi Grimberg
2017-03-09 13:52   ` Johannes Thumshirn
2017-03-09 13:16 ` [PATCH rfc 08/10] nvme-rdma: Support blk_poll_batch Sagi Grimberg
2017-03-09 13:16 ` [PATCH rfc 09/10] nvmet: Use non-selective polling Sagi Grimberg
2017-03-09 13:54   ` Johannes Thumshirn
2017-03-09 13:16 ` [PATCH rfc 10/10] target: " Sagi Grimberg
2017-03-18 23:58   ` Nicholas A. Bellinger
2017-03-21 11:35     ` Sagi Grimberg

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=f4ade02b-9d17-20ae-f910-47c718f2a5bd@grimberg.me \
    --to=sagi@grimberg.me \
    --cc=Bart.VanAssche@sandisk.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=target-devel@vger.kernel.org \
    --subject='Re: [PATCH rfc 06/10] IB/cq: Don'\''t force IB_POLL_DIRECT poll context for ib_process_cq_direct' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
on how to clone and mirror all data and code used for this inbox