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>

1 files changed, 19 insertions, 3 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 747e4d7d7693..e5fb89505a13 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -880,8 +880,10 @@ next:
 	rcu_read_unlock();
 
 	if (likely(polled)) {
-		if (doorbell_pending)
-			mlx4_en_xmit_doorbell(priv->tx_ring[TX_XDP][cq->ring]);
+		if (doorbell_pending) {
+			priv->tx_cq[TX_XDP][cq_ring]->xdp_busy = true;
+			mlx4_en_xmit_doorbell(priv->tx_ring[TX_XDP][cq_ring]);
+		}
 
 		mlx4_cq_set_ci(&cq->mcq);
 		wmb(); /* ensure HW sees CQ consumer before we post new buffers */
@@ -912,16 +914,30 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget)
 	struct mlx4_en_cq *cq = container_of(napi, struct mlx4_en_cq, napi);
 	struct net_device *dev = cq->dev;
 	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_en_cq *xdp_tx_cq = NULL;
+	bool clean_complete = true;
 	int done;
 
+	if (priv->tx_ring_num[TX_XDP]) {
+		xdp_tx_cq = priv->tx_cq[TX_XDP][cq->ring];
+		if (xdp_tx_cq->xdp_busy) {
+			clean_complete = mlx4_en_process_tx_cq(dev, xdp_tx_cq,
+							       budget);
+			xdp_tx_cq->xdp_busy = !clean_complete;
+		}
+	}
+
 	done = mlx4_en_process_rx_cq(dev, cq, budget);
 
 	/* If we used up all the quota - we're probably not done yet... */
-	if (done == budget) {
+	if (done == budget || !clean_complete) {
 		const struct cpumask *aff;
 		struct irq_data *idata;
 		int cpu_curr;
 
+		/* in case we got here because of !clean_complete */
+		done = budget;
+
 		INC_PERF_COUNTER(priv->pstats.napi_quota);
 
 		cpu_curr = smp_processor_id();