1 files changed, 143 insertions, 7 deletions
diff --git a/tests/qtest/migration-test.c b/tests/qtest/migration-test.c
index bc70a14642..e803b46039 100644
--- a/tests/qtest/migration-test.c
+++ b/tests/qtest/migration-test.c
@@ -728,6 +728,7 @@ typedef struct {
     /* Postcopy specific fields */
     void *postcopy_data;
     bool postcopy_preempt;
+    bool postcopy_recovery_test_fail;
 } MigrateCommon;
 
 static int test_migrate_start(QTestState **from, QTestState **to,
@@ -1309,7 +1310,12 @@ static int migrate_postcopy_prepare(QTestState **from_ptr,
 
     migrate_prepare_for_dirty_mem(from);
     qtest_qmp_assert_success(to, "{ 'execute': 'migrate-incoming',"
-                             "  'arguments': { 'uri': 'tcp:127.0.0.1:0' }}");
+                             "  'arguments': { "
+                             "      'channels': [ { 'channel-type': 'main',"
+                             "      'addr': { 'transport': 'socket',"
+                             "                'type': 'inet',"
+                             "                'host': '127.0.0.1',"
+                             "                'port': '0' } } ] } }");
 
     /* Wait for the first serial output from the source */
     wait_for_serial("src_serial");
@@ -1404,6 +1410,80 @@ static void test_postcopy_preempt_tls_psk(void)
 }
 #endif
 
+static void wait_for_postcopy_status(QTestState *one, const char *status)
+{
+    wait_for_migration_status(one, status,
+                              (const char * []) { "failed", "active",
+                                                  "completed", NULL });
+}
+
+#ifndef _WIN32
+static void postcopy_recover_fail(QTestState *from, QTestState *to)
+{
+    int ret, pair1[2], pair2[2];
+    char c;
+
+    /* Create two unrelated socketpairs */
+    ret = qemu_socketpair(PF_LOCAL, SOCK_STREAM, 0, pair1);
+    g_assert_cmpint(ret, ==, 0);
+
+    ret = qemu_socketpair(PF_LOCAL, SOCK_STREAM, 0, pair2);
+    g_assert_cmpint(ret, ==, 0);
+
+    /*
+     * Give the guests unpaired ends of the sockets, so they'll all blocked
+     * at reading.  This mimics a wrong channel established.
+     */
+    qtest_qmp_fds_assert_success(from, &pair1[0], 1,
+                                 "{ 'execute': 'getfd',"
+                                 "  'arguments': { 'fdname': 'fd-mig' }}");
+    qtest_qmp_fds_assert_success(to, &pair2[0], 1,
+                                 "{ 'execute': 'getfd',"
+                                 "  'arguments': { 'fdname': 'fd-mig' }}");
+
+    /*
+     * Write the 1st byte as QEMU_VM_COMMAND (0x8) for the dest socket, to
+     * emulate the 1st byte of a real recovery, but stops from there to
+     * keep dest QEMU in RECOVER.  This is needed so that we can kick off
+     * the recover process on dest QEMU (by triggering the G_IO_IN event).
+     *
+     * NOTE: this trick is not needed on src QEMUs, because src doesn't
+     * rely on an pre-existing G_IO_IN event, so it will always trigger the
+     * upcoming recovery anyway even if it can read nothing.
+     */
+#define QEMU_VM_COMMAND              0x08
+    c = QEMU_VM_COMMAND;
+    ret = send(pair2[1], &c, 1, 0);
+    g_assert_cmpint(ret, ==, 1);
+
+    migrate_recover(to, "fd:fd-mig");
+    migrate_qmp(from, "fd:fd-mig", "{'resume': true}");
+
+    /*
+     * Make sure both QEMU instances will go into RECOVER stage, then test
+     * kicking them out using migrate-pause.
+     */
+    wait_for_postcopy_status(from, "postcopy-recover");
+    wait_for_postcopy_status(to, "postcopy-recover");
+
+    /*
+     * This would be issued by the admin upon noticing the hang, we should
+     * make sure we're able to kick this out.
+     */
+    migrate_pause(from);
+    wait_for_postcopy_status(from, "postcopy-paused");
+
+    /* Do the same test on dest */
+    migrate_pause(to);
+    wait_for_postcopy_status(to, "postcopy-paused");
+
+    close(pair1[0]);
+    close(pair1[1]);
+    close(pair2[0]);
+    close(pair2[1]);
+}
+#endif /* _WIN32 */
+
 static void test_postcopy_recovery_common(MigrateCommon *args)
 {
     QTestState *from, *to;
@@ -1439,9 +1519,19 @@ static void test_postcopy_recovery_common(MigrateCommon *args)
      * migrate-recover command can only succeed if destination machine
      * is in the paused state
      */
-    wait_for_migration_status(to, "postcopy-paused",
-                              (const char * []) { "failed", "active",
-                                                  "completed", NULL });
+    wait_for_postcopy_status(to, "postcopy-paused");
+    wait_for_postcopy_status(from, "postcopy-paused");
+
+#ifndef _WIN32
+    if (args->postcopy_recovery_test_fail) {
+        /*
+         * Test when a wrong socket specified for recover, and then the
+         * ability to kick it out, and continue with a correct socket.
+         */
+        postcopy_recover_fail(from, to);
+        /* continue with a good recovery */
+    }
+#endif /* _WIN32 */
 
     /*
      * Create a new socket to emulate a new channel that is different
@@ -1455,9 +1545,6 @@ static void test_postcopy_recovery_common(MigrateCommon *args)
      * Try to rebuild the migration channel using the resume flag and
      * the newly created channel
      */
-    wait_for_migration_status(from, "postcopy-paused",
-                              (const char * []) { "failed", "active",
-                                                  "completed", NULL });
     migrate_qmp(from, uri, "{'resume': true}");
 
     /* Restore the postcopy bandwidth to unlimited */
@@ -1482,6 +1569,17 @@ static void test_postcopy_recovery_compress(void)
     test_postcopy_recovery_common(&args);
 }
 
+#ifndef _WIN32
+static void test_postcopy_recovery_double_fail(void)
+{
+    MigrateCommon args = {
+        .postcopy_recovery_test_fail = true,
+    };
+
+    test_postcopy_recovery_common(&args);
+}
+#endif /* _WIN32 */
+
 #ifdef CONFIG_GNUTLS
 static void test_postcopy_recovery_tls_psk(void)
 {
@@ -2026,6 +2124,31 @@ static void test_precopy_file_offset_bad(void)
     test_file_common(&args, false);
 }
 
+static void *test_mode_reboot_start(QTestState *from, QTestState *to)
+{
+    migrate_set_parameter_str(from, "mode", "cpr-reboot");
+    migrate_set_parameter_str(to, "mode", "cpr-reboot");
+
+    migrate_set_capability(from, "x-ignore-shared", true);
+    migrate_set_capability(to, "x-ignore-shared", true);
+
+    return NULL;
+}
+
+static void test_mode_reboot(void)
+{
+    g_autofree char *uri = g_strdup_printf("file:%s/%s", tmpfs,
+                                           FILE_TEST_FILENAME);
+    MigrateCommon args = {
+        .start.use_shmem = true,
+        .connect_uri = uri,
+        .listen_uri = "defer",
+        .start_hook = test_mode_reboot_start
+    };
+
+    test_file_common(&args, true);
+}
+
 static void test_precopy_tcp_plain(void)
 {
     MigrateCommon args = {
@@ -3068,6 +3191,11 @@ int main(int argc, char **argv)
             qtest_add_func("/migration/postcopy/recovery/compress/plain",
                            test_postcopy_recovery_compress);
         }
+#ifndef _WIN32
+        qtest_add_func("/migration/postcopy/recovery/double-failures",
+                       test_postcopy_recovery_double_fail);
+#endif /* _WIN32 */
+
     }
 
     qtest_add_func("/migration/bad_dest", test_baddest);
@@ -3096,6 +3224,14 @@ int main(int argc, char **argv)
     qtest_add_func("/migration/precopy/file/offset/bad",
                    test_precopy_file_offset_bad);
 
+    /*
+     * Our CI system has problems with shared memory.
+     * Don't run this test until we find a workaround.
+     */
+    if (getenv("QEMU_TEST_FLAKY_TESTS")) {
+        qtest_add_func("/migration/mode/reboot", test_mode_reboot);
+    }
+
 #ifdef CONFIG_GNUTLS
     qtest_add_func("/migration/precopy/unix/tls/psk",
                    test_precopy_unix_tls_psk);