Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from David Miller:

 1) Fix interrupt name truncation in mv88e6xxx dsa driver, from Andrew
    Lunn.

 2) Process generic XDP even if SKB is cloned, from Toke Høiland-Jørgensen.

 3) Fix leak of kernel memory to userspace in smc, from Eric Dumazet.

 4) Add some missing netlink attribute validation to matchall and
    flower, from Davide Caratti.

 5) Send icmp responses properly when NAT has been applied to the frame
    before we get to the tunnel emitting the icmp, from Jason Donenfeld.

 6) Make sure there is enough SKB headroom when adding dsa tags for qca
    and ar9331. From Per Forlin.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (62 commits)
  netdevice.h: fix all kernel-doc and Sphinx warnings
  net: dsa: tag_ar9331: Make sure there is headroom for tag
  net: dsa: tag_qca: Make sure there is headroom for tag
  net, ip6_tunnel: enhance tunnel locate with link check
  net/smc: no peer ID in CLC decline for SMCD
  net/smc: transfer fasync_list in case of fallback
  net: hns3: fix a copying IPv6 address error in hclge_fd_get_flow_tuples()
  net: hns3: fix VF bandwidth does not take effect in some case
  net: hns3: add management table after IMP reset
  mac80211: fix wrong 160/80+80 MHz setting
  cfg80211: add missing policy for NL80211_ATTR_STATUS_CODE
  xfrm: interface: use icmp_ndo_send helper
  wireguard: device: use icmp_ndo_send helper
  sunvnet: use icmp_ndo_send helper
  gtp: use icmp_ndo_send helper
  icmp: introduce helper for nat'd source address in network device context
  net/sched: flower: add missing validation of TCA_FLOWER_FLAGS
  net/sched: matchall: add missing validation of TCA_MATCHALL_FLAGS
  net/flow_dissector: remove unexist field description
  page_pool: refill page when alloc.count of pool is zero
  ...

2 files changed, 81 insertions, 21 deletions

diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c
index 02045494c24c..e0086758b6ee 100644
--- a/net/ipv6/ip6_icmp.c
+++ b/net/ipv6/ip6_icmp.c
@@ -45,4 +45,38 @@ out:
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL(icmpv6_send);
+
+#if IS_ENABLED(CONFIG_NF_NAT)
+#include <net/netfilter/nf_conntrack.h>
+void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info)
+{
+	struct sk_buff *cloned_skb = NULL;
+	enum ip_conntrack_info ctinfo;
+	struct in6_addr orig_ip;
+	struct nf_conn *ct;
+
+	ct = nf_ct_get(skb_in, &ctinfo);
+	if (!ct || !(ct->status & IPS_SRC_NAT)) {
+		icmpv6_send(skb_in, type, code, info);
+		return;
+	}
+
+	if (skb_shared(skb_in))
+		skb_in = cloned_skb = skb_clone(skb_in, GFP_ATOMIC);
+
+	if (unlikely(!skb_in || skb_network_header(skb_in) < skb_in->head ||
+	    (skb_network_header(skb_in) + sizeof(struct ipv6hdr)) >
+	    skb_tail_pointer(skb_in) || skb_ensure_writable(skb_in,
+	    skb_network_offset(skb_in) + sizeof(struct ipv6hdr))))
+		goto out;
+
+	orig_ip = ipv6_hdr(skb_in)->saddr;
+	ipv6_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.in6;
+	icmpv6_send(skb_in, type, code, info);
+	ipv6_hdr(skb_in)->saddr = orig_ip;
+out:
+	consume_skb(cloned_skb);
+}
+EXPORT_SYMBOL(icmpv6_ndo_send);
+#endif
 #endif
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index b5dd20c4599b..5d65436ad5ad 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -121,6 +121,7 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev)
 
 /**
  * ip6_tnl_lookup - fetch tunnel matching the end-point addresses
+ *   @link: ifindex of underlying interface
  *   @remote: the address of the tunnel exit-point
  *   @local: the address of the tunnel entry-point
  *
@@ -134,37 +135,56 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev)
 	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
 
 static struct ip6_tnl *
-ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_addr *local)
+ip6_tnl_lookup(struct net *net, int link,
+	       const struct in6_addr *remote, const struct in6_addr *local)
 {
 	unsigned int hash = HASH(remote, local);
-	struct ip6_tnl *t;
+	struct ip6_tnl *t, *cand = NULL;
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
 	struct in6_addr any;
 
 	for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
-		if (ipv6_addr_equal(local, &t->parms.laddr) &&
-		    ipv6_addr_equal(remote, &t->parms.raddr) &&
-		    (t->dev->flags & IFF_UP))
+		if (!ipv6_addr_equal(local, &t->parms.laddr) ||
+		    !ipv6_addr_equal(remote, &t->parms.raddr) ||
+		    !(t->dev->flags & IFF_UP))
+			continue;
+
+		if (link == t->parms.link)
 			return t;
+		else
+			cand = t;
 	}
 
 	memset(&any, 0, sizeof(any));
 	hash = HASH(&any, local);
 	for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
-		if (ipv6_addr_equal(local, &t->parms.laddr) &&
-		    ipv6_addr_any(&t->parms.raddr) &&
-		    (t->dev->flags & IFF_UP))
+		if (!ipv6_addr_equal(local, &t->parms.laddr) ||
+		    !ipv6_addr_any(&t->parms.raddr) ||
+		    !(t->dev->flags & IFF_UP))
+			continue;
+
+		if (link == t->parms.link)
 			return t;
+		else if (!cand)
+			cand = t;
 	}
 
 	hash = HASH(remote, &any);
 	for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
-		if (ipv6_addr_equal(remote, &t->parms.raddr) &&
-		    ipv6_addr_any(&t->parms.laddr) &&
-		    (t->dev->flags & IFF_UP))
+		if (!ipv6_addr_equal(remote, &t->parms.raddr) ||
+		    !ipv6_addr_any(&t->parms.laddr) ||
+		    !(t->dev->flags & IFF_UP))
+			continue;
+
+		if (link == t->parms.link)
 			return t;
+		else if (!cand)
+			cand = t;
 	}
 
+	if (cand)
+		return cand;
+
 	t = rcu_dereference(ip6n->collect_md_tun);
 	if (t && t->dev->flags & IFF_UP)
 		return t;
@@ -351,7 +371,8 @@ static struct ip6_tnl *ip6_tnl_locate(struct net *net,
 	     (t = rtnl_dereference(*tp)) != NULL;
 	     tp = &t->next) {
 		if (ipv6_addr_equal(local, &t->parms.laddr) &&
-		    ipv6_addr_equal(remote, &t->parms.raddr)) {
+		    ipv6_addr_equal(remote, &t->parms.raddr) &&
+		    p->link == t->parms.link) {
 			if (create)
 				return ERR_PTR(-EEXIST);
 
@@ -485,7 +506,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
 	   processing of the error. */
 
 	rcu_read_lock();
-	t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->daddr, &ipv6h->saddr);
+	t = ip6_tnl_lookup(dev_net(skb->dev), skb->dev->ifindex, &ipv6h->daddr, &ipv6h->saddr);
 	if (!t)
 		goto out;
 
@@ -887,7 +908,7 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto,
 	int ret = -1;
 
 	rcu_read_lock();
-	t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr);
+	t = ip6_tnl_lookup(dev_net(skb->dev), skb->dev->ifindex, &ipv6h->saddr, &ipv6h->daddr);
 
 	if (t) {
 		u8 tproto = READ_ONCE(t->parms.proto);
@@ -1420,8 +1441,10 @@ tx_err:
 static void ip6_tnl_link_config(struct ip6_tnl *t)
 {
 	struct net_device *dev = t->dev;
+	struct net_device *tdev = NULL;
 	struct __ip6_tnl_parm *p = &t->parms;
 	struct flowi6 *fl6 = &t->fl.u.ip6;
+	unsigned int mtu;
 	int t_hlen;
 
 	memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
@@ -1457,22 +1480,25 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
 		struct rt6_info *rt = rt6_lookup(t->net,
 						 &p->raddr, &p->laddr,
 						 p->link, NULL, strict);
+		if (rt) {
+			tdev = rt->dst.dev;
+			ip6_rt_put(rt);
+		}
 
-		if (!rt)
-			return;
+		if (!tdev && p->link)
+			tdev = __dev_get_by_index(t->net, p->link);
 
-		if (rt->dst.dev) {
-			dev->hard_header_len = rt->dst.dev->hard_header_len +
-				t_hlen;
+		if (tdev) {
+			dev->hard_header_len = tdev->hard_header_len + t_hlen;
+			mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU);
 
-			dev->mtu = rt->dst.dev->mtu - t_hlen;
+			dev->mtu = mtu - t_hlen;
 			if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
 				dev->mtu -= 8;
 
 			if (dev->mtu < IPV6_MIN_MTU)
 				dev->mtu = IPV6_MIN_MTU;
 		}
-		ip6_rt_put(rt);
 	}
 }