summary refs log tree commit diff stats
path: root/linux-headers/linux/vfio.h
diff options
context:
space:
mode:
Diffstat (limited to 'linux-headers/linux/vfio.h')
-rw-r--r--linux-headers/linux/vfio.h278
1 files changed, 274 insertions, 4 deletions
diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h
index ede44b5572..c59692ce0b 100644
--- a/linux-headers/linux/vfio.h
+++ b/linux-headers/linux/vfio.h
@@ -819,12 +819,20 @@ struct vfio_device_feature {
  * VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P means that RUNNING_P2P
  * 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.
  */
 struct vfio_device_feature_migration {
 	__aligned_u64 flags;
 #define VFIO_MIGRATION_STOP_COPY	(1 << 0)
 #define VFIO_MIGRATION_P2P		(1 << 1)
+#define VFIO_MIGRATION_PRE_COPY		(1 << 2)
 };
 #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
  *  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
+ * 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 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.
  *
+ * PRE_COPY -> RUNNING
  * RUNNING_P2P -> RUNNING
  *   While in RUNNING the device is fully operational, the device may generate
  *   interrupts, DMA, respond to MMIO, all vfio device regions are functional,
  *   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
  * STOP -> RUNNING_P2P
  *   While in RUNNING_P2P the device is partially running in the P2P quiescent
  *   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
- *   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
  *   with the addition that the data transfers session continues to stream the
  *   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
  *   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
  *   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
@@ -950,7 +998,7 @@ struct vfio_device_feature_mig_state {
  * 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
  * 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
  * 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
@@ -963,6 +1011,8 @@ struct vfio_device_feature_mig_state {
  * above FSM arcs. As there are multiple paths through the FSM arcs the path
  * should be selected based on the following rules:
  *   - 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.
  *
  * 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
  * VFIO_DEVICE_FEATURE_MIGRATION. By using combination transitions the user can
  * 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 {
 	VFIO_DEVICE_STATE_ERROR = 0,
@@ -984,8 +1037,225 @@ enum vfio_device_mig_state {
 	VFIO_DEVICE_STATE_STOP_COPY = 3,
 	VFIO_DEVICE_STATE_RESUMING = 4,
 	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
+ * state with the platform-based power management.  Device use of lower power
+ * states depends on factors managed by the runtime power management core,
+ * including system level support and coordinating support among dependent
+ * devices.  Enabling device low power entry does not guarantee lower power
+ * usage by the device, nor is a mechanism provided through this feature to
+ * know the current power state of the device.  If any device access happens
+ * (either from the host or through the vfio uAPI) when the device is in the
+ * low power state, then the host will move the device out of the low power
+ * state as necessary prior to the access.  Once the access is completed, the
+ * device may re-enter the low power state.  For single shot low power support
+ * with wake-up notification, see
+ * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP below.  Access to mmap'd
+ * device regions is disabled on LOW_POWER_ENTRY and may only be resumed after
+ * calling LOW_POWER_EXIT.
+ */
+#define VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY 3
+
+/*
+ * This device feature has the same behavior as
+ * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY with the exception that the user
+ * provides an eventfd for wake-up notification.  When the device moves out of
+ * the low power state for the wake-up, the host will not allow the device to
+ * re-enter a low power state without a subsequent user call to one of the low
+ * power entry device feature IOCTLs.  Access to mmap'd device regions is
+ * disabled on LOW_POWER_ENTRY_WITH_WAKEUP and may only be resumed after the
+ * low power exit.  The low power exit can happen either through LOW_POWER_EXIT
+ * or through any other access (where the wake-up notification has been
+ * generated).  The access to mmap'd device regions will not trigger low power
+ * exit.
+ *
+ * The notification through the provided eventfd will be generated only when
+ * the device has entered and is resumed from a low power state after
+ * calling this device feature IOCTL.  A device that has not entered low power
+ * state, as managed through the runtime power management core, will not
+ * generate a notification through the provided eventfd on access.  Calling the
+ * LOW_POWER_EXIT feature is optional in the case where notification has been
+ * signaled on the provided eventfd that a resume from low power has occurred.
+ */
+struct vfio_device_low_power_entry_with_wakeup {
+	__s32 wakeup_eventfd;
+	__u32 reserved;
+};
+
+#define VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP 4
+
+/*
+ * Upon VFIO_DEVICE_FEATURE_SET, disallow use of device low power states as
+ * previously enabled via VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY or
+ * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP device features.
+ * This device feature IOCTL may itself generate a wakeup eventfd notification
+ * in the latter case if the device had previously entered a low power state.
+ */
+#define VFIO_DEVICE_FEATURE_LOW_POWER_EXIT 5
+
+/*
+ * Upon VFIO_DEVICE_FEATURE_SET start/stop device DMA logging.
+ * VFIO_DEVICE_FEATURE_PROBE can be used to detect if the device supports
+ * DMA logging.
+ *
+ * DMA logging allows a device to internally record what DMAs the device is
+ * initiating and report them back to userspace. It is part of the VFIO
+ * migration infrastructure that allows implementing dirty page tracking
+ * during the pre copy phase of live migration. Only DMA WRITEs are logged,
+ * and this API is not connected to VFIO_DEVICE_FEATURE_MIG_DEVICE_STATE.
+ *
+ * When DMA logging is started a range of IOVAs to monitor is provided and the
+ * device can optimize its logging to cover only the IOVA range given. Each
+ * DMA that the device initiates inside the range will be logged by the device
+ * for later retrieval.
+ *
+ * page_size is an input that hints what tracking granularity the device
+ * should try to achieve. If the device cannot do the hinted page size then
+ * it's the driver choice which page size to pick based on its support.
+ * On output the device will return the page size it selected.
+ *
+ * ranges is a pointer to an array of
+ * struct vfio_device_feature_dma_logging_range.
+ *
+ * The core kernel code guarantees to support by minimum num_ranges that fit
+ * into a single kernel page. User space can try higher values but should give
+ * up if the above can't be achieved as of some driver limitations.
+ *
+ * A single call to start device DMA logging can be issued and a matching stop
+ * should follow at the end. Another start is not allowed in the meantime.
+ */
+struct vfio_device_feature_dma_logging_control {
+	__aligned_u64 page_size;
+	__u32 num_ranges;
+	__u32 __reserved;
+	__aligned_u64 ranges;
 };
 
+struct vfio_device_feature_dma_logging_range {
+	__aligned_u64 iova;
+	__aligned_u64 length;
+};
+
+#define VFIO_DEVICE_FEATURE_DMA_LOGGING_START 6
+
+/*
+ * Upon VFIO_DEVICE_FEATURE_SET stop device DMA logging that was started
+ * by VFIO_DEVICE_FEATURE_DMA_LOGGING_START
+ */
+#define VFIO_DEVICE_FEATURE_DMA_LOGGING_STOP 7
+
+/*
+ * Upon VFIO_DEVICE_FEATURE_GET read back and clear the device DMA log
+ *
+ * Query the device's DMA log for written pages within the given IOVA range.
+ * During querying the log is cleared for the IOVA range.
+ *
+ * bitmap is a pointer to an array of u64s that will hold the output bitmap
+ * with 1 bit reporting a page_size unit of IOVA. The mapping of IOVA to bits
+ * is given by:
+ *  bitmap[(addr - iova)/page_size] & (1ULL << (addr % 64))
+ *
+ * The input page_size can be any power of two value and does not have to
+ * match the value given to VFIO_DEVICE_FEATURE_DMA_LOGGING_START. The driver
+ * will format its internal logging to match the reporting page size, possibly
+ * by replicating bits if the internal page size is lower than requested.
+ *
+ * The LOGGING_REPORT will only set bits in the bitmap and never clear or
+ * perform any initialization of the user provided bitmap.
+ *
+ * If any error is returned userspace should assume that the dirty log is
+ * corrupted. Error recovery is to consider all memory dirty and try to
+ * restart the dirty tracking, or to abort/restart the whole migration.
+ *
+ * If DMA logging is not enabled, an error will be returned.
+ *
+ */
+struct vfio_device_feature_dma_logging_report {
+	__aligned_u64 iova;
+	__aligned_u64 length;
+	__aligned_u64 page_size;
+	__aligned_u64 bitmap;
+};
+
+#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 -------- */
 
 /**