[Qemu-devel] [PATCH COLO-Frame v16 19/35] COLO: Implement failover work for Primary VM

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

For PVM, if there is failover request from users.
The colo thread will exit the loop while the failover BH does the
cleanup work and resumes VM.

Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
v13:
- Add Reviewed-by tag
v12:
- Fix error report and remove unnecessary check in
  primary_vm_do_failover() (Dave's suggestion)
v11:
- Don't call migration_end() in primary_vm_do_failover(),
 The cleanup work will be done in migration_thread().
- Remove vm_start() in primary_vm_do_failover() which also been
  done in migraiton_thread()
v10:
- Call migration_end() in primary_vm_do_failover()
---
 include/migration/colo.h     |  3 +++
 include/migration/failover.h |  1 +
 migration/colo-failover.c    |  7 +++++-
 migration/colo.c             | 53 +++++++++++++++++++++++++++++++++++++++++---
 4 files changed, 60 insertions(+), 4 deletions(-)

diff --git a/include/migration/colo.h b/include/migration/colo.h
index e9ac2c3..e32eef4 100644
--- a/include/migration/colo.h
+++ b/include/migration/colo.h
@@ -32,4 +32,7 @@ void *colo_process_incoming_thread(void *opaque);
 bool migration_incoming_in_colo_state(void);
 
 COLOMode get_colo_mode(void);
+
+/* failover */
+void colo_do_failover(MigrationState *s);
 #endif
diff --git a/include/migration/failover.h b/include/migration/failover.h
index fe71bb4..c4bd81e 100644
--- a/include/migration/failover.h
+++ b/include/migration/failover.h
@@ -26,5 +26,6 @@ void failover_init_state(void);
 int failover_set_state(int old_state, int new_state);
 int failover_get_state(void);
 void failover_request_active(Error **errp);
+bool failover_request_is_active(void);
 
 #endif
diff --git a/migration/colo-failover.c b/migration/colo-failover.c
index 69aac55..fa84172 100644
--- a/migration/colo-failover.c
+++ b/migration/colo-failover.c
@@ -33,7 +33,7 @@ static void colo_failover_bh(void *opaque)
         error_report("Unkown error for failover, old_state=%d", old_state);
         return;
     }
-    /*TODO: Do failover work */
+    colo_do_failover(NULL);
 }
 
 void failover_request_active(Error **errp)
@@ -68,6 +68,11 @@ int failover_get_state(void)
     return atomic_read(&failover_state);
 }
 
+bool failover_request_is_active(void)
+{
+    return failover_get_state() != FAILOVER_STATUS_NONE;
+}
+
 void qmp_x_colo_lost_heartbeat(Error **errp)
 {
     if (get_colo_mode() == COLO_MODE_UNKNOWN) {
diff --git a/migration/colo.c b/migration/colo.c
index af1f8c2..bdde182 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -41,6 +41,40 @@ bool migration_incoming_in_colo_state(void)
     return mis && (mis->state == MIGRATION_STATUS_COLO);
 }
 
+static bool colo_runstate_is_stopped(void)
+{
+    return runstate_check(RUN_STATE_COLO) || !runstate_is_running();
+}
+
+static void primary_vm_do_failover(void)
+{
+    MigrationState *s = migrate_get_current();
+    int old_state;
+
+    migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
+                      MIGRATION_STATUS_COMPLETED);
+
+    old_state = failover_set_state(FAILOVER_STATUS_HANDLING,
+                                   FAILOVER_STATUS_COMPLETED);
+    if (old_state != FAILOVER_STATUS_HANDLING) {
+        error_report("Incorrect state (%d) while doing failover for Primary VM",
+                     old_state);
+        return;
+    }
+}
+
+void colo_do_failover(MigrationState *s)
+{
+    /* Make sure vm stopped while failover */
+    if (!colo_runstate_is_stopped()) {
+        vm_stop_force_state(RUN_STATE_COLO);
+    }
+
+    if (get_colo_mode() == COLO_MODE_PRIMARY) {
+        primary_vm_do_failover();
+    }
+}
+
 static void colo_send_message(QEMUFile *f, COLOMessage msg,
                               Error **errp)
 {
@@ -167,9 +201,20 @@ static int colo_do_checkpoint_transaction(MigrationState *s,
     }
 
     qemu_mutex_lock_iothread();
+    if (failover_request_is_active()) {
+        qemu_mutex_unlock_iothread();
+        goto out;
+    }
     vm_stop_force_state(RUN_STATE_COLO);
     qemu_mutex_unlock_iothread();
     trace_colo_vm_state_change("run", "stop");
+    /*
+     * failover request bh could be called after
+     * vm_stop_force_state so we check failover_request_is_active() again.
+     */
+    if (failover_request_is_active()) {
+        goto out;
+    }
 
     /* Disable block migration */
     s->params.blk = 0;
@@ -267,6 +312,11 @@ static void colo_process_checkpoint(MigrationState *s)
     trace_colo_vm_state_change("stop", "run");
 
     while (s->state == MIGRATION_STATUS_COLO) {
+        if (failover_request_is_active()) {
+            error_report("failover request");
+            goto out;
+        }
+
         current_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
         if (current_time - checkpoint_time <
             s->parameters[MIGRATION_PARAMETER_X_CHECKPOINT_DELAY]) {
@@ -289,9 +339,6 @@ out:
     if (local_err) {
         error_report_err(local_err);
     }
-    migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
-                      MIGRATION_STATUS_COMPLETED);
-
     qsb_free(buffer);
     buffer = NULL;
 
-- 
1.8.3.1