1 files changed, 65 insertions, 119 deletions

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index e0b1ab99a359..571847a7f86d 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -26,6 +26,7 @@
 
 #include <linux/inetdevice.h>
 #include <net/arp.h>
+#include <net/flow.h>
 #include <net/ip.h>
 #include <net/ip_fib.h>
 #include <net/ip6_fib.h>
@@ -34,6 +35,7 @@
 #include <net/addrconf.h>
 #include <net/l3mdev.h>
 #include <net/fib_rules.h>
+#include <net/netdev_lock.h>
 #include <net/sch_generic.h>
 #include <net/netns/generic.h>
 #include <net/netfilter/nf_conntrack.h>
@@ -121,59 +123,12 @@ struct net_vrf {
 	int			ifindex;
 };
 
-struct pcpu_dstats {
-	u64			tx_pkts;
-	u64			tx_bytes;
-	u64			tx_drps;
-	u64			rx_pkts;
-	u64			rx_bytes;
-	u64			rx_drps;
-	struct u64_stats_sync	syncp;
-};
-
-static void vrf_rx_stats(struct net_device *dev, int len)
-{
-	struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
-
-	u64_stats_update_begin(&dstats->syncp);
-	dstats->rx_pkts++;
-	dstats->rx_bytes += len;
-	u64_stats_update_end(&dstats->syncp);
-}
-
 static void vrf_tx_error(struct net_device *vrf_dev, struct sk_buff *skb)
 {
 	vrf_dev->stats.tx_errors++;
 	kfree_skb(skb);
 }
 
-static void vrf_get_stats64(struct net_device *dev,
-			    struct rtnl_link_stats64 *stats)
-{
-	int i;
-
-	for_each_possible_cpu(i) {
-		const struct pcpu_dstats *dstats;
-		u64 tbytes, tpkts, tdrops, rbytes, rpkts;
-		unsigned int start;
-
-		dstats = per_cpu_ptr(dev->dstats, i);
-		do {
-			start = u64_stats_fetch_begin_irq(&dstats->syncp);
-			tbytes = dstats->tx_bytes;
-			tpkts = dstats->tx_pkts;
-			tdrops = dstats->tx_drps;
-			rbytes = dstats->rx_bytes;
-			rpkts = dstats->rx_pkts;
-		} while (u64_stats_fetch_retry_irq(&dstats->syncp, start));
-		stats->tx_bytes += tbytes;
-		stats->tx_packets += tpkts;
-		stats->tx_dropped += tdrops;
-		stats->rx_bytes += rbytes;
-		stats->rx_packets += rpkts;
-	}
-}
-
 static struct vrf_map *netns_vrf_map(struct net *net)
 {
 	struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id);
@@ -388,15 +343,13 @@ unlock:
 static bool qdisc_tx_is_default(const struct net_device *dev)
 {
 	struct netdev_queue *txq;
-	struct Qdisc *qdisc;
 
 	if (dev->num_tx_queues > 1)
 		return false;
 
 	txq = netdev_get_tx_queue(dev, 0);
-	qdisc = rcu_access_pointer(txq->qdisc);
 
-	return !qdisc->enqueue;
+	return qdisc_txq_has_no_queue(txq);
 }
 
 /* Local traffic destined to local address. Reinsert the packet to rx
@@ -405,7 +358,7 @@ static bool qdisc_tx_is_default(const struct net_device *dev)
 static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev,
 			  struct dst_entry *dst)
 {
-	int len = skb->len;
+	unsigned int len = skb->len;
 
 	skb_orphan(skb);
 
@@ -418,10 +371,10 @@ static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	skb->protocol = eth_type_trans(skb, dev);
 
-	if (likely(netif_rx(skb) == NET_RX_SUCCESS))
-		vrf_rx_stats(dev, len);
+	if (likely(__netif_rx(skb) == NET_RX_SUCCESS))
+		dev_dstats_rx_add(dev, len);
 	else
-		this_cpu_inc(dev->dstats->rx_drps);
+		dev_dstats_rx_dropped(dev);
 
 	return NETDEV_TX_OK;
 }
@@ -472,14 +425,13 @@ static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
 
 	memset(&fl6, 0, sizeof(fl6));
 	/* needed to match OIF rule */
-	fl6.flowi6_oif = dev->ifindex;
+	fl6.flowi6_l3mdev = dev->ifindex;
 	fl6.flowi6_iif = LOOPBACK_IFINDEX;
 	fl6.daddr = iph->daddr;
 	fl6.saddr = iph->saddr;
 	fl6.flowlabel = ip6_flowinfo(iph);
 	fl6.flowi6_mark = skb->mark;
 	fl6.flowi6_proto = iph->nexthdr;
-	fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF;
 
 	dst = ip6_dst_lookup_flow(net, NULL, &fl6, NULL);
 	if (IS_ERR(dst) || dst == dst_null)
@@ -551,10 +503,10 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
 
 	memset(&fl4, 0, sizeof(fl4));
 	/* needed to match OIF rule */
-	fl4.flowi4_oif = vrf_dev->ifindex;
+	fl4.flowi4_l3mdev = vrf_dev->ifindex;
 	fl4.flowi4_iif = LOOPBACK_IFINDEX;
-	fl4.flowi4_tos = RT_TOS(ip4h->tos);
-	fl4.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_SKIP_NH_OIF;
+	fl4.flowi4_dscp = ip4h_dscp(ip4h);
+	fl4.flowi4_flags = FLOWI_FLAG_ANYSRC;
 	fl4.flowi4_proto = ip4h->protocol;
 	fl4.daddr = ip4h->daddr;
 	fl4.saddr = ip4h->saddr;
@@ -610,19 +562,14 @@ static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev)
 
 static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
 {
-	int len = skb->len;
-	netdev_tx_t ret = is_ip_tx_frame(skb, dev);
-
-	if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
-		struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
+	unsigned int len = skb->len;
+	netdev_tx_t ret;
 
-		u64_stats_update_begin(&dstats->syncp);
-		dstats->tx_pkts++;
-		dstats->tx_bytes += len;
-		u64_stats_update_end(&dstats->syncp);
-	} else {
-		this_cpu_inc(dev->dstats->tx_drps);
-	}
+	ret = is_ip_tx_frame(skb, dev);
+	if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN))
+		dev_dstats_tx_add(dev, len);
+	else
+		dev_dstats_tx_dropped(dev);
 
 	return ret;
 }
@@ -665,18 +612,18 @@ static int vrf_finish_output6(struct net *net, struct sock *sk,
 	skb->protocol = htons(ETH_P_IPV6);
 	skb->dev = dev;
 
-	rcu_read_lock_bh();
-	nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr);
+	rcu_read_lock();
+	nexthop = rt6_nexthop(dst_rt6_info(dst), &ipv6_hdr(skb)->daddr);
 	neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop);
 	if (unlikely(!neigh))
 		neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
 	if (!IS_ERR(neigh)) {
 		sock_confirm_neigh(skb, neigh);
 		ret = neigh_output(neigh, skb, false);
-		rcu_read_unlock_bh();
+		rcu_read_unlock();
 		return ret;
 	}
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 
 	IP6_INC_STATS(dev_net(dst->dev),
 		      ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
@@ -815,8 +762,8 @@ static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf)
 	 */
 	if (rt6) {
 		dst = &rt6->dst;
-		dev_replace_track(dst->dev, net->loopback_dev,
-				  &dst->dev_tracker, GFP_KERNEL);
+		netdev_ref_replace(dst->dev, net->loopback_dev,
+				   &dst->dev_tracker, GFP_KERNEL);
 		dst->dev = net->loopback_dev;
 		dst_release(dst);
 	}
@@ -873,7 +820,7 @@ static int vrf_rt6_create(struct net_device *dev)
 static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
-	struct rtable *rt = (struct rtable *)dst;
+	struct rtable *rt = dst_rtable(dst);
 	struct net_device *dev = dst->dev;
 	unsigned int hh_len = LL_RESERVED_SPACE(dev);
 	struct neighbour *neigh;
@@ -890,7 +837,7 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 		}
 	}
 
-	rcu_read_lock_bh();
+	rcu_read_lock();
 
 	neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
 	if (!IS_ERR(neigh)) {
@@ -899,11 +846,11 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 		sock_confirm_neigh(skb, neigh);
 		/* if crossing protocols, can not use the cached header */
 		ret = neigh_output(neigh, skb, is_v6gw);
-		rcu_read_unlock_bh();
+		rcu_read_unlock();
 		return ret;
 	}
 
-	rcu_read_unlock_bh();
+	rcu_read_unlock();
 	vrf_tx_error(skb->dev, skb);
 	return -EINVAL;
 }
@@ -1062,8 +1009,8 @@ static void vrf_rtable_release(struct net_device *dev, struct net_vrf *vrf)
 	 */
 	if (rth) {
 		dst = &rth->dst;
-		dev_replace_track(dst->dev, net->loopback_dev,
-				  &dst->dev_tracker, GFP_KERNEL);
+		netdev_ref_replace(dst->dev, net->loopback_dev,
+				   &dst->dev_tracker, GFP_KERNEL);
 		dst->dev = net->loopback_dev;
 		dst_release(dst);
 	}
@@ -1078,7 +1025,7 @@ static int vrf_rtable_create(struct net_device *dev)
 		return -ENOMEM;
 
 	/* create a dst for routing packets out through a VRF device */
-	rth = rt_dst_alloc(dev, 0, RTN_UNICAST, 1, 1);
+	rth = rt_dst_alloc(dev, 0, RTN_UNICAST, 1);
 	if (!rth)
 		return -ENOMEM;
 
@@ -1177,22 +1124,15 @@ static void vrf_dev_uninit(struct net_device *dev)
 
 	vrf_rtable_release(dev, vrf);
 	vrf_rt6_release(dev, vrf);
-
-	free_percpu(dev->dstats);
-	dev->dstats = NULL;
 }
 
 static int vrf_dev_init(struct net_device *dev)
 {
 	struct net_vrf *vrf = netdev_priv(dev);
 
-	dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats);
-	if (!dev->dstats)
-		goto out_nomem;
-
 	/* create the default dst which points back to us */
 	if (vrf_rtable_create(dev) != 0)
-		goto out_stats;
+		goto out_nomem;
 
 	if (vrf_rt6_create(dev) != 0)
 		goto out_rth;
@@ -1206,9 +1146,6 @@ static int vrf_dev_init(struct net_device *dev)
 
 out_rth:
 	vrf_rtable_release(dev, vrf);
-out_stats:
-	free_percpu(dev->dstats);
-	dev->dstats = NULL;
 out_nomem:
 	return -ENOMEM;
 }
@@ -1218,7 +1155,6 @@ static const struct net_device_ops vrf_netdev_ops = {
 	.ndo_uninit		= vrf_dev_uninit,
 	.ndo_start_xmit		= vrf_xmit,
 	.ndo_set_mac_address	= eth_mac_addr,
-	.ndo_get_stats64	= vrf_get_stats64,
 	.ndo_add_slave		= vrf_add_slave,
 	.ndo_del_slave		= vrf_del_slave,
 };
@@ -1266,6 +1202,7 @@ static int vrf_prepare_mac_header(struct sk_buff *skb,
 	eth = (struct ethhdr *)skb->data;
 
 	skb_reset_mac_header(skb);
+	skb_reset_mac_len(skb);
 
 	/* we set the ethernet destination and the source addresses to the
 	 * address of the VRF device.
@@ -1295,9 +1232,9 @@ static int vrf_prepare_mac_header(struct sk_buff *skb,
  */
 static int vrf_add_mac_header_if_unset(struct sk_buff *skb,
 				       struct net_device *vrf_dev,
-				       u16 proto)
+				       u16 proto, struct net_device *orig_dev)
 {
-	if (skb_mac_header_was_set(skb))
+	if (skb_mac_header_was_set(skb) && dev_has_header(orig_dev))
 		return 0;
 
 	return vrf_prepare_mac_header(skb, vrf_dev, proto);
@@ -1365,6 +1302,8 @@ static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev,
 	struct net *net = dev_net(vrf_dev);
 	struct rt6_info *rt6;
 
+	skb_dst_drop(skb);
+
 	rt6 = vrf_ip6_route_lookup(net, vrf_dev, &fl6, ifindex, skb,
 				   RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_IFACE);
 	if (unlikely(!rt6))
@@ -1385,8 +1324,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
 
 	/* loopback, multicast & non-ND link-local traffic; do not push through
 	 * packet taps again. Reset pkt_type for upper layers to process skb.
-	 * For strict packets with a source LLA, determine the dst using the
-	 * original ifindex.
+	 * For non-loopback strict packets, determine the dst using the original
+	 * ifindex.
 	 */
 	if (skb->pkt_type == PACKET_LOOPBACK || (need_strict && !is_ndisc)) {
 		skb->dev = vrf_dev;
@@ -1395,7 +1334,7 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
 
 		if (skb->pkt_type == PACKET_LOOPBACK)
 			skb->pkt_type = PACKET_HOST;
-		else if (ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)
+		else
 			vrf_ip6_input_dst(skb, vrf_dev, orig_iif);
 
 		goto out;
@@ -1403,7 +1342,9 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
 
 	/* if packet is NDISC then keep the ingress interface */
 	if (!is_ndisc) {
-		vrf_rx_stats(vrf_dev, skb->len);
+		struct net_device *orig_dev = skb->dev;
+
+		dev_dstats_rx_add(vrf_dev, skb->len);
 		skb->dev = vrf_dev;
 		skb->skb_iif = vrf_dev->ifindex;
 
@@ -1411,7 +1352,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
 			int err;
 
 			err = vrf_add_mac_header_if_unset(skb, vrf_dev,
-							  ETH_P_IPV6);
+							  ETH_P_IPV6,
+							  orig_dev);
 			if (likely(!err)) {
 				skb_push(skb, skb->mac_len);
 				dev_queue_xmit_nit(skb, vrf_dev);
@@ -1441,6 +1383,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
 static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev,
 				  struct sk_buff *skb)
 {
+	struct net_device *orig_dev = skb->dev;
+
 	skb->dev = vrf_dev;
 	skb->skb_iif = vrf_dev->ifindex;
 	IPCB(skb)->flags |= IPSKB_L3SLAVE;
@@ -1456,12 +1400,13 @@ static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev,
 		goto out;
 	}
 
-	vrf_rx_stats(vrf_dev, skb->len);
+	dev_dstats_rx_add(vrf_dev, skb->len);
 
 	if (!list_empty(&vrf_dev->ptype_all)) {
 		int err;
 
-		err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IP);
+		err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IP,
+						  orig_dev);
 		if (likely(!err)) {
 			skb_push(skb, skb->mac_len);
 			dev_queue_xmit_nit(skb, vrf_dev);
@@ -1535,8 +1480,8 @@ static const struct l3mdev_ops vrf_l3mdev_ops = {
 static void vrf_get_drvinfo(struct net_device *dev,
 			    struct ethtool_drvinfo *info)
 {
-	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
-	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strscpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strscpy(info->version, DRV_VERSION, sizeof(info->version));
 }
 
 static const struct ethtool_ops vrf_ethtool_ops = {
@@ -1593,14 +1538,12 @@ static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it)
 
 	nlmsg_end(skb, nlh);
 
-	/* fib_nl_{new,del}rule handling looks for net from skb->sk */
-	skb->sk = dev_net(dev)->rtnl;
 	if (add_it) {
-		err = fib_nl_newrule(skb, nlh, NULL);
+		err = fib_newrule(dev_net(dev), skb, nlh, NULL, true);
 		if (err == -EEXIST)
 			err = 0;
 	} else {
-		err = fib_nl_delrule(skb, nlh, NULL);
+		err = fib_delrule(dev_net(dev), skb, nlh, NULL, true);
 		if (err == -ENOENT)
 			err = 0;
 	}
@@ -1672,10 +1615,10 @@ static void vrf_setup(struct net_device *dev)
 	eth_hw_addr_random(dev);
 
 	/* don't acquire vrf device's netif_tx_lock when transmitting */
-	dev->features |= NETIF_F_LLTX;
+	dev->lltx = true;
 
 	/* don't allow vrf devices to change network namespaces. */
-	dev->features |= NETIF_F_NETNS_LOCAL;
+	dev->netns_immutable = true;
 
 	/* does not make sense for a VLAN to be added to a vrf device */
 	dev->features   |= NETIF_F_VLAN_CHALLENGED;
@@ -1700,6 +1643,8 @@ static void vrf_setup(struct net_device *dev)
 	dev->min_mtu = IPV6_MIN_MTU;
 	dev->max_mtu = IP6_MAX_MTU;
 	dev->mtu = dev->max_mtu;
+
+	dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS;
 }
 
 static int vrf_validate(struct nlattr *tb[], struct nlattr *data[],
@@ -1731,11 +1676,12 @@ static void vrf_dellink(struct net_device *dev, struct list_head *head)
 	unregister_netdevice_queue(dev, head);
 }
 
-static int vrf_newlink(struct net *src_net, struct net_device *dev,
-		       struct nlattr *tb[], struct nlattr *data[],
+static int vrf_newlink(struct net_device *dev,
+		       struct rtnl_newlink_params *params,
 		       struct netlink_ext_ack *extack)
 {
 	struct net_vrf *vrf = netdev_priv(dev);
+	struct nlattr **data = params->data;
 	struct netns_vrf *nn_vrf;
 	bool *add_fib_rules;
 	struct net *net;
@@ -1922,7 +1868,7 @@ unlock:
 	return res;
 }
 
-static int vrf_shared_table_handler(struct ctl_table *table, int write,
+static int vrf_shared_table_handler(const struct ctl_table *table, int write,
 				    void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net = (struct net *)table->extra1;
@@ -1959,7 +1905,6 @@ static const struct ctl_table vrf_table[] = {
 		/* set by the vrf_netns_init */
 		.extra1		= NULL,
 	},
-	{ },
 };
 
 static int vrf_netns_init_sysctl(struct net *net, struct netns_vrf *nn_vrf)
@@ -1973,7 +1918,8 @@ static int vrf_netns_init_sysctl(struct net *net, struct netns_vrf *nn_vrf)
 	/* init the extra1 parameter with the reference to current netns */
 	table[0].extra1 = net;
 
-	nn_vrf->ctl_hdr = register_net_sysctl(net, "net/vrf", table);
+	nn_vrf->ctl_hdr = register_net_sysctl_sz(net, "net/vrf", table,
+						 ARRAY_SIZE(vrf_table));
 	if (!nn_vrf->ctl_hdr) {
 		kfree(table);
 		return -ENOMEM;
@@ -1985,7 +1931,7 @@ static int vrf_netns_init_sysctl(struct net *net, struct netns_vrf *nn_vrf)
 static void vrf_netns_exit_sysctl(struct net *net)
 {
 	struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id);
-	struct ctl_table *table;
+	const struct ctl_table *table;
 
 	table = nn_vrf->ctl_hdr->ctl_table_arg;
 	unregister_net_sysctl_table(nn_vrf->ctl_hdr);