net: ipv6: Add IPv6 support to the ping socket.

This adds the ability to send ICMPv6 echo requests without a
raw socket. The equivalent ability for ICMPv4 was added in
2011.

Instead of having separate code paths for IPv4 and IPv6, make
most of the code in net/ipv4/ping.c dual-stack and only add a
few IPv6-specific bits (like the protocol definition) to a new
net/ipv6/ping.c. Hopefully this will reduce divergence and/or
duplication of bugs in the future.

Caveats:

- Setting options via ancillary data (e.g., using IPV6_PKTINFO
  to specify the outgoing interface) is not yet supported.
- There are no separate security settings for IPv4 and IPv6;
  everything is controlled by /proc/net/ipv4/ping_group_range.
- The proc interface does not yet display IPv6 ping sockets
  properly.

Tested with a patched copy of ping6 and using raw socket calls.
Compiles and works with all of CONFIG_IPV6={n,m,y}.
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/ipv6.h

@@ -260,6 +260,12 @@ static inline void fl6_sock_release(struct ip6_flowlabel *fl)
 
 extern void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info);
 
+int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
+			       struct icmp6hdr *thdr, int len);
+
+struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb,
+				      struct sock *sk, struct flowi6 *fl6);
+
 extern int 			ip6_ra_control(struct sock *sk, int sel);
 
 extern int			ipv6_parse_hopopts(struct sk_buff *skb);

include/net/ping.h

@@ -13,6 +13,7 @@
 #ifndef _PING_H
 #define _PING_H
 
+#include <net/icmp.h>
 #include <net/netns/hash.h>
 
 /* PING_HTABLE_SIZE must be power of 2 */
@@ -28,6 +29,18 @@
  */
 #define GID_T_MAX (((gid_t)~0U) >> 1)
 
+/* Compatibility glue so we can support IPv6 when it's compiled as a module */
+struct pingv6_ops {
+	int (*ipv6_recv_error)(struct sock *sk, struct msghdr *msg, int len);
+	int (*ip6_datagram_recv_ctl)(struct sock *sk, struct msghdr *msg,
+				     struct sk_buff *skb);
+	int (*icmpv6_err_convert)(u8 type, u8 code, int *err);
+	void (*ipv6_icmp_error)(struct sock *sk, struct sk_buff *skb, int err,
+				__be16 port, u32 info, u8 *payload);
+	int (*ipv6_chk_addr)(struct net *net, const struct in6_addr *addr,
+			     struct net_device *dev, int strict);
+};
+
 struct ping_table {
 	struct hlist_nulls_head	hash[PING_HTABLE_SIZE];
 	rwlock_t		lock;
@@ -39,10 +52,39 @@ struct ping_iter_state {
 };
 
 extern struct proto ping_prot;
+extern struct ping_table ping_table;
+#if IS_ENABLED(CONFIG_IPV6)
+extern struct pingv6_ops pingv6_ops;
+#endif
 
+struct pingfakehdr {
+	struct icmphdr icmph;
+	struct iovec *iov;
+	sa_family_t family;
+	__wsum wcheck;
+};
 
-extern void ping_rcv(struct sk_buff *);
-extern void ping_err(struct sk_buff *, u32 info);
+int  ping_get_port(struct sock *sk, unsigned short ident);
+void ping_hash(struct sock *sk);
+void ping_unhash(struct sock *sk);
+
+int  ping_init_sock(struct sock *sk);
+void ping_close(struct sock *sk, long timeout);
+int  ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len);
+void ping_err(struct sk_buff *skb, int offset, u32 info);
+int  ping_getfrag(void *from, char *to, int offset, int fraglen, int odd,
+		  struct sk_buff *);
+
+int  ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+		  size_t len, int noblock, int flags, int *addr_len);
+int  ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
+			 void *user_icmph, size_t icmph_len);
+int  ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+		     size_t len);
+int  ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+		     size_t len);
+int  ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+void ping_rcv(struct sk_buff *skb);
 
 #ifdef CONFIG_PROC_FS
 extern int __init ping_proc_init(void);
@@ -50,6 +92,7 @@ extern void ping_proc_exit(void);
 #endif
 
 void __init ping_init(void);
-
+int  __init pingv6_init(void);
+void pingv6_exit(void);
 
 #endif /* _PING_H */

include/net/transp_v6.h

@@ -11,6 +11,7 @@ extern struct proto rawv6_prot;
 extern struct proto udpv6_prot;
 extern struct proto udplitev6_prot;
 extern struct proto tcpv6_prot;
+extern struct proto pingv6_prot;
 
 struct flowi6;
 
@@ -21,6 +22,8 @@ extern int				ipv6_frag_init(void);
 extern void				ipv6_frag_exit(void);
 
 /* transport protocols */
+extern int				pingv6_init(void);
+extern void				pingv6_exit(void);
 extern int				rawv6_init(void);
 extern void				rawv6_exit(void);
 extern int				udpv6_init(void);

net/ipv4/icmp.c

@@ -939,7 +939,8 @@ int icmp_rcv(struct sk_buff *skb)
 void icmp_err(struct sk_buff *skb, u32 info)
 {
 	struct iphdr *iph = (struct iphdr *)skb->data;
-	struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2));
+	int offset = iph->ihl<<2;
+	struct icmphdr *icmph = (struct icmphdr *)(skb->data + offset);
 	int type = icmp_hdr(skb)->type;
 	int code = icmp_hdr(skb)->code;
 	struct net *net = dev_net(skb->dev);
@@ -949,7 +950,7 @@ void icmp_err(struct sk_buff *skb, u32 info)
 	 * triggered by ICMP_ECHOREPLY which sent from kernel.
 	 */
 	if (icmph->type != ICMP_ECHOREPLY) {
-		ping_err(skb, info);
+		ping_err(skb, offset, info);
 		return;
 	}
 

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 @@ static int ping_v4_get_port(struct sock *sk, unsigned short ident)
 		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 @@ static int ping_v4_get_port(struct sock *sk, unsigned short ident)
 	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. */
+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;
+}
 
+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
+	}
+}
+
+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 @@ static int ping_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	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 @@ static int ping_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	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;
+
+		if (np->sndflow)
+			sin6->sin6_flowinfo = ip6_flowinfo(ip6);
+
+		if (__ipv6_addr_needs_scope_id(
+		    ipv6_addr_type(&sin6->sin6_addr)))
+			sin6->sin6_scope_id = 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 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	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);

net/ipv6/Makefile

@@ -7,7 +7,7 @@ obj-$(CONFIG_IPV6) += ipv6.o
 ipv6-objs :=	af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \
 		addrlabel.o \
 		route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \
-		raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o \
+		raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \
 		exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o
 
 ipv6-offload :=	ip6_offload.o tcpv6_offload.o udp_offload.o exthdrs_offload.o

net/ipv6/af_inet6.c

@@ -49,6 +49,7 @@
 #include <net/udp.h>
 #include <net/udplite.h>
 #include <net/tcp.h>
+#include <net/ping.h>
 #include <net/protocol.h>
 #include <net/inet_common.h>
 #include <net/route.h>
@@ -840,6 +841,9 @@ static int __init inet6_init(void)
 	if (err)
 		goto out_unregister_udplite_proto;
 
+	err = proto_register(&pingv6_prot, 1);
+	if (err)
+		goto out_unregister_ping_proto;
 
 	/* We MUST register RAW sockets before we create the ICMP6,
 	 * IGMP6, or NDISC control sockets.
@@ -930,6 +934,10 @@ static int __init inet6_init(void)
 	if (err)
 		goto ipv6_packet_fail;
 
+	err = pingv6_init();
+	if (err)
+		goto pingv6_fail;
+
 #ifdef CONFIG_SYSCTL
 	err = ipv6_sysctl_register();
 	if (err)
@@ -942,6 +950,8 @@ static int __init inet6_init(void)
 sysctl_fail:
 	ipv6_packet_cleanup();
 #endif
+pingv6_fail:
+	pingv6_exit();
 ipv6_packet_fail:
 	tcpv6_exit();
 tcpv6_fail:
@@ -985,6 +995,8 @@ static int __init inet6_init(void)
 	rtnl_unregister_all(PF_INET6);
 out_sock_register_fail:
 	rawv6_exit();
+out_unregister_ping_proto:
+	proto_unregister(&pingv6_prot);
 out_unregister_raw_proto:
 	proto_unregister(&rawv6_prot);
 out_unregister_udplite_proto:

net/ipv6/icmp.c

@@ -57,6 +57,7 @@
 
 #include <net/ipv6.h>
 #include <net/ip6_checksum.h>
+#include <net/ping.h>
 #include <net/protocol.h>
 #include <net/raw.h>
 #include <net/rawv6.h>
@@ -84,12 +85,18 @@ static inline struct sock *icmpv6_sk(struct net *net)
 static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		       u8 type, u8 code, int offset, __be32 info)
 {
+	/* icmpv6_notify checks 8 bytes can be pulled, icmp6hdr is 8 bytes */
+	struct icmp6hdr *icmp6 = (struct icmp6hdr *) (skb->data + offset);
 	struct net *net = dev_net(skb->dev);
 
 	if (type == ICMPV6_PKT_TOOBIG)
 		ip6_update_pmtu(skb, net, info, 0, 0);
 	else if (type == NDISC_REDIRECT)
 		ip6_redirect(skb, net, 0, 0);
+
+	if (!(type & ICMPV6_INFOMSG_MASK))
+		if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST)
+			ping_err(skb, offset, info);
 }
 
 static int icmpv6_rcv(struct sk_buff *skb);
@@ -224,7 +231,8 @@ static bool opt_unrec(struct sk_buff *skb, __u32 offset)
 	return (*op & 0xC0) == 0x80;
 }
 
-static int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct icmp6hdr *thdr, int len)
+int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
+			       struct icmp6hdr *thdr, int len)
 {
 	struct sk_buff *skb;
 	struct icmp6hdr *icmp6h;
@@ -307,8 +315,8 @@ static void mip6_addr_swap(struct sk_buff *skb)
 static inline void mip6_addr_swap(struct sk_buff *skb) {}
 #endif
 
-static struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb,
-					     struct sock *sk, struct flowi6 *fl6)
+struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb,
+				      struct sock *sk, struct flowi6 *fl6)
 {
 	struct dst_entry *dst, *dst2;
 	struct flowi6 fl2;
@@ -697,7 +705,8 @@ static int icmpv6_rcv(struct sk_buff *skb)
 		skb->csum = ~csum_unfold(csum_ipv6_magic(saddr, daddr, skb->len,
 					     IPPROTO_ICMPV6, 0));
 		if (__skb_checksum_complete(skb)) {
-			LIMIT_NETDEBUG(KERN_DEBUG "ICMPv6 checksum failed [%pI6 > %pI6]\n",
+			LIMIT_NETDEBUG(KERN_DEBUG
+				       "ICMPv6 checksum failed [%pI6c > %pI6c]\n",
 				       saddr, daddr);
 			goto csum_error;
 		}
@@ -718,7 +727,7 @@ static int icmpv6_rcv(struct sk_buff *skb)
 		break;
 
 	case ICMPV6_ECHO_REPLY:
-		/* we couldn't care less */
+		ping_rcv(skb);
 		break;
 
 	case ICMPV6_PKT_TOOBIG:

net/ipv6/ping.c

+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		"Ping" sockets
+ *
+ *		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.
+ *
+ * Based on ipv4/ping.c code.
+ *
+ * Authors:	Lorenzo Colitti (IPv6 support)
+ *		Vasiliy Kulikov / Openwall (IPv4 implementation, for Linux 2.6),
+ *		Pavel Kankovsky (IPv4 implementation, for Linux 2.4.32)
+ *
+ */
+
+#include <net/addrconf.h>
+#include <net/ipv6.h>
+#include <net/ip6_route.h>
+#include <net/protocol.h>
+#include <net/udp.h>
+#include <net/transp_v6.h>
+#include <net/ping.h>
+
+struct proto pingv6_prot = {
+	.name =		"PINGv6",
+	.owner =	THIS_MODULE,
+	.init =		ping_init_sock,
+	.close =	ping_close,
+	.connect =	ip6_datagram_connect,
+	.disconnect =	udp_disconnect,
+	.setsockopt =	ipv6_setsockopt,
+	.getsockopt =	ipv6_getsockopt,
+	.sendmsg =	ping_v6_sendmsg,
+	.recvmsg =	ping_recvmsg,
+	.bind =		ping_bind,
+	.backlog_rcv =	ping_queue_rcv_skb,
+	.hash =		ping_hash,
+	.unhash =	ping_unhash,
+	.get_port =	ping_get_port,
+	.obj_size =	sizeof(struct raw6_sock),
+};
+EXPORT_SYMBOL_GPL(pingv6_prot);
+
+static struct inet_protosw pingv6_protosw = {
+	.type =      SOCK_DGRAM,
+	.protocol =  IPPROTO_ICMPV6,
+	.prot =      &pingv6_prot,
+	.ops =       &inet6_dgram_ops,
+	.no_check =  UDP_CSUM_DEFAULT,
+	.flags =     INET_PROTOSW_REUSE,
+};
+
+
+/* Compatibility glue so we can support IPv6 when it's compiled as a module */
+int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
+{
+	return -EAFNOSUPPORT;
+}
+int dummy_ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
+				 struct sk_buff *skb)
+{
+	return -EAFNOSUPPORT;
+}
+int dummy_icmpv6_err_convert(u8 type, u8 code, int *err)
+{
+	return -EAFNOSUPPORT;
+}
+void dummy_ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
+			    __be16 port, u32 info, u8 *payload) {}
+int dummy_ipv6_chk_addr(struct net *net, const struct in6_addr *addr,
+			struct net_device *dev, int strict)
+{
+	return 0;
+}
+
+int __init pingv6_init(void)
+{
+	pingv6_ops.ipv6_recv_error = ipv6_recv_error;
+	pingv6_ops.ip6_datagram_recv_ctl = ip6_datagram_recv_ctl;
+	pingv6_ops.icmpv6_err_convert = icmpv6_err_convert;
+	pingv6_ops.ipv6_icmp_error = ipv6_icmp_error;
+	pingv6_ops.ipv6_chk_addr = ipv6_chk_addr;
+	return inet6_register_protosw(&pingv6_protosw);
+}
+
+/* This never gets called because it's not possible to unload the ipv6 module,
+ * but just in case.
+ */
+void pingv6_exit(void)
+{
+	pingv6_ops.ipv6_recv_error = dummy_ipv6_recv_error;
+	pingv6_ops.ip6_datagram_recv_ctl = dummy_ip6_datagram_recv_ctl;
+	pingv6_ops.icmpv6_err_convert = dummy_icmpv6_err_convert;
+	pingv6_ops.ipv6_icmp_error = dummy_ipv6_icmp_error;
+	pingv6_ops.ipv6_chk_addr = dummy_ipv6_chk_addr;
+	inet6_unregister_protosw(&pingv6_protosw);
+}
+
+int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+		    size_t len)
+{
+	struct inet_sock *inet = inet_sk(sk);
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct icmp6hdr user_icmph;
+	int addr_type;
+	struct in6_addr *daddr;
+	int iif = 0;
+	struct flowi6 fl6;
+	int err;
+	int hlimit;
+	struct dst_entry *dst;
+	struct rt6_info *rt;
+	struct pingfakehdr pfh;
+
+	pr_debug("ping_v6_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
+
+	err = ping_common_sendmsg(AF_INET6, msg, len, &user_icmph,
+				  sizeof(user_icmph));
+	if (err)
+		return err;
+
+	if (msg->msg_name) {
+		struct sockaddr_in6 *u = (struct sockaddr_in6 *) msg->msg_name;
+		if (msg->msg_namelen < sizeof(struct sockaddr_in6) ||
+		    u->sin6_family != AF_INET6) {
+			return -EINVAL;
+		}
+		if (sk->sk_bound_dev_if &&
+		    sk->sk_bound_dev_if != u->sin6_scope_id) {
+			return -EINVAL;
+		}
+		daddr = &(u->sin6_addr);
+		iif = u->sin6_scope_id;
+	} else {
+		if (sk->sk_state != TCP_ESTABLISHED)
+			return -EDESTADDRREQ;
+		daddr = &np->daddr;
+	}
+
+	if (!iif)
+		iif = sk->sk_bound_dev_if;
+
+	addr_type = ipv6_addr_type(daddr);
+	if (__ipv6_addr_needs_scope_id(addr_type) && !iif)
+		return -EINVAL;
+	if (addr_type & IPV6_ADDR_MAPPED)
+		return -EINVAL;
+
+	/* TODO: use ip6_datagram_send_ctl to get options from cmsg */
+
+	memset(&fl6, 0, sizeof(fl6));
+
+	fl6.flowi6_proto = IPPROTO_ICMPV6;
+	fl6.saddr = np->saddr;
+	fl6.daddr = *daddr;
+	fl6.fl6_icmp_type = user_icmph.icmp6_type;
+	fl6.fl6_icmp_code = user_icmph.icmp6_code;
+	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+
+	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
+		fl6.flowi6_oif = np->mcast_oif;
+	else if (!fl6.flowi6_oif)
+		fl6.flowi6_oif = np->ucast_oif;
+
+	dst = ip6_sk_dst_lookup_flow(sk, &fl6,  daddr, 1);
+	if (IS_ERR(dst))
+		return PTR_ERR(dst);
+	rt = (struct rt6_info *) dst;
+
+	np = inet6_sk(sk);
+	if (!np)
+		return -EBADF;
+
+	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
+		fl6.flowi6_oif = np->mcast_oif;
+	else if (!fl6.flowi6_oif)
+		fl6.flowi6_oif = np->ucast_oif;
+
+	pfh.icmph.type = user_icmph.icmp6_type;
+	pfh.icmph.code = user_icmph.icmp6_code;
+	pfh.icmph.checksum = 0;
+	pfh.icmph.un.echo.id = inet->inet_sport;
+	pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence;
+	pfh.iov = msg->msg_iov;
+	pfh.wcheck = 0;
+	pfh.family = AF_INET6;
+
+	if (ipv6_addr_is_multicast(&fl6.daddr))
+		hlimit = np->mcast_hops;
+	else
+		hlimit = np->hop_limit;
+	if (hlimit < 0)
+		hlimit = ip6_dst_hoplimit(dst);
+
+	err = ip6_append_data(sk, ping_getfrag, &pfh, len,
+			      0, hlimit,
+			      np->tclass, NULL, &fl6, rt,
+			      MSG_DONTWAIT, np->dontfrag);
+
+	if (err) {
+		ICMP6_INC_STATS_BH(sock_net(sk), rt->rt6i_idev,
+				   ICMP6_MIB_OUTERRORS);
+		ip6_flush_pending_frames(sk);
+	} else {
+		err = icmpv6_push_pending_frames(sk, &fl6,
+						 (struct icmp6hdr *) &pfh.icmph,
+						 len);
+	}
+
+	return err;
+}