[Qemu-devel] [PATCH COLO-Frame v11 22/39] COLO failover: Introduce state to record failover process

[zhanghailiang]

When handling failover, we do different things 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 <address@hidden>
Reviewed-by: Dr. David Alan Gilbert <address@hidden>
---
v11:
- fix several typos found by Dave
- Add Reviewed-by tag
---
 include/migration/failover.h | 10 ++++++++++
 migration/colo-failover.c    | 37 +++++++++++++++++++++++++++++++++++++
 migration/colo.c             |  4 ++++
 trace-events                 |  1 +
 4 files changed, 52 insertions(+)

diff --git a/include/migration/failover.h b/include/migration/failover.h
index 1785b52..882c625 100644
--- a/include/migration/failover.h
+++ b/include/migration/failover.h
@@ -15,6 +15,16 @@
 
 #include "qemu-common.h"
 
+typedef enum COLOFailoverStatus {
+    FAILOVER_STATUS_NONE = 0,
+    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 */
+} COLOFailoverStatus;
+
+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);
 
 #endif
diff --git a/migration/colo-failover.c b/migration/colo-failover.c
index e3897c6..1b1be24 100644
--- a/migration/colo-failover.c
+++ b/migration/colo-failover.c
@@ -14,22 +14,59 @@
 #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 COLOFailoverStatus 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_REQUEST,
+                                   FAILOVER_STATUS_HANDLING);
+    if (old_state != FAILOVER_STATUS_REQUEST) {
+        error_report("Unkown error for failover, old_state=%d", old_state);
+        return;
+    }
     /*TODO: Do failover work */
 }
 
 void failover_request_active(Error **errp)
 {
+   if (failover_set_state(FAILOVER_STATUS_NONE, FAILOVER_STATUS_REQUEST)
+         != 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;
+}
+
+int failover_set_state(int old_state, int new_state)
+{
+    int old;
+
+    old = atomic_cmpxchg(&failover_state, old_state, new_state);
+    if (old == old_state) {
+        trace_colo_failover_set_state(new_state);
+    }
+    return old;
+}
+
+int 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 2c4fc1c..cedfc63 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -189,6 +189,8 @@ static void colo_process_checkpoint(MigrationState *s)
     int ret = 0;
     uint64_t value;
 
+    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) {
         ret = -EINVAL;
@@ -307,6 +309,8 @@ 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) {
         ret = -EINVAL;
diff --git a/trace-events b/trace-events
index f158d2a..b80c1e0 100644
--- a/trace-events
+++ b/trace-events
@@ -1582,6 +1582,7 @@ postcopy_ram_incoming_cleanup_join(void) ""
 colo_vm_state_change(const char *old, const char *new) "Change '%s' => '%s'"
 colo_ctl_put(const char *msg, uint64_t value) "Send '%s' cmd, value: %" 
PRIu64""
 colo_ctl_get(const char *msg, uint64_t value) "Receive '%s' cmd, value: %" 
PRIu64""
+colo_failover_set_state(int new_state) "new state %d"
 
 # kvm-all.c
 kvm_ioctl(int type, void *arg) "type 0x%x, arg %p"
-- 
1.8.3.1