Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "This is a re-do of the net-next pull request for the current merge
  window.  The only difference from the one I made the other day is that
  this has Eliezer's interface renames and the timeout handling changes
  made based upon your feedback, as well as a few bug fixes that have
  trickeled in.

  Highlights:

   1) Low latency device polling, eliminating the cost of interrupt
      handling and context switches.  Allows direct polling of a network
      device from socket operations, such as recvmsg() and poll().

      Currently ixgbe, mlx4, and bnx2x support this feature.

      Full high level description, performance numbers, and design in
      commit 0a4db187a999 ("Merge branch 'll_poll'")

      From Eliezer Tamir.

   2) With the routing cache removed, ip_check_mc_rcu() gets exercised
      more than ever before in the case where we have lots of multicast
      addresses.  Use a hash table instead of a simple linked list, from
      Eric Dumazet.

   3) Add driver for Atheros CQA98xx 802.11ac wireless devices, from
      Bartosz Markowski, Janusz Dziedzic, Kalle Valo, Marek Kwaczynski,
      Marek Puzyniak, Michal Kazior, and Sujith Manoharan.

   4) Support reporting the TUN device persist flag to userspace, from
      Pavel Emelyanov.

   5) Allow controlling network device VF link state using netlink, from
      Rony Efraim.

   6) Support GRE tunneling in openvswitch, from Pravin B Shelar.

   7) Adjust SOCK_MIN_RCVBUF and SOCK_MIN_SNDBUF for modern times, from
      Daniel Borkmann and Eric Dumazet.

   8) Allow controlling of TCP quickack behavior on a per-route basis,
      from Cong Wang.

   9) Several bug fixes and improvements to vxlan from Stephen
      Hemminger, Pravin B Shelar, and Mike Rapoport.  In particular,
      support receiving on multiple UDP ports.

  10) Major cleanups, particular in the area of debugging and cookie
      lifetime handline, to the SCTP protocol code.  From Daniel
      Borkmann.

  11) Allow packets to cross network namespaces when traversing tunnel
      devices.  From Nicolas Dichtel.

  12) Allow monitoring netlink traffic via AF_PACKET sockets, in a
      manner akin to how we monitor real network traffic via ptype_all.
      From Daniel Borkmann.

  13) Several bug fixes and improvements for the new alx device driver,
      from Johannes Berg.

  14) Fix scalability issues in the netem packet scheduler's time queue,
      by using an rbtree.  From Eric Dumazet.

  15) Several bug fixes in TCP loss recovery handling, from Yuchung
      Cheng.

  16) Add support for GSO segmentation of MPLS packets, from Simon
      Horman.

  17) Make network notifiers have a real data type for the opaque
      pointer that's passed into them.  Use this to properly handle
      network device flag changes in arp_netdev_event().  From Jiri
      Pirko and Timo Teräs.

  18) Convert several drivers over to module_pci_driver(), from Peter
      Huewe.

  19) tcp_fixup_rcvbuf() can loop 500 times over loopback, just use a
      O(1) calculation instead.  From Eric Dumazet.

  20) Support setting of explicit tunnel peer addresses in ipv6, just
      like ipv4.  From Nicolas Dichtel.

  21) Protect x86 BPF JIT against spraying attacks, from Eric Dumazet.

  22) Prevent a single high rate flow from overruning an individual cpu
      during RX packet processing via selective flow shedding.  From
      Willem de Bruijn.

  23) Don't use spinlocks in TCP md5 signing fast paths, from Eric
      Dumazet.

  24) Don't just drop GSO packets which are above the TBF scheduler's
      burst limit, chop them up so they are in-bounds instead.  Also
      from Eric Dumazet.

  25) VLAN offloads are missed when configured on top of a bridge, fix
      from Vlad Yasevich.

  26) Support IPV6 in ping sockets.  From Lorenzo Colitti.

  27) Receive flow steering targets should be updated at poll() time
      too, from David Majnemer.

  28) Fix several corner case regressions in PMTU/redirect handling due
      to the routing cache removal, from Timo Teräs.

  29) We have to be mindful of ipv4 mapped ipv6 sockets in
      upd_v6_push_pending_frames().  From Hannes Frederic Sowa.

  30) Fix L2TP sequence number handling bugs, from James Chapman."

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1214 commits)
  drivers/net: caif: fix wrong rtnl_is_locked() usage
  drivers/net: enic: release rtnl_lock on error-path
  vhost-net: fix use-after-free in vhost_net_flush
  net: mv643xx_eth: do not use port number as platform device id
  net: sctp: confirm route during forward progress
  virtio_net: fix race in RX VQ processing
  virtio: support unlocked queue poll
  net/cadence/macb: fix bug/typo in extracting gem_irq_read_clear bit
  Documentation: Fix references to defunct linux-net@vger.kernel.org
  net/fs: change busy poll time accounting
  net: rename low latency sockets functions to busy poll
  bridge: fix some kernel warning in multicast timer
  sfc: Fix memory leak when discarding scattered packets
  sit: fix tunnel update via netlink
  dt:net:stmmac: Add dt specific phy reset callback support.
  dt:net:stmmac: Add support to dwmac version 3.610 and 3.710
  dt:net:stmmac: Allocate platform data only if its NULL.
  net:stmmac: fix memleak in the open method
  ipv6: rt6_check_neigh should successfully verify neigh if no NUD information are available
  net: ipv6: fix wrong ping_v6_sendmsg return value
  ...

1 files changed, 451 insertions, 190 deletions

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 7d93d62cd5fd..746427c9e719 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -33,7 +33,6 @@
 #include <linux/netdevice.h>
 #include <net/snmp.h>
 #include <net/ip.h>
-#include <net/ipv6.h>
 #include <net/icmp.h>
 #include <net/protocol.h>
 #include <linux/skbuff.h>
@@ -46,8 +45,18 @@
 #include <net/inet_common.h>
 #include <net/checksum.h>
 
+#if IS_ENABLED(CONFIG_IPV6)
+#include <linux/in6.h>
+#include <linux/icmpv6.h>
+#include <net/addrconf.h>
+#include <net/ipv6.h>
+#include <net/transp_v6.h>
+#endif
 
-static struct ping_table ping_table;
+
+struct ping_table ping_table;
+struct pingv6_ops pingv6_ops;
+EXPORT_SYMBOL_GPL(pingv6_ops);
 
 static u16 ping_port_rover;
 
@@ -58,6 +67,7 @@ static inline int ping_hashfn(struct net *net, unsigned int num, unsigned int ma
 	pr_debug("hash(%d) = %d\n", num, res);
 	return res;
 }
+EXPORT_SYMBOL_GPL(ping_hash);
 
 static inline struct hlist_nulls_head *ping_hashslot(struct ping_table *table,
 					     struct net *net, unsigned int num)
@@ -65,7 +75,7 @@ static inline struct hlist_nulls_head *ping_hashslot(struct ping_table *table,
 	return &table->hash[ping_hashfn(net, num, PING_HTABLE_MASK)];
 }
 
-static int ping_v4_get_port(struct sock *sk, unsigned short ident)
+int ping_get_port(struct sock *sk, unsigned short ident)
 {
 	struct hlist_nulls_node *node;
 	struct hlist_nulls_head *hlist;
@@ -103,6 +113,10 @@ next_port:
 		ping_portaddr_for_each_entry(sk2, node, hlist) {
 			isk2 = inet_sk(sk2);
 
+			/* BUG? Why is this reuse and not reuseaddr? ping.c
+			 * doesn't turn off SO_REUSEADDR, and it doesn't expect
+			 * that other ping processes can steal its packets.
+			 */
 			if ((isk2->inet_num == ident) &&
 			    (sk2 != sk) &&
 			    (!sk2->sk_reuse || !sk->sk_reuse))
@@ -125,17 +139,18 @@ fail:
 	write_unlock_bh(&ping_table.lock);
 	return 1;
 }
+EXPORT_SYMBOL_GPL(ping_get_port);
 
-static void ping_v4_hash(struct sock *sk)
+void ping_hash(struct sock *sk)
 {
-	pr_debug("ping_v4_hash(sk->port=%u)\n", inet_sk(sk)->inet_num);
+	pr_debug("ping_hash(sk->port=%u)\n", inet_sk(sk)->inet_num);
 	BUG(); /* "Please do not press this button again." */
 }
 
-static void ping_v4_unhash(struct sock *sk)
+void ping_unhash(struct sock *sk)
 {
 	struct inet_sock *isk = inet_sk(sk);
-	pr_debug("ping_v4_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
+	pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
 	if (sk_hashed(sk)) {
 		write_lock_bh(&ping_table.lock);
 		hlist_nulls_del(&sk->sk_nulls_node);
@@ -146,31 +161,61 @@ static void ping_v4_unhash(struct sock *sk)
 		write_unlock_bh(&ping_table.lock);
 	}
 }
+EXPORT_SYMBOL_GPL(ping_unhash);
 
-static struct sock *ping_v4_lookup(struct net *net, __be32 saddr, __be32 daddr,
-				   u16 ident, int dif)
+static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
 {
 	struct hlist_nulls_head *hslot = ping_hashslot(&ping_table, net, ident);
 	struct sock *sk = NULL;
 	struct inet_sock *isk;
 	struct hlist_nulls_node *hnode;
+	int dif = skb->dev->ifindex;
+
+	if (skb->protocol == htons(ETH_P_IP)) {
+		pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n",
+			 (int)ident, &ip_hdr(skb)->daddr, dif);
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		pr_debug("try to find: num = %d, daddr = %pI6c, dif = %d\n",
+			 (int)ident, &ipv6_hdr(skb)->daddr, dif);
+#endif
+	}
 
-	pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n",
-		 (int)ident, &daddr, dif);
 	read_lock_bh(&ping_table.lock);
 
 	ping_portaddr_for_each_entry(sk, hnode, hslot) {
 		isk = inet_sk(sk);
 
-		pr_debug("found: %p: num = %d, daddr = %pI4, dif = %d\n", sk,
-			 (int)isk->inet_num, &isk->inet_rcv_saddr,
-			 sk->sk_bound_dev_if);
-
 		pr_debug("iterate\n");
 		if (isk->inet_num != ident)
 			continue;
-		if (isk->inet_rcv_saddr && isk->inet_rcv_saddr != daddr)
-			continue;
+
+		if (skb->protocol == htons(ETH_P_IP) &&
+		    sk->sk_family == AF_INET) {
+			pr_debug("found: %p: num=%d, daddr=%pI4, dif=%d\n", sk,
+				 (int) isk->inet_num, &isk->inet_rcv_saddr,
+				 sk->sk_bound_dev_if);
+
+			if (isk->inet_rcv_saddr &&
+			    isk->inet_rcv_saddr != ip_hdr(skb)->daddr)
+				continue;
+#if IS_ENABLED(CONFIG_IPV6)
+		} else if (skb->protocol == htons(ETH_P_IPV6) &&
+			   sk->sk_family == AF_INET6) {
+			struct ipv6_pinfo *np = inet6_sk(sk);
+
+			pr_debug("found: %p: num=%d, daddr=%pI6c, dif=%d\n", sk,
+				 (int) isk->inet_num,
+				 &inet6_sk(sk)->rcv_saddr,
+				 sk->sk_bound_dev_if);
+
+			if (!ipv6_addr_any(&np->rcv_saddr) &&
+			    !ipv6_addr_equal(&np->rcv_saddr,
+					     &ipv6_hdr(skb)->daddr))
+				continue;
+#endif
+		}
+
 		if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)
 			continue;
 
@@ -200,7 +245,7 @@ static void inet_get_ping_group_range_net(struct net *net, kgid_t *low,
 }
 
 
-static int ping_init_sock(struct sock *sk)
+int ping_init_sock(struct sock *sk)
 {
 	struct net *net = sock_net(sk);
 	kgid_t group = current_egid();
@@ -225,8 +270,9 @@ static int ping_init_sock(struct sock *sk)
 
 	return -EACCES;
 }
+EXPORT_SYMBOL_GPL(ping_init_sock);
 
-static void ping_close(struct sock *sk, long timeout)
+void ping_close(struct sock *sk, long timeout)
 {
 	pr_debug("ping_close(sk=%p,sk->num=%u)\n",
 		 inet_sk(sk), inet_sk(sk)->inet_num);
@@ -234,36 +280,122 @@ static void ping_close(struct sock *sk, long timeout)
 
 	sk_common_release(sk);
 }
+EXPORT_SYMBOL_GPL(ping_close);
+
+/* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */
+static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
+				struct sockaddr *uaddr, int addr_len) {
+	struct net *net = sock_net(sk);
+	if (sk->sk_family == AF_INET) {
+		struct sockaddr_in *addr = (struct sockaddr_in *) uaddr;
+		int chk_addr_ret;
+
+		if (addr_len < sizeof(*addr))
+			return -EINVAL;
+
+		pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n",
+			 sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port));
+
+		chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr);
+
+		if (addr->sin_addr.s_addr == htonl(INADDR_ANY))
+			chk_addr_ret = RTN_LOCAL;
+
+		if ((sysctl_ip_nonlocal_bind == 0 &&
+		    isk->freebind == 0 && isk->transparent == 0 &&
+		     chk_addr_ret != RTN_LOCAL) ||
+		    chk_addr_ret == RTN_MULTICAST ||
+		    chk_addr_ret == RTN_BROADCAST)
+			return -EADDRNOTAVAIL;
+
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (sk->sk_family == AF_INET6) {
+		struct sockaddr_in6 *addr = (struct sockaddr_in6 *) uaddr;
+		int addr_type, scoped, has_addr;
+		struct net_device *dev = NULL;
+
+		if (addr_len < sizeof(*addr))
+			return -EINVAL;
+
+		pr_debug("ping_check_bind_addr(sk=%p,addr=%pI6c,port=%d)\n",
+			 sk, addr->sin6_addr.s6_addr, ntohs(addr->sin6_port));
+
+		addr_type = ipv6_addr_type(&addr->sin6_addr);
+		scoped = __ipv6_addr_needs_scope_id(addr_type);
+		if ((addr_type != IPV6_ADDR_ANY &&
+		     !(addr_type & IPV6_ADDR_UNICAST)) ||
+		    (scoped && !addr->sin6_scope_id))
+			return -EINVAL;
+
+		rcu_read_lock();
+		if (addr->sin6_scope_id) {
+			dev = dev_get_by_index_rcu(net, addr->sin6_scope_id);
+			if (!dev) {
+				rcu_read_unlock();
+				return -ENODEV;
+			}
+		}
+		has_addr = pingv6_ops.ipv6_chk_addr(net, &addr->sin6_addr, dev,
+						    scoped);
+		rcu_read_unlock();
+
+		if (!(isk->freebind || isk->transparent || has_addr ||
+		      addr_type == IPV6_ADDR_ANY))
+			return -EADDRNOTAVAIL;
+
+		if (scoped)
+			sk->sk_bound_dev_if = addr->sin6_scope_id;
+#endif
+	} else {
+		return -EAFNOSUPPORT;
+	}
+	return 0;
+}
+
+static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr)
+{
+	if (saddr->sa_family == AF_INET) {
+		struct inet_sock *isk = inet_sk(sk);
+		struct sockaddr_in *addr = (struct sockaddr_in *) saddr;
+		isk->inet_rcv_saddr = isk->inet_saddr = addr->sin_addr.s_addr;
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (saddr->sa_family == AF_INET6) {
+		struct sockaddr_in6 *addr = (struct sockaddr_in6 *) saddr;
+		struct ipv6_pinfo *np = inet6_sk(sk);
+		np->rcv_saddr = np->saddr = addr->sin6_addr;
+#endif
+	}
+}
 
+static void ping_clear_saddr(struct sock *sk, int dif)
+{
+	sk->sk_bound_dev_if = dif;
+	if (sk->sk_family == AF_INET) {
+		struct inet_sock *isk = inet_sk(sk);
+		isk->inet_rcv_saddr = isk->inet_saddr = 0;
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (sk->sk_family == AF_INET6) {
+		struct ipv6_pinfo *np = inet6_sk(sk);
+		memset(&np->rcv_saddr, 0, sizeof(np->rcv_saddr));
+		memset(&np->saddr, 0, sizeof(np->saddr));
+#endif
+	}
+}
 /*
  * We need our own bind because there are no privileged id's == local ports.
  * Moreover, we don't allow binding to multi- and broadcast addresses.
  */
 
-static int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
-	struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
 	struct inet_sock *isk = inet_sk(sk);
 	unsigned short snum;
-	int chk_addr_ret;
 	int err;
+	int dif = sk->sk_bound_dev_if;
 
-	if (addr_len < sizeof(struct sockaddr_in))
-		return -EINVAL;
-
-	pr_debug("ping_v4_bind(sk=%p,sa_addr=%08x,sa_port=%d)\n",
-		 sk, addr->sin_addr.s_addr, ntohs(addr->sin_port));
-
-	chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr);
-	if (addr->sin_addr.s_addr == htonl(INADDR_ANY))
-		chk_addr_ret = RTN_LOCAL;
-
-	if ((sysctl_ip_nonlocal_bind == 0 &&
-	    isk->freebind == 0 && isk->transparent == 0 &&
-	     chk_addr_ret != RTN_LOCAL) ||
-	    chk_addr_ret == RTN_MULTICAST ||
-	    chk_addr_ret == RTN_BROADCAST)
-		return -EADDRNOTAVAIL;
+	err = ping_check_bind_addr(sk, isk, uaddr, addr_len);
+	if (err)
+		return err;
 
 	lock_sock(sk);
 
@@ -272,42 +404,50 @@ static int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		goto out;
 
 	err = -EADDRINUSE;
-	isk->inet_rcv_saddr = isk->inet_saddr = addr->sin_addr.s_addr;
-	snum = ntohs(addr->sin_port);
-	if (ping_v4_get_port(sk, snum) != 0) {
-		isk->inet_saddr = isk->inet_rcv_saddr = 0;
+	ping_set_saddr(sk, uaddr);
+	snum = ntohs(((struct sockaddr_in *)uaddr)->sin_port);
+	if (ping_get_port(sk, snum) != 0) {
+		ping_clear_saddr(sk, dif);
 		goto out;
 	}
 
-	pr_debug("after bind(): num = %d, daddr = %pI4, dif = %d\n",
+	pr_debug("after bind(): num = %d, dif = %d\n",
 		 (int)isk->inet_num,
-		 &isk->inet_rcv_saddr,
 		 (int)sk->sk_bound_dev_if);
 
 	err = 0;
-	if (isk->inet_rcv_saddr)
+	if ((sk->sk_family == AF_INET && isk->inet_rcv_saddr) ||
+	    (sk->sk_family == AF_INET6 &&
+	     !ipv6_addr_any(&inet6_sk(sk)->rcv_saddr)))
 		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
+
 	if (snum)
 		sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
 	isk->inet_sport = htons(isk->inet_num);
 	isk->inet_daddr = 0;
 	isk->inet_dport = 0;
+
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6)
+		memset(&inet6_sk(sk)->daddr, 0, sizeof(inet6_sk(sk)->daddr));
+#endif
+
 	sk_dst_reset(sk);
 out:
 	release_sock(sk);
 	pr_debug("ping_v4_bind -> %d\n", err);
 	return err;
 }
+EXPORT_SYMBOL_GPL(ping_bind);
 
 /*
  * Is this a supported type of ICMP message?
  */
 
-static inline int ping_supported(int type, int code)
+static inline int ping_supported(int family, int type, int code)
 {
-	if (type == ICMP_ECHO && code == 0)
-		return 1;
-	return 0;
+	return (family == AF_INET && type == ICMP_ECHO && code == 0) ||
+	       (family == AF_INET6 && type == ICMPV6_ECHO_REQUEST && code == 0);
 }
 
 /*
@@ -315,30 +455,42 @@ static inline int ping_supported(int type, int code)
  * sort of error condition.
  */
 
-static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
-
-void ping_err(struct sk_buff *skb, u32 info)
+void ping_err(struct sk_buff *skb, int offset, u32 info)
 {
-	struct iphdr *iph = (struct iphdr *)skb->data;
-	struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2));
+	int family;
+	struct icmphdr *icmph;
 	struct inet_sock *inet_sock;
-	int type = icmp_hdr(skb)->type;
-	int code = icmp_hdr(skb)->code;
+	int type;
+	int code;
 	struct net *net = dev_net(skb->dev);
 	struct sock *sk;
 	int harderr;
 	int err;
 
+	if (skb->protocol == htons(ETH_P_IP)) {
+		family = AF_INET;
+		type = icmp_hdr(skb)->type;
+		code = icmp_hdr(skb)->code;
+		icmph = (struct icmphdr *)(skb->data + offset);
+	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		family = AF_INET6;
+		type = icmp6_hdr(skb)->icmp6_type;
+		code = icmp6_hdr(skb)->icmp6_code;
+		icmph = (struct icmphdr *) (skb->data + offset);
+	} else {
+		BUG();
+	}
+
 	/* We assume the packet has already been checked by icmp_unreach */
 
-	if (!ping_supported(icmph->type, icmph->code))
+	if (!ping_supported(family, icmph->type, icmph->code))
 		return;
 
-	pr_debug("ping_err(type=%04x,code=%04x,id=%04x,seq=%04x)\n", type,
-		 code, ntohs(icmph->un.echo.id), ntohs(icmph->un.echo.sequence));
+	pr_debug("ping_err(proto=0x%x,type=%d,code=%d,id=%04x,seq=%04x)\n",
+		 skb->protocol, type, code, ntohs(icmph->un.echo.id),
+		 ntohs(icmph->un.echo.sequence));
 
-	sk = ping_v4_lookup(net, iph->daddr, iph->saddr,
-			    ntohs(icmph->un.echo.id), skb->dev->ifindex);
+	sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id));
 	if (sk == NULL) {
 		pr_debug("no socket, dropping\n");
 		return;	/* No socket for error */
@@ -349,72 +501,83 @@ void ping_err(struct sk_buff *skb, u32 info)
 	harderr = 0;
 	inet_sock = inet_sk(sk);
 
-	switch (type) {
-	default:
-	case ICMP_TIME_EXCEEDED:
-		err = EHOSTUNREACH;
-		break;
-	case ICMP_SOURCE_QUENCH:
-		/* This is not a real error but ping wants to see it.
-		 * Report it with some fake errno. */
-		err = EREMOTEIO;
-		break;
-	case ICMP_PARAMETERPROB:
-		err = EPROTO;
-		harderr = 1;
-		break;
-	case ICMP_DEST_UNREACH:
-		if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
-			ipv4_sk_update_pmtu(skb, sk, info);
-			if (inet_sock->pmtudisc != IP_PMTUDISC_DONT) {
-				err = EMSGSIZE;
-				harderr = 1;
-				break;
+	if (skb->protocol == htons(ETH_P_IP)) {
+		switch (type) {
+		default:
+		case ICMP_TIME_EXCEEDED:
+			err = EHOSTUNREACH;
+			break;
+		case ICMP_SOURCE_QUENCH:
+			/* This is not a real error but ping wants to see it.
+			 * Report it with some fake errno.
+			 */
+			err = EREMOTEIO;
+			break;
+		case ICMP_PARAMETERPROB:
+			err = EPROTO;
+			harderr = 1;
+			break;
+		case ICMP_DEST_UNREACH:
+			if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
+				ipv4_sk_update_pmtu(skb, sk, info);
+				if (inet_sock->pmtudisc != IP_PMTUDISC_DONT) {
+					err = EMSGSIZE;
+					harderr = 1;
+					break;
+				}
+				goto out;
 			}
-			goto out;
-		}
-		err = EHOSTUNREACH;
-		if (code <= NR_ICMP_UNREACH) {
-			harderr = icmp_err_convert[code].fatal;
-			err = icmp_err_convert[code].errno;
+			err = EHOSTUNREACH;
+			if (code <= NR_ICMP_UNREACH) {
+				harderr = icmp_err_convert[code].fatal;
+				err = icmp_err_convert[code].errno;
+			}
+			break;
+		case ICMP_REDIRECT:
+			/* See ICMP_SOURCE_QUENCH */
+			ipv4_sk_redirect(skb, sk);
+			err = EREMOTEIO;
+			break;
 		}
-		break;
-	case ICMP_REDIRECT:
-		/* See ICMP_SOURCE_QUENCH */
-		ipv4_sk_redirect(skb, sk);
-		err = EREMOTEIO;
-		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		harderr = pingv6_ops.icmpv6_err_convert(type, code, &err);
+#endif
 	}
 
 	/*
 	 *      RFC1122: OK.  Passes ICMP errors back to application, as per
 	 *	4.1.3.3.
 	 */
-	if (!inet_sock->recverr) {
+	if ((family == AF_INET && !inet_sock->recverr) ||
+	    (family == AF_INET6 && !inet6_sk(sk)->recverr)) {
 		if (!harderr || sk->sk_state != TCP_ESTABLISHED)
 			goto out;
 	} else {
-		ip_icmp_error(sk, skb, err, 0 /* no remote port */,
-			 info, (u8 *)icmph);
+		if (family == AF_INET) {
+			ip_icmp_error(sk, skb, err, 0 /* no remote port */,
+				      info, (u8 *)icmph);
+#if IS_ENABLED(CONFIG_IPV6)
+		} else if (family == AF_INET6) {
+			pingv6_ops.ipv6_icmp_error(sk, skb, err, 0,
+						   info, (u8 *)icmph);
+#endif
+		}
 	}
 	sk->sk_err = err;
 	sk->sk_error_report(sk);
 out:
 	sock_put(sk);
 }
+EXPORT_SYMBOL_GPL(ping_err);
 
 /*
- *	Copy and checksum an ICMP Echo packet from user space into a buffer.
+ *	Copy and checksum an ICMP Echo packet from user space into a buffer
+ *	starting from the payload.
  */
 
-struct pingfakehdr {
-	struct icmphdr icmph;
-	struct iovec *iov;
-	__wsum wcheck;
-};
-
-static int ping_getfrag(void *from, char *to,
-			int offset, int fraglen, int odd, struct sk_buff *skb)
+int ping_getfrag(void *from, char *to,
+		 int offset, int fraglen, int odd, struct sk_buff *skb)
 {
 	struct pingfakehdr *pfh = (struct pingfakehdr *)from;
 
@@ -425,20 +588,33 @@ static int ping_getfrag(void *from, char *to,
 			    pfh->iov, 0, fraglen - sizeof(struct icmphdr),
 			    &pfh->wcheck))
 			return -EFAULT;
+	} else if (offset < sizeof(struct icmphdr)) {
+			BUG();
+	} else {
+		if (csum_partial_copy_fromiovecend
+				(to, pfh->iov, offset - sizeof(struct icmphdr),
+				 fraglen, &pfh->wcheck))
+			return -EFAULT;
+	}
 
-		return 0;
+#if IS_ENABLED(CONFIG_IPV6)
+	/* For IPv6, checksum each skb as we go along, as expected by
+	 * icmpv6_push_pending_frames. For IPv4, accumulate the checksum in
+	 * wcheck, it will be finalized in ping_v4_push_pending_frames.
+	 */
+	if (pfh->family == AF_INET6) {
+		skb->csum = pfh->wcheck;
+		skb->ip_summed = CHECKSUM_NONE;
+		pfh->wcheck = 0;
 	}
-	if (offset < sizeof(struct icmphdr))
-		BUG();
-	if (csum_partial_copy_fromiovecend
-			(to, pfh->iov, offset - sizeof(struct icmphdr),
-			 fraglen, &pfh->wcheck))
-		return -EFAULT;
+#endif
+
 	return 0;
 }
+EXPORT_SYMBOL_GPL(ping_getfrag);
 
-static int ping_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
-				    struct flowi4 *fl4)
+static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
+				       struct flowi4 *fl4)
 {
 	struct sk_buff *skb = skb_peek(&sk->sk_write_queue);
 
@@ -450,24 +626,9 @@ static int ping_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
 	return ip_push_pending_frames(sk, fl4);
 }
 
-static int ping_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-			size_t len)
-{
-	struct net *net = sock_net(sk);
-	struct flowi4 fl4;
-	struct inet_sock *inet = inet_sk(sk);
-	struct ipcm_cookie ipc;
-	struct icmphdr user_icmph;
-	struct pingfakehdr pfh;
-	struct rtable *rt = NULL;
-	struct ip_options_data opt_copy;
-	int free = 0;
-	__be32 saddr, daddr, faddr;
-	u8  tos;
-	int err;
-
-	pr_debug("ping_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
-
+int ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
+			void *user_icmph, size_t icmph_len) {
+	u8 type, code;
 
 	if (len > 0xFFFF)
 		return -EMSGSIZE;
@@ -482,15 +643,53 @@ static int ping_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	/*
 	 *	Fetch the ICMP header provided by the userland.
-	 *	iovec is modified!
+	 *	iovec is modified! The ICMP header is consumed.
 	 */
-
-	if (memcpy_fromiovec((u8 *)&user_icmph, msg->msg_iov,
-			     sizeof(struct icmphdr)))
+	if (memcpy_fromiovec(user_icmph, msg->msg_iov, icmph_len))
 		return -EFAULT;
-	if (!ping_supported(user_icmph.type, user_icmph.code))
+
+	if (family == AF_INET) {
+		type = ((struct icmphdr *) user_icmph)->type;
+		code = ((struct icmphdr *) user_icmph)->code;
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (family == AF_INET6) {
+		type = ((struct icmp6hdr *) user_icmph)->icmp6_type;
+		code = ((struct icmp6hdr *) user_icmph)->icmp6_code;
+#endif
+	} else {
+		BUG();
+	}
+
+	if (!ping_supported(family, type, code))
 		return -EINVAL;
 
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ping_common_sendmsg);
+
+int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+		    size_t len)
+{
+	struct net *net = sock_net(sk);
+	struct flowi4 fl4;
+	struct inet_sock *inet = inet_sk(sk);
+	struct ipcm_cookie ipc;
+	struct icmphdr user_icmph;
+	struct pingfakehdr pfh;
+	struct rtable *rt = NULL;
+	struct ip_options_data opt_copy;
+	int free = 0;
+	__be32 saddr, daddr, faddr;
+	u8  tos;
+	int err;
+
+	pr_debug("ping_v4_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
+
+	err = ping_common_sendmsg(AF_INET, msg, len, &user_icmph,
+				  sizeof(user_icmph));
+	if (err)
+		return err;
+
 	/*
 	 *	Get and verify the address.
 	 */
@@ -595,13 +794,14 @@ back_from_confirm:
 	pfh.icmph.un.echo.sequence = user_icmph.un.echo.sequence;
 	pfh.iov = msg->msg_iov;
 	pfh.wcheck = 0;
+	pfh.family = AF_INET;
 
 	err = ip_append_data(sk, &fl4, ping_getfrag, &pfh, len,
 			0, &ipc, &rt, msg->msg_flags);
 	if (err)
 		ip_flush_pending_frames(sk);
 	else
-		err = ping_push_pending_frames(sk, &pfh, &fl4);
+		err = ping_v4_push_pending_frames(sk, &pfh, &fl4);
 	release_sock(sk);
 
 out:
@@ -622,11 +822,13 @@ do_confirm:
 	goto out;
 }
 
-static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-			size_t len, int noblock, int flags, int *addr_len)
+int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+		 size_t len, int noblock, int flags, int *addr_len)
 {
 	struct inet_sock *isk = inet_sk(sk);
-	struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
+	int family = sk->sk_family;
+	struct sockaddr_in *sin;
+	struct sockaddr_in6 *sin6;
 	struct sk_buff *skb;
 	int copied, err;
 
@@ -636,11 +838,22 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	if (flags & MSG_OOB)
 		goto out;
 
-	if (addr_len)
-		*addr_len = sizeof(*sin);
+	if (addr_len) {
+		if (family == AF_INET)
+			*addr_len = sizeof(*sin);
+		else if (family == AF_INET6 && addr_len)
+			*addr_len = sizeof(*sin6);
+	}
 
-	if (flags & MSG_ERRQUEUE)
-		return ip_recv_error(sk, msg, len);
+	if (flags & MSG_ERRQUEUE) {
+		if (family == AF_INET) {
+			return ip_recv_error(sk, msg, len);
+#if IS_ENABLED(CONFIG_IPV6)
+		} else if (family == AF_INET6) {
+			return pingv6_ops.ipv6_recv_error(sk, msg, len);
+#endif
+		}
+	}
 
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb)
@@ -659,15 +872,40 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	sock_recv_timestamp(msg, sk, skb);
 
-	/* Copy the address. */
-	if (sin) {
+	/* Copy the address and add cmsg data. */
+	if (family == AF_INET) {
+		sin = (struct sockaddr_in *) msg->msg_name;
 		sin->sin_family = AF_INET;
 		sin->sin_port = 0 /* skb->h.uh->source */;
 		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
 		memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+
+		if (isk->cmsg_flags)
+			ip_cmsg_recv(msg, skb);
+
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (family == AF_INET6) {
+		struct ipv6_pinfo *np = inet6_sk(sk);
+		struct ipv6hdr *ip6 = ipv6_hdr(skb);
+		sin6 = (struct sockaddr_in6 *) msg->msg_name;
+		sin6->sin6_family = AF_INET6;
+		sin6->sin6_port = 0;
+		sin6->sin6_addr = ip6->saddr;
+
+		sin6->sin6_flowinfo = 0;
+		if (np->sndflow)
+			sin6->sin6_flowinfo = ip6_flowinfo(ip6);
+
+		sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr,
+							  IP6CB(skb)->iif);
+
+		if (inet6_sk(sk)->rxopt.all)
+			pingv6_ops.ip6_datagram_recv_ctl(sk, msg, skb);
+#endif
+	} else {
+		BUG();
 	}
-	if (isk->cmsg_flags)
-		ip_cmsg_recv(msg, skb);
+
 	err = copied;
 
 done:
@@ -676,8 +914,9 @@ out:
 	pr_debug("ping_recvmsg -> %d\n", err);
 	return err;
 }
+EXPORT_SYMBOL_GPL(ping_recvmsg);
 
-static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n",
 		 inet_sk(sk), inet_sk(sk)->inet_num, skb);
@@ -688,6 +927,7 @@ static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(ping_queue_rcv_skb);
 
 
 /*
@@ -698,10 +938,7 @@ void ping_rcv(struct sk_buff *skb)
 {
 	struct sock *sk;
 	struct net *net = dev_net(skb->dev);
-	struct iphdr *iph = ip_hdr(skb);
 	struct icmphdr *icmph = icmp_hdr(skb);
-	__be32 saddr = iph->saddr;
-	__be32 daddr = iph->daddr;
 
 	/* We assume the packet has already been checked by icmp_rcv */
 
@@ -711,8 +948,7 @@ void ping_rcv(struct sk_buff *skb)
 	/* Push ICMP header back */
 	skb_push(skb, skb->data - (u8 *)icmph);
 
-	sk = ping_v4_lookup(net, saddr, daddr, ntohs(icmph->un.echo.id),
-			    skb->dev->ifindex);
+	sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id));
 	if (sk != NULL) {
 		pr_debug("rcv on socket %p\n", sk);
 		ping_queue_rcv_skb(sk, skb_get(skb));
@@ -723,6 +959,7 @@ void ping_rcv(struct sk_buff *skb)
 
 	/* We're called from icmp_rcv(). kfree_skb() is done there. */
 }
+EXPORT_SYMBOL_GPL(ping_rcv);
 
 struct proto ping_prot = {
 	.name =		"PING",
@@ -733,14 +970,14 @@ struct proto ping_prot = {
 	.disconnect =	udp_disconnect,
 	.setsockopt =	ip_setsockopt,
 	.getsockopt =	ip_getsockopt,
-	.sendmsg =	ping_sendmsg,
+	.sendmsg =	ping_v4_sendmsg,
 	.recvmsg =	ping_recvmsg,
 	.bind =		ping_bind,
 	.backlog_rcv =	ping_queue_rcv_skb,
 	.release_cb =	ip4_datagram_release_cb,
-	.hash =		ping_v4_hash,
-	.unhash =	ping_v4_unhash,
-	.get_port =	ping_v4_get_port,
+	.hash =		ping_hash,
+	.unhash =	ping_unhash,
+	.get_port =	ping_get_port,
 	.obj_size =	sizeof(struct inet_sock),
 };
 EXPORT_SYMBOL(ping_prot);
@@ -764,7 +1001,8 @@ static struct sock *ping_get_first(struct seq_file *seq, int start)
 			continue;
 
 		sk_nulls_for_each(sk, node, hslot) {
-			if (net_eq(sock_net(sk), net))
+			if (net_eq(sock_net(sk), net) &&
+			    sk->sk_family == state->family)
 				goto found;
 		}
 	}
@@ -797,17 +1035,24 @@ static struct sock *ping_get_idx(struct seq_file *seq, loff_t pos)
 	return pos ? NULL : sk;
 }
 
-static void *ping_seq_start(struct seq_file *seq, loff_t *pos)
+void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family)
 {
 	struct ping_iter_state *state = seq->private;
 	state->bucket = 0;
+	state->family = family;
 
 	read_lock_bh(&ping_table.lock);
 
 	return *pos ? ping_get_idx(seq, *pos-1) : SEQ_START_TOKEN;
 }
+EXPORT_SYMBOL_GPL(ping_seq_start);
+
+static void *ping_v4_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	return ping_seq_start(seq, pos, AF_INET);
+}
 
-static void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct sock *sk;
 
@@ -819,13 +1064,15 @@ static void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	++*pos;
 	return sk;
 }
+EXPORT_SYMBOL_GPL(ping_seq_next);
 
-static void ping_seq_stop(struct seq_file *seq, void *v)
+void ping_seq_stop(struct seq_file *seq, void *v)
 {
 	read_unlock_bh(&ping_table.lock);
 }
+EXPORT_SYMBOL_GPL(ping_seq_stop);
 
-static void ping_format_sock(struct sock *sp, struct seq_file *f,
+static void ping_v4_format_sock(struct sock *sp, struct seq_file *f,
 		int bucket, int *len)
 {
 	struct inet_sock *inet = inet_sk(sp);
@@ -846,7 +1093,7 @@ static void ping_format_sock(struct sock *sp, struct seq_file *f,
 		atomic_read(&sp->sk_drops), len);
 }
 
-static int ping_seq_show(struct seq_file *seq, void *v)
+static int ping_v4_seq_show(struct seq_file *seq, void *v)
 {
 	if (v == SEQ_START_TOKEN)
 		seq_printf(seq, "%-127s\n",
@@ -857,72 +1104,86 @@ static int ping_seq_show(struct seq_file *seq, void *v)
 		struct ping_iter_state *state = seq->private;
 		int len;
 
-		ping_format_sock(v, seq, state->bucket, &len);
+		ping_v4_format_sock(v, seq, state->bucket, &len);
 		seq_printf(seq, "%*s\n", 127 - len, "");
 	}
 	return 0;
 }
 
-static const struct seq_operations ping_seq_ops = {
-	.show		= ping_seq_show,
-	.start		= ping_seq_start,
+static const struct seq_operations ping_v4_seq_ops = {
+	.show		= ping_v4_seq_show,
+	.start		= ping_v4_seq_start,
 	.next		= ping_seq_next,
 	.stop		= ping_seq_stop,
 };
 
 static int ping_seq_open(struct inode *inode, struct file *file)
 {
-	return seq_open_net(inode, file, &ping_seq_ops,
+	struct ping_seq_afinfo *afinfo = PDE_DATA(inode);
+	return seq_open_net(inode, file, &afinfo->seq_ops,
 			   sizeof(struct ping_iter_state));
 }
 
-static const struct file_operations ping_seq_fops = {
+const struct file_operations ping_seq_fops = {
 	.open		= ping_seq_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release_net,
 };
+EXPORT_SYMBOL_GPL(ping_seq_fops);
+
+static struct ping_seq_afinfo ping_v4_seq_afinfo = {
+	.name		= "icmp",
+	.family		= AF_INET,
+	.seq_fops	= &ping_seq_fops,
+	.seq_ops	= {
+		.start		= ping_v4_seq_start,
+		.show		= ping_v4_seq_show,
+		.next		= ping_seq_next,
+		.stop		= ping_seq_stop,
+	},
+};
 
-static int ping_proc_register(struct net *net)
+int ping_proc_register(struct net *net, struct ping_seq_afinfo *afinfo)
 {
 	struct proc_dir_entry *p;
-	int rc = 0;
-
-	p = proc_create("icmp", S_IRUGO, net->proc_net, &ping_seq_fops);
+	p = proc_create_data(afinfo->name, S_IRUGO, net->proc_net,
+			     afinfo->seq_fops, afinfo);
 	if (!p)
-		rc = -ENOMEM;
-	return rc;
+		return -ENOMEM;
+	return 0;
 }
+EXPORT_SYMBOL_GPL(ping_proc_register);
 
-static void ping_proc_unregister(struct net *net)
+void ping_proc_unregister(struct net *net, struct ping_seq_afinfo *afinfo)
 {
-	remove_proc_entry("icmp", net->proc_net);
+	remove_proc_entry(afinfo->name, net->proc_net);
 }
+EXPORT_SYMBOL_GPL(ping_proc_unregister);
 
-
-static int __net_init ping_proc_init_net(struct net *net)
+static int __net_init ping_v4_proc_init_net(struct net *net)
 {
-	return ping_proc_register(net);
+	return ping_proc_register(net, &ping_v4_seq_afinfo);
 }
 
-static void __net_exit ping_proc_exit_net(struct net *net)
+static void __net_exit ping_v4_proc_exit_net(struct net *net)
 {
-	ping_proc_unregister(net);
+	ping_proc_unregister(net, &ping_v4_seq_afinfo);
 }
 
-static struct pernet_operations ping_net_ops = {
-	.init = ping_proc_init_net,
-	.exit = ping_proc_exit_net,
+static struct pernet_operations ping_v4_net_ops = {
+	.init = ping_v4_proc_init_net,
+	.exit = ping_v4_proc_exit_net,
 };
 
 int __init ping_proc_init(void)
 {
-	return register_pernet_subsys(&ping_net_ops);
+	return register_pernet_subsys(&ping_v4_net_ops);
 }
 
 void ping_proc_exit(void)
 {
-	unregister_pernet_subsys(&ping_net_ops);
+	unregister_pernet_subsys(&ping_v4_net_ops);
 }
 
 #endif