net/mlx4_en: use napi_complete_done() in TX completion

In order to benefit from the new napi_defer_hard_irqs feature,
we need to use napi_complete_done() variant in this driver.

RX path is already using it, this patch implements TX completion side.

mlx4_en_process_tx_cq() now returns the amount of retired packets,
instead of a boolean, so that mlx4_en_poll_tx_cq() can pass
this value to napi_complete_done().
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlx4/en_rx.c

@@ -946,7 +946,7 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget)
 		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);
+							       budget) < budget;
 			xdp_tx_cq->xdp_busy = !clean_complete;
 		}
 	}

drivers/net/ethernet/mellanox/mlx4/en_tx.c

@@ -382,8 +382,8 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring)
 	return cnt;
 }
 
-bool mlx4_en_process_tx_cq(struct net_device *dev,
-			   struct mlx4_en_cq *cq, int napi_budget)
+int mlx4_en_process_tx_cq(struct net_device *dev,
+			  struct mlx4_en_cq *cq, int napi_budget)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_cq *mcq = &cq->mcq;
@@ -405,7 +405,7 @@ bool mlx4_en_process_tx_cq(struct net_device *dev,
 	u32 ring_cons;
 
 	if (unlikely(!priv->port_up))
-		return true;
+		return 0;
 
 	netdev_txq_bql_complete_prefetchw(ring->tx_queue);
 
@@ -480,7 +480,7 @@ bool mlx4_en_process_tx_cq(struct net_device *dev,
 	WRITE_ONCE(ring->cons, ring_cons + txbbs_skipped);
 
 	if (cq->type == TX_XDP)
-		return done < budget;
+		return done;
 
 	netdev_tx_completed_queue(ring->tx_queue, packets, bytes);
 
@@ -492,7 +492,7 @@ bool mlx4_en_process_tx_cq(struct net_device *dev,
 		ring->wake_queue++;
 	}
 
-	return done < budget;
+	return done;
 }
 
 void mlx4_en_tx_irq(struct mlx4_cq *mcq)
@@ -512,14 +512,14 @@ int mlx4_en_poll_tx_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);
-	bool clean_complete;
+	int work_done;
 
-	clean_complete = mlx4_en_process_tx_cq(dev, cq, budget);
-	if (!clean_complete)
+	work_done = mlx4_en_process_tx_cq(dev, cq, budget);
+	if (work_done >= budget)
 		return budget;
 
-	napi_complete(napi);
-	mlx4_en_arm_cq(priv, cq);
+	if (napi_complete_done(napi, work_done))
+		mlx4_en_arm_cq(priv, cq);
 
 	return 0;
 }

drivers/net/ethernet/mellanox/mlx4/mlx4_en.h

@@ -737,8 +737,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev,
 			  int budget);
 int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget);
 int mlx4_en_poll_tx_cq(struct napi_struct *napi, int budget);
-bool mlx4_en_process_tx_cq(struct net_device *dev,
-			   struct mlx4_en_cq *cq, int napi_budget);
+int mlx4_en_process_tx_cq(struct net_device *dev,
+			  struct mlx4_en_cq *cq, int napi_budget);
 u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
 			 struct mlx4_en_tx_ring *ring,
 			 int index, u64 timestamp,