[PATCH] IB/mlx4: Fix possible incorrect cq completions flushing in internal error state

[PATCH] IB/mlx4: Fix possible incorrect cq completions flushing in internal error state

[Sagi Grimberg]

From: Ariel Nahum <arieln-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>

When handling a device internal error, the driver is responsible to
drain the completion queue with flush errors.

In case a completion queue was assigned to multiple send queues, the
driver iterates over the send queues and generates flush errors of
inflight wqes. The driver must correctly pass the wc array with an
offset as a result of the previous send queue iteration. Not doing so
will overwrite previously set completions and return a wrong number
of polled completions which includes ones which were not correctly set.

Fixes: 35f05dabf95a (IB/mlx4: Reset flow support for IB kernel ULPs)
Signed-off-by: Ariel Nahum <arieln-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Cc: Yishai Hadas <yishaih-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
 drivers/infiniband/hw/mlx4/cq.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index 36eb3d0..2f42595 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -638,7 +638,7 @@ static void mlx4_ib_poll_sw_comp(struct mlx4_ib_cq *cq, int num_entries,
 	 * simulated FLUSH_ERR completions
 	 */
 	list_for_each_entry(qp, &cq->send_qp_list, cq_send_list) {
-		mlx4_ib_qp_sw_comp(qp, num_entries, wc, npolled, 1);
+		mlx4_ib_qp_sw_comp(qp, num_entries, wc + *npolled, npolled, 1);
 		if (*npolled >= num_entries)
 			goto out;
 	}
-- 
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH] IB/mlx4: Fix possible incorrect cq completions flushing in internal error state

[Doug Ledford]

[-- Attachment #1: Type: text/plain, Size: 1113 bytes --]

On 08/09/2015 04:16 AM, Sagi Grimberg wrote:
> From: Ariel Nahum <arieln-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
> 
> When handling a device internal error, the driver is responsible to
> drain the completion queue with flush errors.
> 
> In case a completion queue was assigned to multiple send queues, the
> driver iterates over the send queues and generates flush errors of
> inflight wqes. The driver must correctly pass the wc array with an
> offset as a result of the previous send queue iteration. Not doing so
> will overwrite previously set completions and return a wrong number
> of polled completions which includes ones which were not correctly set.
> 
> Fixes: 35f05dabf95a (IB/mlx4: Reset flow support for IB kernel ULPs)
> Signed-off-by: Ariel Nahum <arieln-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
> Signed-off-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
> Cc: Yishai Hadas <yishaih-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>

Applied, thanks.


-- 
Doug Ledford <dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
              GPG KeyID: 0E572FDD



[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 884 bytes --]