net: ip, diag -- Add diag interface for raw sockets

In criu we are actively using diag interface to collect sockets
present in the system when dumping applications. And while for
unix, tcp, udp[lite], packet, netlink it works as expected,
the raw sockets do not have. Thus add it.

v2:
 - add missing sock_put calls in raw_diag_dump_one (by eric.dumazet@)
 - implement @destroy for diag requests (by dsa@)

v3:
 - add export of raw_abort for IPv6 (by dsa@)
 - pass net-admin flag into inet_sk_diag_fill due to
   changes in net-next branch (by dsa@)

v4:
 - use @pad in struct inet_diag_req_v2 for raw socket
   protocol specification: raw module carries sockets
   which may have custom protocol passed from socket()
   syscall and sole @sdiag_protocol is not enough to
   match underlied ones
 - start reporting protocol specifed in socket() call
   when sockets are raw ones for the same reason: user
   space tools like ss may parse this attribute and use
   it for socket matching

v5 (by eric.dumazet@):
 - use sock_hold in raw_sock_get instead of atomic_inc,
   we're holding (raw_v4_hashinfo|raw_v6_hashinfo)->lock
   when looking up so counter won't be zero here.

v6:
 - use sdiag_raw_protocol() helper which will access @pad
   structure used for raw sockets protocol specification:
   we can't simply rename this member without breaking uapi

v7:
 - sine sdiag_raw_protocol() helper is not suitable for
   uapi lets rather make an alias structure with proper
   names. __check_inet_diag_req_raw helper will catch
   if any of structure unintentionally changed.

CC: David S. Miller <davem@davemloft.net>
CC: Eric Dumazet <eric.dumazet@gmail.com>
CC: David Ahern <dsa@cumulusnetworks.com>
CC: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
CC: James Morris <jmorris@namei.org>
CC: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
CC: Patrick McHardy <kaber@trash.net>
CC: Andrey Vagin <avagin@openvz.org>
CC: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/raw.h

@@ -23,6 +23,12 @@
 
 extern struct proto raw_prot;
 
+extern struct raw_hashinfo raw_v4_hashinfo;
+struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
+			     unsigned short num, __be32 raddr,
+			     __be32 laddr, int dif);
+
+int raw_abort(struct sock *sk, int err);
 void raw_icmp_error(struct sk_buff *, int, u32);
 int raw_local_deliver(struct sk_buff *, int);
 

include/net/rawv6.h

@@ -3,6 +3,13 @@
 
 #include <net/protocol.h>
 
+extern struct raw_hashinfo raw_v6_hashinfo;
+struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
+			     unsigned short num, const struct in6_addr *loc_addr,
+			     const struct in6_addr *rmt_addr, int dif);
+
+int raw_abort(struct sock *sk, int err);
+
 void raw6_icmp_error(struct sk_buff *, int nexthdr,
 		u8 type, u8 code, int inner_offset, __be32);
 bool raw6_local_deliver(struct sk_buff *, int);

include/uapi/linux/inet_diag.h

@@ -43,6 +43,23 @@ struct inet_diag_req_v2 {
 	struct inet_diag_sockid id;
 };
 
+/*
+ * SOCK_RAW sockets require the underlied protocol to be
+ * additionally specified so we can use @pad member for
+ * this, but we can't rename it because userspace programs
+ * still may depend on this name. Instead lets use another
+ * structure definition as an alias for struct
+ * @inet_diag_req_v2.
+ */
+struct inet_diag_req_raw {
+	__u8	sdiag_family;
+	__u8	sdiag_protocol;
+	__u8	idiag_ext;
+	__u8	sdiag_raw_protocol;
+	__u32	idiag_states;
+	struct inet_diag_sockid id;
+};
+
 enum {
 	INET_DIAG_REQ_NONE,
 	INET_DIAG_REQ_BYTECODE,

net/ipv4/Kconfig

@@ -430,6 +430,14 @@ config INET_UDP_DIAG
 	  Support for UDP socket monitoring interface used by the ss tool.
 	  If unsure, say Y.
 
+config INET_RAW_DIAG
+	tristate "RAW: socket monitoring interface"
+	depends on INET_DIAG && (IPV6 || IPV6=n)
+	default n
+	---help---
+	  Support for RAW socket monitoring interface used by the ss tool.
+	  If unsure, say Y.
+
 config INET_DIAG_DESTROY
 	bool "INET: allow privileged process to administratively close sockets"
 	depends on INET_DIAG

net/ipv4/Makefile

@@ -40,6 +40,7 @@ obj-$(CONFIG_NETFILTER)	+= netfilter.o netfilter/
 obj-$(CONFIG_INET_DIAG) += inet_diag.o 
 obj-$(CONFIG_INET_TCP_DIAG) += tcp_diag.o
 obj-$(CONFIG_INET_UDP_DIAG) += udp_diag.o
+obj-$(CONFIG_INET_RAW_DIAG) += raw_diag.o
 obj-$(CONFIG_NET_TCPPROBE) += tcp_probe.o
 obj-$(CONFIG_TCP_CONG_BBR) += tcp_bbr.o
 obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o

net/ipv4/inet_diag.c

@@ -200,6 +200,15 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 		if (sock_diag_put_meminfo(sk, skb, INET_DIAG_SKMEMINFO))
 			goto errout;
 
+	/*
+	 * RAW sockets might have user-defined protocols assigned,
+	 * so report the one supplied on socket creation.
+	 */
+	if (sk->sk_type == SOCK_RAW) {
+		if (nla_put_u8(skb, INET_DIAG_PROTOCOL, sk->sk_protocol))
+			goto errout;
+	}
+
 	if (!icsk) {
 		handler->idiag_get_info(sk, r, NULL);
 		goto out;

net/ipv4/raw.c

@@ -89,9 +89,10 @@ struct raw_frag_vec {
 	int hlen;
 };
 
-static struct raw_hashinfo raw_v4_hashinfo = {
+struct raw_hashinfo raw_v4_hashinfo = {
 	.lock = __RW_LOCK_UNLOCKED(raw_v4_hashinfo.lock),
 };
+EXPORT_SYMBOL_GPL(raw_v4_hashinfo);
 
 int raw_hash_sk(struct sock *sk)
 {
@@ -120,7 +121,7 @@ void raw_unhash_sk(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(raw_unhash_sk);
 
-static struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
+struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
 		unsigned short num, __be32 raddr, __be32 laddr, int dif)
 {
 	sk_for_each_from(sk) {
@@ -136,6 +137,7 @@ static struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
 found:
 	return sk;
 }
+EXPORT_SYMBOL_GPL(__raw_v4_lookup);
 
 /*
  *	0 - deliver
@@ -912,6 +914,20 @@ static int compat_raw_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg
 }
 #endif
 
+int raw_abort(struct sock *sk, int err)
+{
+	lock_sock(sk);
+
+	sk->sk_err = err;
+	sk->sk_error_report(sk);
+	udp_disconnect(sk, 0);
+
+	release_sock(sk);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(raw_abort);
+
 struct proto raw_prot = {
 	.name		   = "RAW",
 	.owner		   = THIS_MODULE,
@@ -937,6 +953,7 @@ struct proto raw_prot = {
 	.compat_getsockopt = compat_raw_getsockopt,
 	.compat_ioctl	   = compat_raw_ioctl,
 #endif
+	.diag_destroy	   = raw_abort,
 };
 
 #ifdef CONFIG_PROC_FS