[PATCH net-next 2/5] veth: implement Byte Queue Limits (BQL) for latency reduction

[hawk@kernel.org]

From: Jesper Dangaard Brouer <hawk@kernel.org>

Commit dc82a33297fc ("veth: apply qdisc backpressure on full ptr_ring to
reduce TX drops") gave qdiscs control over veth by returning
NETDEV_TX_BUSY when the ptr_ring is full (DRV_XOFF).  That commit noted
a known limitation: the 256-entry ptr_ring sits in front of the qdisc as
a dark buffer, adding base latency because the qdisc has no visibility
into how many bytes are already queued there.

Add BQL support so the qdisc gets byte-level feedback and can begin
shaping traffic before the ring fills.  In testing with fq_codel, BQL
reduces ping RTT under UDP load from ~6.61ms to ~0.36ms (18x).

Charge BQL inside veth_xdp_rx() under the ptr_ring producer_lock, after
confirming the ring is not full.  The charge must precede the produce
because the NAPI consumer can run on another CPU and complete the SKB
the instant it becomes visible in the ring.  Doing both under the same
lock avoids a pre-charge/undo pattern -- BQL is only charged when
produce is guaranteed to succeed.

BQL is enabled only when a real qdisc is attached (guarded by
!qdisc_txq_has_no_queue), as HARD_TX_LOCK provides serialization
for TXQ modification like dql_queued(). For lltx devices, like veth,
this HARD_TX_LOCK serialization isn't provided.  The ptr_ring
producer_lock provides additional serialization that would allow
BQL to work correctly even with noqueue, though that combination
is not currently enabled, as the netstack will drop and warn.

Track per-SKB BQL state via a VETH_BQL_FLAG pointer tag in the ptr_ring
entry.  This is necessary because the qdisc can be replaced live while
SKBs are in-flight -- each SKB must carry the charge decision made at
enqueue time rather than re-checking the peer's qdisc at completion.

Complete per-SKB in veth_xdp_rcv() rather than in bulk, so STACK_XOFF
clears promptly when producer and consumer run on different CPUs.  Both
charge and completion use skb->len after eth_type_trans() has pulled the
Ethernet header, so the byte counts match naturally.

BQL introduces a second independent queue-stop mechanism (STACK_XOFF)
alongside the existing DRV_XOFF (ring full).  Both must be clear for
the queue to transmit.  Reset BQL state in veth_napi_del_range() after
synchronize_net() to avoid racing with in-flight veth_poll() calls.

Signed-off-by: Jesper Dangaard Brouer <hawk@kernel.org>
---
 drivers/net/veth.c | 71 +++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 60 insertions(+), 11 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index e35df717e65e..b9a79d066703 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -34,6 +34,7 @@
 #define DRV_VERSION	"1.0"
 
 #define VETH_XDP_FLAG		BIT(0)
+#define VETH_BQL_FLAG		BIT(1)
 #define VETH_RING_SIZE		256
 #define VETH_XDP_HEADROOM	(XDP_PACKET_HEADROOM + NET_IP_ALIGN)
 
@@ -280,6 +281,21 @@ static bool veth_is_xdp_frame(void *ptr)
 	return (unsigned long)ptr & VETH_XDP_FLAG;
 }
 
+static bool veth_ptr_is_bql(void *ptr)
+{
+	return (unsigned long)ptr & VETH_BQL_FLAG;
+}
+
+static struct sk_buff *veth_ptr_to_skb(void *ptr)
+{
+	return (void *)((unsigned long)ptr & ~VETH_BQL_FLAG);
+}
+
+static void *veth_skb_to_ptr(struct sk_buff *skb, bool bql)
+{
+	return bql ? (void *)((unsigned long)skb | VETH_BQL_FLAG) : skb;
+}
+
 static struct xdp_frame *veth_ptr_to_xdp(void *ptr)
 {
 	return (void *)((unsigned long)ptr & ~VETH_XDP_FLAG);
@@ -295,7 +311,7 @@ static void veth_ptr_free(void *ptr)
 	if (veth_is_xdp_frame(ptr))
 		xdp_return_frame(veth_ptr_to_xdp(ptr));
 	else
-		kfree_skb(ptr);
+		kfree_skb(veth_ptr_to_skb(ptr));
 }
 
 static void __veth_xdp_flush(struct veth_rq *rq)
@@ -309,19 +325,33 @@ static void __veth_xdp_flush(struct veth_rq *rq)
 	}
 }
 
-static int veth_xdp_rx(struct veth_rq *rq, struct sk_buff *skb)
+static int veth_xdp_rx(struct veth_rq *rq, struct sk_buff *skb, bool do_bql,
+		       struct netdev_queue *txq)
 {
-	if (unlikely(ptr_ring_produce(&rq->xdp_ring, skb)))
+	struct ptr_ring *ring = &rq->xdp_ring;
+
+	spin_lock(&ring->producer_lock);
+	if (unlikely(!ring->size) || __ptr_ring_full(ring)) {
+		spin_unlock(&ring->producer_lock);
 		return NETDEV_TX_BUSY; /* signal qdisc layer */
+	}
+
+	/* BQL charge before produce; consumer cannot see entry yet */
+	if (do_bql)
+		netdev_tx_sent_queue(txq, skb->len);
+
+	__ptr_ring_produce(ring, veth_skb_to_ptr(skb, do_bql));
+	spin_unlock(&ring->producer_lock);
 
 	return NET_RX_SUCCESS; /* same as NETDEV_TX_OK */
 }
 
 static int veth_forward_skb(struct net_device *dev, struct sk_buff *skb,
-			    struct veth_rq *rq, bool xdp)
+			    struct veth_rq *rq, bool xdp, bool do_bql,
+			    struct netdev_queue *txq)
 {
 	return __dev_forward_skb(dev, skb) ?: xdp ?
-		veth_xdp_rx(rq, skb) :
+		veth_xdp_rx(rq, skb, do_bql, txq) :
 		__netif_rx(skb);
 }
 
@@ -352,6 +382,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct net_device *rcv;
 	int length = skb->len;
 	bool use_napi = false;
+	bool do_bql = false;
 	int ret, rxq;
 
 	rcu_read_lock();
@@ -375,8 +406,11 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	skb_tx_timestamp(skb);
+	txq = netdev_get_tx_queue(dev, rxq);
 
-	ret = veth_forward_skb(rcv, skb, rq, use_napi);
+	/* BQL charge happens inside veth_xdp_rx() under producer_lock */
+	do_bql = use_napi && !qdisc_txq_has_no_queue(txq);
+	ret = veth_forward_skb(rcv, skb, rq, use_napi, do_bql, txq);
 	switch (ret) {
 	case NET_RX_SUCCESS: /* same as NETDEV_TX_OK */
 		if (!use_napi)
@@ -388,8 +422,6 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 		/* 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;
@@ -412,6 +444,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 		net_crit_ratelimited("%s(%s): Invalid return code(%d)",
 				     __func__, dev->name, ret);
 	}
+
 	rcu_read_unlock();
 
 	return ret;
@@ -900,7 +933,8 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq,
 
 static int veth_xdp_rcv(struct veth_rq *rq, int budget,
 			struct veth_xdp_tx_bq *bq,
-			struct veth_stats *stats)
+			struct veth_stats *stats,
+			struct netdev_queue *peer_txq)
 {
 	int i, done = 0, n_xdpf = 0;
 	void *xdpf[VETH_XDP_BATCH];
@@ -928,9 +962,13 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget,
 			}
 		} else {
 			/* ndo_start_xmit */
-			struct sk_buff *skb = ptr;
+			bool bql_charged = veth_ptr_is_bql(ptr);
+			struct sk_buff *skb = veth_ptr_to_skb(ptr);
 
 			stats->xdp_bytes += skb->len;
+			if (peer_txq && bql_charged)
+				netdev_tx_completed_queue(peer_txq, 1, skb->len);
+
 			skb = veth_xdp_rcv_skb(rq, skb, bq, stats);
 			if (skb) {
 				if (skb_shared(skb) || skb_unclone(skb, GFP_ATOMIC))
@@ -975,7 +1013,7 @@ static int veth_poll(struct napi_struct *napi, int budget)
 	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);
+	done = veth_xdp_rcv(rq, budget, &bq, &stats, peer_txq);
 
 	if (stats.xdp_redirect > 0)
 		xdp_do_flush();
@@ -1073,6 +1111,7 @@ static int __veth_napi_enable(struct net_device *dev)
 static void veth_napi_del_range(struct net_device *dev, int start, int end)
 {
 	struct veth_priv *priv = netdev_priv(dev);
+	struct net_device *peer;
 	int i;
 
 	for (i = start; i < end; i++) {
@@ -1091,6 +1130,15 @@ static void veth_napi_del_range(struct net_device *dev, int start, int end)
 		ptr_ring_cleanup(&rq->xdp_ring, veth_ptr_free);
 	}
 
+	/* Reset BQL on peer's txqs: remaining ring items were freed above
+	 * without BQL completion, so DQL state must be reset.
+	 */
+	peer = rtnl_dereference(priv->peer);
+	if (peer) {
+		for (i = start; i < end; i++)
+			netdev_tx_reset_queue(netdev_get_tx_queue(peer, i));
+	}
+
 	for (i = start; i < end; i++) {
 		page_pool_destroy(priv->rq[i].page_pool);
 		priv->rq[i].page_pool = NULL;
@@ -1740,6 +1788,7 @@ static void veth_setup(struct net_device *dev)
 	dev->priv_flags |= IFF_PHONY_HEADROOM;
 	dev->priv_flags |= IFF_DISABLE_NETPOLL;
 	dev->lltx = true;
+	dev->bql = true;
 
 	dev->netdev_ops = &veth_netdev_ops;
 	dev->xdp_metadata_ops = &veth_xdp_metadata_ops;
-- 
2.43.0