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 <kwankhede@nvidia.com>
Reviewed-by: Neo Jia <cjia@nvidia.com>
---
hw/vfio/migration.c | 76 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 75 insertions(+), 1 deletion(-)
diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
index 7f9858e6c995..fe0887c27664 100644
--- a/hw/vfio/migration.c
+++ b/hw/vfio/migration.c
@@ -22,6 +22,17 @@
#include "exec/ram_addr.h"
#include "pci.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;
@@ -96,6 +107,69 @@ static int vfio_migration_set_state(VFIODevice *vbasedev, uint32_t state)
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.buffer.mmaps) {
+ qemu_mutex_lock_iothread();
+ ret = vfio_region_mmap(&migration->region.buffer);
+ qemu_mutex_unlock_iothread();
+ if (ret) {
+ error_report("Failed to mmap VFIO migration region %d: %s",
+ migration->region.index, strerror(-ret));
+ return ret;
+ }
+ }
+
+ if (vbasedev->vm_running) {
+ ret = vfio_migration_set_state(vbasedev,
+ VFIO_DEVICE_STATE_RUNNING | VFIO_DEVICE_STATE_SAVING);
+ if (ret) {
+ error_report("Failed to set state RUNNING and SAVING");
+ return ret;
+ }
+ } else {
+ ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_SAVING);
+ if (ret) {
+ error_report("Failed to set state STOP and SAVING");
+ 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.buffer.mmaps) {
+ vfio_region_unmap(&migration->region.buffer);
+ }
+}
+
+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;
@@ -169,7 +243,7 @@ static int vfio_migration_init(VFIODevice *vbasedev,
}
qemu_mutex_init(&vbasedev->migration->lock);
-
+ register_savevm_live(NULL, "vfio", -1, 1, &savevm_vfio_handlers, vbasedev);
vbasedev->vm_state = qemu_add_vm_change_state_handler(vfio_vmstate_change,
vbasedev);
--
2.7.0
* Kirti Wankhede (kwankhede@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 <kwankhede@nvidia.com>
> Reviewed-by: Neo Jia <cjia@nvidia.com>
> ---
> hw/vfio/migration.c | 76 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
> 1 file changed, 75 insertions(+), 1 deletion(-)
>
> diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
> index 7f9858e6c995..fe0887c27664 100644
> --- a/hw/vfio/migration.c
> +++ b/hw/vfio/migration.c
> @@ -22,6 +22,17 @@
> #include "exec/ram_addr.h"
> #include "pci.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;
> @@ -96,6 +107,69 @@ static int vfio_migration_set_state(VFIODevice *vbasedev, uint32_t state)
> 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.buffer.mmaps) {
> + qemu_mutex_lock_iothread();
> + ret = vfio_region_mmap(&migration->region.buffer);
> + qemu_mutex_unlock_iothread();
> + if (ret) {
> + error_report("Failed to mmap VFIO migration region %d: %s",
> + migration->region.index, strerror(-ret));
> + return ret;
> + }
> + }
> +
> + if (vbasedev->vm_running) {
> + ret = vfio_migration_set_state(vbasedev,
> + VFIO_DEVICE_STATE_RUNNING | VFIO_DEVICE_STATE_SAVING);
> + if (ret) {
> + error_report("Failed to set state RUNNING and SAVING");
> + return ret;
> + }
> + } else {
> + ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_SAVING);
> + if (ret) {
> + error_report("Failed to set state STOP and SAVING");
> + 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.buffer.mmaps) {
> + vfio_region_unmap(&migration->region.buffer);
> + }
> +}
> +
> +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;
> @@ -169,7 +243,7 @@ static int vfio_migration_init(VFIODevice *vbasedev,
> }
>
> qemu_mutex_init(&vbasedev->migration->lock);
> -
> + register_savevm_live(NULL, "vfio", -1, 1, &savevm_vfio_handlers, vbasedev);
Does this work OK with multiple devices?
I think I'd expected you to pass a DeviceState as the first parameter
for a real device like vfio.
'ram' and 'block' don't need to because they iterate over all RAM
devices inside their save_setup's and similar handlers; for vfio I'd
expect it to be per-device.
Dave
> vbasedev->vm_state = qemu_add_vm_change_state_handler(vfio_vmstate_change,
> vbasedev);
>
> --
> 2.7.0
>
--
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
On 6/27/2019 3:31 PM, Dr. David Alan Gilbert wrote:
> * Kirti Wankhede (kwankhede@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 <kwankhede@nvidia.com>
>> Reviewed-by: Neo Jia <cjia@nvidia.com>
>> ---
>> hw/vfio/migration.c | 76 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
>> 1 file changed, 75 insertions(+), 1 deletion(-)
>>
>> diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
>> index 7f9858e6c995..fe0887c27664 100644
>> --- a/hw/vfio/migration.c
>> +++ b/hw/vfio/migration.c
>> @@ -22,6 +22,17 @@
>> #include "exec/ram_addr.h"
>> #include "pci.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;
>> @@ -96,6 +107,69 @@ static int vfio_migration_set_state(VFIODevice *vbasedev, uint32_t state)
>> 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.buffer.mmaps) {
>> + qemu_mutex_lock_iothread();
>> + ret = vfio_region_mmap(&migration->region.buffer);
>> + qemu_mutex_unlock_iothread();
>> + if (ret) {
>> + error_report("Failed to mmap VFIO migration region %d: %s",
>> + migration->region.index, strerror(-ret));
>> + return ret;
>> + }
>> + }
>> +
>> + if (vbasedev->vm_running) {
>> + ret = vfio_migration_set_state(vbasedev,
>> + VFIO_DEVICE_STATE_RUNNING | VFIO_DEVICE_STATE_SAVING);
>> + if (ret) {
>> + error_report("Failed to set state RUNNING and SAVING");
>> + return ret;
>> + }
>> + } else {
>> + ret = vfio_migration_set_state(vbasedev, VFIO_DEVICE_STATE_SAVING);
>> + if (ret) {
>> + error_report("Failed to set state STOP and SAVING");
>> + 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.buffer.mmaps) {
>> + vfio_region_unmap(&migration->region.buffer);
>> + }
>> +}
>> +
>> +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;
>> @@ -169,7 +243,7 @@ static int vfio_migration_init(VFIODevice *vbasedev,
>> }
>>
>> qemu_mutex_init(&vbasedev->migration->lock);
>> -
>> + register_savevm_live(NULL, "vfio", -1, 1, &savevm_vfio_handlers, vbasedev);
>
> Does this work OK with multiple devices?
Yes. Tested with multiple vGPU devices.
> I think I'd expected you to pass a DeviceState as the first parameter
> for a real device like vfio.
> 'ram' and 'block' don't need to because they iterate over all RAM
> devices inside their save_setup's and similar handlers; for vfio I'd
> expect it to be per-device.
I do see handlers called per-device. I'll check passing DeviceState as
first parameter.
Thanks,
Kirti
>
> Dave
>
>> vbasedev->vm_state = qemu_add_vm_change_state_handler(vfio_vmstate_change,
>> vbasedev);
>>
>> --
>> 2.7.0
>>
> --
> Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
>
© 2016 - 2026 Red Hat, Inc.