1 files changed, 449 insertions, 321 deletions

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 8a8c2d0cfcc8..f904739e99b9 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -42,6 +42,7 @@
 #include <net/sock.h>
 #include <net/snmp.h>
 
+#include <net/gso.h>
 #include <net/ipv6.h>
 #include <net/ndisc.h>
 #include <net/protocol.h>
@@ -59,19 +60,31 @@
 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 net_device *dev = dst_dev_rcu(dst);
+	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) {
+		/* idev stays alive because we hold rcu_read_lock(). */
+		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
@@ -82,7 +95,7 @@ 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);
@@ -91,9 +104,7 @@ 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;
@@ -103,44 +114,99 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
 	if (lwtunnel_xmit_redirect(dst->lwtstate)) {
 		int res = lwtunnel_xmit(skb);
 
-		if (res < 0 || res == LWTUNNEL_XMIT_DONE)
+		if (res != LWTUNNEL_XMIT_CONTINUE)
 			return res;
 	}
 
-	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;
+	IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len);
+
+	nexthop = rt6_nexthop(dst_rt6_info(dst), daddr);
+	neigh = __ipv6_neigh_lookup_noref(dev, nexthop);
+
+	if (IS_ERR_OR_NULL(neigh)) {
+		if (unlikely(!neigh))
+			neigh = __neigh_create(&nd_tbl, nexthop, dev, false);
+		if (IS_ERR(neigh)) {
+			IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTNOROUTES);
+			kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL);
+			return -EINVAL;
+		}
 	}
-	rcu_read_unlock_bh();
+	sock_confirm_neigh(skb, neigh);
+	ret = neigh_output(neigh, skb, false);
+	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);
+		/* Last GSO segment can be smaller than gso_size (and MTU).
+		 * Adding a fragment header would produce an "atomic fragment",
+		 * which is considered harmful (RFC-8021). Avoid that.
+		 */
+		err = segs->len > mtu ?
+			ip6_fragment(net, sk, segs, ip6_finish_output2) :
+			ip6_finish_output2(net, sk, segs);
+		if (err && ret == 0)
+			ret = err;
+	}
+
+	return ret;
+}
+
+static int ip6_finish_output_gso(struct net *net, struct sock *sk,
+				 struct sk_buff *skb, unsigned int mtu)
+{
+	if (!(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) &&
+	    !skb_gso_validate_network_len(skb, mtu))
+		return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu);
+
+	return ip6_finish_output2(net, sk, skb);
 }
 
 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)) ||
-	    dst_allfrag(skb_dst(skb)) ||
+	mtu = ip6_skb_dst_mtu(skb);
+	if (skb_is_gso(skb))
+		return ip6_finish_output_gso(net, sk, skb, mtu);
+
+	if (skb->len > mtu ||
 	    (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
 		return ip6_fragment(net, sk, skb, ip6_finish_output2);
-	else
-		return ip6_finish_output2(net, sk, skb);
+
+	return ip6_finish_output2(net, sk, skb);
 }
 
 static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
@@ -150,45 +216,52 @@ 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;
 	}
 }
 
 int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev;
-	struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
+	struct dst_entry *dst = skb_dst(skb);
+	struct net_device *dev, *indev = skb->dev;
+	struct inet6_dev *idev;
+	int ret;
 
 	skb->protocol = htons(ETH_P_IPV6);
+	rcu_read_lock();
+	dev = dst_dev_rcu(dst);
+	idev = ip6_dst_idev(dst);
 	skb->dev = dev;
 
-	if (unlikely(idev->cnf.disable_ipv6)) {
+	if (unlikely(!idev || READ_ONCE(idev->cnf.disable_ipv6))) {
 		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
-		kfree_skb(skb);
+		rcu_read_unlock();
+		kfree_skb_reason(skb, SKB_DROP_REASON_IPV6DISABLED);
 		return 0;
 	}
 
-	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING,
-			    net, sk, skb, indev, dev,
-			    ip6_finish_output,
-			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
+	ret = NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING,
+			   net, sk, skb, indev, dev,
+			   ip6_finish_output,
+			   !(IP6CB(skb)->flags & IP6SKB_REROUTED));
+	rcu_read_unlock();
+	return ret;
 }
+EXPORT_SYMBOL(ip6_output);
 
-bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
+bool ip6_autoflowlabel(struct net *net, const struct sock *sk)
 {
-	if (!np->autoflowlabel_set)
+	if (!inet6_test_bit(AUTOFLOWLABEL_SET, sk))
 		return ip6_default_np_autolabel(net);
-	else
-		return np->autoflowlabel;
+	return inet6_test_bit(AUTOFLOWLABEL, sk);
 }
 
 /*
- * xmit an sk_buff (used by TCP, SCTP and DCCP)
+ * xmit an sk_buff (used by TCP and SCTP)
  * Note : socket lock is not held for SYNACK packets, but might be modified
  * by calls to skb_set_owner_w() and ipv6_local_error(),
  * which are using proper atomic operations or spinlocks.
@@ -196,33 +269,36 @@ bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
 int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	     __u32 mark, struct ipv6_txoptions *opt, int tclass, u32 priority)
 {
-	struct net *net = sock_net(sk);
 	const struct ipv6_pinfo *np = inet6_sk(sk);
 	struct in6_addr *first_hop = &fl6->daddr;
 	struct dst_entry *dst = skb_dst(skb);
+	struct inet6_dev *idev = ip6_dst_idev(dst);
+	struct hop_jumbo_hdr *hop_jumbo;
+	int hoplen = sizeof(*hop_jumbo);
+	struct net *net = sock_net(sk);
 	unsigned int head_room;
+	struct net_device *dev;
 	struct ipv6hdr *hdr;
 	u8  proto = fl6->flowi6_proto;
 	int seg_len = skb->len;
-	int hlimit = -1;
+	int ret, hlimit = -1;
 	u32 mtu;
 
-	head_room = sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev);
+	rcu_read_lock();
+
+	dev = dst_dev_rcu(dst);
+	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);
-			return -ENOBUFS;
+	if (unlikely(head_room > skb_headroom(skb))) {
+		/* idev stays alive while we hold rcu_read_lock(). */
+		skb = skb_expand_head(skb, head_room);
+		if (!skb) {
+			IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
+			ret = -ENOBUFS;
+			goto unlock;
 		}
-		if (skb->sk)
-			skb_set_owner_w(skb2, skb->sk);
-		consume_skb(skb);
-		skb = skb2;
 	}
 
 	if (opt) {
@@ -236,6 +312,20 @@ 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);
@@ -244,12 +334,12 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	 *	Fill in the IPv6 header
 	 */
 	if (np)
-		hlimit = np->hop_limit;
+		hlimit = READ_ONCE(np->hop_limit);
 	if (hlimit < 0)
 		hlimit = ip6_dst_hoplimit(dst);
 
 	ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel,
-				ip6_autoflowlabel(net, np), fl6));
+				ip6_autoflowlabel(net, sk), fl6));
 
 	hdr->payload_len = htons(seg_len);
 	hdr->nexthdr = proto;
@@ -264,33 +354,38 @@ 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_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS);
 
 		/* if egress device is enslaved to an L3 master device pass the
 		 * skb to its handler for processing
 		 */
 		skb = l3mdev_ip6_out((struct sock *)sk, skb);
-		if (unlikely(!skb))
-			return 0;
+		if (unlikely(!skb)) {
+			ret = 0;
+			goto unlock;
+		}
 
 		/* hooks should never assume socket lock is held.
 		 * we promote our socket to non const
 		 */
-		return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
-			       net, (struct sock *)sk, skb, NULL, dst->dev,
-			       dst_output);
+		ret = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
+			      net, (struct sock *)sk, skb, NULL, dev,
+			      dst_output);
+		goto unlock;
 	}
 
-	skb->dev = dst->dev;
+	ret = -EMSGSIZE;
+	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;
+unlock:
+	rcu_read_unlock();
+	return ret;
 }
 EXPORT_SYMBOL(ip6_xmit);
 
@@ -305,9 +400,8 @@ static int ip6_call_ra_chain(struct sk_buff *skb, int sel)
 		if (sk && ra->sel == sel &&
 		    (!sk->sk_bound_dev_if ||
 		     sk->sk_bound_dev_if == skb->dev->ifindex)) {
-			struct ipv6_pinfo *np = inet6_sk(sk);
 
-			if (np && np->rtalert_isolate &&
+			if (inet6_test_bit(RTALERT_ISOLATE, sk) &&
 			    !net_eq(sock_net(sk), dev_net(skb->dev))) {
 				continue;
 			}
@@ -384,11 +478,6 @@ static int ip6_forward_proxy_check(struct sk_buff *skb)
 static inline int ip6_forward_finish(struct net *net, struct sock *sk,
 				     struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb_dst(skb);
-
-	__IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
-	__IP6_ADD_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
-
 #ifdef CONFIG_NET_SWITCHDEV
 	if (skb->offload_l3_fwd_mark) {
 		consume_skb(skb);
@@ -396,7 +485,7 @@ 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);
 }
 
@@ -420,14 +509,18 @@ 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 net *net = dev_net(dst_dev(dst));
+	struct net_device *dev;
+	struct inet6_dev *idev;
+	SKB_DR(reason);
 	u32 mtu;
 
-	if (net->ipv6.devconf_all->forwarding == 0)
+	idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif));
+	if (!READ_ONCE(net->ipv6.devconf_all->forwarding) &&
+	    (!idev || !READ_ONCE(idev->cnf.force_forwarding)))
 		goto error;
 
 	if (skb->pkt_type != PACKET_HOST)
@@ -439,7 +532,9 @@ 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 (!READ_ONCE(net->ipv6.devconf_all->disable_policy) &&
+	    (!idev || !READ_ONCE(idev->cnf.disable_policy)) &&
+	    !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
 		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
 		goto drop;
 	}
@@ -468,22 +563,34 @@ 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;
 	}
 
 	/* XXX: idev->cnf.proxy_ndp? */
-	if (net->ipv6.devconf_all->proxy_ndp &&
-	    pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) {
+	if (READ_ONCE(net->ipv6.devconf_all->proxy_ndp) &&
+	    pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev)) {
 		int proxied = ip6_forward_proxy_check(skb);
-		if (proxied > 0)
+		if (proxied > 0) {
+			/* It's tempting to decrease the hop limit
+			 * here by 1, as we do at the end of the
+			 * function too.
+			 *
+			 * But that would be incorrect, as proxying is
+			 * not forwarding.  The ip6_input function
+			 * will handle this packet locally, and it
+			 * depends on the hop limit being unchanged.
+			 *
+			 * One example is the NDP hop limit, that
+			 * always has to stay 255, but other would be
+			 * similar checks around RA packets, where the
+			 * user can even change the desired limit.
+			 */
 			return ip6_input(skb);
-		else if (proxied < 0) {
+		} else if (proxied < 0) {
 			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
 			goto drop;
 		}
@@ -491,15 +598,16 @@ 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);
-
+	dev = dst_dev(dst);
 	/* IPv6 specs say nothing about it, but it is clear that we cannot
 	   send redirects to source routed frames.
 	   We don't send redirects to frames decapsulated from IPsec.
 	 */
-	if (IP6CB(skb)->iif == dst->dev->ifindex &&
+	if (IP6CB(skb)->iif == dev->ifindex &&
 	    opt->srcrt == 0 && !skb_sec_path(skb)) {
 		struct in6_addr *target = NULL;
 		struct inet_peer *peer;
@@ -510,21 +618,21 @@ int ip6_forward(struct sk_buff *skb)
 		 *	send a redirect.
 		 */
 
-		rt = (struct rt6_info *) dst;
+		rt = dst_rt6_info(dst);
 		if (rt->rt6i_flags & RTF_GATEWAY)
 			target = &rt->rt6i_gateway;
 		else
 			target = &hdr->daddr;
 
-		peer = inet_getpeer_v6(net->ipv6.peers, &hdr->daddr, 1);
+		rcu_read_lock();
+		peer = inet_getpeer_v6(net->ipv6.peers, &hdr->daddr);
 
 		/* Limit redirects both by destination (here)
 		   and by source (inside ndisc_send_redirect)
 		 */
 		if (inet_peer_xrlim_allow(peer, 1*HZ))
 			ndisc_send_redirect(skb, target);
-		if (peer)
-			inet_putpeer(peer);
+		rcu_read_unlock();
 	} else {
 		int addrtype = ipv6_addr_type(&hdr->saddr);
 
@@ -539,22 +647,24 @@ int ip6_forward(struct sk_buff *skb)
 		}
 	}
 
-	mtu = ip6_dst_mtu_forward(dst);
+	__IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
+
+	mtu = ip6_dst_mtu_maybe_forward(dst, true);
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
 
 	if (ip6_pkt_too_big(skb, mtu)) {
 		/* Again, force OUTPUT device used as source address */
-		skb->dev = dst->dev;
+		skb->dev = dev;
 		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		__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;
 	}
 
-	if (skb_cow(skb, dst->dev->hard_header_len)) {
+	if (skb_cow(skb, dev->hard_header_len)) {
 		__IP6_INC_STATS(net, ip6_dst_idev(dst),
 				IPSTATS_MIB_OUTDISCARDS);
 		goto drop;
@@ -567,13 +677,14 @@ int ip6_forward(struct sk_buff *skb)
 	hdr->hop_limit--;
 
 	return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD,
-		       net, NULL, skb, skb->dev, dst->dev,
+		       net, NULL, skb, skb->dev, dev,
 		       ip6_forward_finish);
 
 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;
 }
 
@@ -764,9 +875,10 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		 int (*output)(struct net *, struct sock *, struct sk_buff *))
 {
 	struct sk_buff *frag;
-	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
+	struct rt6_info *rt = dst_rt6_info(skb_dst(skb));
 	struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ?
 				inet6_sk(skb->sk) : NULL;
+	u8 tstamp_type = skb->tstamp_type;
 	struct ip6_frag_state state;
 	unsigned int mtu, hlen, nexthdr_offset;
 	ktime_t tstamp = skb->tstamp;
@@ -799,9 +911,11 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 			mtu = IPV6_MIN_MTU;
 	}
 
-	if (np && np->frag_size < mtu) {
-		if (np->frag_size)
-			mtu = np->frag_size;
+	if (np) {
+		u32 frag_size = READ_ONCE(np->frag_size);
+
+		if (frag_size && frag_size < mtu)
+			mtu = frag_size;
 	}
 	if (mtu < hlen + sizeof(struct frag_hdr) + 8)
 		goto fail_toobig;
@@ -851,13 +965,16 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		if (err < 0)
 			goto fail;
 
+		/* We prevent @rt from being freed. */
+		rcu_read_lock();
+
 		for (;;) {
 			/* Prepare header of the next frame,
 			 * before previous one went down. */
 			if (iter.frag)
 				ip6_fraglist_prepare(skb, &iter);
 
-			skb->tstamp = tstamp;
+			skb_set_delivery_time(skb, tstamp, tstamp_type);
 			err = output(net, sk, skb);
 			if (!err)
 				IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
@@ -874,6 +991,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		if (err == 0) {
 			IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
 				      IPSTATS_MIB_FRAGOKS);
+			rcu_read_unlock();
 			return 0;
 		}
 
@@ -881,6 +999,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 
 		IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
 			      IPSTATS_MIB_FRAGFAILS);
+		rcu_read_unlock();
 		return err;
 
 slow_path_clean:
@@ -916,7 +1035,7 @@ slow_path:
 		/*
 		 *	Put this fragment into the sending queue.
 		 */
-		frag->tstamp = tstamp;
+		skb_set_delivery_time(frag, tstamp, tstamp_type);
 		err = output(net, sk, frag);
 		if (err)
 			goto fail;
@@ -930,9 +1049,6 @@ slow_path:
 	return err;
 
 fail_toobig:
-	if (skb->sk && dst_allfrag(skb_dst(skb)))
-		sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK);
-
 	icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 	err = -EMSGSIZE;
 
@@ -966,7 +1082,7 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk,
 		return NULL;
 	}
 
-	rt = (struct rt6_info *)dst;
+	rt = dst_rt6_info(dst);
 	/* Yes, checking route validity in not connected
 	 * case is not very simple. Take into account,
 	 * that we do not support routing by source, TOS,
@@ -984,12 +1100,13 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk,
 	 *    sockets.
 	 * 2. oif also should be the same.
 	 */
-	if (ip6_rt_check(&rt->rt6i_dst, &fl6->daddr, np->daddr_cache) ||
+	if (ip6_rt_check(&rt->rt6i_dst, &fl6->daddr,
+			 np->daddr_cache ? &sk->sk_v6_daddr : NULL) ||
 #ifdef CONFIG_IPV6_SUBTREES
-	    ip6_rt_check(&rt->rt6i_src, &fl6->saddr, np->saddr_cache) ||
+	    ip6_rt_check(&rt->rt6i_src, &fl6->saddr,
+			 np->saddr_cache ? &np->saddr : NULL) ||
 #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(dst)->ifindex)) {
 		dst_release(dst);
 		dst = NULL;
 	}
@@ -1017,19 +1134,18 @@ 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);
-		rt = (*dst)->error ? NULL : (struct rt6_info *)*dst;
+		*dst = ip6_route_output(net, sk, fl6);
+		rt = (*dst)->error ? NULL : dst_rt6_info(*dst);
 
 		rcu_read_lock();
 		from = rt ? rcu_dereference(rt->from) : NULL;
 		err = ip6_route_get_saddr(net, from, &fl6->daddr,
-					  sk ? inet6_sk(sk)->srcprefs : 0,
+					  sk ? READ_ONCE(inet6_sk(sk)->srcprefs) : 0,
+					  fl6->flowi6_l3mdev,
 					  &fl6->saddr);
 		rcu_read_unlock();
 
@@ -1040,7 +1156,7 @@ 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;
 		}
@@ -1065,12 +1181,12 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
 	 * dst entry and replace it instead with the
 	 * dst entry of the nexthop router
 	 */
-	rt = (struct rt6_info *) *dst;
-	rcu_read_lock_bh();
+	rt = dst_rt6_info(*dst);
+	rcu_read_lock();
 	n = __ipv6_neigh_lookup_noref(rt->dst.dev,
 				      rt6_nexthop(rt, &fl6->daddr));
-	err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0;
-	rcu_read_unlock_bh();
+	err = n && !(READ_ONCE(n->nud_state) & NUD_VALID) ? -EINVAL : 0;
+	rcu_read_unlock();
 
 	if (err) {
 		struct inet6_ifaddr *ifp;
@@ -1118,6 +1234,7 @@ 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
@@ -1136,6 +1253,7 @@ 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
@@ -1197,75 +1315,6 @@ 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
- *      @sk: Socket which provides route info
- *      @saddr: Memory to store the src ip address
- *      @info: Tunnel information
- *      @protocol: IP protocol
- *      @use_cahce: 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(RT_TOS(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)
 {
@@ -1304,11 +1353,16 @@ 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;
+	unsigned int mtu, frag_size;
+	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
@@ -1317,80 +1371,75 @@ 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;
+	v6_cork->dontfrag = ipc6->dontfrag;
 	if (rt->dst.flags & DST_XFRM_TUNNEL)
-		mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
+		mtu = READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE ?
 		      READ_ONCE(rt->dst.dev->mtu) : dst_mtu(&rt->dst);
 	else
-		mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
+		mtu = READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE ?
 			READ_ONCE(rt->dst.dev->mtu) : dst_mtu(xfrm_dst_path(&rt->dst));
-	if (np->frag_size < mtu) {
-		if (np->frag_size)
-			mtu = np->frag_size;
-	}
-	if (mtu < IPV6_MIN_MTU)
-		return -EINVAL;
+
+	frag_size = READ_ONCE(np->frag_size);
+	if (frag_size && frag_size < mtu)
+		mtu = frag_size;
+
 	cork->base.fragsize = mtu;
 	cork->base.gso_size = ipc6->gso_size;
 	cork->base.tx_flags = 0;
 	cork->base.mark = ipc6->sockc.mark;
-	sock_tx_timestamp(sk, ipc6->sockc.tsflags, &cork->base.tx_flags);
-
-	if (dst_allfrag(xfrm_dst_path(&rt->dst)))
-		cork->base.flags |= IPCORK_ALLFRAG;
+	cork->base.priority = ipc6->sockc.priority;
+	sock_tx_timestamp(sk, &ipc6->sockc, &cork->base.tx_flags);
+	if (ipc6->sockc.tsflags & SOCKCM_FLAG_TS_OPT_ID) {
+		cork->base.flags |= IPCORK_TS_OPT_ID;
+		cork->base.ts_opt_id = ipc6->sockc.ts_opt_id;
+	}
 	cork->base.length = 0;
-
 	cork->base.transmit_time = ipc6->sockc.transmit_time;
 
 	return 0;
 }
 
 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,
-			     unsigned int flags, struct ipcm6_cookie *ipc6)
+			     void *from, size_t length, int transhdrlen,
+			     unsigned int flags)
 {
 	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;
@@ -1399,13 +1448,14 @@ 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 rt6_info *rt = dst_rt6_info(cork->dst);
+	bool paged, hold_tskey = false, extra_uref = false;
 	struct ipv6_txoptions *opt = v6_cork->opt;
 	int csummode = CHECKSUM_NONE;
 	unsigned int maxnonfragsize, headersize;
 	unsigned int wmem_alloc_delta = 0;
-	bool paged, extra_uref = false;
 
 	skb = skb_peek_tail(queue);
 	if (!skb) {
@@ -1417,31 +1467,31 @@ static int __ip6_append_data(struct sock *sk,
 	mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize;
 	orig_mtu = mtu;
 
-	if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP &&
-	    sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
-		tskey = sk->sk_tskey++;
-
 	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) +
-		     (dst_allfrag(&rt->dst) ?
-		      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
 	 */
 	if (headersize + transhdrlen > mtu)
 		goto emsgsize;
 
-	if (cork->length + length > mtu - headersize && ipc6->dontfrag &&
+	if (cork->length + length > mtu - headersize && v6_cork->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));
@@ -1470,17 +1520,55 @@ 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 ((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),
+						    false);
+			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);
+			}
+		}
+	} else if ((flags & MSG_SPLICE_PAGES) && length) {
+		if (inet_test_bit(HDRINCL, sk))
+			return -EPERM;
 		if (rt->dst.dev->features & NETIF_F_SG &&
-		    csummode == CHECKSUM_PARTIAL) {
+		    getfrag == ip_generic_getfrag)
+			/* We need an empty buffer to attach stuff to */
 			paged = true;
+		else
+			flags &= ~MSG_SPLICE_PAGES;
+	}
+
+	if (cork->tx_flags & SKBTX_ANY_TSTAMP &&
+	    READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) {
+		if (cork->flags & IPCORK_TS_OPT_ID) {
+			tskey = cork->ts_opt_id;
 		} else {
-			uarg->zerocopy = 0;
-			skb_zcopy_set(skb, uarg, &extra_uref);
+			tskey = atomic_inc_return(&sk->sk_tskey) - 1;
+			hold_tskey = true;
 		}
 	}
 
@@ -1490,7 +1578,7 @@ 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.
 	 *
@@ -1506,7 +1594,7 @@ emsgsize:
 
 	while (length > 0) {
 		/* Check if the remaining data fits into current packet. */
-		copy = (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len;
+		copy = (cork->length <= mtu ? mtu : maxfraglen) - skb->len;
 		if (copy < length)
 			copy = maxfraglen - skb->len;
 
@@ -1515,7 +1603,7 @@ 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 */
@@ -1537,22 +1625,33 @@ alloc_new_skb:
 			 */
 			datalen = length + fraggap;
 
-			if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
+			if (datalen > (cork->length <= mtu ? mtu : maxfraglen) - fragheaderlen)
 				datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
 			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) {
 				/*
@@ -1562,30 +1661,24 @@ 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) {
+			/* [!] NOTE: copy may be negative if pagedlen>0
+			 * because then the equation may reduces to -fraggap.
+			 */
+			if (copy < 0 && !(flags & MSG_SPLICE_PAGES)) {
 				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;
@@ -1613,18 +1706,21 @@ 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;
 				pskb_trim_unique(skb_prev, maxfraglen);
 			}
 			if (copy > 0 &&
-			    getfrag(from, data + transhdrlen, offset,
-				    copy, fraggap, skb) < 0) {
+			    INDIRECT_CALL_1(getfrag, ip_generic_getfrag,
+					   from, data + transhdrlen, offset,
+					   copy, fraggap, skb) < 0) {
 				err = -EFAULT;
 				kfree_skb(skb);
 				goto error;
+			} else if (flags & MSG_SPLICE_PAGES) {
+				copy = 0;
 			}
 
 			offset += copy;
@@ -1663,19 +1759,33 @@ alloc_new_skb:
 			unsigned int off;
 
 			off = skb->len;
-			if (getfrag(from, skb_put(skb, copy),
-						offset, copy, off, skb) < 0) {
+			if (INDIRECT_CALL_1(getfrag, ip_generic_getfrag,
+					    from, skb_put(skb, copy),
+					    offset, copy, off, skb) < 0) {
 				__skb_trim(skb, off);
 				err = -EFAULT;
 				goto error;
 			}
-		} else if (!uarg || !uarg->zerocopy) {
+		} else if (flags & MSG_SPLICE_PAGES) {
+			struct msghdr *msg = from;
+
+			err = -EIO;
+			if (WARN_ON_ONCE(copy > msg->msg_iter.count))
+				goto error;
+
+			err = skb_splice_from_iter(skb, &msg->msg_iter, copy);
+			if (err < 0)
+				goto error;
+			copy = err;
+			wmem_alloc_delta += copy;
+		} 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;
@@ -1688,7 +1798,8 @@ alloc_new_skb:
 				get_page(pfrag->page);
 			}
 			copy = min_t(int, copy, pfrag->size - pfrag->offset);
-			if (getfrag(from,
+			if (INDIRECT_CALL_1(getfrag, ip_generic_getfrag,
+				    from,
 				    page_address(pfrag->page) + pfrag->offset,
 				    offset, copy, skb->len, skb) < 0)
 				goto error_efault;
@@ -1715,18 +1826,19 @@ 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);
+	if (hold_tskey)
+		atomic_dec(&sk->sk_tskey);
 	return err;
 }
 
 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)
 {
@@ -1741,43 +1853,52 @@ 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);
+				 from, length, transhdrlen, flags);
 }
 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;
+	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;
 	}
 
 	if (cork->base.dst) {
 		dst_release(cork->base.dst);
 		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,
@@ -1787,12 +1908,11 @@ 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 ipv6_pinfo *np = inet6_sk(sk);
+	struct in6_addr *final_dst;
 	struct net *net = sock_net(sk);
 	struct ipv6hdr *hdr;
 	struct ipv6_txoptions *opt = v6_cork->opt;
-	struct rt6_info *rt = (struct rt6_info *)cork->base.dst;
+	struct rt6_info *rt = dst_rt6_info(cork->base.dst);
 	struct flowi6 *fl6 = &cork->fl.u.ip6;
 	unsigned char proto = fl6->flowi6_proto;
 
@@ -1817,9 +1937,9 @@ 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)
@@ -1831,23 +1951,31 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 
 	ip6_flow_hdr(hdr, v6_cork->tclass,
 		     ip6_make_flowlabel(net, skb, fl6->flowlabel,
-					ip6_autoflowlabel(net, np), fl6));
+					ip6_autoflowlabel(net, sk), fl6));
 	hdr->hop_limit = v6_cork->hop_limit;
 	hdr->nexthdr = proto;
 	hdr->saddr = fl6->saddr;
 	hdr->daddr = *final_dst;
 
-	skb->priority = sk->sk_priority;
+	skb->priority = cork->base.priority;
 	skb->mark = cork->base.mark;
+	if (sk_is_tcp(sk))
+		skb_set_delivery_time(skb, cork->base.transmit_time, SKB_CLOCK_MONOTONIC);
+	else
+		skb_set_delivery_type_by_clockid(skb, cork->base.transmit_time, sk->sk_clockid);
 
-	skb->tstamp = cork->base.transmit_time;
-
-	skb_dst_set(skb, dst_clone(&rt->dst));
-	IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
+	ip6_cork_steal_dst(skb, cork);
+	IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS);
 	if (proto == IPPROTO_ICMPV6) {
 		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
+		u8 icmp6_type;
 
-		ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type);
+		if (sk->sk_socket->type == SOCK_RAW &&
+		   !(fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH))
+			icmp6_type = fl6->fl6_icmp_type;
+		else
+			icmp6_type = icmp6_hdr(skb)->icmp6_type;
+		ICMP6MSGOUT_INC_STATS(net, idev, icmp6_type);
 		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
 	}
 
@@ -1859,9 +1987,10 @@ out:
 int ip6_send_skb(struct sk_buff *skb)
 {
 	struct net *net = sock_net(skb->sk);
-	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
+	struct rt6_info *rt = dst_rt6_info(skb_dst(skb));
 	int err;
 
+	rcu_read_lock();
 	err = ip6_local_out(net, skb->sk, skb);
 	if (err) {
 		if (err > 0)
@@ -1871,6 +2000,7 @@ int ip6_send_skb(struct sk_buff *skb)
 				      IPSTATS_MIB_OUTDISCARDS);
 	}
 
+	rcu_read_unlock();
 	return err;
 }
 
@@ -1913,38 +2043,36 @@ 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);
 	}
-	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);
+				flags);
 	if (err) {
 		__ip6_flush_pending_frames(sk, &queue, cork, &v6_cork);
 		return ERR_PTR(err);