migration: Implement switchover ack logic

Implement switchover ack logic. This prevents the source from stopping
the VM and completing the migration until an ACK is received from the
destination that it's OK to do so.

To achieve this, a new SaveVMHandlers handler switchover_ack_needed()
and a new return path message MIG_RP_MSG_SWITCHOVER_ACK are added.

The switchover_ack_needed() handler is called during migration setup in
the destination to check if switchover ack is used by the migrated
device.

When switchover is approved by all migrated devices in the destination
that support this capability, the MIG_RP_MSG_SWITCHOVER_ACK return path
message is sent to the source to notify it that it's OK to do
switchover.

Signed-off-by: Avihai Horon <avihaih@nvidia.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Tested-by: YangHang Liu <yanghliu@redhat.com>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>

1 files changed, 30 insertions, 2 deletions

diff --git a/migration/migration.c b/migration/migration.c
index dc05c6f6ea..7653787f74 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -78,6 +78,7 @@ enum mig_rp_message_type {
     MIG_RP_MSG_REQ_PAGES,    /* data (start: be64, len: be32) */
     MIG_RP_MSG_RECV_BITMAP,  /* send recved_bitmap back to source */
     MIG_RP_MSG_RESUME_ACK,   /* tell source that we are ready to resume */
+    MIG_RP_MSG_SWITCHOVER_ACK, /* Tell source it's OK to do switchover */
 
     MIG_RP_MSG_MAX
 };
@@ -760,6 +761,11 @@ bool migration_has_all_channels(void)
     return true;
 }
 
+int migrate_send_rp_switchover_ack(MigrationIncomingState *mis)
+{
+    return migrate_send_rp_message(mis, MIG_RP_MSG_SWITCHOVER_ACK, 0, NULL);
+}
+
 /*
  * Send a 'SHUT' message on the return channel with the given value
  * to indicate that we've finished with the RP.  Non-0 value indicates
@@ -1405,6 +1411,7 @@ void migrate_init(MigrationState *s)
     s->vm_old_state = -1;
     s->iteration_initial_bytes = 0;
     s->threshold_size = 0;
+    s->switchover_acked = false;
 }
 
 int migrate_add_blocker_internal(Error *reason, Error **errp)
@@ -1721,6 +1728,7 @@ static struct rp_cmd_args {
     [MIG_RP_MSG_REQ_PAGES_ID]   = { .len = -1, .name = "REQ_PAGES_ID" },
     [MIG_RP_MSG_RECV_BITMAP]    = { .len = -1, .name = "RECV_BITMAP" },
     [MIG_RP_MSG_RESUME_ACK]     = { .len =  4, .name = "RESUME_ACK" },
+    [MIG_RP_MSG_SWITCHOVER_ACK] = { .len =  0, .name = "SWITCHOVER_ACK" },
     [MIG_RP_MSG_MAX]            = { .len = -1, .name = "MAX" },
 };
 
@@ -1959,6 +1967,11 @@ retry:
             }
             break;
 
+        case MIG_RP_MSG_SWITCHOVER_ACK:
+            ms->switchover_acked = true;
+            trace_source_return_path_thread_switchover_acked();
+            break;
+
         default:
             break;
         }
@@ -2693,6 +2706,20 @@ static void migration_update_counters(MigrationState *s,
                               bandwidth, s->threshold_size);
 }
 
+static bool migration_can_switchover(MigrationState *s)
+{
+    if (!migrate_switchover_ack()) {
+        return true;
+    }
+
+    /* No reason to wait for switchover ACK if VM is stopped */
+    if (!runstate_is_running()) {
+        return true;
+    }
+
+    return s->switchover_acked;
+}
+
 /* Migration thread iteration status */
 typedef enum {
     MIG_ITERATE_RESUME,         /* Resume current iteration */
@@ -2708,6 +2735,7 @@ static MigIterateState migration_iteration_run(MigrationState *s)
 {
     uint64_t must_precopy, can_postcopy;
     bool in_postcopy = s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE;
+    bool can_switchover = migration_can_switchover(s);
 
     qemu_savevm_state_pending_estimate(&must_precopy, &can_postcopy);
     uint64_t pending_size = must_precopy + can_postcopy;
@@ -2720,14 +2748,14 @@ static MigIterateState migration_iteration_run(MigrationState *s)
         trace_migrate_pending_exact(pending_size, must_precopy, can_postcopy);
     }
 
-    if (!pending_size || pending_size < s->threshold_size) {
+    if ((!pending_size || pending_size < s->threshold_size) && can_switchover) {
         trace_migration_thread_low_pending(pending_size);
         migration_completion(s);
         return MIG_ITERATE_BREAK;
     }
 
     /* Still a significant amount to transfer */
-    if (!in_postcopy && must_precopy <= s->threshold_size &&
+    if (!in_postcopy && must_precopy <= s->threshold_size && can_switchover &&
         qatomic_read(&s->start_postcopy)) {
         if (postcopy_start(s)) {
             error_report("%s: postcopy failed to start", __func__);