[Qemu-devel] [PATCH COLO-Frame v16 24/35] COLO: Process 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, PVM will send the shutdown command to SVM if it gets this command.

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>
---
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         | 45 +++++++++++++++++++++++++++++++++++++++++++--
 qapi-schema.json         |  4 +++-
 stubs/migration-colo.c   |  5 +++++
 vl.c                     | 19 ++++++++++++++++---
 6 files changed, 72 insertions(+), 6 deletions(-)

diff --git a/include/migration/colo.h b/include/migration/colo.h
index e32eef4..919b135 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_shutdown(void);
 #endif
diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h
index 38fb3ca..8537bed 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 252a290..2873bab 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -331,6 +331,21 @@ 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;
     /* Resume primary guest */
     qemu_mutex_lock_iothread();
@@ -391,8 +406,9 @@ static void colo_process_checkpoint(MigrationState *s)
         }
 
         current_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
-        if (current_time - checkpoint_time <
-            s->parameters[MIGRATION_PARAMETER_X_CHECKPOINT_DELAY]) {
+        if ((current_time - checkpoint_time <
+            s->parameters[MIGRATION_PARAMETER_X_CHECKPOINT_DELAY]) &&
+            !colo_shutdown_requested) {
             int64_t delay_ms;
 
             delay_ms = s->parameters[MIGRATION_PARAMETER_X_CHECKPOINT_DELAY] -
@@ -466,6 +482,15 @@ 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 exit and terminate the whole
+        * process, do we need some cleanup?
+        */
+        qemu_thread_exit(0);
     default:
         *checkpoint_request = 0;
         error_setg(errp, "Got unknown COLO message: %d", msg);
@@ -637,3 +662,19 @@ out:
 
     return NULL;
 }
+
+bool colo_shutdown(void)
+{
+    /*
+    * if in colo mode, we need do some significant work before respond
+    * to the shutdown request.
+    */
+    if (migration_incoming_in_colo_state()) {
+        return true; /* primary's responsibility */
+    }
+    if (migration_in_colo_state()) {
+        colo_shutdown_requested = 1;
+        return true;
+    }
+    return false;
+}
diff --git a/qapi-schema.json b/qapi-schema.json
index 719fcde..02c56a8 100644
--- a/qapi-schema.json
+++ b/qapi-schema.json
@@ -752,12 +752,14 @@
 #
 # @vmstate-loaded: VM's state has been loaded by SVM.
 #
+# @guest-shutdown: shutdown require from PVM to SVM
+#
 # Since: 2.7
 ##
 { '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..e507e17 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_shutdown(void)
+{
+    return false;
+}
diff --git a/vl.c b/vl.c
index f47ef3c..cbe51ac 100644
--- a/vl.c
+++ b/vl.c
@@ -1646,6 +1646,8 @@ 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;
@@ -1779,7 +1781,10 @@ 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;
     }
@@ -1852,14 +1857,22 @@ 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_shutdown()) {
+        return;
+    }
+    qemu_system_shutdown_request_core();
+}
+
 static void qemu_system_powerdown(void)
 {
     qapi_event_send_powerdown(&error_abort);
-- 
1.8.3.1