+
+ return ret;
+}
+
static int vfio_v1_load_buffer(QEMUFile *f, VFIODevice *vbasedev,
uint64_t data_size)
{
@@ -394,6 +484,14 @@ static int vfio_load_device_config_state(QEMUFile *f, void
*opaque)
return qemu_file_get_error(f);
}
+static void vfio_migration_cleanup(VFIODevice *vbasedev)
+{
+ VFIOMigration *migration = vbasedev->migration;
+
+ close(migration->data_fd);
+ migration->data_fd = -1;
+}
+
static void vfio_migration_v1_cleanup(VFIODevice *vbasedev)
{
VFIOMigration *migration = vbasedev->migration;
@@ -405,6 +503,18 @@ static void vfio_migration_v1_cleanup(VFIODevice *vbasedev)
/* ---------------------------------------------------------------------- */
+static int vfio_save_setup(QEMUFile *f, void *opaque)
+{
+ VFIODevice *vbasedev = opaque;
+
+ trace_vfio_save_setup(vbasedev->name);
+
+ qemu_put_be64(f, VFIO_MIG_FLAG_DEV_SETUP_STATE);
+ qemu_put_be64(f, VFIO_MIG_FLAG_END_OF_STATE);
+
+ return qemu_file_get_error(f);
+}
+
static int vfio_v1_save_setup(QEMUFile *f, void *opaque)
{
VFIODevice *vbasedev = opaque;
@@ -448,6 +558,14 @@ static int vfio_v1_save_setup(QEMUFile *f, void *opaque)
return 0;
}
+static void vfio_save_cleanup(void *opaque)
+{
+ VFIODevice *vbasedev = opaque;
+
+ vfio_migration_cleanup(vbasedev);
+ trace_vfio_save_cleanup(vbasedev->name);
+}
+
static void vfio_v1_save_cleanup(void *opaque)
{
VFIODevice *vbasedev = opaque;
@@ -456,6 +574,23 @@ static void vfio_v1_save_cleanup(void *opaque)
trace_vfio_save_cleanup(vbasedev->name);
}
+#define VFIO_MIG_PENDING_SIZE (512 * 1024 * 1024)
+static void vfio_save_pending(void *opaque, uint64_t threshold_size,
+ uint64_t *res_precopy, uint64_t *res_postcopy)
+{
+ VFIODevice *vbasedev = opaque;
+
+ /*
+ * VFIO migration protocol v2 currently doesn't have an API to get pending
+ * device state size. Until such API is introduced, report some big
+ * arbitrary pending size so the device will be taken into account for
+ * downtime limit calculations.
+ */
+ *res_postcopy += VFIO_MIG_PENDING_SIZE;
+
+ trace_vfio_save_pending(vbasedev->name, *res_precopy, *res_postcopy);
+}
+
static void vfio_v1_save_pending(void *opaque, uint64_t threshold_size,
uint64_t *res_precopy, uint64_t
*res_postcopy)
{
@@ -520,6 +655,67 @@ static int vfio_save_iterate(QEMUFile *f, void *opaque)
return 0;
}
+/* Returns 1 if end-of-stream is reached, 0 if more data and -1 if error */
+static int vfio_save_block(QEMUFile *f, VFIOMigration *migration)
+{
+ ssize_t data_size;
+
+ data_size = read(migration->data_fd, migration->data_buffer,
+ migration->data_buffer_size);
+ if (data_size < 0) {
+ return -1;
+ }
+ if (data_size == 0) {
+ return 1;
+ }
+
+ qemu_put_be64(f, VFIO_MIG_FLAG_DEV_DATA_STATE);
+ qemu_put_be64(f, data_size);
+ qemu_put_buffer(f, migration->data_buffer, data_size);
+ bytes_transferred += data_size;
+
+ trace_vfio_save_block(migration->vbasedev->name, data_size);
+
+ return qemu_file_get_error(f);
+}
+
+static int vfio_save_complete_precopy(QEMUFile *f, void *opaque)
+{
+ VFIODevice *vbasedev = opaque;
+ enum vfio_device_mig_state recover_state;
+ int ret;
+
+ /* We reach here with device state STOP only */
+ recover_state = VFIO_DEVICE_STATE_STOP;
+ ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_STOP_COPY,
+ recover_state);
+ if (ret) {
+ return ret;
+ }
+
+ do {
+ ret = vfio_save_block(f, vbasedev->migration);
+ if (ret < 0) {
+ return ret;
+ }
+ } while (!ret);
+
+ qemu_put_be64(f, VFIO_MIG_FLAG_END_OF_STATE);
+ ret = qemu_file_get_error(f);
+ if (ret) {
+ return ret;
+ }
+
+ recover_state = VFIO_DEVICE_STATE_ERROR;
+ ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_STOP,
+ recover_state);
+ if (!ret) {
+ trace_vfio_save_complete_precopy(vbasedev->name);
+ }
+
+ return ret;
+}
+
static int vfio_v1_save_complete_precopy(QEMUFile *f, void *opaque)
{
VFIODevice *vbasedev = opaque;
@@ -589,6 +785,14 @@ static void vfio_save_state(QEMUFile *f, void *opaque)
}
}
+static int vfio_load_setup(QEMUFile *f, void *opaque)
+{
+ VFIODevice *vbasedev = opaque;
+
+ return vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_RESUMING,
+ vbasedev->migration->device_state);
+}
+
static int vfio_v1_load_setup(QEMUFile *f, void *opaque)
{
VFIODevice *vbasedev = opaque;
@@ -616,6 +820,16 @@ static int vfio_v1_load_setup(QEMUFile *f, void *opaque)
return ret;
}
+static int vfio_load_cleanup(void *opaque)
+{
+ VFIODevice *vbasedev = opaque;
+
+ vfio_migration_cleanup(vbasedev);
+ trace_vfio_load_cleanup(vbasedev->name);
+
+ return 0;
+}
+
static int vfio_v1_load_cleanup(void *opaque)
{
VFIODevice *vbasedev = opaque;
@@ -658,7 +872,11 @@ static int vfio_load_state(QEMUFile *f, void *opaque, int
version_id)
uint64_t data_size = qemu_get_be64(f);
if (data_size) {
- ret = vfio_v1_load_buffer(f, vbasedev, data_size);
+ if (vbasedev->migration->v2) {
+ ret = vfio_load_buffer(f, vbasedev, data_size);
+ } else {
+ ret = vfio_v1_load_buffer(f, vbasedev, data_size);
+ }
if (ret < 0) {
return ret;
}
@@ -679,6 +897,17 @@ static int vfio_load_state(QEMUFile *f, void *opaque, int
version_id)
return ret;
}
+static const SaveVMHandlers savevm_vfio_handlers = {
+ .save_setup = vfio_save_setup,
+ .save_cleanup = vfio_save_cleanup,
+ .save_live_pending = vfio_save_pending,
+ .save_live_complete_precopy = vfio_save_complete_precopy,
+ .save_state = vfio_save_state,
+ .load_setup = vfio_load_setup,
+ .load_cleanup = vfio_load_cleanup,
+ .load_state = vfio_load_state,
+};
+
static SaveVMHandlers savevm_vfio_v1_handlers = {
.save_setup = vfio_v1_save_setup,
.save_cleanup = vfio_v1_save_cleanup,
@@ -693,6 +922,34 @@ static SaveVMHandlers savevm_vfio_v1_handlers = {
/* ---------------------------------------------------------------------- */
+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 = VFIO_DEVICE_STATE_STOP;
+ }
+
+ 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(vbasedev->name, running, RunState_str(state),
+ mig_state_to_str(new_state));
+}
+
static void vfio_v1_vmstate_change(void *opaque, bool running, RunState state)
{
VFIODevice *vbasedev = opaque;
@@ -766,12 +1023,17 @@ static void vfio_migration_state_notifier(Notifier
*notifier, void *data)
case MIGRATION_STATUS_CANCELLED:
case MIGRATION_STATUS_FAILED:
bytes_transferred = 0;
- ret = vfio_migration_v1_set_state(vbasedev,
- ~(VFIO_DEVICE_STATE_V1_SAVING |
- VFIO_DEVICE_STATE_V1_RESUMING),
- VFIO_DEVICE_STATE_V1_RUNNING);
- if (ret) {
- error_report("%s: Failed to set state RUNNING", vbasedev->name);
+ if (migration->v2) {
+ vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_RUNNING,
+ VFIO_DEVICE_STATE_ERROR);
+ } else {
+ ret = vfio_migration_v1_set_state(vbasedev,
+ ~(VFIO_DEVICE_STATE_V1_SAVING |
+ VFIO_DEVICE_STATE_V1_RESUMING),
+ VFIO_DEVICE_STATE_V1_RUNNING);
+ if (ret) {
+ error_report("%s: Failed to set state RUNNING",
vbasedev->name);
+ }
}
}
}
@@ -780,12 +1042,35 @@ static void vfio_migration_exit(VFIODevice *vbasedev)
{
VFIOMigration *migration = vbasedev->migration;
- vfio_region_exit(&migration->region);
- vfio_region_finalize(&migration->region);
+ if (migration->v2) {
+ g_free(migration->data_buffer);
+ } else {
+ vfio_region_exit(&migration->region);
+ vfio_region_finalize(&migration->region);
+ }
g_free(vbasedev->migration);
vbasedev->migration = NULL;
}
+static int vfio_migration_query_flags(VFIODevice *vbasedev, uint64_t
*mig_flags)
+{
+ uint64_t buf[DIV_ROUND_UP(sizeof(struct vfio_device_feature) +
+ sizeof(struct vfio_device_feature_migration),
+ sizeof(uint64_t))] = {};
+ struct vfio_device_feature *feature = (void *)buf;
+ struct vfio_device_feature_migration *mig = (void *)feature->data;
+
+ feature->argsz = sizeof(buf);
+ feature->flags = VFIO_DEVICE_FEATURE_GET | VFIO_DEVICE_FEATURE_MIGRATION;
+ if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) {
+ return -EOPNOTSUPP;
+ }
+
+ *mig_flags = mig->flags;
+
+ return 0;
+}
+
static int vfio_migration_init(VFIODevice *vbasedev)
{
int ret;
@@ -794,6 +1079,7 @@ static int vfio_migration_init(VFIODevice *vbasedev)
char id[256] = "";
g_autofree char *path = NULL, *oid = NULL;
struct vfio_region_info *info = NULL;
+ uint64_t mig_flags;
if (!vbasedev->ops->vfio_get_object) {
return -EINVAL;
@@ -804,34 +1090,51 @@ static int vfio_migration_init(VFIODevice *vbasedev)
return -EINVAL;
}
- ret = vfio_get_dev_region_info(vbasedev,
- VFIO_REGION_TYPE_MIGRATION_DEPRECATED,
- VFIO_REGION_SUBTYPE_MIGRATION_DEPRECATED,
- &info);
- if (ret) {
- return ret;
- }
+ ret = vfio_migration_query_flags(vbasedev, &mig_flags);
+ if (!ret) {
+ /* Migration v2 */
+ /* Basic migration functionality must be supported */
+ if (!(mig_flags & VFIO_MIGRATION_STOP_COPY)) {
+ return -EOPNOTSUPP;
+ }
+ vbasedev->migration = g_new0(VFIOMigration, 1);
+ vbasedev->migration->device_state = VFIO_DEVICE_STATE_RUNNING;
+ vbasedev->migration->data_buffer_size = VFIO_MIG_DATA_BUFFER_SIZE;
+ vbasedev->migration->data_buffer =
+ g_malloc0(vbasedev->migration->data_buffer_size);
+ vbasedev->migration->data_fd = -1;
+ vbasedev->migration->v2 = true;
+ } else {
+ /* Migration v1 */
+ ret = vfio_get_dev_region_info(vbasedev,
+ VFIO_REGION_TYPE_MIGRATION_DEPRECATED,
+
VFIO_REGION_SUBTYPE_MIGRATION_DEPRECATED,
+ &info);
+ if (ret) {
+ return ret;
+ }
- vbasedev->migration = g_new0(VFIOMigration, 1);
- vbasedev->migration->device_state_v1 = VFIO_DEVICE_STATE_V1_RUNNING;
- vbasedev->migration->vm_running = runstate_is_running();
+ vbasedev->migration = g_new0(VFIOMigration, 1);
+ vbasedev->migration->device_state_v1 = VFIO_DEVICE_STATE_V1_RUNNING;
+ vbasedev->migration->vm_running = runstate_is_running();
- ret = vfio_region_setup(obj, vbasedev, &vbasedev->migration->region,
- info->index, "migration");
- if (ret) {
- error_report("%s: Failed to setup VFIO migration region %d: %s",
- vbasedev->name, info->index, strerror(-ret));
- goto err;
- }
+ ret = vfio_region_setup(obj, vbasedev, &vbasedev->migration->region,
+ info->index, "migration");
+ if (ret) {
+ error_report("%s: Failed to setup VFIO migration region %d: %s",
+ vbasedev->name, info->index, strerror(-ret));
+ goto err;
+ }
- if (!vbasedev->migration->region.size) {
- error_report("%s: Invalid zero-sized VFIO migration region %d",
- vbasedev->name, info->index);
- ret = -EINVAL;
- goto err;
- }
+ if (!vbasedev->migration->region.size) {
+ error_report("%s: Invalid zero-sized VFIO migration region %d",
+ vbasedev->name, info->index);
+ ret = -EINVAL;
+ goto err;
+ }
- g_free(info);
+ g_free(info);
+ }
migration = vbasedev->migration;
migration->vbasedev = vbasedev;
@@ -844,11 +1147,20 @@ static int vfio_migration_init(VFIODevice *vbasedev)
}
strpadcpy(id, sizeof(id), path, '\0');
- register_savevm_live(id, VMSTATE_INSTANCE_ID_ANY, 1,
- &savevm_vfio_v1_handlers, vbasedev);
+ if (migration->v2) {
+ 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);
+ } else {
+ register_savevm_live(id, VMSTATE_INSTANCE_ID_ANY, 1,
+ &savevm_vfio_v1_handlers, vbasedev);
+
+ migration->vm_state = qdev_add_vm_change_state_handler(
+ vbasedev->dev, vfio_v1_vmstate_change, vbasedev);
+ }
- migration->vm_state = qdev_add_vm_change_state_handler(
- vbasedev->dev, vfio_v1_vmstate_change, vbasedev);
migration->migration_state.notify = vfio_migration_state_notifier;
add_migration_state_change_notifier(&migration->migration_state);
return 0;
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index d88d2b4053..9ef84e24b2 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -149,7 +149,9 @@ vfio_display_edid_write_error(void) ""
# migration.c
vfio_migration_probe(const char *name) " (%s)"
+vfio_migration_set_state(const char *name, const char *state) " (%s) state %s"
vfio_migration_v1_set_state(const char *name, uint32_t state) " (%s) state %d"
+vfio_vmstate_change(const char *name, int running, const char *reason, const char
*dev_state) " (%s) running %d reason %s device state %s"
vfio_v1_vmstate_change(const char *name, int running, const char *reason, uint32_t
dev_state) " (%s) running %d reason %s device state %d"
vfio_migration_state_notifier(const char *name, const char *state) " (%s) state
%s"
vfio_save_setup(const char *name) " (%s)"
@@ -163,6 +165,8 @@ vfio_save_complete_precopy(const char *name) " (%s)"
vfio_load_device_config_state(const char *name) " (%s)"
vfio_load_state(const char *name, uint64_t data) " (%s) data 0x%"PRIx64
vfio_v1_load_state_device_data(const char *name, uint64_t data_offset, uint64_t data_size) "
(%s) Offset 0x%"PRIx64" size 0x%"PRIx64
+vfio_load_state_device_data(const char *name, uint64_t data_size) " (%s) size
0x%"PRIx64
vfio_load_cleanup(const char *name) " (%s)"
vfio_get_dirty_bitmap(int fd, uint64_t iova, uint64_t size, uint64_t bitmap_size, uint64_t start) "container
fd=%d, iova=0x%"PRIx64" size= 0x%"PRIx64" bitmap_size=0x%"PRIx64" start=0x%"PRIx64
vfio_iommu_map_dirty_notify(uint64_t iova_start, uint64_t iova_end) "iommu dirty @
0x%"PRIx64" - 0x%"PRIx64
+vfio_save_block(const char *name, int data_size) " (%s) data_size %d"
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index bbaf72ba00..2ec3346fea 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -66,6 +66,11 @@ typedef struct VFIOMigration {
int vm_running;
Notifier migration_state;
uint64_t pending_bytes;
+ enum vfio_device_mig_state device_state;
+ int data_fd;
+ void *data_buffer;
+ size_t data_buffer_size;
+ bool v2;
} VFIOMigration;
typedef struct VFIOAddressSpace {
--
2.21.3