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/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;
+}