diff options
| author | Amir Vadai <amirv@mellanox.com> | 2012-04-05 01:33:24 +0400 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2012-04-05 13:08:03 +0400 |
| commit | 0e98b523c4a4119cbd17e58dff385cc329064694 (patch) | |
| tree | 4c16b13b5f118cfcf607195d1683ed01ba508b77 /drivers/net/ethernet/mellanox/mlx4/en_resources.c | |
| parent | 73a0d907301ece200d32b4e8ba2da2ca296b507f (diff) | |
| download | linux-0e98b523c4a4119cbd17e58dff385cc329064694.tar.xz | |
net/mlx4_en: Force user priority by QP attribute
Instead of relying on HW to change schedule queue by UP, schedule
queue is fixed for a tx_ring, and UP in WQE is ignored in this aspect. This
resolves two issues with untagged traffic:
1. untagged traffic has no UP in packet which is needed for QoS. The change
above allows setting the schedule queue (and by that the UP) of such a stream.
2. BlueFlame uses the same field used by vlan tag. So forcing UP from QPC
allows using BF for untagged but prioritized traffic.
In old firmware that force UP is not supported, untagged traffic will not subject to
QoS.
Because UP is set by QP, need to always have a tx ring per UP, even if pfcrx
module paramter is false.
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx4/en_resources.c')
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx4/en_resources.c | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c index bcbc54c16947..10c24c784b70 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c @@ -39,7 +39,7 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride, int is_tx, int rss, int qpn, int cqn, - struct mlx4_qp_context *context) + int user_prio, struct mlx4_qp_context *context) { struct mlx4_en_dev *mdev = priv->mdev; @@ -57,6 +57,10 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride, context->local_qpn = cpu_to_be32(qpn); context->pri_path.ackto = 1 & 0x07; context->pri_path.sched_queue = 0x83 | (priv->port - 1) << 6; + if (user_prio >= 0) { + context->pri_path.sched_queue |= user_prio << 3; + context->pri_path.feup = 1 << 6; + } context->pri_path.counter_index = 0xff; context->cqn_send = cpu_to_be32(cqn); context->cqn_recv = cpu_to_be32(cqn); |