diff mbox series

[net-next,3/6] net/mlx5: Increase hairpin buffer size

Message ID 20210626074417.714833-4-saeed@kernel.org
State New
Headers show
Series mlx5 updates 2021-06-26 | expand

Commit Message

Saeed Mahameed June 26, 2021, 7:44 a.m. UTC 
From: Ariel Levkovich <lariel@nvidia.com>

The max packet size a hairpin queue is able to handle
is determined by the total hairpin buffer size divided
by 4.

Currently the buffer size is set to 32KB which makes
the max packet size to be 8KB and doesn't support
jumbo frames of size 9KB.

This change increases the buffer size to 64KB to increase
the max frame size and support 9KB frames.

Signed-off-by: Ariel Levkovich <lariel@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 8d84d0712c20..629a61e8022f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -846,7 +846,7 @@  static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv,
 		 hash_hairpin_info(peer_id, match_prio));
 	mutex_unlock(&priv->fs.tc.hairpin_tbl_lock);
 
-	params.log_data_size = 15;
+	params.log_data_size = 16;
 	params.log_data_size = min_t(u8, params.log_data_size,
 				     MLX5_CAP_GEN(priv->mdev, log_max_hairpin_wq_data_sz));
 	params.log_data_size = max_t(u8, params.log_data_size,