net/mlx5: DR, Enable QP retransmission

[ Upstream commit ec449ed8230cd30769de3cb70ee0fce293047372 ]

Under high stress, SW steering might get stuck on polling for completion
that never comes.
For such cases QP needs to have protocol retransmission mechanism enabled.
Currently the retransmission timeout is defined as 0 (unlimited). Fix this
by defining a real timeout.

Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index 9df0e73d1c358d7c3a96382740115fbecb3ef119..69b49deb66b225d8b08889e1960d16303dae62d7 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -620,6 +620,7 @@ static int dr_cmd_modify_qp_rtr2rts(struct mlx5_core_dev *mdev,
 
        MLX5_SET(qpc, qpc, retry_count, attr->retry_cnt);
        MLX5_SET(qpc, qpc, rnr_retry, attr->rnr_retry);
+       MLX5_SET(qpc, qpc, primary_address_path.ack_timeout, 0x8); /* ~1ms */
 
        MLX5_SET(rtr2rts_qp_in, in, opcode, MLX5_CMD_OP_RTR2RTS_QP);
        MLX5_SET(rtr2rts_qp_in, in, qpn, dr_qp->qpn);