[Qemu-devel] [PATCH COLO-Frame v9 24/32] COLO failover: Don't do failover during loading VM's state

[zhanghailiang <zhang.zhanghailiang@huawei.com>]

We should not do failover work while the main thread is loading
VM's state, otherwise it will destroy the consistent of VM's memory and
device state.

Here we add a new failover status 'RELAUNCH' which means we should
relaunch the process of failover.

Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
---
 include/migration/failover.h |  2 ++
 migration/colo.c             | 24 ++++++++++++++++++++++++
 2 files changed, 26 insertions(+)

diff --git a/include/migration/failover.h b/include/migration/failover.h
index fba3931..e115d25 100644
--- a/include/migration/failover.h
+++ b/include/migration/failover.h
@@ -20,6 +20,8 @@ typedef enum COLOFailoverStatus {
     FAILOVER_STATUS_REQUEST = 1, /* Request but not handled */
     FAILOVER_STATUS_HANDLING = 2, /* In the process of handling failover */
     FAILOVER_STATUS_COMPLETED = 3, /* Finish the failover process */
+    /* Optional, Relaunch the failover process, again 'NONE' -> 'COMPLETED' */
+    FAILOVER_STATUS_RELAUNCH = 4,
 } COLOFailoverStatus;
 
 void failover_init_state(void);
diff --git a/migration/colo.c b/migration/colo.c
index e443dfa..6bfebd1 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -35,6 +35,7 @@
 #define DEFAULT_FAILOVER_DELAY 2000
 
 static QEMUBH *colo_bh;
+static bool vmstate_loading;
 /* colo buffer */
 #define COLO_BUFFER_BASE_SIZE (4 * 1024 * 1024)
 
@@ -67,6 +68,19 @@ static void secondary_vm_do_failover(void)
     int old_state;
     MigrationIncomingState *mis = migration_incoming_get_current();
 
+    /* Can not do failover during the process of VM's loading VMstate, Or
+      * it will break the secondary VM.
+      */
+    if (vmstate_loading) {
+        old_state = failover_set_state(FAILOVER_STATUS_HANDLING,
+                                       FAILOVER_STATUS_RELAUNCH);
+        if (old_state != FAILOVER_STATUS_HANDLING) {
+            error_report("Unknow error while do failover for secondary VM,"
+                         "old_state: %d", old_state);
+        }
+        return;
+    }
+
     migrate_set_state(&mis->state, MIGRATION_STATUS_COLO,
                       MIGRATION_STATUS_COMPLETED);
 
@@ -557,13 +571,23 @@ void *colo_process_incoming_thread(void *opaque)
 
         qemu_mutex_lock_iothread();
         qemu_system_reset(VMRESET_SILENT);
+        vmstate_loading = true;
         if (qemu_loadvm_state(fb) < 0) {
             error_report("COLO: loadvm failed");
+            vmstate_loading = false;
             qemu_mutex_unlock_iothread();
             goto out;
         }
+
+        vmstate_loading = false;
         qemu_mutex_unlock_iothread();
 
+        if (failover_get_state() == FAILOVER_STATUS_RELAUNCH) {
+            failover_set_state(FAILOVER_STATUS_RELAUNCH, FAILOVER_STATUS_NONE);
+            failover_request_active(NULL);
+            goto out;
+        }
+
         ret = colo_ctl_put(mis->to_src_file, COLO_CMD_VMSTATE_LOADED, 0);
         if (ret < 0) {
             goto out;
-- 
1.8.3.1