---
include/uapi/linux/vfio.h | 227 ++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 227 insertions(+)
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 9e843a147ead..d0021467af53 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -305,6 +305,7 @@ struct vfio_region_info_cap_type {
#define VFIO_REGION_TYPE_PCI_VENDOR_MASK (0xffff)
#define VFIO_REGION_TYPE_GFX (1)
#define VFIO_REGION_TYPE_CCW (2)
+#define VFIO_REGION_TYPE_MIGRATION (3)
/* sub-types for VFIO_REGION_TYPE_PCI_* */
@@ -379,6 +380,232 @@ struct vfio_region_gfx_edid {
/* sub-types for VFIO_REGION_TYPE_CCW */
#define VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD (1)
+/* sub-types for VFIO_REGION_TYPE_MIGRATION */
+#define VFIO_REGION_SUBTYPE_MIGRATION (1)
+
+/*
+ * The structure vfio_device_migration_info is placed at the 0th offset of
+ * the VFIO_REGION_SUBTYPE_MIGRATION region to get and set VFIO device related
+ * migration information. Field accesses from this structure are only supported
+ * at their native width and alignment. Otherwise, the result is undefined and
+ * vendor drivers should return an error.
+ *
+ * device_state: (read/write)
+ * - The user application writes to this field to inform the vendor driver
+ * about the device state to be transitioned to.
+ * - The vendor driver should take the necessary actions to change the
+ * device state. After successful transition to a given state, the
+ * vendor driver should return success on write(device_state, state)
+ * system call. If the device state transition fails, the vendor driver
+ * should return an appropriate -errno for the fault condition.
+ * - On the user application side, if the device state transition fails,
+ * that is, if write(device_state, state) returns an error, read
+ * device_state again to determine the current state of the device from
+ * the vendor driver.
+ * - The vendor driver should return previous state of the device unless
+ * the vendor driver has encountered an internal error, in which case
+ * the vendor driver may report the device_state
VFIO_DEVICE_STATE_ERROR.
+ * - The user application must use the device reset ioctl to recover the
+ * device from VFIO_DEVICE_STATE_ERROR state. If the device is
+ * indicated to be in a valid device state by reading device_state, the
+ * user application may attempt to transition the device to any valid
+ * state reachable from the current state or terminate itself.
+ *
+ * device_state consists of 3 bits:
+ * - If bit 0 is set, it indicates the _RUNNING state. If bit 0 is clear,
+ * it indicates the _STOP state. When the device state is changed to
+ * _STOP, driver should stop the device before write() returns.
+ * - If bit 1 is set, it indicates the _SAVING state, which means that the
+ * driver should start gathering device state information that will be
+ * provided to the VFIO user application to save the device's state.
+ * - If bit 2 is set, it indicates the _RESUMING state, which means that
+ * the driver should prepare to resume the device. Data provided through
+ * the migration region should be used to resume the device.
+ * Bits 3 - 31 are reserved for future use. To preserve them, the user
+ * application should perform a read-modify-write operation on this
+ * field when modifying the specified bits.
+ *
+ * +------- _RESUMING
+ * |+------ _SAVING
+ * ||+----- _RUNNING
+ * |||
+ * 000b => Device Stopped, not saving or resuming
+ * 001b => Device running, which is the default state
+ * 010b => Stop the device & save the device state, stop-and-copy state
+ * 011b => Device running and save the device state, pre-copy state
+ * 100b => Device stopped and the device state is resuming
+ * 101b => Invalid state
+ * 110b => Error state
+ * 111b => Invalid state
+ *
+ * State transitions:
+ *
+ * _RESUMING _RUNNING Pre-copy Stop-and-copy _STOP
+ * (100b) (001b) (011b) (010b) (000b)
+ * 0. Running or default state
+ * |
+ *
+ * 1. Normal Shutdown (optional)
+ * |------------------------------------->|
+ *
+ * 2. Save the state or suspend
+ * |------------------------->|---------->|
+ *
+ * 3. Save the state during live migration
+ * |----------->|------------>|---------->|
+ *
+ * 4. Resuming
+ * |<---------|
+ *
+ * 5. Resumed
+ * |--------->|
+ *
+ * 0. Default state of VFIO device is _RUNNNG when the user application starts.
+ * 1. During normal shutdown of the user application, the user application may
+ * optionally change the VFIO device state from _RUNNING to _STOP. This
+ * transition is optional. The vendor driver must support this transition
but
+ * must not require it.
+ * 2. When the user application saves state or suspends the application, the
+ * device state transitions from _RUNNING to stop-and-copy and then to
_STOP.
+ * On state transition from _RUNNING to stop-and-copy, driver must stop the
+ * device, save the device state and send it to the application through the
+ * migration region. The sequence to be followed for such transition is
given
+ * below.
+ * 3. In live migration of user application, the state transitions from
_RUNNING
+ * to pre-copy, to stop-and-copy, and to _STOP.
+ * On state transition from _RUNNING to pre-copy, the driver should start
+ * gathering the device state while the application is still running and
send
+ * the device state data to application through the migration region.
+ * On state transition from pre-copy to stop-and-copy, the driver must stop
+ * the device, save the device state and send it to the user application
+ * through the migration region.
+ * Vendor drivers must support the pre-copy state even for implementations
+ * where no data is provided to the user before the stop-and-copy state. The
+ * user must not be required to consume all migration data before the device
+ * transitions to a new state, including the stop-and-copy state.
+ * The sequence to be followed for above two transitions is given below.
+ * 4. To start the resuming phase, the device state should be transitioned from
+ * the _RUNNING to the _RESUMING state.
+ * In the _RESUMING state, the driver should use the device state data
+ * received through the migration region to resume the device.
+ * 5. After providing saved device data to the driver, the application should
+ * change the state from _RESUMING to _RUNNING.
+ *
+ * reserved:
+ * Reads on this field return zero and writes are ignored.
+ *
+ * pending_bytes: (read only)
+ * The number of pending bytes still to be migrated from the vendor
driver.
+ *
+ * data_offset: (read only)
+ * The user application should read data_offset in the migration region
+ * from where the user application should read the device data during the
+ * _SAVING state or write the device data during the _RESUMING state. See
+ * below for details of sequence to be followed.
+ *
+ * data_size: (read/write)
+ * The user application should read data_size to get the size in bytes of
+ * the data copied in the migration region during the _SAVING state and
+ * write the size in bytes of the data copied in the migration region
+ * during the _RESUMING state.
+ *
+ * The format of the migration region is as follows:
+ * ------------------------------------------------------------------
+ * |vfio_device_migration_info| data section |
+ * | | /////////////////////////////// |
+ * ------------------------------------------------------------------
+ * ^ ^
+ * offset 0-trapped part data_offset
+ *
+ * The structure vfio_device_migration_info is always followed by the data
+ * section in the region, so data_offset will always be nonzero. The offset
+ * from where the data is copied is decided by the kernel driver. The data
+ * section can be trapped, mapped, or partitioned, depending on how the kernel
+ * driver defines the data section. The data section partition can be defined
+ * as mapped by the sparse mmap capability. If mmapped, data_offset should be
+ * page aligned, whereas initial section which contains the
+ * vfio_device_migration_info structure, might not end at the offset, which is
+ * page aligned. The user is not required to access through mmap regardless
+ * of the capabilities of the region mmap.
+ * The vendor driver should determine whether and how to partition the data
+ * section. The vendor driver should return data_offset accordingly.
+ *
+ * The sequence to be followed for the _SAVING|_RUNNING device state or
+ * pre-copy phase and for the _SAVING device state or stop-and-copy phase is as
+ * follows:
+ * a. Read pending_bytes, indicating the start of a new iteration to get device
+ * data. Repeated read on pending_bytes at this stage should have no side
+ * effects.
+ * If pending_bytes == 0, the user application should not iterate to get
data
+ * for that device.
