On Thu, 22 Oct 2020 16:41:57 +0530
Kirti Wankhede <kwankh...@nvidia.com> wrote:
> Define flags to be used as delimiter in migration stream for VFIO devices.
> Added .save_setup and .save_cleanup functions. Map & unmap migration
> region from these functions at source during saving or pre-copy phase.
>
> Set VFIO device state depending on VM's state. During live migration, VM is
> running when .save_setup is called, _SAVING | _RUNNING state is set for VFIO
> device. During save-restore, VM is paused, _SAVING state is set for VFIO
> device.
>
> Signed-off-by: Kirti Wankhede <kwankh...@nvidia.com>
> Reviewed-by: Neo Jia <c...@nvidia.com>
> ---
> hw/vfio/migration.c | 96
> ++++++++++++++++++++++++++++++++++++++++++++++++++++
> hw/vfio/trace-events | 2 ++
> 2 files changed, 98 insertions(+)
>
> diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
> index 7c4fa0d08ea6..2e1054bf7f43 100644
> --- a/hw/vfio/migration.c
> +++ b/hw/vfio/migration.c
> @@ -8,12 +8,15 @@
> */
>
> #include "qemu/osdep.h"
> +#include "qemu/main-loop.h"
> +#include "qemu/cutils.h"
> #include <linux/vfio.h>
>
> #include "sysemu/runstate.h"
> #include "hw/vfio/vfio-common.h"
> #include "cpu.h"
> #include "migration/migration.h"
> +#include "migration/vmstate.h"
> #include "migration/qemu-file.h"
> #include "migration/register.h"
> #include "migration/blocker.h"
> @@ -25,6 +28,22 @@
> #include "trace.h"
> #include "hw/hw.h"
>
> +/*
> + * Flags to be used as unique delimiters for VFIO devices in the migration
> + * stream. These flags are composed as:
> + * 0xffffffff => MSB 32-bit all 1s
> + * 0xef10 => Magic ID, represents emulated (virtual) function IO
> + * 0x0000 => 16-bits reserved for flags
> + *
> + * The beginning of state information is marked by _DEV_CONFIG_STATE,
> + * _DEV_SETUP_STATE, or _DEV_DATA_STATE, respectively. The end of a
> + * certain state information is marked by _END_OF_STATE.
> + */
> +#define VFIO_MIG_FLAG_END_OF_STATE (0xffffffffef100001ULL)
> +#define VFIO_MIG_FLAG_DEV_CONFIG_STATE (0xffffffffef100002ULL)
> +#define VFIO_MIG_FLAG_DEV_SETUP_STATE (0xffffffffef100003ULL)
> +#define VFIO_MIG_FLAG_DEV_DATA_STATE (0xffffffffef100004ULL)
> +
> static inline int vfio_mig_access(VFIODevice *vbasedev, void *val, int count,
> off_t off, bool iswrite)
> {
> @@ -129,6 +148,69 @@ static int vfio_migration_set_state(VFIODevice
> *vbasedev, uint32_t mask,
> return 0;
> }
>
> +/* ---------------------------------------------------------------------- */
> +
> +static int vfio_save_setup(QEMUFile *f, void *opaque)
> +{
> + VFIODevice *vbasedev = opaque;
> + VFIOMigration *migration = vbasedev->migration;
> + int ret;
> +
> + trace_vfio_save_setup(vbasedev->name);
> +
> + qemu_put_be64(f, VFIO_MIG_FLAG_DEV_SETUP_STATE);
> +
> + if (migration->region.mmaps) {
> + /*
> + * vfio_region_mmap() called from migration thread. Memory API called
> + * from vfio_regio_mmap() need it when called from outdide the main
> loop
> + * thread.
> + */
Thanks for adding this detail, maybe refine slightly as:
Calling vfio_region_mmap() from migration thread. Memory APIs called
from this function require locking the iothread when called from
outside the main loop thread.
Does that capture the intent?
> + qemu_mutex_lock_iothread();
> + ret = vfio_region_mmap(&migration->region);
> + qemu_mutex_unlock_iothread();
> + if (ret) {
> + error_report("%s: Failed to mmap VFIO migration region: %s",
> + vbasedev->name, strerror(-ret));
> + error_report("%s: Falling back to slow path", vbasedev->name);
> + }
> + }
> +
> + ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_MASK,
> + VFIO_DEVICE_STATE_SAVING);
> + if (ret) {
> + error_report("%s: Failed to set state SAVING", vbasedev->name);
> + return ret;
> + }
> +
> + qemu_put_be64(f, VFIO_MIG_FLAG_END_OF_STATE);
> +
> + ret = qemu_file_get_error(f);
> + if (ret) {
> + return ret;
> + }
> +
> + return 0;
> +}
> +
> +static void vfio_save_cleanup(void *opaque)
> +{
> + VFIODevice *vbasedev = opaque;
> + VFIOMigration *migration = vbasedev->migration;
> +
> + if (migration->region.mmaps) {
> + vfio_region_unmap(&migration->region);
> + }
Are we in a different thread context here that we don't need that same
iothread locking?
> + trace_vfio_save_cleanup(vbasedev->name);
> +}
> +
> +static SaveVMHandlers savevm_vfio_handlers = {
> + .save_setup = vfio_save_setup,
> + .save_cleanup = vfio_save_cleanup,
> +};
> +
> +/* ---------------------------------------------------------------------- */
> +
> static void vfio_vmstate_change(void *opaque, int running, RunState state)
> {
> VFIODevice *vbasedev = opaque;
> @@ -219,6 +301,8 @@ static int vfio_migration_init(VFIODevice *vbasedev,
> int ret;
> Object *obj;
> VFIOMigration *migration;
> + char id[256] = "";
> + g_autofree char *path = NULL, *oid;
AIUI, oid must also be initialized as a g_autofree variable.
>
> if (!vbasedev->ops->vfio_get_object) {
> return -EINVAL;
> @@ -248,6 +332,18 @@ static int vfio_migration_init(VFIODevice *vbasedev,
>
> vbasedev->migration = migration;
> migration->vbasedev = vbasedev;
> +
> + oid = vmstate_if_get_id(VMSTATE_IF(DEVICE(obj)));
> + if (oid) {
> + path = g_strdup_printf("%s/vfio", oid);
> + } else {
> + path = g_strdup("vfio");
If we get here then all vfio devices have the same id string. Isn't
that a problem? Thanks,
Alex
> + }
> + strpadcpy(id, sizeof(id), path, '\0');
> +
> + register_savevm_live(id, VMSTATE_INSTANCE_ID_ANY, 1,
> &savevm_vfio_handlers,
> + vbasedev);
> +
> migration->vm_state =
> qemu_add_vm_change_state_handler(vfio_vmstate_change,
> vbasedev);
> migration->migration_state.notify = vfio_migration_state_notifier;
> diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
> index 78d7d83b5ef8..f148b5e828c1 100644
> --- a/hw/vfio/trace-events
> +++ b/hw/vfio/trace-events
> @@ -151,3 +151,5 @@ vfio_migration_probe(const char *name, uint32_t index) "
> (%s) Region %d"
> vfio_migration_set_state(const char *name, uint32_t state) " (%s) state %d"
> vfio_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)"
> +vfio_save_cleanup(const char *name) " (%s)"
