1 files changed, 320 insertions, 149 deletions

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 087304427bbb..e19507614f64 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -54,23 +54,35 @@
 #include <linux/mroute6.h>
 #include <net/l3mdev.h>
 #include <net/lwtunnel.h>
+#include <net/ip_tunnels.h>
 
 static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *dev = dst->dev;
-	const struct in6_addr *nexthop;
+	struct inet6_dev *idev = ip6_dst_idev(dst);
+	unsigned int hh_len = LL_RESERVED_SPACE(dev);
+	const struct in6_addr *daddr, *nexthop;
+	struct ipv6hdr *hdr;
 	struct neighbour *neigh;
 	int ret;
 
-	if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) {
-		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
+	/* Be paranoid, rather than too clever. */
+	if (unlikely(hh_len > skb_headroom(skb)) && dev->header_ops) {
+		skb = skb_expand_head(skb, hh_len);
+		if (!skb) {
+			IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
+			return -ENOMEM;
+		}
+	}
 
+	hdr = ipv6_hdr(skb);
+	daddr = &hdr->daddr;
+	if (ipv6_addr_is_multicast(daddr)) {
 		if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(sk) &&
 		    ((mroute6_is_socket(net, skb) &&
 		     !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) ||
-		     ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr,
-					 &ipv6_hdr(skb)->saddr))) {
+		     ipv6_chk_mcast_addr(dev, daddr, &hdr->saddr))) {
 			struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
 
 			/* Do not check for IFF_ALLMULTI; multicast routing
@@ -81,7 +93,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
 					net, sk, newskb, NULL, newskb->dev,
 					dev_loopback_xmit);
 
-			if (ipv6_hdr(skb)->hop_limit == 0) {
+			if (hdr->hop_limit == 0) {
 				IP6_INC_STATS(net, idev,
 					      IPSTATS_MIB_OUTDISCARDS);
 				kfree_skb(skb);
@@ -90,9 +102,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
 		}
 
 		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, skb->len);
-
-		if (IPV6_ADDR_MC_SCOPE(&ipv6_hdr(skb)->daddr) <=
-		    IPV6_ADDR_SCOPE_NODELOCAL &&
+		if (IPV6_ADDR_MC_SCOPE(daddr) <= IPV6_ADDR_SCOPE_NODELOCAL &&
 		    !(dev->flags & IFF_LOOPBACK)) {
 			kfree_skb(skb);
 			return 0;
@@ -107,34 +117,77 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
 	}
 
 	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)) {
-		sock_confirm_neigh(skb, neigh);
-		ret = neigh_output(neigh, skb, false);
-		rcu_read_unlock_bh();
-		return ret;
+	nexthop = rt6_nexthop((struct rt6_info *)dst, daddr);
+	neigh = __ipv6_neigh_lookup_noref(dev, nexthop);
+
+	if (unlikely(IS_ERR_OR_NULL(neigh))) {
+		if (unlikely(!neigh))
+			neigh = __neigh_create(&nd_tbl, nexthop, dev, false);
+		if (IS_ERR(neigh)) {
+			rcu_read_unlock_bh();
+			IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTNOROUTES);
+			kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL);
+			return -EINVAL;
+		}
 	}
+	sock_confirm_neigh(skb, neigh);
+	ret = neigh_output(neigh, skb, false);
 	rcu_read_unlock_bh();
+	return ret;
+}
 
-	IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
-	kfree_skb(skb);
-	return -EINVAL;
+static int
+ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk,
+				    struct sk_buff *skb, unsigned int mtu)
+{
+	struct sk_buff *segs, *nskb;
+	netdev_features_t features;
+	int ret = 0;
+
+	/* Please see corresponding comment in ip_finish_output_gso
+	 * describing the cases where GSO segment length exceeds the
+	 * egress MTU.
+	 */
+	features = netif_skb_features(skb);
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+	if (IS_ERR_OR_NULL(segs)) {
+		kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	consume_skb(skb);
+
+	skb_list_walk_safe(segs, segs, nskb) {
+		int err;
+
+		skb_mark_not_on_list(segs);
+		err = ip6_fragment(net, sk, segs, ip6_finish_output2);
+		if (err && ret == 0)
+			ret = err;
+	}
+
+	return ret;
 }
 
 static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	unsigned int mtu;
+
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
 	/* Policy lookup after SNAT yielded a new policy */
 	if (skb_dst(skb)->xfrm) {
-		IPCB(skb)->flags |= IPSKB_REROUTED;
+		IP6CB(skb)->flags |= IP6SKB_REROUTED;
 		return dst_output(net, sk, skb);
 	}
 #endif
 
-	if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
+	mtu = ip6_skb_dst_mtu(skb);
+	if (skb_is_gso(skb) &&
+	    !(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) &&
+	    !skb_gso_validate_network_len(skb, mtu))
+		return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu);
+
+	if ((skb->len > mtu && !skb_is_gso(skb)) ||
 	    dst_allfrag(skb_dst(skb)) ||
 	    (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
 		return ip6_fragment(net, sk, skb, ip6_finish_output2);
@@ -149,11 +202,10 @@ static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 	ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
 	switch (ret) {
 	case NET_XMIT_SUCCESS:
-		return __ip6_finish_output(net, sk, skb);
 	case NET_XMIT_CN:
 		return __ip6_finish_output(net, sk, skb) ? : ret;
 	default:
-		kfree_skb(skb);
+		kfree_skb_reason(skb, SKB_DROP_REASON_BPF_CGROUP_EGRESS);
 		return ret;
 	}
 }
@@ -168,7 +220,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 
 	if (unlikely(idev->cnf.disable_ipv6)) {
 		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
-		kfree_skb(skb);
+		kfree_skb_reason(skb, SKB_DROP_REASON_IPV6DISABLED);
 		return 0;
 	}
 
@@ -177,6 +229,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 			    ip6_finish_output,
 			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
 }
+EXPORT_SYMBOL(ip6_output);
 
 bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
 {
@@ -199,6 +252,10 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	const struct ipv6_pinfo *np = inet6_sk(sk);
 	struct in6_addr *first_hop = &fl6->daddr;
 	struct dst_entry *dst = skb_dst(skb);
+	struct net_device *dev = dst->dev;
+	struct inet6_dev *idev = ip6_dst_idev(dst);
+	struct hop_jumbo_hdr *hop_jumbo;
+	int hoplen = sizeof(*hop_jumbo);
 	unsigned int head_room;
 	struct ipv6hdr *hdr;
 	u8  proto = fl6->flowi6_proto;
@@ -206,22 +263,16 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	int hlimit = -1;
 	u32 mtu;
 
-	head_room = sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev);
+	head_room = sizeof(struct ipv6hdr) + hoplen + LL_RESERVED_SPACE(dev);
 	if (opt)
 		head_room += opt->opt_nflen + opt->opt_flen;
 
-	if (unlikely(skb_headroom(skb) < head_room)) {
-		struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
-		if (!skb2) {
-			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
-				      IPSTATS_MIB_OUTDISCARDS);
-			kfree_skb(skb);
+	if (unlikely(head_room > skb_headroom(skb))) {
+		skb = skb_expand_head(skb, head_room);
+		if (!skb) {
+			IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
 			return -ENOBUFS;
 		}
-		if (skb->sk)
-			skb_set_owner_w(skb2, skb->sk);
-		consume_skb(skb);
-		skb = skb2;
 	}
 
 	if (opt) {
@@ -235,6 +286,20 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 					     &fl6->saddr);
 	}
 
+	if (unlikely(seg_len > IPV6_MAXPLEN)) {
+		hop_jumbo = skb_push(skb, hoplen);
+
+		hop_jumbo->nexthdr = proto;
+		hop_jumbo->hdrlen = 0;
+		hop_jumbo->tlv_type = IPV6_TLV_JUMBO;
+		hop_jumbo->tlv_len = 4;
+		hop_jumbo->jumbo_payload_len = htonl(seg_len + hoplen);
+
+		proto = IPPROTO_HOPOPTS;
+		seg_len = 0;
+		IP6CB(skb)->flags |= IP6SKB_FAKEJUMBO;
+	}
+
 	skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	hdr = ipv6_hdr(skb);
@@ -263,8 +328,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 
 	mtu = dst_mtu(dst);
 	if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) {
-		IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)),
-			      IPSTATS_MIB_OUT, skb->len);
+		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len);
 
 		/* if egress device is enslaved to an L3 master device pass the
 		 * skb to its handler for processing
@@ -277,17 +341,17 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 		 * we promote our socket to non const
 		 */
 		return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
-			       net, (struct sock *)sk, skb, NULL, dst->dev,
+			       net, (struct sock *)sk, skb, NULL, dev,
 			       dst_output);
 	}
 
-	skb->dev = dst->dev;
+	skb->dev = dev;
 	/* ipv6_local_error() does not require socket lock,
 	 * we promote our socket to non const
 	 */
 	ipv6_local_error((struct sock *)sk, EMSGSIZE, fl6, mtu);
 
-	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS);
+	IP6_INC_STATS(net, idev, IPSTATS_MIB_FRAGFAILS);
 	kfree_skb(skb);
 	return -EMSGSIZE;
 }
@@ -395,7 +459,7 @@ static inline int ip6_forward_finish(struct net *net, struct sock *sk,
 	}
 #endif
 
-	skb->tstamp = 0;
+	skb_clear_tstamp(skb);
 	return dst_output(net, sk, skb);
 }
 
@@ -419,13 +483,15 @@ static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
 
 int ip6_forward(struct sk_buff *skb)
 {
-	struct inet6_dev *idev = __in6_dev_get_safely(skb->dev);
 	struct dst_entry *dst = skb_dst(skb);
 	struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct inet6_skb_parm *opt = IP6CB(skb);
 	struct net *net = dev_net(dst->dev);
+	struct inet6_dev *idev;
+	SKB_DR(reason);
 	u32 mtu;
 
+	idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif));
 	if (net->ipv6.devconf_all->forwarding == 0)
 		goto error;
 
@@ -438,7 +504,9 @@ int ip6_forward(struct sk_buff *skb)
 	if (skb_warn_if_lro(skb))
 		goto drop;
 
-	if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
+	if (!net->ipv6.devconf_all->disable_policy &&
+	    (!idev || !idev->cnf.disable_policy) &&
+	    !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
 		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
 		goto drop;
 	}
@@ -467,12 +535,10 @@ int ip6_forward(struct sk_buff *skb)
 	 *	check and decrement ttl
 	 */
 	if (hdr->hop_limit <= 1) {
-		/* Force OUTPUT device used as source address */
-		skb->dev = dst->dev;
 		icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0);
 		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
 
-		kfree_skb(skb);
+		kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR);
 		return -ETIMEDOUT;
 	}
 
@@ -480,9 +546,10 @@ int ip6_forward(struct sk_buff *skb)
 	if (net->ipv6.devconf_all->proxy_ndp &&
 	    pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) {
 		int proxied = ip6_forward_proxy_check(skb);
-		if (proxied > 0)
+		if (proxied > 0) {
+			hdr->hop_limit--;
 			return ip6_input(skb);
-		else if (proxied < 0) {
+		} else if (proxied < 0) {
 			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
 			goto drop;
 		}
@@ -490,6 +557,7 @@ int ip6_forward(struct sk_buff *skb)
 
 	if (!xfrm6_route_forward(skb)) {
 		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
+		SKB_DR_SET(reason, XFRM_POLICY);
 		goto drop;
 	}
 	dst = skb_dst(skb);
@@ -538,7 +606,7 @@ int ip6_forward(struct sk_buff *skb)
 		}
 	}
 
-	mtu = ip6_dst_mtu_forward(dst);
+	mtu = ip6_dst_mtu_maybe_forward(dst, true);
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
 
@@ -549,7 +617,7 @@ int ip6_forward(struct sk_buff *skb)
 		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INTOOBIGERRORS);
 		__IP6_INC_STATS(net, ip6_dst_idev(dst),
 				IPSTATS_MIB_FRAGFAILS);
-		kfree_skb(skb);
+		kfree_skb_reason(skb, SKB_DROP_REASON_PKT_TOO_BIG);
 		return -EMSGSIZE;
 	}
 
@@ -571,8 +639,9 @@ int ip6_forward(struct sk_buff *skb)
 
 error:
 	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS);
+	SKB_DR_SET(reason, IP_INADDRERRORS);
 drop:
-	kfree_skb(skb);
+	kfree_skb_reason(skb, reason);
 	return -EINVAL;
 }
 
@@ -766,6 +835,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
 	struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ?
 				inet6_sk(skb->sk) : NULL;
+	bool mono_delivery_time = skb->mono_delivery_time;
 	struct ip6_frag_state state;
 	unsigned int mtu, hlen, nexthdr_offset;
 	ktime_t tstamp = skb->tstamp;
@@ -856,7 +926,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 			if (iter.frag)
 				ip6_fraglist_prepare(skb, &iter);
 
-			skb->tstamp = tstamp;
+			skb_set_delivery_time(skb, tstamp, mono_delivery_time);
 			err = output(net, sk, skb);
 			if (!err)
 				IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
@@ -915,7 +985,7 @@ slow_path:
 		/*
 		 *	Put this fragment into the sending queue.
 		 */
-		frag->tstamp = tstamp;
+		skb_set_delivery_time(frag, tstamp, mono_delivery_time);
 		err = output(net, sk, frag);
 		if (err)
 			goto fail;
@@ -930,7 +1000,7 @@ slow_path:
 
 fail_toobig:
 	if (skb->sk && dst_allfrag(skb_dst(skb)))
-		sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK);
+		sk_gso_disable(skb->sk);
 
 	icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 	err = -EMSGSIZE;
@@ -987,8 +1057,7 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk,
 #ifdef CONFIG_IPV6_SUBTREES
 	    ip6_rt_check(&rt->rt6i_src, &fl6->saddr, np->saddr_cache) ||
 #endif
-	   (!(fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF) &&
-	      (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex))) {
+	   (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex)) {
 		dst_release(dst);
 		dst = NULL;
 	}
@@ -1016,13 +1085,11 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
 	 * ip6_route_output will fail given src=any saddr, though, so
 	 * that's why we try it again later.
 	 */
-	if (ipv6_addr_any(&fl6->saddr) && (!*dst || !(*dst)->error)) {
+	if (ipv6_addr_any(&fl6->saddr)) {
 		struct fib6_info *from;
 		struct rt6_info *rt;
-		bool had_dst = *dst != NULL;
 
-		if (!had_dst)
-			*dst = ip6_route_output(net, sk, fl6);
+		*dst = ip6_route_output(net, sk, fl6);
 		rt = (*dst)->error ? NULL : (struct rt6_info *)*dst;
 
 		rcu_read_lock();
@@ -1039,7 +1106,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
 		 * never existed and let the SA-enabled version take
 		 * over.
 		 */
-		if (!had_dst && (*dst)->error) {
+		if ((*dst)->error) {
 			dst_release(*dst);
 			*dst = NULL;
 		}
@@ -1117,6 +1184,7 @@ out_err_release:
 
 /**
  *	ip6_dst_lookup - perform route lookup on flow
+ *	@net: Network namespace to perform lookup in
  *	@sk: socket which provides route info
  *	@dst: pointer to dst_entry * for result
  *	@fl6: flow to lookup
@@ -1135,6 +1203,7 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup);
 
 /**
  *	ip6_dst_lookup_flow - perform route lookup on flow with ipsec
+ *	@net: Network namespace to perform lookup in
  *	@sk: socket which provides route info
  *	@fl6: flow to lookup
  *	@final_dst: final destination address for ipsec lookup
@@ -1196,6 +1265,74 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 }
 EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
 
+/**
+ *      ip6_dst_lookup_tunnel - perform route lookup on tunnel
+ *      @skb: Packet for which lookup is done
+ *      @dev: Tunnel device
+ *      @net: Network namespace of tunnel device
+ *      @sock: Socket which provides route info
+ *      @saddr: Memory to store the src ip address
+ *      @info: Tunnel information
+ *      @protocol: IP protocol
+ *      @use_cache: Flag to enable cache usage
+ *      This function performs a route lookup on a tunnel
+ *
+ *      It returns a valid dst pointer and stores src address to be used in
+ *      tunnel in param saddr on success, else a pointer encoded error code.
+ */
+
+struct dst_entry *ip6_dst_lookup_tunnel(struct sk_buff *skb,
+					struct net_device *dev,
+					struct net *net,
+					struct socket *sock,
+					struct in6_addr *saddr,
+					const struct ip_tunnel_info *info,
+					u8 protocol,
+					bool use_cache)
+{
+	struct dst_entry *dst = NULL;
+#ifdef CONFIG_DST_CACHE
+	struct dst_cache *dst_cache;
+#endif
+	struct flowi6 fl6;
+	__u8 prio;
+
+#ifdef CONFIG_DST_CACHE
+	dst_cache = (struct dst_cache *)&info->dst_cache;
+	if (use_cache) {
+		dst = dst_cache_get_ip6(dst_cache, saddr);
+		if (dst)
+			return dst;
+	}
+#endif
+	memset(&fl6, 0, sizeof(fl6));
+	fl6.flowi6_mark = skb->mark;
+	fl6.flowi6_proto = protocol;
+	fl6.daddr = info->key.u.ipv6.dst;
+	fl6.saddr = info->key.u.ipv6.src;
+	prio = info->key.tos;
+	fl6.flowlabel = ip6_make_flowinfo(prio, info->key.label);
+
+	dst = ipv6_stub->ipv6_dst_lookup_flow(net, sock->sk, &fl6,
+					      NULL);
+	if (IS_ERR(dst)) {
+		netdev_dbg(dev, "no route to %pI6\n", &fl6.daddr);
+		return ERR_PTR(-ENETUNREACH);
+	}
+	if (dst->dev == dev) { /* is this necessary? */
+		netdev_dbg(dev, "circular route to %pI6\n", &fl6.daddr);
+		dst_release(dst);
+		return ERR_PTR(-ELOOP);
+	}
+#ifdef CONFIG_DST_CACHE
+	if (use_cache)
+		dst_cache_set_ip6(dst_cache, dst, &fl6.saddr);
+#endif
+	*saddr = fl6.saddr;
+	return dst;
+}
+EXPORT_SYMBOL_GPL(ip6_dst_lookup_tunnel);
+
 static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src,
 					       gfp_t gfp)
 {
@@ -1234,11 +1371,16 @@ static void ip6_append_data_mtu(unsigned int *mtu,
 
 static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 			  struct inet6_cork *v6_cork, struct ipcm6_cookie *ipc6,
-			  struct rt6_info *rt, struct flowi6 *fl6)
+			  struct rt6_info *rt)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	unsigned int mtu;
-	struct ipv6_txoptions *opt = ipc6->opt;
+	struct ipv6_txoptions *nopt, *opt = ipc6->opt;
+
+	/* callers pass dst together with a reference, set it first so
+	 * ip6_cork_release() can put it down even in case of an error.
+	 */
+	cork->base.dst = &rt->dst;
 
 	/*
 	 * setup for corking
@@ -1247,39 +1389,32 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 		if (WARN_ON(v6_cork->opt))
 			return -EINVAL;
 
-		v6_cork->opt = kzalloc(sizeof(*opt), sk->sk_allocation);
-		if (unlikely(!v6_cork->opt))
+		nopt = v6_cork->opt = kzalloc(sizeof(*opt), sk->sk_allocation);
+		if (unlikely(!nopt))
 			return -ENOBUFS;
 
-		v6_cork->opt->tot_len = sizeof(*opt);
-		v6_cork->opt->opt_flen = opt->opt_flen;
-		v6_cork->opt->opt_nflen = opt->opt_nflen;
+		nopt->tot_len = sizeof(*opt);
+		nopt->opt_flen = opt->opt_flen;
+		nopt->opt_nflen = opt->opt_nflen;
 
-		v6_cork->opt->dst0opt = ip6_opt_dup(opt->dst0opt,
-						    sk->sk_allocation);
-		if (opt->dst0opt && !v6_cork->opt->dst0opt)
+		nopt->dst0opt = ip6_opt_dup(opt->dst0opt, sk->sk_allocation);
+		if (opt->dst0opt && !nopt->dst0opt)
 			return -ENOBUFS;
 
-		v6_cork->opt->dst1opt = ip6_opt_dup(opt->dst1opt,
-						    sk->sk_allocation);
-		if (opt->dst1opt && !v6_cork->opt->dst1opt)
+		nopt->dst1opt = ip6_opt_dup(opt->dst1opt, sk->sk_allocation);
+		if (opt->dst1opt && !nopt->dst1opt)
 			return -ENOBUFS;
 
-		v6_cork->opt->hopopt = ip6_opt_dup(opt->hopopt,
-						   sk->sk_allocation);
-		if (opt->hopopt && !v6_cork->opt->hopopt)
+		nopt->hopopt = ip6_opt_dup(opt->hopopt, sk->sk_allocation);
+		if (opt->hopopt && !nopt->hopopt)
 			return -ENOBUFS;
 
-		v6_cork->opt->srcrt = ip6_rthdr_dup(opt->srcrt,
-						    sk->sk_allocation);
-		if (opt->srcrt && !v6_cork->opt->srcrt)
+		nopt->srcrt = ip6_rthdr_dup(opt->srcrt, sk->sk_allocation);
+		if (opt->srcrt && !nopt->srcrt)
 			return -ENOBUFS;
 
 		/* need source address above miyazawa*/
 	}
-	dst_hold(&rt->dst);
-	cork->base.dst = &rt->dst;
-	cork->fl.u.ip6 = *fl6;
 	v6_cork->hop_limit = ipc6->hlimit;
 	v6_cork->tclass = ipc6->tclass;
 	if (rt->dst.flags & DST_XFRM_TUNNEL)
@@ -1292,8 +1427,6 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 		if (np->frag_size)
 			mtu = np->frag_size;
 	}
-	if (mtu < IPV6_MIN_MTU)
-		return -EINVAL;
 	cork->base.fragsize = mtu;
 	cork->base.gso_size = ipc6->gso_size;
 	cork->base.tx_flags = 0;
@@ -1310,17 +1443,18 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 }
 
 static int __ip6_append_data(struct sock *sk,
-			     struct flowi6 *fl6,
 			     struct sk_buff_head *queue,
-			     struct inet_cork *cork,
+			     struct inet_cork_full *cork_full,
 			     struct inet6_cork *v6_cork,
 			     struct page_frag *pfrag,
 			     int getfrag(void *from, char *to, int offset,
 					 int len, int odd, struct sk_buff *skb),
-			     void *from, int length, int transhdrlen,
+			     void *from, size_t length, int transhdrlen,
 			     unsigned int flags, struct ipcm6_cookie *ipc6)
 {
 	struct sk_buff *skb, *skb_prev = NULL;
+	struct inet_cork *cork = &cork_full->base;
+	struct flowi6 *fl6 = &cork_full->fl.u.ip6;
 	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu;
 	struct ubuf_info *uarg = NULL;
 	int exthdrlen = 0;
@@ -1329,6 +1463,7 @@ static int __ip6_append_data(struct sock *sk,
 	int copy;
 	int err;
 	int offset = 0;
+	bool zc = false;
 	u32 tskey = 0;
 	struct rt6_info *rt = (struct rt6_info *)cork->dst;
 	struct ipv6_txoptions *opt = v6_cork->opt;
@@ -1349,14 +1484,12 @@ static int __ip6_append_data(struct sock *sk,
 
 	if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP &&
 	    sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
-		tskey = sk->sk_tskey++;
+		tskey = atomic_inc_return(&sk->sk_tskey) - 1;
 
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
 
 	fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
 			(opt ? opt->opt_nflen : 0);
-	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen -
-		     sizeof(struct frag_hdr);
 
 	headersize = sizeof(struct ipv6hdr) +
 		     (opt ? opt->opt_flen + opt->opt_nflen : 0) +
@@ -1364,6 +1497,13 @@ static int __ip6_append_data(struct sock *sk,
 		      sizeof(struct frag_hdr) : 0) +
 		     rt->rt6i_nfheader_len;
 
+	if (mtu <= fragheaderlen ||
+	    ((mtu - fragheaderlen) & ~7) + fragheaderlen <= sizeof(struct frag_hdr))
+		goto emsgsize;
+
+	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen -
+		     sizeof(struct frag_hdr);
+
 	/* as per RFC 7112 section 5, the entire IPv6 Header Chain must fit
 	 * the first fragment
 	 */
@@ -1372,6 +1512,7 @@ static int __ip6_append_data(struct sock *sk,
 
 	if (cork->length + length > mtu - headersize && ipc6->dontfrag &&
 	    (sk->sk_protocol == IPPROTO_UDP ||
+	     sk->sk_protocol == IPPROTO_ICMPV6 ||
 	     sk->sk_protocol == IPPROTO_RAW)) {
 		ipv6_local_rxpmtu(sk, fl6, mtu - headersize +
 				sizeof(struct ipv6hdr));
@@ -1400,17 +1541,35 @@ emsgsize:
 	    rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))
 		csummode = CHECKSUM_PARTIAL;
 
-	if (flags & MSG_ZEROCOPY && length && sock_flag(sk, SOCK_ZEROCOPY)) {
-		uarg = sock_zerocopy_realloc(sk, length, skb_zcopy(skb));
-		if (!uarg)
-			return -ENOBUFS;
-		extra_uref = !skb_zcopy(skb);	/* only ref on new uarg */
-		if (rt->dst.dev->features & NETIF_F_SG &&
-		    csummode == CHECKSUM_PARTIAL) {
-			paged = true;
-		} else {
-			uarg->zerocopy = 0;
-			skb_zcopy_set(skb, uarg, &extra_uref);
+	if ((flags & MSG_ZEROCOPY) && length) {
+		struct msghdr *msg = from;
+
+		if (getfrag == ip_generic_getfrag && msg->msg_ubuf) {
+			if (skb_zcopy(skb) && msg->msg_ubuf != skb_zcopy(skb))
+				return -EINVAL;
+
+			/* Leave uarg NULL if can't zerocopy, callers should
+			 * be able to handle it.
+			 */
+			if ((rt->dst.dev->features & NETIF_F_SG) &&
+			    csummode == CHECKSUM_PARTIAL) {
+				paged = true;
+				zc = true;
+				uarg = msg->msg_ubuf;
+			}
+		} else if (sock_flag(sk, SOCK_ZEROCOPY)) {
+			uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb));
+			if (!uarg)
+				return -ENOBUFS;
+			extra_uref = !skb_zcopy(skb);	/* only ref on new uarg */
+			if (rt->dst.dev->features & NETIF_F_SG &&
+			    csummode == CHECKSUM_PARTIAL) {
+				paged = true;
+				zc = true;
+			} else {
+				uarg_to_msgzc(uarg)->zerocopy = 0;
+				skb_zcopy_set(skb, uarg, &extra_uref);
+			}
 		}
 	}
 
@@ -1420,7 +1579,7 @@ emsgsize:
 	 * Otherwise, we need to reserve fragment header and
 	 * fragment alignment (= 8-15 octects, in total).
 	 *
-	 * Note that we may need to "move" the data from the tail of
+	 * Note that we may need to "move" the data from the tail
 	 * of the buffer to the new fragment when we split
 	 * the message.
 	 *
@@ -1445,7 +1604,7 @@ emsgsize:
 			unsigned int datalen;
 			unsigned int fraglen;
 			unsigned int fraggap;
-			unsigned int alloclen;
+			unsigned int alloclen, alloc_extra;
 			unsigned int pagedlen;
 alloc_new_skb:
 			/* There's no room in the current skb */
@@ -1472,17 +1631,28 @@ alloc_new_skb:
 			fraglen = datalen + fragheaderlen;
 			pagedlen = 0;
 
+			alloc_extra = hh_len;
+			alloc_extra += dst_exthdrlen;
+			alloc_extra += rt->dst.trailer_len;
+
+			/* We just reserve space for fragment header.
+			 * Note: this may be overallocation if the message
+			 * (without MSG_MORE) fits into the MTU.
+			 */
+			alloc_extra += sizeof(struct frag_hdr);
+
 			if ((flags & MSG_MORE) &&
 			    !(rt->dst.dev->features&NETIF_F_SG))
 				alloclen = mtu;
-			else if (!paged)
+			else if (!paged &&
+				 (fraglen + alloc_extra < SKB_MAX_ALLOC ||
+				  !(rt->dst.dev->features & NETIF_F_SG)))
 				alloclen = fraglen;
 			else {
-				alloclen = min_t(int, fraglen, MAX_HEADER);
-				pagedlen = fraglen - alloclen;
+				alloclen = fragheaderlen + transhdrlen;
+				pagedlen = datalen - transhdrlen;
 			}
-
-			alloclen += dst_exthdrlen;
+			alloclen += alloc_extra;
 
 			if (datalen != length + fraggap) {
 				/*
@@ -1492,30 +1662,21 @@ alloc_new_skb:
 				datalen += rt->dst.trailer_len;
 			}
 
-			alloclen += rt->dst.trailer_len;
 			fraglen = datalen + fragheaderlen;
 
-			/*
-			 * We just reserve space for fragment header.
-			 * Note: this may be overallocation if the message
-			 * (without MSG_MORE) fits into the MTU.
-			 */
-			alloclen += sizeof(struct frag_hdr);
-
 			copy = datalen - transhdrlen - fraggap - pagedlen;
 			if (copy < 0) {
 				err = -EINVAL;
 				goto error;
 			}
 			if (transhdrlen) {
-				skb = sock_alloc_send_skb(sk,
-						alloclen + hh_len,
+				skb = sock_alloc_send_skb(sk, alloclen,
 						(flags & MSG_DONTWAIT), &err);
 			} else {
 				skb = NULL;
 				if (refcount_read(&sk->sk_wmem_alloc) + wmem_alloc_delta <=
 				    2 * sk->sk_sndbuf)
-					skb = alloc_skb(alloclen + hh_len,
+					skb = alloc_skb(alloclen,
 							sk->sk_allocation);
 				if (unlikely(!skb))
 					err = -ENOBUFS;
@@ -1543,7 +1704,7 @@ alloc_new_skb:
 			if (fraggap) {
 				skb->csum = skb_copy_and_csum_bits(
 					skb_prev, maxfraglen,
-					data + transhdrlen, fraggap, 0);
+					data + transhdrlen, fraggap);
 				skb_prev->csum = csum_sub(skb_prev->csum,
 							  skb->csum);
 				data += fraggap;
@@ -1599,13 +1760,14 @@ alloc_new_skb:
 				err = -EFAULT;
 				goto error;
 			}
-		} else if (!uarg || !uarg->zerocopy) {
+		} else if (!zc) {
 			int i = skb_shinfo(skb)->nr_frags;
 
 			err = -ENOMEM;
 			if (!sk_page_frag_refill(sk, pfrag))
 				goto error;
 
+			skb_zcopy_downgrade_managed(skb);
 			if (!skb_can_coalesce(skb, i, pfrag->page,
 					      pfrag->offset)) {
 				err = -EMSGSIZE;
@@ -1645,8 +1807,7 @@ alloc_new_skb:
 error_efault:
 	err = -EFAULT;
 error:
-	if (uarg)
-		sock_zerocopy_put_abort(uarg, extra_uref);
+	net_zcopy_put_abort(uarg, extra_uref);
 	cork->length -= length;
 	IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
 	refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
@@ -1656,7 +1817,7 @@ error:
 int ip6_append_data(struct sock *sk,
 		    int getfrag(void *from, char *to, int offset, int len,
 				int odd, struct sk_buff *skb),
-		    void *from, int length, int transhdrlen,
+		    void *from, size_t length, int transhdrlen,
 		    struct ipcm6_cookie *ipc6, struct flowi6 *fl6,
 		    struct rt6_info *rt, unsigned int flags)
 {
@@ -1671,34 +1832,46 @@ int ip6_append_data(struct sock *sk,
 		/*
 		 * setup for corking
 		 */
+		dst_hold(&rt->dst);
 		err = ip6_setup_cork(sk, &inet->cork, &np->cork,
-				     ipc6, rt, fl6);
+				     ipc6, rt);
 		if (err)
 			return err;
 
+		inet->cork.fl.u.ip6 = *fl6;
 		exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0);
 		length += exthdrlen;
 		transhdrlen += exthdrlen;
 	} else {
-		fl6 = &inet->cork.fl.u.ip6;
 		transhdrlen = 0;
 	}
 
-	return __ip6_append_data(sk, fl6, &sk->sk_write_queue, &inet->cork.base,
+	return __ip6_append_data(sk, &sk->sk_write_queue, &inet->cork,
 				 &np->cork, sk_page_frag(sk), getfrag,
 				 from, length, transhdrlen, flags, ipc6);
 }
 EXPORT_SYMBOL_GPL(ip6_append_data);
 
+static void ip6_cork_steal_dst(struct sk_buff *skb, struct inet_cork_full *cork)
+{
+	struct dst_entry *dst = cork->base.dst;
+
+	cork->base.dst = NULL;
+	cork->base.flags &= ~IPCORK_ALLFRAG;
+	skb_dst_set(skb, dst);
+}
+
 static void ip6_cork_release(struct inet_cork_full *cork,
 			     struct inet6_cork *v6_cork)
 {
 	if (v6_cork->opt) {
-		kfree(v6_cork->opt->dst0opt);
-		kfree(v6_cork->opt->dst1opt);
-		kfree(v6_cork->opt->hopopt);
-		kfree(v6_cork->opt->srcrt);
-		kfree(v6_cork->opt);
+		struct ipv6_txoptions *opt = v6_cork->opt;
+
+		kfree(opt->dst0opt);
+		kfree(opt->dst1opt);
+		kfree(opt->hopopt);
+		kfree(opt->srcrt);
+		kfree(opt);
 		v6_cork->opt = NULL;
 	}
 
@@ -1707,7 +1880,6 @@ static void ip6_cork_release(struct inet_cork_full *cork,
 		cork->base.dst = NULL;
 		cork->base.flags &= ~IPCORK_ALLFRAG;
 	}
-	memset(&cork->fl, 0, sizeof(cork->fl));
 }
 
 struct sk_buff *__ip6_make_skb(struct sock *sk,
@@ -1717,7 +1889,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 {
 	struct sk_buff *skb, *tmp_skb;
 	struct sk_buff **tail_skb;
-	struct in6_addr final_dst_buf, *final_dst = &final_dst_buf;
+	struct in6_addr *final_dst;
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct net *net = sock_net(sk);
 	struct ipv6hdr *hdr;
@@ -1747,9 +1919,9 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 
 	/* Allow local fragmentation. */
 	skb->ignore_df = ip6_sk_ignore_df(sk);
-
-	*final_dst = fl6->daddr;
 	__skb_pull(skb, skb_network_header_len(skb));
+
+	final_dst = &fl6->daddr;
 	if (opt && opt->opt_flen)
 		ipv6_push_frag_opts(skb, opt, &proto);
 	if (opt && opt->opt_nflen)
@@ -1769,10 +1941,9 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 
 	skb->priority = sk->sk_priority;
 	skb->mark = cork->base.mark;
-
 	skb->tstamp = cork->base.transmit_time;
 
-	skb_dst_set(skb, dst_clone(&rt->dst));
+	ip6_cork_steal_dst(skb, cork);
 	IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
 	if (proto == IPPROTO_ICMPV6) {
 		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
@@ -1843,27 +2014,27 @@ EXPORT_SYMBOL_GPL(ip6_flush_pending_frames);
 struct sk_buff *ip6_make_skb(struct sock *sk,
 			     int getfrag(void *from, char *to, int offset,
 					 int len, int odd, struct sk_buff *skb),
-			     void *from, int length, int transhdrlen,
-			     struct ipcm6_cookie *ipc6, struct flowi6 *fl6,
-			     struct rt6_info *rt, unsigned int flags,
-			     struct inet_cork_full *cork)
+			     void *from, size_t length, int transhdrlen,
+			     struct ipcm6_cookie *ipc6, struct rt6_info *rt,
+			     unsigned int flags, struct inet_cork_full *cork)
 {
 	struct inet6_cork v6_cork;
 	struct sk_buff_head queue;
 	int exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0);
 	int err;
 
-	if (flags & MSG_PROBE)
+	if (flags & MSG_PROBE) {
+		dst_release(&rt->dst);
 		return NULL;
+	}
 
 	__skb_queue_head_init(&queue);
 
 	cork->base.flags = 0;
 	cork->base.addr = 0;
 	cork->base.opt = NULL;
-	cork->base.dst = NULL;
 	v6_cork.opt = NULL;
-	err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt, fl6);
+	err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt);
 	if (err) {
 		ip6_cork_release(cork, &v6_cork);
 		return ERR_PTR(err);
@@ -1871,7 +2042,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
 	if (ipc6->dontfrag < 0)
 		ipc6->dontfrag = inet6_sk(sk)->dontfrag;
 
-	err = __ip6_append_data(sk, fl6, &queue, &cork->base, &v6_cork,
+	err = __ip6_append_data(sk, &queue, cork, &v6_cork,
 				&current->task_frag, getfrag, from,
 				length + exthdrlen, transhdrlen + exthdrlen,
 				flags, ipc6);