tcp: Dump bound-only sockets in inet_diag.

Walk the hashinfo->bhash2 table so that inet_diag can dump TCP sockets
that are bound but haven't yet called connect() or listen().

The code is inspired by the ->lhash2 loop. However there's no manual
test of the source port, since this kind of filtering is already
handled by inet_diag_bc_sk(). Also, a maximum of 16 sockets are dumped
at a time, to avoid running with bh disabled for too long.

There's no TCP state for bound but otherwise inactive sockets. Such
sockets normally map to TCP_CLOSE. However, "ss -l", which is supposed
to only dump listening sockets, actually requests the kernel to dump
sockets in either the TCP_LISTEN or TCP_CLOSE states. To avoid dumping
bound-only sockets with "ss -l", we therefore need to define a new
pseudo-state (TCP_BOUND_INACTIVE) that user space will be able to set
explicitly.

With an IPv4, an IPv6 and an IPv6-only socket, bound respectively to
40000, 64000, 60000, an updated version of iproute2 could work as
follow:

  $ ss -t state bound-inactive
  Recv-Q   Send-Q     Local Address:Port       Peer Address:Port   Process
  0        0                0.0.0.0:40000           0.0.0.0:*
  0        0                   [::]:60000              [::]:*
  0        0                      *:64000                 *:*

Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/b3a84ae61e19c06806eea9c602b3b66e8f0cfc81.1701362867.git.gnault@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/net/tcp_states.h

@@ -22,6 +22,7 @@ enum {
 	TCP_LISTEN,
 	TCP_CLOSING,	/* Now a valid state */
 	TCP_NEW_SYN_RECV,
+	TCP_BOUND_INACTIVE, /* Pseudo-state for inet_diag */
 
 	TCP_MAX_STATES	/* Leave at the end! */
 };
@@ -43,6 +44,7 @@ enum {
 	TCPF_LISTEN	 = (1 << TCP_LISTEN),
 	TCPF_CLOSING	 = (1 << TCP_CLOSING),
 	TCPF_NEW_SYN_RECV = (1 << TCP_NEW_SYN_RECV),
+	TCPF_BOUND_INACTIVE = (1 << TCP_BOUND_INACTIVE),
 };
 
 #endif	/* _LINUX_TCP_STATES_H */

include/uapi/linux/bpf.h

@@ -6902,6 +6902,7 @@ enum {
 	BPF_TCP_LISTEN,
 	BPF_TCP_CLOSING,	/* Now a valid state */
 	BPF_TCP_NEW_SYN_RECV,
+	BPF_TCP_BOUND_INACTIVE,
 
 	BPF_TCP_MAX_STATES	/* Leave at the end! */
 };

net/ipv4/inet_diag.c

@@ -1077,10 +1077,94 @@ skip_listen_ht:
 		s_i = num = s_num = 0;
 	}
 
+/* Process a maximum of SKARR_SZ sockets at a time when walking hash buckets
+ * with bh disabled.
+ */
+#define SKARR_SZ 16
+
+	/* Dump bound but inactive (not listening, connecting, etc.) sockets */
+	if (cb->args[0] == 1) {
+		if (!(idiag_states & TCPF_BOUND_INACTIVE))
+			goto skip_bind_ht;
+
+		for (i = s_i; i < hashinfo->bhash_size; i++) {
+			struct inet_bind_hashbucket *ibb;
+			struct inet_bind2_bucket *tb2;
+			struct sock *sk_arr[SKARR_SZ];
+			int num_arr[SKARR_SZ];
+			int idx, accum, res;
+
+resume_bind_walk:
+			num = 0;
+			accum = 0;
+			ibb = &hashinfo->bhash2[i];
+
+			spin_lock_bh(&ibb->lock);
+			inet_bind_bucket_for_each(tb2, &ibb->chain) {
+				if (!net_eq(ib2_net(tb2), net))
+					continue;
+
+				sk_for_each_bound_bhash2(sk, &tb2->owners) {
+					struct inet_sock *inet = inet_sk(sk);
+
+					if (num < s_num)
+						goto next_bind;
+
+					if (sk->sk_state != TCP_CLOSE ||
+					    !inet->inet_num)
+						goto next_bind;
+
+					if (r->sdiag_family != AF_UNSPEC &&
+					    r->sdiag_family != sk->sk_family)
+						goto next_bind;
+
+					if (!inet_diag_bc_sk(bc, sk))
+						goto next_bind;
+
+					sock_hold(sk);
+					num_arr[accum] = num;
+					sk_arr[accum] = sk;
+					if (++accum == SKARR_SZ)
+						goto pause_bind_walk;
+next_bind:
+					num++;
+				}
+			}
+pause_bind_walk:
+			spin_unlock_bh(&ibb->lock);
+
+			res = 0;
+			for (idx = 0; idx < accum; idx++) {
+				if (res >= 0) {
+					res = inet_sk_diag_fill(sk_arr[idx],
+								NULL, skb, cb,
+								r, NLM_F_MULTI,
+								net_admin);
+					if (res < 0)
+						num = num_arr[idx];
+				}
+				sock_put(sk_arr[idx]);
+			}
+			if (res < 0)
+				goto done;
+
+			cond_resched();
+
+			if (accum == SKARR_SZ) {
+				s_num = num + 1;
+				goto resume_bind_walk;
+			}
+
+			s_num = 0;
+		}
+skip_bind_ht:
+		cb->args[0] = 2;
+		s_i = num = s_num = 0;
+	}
+
 	if (!(idiag_states & ~TCPF_LISTEN))
 		goto out;
 
-#define SKARR_SZ 16
 	for (i = s_i; i <= hashinfo->ehash_mask; i++) {
 		struct inet_ehash_bucket *head = &hashinfo->ehash[i];
 		spinlock_t *lock = inet_ehash_lockp(hashinfo, i);

net/ipv4/tcp.c

@@ -2605,6 +2605,7 @@ void tcp_set_state(struct sock *sk, int state)
 	BUILD_BUG_ON((int)BPF_TCP_LISTEN != (int)TCP_LISTEN);
 	BUILD_BUG_ON((int)BPF_TCP_CLOSING != (int)TCP_CLOSING);
 	BUILD_BUG_ON((int)BPF_TCP_NEW_SYN_RECV != (int)TCP_NEW_SYN_RECV);
+	BUILD_BUG_ON((int)BPF_TCP_BOUND_INACTIVE != (int)TCP_BOUND_INACTIVE);
 	BUILD_BUG_ON((int)BPF_TCP_MAX_STATES != (int)TCP_MAX_STATES);
 
 	/* bpf uapi header bpf.h defines an anonymous enum with values