migration: add new migration state wait-unplug

This patch adds a new migration state called wait-unplug.  It is entered
after the SETUP state if failover devices are present. It will transition
into ACTIVE once all devices were succesfully unplugged from the guest.

So if a guest doesn't respond or takes long to honor the unplug request
the user will see the migration state 'wait-unplug'.

In the migration thread we query failover devices if they're are still
pending the guest unplug. When all are unplugged the migration
continues. If one device won't unplug migration will stay in wait_unplug
state.

Signed-off-by: Jens Freimann <jfreimann@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Message-Id: <20191029114905.6856-9-jfreimann@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

1 files changed, 21 insertions, 0 deletions

diff --git a/migration/migration.c b/migration/migration.c
index 4133ed2684..354ad072fa 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -52,6 +52,7 @@
 #include "hw/qdev-properties.h"
 #include "monitor/monitor.h"
 #include "net/announce.h"
+#include "qemu/queue.h"
 
 #define MAX_THROTTLE  (32 << 20)      /* Migration transfer speed throttling */
 
@@ -819,6 +820,7 @@ bool migration_is_setup_or_active(int state)
     case MIGRATION_STATUS_SETUP:
     case MIGRATION_STATUS_PRE_SWITCHOVER:
     case MIGRATION_STATUS_DEVICE:
+    case MIGRATION_STATUS_WAIT_UNPLUG:
         return true;
 
     default:
@@ -954,6 +956,9 @@ static void fill_source_migration_info(MigrationInfo *info)
     case MIGRATION_STATUS_CANCELLED:
         info->has_status = true;
         break;
+    case MIGRATION_STATUS_WAIT_UNPLUG:
+        info->has_status = true;
+        break;
     }
     info->status = s->state;
 }
@@ -1694,6 +1699,7 @@ bool migration_is_idle(void)
     case MIGRATION_STATUS_COLO:
     case MIGRATION_STATUS_PRE_SWITCHOVER:
     case MIGRATION_STATUS_DEVICE:
+    case MIGRATION_STATUS_WAIT_UNPLUG:
         return false;
     case MIGRATION_STATUS__MAX:
         g_assert_not_reached();
@@ -3264,6 +3270,19 @@ static void *migration_thread(void *opaque)
 
     qemu_savevm_state_setup(s->to_dst_file);
 
+    if (qemu_savevm_nr_failover_devices()) {
+        migrate_set_state(&s->state, MIGRATION_STATUS_SETUP,
+                          MIGRATION_STATUS_WAIT_UNPLUG);
+
+        while (s->state == MIGRATION_STATUS_WAIT_UNPLUG &&
+               qemu_savevm_state_guest_unplug_pending()) {
+            qemu_sem_timedwait(&s->wait_unplug_sem, 250);
+        }
+
+        migrate_set_state(&s->state, MIGRATION_STATUS_WAIT_UNPLUG,
+                MIGRATION_STATUS_ACTIVE);
+    }
+
     s->setup_time = qemu_clock_get_ms(QEMU_CLOCK_HOST) - setup_start;
     migrate_set_state(&s->state, MIGRATION_STATUS_SETUP,
                       MIGRATION_STATUS_ACTIVE);
@@ -3511,6 +3530,7 @@ static void migration_instance_finalize(Object *obj)
     qemu_mutex_destroy(&ms->qemu_file_lock);
     g_free(params->tls_hostname);
     g_free(params->tls_creds);
+    qemu_sem_destroy(&ms->wait_unplug_sem);
     qemu_sem_destroy(&ms->rate_limit_sem);
     qemu_sem_destroy(&ms->pause_sem);
     qemu_sem_destroy(&ms->postcopy_pause_sem);
@@ -3556,6 +3576,7 @@ static void migration_instance_init(Object *obj)
     qemu_sem_init(&ms->postcopy_pause_rp_sem, 0);
     qemu_sem_init(&ms->rp_state.rp_sem, 0);
     qemu_sem_init(&ms->rate_limit_sem, 0);
+    qemu_sem_init(&ms->wait_unplug_sem, 0);
     qemu_mutex_init(&ms->qemu_file_lock);
 }