[PATCH rdma-rc] RDMA/mlx5: Set user priority for DCT

From: Leon Romanovsky <leon@kernel.org>
To: Doug Ledford <dledford@redhat.com>, Jason Gunthorpe <jgg@nvidia.com>
Cc: Patrisious Haddad <phaddad@nvidia.com>,
	linux-kernel@vger.kernel.org, linux-rdma@vger.kernel.org,
	Maor Gottlieb <maorg@nvidia.com>, Moni Shoua <monis@mellanox.com>,
	Yishai Hadas <yishaih@mellanox.com>
Subject: [PATCH rdma-rc] RDMA/mlx5: Set user priority for DCT
Date: Wed,  6 Oct 2021 12:31:53 +0300	[thread overview]
Message-ID: <5fd2d94a13f5742d8803c218927322257d53205c.1633512672.git.leonro@nvidia.com> (raw)

From: Patrisious Haddad <phaddad@nvidia.com>

Currently, the driver doesn't set the PCP-based priority for DCT,
hence DCT response packets are transmitted without user priority.

Fix it by setting user provided priority in the eth_prio field
in the DCT context, which in turn sets the value in the transmitted packet.

Fixes: 776a3906b692 ("IB/mlx5: Add support for DC target QP")
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/qp.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index b2fca110346c..e5abbcfc1d57 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -4458,6 +4458,8 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 		MLX5_SET(dctc, dctc, mtu, attr->path_mtu);
 		MLX5_SET(dctc, dctc, my_addr_index, attr->ah_attr.grh.sgid_index);
 		MLX5_SET(dctc, dctc, hop_limit, attr->ah_attr.grh.hop_limit);
+		if (attr->ah_attr.type == RDMA_AH_ATTR_TYPE_ROCE)
+			MLX5_SET(dctc, dctc, eth_prio, attr->ah_attr.sl & 0x7);
 
 		err = mlx5_core_create_dct(dev, &qp->dct.mdct, qp->dct.in,
 					   MLX5_ST_SZ_BYTES(create_dct_in), out,
-- 
2.31.1

