[PATCH net-next] net: bcmgenet: complete Tx NAPI after one reclaim pass

[Nicolai Buchwitz]

After reclaiming, the Tx poll asks to be polled again. That extra poll
finds nothing to do and does not reduce the interrupt rate.

Complete the NAPI and unmask the ring interrupt right after the reclaim.

On a CM4 this raises 60 byte pktgen Tx from about 187k to 224k pps and
saves about 5% of one core at TCP line rate.

Signed-off-by: Nicolai Buchwitz <nb@xxxxxxxxxxx>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 21668e41b696..f17ad20b4b9c 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2020,25 +2020,20 @@ static int bcmgenet_tx_poll(struct napi_struct *napi, int budget)
 {
 	struct bcmgenet_tx_ring *ring =
 		container_of(napi, struct bcmgenet_tx_ring, napi);
-	unsigned int work_done = 0;
 	struct netdev_queue *txq;
 
 	spin_lock(&ring->lock);
-	work_done = __bcmgenet_tx_reclaim(ring->priv->dev, ring);
+	__bcmgenet_tx_reclaim(ring->priv->dev, ring);
 	if (ring->free_bds > (MAX_SKB_FRAGS + 1)) {
 		txq = netdev_get_tx_queue(ring->priv->dev, ring->index);
 		netif_tx_wake_queue(txq);
 	}
 	spin_unlock(&ring->lock);
 
-	if (work_done == 0) {
-		napi_complete(napi);
+	if (budget && napi_complete_done(napi, 0))
 		bcmgenet_tx_ring_int_enable(ring);
 
-		return 0;
-	}
-
-	return budget;
+	return 0;
 }
 
 static void bcmgenet_tx_reclaim_all(struct net_device *dev)
-- 
2.53.0