On Wed, 25 Mar 2020 02:39:06 +0530
Kirti Wankhede <kwankh...@nvidia.com> wrote:
> Define flags to be used as delimeter in migration file stream.
> Added .save_setup and .save_cleanup functions. Mapped & unmapped 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 | 76
> ++++++++++++++++++++++++++++++++++++++++++++++++++++
> hw/vfio/trace-events | 2 ++
> 2 files changed, 78 insertions(+)
>
> diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
> index 22ded9d28cf3..033f76526e49 100644
> --- a/hw/vfio/migration.c
> +++ b/hw/vfio/migration.c
> @@ -8,6 +8,7 @@
> */
>
> #include "qemu/osdep.h"
> +#include "qemu/main-loop.h"
> #include <linux/vfio.h>
>
> #include "sysemu/runstate.h"
> @@ -24,6 +25,17 @@
> #include "pci.h"
> #include "trace.h"
>
> +/*
> + * Flags used as delimiter:
> + * 0xffffffff => MSB 32-bit all 1s
> + * 0xef10 => emulated (virtual) function IO
> + * 0x0000 => 16-bits reserved for flags
> + */
> +#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 void vfio_migration_region_exit(VFIODevice *vbasedev)
> {
> VFIOMigration *migration = vbasedev->migration;
> @@ -126,6 +138,69 @@ 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;
> +
> + qemu_put_be64(f, VFIO_MIG_FLAG_DEV_SETUP_STATE);
> +
> + if (migration->region.mmaps) {
> + 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 %d: %s",
> + vbasedev->name, migration->region.index,
> + strerror(-ret));
> + return ret;
> + }
> + }
> +
> + ret = vfio_migration_set_state(vbasedev, ~0, VFIO_DEVICE_STATE_SAVING);
> + if (ret) {
> + error_report("%s: Failed to set state SAVING", vbasedev->name);
> + return ret;
> + }
> +
> + /*
> + * Save migration region size. This is used to verify migration region
> size
> + * is greater than or equal to migration region size at destination
> + */
> + qemu_put_be64(f, migration->region.size);
Is this requirement supported by the uapi? The vendor driver operates
within the migration region, but it has no requirement to use the full
extent of the region. Shouldn't we instead insert the version string
from versioning API Yan proposed? Is this were we might choose to use
an interface via the vfio API rather than sysfs if we had one?
> +
> + qemu_put_be64(f, VFIO_MIG_FLAG_END_OF_STATE);
> +
> + ret = qemu_file_get_error(f);
> + if (ret) {
> + return ret;
> + }
> +
> + trace_vfio_save_setup(vbasedev->name);
> + 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);
> + }
> + 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;
> @@ -191,6 +266,7 @@ static int vfio_migration_init(VFIODevice *vbasedev,
> return ret;
> }
>
> + register_savevm_live("vfio", -1, 1, &savevm_vfio_handlers, vbasedev);
> vbasedev->vm_state =
> qemu_add_vm_change_state_handler(vfio_vmstate_change,
> vbasedev);
>
> diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
> index 69503228f20e..4bb43f18f315 100644
> --- a/hw/vfio/trace-events
> +++ b/hw/vfio/trace-events
> @@ -149,3 +149,5 @@ vfio_migration_probe(char *name, uint32_t index) " (%s)
> Region %d"
> vfio_migration_set_state(char *name, uint32_t state) " (%s) state %d"
> vfio_vmstate_change(char *name, int running, const char *reason, uint32_t
> dev_state) " (%s) running %d reason %s device state %d"
> vfio_migration_state_notifier(char *name, int state) " (%s) state %d"
> +vfio_save_setup(char *name) " (%s)"
> +vfio_save_cleanup(char *name) " (%s)"
