COLO: Introduce state to record failover process

When handling failover, COLO processes differently according to
the different stage of failover process, here we introduce a global
atomic variable to record the status of failover.

We add four failover status to indicate the different stage of failover process.
You should use the helpers to get and set the value.

Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Amit Shah <amit.shah@redhat.com>
Signed-off-by: Amit Shah <amit@amitshah.net>

5 files changed, 69 insertions, 0 deletions

diff --git a/include/migration/failover.h b/include/migration/failover.h
index 32747350687..7e0f36a2742 100644
--- a/include/migration/failover.h
+++ b/include/migration/failover.h
@@ -14,7 +14,12 @@
 #define QEMU_FAILOVER_H
 
 #include "qemu-common.h"
+#include "qapi-types.h"
 
+void failover_init_state(void);
+FailoverStatus failover_set_state(FailoverStatus old_state,
+                                     FailoverStatus new_state);
+FailoverStatus failover_get_state(void);
 void failover_request_active(Error **errp);
 
 #endif
diff --git a/migration/colo-failover.c b/migration/colo-failover.c
index e31fc10c826..6cca039eb99 100644
--- a/migration/colo-failover.c
+++ b/migration/colo-failover.c
@@ -15,22 +15,63 @@
 #include "migration/failover.h"
 #include "qmp-commands.h"
 #include "qapi/qmp/qerror.h"
+#include "qemu/error-report.h"
+#include "trace.h"
 
 static QEMUBH *failover_bh;
+static FailoverStatus failover_state;
 
 static void colo_failover_bh(void *opaque)
 {
+    int old_state;
+
     qemu_bh_delete(failover_bh);
     failover_bh = NULL;
+
+    old_state = failover_set_state(FAILOVER_STATUS_REQUIRE,
+                                   FAILOVER_STATUS_ACTIVE);
+    if (old_state != FAILOVER_STATUS_REQUIRE) {
+        error_report("Unknown error for failover, old_state = %s",
+                    FailoverStatus_lookup[old_state]);
+        return;
+    }
+
     /* TODO: Do failover work */
 }
 
 void failover_request_active(Error **errp)
 {
+   if (failover_set_state(FAILOVER_STATUS_NONE,
+        FAILOVER_STATUS_REQUIRE) != FAILOVER_STATUS_NONE) {
+        error_setg(errp, "COLO failover is already actived");
+        return;
+    }
     failover_bh = qemu_bh_new(colo_failover_bh, NULL);
     qemu_bh_schedule(failover_bh);
 }
 
+void failover_init_state(void)
+{
+    failover_state = FAILOVER_STATUS_NONE;
+}
+
+FailoverStatus failover_set_state(FailoverStatus old_state,
+                    FailoverStatus new_state)
+{
+    FailoverStatus old;
+
+    old = atomic_cmpxchg(&failover_state, old_state, new_state);
+    if (old == old_state) {
+        trace_colo_failover_set_state(FailoverStatus_lookup[new_state]);
+    }
+    return old;
+}
+
+FailoverStatus failover_get_state(void)
+{
+    return atomic_read(&failover_state);
+}
+
 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 12fa0b41115..6b32c9183c6 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -232,6 +232,8 @@ static void colo_process_checkpoint(MigrationState *s)
     Error *local_err = NULL;
     int ret;
 
+    failover_init_state();
+
     s->rp_state.from_dst_file = qemu_file_get_return_path(s->to_dst_file);
     if (!s->rp_state.from_dst_file) {
         error_report("Open QEMUFile from_dst_file failed");
@@ -332,6 +334,8 @@ void *colo_process_incoming_thread(void *opaque)
     migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
                       MIGRATION_STATUS_COLO);
 
+    failover_init_state();
+
     mis->to_src_file = qemu_file_get_return_path(mis->from_src_file);
     if (!mis->to_src_file) {
         error_report("COLO incoming thread: Open QEMUFile to_src_file failed");
diff --git a/migration/trace-events b/migration/trace-events
index f374c8cf274..94134f700bb 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -212,3 +212,4 @@ migration_tls_incoming_handshake_complete(void) ""
 colo_vm_state_change(const char *old, const char *new) "Change '%s' => '%s'"
 colo_send_message(const char *msg) "Send '%s' message"
 colo_receive_message(const char *msg) "Receive '%s' message"
+colo_failover_set_state(const char *new_state) "new state %s"
diff --git a/qapi-schema.json b/qapi-schema.json
index a18484115f6..8a7b5270910 100644
--- a/qapi-schema.json
+++ b/qapi-schema.json
@@ -840,6 +840,24 @@
   'data': [ 'unknown', 'primary', 'secondary'] }
 
 ##
+# @FailoverStatus
+#
+# An enumeration of COLO failover status
+#
+# @none: no failover has ever happened
+#
+# @require: got failover requirement but not handled
+#
+# @active: in the process of doing failover
+#
+# @completed: finish the process of failover
+#
+# Since: 2.8
+##
+{ 'enum': 'FailoverStatus',
+  'data': [ 'none', 'require', 'active', 'completed'] }
+
+##
 # @x-colo-lost-heartbeat
 #
 # Tell qemu that heartbeat is lost, request it to do takeover procedures.