[Qemu-devel] [PATCH COLO-Frame v10 20/38] COLO: Implement failover work for Primary VM

[zhanghailiang]

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 <address@hidden>
Signed-off-by: Li Zhijian <address@hidden>
---
v10: Call migration_end() in primary_vm_do_failover()
---
 include/migration/colo.h      |  4 +++
 include/migration/failover.h  |  1 +
 include/migration/migration.h |  1 +
 migration/colo-failover.c     |  7 ++++-
 migration/colo.c              | 59 +++++++++++++++++++++++++++++++++++++++++--
 migration/ram.c               |  2 +-
 6 files changed, 70 insertions(+), 4 deletions(-)

diff --git a/include/migration/colo.h b/include/migration/colo.h
index 34e8127..3e375c1 100644
--- a/include/migration/colo.h
+++ b/include/migration/colo.h
@@ -37,4 +37,8 @@ int get_colo_mode(void);
 int colo_init_ram_cache(void);
 void colo_release_ram_cache(void);
 void colo_flush_ram_cache(void);
+
+/* failover */
+void colo_do_failover(MigrationState *s);
+
 #endif
diff --git a/include/migration/failover.h b/include/migration/failover.h
index 882c625..fba3931 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/include/migration/migration.h b/include/migration/migration.h
index 0c0309d..406874f 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -210,6 +210,7 @@ size_t ram_control_save_page(QEMUFile *f, ram_addr_t 
block_offset,
                              uint64_t *bytes_sent);
 
 void ram_mig_init(void);
+void migration_end(void);
 void savevm_skip_section_footers(void);
 void register_global_state(void);
 void global_state_set_optional(void);
diff --git a/migration/colo-failover.c b/migration/colo-failover.c
index ae06c16..33c82c1 100644
--- a/migration/colo-failover.c
+++ b/migration/colo-failover.c
@@ -32,7 +32,7 @@ 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)
@@ -67,6 +67,11 @@ 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 7732f60..95f1405 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -47,6 +47,45 @@ 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;
+
+    if (s->state != MIGRATION_STATUS_FAILED) {
+        migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
+                          MIGRATION_STATUS_COMPLETED);
+    }
+    migration_end();
+
+    vm_start();
+
+    old_state = failover_set_state(FAILOVER_STATUS_HANDLING,
+                                   FAILOVER_STATUS_COMPLETED);
+    if (old_state != FAILOVER_STATUS_HANDLING) {
+        error_report("Serious error while do failover for Primary VM,"
+                     "old_state: %d", 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();
+    }
+}
+
 /* colo checkpoint control helper */
 static int colo_ctl_put(QEMUFile *f, uint32_t cmd, uint64_t value)
 {
@@ -130,9 +169,22 @@ static int colo_do_checkpoint_transaction(MigrationState 
*s,
     }
 
     qemu_mutex_lock_iothread();
+    if (failover_request_is_active()) {
+        qemu_mutex_unlock_iothread();
+        ret = -1;
+        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()) {
+        ret = -1;
+        goto out;
+    }
 
     /* Disable block migration */
     s->params.blk = 0;
@@ -231,6 +283,11 @@ 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 < CHECKPOINT_MAX_PEROID) {
             g_usleep(100000);
@@ -248,8 +305,6 @@ out:
     if (ret < 0) {
         error_report("%s: %s", __func__, strerror(-ret));
     }
-    migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
-                      MIGRATION_STATUS_COMPLETED);
 
     qsb_free(buffer);
     buffer = NULL;
diff --git a/migration/ram.c b/migration/ram.c
index d7e0e37..8de5a5f 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -1102,7 +1102,7 @@ static void migration_bitmap_free(struct BitmapRcu *bmap)
     g_free(bmap);
 }
 
-static void migration_end(void)
+void migration_end(void)
 {
     /* caller have hold iothread lock or is in a bh, so there is
      * no writing race against this migration_bitmap
-- 
1.8.3.1