[PATCH 1/1] nvme-pci: Hold cq_poll_lock while completing CQEs

[PATCH 1/1] nvme-pci: Hold cq_poll_lock while completing CQEs

[Bijan Mottahedeh]

Avoid scheduling a polling thread if it has cqe's to complete, otherwise
another thread may free enough tags out of order, allowing a queue wrap.

This is an interim solution. Longer term, the two-pass completion should
be fixed.  It was done that way when submit and complete processing were
using the same spinlock, so reducing the critical section was helpful,
but that's not needed anymore.

Signed-off-by: Bijan Mottahedeh <bijan.mottahedeh@oracle.com>
---
 drivers/nvme/host/pci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index ace4dd9..d3f23d6 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1078,9 +1078,9 @@ static int nvme_poll(struct blk_mq_hw_ctx *hctx)
 
 	spin_lock(&nvmeq->cq_poll_lock);
 	found = nvme_process_cq(nvmeq, &start, &end, -1);
+	nvme_complete_cqes(nvmeq, start, end);
 	spin_unlock(&nvmeq->cq_poll_lock);
 
-	nvme_complete_cqes(nvmeq, start, end);
 	return found;
 }
 
-- 
1.8.3.1


_______________________________________________
linux-nvme mailing list
linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

Re: [PATCH 1/1] nvme-pci: Hold cq_poll_lock while completing CQEs

[Sagi Grimberg]

This needs a Fixes tag, and should probably also be
picked up for stable. Other than that, looks fine,

Reviewed-by: Sagi Grimberg <sagi@grimberg.me>

_______________________________________________
linux-nvme mailing list
linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

Re: [PATCH 1/1] nvme-pci: Hold cq_poll_lock while completing CQEs

[Bijan Mottahedeh]

On 2/26/2020 3:06 PM, Sagi Grimberg wrote:
 > This needs a Fixes tag, and should probably also be
 > picked up for stable. Other than that, looks fine,
 >
 > Reviewed-by: Sagi Grimberg <sagi@grimberg.me>

Is this the right tag?

Fixes: dabcefab45d3 (nvme: provide optimized poll function for separate 
poll queues)

Should I send a v2?

Thanks.

--bijan

_______________________________________________
linux-nvme mailing list
linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

Re: [PATCH 1/1] nvme-pci: Hold cq_poll_lock while completing CQEs

[Jens Axboe]

On 2/26/20 7:31 PM, Bijan Mottahedeh wrote:
> On 2/26/2020 3:06 PM, Sagi Grimberg wrote:
>  > This needs a Fixes tag, and should probably also be
>  > picked up for stable. Other than that, looks fine,
>  >
>  > Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
> 
> Is this the right tag?
> 
> Fixes: dabcefab45d3 (nvme: provide optimized poll function for separate 
> poll queues)

Should be:

Fixes: dabcefab45d3 ("nvme: provide optimized poll function for separate poll queues")

> Should I send a v2?

I think so, always better that way.

Feel free to add my:

Reviewed-by: Jens Axboe <axboe@kernel.dk>

to it as well.

-- 
Jens Axboe


_______________________________________________
linux-nvme mailing list
linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme