[PULL 16/27] vfio/migration: Add new switchover-ack mechanism

["Cédric Le Goater" <clg@redhat.com>]

From: Avihai Horon <avihaih@nvidia.com>

Add support for the new switchover-ack mechanism. This includes
requesting a switchover ACK on the first save_query_pending call (with
exact=false) if VFIO precopy is supported.

This achieves the same functionality of legacy switchover-ack but with
the new switchover-ack mechanism.

Keep legacy switchover-ack functionality for backward compatibility.

Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Avihai Horon <avihaih@nvidia.com>
Link: https://lore.kernel.org/qemu-devel/20260706085211.13905-12-avihaih@nvidia.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
 hw/vfio/vfio-migration-internal.h |  1 +
 hw/vfio/migration.c               | 13 ++++++++++++-
 hw/vfio/trace-events              |  2 +-
 3 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/hw/vfio/vfio-migration-internal.h b/hw/vfio/vfio-migration-internal.h
index a15fc74703998da1956a92c4fb8cfe9ff3a68867..dc741e51421eec6d4ad4d9ce0f9c0c2f6199788d 100644
--- a/hw/vfio/vfio-migration-internal.h
+++ b/hw/vfio/vfio-migration-internal.h
@@ -58,6 +58,7 @@ typedef struct VFIOMigration {
     bool multifd_transfer;
     VFIOMultifd *multifd;
     bool initial_data_sent;
+    bool request_switchover_ack;
 
     bool event_save_iterate_started;
     bool event_precopy_empty_hit;
diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
index 3ab6b7248fea34dec3b58e508f97c8be4c962ce4..ebe2eafded50cdc3c1518a2f1e768fdfe6722c5a 100644
--- a/hw/vfio/migration.c
+++ b/hw/vfio/migration.c
@@ -582,6 +582,9 @@ static int vfio_save_setup(QEMUFile *f, void *opaque, Error **errp)
             }
 
             vfio_query_precopy_size(migration);
+            if (migrate_switchover_ack() && !migrate_switchover_ack_legacy()) {
+                migration->request_switchover_ack = true;
+            }
 
             break;
         case VFIO_DEVICE_STATE_STOP:
@@ -634,6 +637,7 @@ static void vfio_save_cleanup(void *opaque)
     migration->precopy_init_size = 0;
     migration->precopy_dirty_size = 0;
     migration->initial_data_sent = false;
+    migration->request_switchover_ack = false;
     vfio_migration_cleanup(vbasedev);
     trace_vfio_save_cleanup(vbasedev->name);
 }
@@ -655,6 +659,7 @@ static void vfio_state_pending(void *opaque, MigPendingData *pending,
     VFIODevice *vbasedev = opaque;
     VFIOMigration *migration = vbasedev->migration;
     uint64_t precopy_size, stopcopy_size;
+    bool request_switchover_ack = false;
 
     /*
      * The final pending query runs during switchover downtime. VFIO does not
@@ -676,10 +681,16 @@ static void vfio_state_pending(void *opaque, MigPendingData *pending,
 
     pending->precopy_bytes += precopy_size;
     pending->stopcopy_bytes += stopcopy_size;
+    if (migration->request_switchover_ack) {
+        pending->switchover_ack_pending++;
+        request_switchover_ack = true;
+        migration->request_switchover_ack = false;
+    }
 
     trace_vfio_state_pending(vbasedev->name, migration->stopcopy_size,
                              migration->precopy_init_size,
-                             migration->precopy_dirty_size, exact, final);
+                             migration->precopy_dirty_size,
+                             request_switchover_ack, exact, final);
 }
 
 static bool vfio_is_active_iterate(void *opaque)
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index fe0d2cc06f946b3f0db28d13994fbd0dfd854fbd..c9d143826d38d77048ecf179cbda19a7184989a4 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -176,7 +176,7 @@ vfio_save_device_config_state(const char *name) " (%s)"
 vfio_save_iterate(const char *name, uint64_t precopy_init_size, uint64_t precopy_dirty_size) " (%s) precopy initial size %"PRIu64" precopy dirty size %"PRIu64
 vfio_save_iterate_start(const char *name) " (%s)"
 vfio_save_setup(const char *name, uint64_t data_buffer_size) " (%s) data buffer size %"PRIu64
-vfio_state_pending(const char *name, uint64_t stopcopy_size, uint64_t precopy_init_size, uint64_t precopy_dirty_size, bool exact, bool final) " (%s) stopcopy size %"PRIu64", precopy initial size %"PRIu64", precopy dirty size %"PRIu64", exact %d, final %d"
+vfio_state_pending(const char *name, uint64_t stopcopy_size, uint64_t precopy_init_size, uint64_t precopy_dirty_size, bool request_switchover_ack, bool exact, bool final) " (%s) stopcopy size %"PRIu64", precopy initial size %"PRIu64", precopy dirty size %"PRIu64", request switchover ack %d, exact %d, final %d"
 vfio_send_init_data_flag(const char *name) " (%s)"
 vfio_vmstate_change(const char *name, int running, const char *reason, const char *dev_state) " (%s) running %d reason %s device state %s"
 vfio_vmstate_change_prepare(const char *name, int running, const char *reason, const char *dev_state) " (%s) running %d reason %s device state %s"
-- 
2.54.0