summary refs log tree commit diff stats
path: root/hw/vfio/migration.c
diff options
context:
space:
mode:
Diffstat (limited to 'hw/vfio/migration.c')
-rw-r--r--hw/vfio/migration.c106
1 files changed, 91 insertions, 15 deletions
diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
index 2674f4bc47..da43dcd2fe 100644
--- a/hw/vfio/migration.c
+++ b/hw/vfio/migration.c
@@ -71,8 +71,12 @@ static const char *mig_state_to_str(enum vfio_device_mig_state state)
         return "STOP_COPY";
     case VFIO_DEVICE_STATE_RESUMING:
         return "RESUMING";
+    case VFIO_DEVICE_STATE_RUNNING_P2P:
+        return "RUNNING_P2P";
     case VFIO_DEVICE_STATE_PRE_COPY:
         return "PRE_COPY";
+    case VFIO_DEVICE_STATE_PRE_COPY_P2P:
+        return "PRE_COPY_P2P";
     default:
         return "UNKNOWN STATE";
     }
@@ -331,6 +335,36 @@ static bool vfio_precopy_supported(VFIODevice *vbasedev)
 
 /* ---------------------------------------------------------------------- */
 
+static int vfio_save_prepare(void *opaque, Error **errp)
+{
+    VFIODevice *vbasedev = opaque;
+
+    /*
+     * Snapshot doesn't use postcopy nor background snapshot, so allow snapshot
+     * even if they are on.
+     */
+    if (runstate_check(RUN_STATE_SAVE_VM)) {
+        return 0;
+    }
+
+    if (migrate_postcopy_ram()) {
+        error_setg(
+            errp, "%s: VFIO migration is not supported with postcopy migration",
+            vbasedev->name);
+        return -EOPNOTSUPP;
+    }
+
+    if (migrate_background_snapshot()) {
+        error_setg(
+            errp,
+            "%s: VFIO migration is not supported with background snapshot",
+            vbasedev->name);
+        return -EOPNOTSUPP;
+    }
+
+    return 0;
+}
+
 static int vfio_save_setup(QEMUFile *f, void *opaque)
 {
     VFIODevice *vbasedev = opaque;
@@ -383,6 +417,19 @@ static void vfio_save_cleanup(void *opaque)
     VFIODevice *vbasedev = opaque;
     VFIOMigration *migration = vbasedev->migration;
 
+    /*
+     * Changing device state from STOP_COPY to STOP can take time. Do it here,
+     * after migration has completed, so it won't increase downtime.
+     */
+    if (migration->device_state == VFIO_DEVICE_STATE_STOP_COPY) {
+        /*
+         * If setting the device in STOP state fails, the device should be
+         * reset. To do so, use ERROR state as a recover state.
+         */
+        vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_STOP,
+                                 VFIO_DEVICE_STATE_ERROR);
+    }
+
     g_free(migration->data_buffer);
     migration->data_buffer = NULL;
     migration->precopy_init_size = 0;
@@ -398,7 +445,7 @@ static void vfio_state_pending_estimate(void *opaque, uint64_t *must_precopy,
     VFIODevice *vbasedev = opaque;
     VFIOMigration *migration = vbasedev->migration;
 
-    if (migration->device_state != VFIO_DEVICE_STATE_PRE_COPY) {
+    if (!vfio_device_state_is_precopy(vbasedev)) {
         return;
     }
 
@@ -431,7 +478,7 @@ static void vfio_state_pending_exact(void *opaque, uint64_t *must_precopy,
     vfio_query_stop_copy_size(vbasedev, &stop_copy_size);
     *must_precopy += stop_copy_size;
 
-    if (migration->device_state == VFIO_DEVICE_STATE_PRE_COPY) {
+    if (vfio_device_state_is_precopy(vbasedev)) {
         vfio_query_precopy_size(migration);
 
         *must_precopy +=
@@ -446,9 +493,8 @@ static void vfio_state_pending_exact(void *opaque, uint64_t *must_precopy,
 static bool vfio_is_active_iterate(void *opaque)
 {
     VFIODevice *vbasedev = opaque;
-    VFIOMigration *migration = vbasedev->migration;
 
-    return migration->device_state == VFIO_DEVICE_STATE_PRE_COPY;
+    return vfio_device_state_is_precopy(vbasedev);
 }
 
 static int vfio_save_iterate(QEMUFile *f, void *opaque)
@@ -508,12 +554,6 @@ static int vfio_save_complete_precopy(QEMUFile *f, void *opaque)
         return ret;
     }
 
-    /*
-     * If setting the device in STOP state fails, the device should be reset.
-     * To do so, use ERROR state as a recover state.
-     */
-    ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_STOP,
-                                   VFIO_DEVICE_STATE_ERROR);
     trace_vfio_save_complete_precopy(vbasedev->name, ret);
 
     return ret;
@@ -630,6 +670,7 @@ static bool vfio_switchover_ack_needed(void *opaque)
 }
 
 static const SaveVMHandlers savevm_vfio_handlers = {
+    .save_prepare = vfio_save_prepare,
     .save_setup = vfio_save_setup,
     .save_cleanup = vfio_save_cleanup,
     .state_pending_estimate = vfio_state_pending_estimate,
@@ -646,18 +687,50 @@ static const SaveVMHandlers savevm_vfio_handlers = {
 
 /* ---------------------------------------------------------------------- */
 
-static void vfio_vmstate_change(void *opaque, bool running, RunState state)
+static void vfio_vmstate_change_prepare(void *opaque, bool running,
+                                        RunState state)
 {
     VFIODevice *vbasedev = opaque;
     VFIOMigration *migration = vbasedev->migration;
     enum vfio_device_mig_state new_state;
     int ret;
 
+    new_state = migration->device_state == VFIO_DEVICE_STATE_PRE_COPY ?
+                    VFIO_DEVICE_STATE_PRE_COPY_P2P :
+                    VFIO_DEVICE_STATE_RUNNING_P2P;
+
+    /*
+     * If setting the device in new_state fails, the device should be reset.
+     * To do so, use ERROR state as a recover state.
+     */
+    ret = vfio_migration_set_state(vbasedev, new_state,
+                                   VFIO_DEVICE_STATE_ERROR);
+    if (ret) {
+        /*
+         * Migration should be aborted in this case, but vm_state_notify()
+         * currently does not support reporting failures.
+         */
+        if (migrate_get_current()->to_dst_file) {
+            qemu_file_set_error(migrate_get_current()->to_dst_file, ret);
+        }
+    }
+
+    trace_vfio_vmstate_change_prepare(vbasedev->name, running,
+                                      RunState_str(state),
+                                      mig_state_to_str(new_state));
+}
+
+static void vfio_vmstate_change(void *opaque, bool running, RunState state)
+{
+    VFIODevice *vbasedev = opaque;
+    enum vfio_device_mig_state new_state;
+    int ret;
+
     if (running) {
         new_state = VFIO_DEVICE_STATE_RUNNING;
     } else {
         new_state =
-            (migration->device_state == VFIO_DEVICE_STATE_PRE_COPY &&
+            (vfio_device_state_is_precopy(vbasedev) &&
              (state == RUN_STATE_FINISH_MIGRATE || state == RUN_STATE_PAUSED)) ?
                 VFIO_DEVICE_STATE_STOP_COPY :
                 VFIO_DEVICE_STATE_STOP;
@@ -753,6 +826,7 @@ static int vfio_migration_init(VFIODevice *vbasedev)
     char id[256] = "";
     g_autofree char *path = NULL, *oid = NULL;
     uint64_t mig_flags = 0;
+    VMChangeStateHandler *prepare_cb;
 
     if (!vbasedev->ops->vfio_get_object) {
         return -EINVAL;
@@ -793,9 +867,11 @@ static int vfio_migration_init(VFIODevice *vbasedev)
     register_savevm_live(id, VMSTATE_INSTANCE_ID_ANY, 1, &savevm_vfio_handlers,
                          vbasedev);
 
-    migration->vm_state = qdev_add_vm_change_state_handler(vbasedev->dev,
-                                                           vfio_vmstate_change,
-                                                           vbasedev);
+    prepare_cb = migration->mig_flags & VFIO_MIGRATION_P2P ?
+                     vfio_vmstate_change_prepare :
+                     NULL;
+    migration->vm_state = qdev_add_vm_change_state_handler_full(
+        vbasedev->dev, vfio_vmstate_change, prepare_cb, vbasedev);
     migration->migration_state.notify = vfio_migration_state_notifier;
     add_migration_state_change_notifier(&migration->migration_state);