python/machine: use socketpair() for console connections

Create a socketpair for the console output. This should help eliminate
race conditions around console text early in the boot process that might
otherwise have been dropped on the floor before being able to connect to
QEMU under "server,nowait".

Signed-off-by: John Snow <jsnow@redhat.com>
Reviewed-by: Ani Sinha <anisinha@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-id: 20230928044943.849073-5-jsnow@redhat.com
Signed-off-by: John Snow <jsnow@redhat.com>

diff --git a/python/qemu/machine/machine.py b/python/qemu/machine/machine.py
index e26109e6f0e6fb8a39aee2039a83a2fed368f684..4156b8cf7d4f5e02eb462db48cb8273b6f51d9a1 100644 (file)
--- a/python/qemu/machine/machine.py
+++ b/python/qemu/machine/machine.py
@@ -159,6 +159,8 @@ class QEMUMachine:
 
         self._name = name or f"{id(self):x}"
         self._sock_pair: Optional[Tuple[socket.socket, socket.socket]] = None
+        self._cons_sock_pair: Optional[
+            Tuple[socket.socket, socket.socket]] = None
         self._temp_dir: Optional[str] = None
         self._base_temp_dir = base_temp_dir
         self._sock_dir = sock_dir
@@ -316,8 +318,9 @@ class QEMUMachine:
         for _ in range(self._console_index):
             args.extend(['-serial', 'null'])
         if self._console_set:
-            chardev = ('socket,id=console,path=%s,server=on,wait=off' %
-                       self._console_address)
+            assert self._cons_sock_pair is not None
+            fd = self._cons_sock_pair[0].fileno()
+            chardev = f"socket,id=console,fd={fd}"
             args.extend(['-chardev', chardev])
             if self._console_device_type is None:
                 args.extend(['-serial', 'chardev:console'])
@@ -352,6 +355,10 @@ class QEMUMachine:
                 nickname=self._name
             )
 
+        if self._console_set:
+            self._cons_sock_pair = socket.socketpair()
+            os.set_inheritable(self._cons_sock_pair[0].fileno(), True)
+
         # NOTE: Make sure any opened resources are *definitely* freed in
         # _post_shutdown()!
         # pylint: disable=consider-using-with
@@ -369,6 +376,9 @@ class QEMUMachine:
     def _post_launch(self) -> None:
         if self._sock_pair:
             self._sock_pair[0].close()
+        if self._cons_sock_pair:
+            self._cons_sock_pair[0].close()
+
         if self._qmp_connection:
             if self._sock_pair:
                 self._qmp.connect()
@@ -524,6 +534,11 @@ class QEMUMachine:
             self._console_socket.close()
             self._console_socket = None
 
+        if self._cons_sock_pair:
+            self._cons_sock_pair[0].close()
+            self._cons_sock_pair[1].close()
+            self._cons_sock_pair = None
+
     def _hard_shutdown(self) -> None:
         """
         Perform early cleanup, kill the VM, and wait for it to terminate.
@@ -885,10 +900,19 @@ class QEMUMachine:
         """
         if self._console_socket is None:
             LOG.debug("Opening console socket")
+            if not self._console_set:
+                raise QEMUMachineError(
+                    "Attempt to access console socket with no connection")
+            assert self._cons_sock_pair is not None
+            # os.dup() is used here for sock_fd because otherwise we'd
+            # have two rich python socket objects that would each try to
+            # close the same underlying fd when either one gets garbage
+            # collected.
             self._console_socket = console_socket.ConsoleSocket(
-                self._console_address,
+                sock_fd=os.dup(self._cons_sock_pair[1].fileno()),
                 file=self._console_log_path,
                 drain=self._drain_console)
+            self._cons_sock_pair[1].close()
         return self._console_socket
 
     @property