Merge v6.12.62linux-rolling-lts

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 51 insertions, 13 deletions

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 18148e068aa0..4ff0d4232914 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -306,12 +306,10 @@ static void __veth_xdp_flush(struct veth_rq *rq)
 
 static int veth_xdp_rx(struct veth_rq *rq, struct sk_buff *skb)
 {
-	if (unlikely(ptr_ring_produce(&rq->xdp_ring, skb))) {
-		dev_kfree_skb_any(skb);
-		return NET_RX_DROP;
-	}
+	if (unlikely(ptr_ring_produce(&rq->xdp_ring, skb)))
+		return NETDEV_TX_BUSY; /* signal qdisc layer */
 
-	return NET_RX_SUCCESS;
+	return NET_RX_SUCCESS; /* same as NETDEV_TX_OK */
 }
 
 static int veth_forward_skb(struct net_device *dev, struct sk_buff *skb,
@@ -345,11 +343,11 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
 	struct veth_rq *rq = NULL;
-	int ret = NETDEV_TX_OK;
+	struct netdev_queue *txq;
 	struct net_device *rcv;
 	int length = skb->len;
 	bool use_napi = false;
-	int rxq;
+	int ret, rxq;
 
 	rcu_read_lock();
 	rcv = rcu_dereference(priv->peer);
@@ -372,17 +370,43 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	skb_tx_timestamp(skb);
-	if (likely(veth_forward_skb(rcv, skb, rq, use_napi) == NET_RX_SUCCESS)) {
+
+	ret = veth_forward_skb(rcv, skb, rq, use_napi);
+	switch (ret) {
+	case NET_RX_SUCCESS: /* same as NETDEV_TX_OK */
 		if (!use_napi)
 			dev_sw_netstats_tx_add(dev, 1, length);
 		else
 			__veth_xdp_flush(rq);
-	} else {
+		break;
+	case NETDEV_TX_BUSY:
+		/* If a qdisc is attached to our virtual device, returning
+		 * NETDEV_TX_BUSY is allowed.
+		 */
+		txq = netdev_get_tx_queue(dev, rxq);
+
+		if (qdisc_txq_has_no_queue(txq)) {
+			dev_kfree_skb_any(skb);
+			goto drop;
+		}
+		/* Restore Eth hdr pulled by dev_forward_skb/eth_type_trans */
+		__skb_push(skb, ETH_HLEN);
+		netif_tx_stop_queue(txq);
+		/* Makes sure NAPI peer consumer runs. Consumer is responsible
+		 * for starting txq again, until then ndo_start_xmit (this
+		 * function) will not be invoked by the netstack again.
+		 */
+		__veth_xdp_flush(rq);
+		break;
+	case NET_RX_DROP: /* same as NET_XMIT_DROP */
 drop:
 		atomic64_inc(&priv->dropped);
 		ret = NET_XMIT_DROP;
+		break;
+	default:
+		net_crit_ratelimited("%s(%s): Invalid return code(%d)",
+				     __func__, dev->name, ret);
 	}
-
 	rcu_read_unlock();
 
 	return ret;
@@ -932,17 +956,28 @@ static int veth_poll(struct napi_struct *napi, int budget)
 {
 	struct veth_rq *rq =
 		container_of(napi, struct veth_rq, xdp_napi);
+	struct veth_priv *priv = netdev_priv(rq->dev);
+	int queue_idx = rq->xdp_rxq.queue_index;
+	struct netdev_queue *peer_txq;
 	struct veth_stats stats = {};
+	struct net_device *peer_dev;
 	struct veth_xdp_tx_bq bq;
 	int done;
 
 	bq.count = 0;
 
+	/* NAPI functions as RCU section */
+	peer_dev = rcu_dereference_check(priv->peer, rcu_read_lock_bh_held());
+	peer_txq = peer_dev ? netdev_get_tx_queue(peer_dev, queue_idx) : NULL;
+
 	xdp_set_return_frame_no_direct();
 	done = veth_xdp_rcv(rq, budget, &bq, &stats);
 
 	if (stats.xdp_redirect > 0)
 		xdp_do_flush();
+	if (stats.xdp_tx > 0)
+		veth_xdp_flush(rq, &bq);
+	xdp_clear_return_frame_no_direct();
 
 	if (done < budget && napi_complete_done(napi, done)) {
 		/* Write rx_notify_masked before reading ptr_ring */
@@ -955,9 +990,12 @@ static int veth_poll(struct napi_struct *napi, int budget)
 		}
 	}
 
-	if (stats.xdp_tx > 0)
-		veth_xdp_flush(rq, &bq);
-	xdp_clear_return_frame_no_direct();
+	/* Release backpressure per NAPI poll */
+	smp_rmb(); /* Paired with netif_tx_stop_queue set_bit */
+	if (peer_txq && netif_tx_queue_stopped(peer_txq)) {
+		txq_trans_cond_update(peer_txq);
+		netif_tx_wake_queue(peer_txq);
+	}
 
 	return done;
 }