diff mbox

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

Message ID 1439108187-12785-1-git-send-email-sagig@mellanox.com (mailing list archive)
State Accepted
Headers show

Commit Message

Sagi Grimberg Aug. 9, 2015, 8:16 a.m. UTC 
From: Ariel Nahum <arieln@mellanox.com>

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@mellanox.com>
Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Cc: Yishai Hadas <yishaih@mellanox.com>
---
 drivers/infiniband/hw/mlx4/cq.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

Comments

Doug Ledford Aug. 15, 2015, 1:41 a.m. UTC | #1 
On 08/09/2015 04:16 AM, Sagi Grimberg wrote:
> From: Ariel Nahum <arieln@mellanox.com>
> 
> 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@mellanox.com>
> Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
> Cc: Yishai Hadas <yishaih@mellanox.com>

Applied, thanks.
diff mbox

Patch

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;
 	}