T8454: fix VRF-bind port availability check in service_https

When service https is configured with a listen-address on a VRF
interface, adding or changing the vrf option causes the commit to
fail with "TCP port 443 is used by another service!" even though
no conflict exists.

Root cause: check_port_availability() performs a socket.bind() in
the default network namespace. When the listen-address belongs to
a VRF interface the address is unreachable from the default
namespace, so the bind fails with OSError which is misinterpreted
as "port in use". The secondary check via is_listen_port_bind_service()
also fails because psutil cannot see sockets bound inside a VRF.

Fix: add an optional vrf parameter to check_port_availability().
When set, the test socket is bound to the VRF master device via
SO_BINDTODEVICE before the bind() call, so that the address is
resolved in the correct L3 domain. This is done in-process (no
subprocess) and works for both IPv4 and IPv6.

service_https verify() now passes the configured VRF (if any) to
check_port_availability(). Non-VRF configurations are unaffected.

Add smoke test for HTTPS with listen-address inside a VRF.

Co-authored-by: Christian Breunig <christian@breunig.cc>

1 files changed, 30 insertions, 0 deletions

diff --git a/smoketest/scripts/cli/test_service_https.py b/smoketest/scripts/cli/test_service_https.py
index 4585bb0bd..b29be9eda 100755
--- a/smoketest/scripts/cli/test_service_https.py
+++ b/smoketest/scripts/cli/test_service_https.py
@@ -28,6 +28,7 @@ from base_vyostest_shim import ignore_warning
 from vyos.utils.file import read_file
 from vyos.utils.file import write_file
 from vyos.utils.process import call
+from vyos.utils.process import cmd
 from vyos.utils.process import process_named_running
 from vyos.xml_ref import default_value
 
@@ -177,6 +178,35 @@ class TestHTTPSService(VyOSUnitTestSHIM.TestCase):
 
         self.assertEqual(res, set(test_addr))
 
+    def test_listen_address_vrf(self):
+        # Verify that HTTPS service can be configured with a listen-address
+        # inside a VRF.  Regression test: the port availability check used to
+        # fail because it ran in the default namespace where the VRF address
+        # is unreachable.
+        vrf = 'mgmt'
+        vrf_table = '1337'
+        test_addr = '192.0.2.1'
+        test_prefix = f'{test_addr}/26'
+        interface = 'dum0'
+
+        self.cli_set(['interfaces', 'dummy', interface, 'address', test_prefix])
+        self.cli_set(['interfaces', 'dummy', interface, 'vrf', vrf])
+        self.cli_set(['vrf', 'name', vrf, 'table', vrf_table])
+
+        self.cli_set(
+            base_path + ['api', 'keys', 'id', 'key-01', 'key', 'MySuperSecretVyOS']
+        )
+        self.cli_set(base_path + ['listen-address', test_addr])
+        self.cli_set(base_path + ['vrf', vrf])
+        self.cli_commit()
+
+        # Verify nginx is running inside the VRF
+        tmp = cmd(f'ip vrf pids {vrf}')
+        self.assertIn(PROCESS_NAME, tmp)
+
+        self.cli_delete(['interfaces', 'dummy', interface])
+        self.cli_delete(['vrf', 'name', vrf])
+
     def test_certificate(self):
         cert_name = 'test_https'
         dh_name = 'dh-test'