dccp/tcp: Fixup bhash2 bucket when connect() fails.

If a socket bound to a wildcard address fails to connect(), we
only reset saddr and keep the port.  Then, we have to fix up the
bhash2 bucket; otherwise, the bucket has an inconsistent address
in the list.

Also, listen() for such a socket will fire the WARN_ON() in
inet_csk_get_port(). [0]

Note that when a system runs out of memory, we give up fixing the
bucket and unlink sk from bhash and bhash2 by inet_put_port().

[0]:
WARNING: CPU: 0 PID: 207 at net/ipv4/inet_connection_sock.c:548 inet_csk_get_port (net/ipv4/inet_connection_sock.c:548 (discriminator 1))
Modules linked in:
CPU: 0 PID: 207 Comm: bhash2_prev_rep Not tainted 6.1.0-rc3-00799-gc8421681c845 #63
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.amzn2022.0.1 04/01/2014
RIP: 0010:inet_csk_get_port (net/ipv4/inet_connection_sock.c:548 (discriminator 1))
Code: 74 a7 eb 93 48 8b 54 24 18 0f b7 cb 4c 89 e6 4c 89 ff e8 48 b2 ff ff 49 8b 87 18 04 00 00 e9 32 ff ff ff 0f 0b e9 34 ff ff ff <0f> 0b e9 42 ff ff ff 41 8b 7f 50 41 8b 4f 54 89 fe 81 f6 00 00 ff
RSP: 0018:ffffc900003d7e50 EFLAGS: 00010202
RAX: ffff8881047fb500 RBX: 0000000000004e20 RCX: 0000000000000000
RDX: 000000000000000a RSI: 00000000fffffe00 RDI: 00000000ffffffff
RBP: ffffffff8324dc00 R08: 0000000000000001 R09: 0000000000000001
R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000000
R13: 0000000000000001 R14: 0000000000004e20 R15: ffff8881054e1280
FS:  00007f8ac04dc740(0000) GS:ffff88842fc00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020001540 CR3: 00000001055fa003 CR4: 0000000000770ef0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
PKRU: 55555554
Call Trace:
 <TASK>
 inet_csk_listen_start (net/ipv4/inet_connection_sock.c:1205)
 inet_listen (net/ipv4/af_inet.c:228)
 __sys_listen (net/socket.c:1810)
 __x64_sys_listen (net/socket.c:1819 net/socket.c:1817 net/socket.c:1817)
 do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80)
 entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120)
RIP: 0033:0x7f8ac051de5d
Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 93 af 1b 00 f7 d8 64 89 01 48
RSP: 002b:00007ffc1c177248 EFLAGS: 00000206 ORIG_RAX: 0000000000000032
RAX: ffffffffffffffda RBX: 0000000020001550 RCX: 00007f8ac051de5d
RDX: ffffffffffffff80 RSI: 0000000000000000 RDI: 0000000000000004
RBP: 00007ffc1c177270 R08: 0000000000000018 R09: 0000000000000007
R10: 0000000020001540 R11: 0000000000000206 R12: 00007ffc1c177388
R13: 0000000000401169 R14: 0000000000403e18 R15: 00007f8ac0723000
 </TASK>

Fixes: 28044fc1d495 ("net: Add a bhash2 table hashed by port and address")
Reported-by: syzbot <syzkaller@googlegroups.com>
Reported-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Acked-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 36 insertions, 8 deletions

diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 18ef370af113..3cec471a2cd2 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -871,7 +871,7 @@ static void inet_update_saddr(struct sock *sk, void *saddr, int family)
 #endif
 }
 
-int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family)
+static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family, bool reset)
 {
 	struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk);
 	struct inet_bind_hashbucket *head, *head2;
@@ -883,7 +883,11 @@ int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family)
 
 	if (!inet_csk(sk)->icsk_bind2_hash) {
 		/* Not bind()ed before. */
-		inet_update_saddr(sk, saddr, family);
+		if (reset)
+			inet_reset_saddr(sk);
+		else
+			inet_update_saddr(sk, saddr, family);
+
 		return 0;
 	}
 
@@ -892,8 +896,19 @@ int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family)
 	 * allocation fails.
 	 */
 	new_tb2 = kmem_cache_alloc(hinfo->bind2_bucket_cachep, GFP_ATOMIC);
-	if (!new_tb2)
+	if (!new_tb2) {
+		if (reset) {
+			/* The (INADDR_ANY, port) bucket might have already
+			 * been freed, then we cannot fixup icsk_bind2_hash,
+			 * so we give up and unlink sk from bhash/bhash2 not
+			 * to leave inconsistency in bhash2.
+			 */
+			inet_put_port(sk);
+			inet_reset_saddr(sk);
+		}
+
 		return -ENOMEM;
+	}
 
 	bhash = inet_bhashfn(net, port, hinfo->bhash_size);
 	head = &hinfo->bhash[bhash];
@@ -909,7 +924,10 @@ int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family)
 	inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, inet_csk(sk)->icsk_bind2_hash);
 	spin_unlock(&head2->lock);
 
-	inet_update_saddr(sk, saddr, family);
+	if (reset)
+		inet_reset_saddr(sk);
+	else
+		inet_update_saddr(sk, saddr, family);
 
 	head2 = inet_bhashfn_portaddr(hinfo, sk, net, port);
 
@@ -930,8 +948,20 @@ int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family)
 
 	return 0;
 }
+
+int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family)
+{
+	return __inet_bhash2_update_saddr(sk, saddr, family, false);
+}
 EXPORT_SYMBOL_GPL(inet_bhash2_update_saddr);
 
+void inet_bhash2_reset_saddr(struct sock *sk)
+{
+	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
+		__inet_bhash2_update_saddr(sk, NULL, 0, true);
+}
+EXPORT_SYMBOL_GPL(inet_bhash2_reset_saddr);
+
 /* RFC 6056 3.3.4.  Algorithm 4: Double-Hash Port Selection Algorithm
  * Note that we use 32bit integers (vs RFC 'short integers')
  * because 2^16 is not a multiple of num_ephemeral and this
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 54836a6b81d6..4f2205756cfe 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3114,8 +3114,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 
 	inet->inet_dport = 0;
 
-	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
-		inet_reset_saddr(sk);
+	inet_bhash2_reset_saddr(sk);
 
 	sk->sk_shutdown = 0;
 	sock_reset_flag(sk, SOCK_DONE);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 23dd7e9df2d5..da46357f501b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -331,8 +331,7 @@ failure:
 	 * if necessary.
 	 */
 	tcp_set_state(sk, TCP_CLOSE);
-	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
-		inet_reset_saddr(sk);
+	inet_bhash2_reset_saddr(sk);
 	ip_rt_put(rt);
 	sk->sk_route_caps = 0;
 	inet->inet_dport = 0;