Hi Cédric,
On 3/6/24 14:34, Cédric Le Goater wrote:
> Add an Error** argument to vfio_migration_set_state() and adjust
> callers, including vfio_save_setup(). The error will be propagated up
> to qemu_savevm_state_setup() where the save_setup() handler is
> executed.
>
> Modify vfio_vmstate_change_prepare() and vfio_vmstate_change() to
> store a reported error under the migration stream if a migration is in
> progress.
>
> Signed-off-by: Cédric Le Goater <c...@redhat.com>
> ---
>
> Changes in v3:
>
> - Use error_setg_errno() in vfio_save_setup()
> - Made sure an error is always set in case of failure in
> vfio_load_setup()
>
> hw/vfio/migration.c | 67 ++++++++++++++++++++++++++-------------------
> 1 file changed, 39 insertions(+), 28 deletions(-)
>
> diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
> index
> a3bb1a92ba0b9c2c585efe54cfda0b774a81dcb9..71ade14a7942358094371a86c00718f5979113ea
> 100644
> --- a/hw/vfio/migration.c
> +++ b/hw/vfio/migration.c
> @@ -84,7 +84,8 @@ static const char *mig_state_to_str(enum
> vfio_device_mig_state state)
>
> static int vfio_migration_set_state(VFIODevice *vbasedev,
> enum vfio_device_mig_state new_state,
> - enum vfio_device_mig_state recover_state)
> + enum vfio_device_mig_state recover_state,
> + Error **errp)
> {
> VFIOMigration *migration = vbasedev->migration;
> uint64_t buf[DIV_ROUND_UP(sizeof(struct vfio_device_feature) +
> @@ -104,15 +105,15 @@ static int vfio_migration_set_state(VFIODevice
> *vbasedev,
> ret = -errno;
>
> if (recover_state == VFIO_DEVICE_STATE_ERROR) {
> - error_report("%s: Failed setting device state to %s, err: %s. "
> - "Recover state is ERROR. Resetting device",
> - vbasedev->name, mig_state_to_str(new_state),
> - strerror(errno));
> + error_setg(errp, "%s: Failed setting device state to %s, err:
> %s. "
> + "Recover state is ERROR. Resetting device",
> + vbasedev->name, mig_state_to_str(new_state),
> + strerror(errno));
you can use the error_setg_errno variant here and below.
>
> goto reset_device;
> }
>
> - error_report(
> + error_setg(errp,
> "%s: Failed setting device state to %s, err: %s. Setting device
> in recover state %s",
> vbasedev->name, mig_state_to_str(new_state),
> strerror(errno), mig_state_to_str(recover_state));
> @@ -120,7 +121,7 @@ static int vfio_migration_set_state(VFIODevice *vbasedev,
> mig_state->device_state = recover_state;
> if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) {
> ret = -errno;
> - error_report(
> + error_setg(errp,
> "%s: Failed setting device in recover state, err: %s.
> Resetting device",
> vbasedev->name, strerror(errno));
>
> @@ -139,7 +140,7 @@ static int vfio_migration_set_state(VFIODevice *vbasedev,
> * This can happen if the device is asynchronously reset and
> * terminates a data transfer.
> */
> - error_report("%s: data_fd out of sync", vbasedev->name);
> + error_setg(errp, "%s: data_fd out of sync", vbasedev->name);
> close(mig_state->data_fd);
>
> return -EBADF;
> @@ -170,10 +171,11 @@ reset_device:
> */
> static int
> vfio_migration_set_state_or_reset(VFIODevice *vbasedev,
> - enum vfio_device_mig_state new_state)
> + enum vfio_device_mig_state new_state,
> + Error **errp)
> {
> return vfio_migration_set_state(vbasedev, new_state,
> - VFIO_DEVICE_STATE_ERROR);
> + VFIO_DEVICE_STATE_ERROR, errp);
> }
>
> static int vfio_load_buffer(QEMUFile *f, VFIODevice *vbasedev,
> @@ -401,10 +403,8 @@ static int vfio_save_setup(QEMUFile *f, void *opaque,
> Error **errp)
> switch (migration->device_state) {
> case VFIO_DEVICE_STATE_RUNNING:
> ret = vfio_migration_set_state(vbasedev,
> VFIO_DEVICE_STATE_PRE_COPY,
> - VFIO_DEVICE_STATE_RUNNING);
> + VFIO_DEVICE_STATE_RUNNING, errp);
> if (ret) {
> - error_setg(errp, "%s: Failed to set new PRE_COPY state",
> - vbasedev->name);
> return ret;
> }
>
> @@ -437,13 +437,20 @@ static void vfio_save_cleanup(void *opaque)
> {
> VFIODevice *vbasedev = opaque;
> VFIOMigration *migration = vbasedev->migration;
> + Error *local_err = NULL;
> + int ret;
>
> /*
> * 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) {
> - vfio_migration_set_state_or_reset(vbasedev, VFIO_DEVICE_STATE_STOP);
> + ret = vfio_migration_set_state_or_reset(vbasedev,
> + VFIO_DEVICE_STATE_STOP,
> + &local_err);
> + if (ret) {
> + error_report_err(local_err);
> + }
> }
>
> g_free(migration->data_buffer);
> @@ -549,11 +556,13 @@ static int vfio_save_complete_precopy(QEMUFile *f, void
> *opaque)
> VFIODevice *vbasedev = opaque;
> ssize_t data_size;
> int ret;
> + Error *local_err = NULL;
>
> /* We reach here with device state STOP or STOP_COPY only */
> ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_STOP_COPY,
> - VFIO_DEVICE_STATE_STOP);
> + VFIO_DEVICE_STATE_STOP, &local_err);
> if (ret) {
> + error_report_err(local_err);
> return ret;
> }
>
> @@ -591,14 +600,9 @@ static void vfio_save_state(QEMUFile *f, void *opaque)
> static int vfio_load_setup(QEMUFile *f, void *opaque, Error **errp)
> {
> VFIODevice *vbasedev = opaque;
> - int ret;
>
> - ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_RESUMING,
> - vbasedev->migration->device_state);
> - if (ret) {
> - error_setg(errp, "%s: Failed to set RESUMING state", vbasedev->name);
> - }
> - return ret;
> + return vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_RESUMING,
> + vbasedev->migration->device_state, errp);
> }
>
> static int vfio_load_cleanup(void *opaque)
> @@ -714,20 +718,22 @@ static void vfio_vmstate_change_prepare(void *opaque,
> bool running,
> VFIODevice *vbasedev = opaque;
> VFIOMigration *migration = vbasedev->migration;
> enum vfio_device_mig_state new_state;
> + Error *local_err = NULL;
> int ret;
>
> new_state = migration->device_state == VFIO_DEVICE_STATE_PRE_COPY ?
> VFIO_DEVICE_STATE_PRE_COPY_P2P :
> VFIO_DEVICE_STATE_RUNNING_P2P;
>
> - ret = vfio_migration_set_state_or_reset(vbasedev, new_state);
> + ret = vfio_migration_set_state_or_reset(vbasedev, new_state, &local_err);
> if (ret) {
> /*
> * Migration should be aborted in this case, but vm_state_notify()
> * currently does not support reporting failures.
> */
if ret and we do not enter the condition below, we may leak the
local_err. Same below.
Eric
> if (migrate_get_current()->to_dst_file) {
> - qemu_file_set_error(migrate_get_current()->to_dst_file, ret);
> + qemu_file_set_error_obj(migrate_get_current()->to_dst_file, ret,
> + local_err);
> }
> }
>
> @@ -740,6 +746,7 @@ static void vfio_vmstate_change(void *opaque, bool
> running, RunState state)
> {
> VFIODevice *vbasedev = opaque;
> enum vfio_device_mig_state new_state;
> + Error *local_err = NULL;
> int ret;
>
> if (running) {
> @@ -752,14 +759,15 @@ static void vfio_vmstate_change(void *opaque, bool
> running, RunState state)
> VFIO_DEVICE_STATE_STOP;
> }
>
> - ret = vfio_migration_set_state_or_reset(vbasedev, new_state);
> + ret = vfio_migration_set_state_or_reset(vbasedev, new_state, &local_err);
> 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);
> + qemu_file_set_error_obj(migrate_get_current()->to_dst_file, ret,
> + local_err);
> }
> }
>
> @@ -773,13 +781,16 @@ static int
> vfio_migration_state_notifier(NotifierWithReturn *notifier,
> VFIOMigration *migration = container_of(notifier, VFIOMigration,
> migration_state);
> VFIODevice *vbasedev = migration->vbasedev;
> + int ret = 0;
>
> trace_vfio_migration_state_notifier(vbasedev->name, e->type);
>
> if (e->type == MIG_EVENT_PRECOPY_FAILED) {
> - vfio_migration_set_state_or_reset(vbasedev,
> VFIO_DEVICE_STATE_RUNNING);
> + ret = vfio_migration_set_state_or_reset(vbasedev,
> + VFIO_DEVICE_STATE_RUNNING,
> + errp);
> }
> - return 0;
> + return ret;
> }
>
> static void vfio_migration_free(VFIODevice *vbasedev)
