1 files changed, 114 insertions, 163 deletions

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index d43e62ebc2fc..14e6f2a2fb77 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -17,6 +17,7 @@
 
 #include <net/rtnetlink.h>
 #include <net/dst.h>
+#include <net/netdev_lock.h>
 #include <net/xfrm.h>
 #include <net/xdp.h>
 #include <linux/veth.h>
@@ -26,6 +27,7 @@
 #include <linux/ptr_ring.h>
 #include <linux/bpf_trace.h>
 #include <linux/net_tstamp.h>
+#include <linux/skbuff_ref.h>
 #include <net/page_pool/helpers.h>
 
 #define DRV_NAME	"veth"
@@ -236,8 +238,8 @@ static void veth_get_ethtool_stats(struct net_device *dev,
 				data[tx_idx + j] += *(u64 *)(base + offset);
 			}
 		} while (u64_stats_fetch_retry(&rq_stats->syncp, start));
-		pp_idx = tx_idx + VETH_TQ_STATS_LEN;
 	}
+	pp_idx = idx + dev->real_num_tx_queues * VETH_TQ_STATS_LEN;
 
 page_pool_stats:
 	veth_get_page_pool_stats(dev, &data[pp_idx]);
@@ -305,12 +307,10 @@ 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,
@@ -344,10 +344,11 @@ 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;
+	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);
@@ -370,27 +371,46 @@ 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_lstats_add(dev, length);
+			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 NETDEV_TX_OK;
-}
-
-static u64 veth_stats_tx(struct net_device *dev, u64 *packets, u64 *bytes)
-{
-	struct veth_priv *priv = netdev_priv(dev);
-
-	dev_lstats_read(dev, packets, bytes);
-	return atomic64_read(&priv->dropped);
+	return ret;
 }
 
 static void veth_stats_rx(struct veth_stats *result, struct net_device *dev)
@@ -430,24 +450,24 @@ static void veth_get_stats64(struct net_device *dev,
 	struct veth_priv *priv = netdev_priv(dev);
 	struct net_device *peer;
 	struct veth_stats rx;
-	u64 packets, bytes;
 
-	tot->tx_dropped = veth_stats_tx(dev, &packets, &bytes);
-	tot->tx_bytes = bytes;
-	tot->tx_packets = packets;
+	tot->tx_dropped = atomic64_read(&priv->dropped);
+	dev_fetch_sw_netstats(tot, dev->tstats);
 
 	veth_stats_rx(&rx, dev);
 	tot->tx_dropped += rx.xdp_tx_err;
 	tot->rx_dropped = rx.rx_drops + rx.peer_tq_xdp_xmit_err;
-	tot->rx_bytes = rx.xdp_bytes;
-	tot->rx_packets = rx.xdp_packets;
+	tot->rx_bytes += rx.xdp_bytes;
+	tot->rx_packets += rx.xdp_packets;
 
 	rcu_read_lock();
 	peer = rcu_dereference(priv->peer);
 	if (peer) {
-		veth_stats_tx(peer, &packets, &bytes);
-		tot->rx_bytes += bytes;
-		tot->rx_packets += packets;
+		struct rtnl_link_stats64 tot_peer = {};
+
+		dev_fetch_sw_netstats(&tot_peer, peer->tstats);
+		tot->rx_bytes += tot_peer.tx_bytes;
+		tot->rx_packets += tot_peer.tx_packets;
 
 		veth_stats_rx(&rx, peer);
 		tot->tx_dropped += rx.peer_tq_xdp_xmit_err;
@@ -639,7 +659,7 @@ static struct xdp_frame *veth_xdp_rcv_one(struct veth_rq *rq,
 			break;
 		case XDP_TX:
 			orig_frame = *frame;
-			xdp->rxq->mem = frame->mem;
+			xdp->rxq->mem.type = frame->mem_type;
 			if (unlikely(veth_xdp_tx(rq, xdp, bq) < 0)) {
 				trace_xdp_exception(rq->dev, xdp_prog, act);
 				frame = &orig_frame;
@@ -651,7 +671,7 @@ static struct xdp_frame *veth_xdp_rcv_one(struct veth_rq *rq,
 			goto xdp_xmit;
 		case XDP_REDIRECT:
 			orig_frame = *frame;
-			xdp->rxq->mem = frame->mem;
+			xdp->rxq->mem.type = frame->mem_type;
 			if (xdp_do_redirect(rq->dev, xdp, xdp_prog)) {
 				frame = &orig_frame;
 				stats->rx_drops++;
@@ -689,8 +709,7 @@ static void veth_xdp_rcv_bulk_skb(struct veth_rq *rq, void **frames,
 	void *skbs[VETH_XDP_BATCH];
 	int i;
 
-	if (xdp_alloc_skb_bulk(skbs, n_xdpf,
-			       GFP_ATOMIC | __GFP_ZERO) < 0) {
+	if (unlikely(!napi_skb_cache_get_bulk(skbs, n_xdpf))) {
 		for (i = 0; i < n_xdpf; i++)
 			xdp_return_frame(frames[i]);
 		stats->rx_drops += n_xdpf;
@@ -735,72 +754,10 @@ static int veth_convert_skb_to_xdp_buff(struct veth_rq *rq,
 	if (skb_shared(skb) || skb_head_is_locked(skb) ||
 	    skb_shinfo(skb)->nr_frags ||
 	    skb_headroom(skb) < XDP_PACKET_HEADROOM) {
-		u32 size, len, max_head_size, off;
-		struct sk_buff *nskb;
-		struct page *page;
-		int i, head_off;
-
-		/* We need a private copy of the skb and data buffers since
-		 * the ebpf program can modify it. We segment the original skb
-		 * into order-0 pages without linearize it.
-		 *
-		 * Make sure we have enough space for linear and paged area
-		 */
-		max_head_size = SKB_WITH_OVERHEAD(PAGE_SIZE -
-						  VETH_XDP_HEADROOM);
-		if (skb->len > PAGE_SIZE * MAX_SKB_FRAGS + max_head_size)
+		if (skb_pp_cow_data(rq->page_pool, pskb, XDP_PACKET_HEADROOM))
 			goto drop;
 
-		/* Allocate skb head */
-		page = page_pool_dev_alloc_pages(rq->page_pool);
-		if (!page)
-			goto drop;
-
-		nskb = napi_build_skb(page_address(page), PAGE_SIZE);
-		if (!nskb) {
-			page_pool_put_full_page(rq->page_pool, page, true);
-			goto drop;
-		}
-
-		skb_reserve(nskb, VETH_XDP_HEADROOM);
-		skb_copy_header(nskb, skb);
-		skb_mark_for_recycle(nskb);
-
-		size = min_t(u32, skb->len, max_head_size);
-		if (skb_copy_bits(skb, 0, nskb->data, size)) {
-			consume_skb(nskb);
-			goto drop;
-		}
-		skb_put(nskb, size);
-
-		head_off = skb_headroom(nskb) - skb_headroom(skb);
-		skb_headers_offset_update(nskb, head_off);
-
-		/* Allocate paged area of new skb */
-		off = size;
-		len = skb->len - off;
-
-		for (i = 0; i < MAX_SKB_FRAGS && off < skb->len; i++) {
-			page = page_pool_dev_alloc_pages(rq->page_pool);
-			if (!page) {
-				consume_skb(nskb);
-				goto drop;
-			}
-
-			size = min_t(u32, len, PAGE_SIZE);
-			skb_add_rx_frag(nskb, i, page, 0, size, PAGE_SIZE);
-			if (skb_copy_bits(skb, off, page_address(page),
-					  size)) {
-				consume_skb(nskb);
-				goto drop;
-			}
-
-			len -= size;
-			off += size;
-		}
-
-		consume_skb(skb);
-		skb = nskb;
+		skb = *pskb;
 	}
 
 	/* SKB "head" area always have tailroom for skb_shared_info */
@@ -999,17 +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 */
@@ -1022,9 +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;
 }
@@ -1206,14 +1177,6 @@ static int veth_enable_xdp(struct net_device *dev)
 				veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, true);
 				return err;
 			}
-
-			if (!veth_gro_requested(dev)) {
-				/* user-space did not require GRO, but adding XDP
-				 * is supposed to get GRO working
-				 */
-				dev->features |= NETIF_F_GRO;
-				netdev_features_change(dev);
-			}
 		}
 	}
 
@@ -1233,18 +1196,9 @@ static void veth_disable_xdp(struct net_device *dev)
 	for (i = 0; i < dev->real_num_rx_queues; i++)
 		rcu_assign_pointer(priv->rq[i].xdp_prog, NULL);
 
-	if (!netif_running(dev) || !veth_gro_requested(dev)) {
+	if (!netif_running(dev) || !veth_gro_requested(dev))
 		veth_napi_del(dev);
 
-		/* if user-space did not require GRO, since adding XDP
-		 * enabled it, clear it now
-		 */
-		if (!veth_gro_requested(dev) && netif_running(dev)) {
-			dev->features &= ~NETIF_F_GRO;
-			netdev_features_change(dev);
-		}
-	}
-
 	veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, false);
 }
 
@@ -1370,7 +1324,7 @@ static int veth_set_channels(struct net_device *dev,
 		if (peer)
 			netif_carrier_off(peer);
 
-		/* try to allocate new resurces, as needed*/
+		/* try to allocate new resources, as needed*/
 		err = veth_enable_range_safe(dev, old_rx_count, new_rx_count);
 		if (err)
 			goto out;
@@ -1444,6 +1398,8 @@ static int veth_open(struct net_device *dev)
 		netif_carrier_on(peer);
 	}
 
+	veth_set_xdp_features(dev);
+
 	return 0;
 }
 
@@ -1474,7 +1430,8 @@ static int veth_alloc_queues(struct net_device *dev)
 	struct veth_priv *priv = netdev_priv(dev);
 	int i;
 
-	priv->rq = kcalloc(dev->num_rx_queues, sizeof(*priv->rq), GFP_KERNEL_ACCOUNT);
+	priv->rq = kvcalloc(dev->num_rx_queues, sizeof(*priv->rq),
+			    GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL);
 	if (!priv->rq)
 		return -ENOMEM;
 
@@ -1490,30 +1447,18 @@ static void veth_free_queues(struct net_device *dev)
 {
 	struct veth_priv *priv = netdev_priv(dev);
 
-	kfree(priv->rq);
+	kvfree(priv->rq);
 }
 
 static int veth_dev_init(struct net_device *dev)
 {
-	int err;
-
-	dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats);
-	if (!dev->lstats)
-		return -ENOMEM;
-
-	err = veth_alloc_queues(dev);
-	if (err) {
-		free_percpu(dev->lstats);
-		return err;
-	}
-
-	return 0;
+	netdev_lockdep_set_classes(dev);
+	return veth_alloc_queues(dev);
 }
 
 static void veth_dev_free(struct net_device *dev)
 {
 	veth_free_queues(dev);
-	free_percpu(dev->lstats);
 }
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -1539,7 +1484,7 @@ static int veth_get_iflink(const struct net_device *dev)
 
 	rcu_read_lock();
 	peer = rcu_dereference(priv->peer);
-	iflink = peer ? peer->ifindex : 0;
+	iflink = peer ? READ_ONCE(peer->ifindex) : 0;
 	rcu_read_unlock();
 
 	return iflink;
@@ -1558,8 +1503,6 @@ static netdev_features_t veth_fix_features(struct net_device *dev,
 		if (peer_priv->_xdp_prog)
 			features &= ~NETIF_F_GSO_SOFTWARE;
 	}
-	if (priv->_xdp_prog)
-		features |= NETIF_F_GRO;
 
 	return features;
 }
@@ -1732,6 +1675,24 @@ static int veth_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
 	return 0;
 }
 
+static int veth_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto,
+				u16 *vlan_tci)
+{
+	const struct veth_xdp_buff *_ctx = (void *)ctx;
+	const struct sk_buff *skb = _ctx->skb;
+	int err;
+
+	if (!skb)
+		return -ENODATA;
+
+	err = __vlan_hwaccel_get_tag(skb, vlan_tci);
+	if (err)
+		return err;
+
+	*vlan_proto = skb->vlan_proto;
+	return err;
+}
+
 static const struct net_device_ops veth_netdev_ops = {
 	.ndo_init            = veth_dev_init,
 	.ndo_open            = veth_open,
@@ -1756,6 +1717,7 @@ static const struct net_device_ops veth_netdev_ops = {
 static const struct xdp_metadata_ops veth_xdp_metadata_ops = {
 	.xmo_rx_timestamp		= veth_xdp_rx_timestamp,
 	.xmo_rx_hash			= veth_xdp_rx_hash,
+	.xmo_rx_vlan_tag		= veth_xdp_rx_vlan_tag,
 };
 
 #define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \
@@ -1772,11 +1734,12 @@ static void veth_setup(struct net_device *dev)
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	dev->priv_flags |= IFF_NO_QUEUE;
 	dev->priv_flags |= IFF_PHONY_HEADROOM;
+	dev->priv_flags |= IFF_DISABLE_NETPOLL;
+	dev->lltx = true;
 
 	dev->netdev_ops = &veth_netdev_ops;
 	dev->xdp_metadata_ops = &veth_xdp_metadata_ops;
 	dev->ethtool_ops = &veth_ethtool_ops;
-	dev->features |= NETIF_F_LLTX;
 	dev->features |= VETH_FEATURES;
 	dev->vlan_features = dev->features &
 			     ~(NETIF_F_HW_VLAN_CTAG_TX |
@@ -1785,6 +1748,7 @@ static void veth_setup(struct net_device *dev)
 			       NETIF_F_HW_VLAN_STAG_RX);
 	dev->needs_free_netdev = true;
 	dev->priv_destructor = veth_dev_free;
+	dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
 	dev->max_mtu = ETH_MAX_MTU;
 
 	dev->hw_features = VETH_FEATURES;
@@ -1839,10 +1803,13 @@ static int veth_init_queues(struct net_device *dev, struct nlattr *tb[])
 	return 0;
 }
 
-static int veth_newlink(struct net *src_net, struct net_device *dev,
-			struct nlattr *tb[], struct nlattr *data[],
+static int veth_newlink(struct net_device *dev,
+			struct rtnl_newlink_params *params,
 			struct netlink_ext_ack *extack)
 {
+	struct net *peer_net = rtnl_newlink_peer_net(params);
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
 	int err;
 	struct net_device *peer;
 	struct veth_priv *priv;
@@ -1850,24 +1817,15 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
 	struct nlattr *peer_tb[IFLA_MAX + 1], **tbp;
 	unsigned char name_assign_type;
 	struct ifinfomsg *ifmp;
-	struct net *net;
 
 	/*
 	 * create and register peer first
 	 */
-	if (data != NULL && data[VETH_INFO_PEER] != NULL) {
-		struct nlattr *nla_peer;
+	if (data && data[VETH_INFO_PEER]) {
+		struct nlattr *nla_peer = data[VETH_INFO_PEER];
 
-		nla_peer = data[VETH_INFO_PEER];
 		ifmp = nla_data(nla_peer);
-		err = rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack);
-		if (err < 0)
-			return err;
-
-		err = veth_validate(peer_tb, NULL, extack);
-		if (err < 0)
-			return err;
-
+		rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack);
 		tbp = peer_tb;
 	} else {
 		ifmp = NULL;
@@ -1882,16 +1840,10 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
 		name_assign_type = NET_NAME_ENUM;
 	}
 
-	net = rtnl_link_get_net(src_net, tbp);
-	if (IS_ERR(net))
-		return PTR_ERR(net);
-
-	peer = rtnl_create_link(net, ifname, name_assign_type,
+	peer = rtnl_create_link(peer_net, ifname, name_assign_type,
 				&veth_link_ops, tbp, extack);
-	if (IS_ERR(peer)) {
-		put_net(net);
+	if (IS_ERR(peer))
 		return PTR_ERR(peer);
-	}
 
 	if (!ifmp || !tbp[IFLA_ADDRESS])
 		eth_hw_addr_random(peer);
@@ -1902,8 +1854,6 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
 	netif_inherit_tso_max(peer, dev);
 
 	err = register_netdevice(peer);
-	put_net(net);
-	net = NULL;
 	if (err < 0)
 		goto err_register_peer;
 
@@ -2026,6 +1976,7 @@ static struct rtnl_link_ops veth_link_ops = {
 	.newlink	= veth_newlink,
 	.dellink	= veth_dellink,
 	.policy		= veth_policy,
+	.peer_type	= VETH_INFO_PEER,
 	.maxtype	= VETH_INFO_MAX,
 	.get_link_net	= veth_get_link_net,
 	.get_num_tx_queues	= veth_get_num_queues,