1 files changed, 333 insertions, 169 deletions

diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 197e6f4a2b74..83e03176819c 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *	common UDP/RAW code
  *	Linux INET6 implementation
  *
  *	Authors:
  *	Pedro Roque		<roque@di.fc.ul.pt>
- *
- *	This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 #include <linux/capability.h>
@@ -23,6 +19,7 @@
 #include <linux/route.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/icmp.h>
 
 #include <net/ipv6.h>
 #include <net/ndisc.h>
@@ -31,32 +28,133 @@
 #include <net/ip6_route.h>
 #include <net/tcp_states.h>
 #include <net/dsfield.h>
+#include <net/sock_reuseport.h>
 
 #include <linux/errqueue.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static bool ipv6_mapped_addr_any(const struct in6_addr *a)
 {
 	return ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0);
 }
 
-int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+static void ip6_datagram_flow_key_init(struct flowi6 *fl6,
+				       const struct sock *sk)
+{
+	const struct inet_sock *inet = inet_sk(sk);
+	const struct ipv6_pinfo *np = inet6_sk(sk);
+	int oif = sk->sk_bound_dev_if;
+
+	memset(fl6, 0, sizeof(*fl6));
+	fl6->flowi6_proto = sk->sk_protocol;
+	fl6->daddr = sk->sk_v6_daddr;
+	fl6->saddr = np->saddr;
+	fl6->flowi6_mark = sk->sk_mark;
+	fl6->fl6_dport = inet->inet_dport;
+	fl6->fl6_sport = inet->inet_sport;
+	fl6->flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label);
+	fl6->flowi6_uid = sk_uid(sk);
+
+	if (!oif)
+		oif = np->sticky_pktinfo.ipi6_ifindex;
+
+	if (!oif) {
+		if (ipv6_addr_is_multicast(&fl6->daddr))
+			oif = READ_ONCE(np->mcast_oif);
+		else
+			oif = READ_ONCE(np->ucast_oif);
+	}
+
+	fl6->flowi6_oif = oif;
+	security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6));
+}
+
+int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr)
+{
+	struct ip6_flowlabel *flowlabel = NULL;
+	struct in6_addr *final_p, final;
+	struct ipv6_txoptions *opt;
+	struct dst_entry *dst;
+	struct inet_sock *inet = inet_sk(sk);
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct flowi6 fl6;
+	int err = 0;
+
+	if (inet6_test_bit(SNDFLOW, sk) &&
+	    (np->flow_label & IPV6_FLOWLABEL_MASK)) {
+		flowlabel = fl6_sock_lookup(sk, np->flow_label);
+		if (IS_ERR(flowlabel))
+			return -EINVAL;
+	}
+	ip6_datagram_flow_key_init(&fl6, sk);
+
+	rcu_read_lock();
+	opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt);
+	final_p = fl6_update_dst(&fl6, opt, &final);
+	rcu_read_unlock();
+
+	dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
+	if (IS_ERR(dst)) {
+		err = PTR_ERR(dst);
+		goto out;
+	}
+
+	if (fix_sk_saddr) {
+		if (ipv6_addr_any(&np->saddr))
+			np->saddr = fl6.saddr;
+
+		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
+			sk->sk_v6_rcv_saddr = fl6.saddr;
+			inet->inet_rcv_saddr = LOOPBACK4_IPV6;
+			if (sk->sk_prot->rehash)
+				sk->sk_prot->rehash(sk);
+		}
+	}
+
+	ip6_sk_dst_store_flow(sk, dst, &fl6);
+
+out:
+	fl6_sock_release(flowlabel);
+	return err;
+}
+
+void ip6_datagram_release_cb(struct sock *sk)
+{
+	struct dst_entry *dst;
+
+	if (ipv6_addr_v4mapped(&sk->sk_v6_daddr))
+		return;
+
+	rcu_read_lock();
+	dst = __sk_dst_get(sk);
+	if (!dst || !READ_ONCE(dst->obsolete) ||
+	    dst->ops->check(dst, inet6_sk(sk)->dst_cookie)) {
+		rcu_read_unlock();
+		return;
+	}
+	rcu_read_unlock();
+
+	ip6_datagram_dst_update(sk, false);
+}
+EXPORT_SYMBOL_GPL(ip6_datagram_release_cb);
+
+int __ip6_datagram_connect(struct sock *sk, struct sockaddr_unsized *uaddr,
+			   int addr_len)
 {
 	struct sockaddr_in6	*usin = (struct sockaddr_in6 *) uaddr;
-	struct inet_sock      	*inet = inet_sk(sk);
-	struct ipv6_pinfo      	*np = inet6_sk(sk);
-	struct in6_addr		*daddr, *final_p, final;
-	struct dst_entry	*dst;
-	struct flowi6		fl6;
-	struct ip6_flowlabel	*flowlabel = NULL;
-	struct ipv6_txoptions   *opt;
+	struct inet_sock	*inet = inet_sk(sk);
+	struct ipv6_pinfo	*np = inet6_sk(sk);
+	struct in6_addr		*daddr, old_daddr;
+	__be32			fl6_flowlabel = 0;
+	__be32			old_fl6_flowlabel;
+	__be16			old_dport;
 	int			addr_type;
 	int			err;
 
 	if (usin->sin6_family == AF_INET) {
-		if (__ipv6_only_sock(sk))
+		if (ipv6_only_sock(sk))
 			return -EAFNOSUPPORT;
-		err = ip4_datagram_connect(sk, uaddr, addr_len);
+		err = __ip4_datagram_connect(sk, uaddr, addr_len);
 		goto ipv4_connected;
 	}
 
@@ -66,32 +164,28 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (usin->sin6_family != AF_INET6)
 		return -EAFNOSUPPORT;
 
-	memset(&fl6, 0, sizeof(fl6));
-	if (np->sndflow) {
-		fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
-		if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
-			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
-			if (flowlabel == NULL)
-				return -EINVAL;
-			usin->sin6_addr = flowlabel->dst;
-		}
-	}
-
-	addr_type = ipv6_addr_type(&usin->sin6_addr);
+	if (inet6_test_bit(SNDFLOW, sk))
+		fl6_flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK;
 
-	if (addr_type == IPV6_ADDR_ANY) {
+	if (ipv6_addr_any(&usin->sin6_addr)) {
 		/*
 		 *	connect to self
 		 */
-		usin->sin6_addr.s6_addr[15] = 0x01;
+		if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+			ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
+					       &usin->sin6_addr);
+		else
+			usin->sin6_addr = in6addr_loopback;
 	}
 
+	addr_type = ipv6_addr_type(&usin->sin6_addr);
+
 	daddr = &usin->sin6_addr;
 
-	if (addr_type == IPV6_ADDR_MAPPED) {
+	if (addr_type & IPV6_ADDR_MAPPED) {
 		struct sockaddr_in sin;
 
-		if (__ipv6_only_sock(sk)) {
+		if (ipv6_only_sock(sk)) {
 			err = -ENETUNREACH;
 			goto out;
 		}
@@ -99,24 +193,24 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		sin.sin_addr.s_addr = daddr->s6_addr32[3];
 		sin.sin_port = usin->sin6_port;
 
-		err = ip4_datagram_connect(sk,
-					   (struct sockaddr *) &sin,
-					   sizeof(sin));
+		err = __ip4_datagram_connect(sk,
+					     (struct sockaddr_unsized *)&sin,
+					     sizeof(sin));
 
 ipv4_connected:
 		if (err)
 			goto out;
 
-		ipv6_addr_set_v4mapped(inet->inet_daddr, &np->daddr);
+		ipv6_addr_set_v4mapped(inet->inet_daddr, &sk->sk_v6_daddr);
 
 		if (ipv6_addr_any(&np->saddr) ||
 		    ipv6_mapped_addr_any(&np->saddr))
 			ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
 
-		if (ipv6_addr_any(&np->rcv_saddr) ||
-		    ipv6_mapped_addr_any(&np->rcv_saddr)) {
+		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr) ||
+		    ipv6_mapped_addr_any(&sk->sk_v6_rcv_saddr)) {
 			ipv6_addr_set_v4mapped(inet->inet_rcv_saddr,
-					       &np->rcv_saddr);
+					       &sk->sk_v6_rcv_saddr);
 			if (sk->sk_prot->rehash)
 				sk->sk_prot->rehash(sk);
 		}
@@ -127,16 +221,15 @@ ipv4_connected:
 	if (__ipv6_addr_needs_scope_id(addr_type)) {
 		if (addr_len >= sizeof(struct sockaddr_in6) &&
 		    usin->sin6_scope_id) {
-			if (sk->sk_bound_dev_if &&
-			    sk->sk_bound_dev_if != usin->sin6_scope_id) {
+			if (!sk_dev_equal_l3scope(sk, usin->sin6_scope_id)) {
 				err = -EINVAL;
 				goto out;
 			}
-			sk->sk_bound_dev_if = usin->sin6_scope_id;
+			WRITE_ONCE(sk->sk_bound_dev_if, usin->sin6_scope_id);
 		}
 
 		if (!sk->sk_bound_dev_if && (addr_type & IPV6_ADDR_MULTICAST))
-			sk->sk_bound_dev_if = np->mcast_oif;
+			WRITE_ONCE(sk->sk_bound_dev_if, READ_ONCE(np->mcast_oif));
 
 		/* Connect to link-local address requires an interface */
 		if (!sk->sk_bound_dev_if) {
@@ -145,9 +238,13 @@ ipv4_connected:
 		}
 	}
 
-	np->daddr = *daddr;
-	np->flow_label = fl6.flowlabel;
+	/* save the current peer information before updating it */
+	old_daddr = sk->sk_v6_daddr;
+	old_fl6_flowlabel = np->flow_label;
+	old_dport = inet->inet_dport;
 
+	sk->sk_v6_daddr = *daddr;
+	np->flow_label = fl6_flowlabel;
 	inet->inet_dport = usin->sin6_port;
 
 	/*
@@ -155,65 +252,64 @@ ipv4_connected:
 	 *	destination cache for it.
 	 */
 
-	fl6.flowi6_proto = sk->sk_protocol;
-	fl6.daddr = np->daddr;
-	fl6.saddr = np->saddr;
-	fl6.flowi6_oif = sk->sk_bound_dev_if;
-	fl6.flowi6_mark = sk->sk_mark;
-	fl6.fl6_dport = inet->inet_dport;
-	fl6.fl6_sport = inet->inet_sport;
-
-	if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST))
-		fl6.flowi6_oif = np->mcast_oif;
-
-	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
-
-	opt = flowlabel ? flowlabel->opt : np->opt;
-	final_p = fl6_update_dst(&fl6, opt, &final);
-
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true);
-	err = 0;
-	if (IS_ERR(dst)) {
-		err = PTR_ERR(dst);
+	err = ip6_datagram_dst_update(sk, true);
+	if (err) {
+		/* Restore the socket peer info, to keep it consistent with
+		 * the old socket state
+		 */
+		sk->sk_v6_daddr = old_daddr;
+		np->flow_label = old_fl6_flowlabel;
+		inet->inet_dport = old_dport;
 		goto out;
 	}
 
-	/* source address lookup done in ip6_dst_lookup */
-
-	if (ipv6_addr_any(&np->saddr))
-		np->saddr = fl6.saddr;
-
-	if (ipv6_addr_any(&np->rcv_saddr)) {
-		np->rcv_saddr = fl6.saddr;
-		inet->inet_rcv_saddr = LOOPBACK4_IPV6;
-		if (sk->sk_prot->rehash)
-			sk->sk_prot->rehash(sk);
-	}
-
-	ip6_dst_store(sk, dst,
-		      ipv6_addr_equal(&fl6.daddr, &np->daddr) ?
-		      &np->daddr : NULL,
-#ifdef CONFIG_IPV6_SUBTREES
-		      ipv6_addr_equal(&fl6.saddr, &np->saddr) ?
-		      &np->saddr :
-#endif
-		      NULL);
-
+	reuseport_has_conns_set(sk);
 	sk->sk_state = TCP_ESTABLISHED;
+	sk_set_txhash(sk);
 out:
-	fl6_sock_release(flowlabel);
 	return err;
 }
+EXPORT_SYMBOL_GPL(__ip6_datagram_connect);
+
+int ip6_datagram_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len)
+{
+	int res;
+
+	lock_sock(sk);
+	res = __ip6_datagram_connect(sk, uaddr, addr_len);
+	release_sock(sk);
+	return res;
+}
 EXPORT_SYMBOL_GPL(ip6_datagram_connect);
 
+int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr_unsized *uaddr,
+				 int addr_len)
+{
+	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, uaddr);
+	if (sin6->sin6_family != AF_INET6)
+		return -EAFNOSUPPORT;
+	return ip6_datagram_connect(sk, uaddr, addr_len);
+}
+EXPORT_SYMBOL_GPL(ip6_datagram_connect_v6_only);
+
+static void ipv6_icmp_error_rfc4884(const struct sk_buff *skb,
+				    struct sock_ee_data_rfc4884 *out)
+{
+	switch (icmp6_hdr(skb)->icmp6_type) {
+	case ICMPV6_TIME_EXCEED:
+	case ICMPV6_DEST_UNREACH:
+		ip_icmp_error_rfc4884(skb, out, sizeof(struct icmp6hdr),
+				      icmp6_hdr(skb)->icmp6_datagram_len * 8);
+	}
+}
+
 void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
 		     __be16 port, u32 info, u8 *payload)
 {
-	struct ipv6_pinfo *np  = inet6_sk(sk);
 	struct icmp6hdr *icmph = icmp6_hdr(skb);
 	struct sock_exterr_skb *serr;
 
-	if (!np->recverr)
+	if (!inet6_test_bit(RECVERR6, sk))
 		return;
 
 	skb = skb_clone(skb, GFP_ATOMIC);
@@ -235,20 +331,24 @@ void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
 	serr->port = port;
 
 	__skb_pull(skb, payload - skb->data);
+
+	if (inet6_test_bit(RECVERR6_RFC4884, sk))
+		ipv6_icmp_error_rfc4884(skb, &serr->ee.ee_rfc4884);
+
 	skb_reset_transport_header(skb);
 
 	if (sock_queue_err_skb(sk, skb))
 		kfree_skb(skb);
 }
+EXPORT_SYMBOL_GPL(ipv6_icmp_error);
 
 void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info)
 {
-	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sock_exterr_skb *serr;
 	struct ipv6hdr *iph;
 	struct sk_buff *skb;
 
-	if (!np->recverr)
+	if (!inet6_test_bit(RECVERR6, sk))
 		return;
 
 	skb = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC);
@@ -261,6 +361,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info)
 	skb_reset_network_header(skb);
 	iph = ipv6_hdr(skb);
 	iph->daddr = fl6->daddr;
+	ip6_flow_hdr(iph, 0, 0);
 
 	serr = SKB_EXT_ERR(skb);
 	serr->ee.ee_errno = err;
@@ -315,15 +416,47 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu)
 	kfree_skb(skb);
 }
 
+/* For some errors we have valid addr_offset even with zero payload and
+ * zero port. Also, addr_offset should be supported if port is set.
+ */
+static inline bool ipv6_datagram_support_addr(struct sock_exterr_skb *serr)
+{
+	return serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6 ||
+	       serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
+	       serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL || serr->port;
+}
+
+/* IPv6 supports cmsg on all origins aside from SO_EE_ORIGIN_LOCAL.
+ *
+ * At one point, excluding local errors was a quick test to identify icmp/icmp6
+ * errors. This is no longer true, but the test remained, so the v6 stack,
+ * unlike v4, also honors cmsg requests on all wifi and timestamp errors.
+ */
+static bool ip6_datagram_support_cmsg(struct sk_buff *skb,
+				      struct sock_exterr_skb *serr)
+{
+	if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
+	    serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6)
+		return true;
+
+	if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL)
+		return false;
+
+	if (!IP6CB(skb)->iif)
+		return false;
+
+	return true;
+}
+
 /*
  *	Handle MSG_ERRQUEUE
  */
-int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
+int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sock_exterr_skb *serr;
-	struct sk_buff *skb, *skb2;
-	struct sockaddr_in6 *sin;
+	struct sk_buff *skb;
+	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin, msg->msg_name);
 	struct {
 		struct sock_extended_err ee;
 		struct sockaddr_in6	 offender;
@@ -332,8 +465,8 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
 	int copied;
 
 	err = -EAGAIN;
-	skb = skb_dequeue(&sk->sk_error_queue);
-	if (skb == NULL)
+	skb = sock_dequeue_err_skb(sk);
+	if (!skb)
 		goto out;
 
 	copied = skb->len;
@@ -341,16 +474,16 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
 		msg->msg_flags |= MSG_TRUNC;
 		copied = len;
 	}
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
-	if (err)
-		goto out_free_skb;
-
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
+	if (unlikely(err)) {
+		kfree_skb(skb);
+		return err;
+	}
 	sock_recv_timestamp(msg, sk, skb);
 
 	serr = SKB_EXT_ERR(skb);
 
-	sin = (struct sockaddr_in6 *)msg->msg_name;
-	if (sin) {
+	if (sin && ipv6_datagram_support_addr(serr)) {
 		const unsigned char *nh = skb_network_header(skb);
 		sin->sin6_family = AF_INET6;
 		sin->sin6_flowinfo = 0;
@@ -359,7 +492,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
 			const struct ipv6hdr *ip6h = container_of((struct in6_addr *)(nh + serr->addr_offset),
 								  struct ipv6hdr, daddr);
 			sin->sin6_addr = ip6h->daddr;
-			if (np->sndflow)
+			if (inet6_test_bit(SNDFLOW, sk))
 				sin->sin6_flowinfo = ip6_flowinfo(ip6h);
 			sin->sin6_scope_id =
 				ipv6_iface_scope_id(&sin->sin6_addr,
@@ -369,28 +502,28 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
 					       &sin->sin6_addr);
 			sin->sin6_scope_id = 0;
 		}
+		*addr_len = sizeof(*sin);
 	}
 
 	memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
 	sin = &errhdr.offender;
-	sin->sin6_family = AF_UNSPEC;
-	if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) {
+	memset(sin, 0, sizeof(*sin));
+
+	if (ip6_datagram_support_cmsg(skb, serr)) {
 		sin->sin6_family = AF_INET6;
-		sin->sin6_flowinfo = 0;
+		if (np->rxopt.all)
+			ip6_datagram_recv_common_ctl(sk, msg, skb);
 		if (skb->protocol == htons(ETH_P_IPV6)) {
 			sin->sin6_addr = ipv6_hdr(skb)->saddr;
 			if (np->rxopt.all)
-				ip6_datagram_recv_ctl(sk, msg, skb);
+				ip6_datagram_recv_specific_ctl(sk, msg, skb);
 			sin->sin6_scope_id =
 				ipv6_iface_scope_id(&sin->sin6_addr,
 						    IP6CB(skb)->iif);
 		} else {
-			struct inet_sock *inet = inet_sk(sk);
-
 			ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr,
 					       &sin->sin6_addr);
-			sin->sin6_scope_id = 0;
-			if (inet->cmsg_flags)
+			if (inet_cmsg_flags(inet_sk(sk)))
 				ip_cmsg_recv(msg, skb);
 		}
 	}
@@ -402,19 +535,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
 	msg->msg_flags |= MSG_ERRQUEUE;
 	err = copied;
 
-	/* Reset and regenerate socket error */
-	spin_lock_bh(&sk->sk_error_queue.lock);
-	sk->sk_err = 0;
-	if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) {
-		sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno;
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-		sk->sk_error_report(sk);
-	} else {
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-	}
-
-out_free_skb:
-	kfree_skb(skb);
+	consume_skb(skb);
 out:
 	return err;
 }
@@ -423,18 +544,19 @@ EXPORT_SYMBOL_GPL(ipv6_recv_error);
 /*
  *	Handle IPV6_RECVPATHMTU
  */
-int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len)
+int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len,
+		     int *addr_len)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sk_buff *skb;
-	struct sockaddr_in6 *sin;
 	struct ip6_mtuinfo mtu_info;
+	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin, msg->msg_name);
 	int err;
 	int copied;
 
 	err = -EAGAIN;
 	skb = xchg(&np->rxpmtu, NULL);
-	if (skb == NULL)
+	if (!skb)
 		goto out;
 
 	copied = skb->len;
@@ -442,7 +564,7 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len)
 		msg->msg_flags |= MSG_TRUNC;
 		copied = len;
 	}
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto out_free_skb;
 
@@ -450,13 +572,13 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len)
 
 	memcpy(&mtu_info, IP6CBMTU(skb), sizeof(mtu_info));
 
-	sin = (struct sockaddr_in6 *)msg->msg_name;
 	if (sin) {
 		sin->sin6_family = AF_INET6;
 		sin->sin6_flowinfo = 0;
 		sin->sin6_port = 0;
 		sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id;
 		sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr;
+		*addr_len = sizeof(*sin);
 	}
 
 	put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info);
@@ -470,20 +592,37 @@ out:
 }
 
 
-int ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
-			  struct sk_buff *skb)
+void ip6_datagram_recv_common_ctl(struct sock *sk, struct msghdr *msg,
+				 struct sk_buff *skb)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct inet6_skb_parm *opt = IP6CB(skb);
-	unsigned char *nh = skb_network_header(skb);
+	bool is_ipv6 = skb->protocol == htons(ETH_P_IPV6);
 
 	if (np->rxopt.bits.rxinfo) {
 		struct in6_pktinfo src_info;
 
-		src_info.ipi6_ifindex = opt->iif;
-		src_info.ipi6_addr = ipv6_hdr(skb)->daddr;
-		put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
+		if (is_ipv6) {
+			src_info.ipi6_ifindex = IP6CB(skb)->iif;
+			src_info.ipi6_addr = ipv6_hdr(skb)->daddr;
+		} else {
+			src_info.ipi6_ifindex =
+				PKTINFO_SKB_CB(skb)->ipi_ifindex;
+			ipv6_addr_set_v4mapped(ip_hdr(skb)->daddr,
+					       &src_info.ipi6_addr);
+		}
+
+		if (src_info.ipi6_ifindex >= 0)
+			put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO,
+				 sizeof(src_info), &src_info);
 	}
+}
+
+void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
+				    struct sk_buff *skb)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct inet6_skb_parm *opt = IP6CB(skb);
+	unsigned char *nh = skb_network_header(skb);
 
 	if (np->rxopt.bits.rxhlim) {
 		int hlim = ipv6_hdr(skb)->hop_limit;
@@ -502,8 +641,8 @@ int ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
 	}
 
 	/* HbH is allowed only once */
-	if (np->rxopt.bits.hopopts && opt->hop) {
-		u8 *ptr = nh + opt->hop;
+	if (np->rxopt.bits.hopopts && (opt->flags & IP6SKB_HOPBYHOP)) {
+		u8 *ptr = nh + sizeof(struct ipv6hdr);
 		put_cmsg(msg, SOL_IPV6, IPV6_HOPOPTS, (ptr[1]+1)<<3, ptr);
 	}
 
@@ -564,8 +703,8 @@ int ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
 		int hlim = ipv6_hdr(skb)->hop_limit;
 		put_cmsg(msg, SOL_IPV6, IPV6_2292HOPLIMIT, sizeof(hlim), &hlim);
 	}
-	if (np->rxopt.bits.ohopopts && opt->hop) {
-		u8 *ptr = nh + opt->hop;
+	if (np->rxopt.bits.ohopopts && (opt->flags & IP6SKB_HOPBYHOP)) {
+		u8 *ptr = nh + sizeof(struct ipv6hdr);
 		put_cmsg(msg, SOL_IPV6, IPV6_2292HOPOPTS, (ptr[1]+1)<<3, ptr);
 	}
 	if (np->rxopt.bits.odstopts && opt->dst0) {
@@ -582,14 +721,15 @@ int ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
 	}
 	if (np->rxopt.bits.rxorigdstaddr) {
 		struct sockaddr_in6 sin6;
-		__be16 *ports = (__be16 *) skb_transport_header(skb);
+		__be16 _ports[2], *ports;
 
-		if (skb_transport_offset(skb) + 4 <= skb->len) {
+		ports = skb_header_pointer(skb, skb_transport_offset(skb),
+					   sizeof(_ports), &_ports);
+		if (ports) {
 			/* All current transport protocols have the port numbers in the
 			 * first four bytes of the transport header and this function is
 			 * written with this assumption in mind.
 			 */
-
 			sin6.sin6_family = AF_INET6;
 			sin6.sin6_addr = ipv6_hdr(skb)->daddr;
 			sin6.sin6_port = ports[1];
@@ -601,23 +741,34 @@ int ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
 			put_cmsg(msg, SOL_IPV6, IPV6_ORIGDSTADDR, sizeof(sin6), &sin6);
 		}
 	}
-	return 0;
+	if (np->rxopt.bits.recvfragsize && opt->frag_max_size) {
+		int val = opt->frag_max_size;
+
+		put_cmsg(msg, SOL_IPV6, IPV6_RECVFRAGSIZE, sizeof(val), &val);
+	}
+}
+
+void ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
+			  struct sk_buff *skb)
+{
+	ip6_datagram_recv_common_ctl(sk, msg, skb);
+	ip6_datagram_recv_specific_ctl(sk, msg, skb);
 }
 EXPORT_SYMBOL_GPL(ip6_datagram_recv_ctl);
 
 int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 			  struct msghdr *msg, struct flowi6 *fl6,
-			  struct ipv6_txoptions *opt,
-			  int *hlimit, int *tclass, int *dontfrag)
+			  struct ipcm6_cookie *ipc6)
 {
 	struct in6_pktinfo *src_info;
 	struct cmsghdr *cmsg;
 	struct ipv6_rt_hdr *rthdr;
 	struct ipv6_opt_hdr *hdr;
+	struct ipv6_txoptions *opt = ipc6->opt;
 	int len;
 	int err = 0;
 
-	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
+	for_each_cmsghdr(cmsg, msg) {
 		int addr_type;
 
 		if (!CMSG_OK(msg, cmsg)) {
@@ -625,6 +776,13 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 			goto exit_f;
 		}
 
+		if (cmsg->cmsg_level == SOL_SOCKET) {
+			err = __sock_cmsg_send(sk, cmsg, &ipc6->sockc);
+			if (err)
+				return err;
+			continue;
+		}
+
 		if (cmsg->cmsg_level != SOL_IPV6)
 			continue;
 
@@ -633,6 +791,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 		case IPV6_2292PKTINFO:
 		    {
 			struct net_device *dev = NULL;
+			int src_idx;
 
 			if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct in6_pktinfo))) {
 				err = -EINVAL;
@@ -640,12 +799,15 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 			}
 
 			src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg);
+			src_idx = src_info->ipi6_ifindex;
 
-			if (src_info->ipi6_ifindex) {
+			if (src_idx) {
 				if (fl6->flowi6_oif &&
-				    src_info->ipi6_ifindex != fl6->flowi6_oif)
+				    src_idx != fl6->flowi6_oif &&
+				    (READ_ONCE(sk->sk_bound_dev_if) != fl6->flowi6_oif ||
+				     !sk_dev_equal_l3scope(sk, src_idx)))
 					return -EINVAL;
-				fl6->flowi6_oif = src_info->ipi6_ifindex;
+				fl6->flowi6_oif = src_idx;
 			}
 
 			addr_type = __ipv6_addr_type(&src_info->ipi6_addr);
@@ -664,9 +826,12 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 
 			if (addr_type != IPV6_ADDR_ANY) {
 				int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL;
-				if (!(inet_sk(sk)->freebind || inet_sk(sk)->transparent) &&
-				    !ipv6_chk_addr(net, &src_info->ipi6_addr,
-						   strict ? dev : NULL, 0))
+				if (!ipv6_can_nonlocal_bind(net, inet_sk(sk)) &&
+				    !ipv6_chk_addr_and_flags(net, &src_info->ipi6_addr,
+							     dev, !strict, 0,
+							     IFA_F_TENTATIVE) &&
+				    !ipv6_chk_acast_addr_src(net, dev,
+							     &src_info->ipi6_addr))
 					err = -EINVAL;
 				else
 					fl6->saddr = src_info->ipi6_addr;
@@ -824,8 +989,8 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 				goto exit_f;
 			}
 
-			*hlimit = *(int *)CMSG_DATA(cmsg);
-			if (*hlimit < -1 || *hlimit > 0xff) {
+			ipc6->hlimit = *(int *)CMSG_DATA(cmsg);
+			if (ipc6->hlimit < -1 || ipc6->hlimit > 0xff) {
 				err = -EINVAL;
 				goto exit_f;
 			}
@@ -845,7 +1010,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 				goto exit_f;
 
 			err = 0;
-			*tclass = tc;
+			ipc6->tclass = tc;
 
 			break;
 		    }
@@ -863,13 +1028,13 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 				goto exit_f;
 
 			err = 0;
-			*dontfrag = df;
+			ipc6->dontfrag = df;
 
 			break;
 		    }
 		default:
-			LIMIT_NETDEBUG(KERN_DEBUG "invalid cmsg type: %d\n",
-				       cmsg->cmsg_type);
+			net_dbg_ratelimited("invalid cmsg type: %d\n",
+					    cmsg->cmsg_type);
 			err = -EINVAL;
 			goto exit_f;
 		}
@@ -880,17 +1045,16 @@ exit_f:
 }
 EXPORT_SYMBOL_GPL(ip6_datagram_send_ctl);
 
-void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
-			     __u16 srcp, __u16 destp, int bucket)
+void __ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
+			       __u16 srcp, __u16 destp, int rqueue, int bucket)
 {
-	struct ipv6_pinfo *np = inet6_sk(sp);
 	const struct in6_addr *dest, *src;
 
-	dest  = &np->daddr;
-	src   = &np->rcv_saddr;
+	dest  = &sp->sk_v6_daddr;
+	src   = &sp->sk_v6_rcv_saddr;
 	seq_printf(seq,
 		   "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
-		   "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d\n",
+		   "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u\n",
 		   bucket,
 		   src->s6_addr32[0], src->s6_addr32[1],
 		   src->s6_addr32[2], src->s6_addr32[3], srcp,
@@ -898,11 +1062,11 @@ void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
 		   dest->s6_addr32[2], dest->s6_addr32[3], destp,
 		   sp->sk_state,
 		   sk_wmem_alloc_get(sp),
-		   sk_rmem_alloc_get(sp),
+		   rqueue,
 		   0, 0L, 0,
-		   from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)),
+		   from_kuid_munged(seq_user_ns(seq), sk_uid(sp)),
 		   0,
 		   sock_i_ino(sp),
-		   atomic_read(&sp->sk_refcnt), sp,
-		   atomic_read(&sp->sk_drops));
+		   refcount_read(&sp->sk_refcnt), sp,
+		   sk_drops_read(sp));
 }