diff options
author | Tariq Toukan <tariqt@mellanox.com> | 2017-06-15 13:35:37 +0200 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2017-06-16 04:53:23 +0200 |
commit | 6c78511b0503c9b53fd0f5ccc8b28d5e94a3dfcb (patch) | |
tree | 3e1e040b393aa76fb287bc8c6b13775b653324f6 /drivers/net/ethernet/mellanox/mlx4/en_cq.c | |
parent | net/mlx4_en: Improve XDP xmit function (diff) | |
download | linux-6c78511b0503c9b53fd0f5ccc8b28d5e94a3dfcb.tar.xz linux-6c78511b0503c9b53fd0f5ccc8b28d5e94a3dfcb.zip |
net/mlx4_en: Poll XDP TX completion queue in RX NAPI
Instead of having their own NAPIs, XDP TX completion queues get
polled within the corresponding RX NAPI.
This prevents any possible race on TX ring prod/cons indices,
between the context that issues the transmits (RX NAPI) and the
context that handles the completions (was previously done in
a separate NAPI).
This also improves performance, as it decreases the number
of NAPIs running on a CPU, saving the overhead of syncing
and switching between the contexts.
Performance tests:
Tested on ConnectX3Pro, Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz
Single queue no-RSS optimization ON.
XDP_TX packet rate:
-------------------------------------
| Before | After | Gain |
IPv4 | 12.0 Mpps | 13.8 Mpps | 15% |
IPv6 | 12.0 Mpps | 13.8 Mpps | 15% |
-------------------------------------
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Cc: kernel-team@fb.com
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx4/en_cq.c')
-rw-r--r-- | drivers/net/ethernet/mellanox/mlx4/en_cq.c | 25 |
1 files changed, 18 insertions, 7 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c index 09dd3776db76..85fe17e4dcfb 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c @@ -146,16 +146,25 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, if (err) goto free_eq; - cq->mcq.comp = cq->type != RX ? mlx4_en_tx_irq : mlx4_en_rx_irq; cq->mcq.event = mlx4_en_cq_event; - if (cq->type != RX) + switch (cq->type) { + case TX: + cq->mcq.comp = mlx4_en_tx_irq; netif_tx_napi_add(cq->dev, &cq->napi, mlx4_en_poll_tx_cq, NAPI_POLL_WEIGHT); - else + napi_enable(&cq->napi); + break; + case RX: + cq->mcq.comp = mlx4_en_rx_irq; netif_napi_add(cq->dev, &cq->napi, mlx4_en_poll_rx_cq, 64); - - napi_enable(&cq->napi); + napi_enable(&cq->napi); + break; + case TX_XDP: + /* nothing regarding napi, it's shared with rx ring */ + cq->xdp_busy = false; + break; + } return 0; @@ -184,8 +193,10 @@ void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq) void mlx4_en_deactivate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq) { - napi_disable(&cq->napi); - netif_napi_del(&cq->napi); + if (cq->type != TX_XDP) { + napi_disable(&cq->napi); + netif_napi_del(&cq->napi); + } mlx4_cq_free(priv->mdev->dev, &cq->mcq); } |