mptcp: fallback in case of simultaneous connect

when a MPTCP client tries to connect to itself, tcp_finish_connect() is
never reached. Because of this, depending on the socket current state,
multiple faulty behaviours can be observed:

1) a WARN_ON() in subflow_data_ready() is hit
 WARNING: CPU: 2 PID: 882 at net/mptcp/subflow.c:911 subflow_data_ready+0x18b/0x230
 [...]
 CPU: 2 PID: 882 Comm: gh35 Not tainted 5.7.0+ kernel-patches#187
 [...]
 RIP: 0010:subflow_data_ready+0x18b/0x230
 [...]
 Call Trace:
  tcp_data_queue+0xd2f/0x4250
  tcp_rcv_state_process+0xb1c/0x49d3
  tcp_v4_do_rcv+0x2bc/0x790
  __release_sock+0x153/0x2d0
  release_sock+0x4f/0x170
  mptcp_shutdown+0x167/0x4e0
  __sys_shutdown+0xe6/0x180
  __x64_sys_shutdown+0x50/0x70
  do_syscall_64+0x9a/0x370
  entry_SYSCALL_64_after_hwframe+0x44/0xa9

2) client is stuck forever in mptcp_sendmsg() because the socket is not
   TCP_ESTABLISHED

 crash> bt 4847
 PID: 4847   TASK: ffff88814b2fb100  CPU: 1   COMMAND: "gh35"
  #0 [ffff8881376ff680] __schedule at ffffffff97248da4
  kernel-patches#1 [ffff8881376ff778] schedule at ffffffff9724a34f
  kernel-patches#2 [ffff8881376ff7a0] schedule_timeout at ffffffff97252ba0
  kernel-patches#3 [ffff8881376ff8a8] wait_woken at ffffffff958ab4ba
  kernel-patches#4 [ffff8881376ff940] sk_stream_wait_connect at ffffffff96c2d859
  kernel-patches#5 [ffff8881376ffa28] mptcp_sendmsg at ffffffff97207fca
  kernel-patches#6 [ffff8881376ffbc0] sock_sendmsg at ffffffff96be1b5b
  kernel-patches#7 [ffff8881376ffbe8] sock_write_iter at ffffffff96be1daa
  kernel-patches#8 [ffff8881376ffce8] new_sync_write at ffffffff95e5cb52
  kernel-patches#9 [ffff8881376ffe50] vfs_write at ffffffff95e6547f
 kernel-patches#10 [ffff8881376ffe90] ksys_write at ffffffff95e65d26
 kernel-patches#11 [ffff8881376fff28] do_syscall_64 at ffffffff956088ba
 kernel-patches#12 [ffff8881376fff50] entry_SYSCALL_64_after_hwframe at ffffffff9740008c
     RIP: 00007f126f6956ed  RSP: 00007ffc2a320278  RFLAGS: 00000217
     RAX: ffffffffffffffda  RBX: 0000000020000044  RCX: 00007f126f6956ed
     RDX: 0000000000000004  RSI: 00000000004007b8  RDI: 0000000000000003
     RBP: 00007ffc2a3202a0   R8: 0000000000400720   R9: 0000000000400720
     R10: 0000000000400720  R11: 0000000000000217  R12: 00000000004004b0
     R13: 00007ffc2a320380  R14: 0000000000000000  R15: 0000000000000000
     ORIG_RAX: 0000000000000001  CS: 0033  SS: 002b

3) tcpdump captures show that DSS is exchanged even when MP_CAPABLE handshake
   didn't complete.

 $ tcpdump -tnnr bad.pcap
 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [S], seq 3208913911, win 65483, options [mss 65495,sackOK,TS val 3291706876 ecr 3291694721,nop,wscale 7,mptcp capable v1], length 0
 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [S.], seq 3208913911, ack 3208913912, win 65483, options [mss 65495,sackOK,TS val 3291706876 ecr 3291706876,nop,wscale 7,mptcp capable v1], length 0
 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [.], ack 1, win 512, options [nop,nop,TS val 3291706876 ecr 3291706876], length 0
 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [F.], seq 1, ack 1, win 512, options [nop,nop,TS val 3291707876 ecr 3291706876,mptcp dss fin seq 0 subseq 0 len 1,nop,nop], length 0
 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [.], ack 2, win 512, options [nop,nop,TS val 3291707876 ecr 3291707876], length 0

force a fallback to TCP in these cases, and adjust the main socket
state to avoid hanging in mptcp_sendmsg().

Closes: multipath-tcp/mptcp_net-next#35
Reported-by: Christoph Paasch <[email protected]>
Suggested-by: Paolo Abeni <[email protected]>
Signed-off-by: Davide Caratti <[email protected]>
Reviewed-by: Mat Martineau <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: dcaratti

net/mptcp/protocol.h

@@ -490,4 +490,14 @@ static inline void mptcp_do_fallback(struct sock *sk)
 
 #define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a)
 
+static inline bool subflow_simultaneous_connect(struct sock *sk)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct sock *parent = subflow->conn;
+
+	return sk->sk_state == TCP_ESTABLISHED &&
+	       !mptcp_sk(parent)->pm.server_side &&
+	       !subflow->conn_finished;
+}
+
 #endif /* __MPTCP_PROTOCOL_H */

net/mptcp/subflow.c

@@ -1128,6 +1128,16 @@ static void subflow_state_change(struct sock *sk)
 
 	__subflow_state_change(sk);
 
+	if (subflow_simultaneous_connect(sk)) {
+		mptcp_do_fallback(sk);
+		pr_fallback(mptcp_sk(parent));
+		subflow->conn_finished = 1;
+		if (inet_sk_state_load(parent) == TCP_SYN_SENT) {
+			inet_sk_state_store(parent, TCP_ESTABLISHED);
+			parent->sk_state_change(parent);
+		}
+	}
+
 	/* as recvmsg() does not acquire the subflow socket for ssk selection
 	 * a fin packet carrying a DSS can be unnoticed if we don't trigger
 	 * the data available machinery here.