swrap: fallback to libc_getpeername() when we get an empty sun_path from accept()

This hopefully hides the strange behaviour of FreeBSD (at least 12.1)
for already disconnected AF_UNIX sockets.

The race is triggered when the following detects the usage of 'getpeername':

truss -o ./truss.out -f -H -a -e -D -s 160 ctest -V -R test_thread_echo_tcp_connect;
grep getpeername truss.out

In a simplified log the following is happening:

 ECHO_SRV(parent): socket(PF_LOCAL,SOCK_STREAM,0) = 4 (0x4)
 ECHO_SRV(parent): unlink("/tmp/w_E37bkf/T0A0007") ERR#2 'No such file or directory'
 ECHO_SRV(parent): bind(4,{ AF_UNIX "/tmp/w_E37bkf/T0A0007" },106) = 0 (0x0)
 ECHO_SRV(parent): listen(4,16)		 = 0 (0x0)
 ...
 ECHO_SRV(parent): write(2,"SWRAP_ERROR[echo_srv (9792)] - swrap_accept: before accept(sa_socklen=106)\n",75) = 75 (0x4b)
 ECHO_SRV(parent): accept4(0x4,0x7ffffffde158,0x7ffffffde150,0x0) = 5 (0x5)
 ECHO_SRV(parent): write(2,"SWRAP_ERROR[echo_srv (9792)] - swrap_accept: after accept(sa_socklen=106, family=1)\n",84) = 84 (0x54)
 ECHO_SRV(parent): getsockname(5,{ AF_UNIX "/tmp/w_E37bkf/T0A0007" },0x7ffffffde0c0) = 0 (0x0)

 ECHO_SRV(parent): swrap_accept() returned a valid connection and a per connection child (pid=9793) handles it

 TEST_THREAD:      socket(PF_LOCAL,SOCK_STREAM,0) = 7 (0x7)
 TEST_THREAD:      bind(7,{ AF_UNIX "/tmp/w_E37bkf/T014D4F" },106) = 0 (0x0)
 TEST_THREAD:      connect(7,{ AF_UNIX "/tmp/w_E37bkf/T0A0007" },106) = 0 (0x0)
 TEST_THREAD:      close(7)		 = 0 (0x0)

 ECHO_SRV(parent): wait4(-1,0x0,0x0,0x0)	 = 9793 (0x2641)
 ECHO_SRV(parent): close(5)		 = 0 (0x0)
 ECHO_SRV(parent): write(2,"SWRAP_ERROR[echo_srv (9792)] - swrap_accept: before accept(sa_socklen=106)\n",75) = 75 (0x4b)
 ECHO_SRV(parent): accept4(0x4,0x7ffffffde158,0x7ffffffde150,0x0) = 5 (0x5)

 TEST_THREAD:      unlink("/tmp/w_E37bkf/T014D4F") = 0 (0x0)

 ECHO_SRV(parent): write(2,"SWRAP_ERROR[echo_srv (9792)] - swrap_accept: after accept(sa_socklen=16, family=1)\n",83) = 83 (0x53)
 ECHO_SRV(parent): getpeername(5,0x7ffffffde158,0x7ffffffde150) ERR#57 'Socket is not connected'
 ECHO_SRV(parent): getsockname(5,{ AF_UNIX "/tmp/w_E37bkf/T0A0007" },0x7ffffffde0c0) = 0 (0x0)
 ECHO_SRV(parent): getpeername(5,0x7ffffffde158,0x7ffffffde150) ERR#57 'Socket is not connected'

Signed-off-by: Stefan Metzmacher <metze@samba.org>
Reviewed-by: Andreas Schneider <asn@samba.org>

1 files changed, 27 insertions, 0 deletions

diff --git a/src/socket_wrapper.c b/src/socket_wrapper.c
index d72b31f..0f37605 100644
--- a/src/socket_wrapper.c
+++ b/src/socket_wrapper.c
@@ -3656,6 +3656,33 @@ static int swrap_accept(int s,
 	/* Check if we have a stale fd and remove it */
 	swrap_remove_stale(fd);
 
+	if (un_addr.sa.un.sun_path[0] == '\0') {
+		/*
+		 * FreeBSD seems to have a problem where
+		 * accept4() on the unix socket doesn't
+		 * ECONNABORTED for already disconnected connections.
+		 *
+		 * Let's try libc_getpeername() to get the peer address
+		 * as a fallback, but it'll likely return ENOTCONN,
+		 * which we have to map to ECONNABORTED.
+		 */
+		un_addr.sa_socklen = sizeof(struct sockaddr_un),
+		ret = libc_getpeername(fd, &un_addr.sa.s, &un_addr.sa_socklen);
+		if (ret == -1) {
+			int saved_errno = errno;
+			libc_close(fd);
+			if (saved_errno == ENOTCONN) {
+				/*
+				 * If the connection is already disconnected
+				 * we should return ECONNABORTED.
+				 */
+				saved_errno = ECONNABORTED;
+			}
+			errno = saved_errno;
+			return ret;
+		}
+	}
+
 	ret = libc_getsockname(fd,
 			       &un_my_addr.sa.s,
 			       &un_my_addr.sa_socklen);