[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20220907233636.388475-7-saeed@kernel.org>
Date: Wed, 7 Sep 2022 16:36:28 -0700
From: Saeed Mahameed <saeed@...nel.org>
To: Saeed Mahameed <saeedm@...dia.com>,
Leon Romanovsky <leonro@...dia.com>
Cc: "David S. Miller" <davem@...emloft.net>,
Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>,
Eric Dumazet <edumazet@...gle.com>, netdev@...r.kernel.org,
Tariq Toukan <tariqt@...dia.com>,
Jason Gunthorpe <jgg@...dia.com>, linux-rdma@...r.kernel.org,
"Liu, Changcheng" <jerrliu@...dia.com>, Liu@...r.kernel.org,
Mark Bloch <mbloch@...dia.com>
Subject: [PATCH mlx5-next 06/14] net/mlx5: Lag, enable hash mode by default for all NICs
From: "Liu, Changcheng" <jerrliu@...dia.com>
The firmware supports adding a steering rule to catch egress traffic
of the QPs/TISs which are set port affinity explicitly in hash mode.
Enable that mode for NICS with 2 ports as well.
Signed-off-by: Liu, Changcheng <jerrliu@...dia.com>
Reviewed-by: Mark Bloch <mbloch@...dia.com>
Signed-off-by: Saeed Mahameed <saeedm@...dia.com>
---
.../net/ethernet/mellanox/mlx5/core/lag/lag.c | 17 +++++++++--------
1 file changed, 9 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index d4d4d1d1e8c7..97c4a525226b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -484,21 +484,22 @@ void mlx5_modify_lag(struct mlx5_lag *ldev,
mlx5_lag_drop_rule_setup(ldev, tracker);
}
-#define MLX5_LAG_ROCE_HASH_PORTS_SUPPORTED 4
static int mlx5_lag_set_port_sel_mode_roce(struct mlx5_lag *ldev,
unsigned long *flags)
{
- struct lag_func *dev0 = &ldev->pf[MLX5_LAG_P1];
+ struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
- if (ldev->ports == MLX5_LAG_ROCE_HASH_PORTS_SUPPORTED) {
- /* Four ports are support only in hash mode */
- if (!MLX5_CAP_PORT_SELECTION(dev0->dev, port_select_flow_table))
- return -EINVAL;
- set_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, flags);
+ if (!MLX5_CAP_PORT_SELECTION(dev0, port_select_flow_table)) {
if (ldev->ports > 2)
- ldev->buckets = MLX5_LAG_MAX_HASH_BUCKETS;
+ return -EINVAL;
+ return 0;
}
+ if (ldev->ports > 2)
+ ldev->buckets = MLX5_LAG_MAX_HASH_BUCKETS;
+
+ set_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, flags);
+
return 0;
}
--
2.37.2
Powered by blists - more mailing lists