net/mlx5e: Support HTB offload

This commit adds support for HTB offload in the mlx5e driver.

Performance:

  NIC: Mellanox ConnectX-6 Dx
  CPU: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz (24 cores with HT)

  100 Gbit/s line rate, 500 UDP streams @ ~200 Mbit/s each
  48 traffic classes, flower used for steering
  No shaping (rate limits set to 4 Gbit/s per TC) - checking for max
  throughput.

  Baseline: 98.7 Gbps, 8.25 Mpps
  HTB: 6.7 Gbps, 0.56 Mpps
  HTB offload: 95.6 Gbps, 8.00 Mpps

Limitations:

1. 256 leaf nodes, 3 levels of depth.

2. Granularity for ceil is 1 Mbit/s. Rates are converted to weights, and
the bandwidth is split among the siblings according to these weights.
Other parameters for classes are not supported.

Ethtool statistics support for QoS SQs are also added. The counters are
called qos_txN_*, where N is the QoS queue number (starting from 0, the
numeration is separate from the normal SQs), and * is the counter name
(the counters are the same as for the normal SQs).

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 26 insertions, 0 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index a3cfe06d5116..d54da3797c30 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -115,17 +115,21 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 					       napi);
 	struct mlx5e_ch_stats *ch_stats = c->stats;
 	struct mlx5e_xdpsq *xsksq = &c->xsksq;
+	struct mlx5e_txqsq __rcu **qos_sqs;
 	struct mlx5e_rq *xskrq = &c->xskrq;
 	struct mlx5e_rq *rq = &c->rq;
 	bool aff_change = false;
 	bool busy_xsk = false;
 	bool busy = false;
 	int work_done = 0;
+	u16 qos_sqs_size;
 	bool xsk_open;
 	int i;
 
 	rcu_read_lock();
 
+	qos_sqs = rcu_dereference(c->qos_sqs);
+
 	xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
 
 	ch_stats->poll++;
@@ -133,6 +137,18 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	for (i = 0; i < c->num_tc; i++)
 		busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget);
 
+	if (unlikely(qos_sqs)) {
+		smp_rmb(); /* Pairs with mlx5e_qos_alloc_queues. */
+		qos_sqs_size = READ_ONCE(c->qos_sqs_size);
+
+		for (i = 0; i < qos_sqs_size; i++) {
+			struct mlx5e_txqsq *sq = rcu_dereference(qos_sqs[i]);
+
+			if (sq)
+				busy |= mlx5e_poll_tx_cq(&sq->cq, budget);
+		}
+	}
+
 	busy |= mlx5e_poll_xdpsq_cq(&c->xdpsq.cq);
 
 	if (c->xdp)
@@ -186,6 +202,16 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 		mlx5e_handle_tx_dim(&c->sq[i]);
 		mlx5e_cq_arm(&c->sq[i].cq);
 	}
+	if (unlikely(qos_sqs)) {
+		for (i = 0; i < qos_sqs_size; i++) {
+			struct mlx5e_txqsq *sq = rcu_dereference(qos_sqs[i]);
+
+			if (sq) {
+				mlx5e_handle_tx_dim(sq);
+				mlx5e_cq_arm(&sq->cq);
+			}
+		}
+	}
 
 	mlx5e_handle_rx_dim(rq);