Remove migrate_set_block_enabled in checkpoint

[qemu.git] / migration / colo.c

diff --git a/migration/colo.c b/migration/colo.c
index 44942c4e2345e22d93f0a9f7316c09e3ef7ac900..79fa1f66194beaae528c1605a1dca93ecd7e7c7d 100644 (file)
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -28,7 +28,7 @@
 #include "migration/failover.h"
 #include "migration/ram.h"
 #ifdef CONFIG_REPLICATION
-#include "replication.h"
+#include "block/replication.h"
 #endif
 #include "net/colo-compare.h"
 #include "net/colo.h"
@@ -93,6 +93,7 @@ static void secondary_vm_do_failover(void)
     replication_stop_all(true, &local_err);
     if (local_err) {
         error_report_err(local_err);
+        local_err = NULL;
     }
 
     /* Notify all filters of all NIC to do checkpoint */
@@ -262,7 +263,13 @@ ReplicationStatus *qmp_query_xen_replication_status(Error **errp)
 
 void qmp_xen_colo_do_checkpoint(Error **errp)
 {
-    replication_do_checkpoint_all(errp);
+    Error *err = NULL;
+
+    replication_do_checkpoint_all(&err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
     /* Notify all filters of all NIC to do checkpoint */
     colo_notify_filters_event(COLO_EVENT_CHECKPOINT, errp);
 }
@@ -428,14 +435,6 @@ static int colo_do_checkpoint_transaction(MigrationState *s,
     if (failover_get_state() != FAILOVER_STATUS_NONE) {
         goto out;
     }
-
-    colo_notify_compares_event(NULL, COLO_EVENT_CHECKPOINT, &local_err);
-    if (local_err) {
-        goto out;
-    }
-
-    /* Disable block migration */
-    migrate_set_block_enabled(false, &local_err);
     qemu_mutex_lock_iothread();
 
 #ifdef CONFIG_REPLICATION
@@ -492,6 +491,12 @@ static int colo_do_checkpoint_transaction(MigrationState *s,
         goto out;
     }
 
+    qemu_event_reset(&s->colo_checkpoint_event);
+    colo_notify_compares_event(NULL, COLO_EVENT_CHECKPOINT, &local_err);
+    if (local_err) {
+        goto out;
+    }
+
     colo_receive_check_message(s->rp_state.from_dst_file,
                        COLO_MESSAGE_VMSTATE_LOADED, &local_err);
     if (local_err) {
@@ -579,7 +584,7 @@ static void colo_process_checkpoint(MigrationState *s)
             goto out;
         }
 
-        qemu_sem_wait(&s->colo_checkpoint_sem);
+        qemu_event_wait(&s->colo_checkpoint_event);
 
         if (s->state != MIGRATION_STATUS_COLO) {
             goto out;
@@ -621,13 +626,12 @@ out:
     /*
      * It is safe to unregister notifier after failover finished.
      * Besides, colo_delay_timer and colo_checkpoint_sem can't be
-     * released befor unregister notifier, or there will be use-after-free
+     * released before unregister notifier, or there will be use-after-free
      * error.
      */
     colo_compare_unregister_notifier(&packets_compare_notifier);
-    timer_del(s->colo_delay_timer);
     timer_free(s->colo_delay_timer);
-    qemu_sem_destroy(&s->colo_checkpoint_sem);
+    qemu_event_destroy(&s->colo_checkpoint_event);
 
     /*
      * Must be called after failover BH is completed,
@@ -644,7 +648,7 @@ void colo_checkpoint_notify(void *opaque)
     MigrationState *s = opaque;
     int64_t next_notify_time;
 
-    qemu_sem_post(&s->colo_checkpoint_sem);
+    qemu_event_set(&s->colo_checkpoint_event);
     s->colo_checkpoint_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
     next_notify_time = s->colo_checkpoint_time +
                     s->parameters.x_checkpoint_delay;
@@ -654,7 +658,7 @@ void colo_checkpoint_notify(void *opaque)
 void migrate_start_colo_process(MigrationState *s)
 {
     qemu_mutex_unlock_iothread();
-    qemu_sem_init(&s->colo_checkpoint_sem, 0);
+    qemu_event_init(&s->colo_checkpoint_event, false);
     s->colo_delay_timer =  timer_new_ms(QEMU_CLOCK_HOST,
                                 colo_checkpoint_notify, s);
 
@@ -694,7 +698,7 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis,
     }
 
     qemu_mutex_lock_iothread();
-    cpu_synchronize_all_pre_loadvm();
+    cpu_synchronize_all_states();
     ret = qemu_loadvm_state_main(mis->from_src_file, mis);
     qemu_mutex_unlock_iothread();
 
@@ -737,9 +741,11 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis,
 
     qemu_mutex_lock_iothread();
     vmstate_loading = true;
+    colo_flush_ram_cache();
     ret = qemu_load_device_state(fb);
     if (ret < 0) {
         error_setg(errp, "COLO: load device state failed");
+        vmstate_loading = false;
         qemu_mutex_unlock_iothread();
         return;
     }
@@ -748,6 +754,7 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis,
     replication_get_error_all(&local_err);
     if (local_err) {
         error_propagate(errp, local_err);
+        vmstate_loading = false;
         qemu_mutex_unlock_iothread();
         return;
     }
@@ -756,6 +763,7 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis,
     replication_do_checkpoint_all(&local_err);
     if (local_err) {
         error_propagate(errp, local_err);
+        vmstate_loading = false;
         qemu_mutex_unlock_iothread();
         return;
     }
@@ -767,6 +775,7 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis,
 
     if (local_err) {
         error_propagate(errp, local_err);
+        vmstate_loading = false;
         qemu_mutex_unlock_iothread();
         return;
     }
@@ -777,17 +786,12 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis,
     qemu_mutex_unlock_iothread();
 
     if (failover_get_state() == FAILOVER_STATUS_RELAUNCH) {
-        failover_set_state(FAILOVER_STATUS_RELAUNCH,
-                        FAILOVER_STATUS_NONE);
-        failover_request_active(NULL);
         return;
     }
 
     colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_LOADED,
                  &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-    }
+    error_propagate(errp, local_err);
 }
 
 static void colo_wait_handle_message(MigrationIncomingState *mis,
@@ -878,6 +882,14 @@ void *colo_process_incoming_thread(void *opaque)
             error_report_err(local_err);
             break;
         }
+
+        if (failover_get_state() == FAILOVER_STATUS_RELAUNCH) {
+            failover_set_state(FAILOVER_STATUS_RELAUNCH,
+                            FAILOVER_STATUS_NONE);
+            failover_request_active(NULL);
+            break;
+        }
+
         if (failover_get_state() != FAILOVER_STATUS_NONE) {
             error_report("failover request");
             break;
@@ -885,8 +897,6 @@ void *colo_process_incoming_thread(void *opaque)
     }
 
 out:
-    vmstate_loading = false;
-
     /*
      * There are only two reasons we can get here, some error happened
      * or the user triggered failover.