mctp: Add retry for one-time peer property queries on timeout

The function `query_peer_properties()` is called once during peer initialization
to query basic information after the EID becomes routable.
To improve reliability, this change adds a retry mechanism when the query
fails with `-ETIMEDOUT`. Since these queries are one-time initialization steps,
a single successful attempt is sufficient, and retrying enhances stability
under transient MCTP bus contention or multi-master timing issues.

Testing:
add stress test for peer initialization under multi-master
```
while true; do
    echo "Restarting mctpd.service..."
    systemctl restart mctpd.service

    # Wait a few seconds to allow service to initialize
    sleep 20
done
```
After the 30 loops, the script checks mctpd.service journal for expected
retry messages to verify robustness under transient MCTP bus contention.
```
root@bmc:~# journalctl -xeu mctpd.service | grep Retrying
Oct 29 00:35:21 bmc mctpd[31801]: mctpd: Retrying to get endpoint types for peer eid 10 net 1 phys physaddr if 4 hw len 1 0x20 state 1. Attempt 1
Oct 29 00:39:00 bmc mctpd[32065]: mctpd: Retrying to get endpoint types for peer eid 10 net 1 phys physaddr if 4 hw len 1 0x20 state 1. Attempt 1
Oct 29 00:39:01 bmc mctpd[32065]: mctpd: Retrying to get endpoint types for peer eid 10 net 1 phys physaddr if 4 hw len 1 0x20 state 1. Attempt 2
Oct 29 00:45:08 bmc mctpd[32360]: mctpd: Retrying to get endpoint types for peer eid 10 net 1 phys physaddr if 4 hw len 1 0x20 state 1. Attempt 1
```

Signed-off-by: Daniel Hsu <Daniel-Hsu@quantatw.com>

Author: JunYe1993

src/mctpd.c

@@ -2835,23 +2835,57 @@ static int method_learn_endpoint(sd_bus_message *call, void *data,
 // and routable.
 static int query_peer_properties(struct peer *peer)
 {
+	const unsigned int max_retries = 4;
 	int rc;
 
-	rc = query_get_peer_msgtypes(peer);
-	if (rc < 0) {
-		// Warn here, it's a mandatory command code.
-		// It might be too noisy if some devices don't implement it.
-		warnx("Error getting endpoint types for %s. Ignoring error %d %s",
-		      peer_tostr(peer), rc, strerror(-rc));
-		rc = 0;
+	for (unsigned int i = 0; i < max_retries; i++) {
+		rc = query_get_peer_msgtypes(peer);
+
+		// Success
+		if (rc == 0)
+			break;
+
+		// On timeout, retry
+		if (rc == -ETIMEDOUT) {
+			if (peer->ctx->verbose)
+				warnx("Retrying to get endpoint types for %s. Attempt %u",
+				      peer_tostr(peer), i + 1);
+			continue;
+		}
+
+		// On other errors, warn and ignore
+		if (rc < 0) {
+			if (peer->ctx->verbose)
+				warnx("Error getting endpoint types for %s. Ignoring error %d %s",
+				      peer_tostr(peer), -rc, strerror(-rc));
+			rc = 0;
+			break;
+		}
 	}
 
-	rc = query_get_peer_uuid(peer);
-	if (rc < 0) {
-		if (peer->ctx->verbose)
-			warnx("Error getting UUID for %s. Ignoring error %d %s",
-			      peer_tostr(peer), rc, strerror(-rc));
-		rc = 0;
+	for (unsigned int i = 0; i < max_retries; i++) {
+		rc = query_get_peer_uuid(peer);
+
+		// Success
+		if (rc == 0)
+			break;
+
+		// On timeout, retry
+		if (rc == -ETIMEDOUT) {
+			if (peer->ctx->verbose)
+				warnx("Retrying to get peer UUID for %s. Attempt %u",
+				      peer_tostr(peer), i + 1);
+			continue;
+		}
+
+		// On other errors, warn and ignore
+		if (rc < 0) {
+			if (peer->ctx->verbose)
+				warnx("Error getting UUID for %s. Ignoring error %d %s",
+				      peer_tostr(peer), -rc, strerror(-rc));
+			rc = 0;
+			break;
+		}
 	}
 
 	// TODO: emit property changed? Though currently they are all const.

tests/__pycache__/conftest.cpython-312-pytest-7.4.4.pyc

@@ -1289,3 +1289,50 @@ async def test_get_message_types(dbus, mctpd):
     cmd = MCTPControlCommand(True, 0, 0x04, bytes([0x05]))
     rsp = await ep.send_control(mctpd.network.mctp_socket, cmd)
     assert rsp.hex(' ') == '00 04 00 01 f4 f3 f2 f1'
+
+async def test_query_peer_properties_retry_timeout(nursery, dbus, sysnet):
+
+    # activate mctpd
+    mctpd = MctpdWrapper(dbus, sysnet)
+    await mctpd.start_mctpd(nursery)
+
+    iface = mctpd.system.interfaces[0]
+    ep = mctpd.network.endpoints[0]
+
+    mctp = await mctpd_mctp_iface_obj(dbus, iface)
+
+    # add a bridged endpoint to ep
+    fake_ep = Endpoint(iface, b'\x12\x34', types=[0, 2])
+    ep.add_bridged_ep(fake_ep)
+    mctpd.network.add_endpoint(fake_ep)
+
+    # override fake_ep.send_control to simulate a timeout on the first call
+    original_send = fake_ep.send_control
+    fake_ep._first_timeout = True
+
+    async def fake_send(sock, cmd):
+        if fake_ep._first_timeout:
+            fake_ep._first_timeout = False
+            # simulate timeout
+            await trio.sleep(1.0)
+            return None
+        # normal response on second call
+        return await original_send(sock, cmd)
+
+    fake_ep.send_control = fake_send
+
+    # call assign_endpoint on ep, which will allocate a pool for fake_ep
+    mctp = await mctpd_mctp_iface_obj(dbus, iface)
+    await mctp.call_assign_endpoint(ep.lladdr)
+
+    # collect mctpd logs to verify retry occurred
+    logs = []
+    async for line in mctpd.proc.stdout:
+        logs.append(line.decode())
+
+    retry_found = any("Retrying to get endpoint types" in l for l in logs)
+    assert retry_found, "mctpd did not retry on timeout"
+
+    # exit mctpd
+    res = await mctpd.stop_mctpd()
+    assert res == 0