[Qemu-devel] [PATCH COLO-Frame v19 18/22] COLO: Handle shutdown command for VM in COLO state

[zhanghailiang]

If VM is in COLO FT state, we should do some extra work before
normal shutdown process. SVM will ignore the shutdown command if
this command is issued directly to it.

COLO will send the shutdown command to Secondary side if it gets
shutdown request from user.

Cc: Paolo Bonzini <address@hidden>
Signed-off-by: zhanghailiang <address@hidden>
Signed-off-by: Li Zhijian <address@hidden>
Reviewed-by: Dr. David Alan Gilbert <address@hidden>
---
v19:
- fix title and comment
v15:
- Go on the shutdown process even some error happened
  while sent 'SHUTDOWN' message to SVM.
- Add Reviewed-by tag
v14:
- Remove 'colo_shutdown' variable, use colo_shutdown_request directly
v13:
- Move COLO shutdown related codes to colo.c file (Dave's suggestion)
---
 include/migration/colo.h |  2 ++
 include/sysemu/sysemu.h  |  3 +++
 migration/colo.c         | 47 +++++++++++++++++++++++++++++++++++++++++++++--
 qapi-schema.json         |  4 +++-
 stubs/migration-colo.c   |  5 +++++
 vl.c                     | 19 ++++++++++++++++---
 6 files changed, 74 insertions(+), 6 deletions(-)

diff --git a/include/migration/colo.h b/include/migration/colo.h
index e32eef4..b16c642 100644
--- a/include/migration/colo.h
+++ b/include/migration/colo.h
@@ -35,4 +35,6 @@ COLOMode get_colo_mode(void);
 
 /* failover */
 void colo_do_failover(MigrationState *s);
+
+bool colo_handle_shutdown(void);
 #endif
diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h
index ee7c760..1497c8b 100644
--- a/include/sysemu/sysemu.h
+++ b/include/sysemu/sysemu.h
@@ -51,6 +51,8 @@ typedef enum WakeupReason {
     QEMU_WAKEUP_REASON_OTHER,
 } WakeupReason;
 
+extern int colo_shutdown_requested;
+
 void qemu_system_reset_request(void);
 void qemu_system_suspend_request(void);
 void qemu_register_suspend_notifier(Notifier *notifier);
@@ -58,6 +60,7 @@ void qemu_system_wakeup_request(WakeupReason reason);
 void qemu_system_wakeup_enable(WakeupReason reason, bool enabled);
 void qemu_register_wakeup_notifier(Notifier *notifier);
 void qemu_system_shutdown_request(void);
+void qemu_system_shutdown_request_core(void);
 void qemu_system_powerdown_request(void);
 void qemu_register_powerdown_notifier(Notifier *notifier);
 void qemu_system_debug_request(void);
diff --git a/migration/colo.c b/migration/colo.c
index 69d1948..0a4cd80 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -327,6 +327,21 @@ static int colo_do_checkpoint_transaction(MigrationState 
*s,
         goto out;
     }
 
+    if (colo_shutdown_requested) {
+        colo_send_message(s->to_dst_file, COLO_MESSAGE_GUEST_SHUTDOWN,
+                          &local_err);
+        if (local_err) {
+            error_free(local_err);
+            /* Go on the shutdown process and throw the error message */
+            error_report("Failed to send shutdown message to SVM");
+        }
+        qemu_fflush(s->to_dst_file);
+        colo_shutdown_requested = 0;
+        qemu_system_shutdown_request_core();
+        /* Fix me: Just let the colo thread exit ? */
+        qemu_thread_exit(0);
+    }
+
     ret = 0;
 
     qemu_mutex_lock_iothread();
@@ -382,8 +397,9 @@ static void colo_process_checkpoint(MigrationState *s)
         }
 
         current_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
-        if (current_time - checkpoint_time <
-            s->parameters.x_checkpoint_delay) {
+        if ((current_time - checkpoint_time <
+            s->parameters.x_checkpoint_delay) &&
+            !colo_shutdown_requested) {
             int64_t delay_ms;
 
             delay_ms = s->parameters.x_checkpoint_delay -
@@ -444,6 +460,16 @@ static void colo_wait_handle_message(QEMUFile *f, int 
*checkpoint_request,
     case COLO_MESSAGE_CHECKPOINT_REQUEST:
         *checkpoint_request = 1;
         break;
+    case COLO_MESSAGE_GUEST_SHUTDOWN:
+        qemu_mutex_lock_iothread();
+        vm_stop_force_state(RUN_STATE_COLO);
+        qemu_system_shutdown_request_core();
+        qemu_mutex_unlock_iothread();
+        /*
+         * The main thread will be exit and terminate the whole
+         * process, do need some cleanup ?
+         */
+        qemu_thread_exit(0);
     default:
         *checkpoint_request = 0;
         error_setg(errp, "Got unknown COLO message: %d", msg);
@@ -592,3 +618,20 @@ out:
 
     return NULL;
 }
+
+bool colo_handle_shutdown(void)
+{
+    /*
+     * If VM is in COLO-FT mode, we need do some significant work before
+     * respond to the shutdown request. Besides, Secondary VM will ignore
+     * the shutdown request from users.
+     */
+    if (migration_incoming_in_colo_state()) {
+        return true;
+    }
+    if (migration_in_colo_state()) {
+        colo_shutdown_requested = 1;
+        return true;
+    }
+    return false;
+}
diff --git a/qapi-schema.json b/qapi-schema.json
index ee7131d..d65b0d3 100644
--- a/qapi-schema.json
+++ b/qapi-schema.json
@@ -811,12 +811,14 @@
 #
 # @vmstate-loaded: VM's state has been loaded by SVM.
 #
+# @guest-shutdown: shutdown require from PVM to SVM
+#
 # Since: 2.8
 ##
 { 'enum': 'COLOMessage',
   'data': [ 'checkpoint-ready', 'checkpoint-request', 'checkpoint-reply',
             'vmstate-send', 'vmstate-size', 'vmstate-received',
-            'vmstate-loaded' ] }
+            'vmstate-loaded', 'guest-shutdown' ] }
 
 ##
 # @COLOMode
diff --git a/stubs/migration-colo.c b/stubs/migration-colo.c
index 7811764..167b191 100644
--- a/stubs/migration-colo.c
+++ b/stubs/migration-colo.c
@@ -44,3 +44,8 @@ void qmp_x_colo_lost_heartbeat(Error **errp)
                      " with --enable-colo option in order to support"
                      " COLO feature");
 }
+
+bool colo_handle_shutdown(void)
+{
+    return false;
+}
diff --git a/vl.c b/vl.c
index 72927b8..8cd3c77 100644
--- a/vl.c
+++ b/vl.c
@@ -1620,6 +1620,8 @@ static NotifierList wakeup_notifiers =
     NOTIFIER_LIST_INITIALIZER(wakeup_notifiers);
 static uint32_t wakeup_reason_mask = ~(1 << QEMU_WAKEUP_REASON_NONE);
 
+int colo_shutdown_requested;
+
 int qemu_shutdown_requested_get(void)
 {
     return shutdown_requested;
@@ -1753,7 +1755,10 @@ void qemu_system_guest_panicked(void)
 void qemu_system_reset_request(void)
 {
     if (no_reboot) {
-        shutdown_requested = 1;
+        qemu_system_shutdown_request();
+        if (!shutdown_requested) {/* colo handle it ? */
+            return;
+        }
     } else {
         reset_requested = 1;
     }
@@ -1826,14 +1831,22 @@ void qemu_system_killed(int signal, pid_t pid)
     qemu_notify_event();
 }
 
-void qemu_system_shutdown_request(void)
+void qemu_system_shutdown_request_core(void)
 {
-    trace_qemu_system_shutdown_request();
     replay_shutdown_request();
     shutdown_requested = 1;
     qemu_notify_event();
 }
 
+void qemu_system_shutdown_request(void)
+{
+    trace_qemu_system_shutdown_request();
+    if (colo_handle_shutdown()) {
+        return;
+    }
+    qemu_system_shutdown_request_core();
+}
+
 static void qemu_system_powerdown(void)
 {
     qapi_event_send_powerdown(&error_abort);
-- 
1.8.3.1