net/mlx5e: Enable adaptive-TX moderation

Add support for adaptive TX moderation. This greatly reduces TX interrupt
rate and increases bandwidth, mostly for TCP bandwidth over ARM
architecture (below). There is a slight single stream TCP with very large
message sizes degradation (x86). In this case if there's any moderation on
transmitted packets the bandwidth would reduce due to hitting TCP output limit.
Since this is a synthetic case, this is still worth doing.

Performance improvement (ConnectX-4Lx 40GbE, ARM)
TCP 64B bandwidth with 1-50 streams increased 6-35%.
TCP 64B bandwidth with 100-500 streams increased 20-70%.

Performance improvement (ConnectX-5 100GbE, x86)
Bandwidth: increased up to 40% (1024B with 10s of streams).
Interrupt rate: reduced up to 50% (1024B with 1000s of streams).

Performance degradation (ConnectX-5 100GbE, x86)
Bandwidth: up to 10% decrease single stream TCP (1MB message size from
51Gb/s to 47Gb/s).

Signed-off-by: Tal Gilboa <talgi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 28 insertions, 9 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index f292bb346985..900661d45c8a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -44,6 +44,30 @@ static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c)
 	return cpumask_test_cpu(current_cpu, aff);
 }
 
+static void mlx5e_handle_tx_dim(struct mlx5e_txqsq *sq)
+{
+	struct net_dim_sample dim_sample;
+
+	if (unlikely(!MLX5E_TEST_BIT(sq->state, MLX5E_SQ_STATE_AM)))
+		return;
+
+	net_dim_sample(sq->cq.event_ctr, sq->stats.packets, sq->stats.bytes,
+		       &dim_sample);
+	net_dim(&sq->dim, dim_sample);
+}
+
+static void mlx5e_handle_rx_dim(struct mlx5e_rq *rq)
+{
+	struct net_dim_sample dim_sample;
+
+	if (unlikely(!MLX5E_TEST_BIT(rq->state, MLX5E_RQ_STATE_AM)))
+		return;
+
+	net_dim_sample(rq->cq.event_ctr, rq->stats.packets, rq->stats.bytes,
+		       &dim_sample);
+	net_dim(&rq->dim, dim_sample);
+}
+
 int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel,
@@ -75,18 +99,13 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	if (unlikely(!napi_complete_done(napi, work_done)))
 		return work_done;
 
-	for (i = 0; i < c->num_tc; i++)
+	for (i = 0; i < c->num_tc; i++) {
+		mlx5e_handle_tx_dim(&c->sq[i]);
 		mlx5e_cq_arm(&c->sq[i].cq);
-
-	if (MLX5E_TEST_BIT(c->rq.state, MLX5E_RQ_STATE_AM)) {
-		struct net_dim_sample dim_sample;
-		net_dim_sample(c->rq.cq.event_ctr,
-			       c->rq.stats.packets,
-			       c->rq.stats.bytes,
-			       &dim_sample);
-		net_dim(&c->rq.dim, dim_sample);
 	}
 
+	mlx5e_handle_rx_dim(&c->rq);
+
 	mlx5e_cq_arm(&c->rq.cq);
 	mlx5e_cq_arm(&c->icosq.cq);