|
@@ -819,12 +819,20 @@ struct vfio_device_feature {
|
|
* VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P means that RUNNING_P2P
|
|
* VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P means that RUNNING_P2P
|
|
* is supported in addition to the STOP_COPY states.
|
|
* is supported in addition to the STOP_COPY states.
|
|
*
|
|
*
|
|
|
|
+ * VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_PRE_COPY means that
|
|
|
|
+ * PRE_COPY is supported in addition to the STOP_COPY states.
|
|
|
|
+ *
|
|
|
|
+ * VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P | VFIO_MIGRATION_PRE_COPY
|
|
|
|
+ * means that RUNNING_P2P, PRE_COPY and PRE_COPY_P2P are supported
|
|
|
|
+ * in addition to the STOP_COPY states.
|
|
|
|
+ *
|
|
* Other combinations of flags have behavior to be defined in the future.
|
|
* Other combinations of flags have behavior to be defined in the future.
|
|
*/
|
|
*/
|
|
struct vfio_device_feature_migration {
|
|
struct vfio_device_feature_migration {
|
|
__aligned_u64 flags;
|
|
__aligned_u64 flags;
|
|
#define VFIO_MIGRATION_STOP_COPY (1 << 0)
|
|
#define VFIO_MIGRATION_STOP_COPY (1 << 0)
|
|
#define VFIO_MIGRATION_P2P (1 << 1)
|
|
#define VFIO_MIGRATION_P2P (1 << 1)
|
|
|
|
+#define VFIO_MIGRATION_PRE_COPY (1 << 2)
|
|
};
|
|
};
|
|
#define VFIO_DEVICE_FEATURE_MIGRATION 1
|
|
#define VFIO_DEVICE_FEATURE_MIGRATION 1
|
|
|
|
|
|
@@ -875,8 +883,13 @@ struct vfio_device_feature_mig_state {
|
|
* RESUMING - The device is stopped and is loading a new internal state
|
|
* RESUMING - The device is stopped and is loading a new internal state
|
|
* ERROR - The device has failed and must be reset
|
|
* ERROR - The device has failed and must be reset
|
|
*
|
|
*
|
|
- * And 1 optional state to support VFIO_MIGRATION_P2P:
|
|
|
|
|
|
+ * And optional states to support VFIO_MIGRATION_P2P:
|
|
* RUNNING_P2P - RUNNING, except the device cannot do peer to peer DMA
|
|
* RUNNING_P2P - RUNNING, except the device cannot do peer to peer DMA
|
|
|
|
+ * And VFIO_MIGRATION_PRE_COPY:
|
|
|
|
+ * PRE_COPY - The device is running normally but tracking internal state
|
|
|
|
+ * changes
|
|
|
|
+ * And VFIO_MIGRATION_P2P | VFIO_MIGRATION_PRE_COPY:
|
|
|
|
+ * PRE_COPY_P2P - PRE_COPY, except the device cannot do peer to peer DMA
|
|
*
|
|
*
|
|
* The FSM takes actions on the arcs between FSM states. The driver implements
|
|
* The FSM takes actions on the arcs between FSM states. The driver implements
|
|
* the following behavior for the FSM arcs:
|
|
* the following behavior for the FSM arcs:
|
|
@@ -908,20 +921,48 @@ struct vfio_device_feature_mig_state {
|
|
*
|
|
*
|
|
* To abort a RESUMING session the device must be reset.
|
|
* To abort a RESUMING session the device must be reset.
|
|
*
|
|
*
|
|
|
|
+ * PRE_COPY -> RUNNING
|
|
* RUNNING_P2P -> RUNNING
|
|
* RUNNING_P2P -> RUNNING
|
|
* While in RUNNING the device is fully operational, the device may generate
|
|
* While in RUNNING the device is fully operational, the device may generate
|
|
* interrupts, DMA, respond to MMIO, all vfio device regions are functional,
|
|
* interrupts, DMA, respond to MMIO, all vfio device regions are functional,
|
|
* and the device may advance its internal state.
|
|
* and the device may advance its internal state.
|
|
*
|
|
*
|
|
|
|
+ * The PRE_COPY arc will terminate a data transfer session.
|
|
|
|
+ *
|
|
|
|
+ * PRE_COPY_P2P -> RUNNING_P2P
|
|
* RUNNING -> RUNNING_P2P
|
|
* RUNNING -> RUNNING_P2P
|
|
* STOP -> RUNNING_P2P
|
|
* STOP -> RUNNING_P2P
|
|
* While in RUNNING_P2P the device is partially running in the P2P quiescent
|
|
* While in RUNNING_P2P the device is partially running in the P2P quiescent
|
|
* state defined below.
|
|
* state defined below.
|
|
*
|
|
*
|
|
|
|
+ * The PRE_COPY_P2P arc will terminate a data transfer session.
|
|
|
|
+ *
|
|
|
|
+ * RUNNING -> PRE_COPY
|
|
|
|
+ * RUNNING_P2P -> PRE_COPY_P2P
|
|
* STOP -> STOP_COPY
|
|
* STOP -> STOP_COPY
|
|
- * This arc begin the process of saving the device state and will return a
|
|
|
|
- * new data_fd.
|
|
|
|
|
|
+ * PRE_COPY, PRE_COPY_P2P and STOP_COPY form the "saving group" of states
|
|
|
|
+ * which share a data transfer session. Moving between these states alters
|
|
|
|
+ * what is streamed in session, but does not terminate or otherwise affect
|
|
|
|
+ * the associated fd.
|
|
|
|
+ *
|
|
|
|
+ * These arcs begin the process of saving the device state and will return a
|
|
|
|
+ * new data_fd. The migration driver may perform actions such as enabling
|
|
|
|
+ * dirty logging of device state when entering PRE_COPY or PER_COPY_P2P.
|
|
|
|
+ *
|
|
|
|
+ * Each arc does not change the device operation, the device remains
|
|
|
|
+ * RUNNING, P2P quiesced or in STOP. The STOP_COPY state is described below
|
|
|
|
+ * in PRE_COPY_P2P -> STOP_COPY.
|
|
*
|
|
*
|
|
|
|
+ * PRE_COPY -> PRE_COPY_P2P
|
|
|
|
+ * Entering PRE_COPY_P2P continues all the behaviors of PRE_COPY above.
|
|
|
|
+ * However, while in the PRE_COPY_P2P state, the device is partially running
|
|
|
|
+ * in the P2P quiescent state defined below, like RUNNING_P2P.
|
|
|
|
+ *
|
|
|
|
+ * PRE_COPY_P2P -> PRE_COPY
|
|
|
|
+ * This arc allows returning the device to a full RUNNING behavior while
|
|
|
|
+ * continuing all the behaviors of PRE_COPY.
|
|
|
|
+ *
|
|
|
|
+ * PRE_COPY_P2P -> STOP_COPY
|
|
* While in the STOP_COPY state the device has the same behavior as STOP
|
|
* While in the STOP_COPY state the device has the same behavior as STOP
|
|
* with the addition that the data transfers session continues to stream the
|
|
* with the addition that the data transfers session continues to stream the
|
|
* migration state. End of stream on the FD indicates the entire device
|
|
* migration state. End of stream on the FD indicates the entire device
|
|
@@ -939,6 +980,13 @@ struct vfio_device_feature_mig_state {
|
|
* device state for this arc if required to prepare the device to receive the
|
|
* device state for this arc if required to prepare the device to receive the
|
|
* migration data.
|
|
* migration data.
|
|
*
|
|
*
|
|
|
|
+ * STOP_COPY -> PRE_COPY
|
|
|
|
+ * STOP_COPY -> PRE_COPY_P2P
|
|
|
|
+ * These arcs are not permitted and return error if requested. Future
|
|
|
|
+ * revisions of this API may define behaviors for these arcs, in this case
|
|
|
|
+ * support will be discoverable by a new flag in
|
|
|
|
+ * VFIO_DEVICE_FEATURE_MIGRATION.
|
|
|
|
+ *
|
|
* any -> ERROR
|
|
* any -> ERROR
|
|
* ERROR cannot be specified as a device state, however any transition request
|
|
* ERROR cannot be specified as a device state, however any transition request
|
|
* can be failed with an errno return and may then move the device_state into
|
|
* can be failed with an errno return and may then move the device_state into
|
|
@@ -950,7 +998,7 @@ struct vfio_device_feature_mig_state {
|
|
* The optional peer to peer (P2P) quiescent state is intended to be a quiescent
|
|
* The optional peer to peer (P2P) quiescent state is intended to be a quiescent
|
|
* state for the device for the purposes of managing multiple devices within a
|
|
* state for the device for the purposes of managing multiple devices within a
|
|
* user context where peer-to-peer DMA between devices may be active. The
|
|
* user context where peer-to-peer DMA between devices may be active. The
|
|
- * RUNNING_P2P states must prevent the device from initiating
|
|
|
|
|
|
+ * RUNNING_P2P and PRE_COPY_P2P states must prevent the device from initiating
|
|
* any new P2P DMA transactions. If the device can identify P2P transactions
|
|
* any new P2P DMA transactions. If the device can identify P2P transactions
|
|
* then it can stop only P2P DMA, otherwise it must stop all DMA. The migration
|
|
* then it can stop only P2P DMA, otherwise it must stop all DMA. The migration
|
|
* driver must complete any such outstanding operations prior to completing the
|
|
* driver must complete any such outstanding operations prior to completing the
|
|
@@ -963,6 +1011,8 @@ struct vfio_device_feature_mig_state {
|
|
* above FSM arcs. As there are multiple paths through the FSM arcs the path
|
|
* above FSM arcs. As there are multiple paths through the FSM arcs the path
|
|
* should be selected based on the following rules:
|
|
* should be selected based on the following rules:
|
|
* - Select the shortest path.
|
|
* - Select the shortest path.
|
|
|
|
+ * - The path cannot have saving group states as interior arcs, only
|
|
|
|
+ * starting/end states.
|
|
* Refer to vfio_mig_get_next_state() for the result of the algorithm.
|
|
* Refer to vfio_mig_get_next_state() for the result of the algorithm.
|
|
*
|
|
*
|
|
* The automatic transit through the FSM arcs that make up the combination
|
|
* The automatic transit through the FSM arcs that make up the combination
|
|
@@ -976,6 +1026,9 @@ struct vfio_device_feature_mig_state {
|
|
* support them. The user can discover if these states are supported by using
|
|
* support them. The user can discover if these states are supported by using
|
|
* VFIO_DEVICE_FEATURE_MIGRATION. By using combination transitions the user can
|
|
* VFIO_DEVICE_FEATURE_MIGRATION. By using combination transitions the user can
|
|
* avoid knowing about these optional states if the kernel driver supports them.
|
|
* avoid knowing about these optional states if the kernel driver supports them.
|
|
|
|
+ *
|
|
|
|
+ * Arcs touching PRE_COPY and PRE_COPY_P2P are removed if support for PRE_COPY
|
|
|
|
+ * is not present.
|
|
*/
|
|
*/
|
|
enum vfio_device_mig_state {
|
|
enum vfio_device_mig_state {
|
|
VFIO_DEVICE_STATE_ERROR = 0,
|
|
VFIO_DEVICE_STATE_ERROR = 0,
|
|
@@ -984,8 +1037,70 @@ enum vfio_device_mig_state {
|
|
VFIO_DEVICE_STATE_STOP_COPY = 3,
|
|
VFIO_DEVICE_STATE_STOP_COPY = 3,
|
|
VFIO_DEVICE_STATE_RESUMING = 4,
|
|
VFIO_DEVICE_STATE_RESUMING = 4,
|
|
VFIO_DEVICE_STATE_RUNNING_P2P = 5,
|
|
VFIO_DEVICE_STATE_RUNNING_P2P = 5,
|
|
|
|
+ VFIO_DEVICE_STATE_PRE_COPY = 6,
|
|
|
|
+ VFIO_DEVICE_STATE_PRE_COPY_P2P = 7,
|
|
|
|
+};
|
|
|
|
+
|
|
|
|
+/**
|
|
|
|
+ * VFIO_MIG_GET_PRECOPY_INFO - _IO(VFIO_TYPE, VFIO_BASE + 21)
|
|
|
|
+ *
|
|
|
|
+ * This ioctl is used on the migration data FD in the precopy phase of the
|
|
|
|
+ * migration data transfer. It returns an estimate of the current data sizes
|
|
|
|
+ * remaining to be transferred. It allows the user to judge when it is
|
|
|
|
+ * appropriate to leave PRE_COPY for STOP_COPY.
|
|
|
|
+ *
|
|
|
|
+ * This ioctl is valid only in PRE_COPY states and kernel driver should
|
|
|
|
+ * return -EINVAL from any other migration state.
|
|
|
|
+ *
|
|
|
|
+ * The vfio_precopy_info data structure returned by this ioctl provides
|
|
|
|
+ * estimates of data available from the device during the PRE_COPY states.
|
|
|
|
+ * This estimate is split into two categories, initial_bytes and
|
|
|
|
+ * dirty_bytes.
|
|
|
|
+ *
|
|
|
|
+ * The initial_bytes field indicates the amount of initial precopy
|
|
|
|
+ * data available from the device. This field should have a non-zero initial
|
|
|
|
+ * value and decrease as migration data is read from the device.
|
|
|
|
+ * It is recommended to leave PRE_COPY for STOP_COPY only after this field
|
|
|
|
+ * reaches zero. Leaving PRE_COPY earlier might make things slower.
|
|
|
|
+ *
|
|
|
|
+ * The dirty_bytes field tracks device state changes relative to data
|
|
|
|
+ * previously retrieved. This field starts at zero and may increase as
|
|
|
|
+ * the internal device state is modified or decrease as that modified
|
|
|
|
+ * state is read from the device.
|
|
|
|
+ *
|
|
|
|
+ * Userspace may use the combination of these fields to estimate the
|
|
|
|
+ * potential data size available during the PRE_COPY phases, as well as
|
|
|
|
+ * trends relative to the rate the device is dirtying its internal
|
|
|
|
+ * state, but these fields are not required to have any bearing relative
|
|
|
|
+ * to the data size available during the STOP_COPY phase.
|
|
|
|
+ *
|
|
|
|
+ * Drivers have a lot of flexibility in when and what they transfer during the
|
|
|
|
+ * PRE_COPY phase, and how they report this from VFIO_MIG_GET_PRECOPY_INFO.
|
|
|
|
+ *
|
|
|
|
+ * During pre-copy the migration data FD has a temporary "end of stream" that is
|
|
|
|
+ * reached when both initial_bytes and dirty_byte are zero. For instance, this
|
|
|
|
+ * may indicate that the device is idle and not currently dirtying any internal
|
|
|
|
+ * state. When read() is done on this temporary end of stream the kernel driver
|
|
|
|
+ * should return ENOMSG from read(). Userspace can wait for more data (which may
|
|
|
|
+ * never come) by using poll.
|
|
|
|
+ *
|
|
|
|
+ * Once in STOP_COPY the migration data FD has a permanent end of stream
|
|
|
|
+ * signaled in the usual way by read() always returning 0 and poll always
|
|
|
|
+ * returning readable. ENOMSG may not be returned in STOP_COPY.
|
|
|
|
+ * Support for this ioctl is mandatory if a driver claims to support
|
|
|
|
+ * VFIO_MIGRATION_PRE_COPY.
|
|
|
|
+ *
|
|
|
|
+ * Return: 0 on success, -1 and errno set on failure.
|
|
|
|
+ */
|
|
|
|
+struct vfio_precopy_info {
|
|
|
|
+ __u32 argsz;
|
|
|
|
+ __u32 flags;
|
|
|
|
+ __aligned_u64 initial_bytes;
|
|
|
|
+ __aligned_u64 dirty_bytes;
|
|
};
|
|
};
|
|
|
|
|
|
|
|
+#define VFIO_MIG_GET_PRECOPY_INFO _IO(VFIO_TYPE, VFIO_BASE + 21)
|
|
|
|
+
|
|
/*
|
|
/*
|
|
* Upon VFIO_DEVICE_FEATURE_SET, allow the device to be moved into a low power
|
|
* Upon VFIO_DEVICE_FEATURE_SET, allow the device to be moved into a low power
|
|
* state with the platform-based power management. Device use of lower power
|
|
* state with the platform-based power management. Device use of lower power
|
|
@@ -1128,6 +1243,19 @@ struct vfio_device_feature_dma_logging_report {
|
|
|
|
|
|
#define VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT 8
|
|
#define VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT 8
|
|
|
|
|
|
|
|
+/*
|
|
|
|
+ * Upon VFIO_DEVICE_FEATURE_GET read back the estimated data length that will
|
|
|
|
+ * be required to complete stop copy.
|
|
|
|
+ *
|
|
|
|
+ * Note: Can be called on each device state.
|
|
|
|
+ */
|
|
|
|
+
|
|
|
|
+struct vfio_device_feature_mig_data_size {
|
|
|
|
+ __aligned_u64 stop_copy_length;
|
|
|
|
+};
|
|
|
|
+
|
|
|
|
+#define VFIO_DEVICE_FEATURE_MIG_DATA_SIZE 9
|
|
|
|
+
|
|
/* -------- API for Type1 VFIO IOMMU -------- */
|
|
/* -------- API for Type1 VFIO IOMMU -------- */
|
|
|
|
|
|
/**
|
|
/**
|