1 files changed, 317 insertions, 14 deletions

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 64f2ab663ffe..92fa3e1ea65c 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -30,17 +30,19 @@
 #include <net/arp.h>
 #include <net/ip.h>
 #include <net/ip_fib.h>
+#include <net/ip6_fib.h>
 #include <net/ip6_route.h>
 #include <net/rtnetlink.h>
 #include <net/route.h>
 #include <net/addrconf.h>
 #include <net/l3mdev.h>
 
+#define RT_FL_TOS(oldflp4) \
+	((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))
+
 #define DRV_NAME	"vrf"
 #define DRV_VERSION	"1.0"
 
-#define vrf_is_slave(dev)   ((dev)->flags & IFF_SLAVE)
-
 #define vrf_master_get_rcu(dev) \
 	((struct net_device *)rcu_dereference(dev->rx_handler_data))
 
@@ -56,6 +58,7 @@ struct slave_queue {
 struct net_vrf {
 	struct slave_queue      queue;
 	struct rtable           *rth;
+	struct rt6_info		*rt6;
 	u32                     tb_id;
 };
 
@@ -73,9 +76,9 @@ static struct dst_entry *vrf_ip_check(struct dst_entry *dst, u32 cookie)
 	return dst;
 }
 
-static int vrf_ip_local_out(struct sk_buff *skb)
+static int vrf_ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	return ip_local_out(skb);
+	return ip_local_out(net, sk, skb);
 }
 
 static unsigned int vrf_v4_mtu(const struct dst_entry *dst)
@@ -103,12 +106,56 @@ static struct dst_ops vrf_dst_ops = {
 	.default_advmss	= vrf_default_advmss,
 };
 
+/* neighbor handling is done with actual device; do not want
+ * to flip skb->dev for those ndisc packets. This really fails
+ * for multiple next protocols (e.g., NEXTHDR_HOP). But it is
+ * a start.
+ */
+#if IS_ENABLED(CONFIG_IPV6)
+static bool check_ipv6_frame(const struct sk_buff *skb)
+{
+	const struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb->data;
+	size_t hlen = sizeof(*ipv6h);
+	bool rc = true;
+
+	if (skb->len < hlen)
+		goto out;
+
+	if (ipv6h->nexthdr == NEXTHDR_ICMP) {
+		const struct icmp6hdr *icmph;
+
+		if (skb->len < hlen + sizeof(*icmph))
+			goto out;
+
+		icmph = (struct icmp6hdr *)(skb->data + sizeof(*ipv6h));
+		switch (icmph->icmp6_type) {
+		case NDISC_ROUTER_SOLICITATION:
+		case NDISC_ROUTER_ADVERTISEMENT:
+		case NDISC_NEIGHBOUR_SOLICITATION:
+		case NDISC_NEIGHBOUR_ADVERTISEMENT:
+		case NDISC_REDIRECT:
+			rc = false;
+			break;
+		}
+	}
+
+out:
+	return rc;
+}
+#else
+static bool check_ipv6_frame(const struct sk_buff *skb)
+{
+	return false;
+}
+#endif
+
 static bool is_ip_rx_frame(struct sk_buff *skb)
 {
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
-	case htons(ETH_P_IPV6):
 		return true;
+	case htons(ETH_P_IPV6):
+		return check_ipv6_frame(skb);
 	}
 	return false;
 }
@@ -168,12 +215,53 @@ static struct rtnl_link_stats64 *vrf_get_stats64(struct net_device *dev,
 	return stats;
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
+static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
+					   struct net_device *dev)
+{
+	const struct ipv6hdr *iph = ipv6_hdr(skb);
+	struct net *net = dev_net(skb->dev);
+	struct flowi6 fl6 = {
+		/* needed to match OIF rule */
+		.flowi6_oif = dev->ifindex,
+		.flowi6_iif = LOOPBACK_IFINDEX,
+		.daddr = iph->daddr,
+		.saddr = iph->saddr,
+		.flowlabel = ip6_flowinfo(iph),
+		.flowi6_mark = skb->mark,
+		.flowi6_proto = iph->nexthdr,
+		.flowi6_flags = FLOWI_FLAG_L3MDEV_SRC | FLOWI_FLAG_SKIP_NH_OIF,
+	};
+	int ret = NET_XMIT_DROP;
+	struct dst_entry *dst;
+	struct dst_entry *dst_null = &net->ipv6.ip6_null_entry->dst;
+
+	dst = ip6_route_output(net, NULL, &fl6);
+	if (dst == dst_null)
+		goto err;
+
+	skb_dst_drop(skb);
+	skb_dst_set(skb, dst);
+
+	ret = ip6_local_out(net, skb->sk, skb);
+	if (unlikely(net_xmit_eval(ret)))
+		dev->stats.tx_errors++;
+	else
+		ret = NET_XMIT_SUCCESS;
+
+	return ret;
+err:
+	vrf_tx_error(dev, skb);
+	return NET_XMIT_DROP;
+}
+#else
 static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
 					   struct net_device *dev)
 {
 	vrf_tx_error(dev, skb);
 	return NET_XMIT_DROP;
 }
+#endif
 
 static int vrf_send_v4_prep(struct sk_buff *skb, struct flowi4 *fl4,
 			    struct net_device *vrf_dev)
@@ -208,7 +296,7 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
 		.flowi4_oif = vrf_dev->ifindex,
 		.flowi4_iif = LOOPBACK_IFINDEX,
 		.flowi4_tos = RT_TOS(ip4h->tos),
-		.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_VRFSRC |
+		.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_L3MDEV_SRC |
 				FLOWI_FLAG_SKIP_NH_OIF,
 		.daddr = ip4h->daddr,
 	};
@@ -221,7 +309,7 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
 					       RT_SCOPE_LINK);
 	}
 
-	ret = ip_local_out(skb);
+	ret = ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
 	if (unlikely(net_xmit_eval(ret)))
 		vrf_dev->stats.tx_errors++;
 	else
@@ -268,6 +356,157 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
 	return ret;
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
+static struct dst_entry *vrf_ip6_check(struct dst_entry *dst, u32 cookie)
+{
+	return dst;
+}
+
+static struct dst_ops vrf_dst_ops6 = {
+	.family		= AF_INET6,
+	.local_out	= ip6_local_out,
+	.check		= vrf_ip6_check,
+	.mtu		= vrf_v4_mtu,
+	.destroy	= vrf_dst_destroy,
+	.default_advmss	= vrf_default_advmss,
+};
+
+static int init_dst_ops6_kmem_cachep(void)
+{
+	vrf_dst_ops6.kmem_cachep = kmem_cache_create("vrf_ip6_dst_cache",
+						     sizeof(struct rt6_info),
+						     0,
+						     SLAB_HWCACHE_ALIGN,
+						     NULL);
+
+	if (!vrf_dst_ops6.kmem_cachep)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void free_dst_ops6_kmem_cachep(void)
+{
+	kmem_cache_destroy(vrf_dst_ops6.kmem_cachep);
+}
+
+static int vrf_input6(struct sk_buff *skb)
+{
+	skb->dev->stats.rx_errors++;
+	kfree_skb(skb);
+	return 0;
+}
+
+/* modelled after ip6_finish_output2 */
+static int vrf_finish_output6(struct net *net, struct sock *sk,
+			      struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct net_device *dev = dst->dev;
+	struct neighbour *neigh;
+	struct in6_addr *nexthop;
+	int ret;
+
+	skb->protocol = htons(ETH_P_IPV6);
+	skb->dev = dev;
+
+	rcu_read_lock_bh();
+	nexthop = rt6_nexthop((struct 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)) {
+		ret = dst_neigh_output(dst, neigh, skb);
+		rcu_read_unlock_bh();
+		return ret;
+	}
+	rcu_read_unlock_bh();
+
+	IP6_INC_STATS(dev_net(dst->dev),
+		      ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+	kfree_skb(skb);
+	return -EINVAL;
+}
+
+/* modelled after ip6_output */
+static int vrf_output6(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING,
+			    net, sk, skb, NULL, skb_dst(skb)->dev,
+			    vrf_finish_output6,
+			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
+}
+
+static void vrf_rt6_destroy(struct net_vrf *vrf)
+{
+	dst_destroy(&vrf->rt6->dst);
+	free_percpu(vrf->rt6->rt6i_pcpu);
+	vrf->rt6 = NULL;
+}
+
+static int vrf_rt6_create(struct net_device *dev)
+{
+	struct net_vrf *vrf = netdev_priv(dev);
+	struct dst_entry *dst;
+	struct rt6_info *rt6;
+	int cpu;
+	int rc = -ENOMEM;
+
+	rt6 = dst_alloc(&vrf_dst_ops6, dev, 0,
+			DST_OBSOLETE_NONE,
+			(DST_HOST | DST_NOPOLICY | DST_NOXFRM));
+	if (!rt6)
+		goto out;
+
+	dst = &rt6->dst;
+
+	rt6->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, GFP_KERNEL);
+	if (!rt6->rt6i_pcpu) {
+		dst_destroy(dst);
+		goto out;
+	}
+	for_each_possible_cpu(cpu) {
+		struct rt6_info **p = per_cpu_ptr(rt6->rt6i_pcpu, cpu);
+		*p =  NULL;
+	}
+
+	memset(dst + 1, 0, sizeof(*rt6) - sizeof(*dst));
+
+	INIT_LIST_HEAD(&rt6->rt6i_siblings);
+	INIT_LIST_HEAD(&rt6->rt6i_uncached);
+
+	rt6->dst.input	= vrf_input6;
+	rt6->dst.output	= vrf_output6;
+
+	rt6->rt6i_table = fib6_get_table(dev_net(dev), vrf->tb_id);
+
+	atomic_set(&rt6->dst.__refcnt, 2);
+
+	vrf->rt6 = rt6;
+	rc = 0;
+out:
+	return rc;
+}
+#else
+static int init_dst_ops6_kmem_cachep(void)
+{
+	return 0;
+}
+
+static void free_dst_ops6_kmem_cachep(void)
+{
+}
+
+static void vrf_rt6_destroy(struct net_vrf *vrf)
+{
+}
+
+static int vrf_rt6_create(struct net_device *dev)
+{
+	return 0;
+}
+#endif
+
 /* modelled after ip_finish_output2 */
 static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
@@ -311,10 +550,9 @@ err:
 	return ret;
 }
 
-static int vrf_output(struct sock *sk, struct sk_buff *skb)
+static int vrf_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct net_device *dev = skb_dst(skb)->dev;
-	struct net *net = dev_net(dev);
 
 	IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len);
 
@@ -433,7 +671,7 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
 	if (ret < 0)
 		goto out_unregister;
 
-	port_dev->flags |= IFF_SLAVE;
+	port_dev->priv_flags |= IFF_L3MDEV_SLAVE;
 	__vrf_insert_slave(queue, slave);
 	cycle_netdev(port_dev);
 
@@ -448,7 +686,7 @@ out_fail:
 
 static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
 {
-	if (netif_is_l3_master(port_dev) || vrf_is_slave(port_dev))
+	if (netif_is_l3_master(port_dev) || netif_is_l3_slave(port_dev))
 		return -EINVAL;
 
 	return do_vrf_add_slave(dev, port_dev);
@@ -462,7 +700,7 @@ static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev)
 	struct slave *slave;
 
 	netdev_upper_dev_unlink(port_dev, dev);
-	port_dev->flags &= ~IFF_SLAVE;
+	port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE;
 
 	netdev_rx_handler_unregister(port_dev);
 
@@ -490,6 +728,7 @@ static void vrf_dev_uninit(struct net_device *dev)
 	struct slave *slave, *next;
 
 	vrf_rtable_destroy(vrf);
+	vrf_rt6_destroy(vrf);
 
 	list_for_each_entry_safe(slave, next, head, list)
 		vrf_del_slave(dev, slave->dev);
@@ -513,10 +752,15 @@ static int vrf_dev_init(struct net_device *dev)
 	if (!vrf->rth)
 		goto out_stats;
 
+	if (vrf_rt6_create(dev) != 0)
+		goto out_rth;
+
 	dev->flags = IFF_MASTER | IFF_NOARP;
 
 	return 0;
 
+out_rth:
+	vrf_rtable_destroy(vrf);
 out_stats:
 	free_percpu(dev->dstats);
 	dev->dstats = NULL;
@@ -545,7 +789,7 @@ static struct rtable *vrf_get_rtable(const struct net_device *dev,
 {
 	struct rtable *rth = NULL;
 
-	if (!(fl4->flowi4_flags & FLOWI_FLAG_VRFSRC)) {
+	if (!(fl4->flowi4_flags & FLOWI_FLAG_L3MDEV_SRC)) {
 		struct net_vrf *vrf = netdev_priv(dev);
 
 		rth = vrf->rth;
@@ -555,9 +799,61 @@ static struct rtable *vrf_get_rtable(const struct net_device *dev,
 	return rth;
 }
 
+/* called under rcu_read_lock */
+static void vrf_get_saddr(struct net_device *dev, struct flowi4 *fl4)
+{
+	struct fib_result res = { .tclassid = 0 };
+	struct net *net = dev_net(dev);
+	u32 orig_tos = fl4->flowi4_tos;
+	u8 flags = fl4->flowi4_flags;
+	u8 scope = fl4->flowi4_scope;
+	u8 tos = RT_FL_TOS(fl4);
+
+	if (unlikely(!fl4->daddr))
+		return;
+
+	fl4->flowi4_flags |= FLOWI_FLAG_SKIP_NH_OIF;
+	fl4->flowi4_iif = LOOPBACK_IFINDEX;
+	fl4->flowi4_tos = tos & IPTOS_RT_MASK;
+	fl4->flowi4_scope = ((tos & RTO_ONLINK) ?
+			     RT_SCOPE_LINK : RT_SCOPE_UNIVERSE);
+
+	if (!fib_lookup(net, fl4, &res, 0)) {
+		if (res.type == RTN_LOCAL)
+			fl4->saddr = res.fi->fib_prefsrc ? : fl4->daddr;
+		else
+			fib_select_path(net, &res, fl4, -1);
+	}
+
+	fl4->flowi4_flags = flags;
+	fl4->flowi4_tos = orig_tos;
+	fl4->flowi4_scope = scope;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static struct dst_entry *vrf_get_rt6_dst(const struct net_device *dev,
+					 const struct flowi6 *fl6)
+{
+	struct rt6_info *rt = NULL;
+
+	if (!(fl6->flowi6_flags & FLOWI_FLAG_L3MDEV_SRC)) {
+		struct net_vrf *vrf = netdev_priv(dev);
+
+		rt = vrf->rt6;
+		atomic_inc(&rt->dst.__refcnt);
+	}
+
+	return (struct dst_entry *)rt;
+}
+#endif
+
 static const struct l3mdev_ops vrf_l3mdev_ops = {
 	.l3mdev_fib_table	= vrf_fib_table,
 	.l3mdev_get_rtable	= vrf_get_rtable,
+	.l3mdev_get_saddr	= vrf_get_saddr,
+#if IS_ENABLED(CONFIG_IPV6)
+	.l3mdev_get_rt6_dst	= vrf_get_rt6_dst,
+#endif
 };
 
 static void vrf_get_drvinfo(struct net_device *dev,
@@ -672,7 +968,7 @@ static int vrf_device_event(struct notifier_block *unused,
 	if (event == NETDEV_UNREGISTER) {
 		struct net_device *vrf_dev;
 
-		if (netif_is_l3_master(dev))
+		if (!netif_is_l3_slave(dev))
 			goto out;
 
 		vrf_dev = netdev_master_upper_dev_get(dev);
@@ -699,6 +995,10 @@ static int __init vrf_init_module(void)
 	if (!vrf_dst_ops.kmem_cachep)
 		return -ENOMEM;
 
+	rc = init_dst_ops6_kmem_cachep();
+	if (rc != 0)
+		goto error2;
+
 	register_netdevice_notifier(&vrf_notifier_block);
 
 	rc = rtnl_link_register(&vrf_link_ops);
@@ -709,6 +1009,8 @@ static int __init vrf_init_module(void)
 
 error:
 	unregister_netdevice_notifier(&vrf_notifier_block);
+	free_dst_ops6_kmem_cachep();
+error2:
 	kmem_cache_destroy(vrf_dst_ops.kmem_cachep);
 	return rc;
 }
@@ -718,6 +1020,7 @@ static void __exit vrf_cleanup_module(void)
 	rtnl_link_unregister(&vrf_link_ops);
 	unregister_netdevice_notifier(&vrf_notifier_block);
 	kmem_cache_destroy(vrf_dst_ops.kmem_cachep);
+	free_dst_ops6_kmem_cachep();
 }
 
 module_init(vrf_init_module);