@@ -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.
+ * If pending_bytes > 0, perform the following steps.
+ * b. Read data_offset, indicating that the vendor driver should make data
+ * available through the data section. The vendor driver should return this
+ * read operation only after data is available from (region + data_offset)
+ * to (region + data_offset + data_size).
+ * c. Read data_size, which is the amount of data in bytes available through
+ * the migration region.
+ * Read on data_offset and data_size should return the offset and size of
+ * the current buffer if the user application reads data_offset and
+ * data_size more than once here.
+ * d. Read data_size bytes of data from (region + data_offset) from the
+ * migration region.
+ * e. Process the data.
+ * f. Read pending_bytes, which indicates that the data from the previous
+ * iteration has been read. If pending_bytes > 0, go to step b.
+ *
+ * If an error occurs during the above sequence, the vendor driver can return
+ * an error code for next read() or write() operation, which will terminate the
+ * loop. The user application should then take the next necessary action, for
+ * example, failing migration or terminating the user application.
+ *
+ * The user application can transition from the _SAVING|_RUNNING
+ * (pre-copy state) to the _SAVING (stop-and-copy) state regardless of the
+ * number of pending bytes. The user application should iterate in _SAVING
+ * (stop-and-copy) until pending_bytes is 0.
+ *
+ * The sequence to be followed while _RESUMING device state is as follows:
+ * While data for this device is available, repeat the following steps:
+ * a. Read data_offset from where the user application should write data.
+ * b. Write migration data starting at the migration region + data_offset for
+ * the length determined by data_size from the migration source.
+ * c. Write data_size, which indicates to the vendor driver that data is
+ * written in the migration region. Vendor driver should apply the
+ * user-provided migration region data to the device resume state.
+ *
+ * For the user application, data is opaque. The user application should write
+ * data in the same order as the data is received and the data should be of
+ * same transaction size at the source.
+ */
+
+struct vfio_device_migration_info {
+ __u32 device_state; /* VFIO device state */
+#define VFIO_DEVICE_STATE_STOP (0)
+#define VFIO_DEVICE_STATE_RUNNING (1 << 0)
+#define VFIO_DEVICE_STATE_SAVING (1 << 1)
+#define VFIO_DEVICE_STATE_RESUMING (1 << 2)
+#define VFIO_DEVICE_STATE_MASK (VFIO_DEVICE_STATE_RUNNING | \
+ VFIO_DEVICE_STATE_SAVING | \
+ VFIO_DEVICE_STATE_RESUMING)
+
+#define VFIO_DEVICE_STATE_VALID(state) \
+ (state & VFIO_DEVICE_STATE_RESUMING ? \
+ (state & VFIO_DEVICE_STATE_MASK) == VFIO_DEVICE_STATE_RESUMING : 1)
+
+#define VFIO_DEVICE_STATE_IS_ERROR(state) \
+ ((state & VFIO_DEVICE_STATE_MASK) == (VFIO_DEVICE_STATE_SAVING | \
+ VFIO_DEVICE_STATE_RESUMING))
+
+#define VFIO_DEVICE_STATE_SET_ERROR(state) \
+ ((state & ~VFIO_DEVICE_STATE_MASK) | VFIO_DEVICE_SATE_SAVING | \
+ VFIO_DEVICE_STATE_RESUMING)
+
+ __u32 reserved;
+ __u64 pending_bytes;
+ __u64 data_offset;
+ __u64 data_size;
+} __attribute__((packed));
+
/*
* The MSIX mappable capability informs that MSIX data of a BAR can be mmapped
* which allows direct access to non-MSIX registers which happened to be within
@@ -720,8 +947,9 @@ struct vfio_device_ioeventfd {
struct vfio_iommu_type1_info {
__u32 argsz;
__u32 flags;
-#define VFIO_IOMMU_INFO_PGSIZES (1 << 0) /* supported page sizes info */
-#define VFIO_IOMMU_INFO_CAPS (1 << 1) /* Info supports caps */
+#define VFIO_IOMMU_INFO_PGSIZES (1 << 0) /* supported page sizes info */
+#define VFIO_IOMMU_INFO_CAPS (1 << 1) /* Info supports caps */
+#define VFIO_IOMMU_INFO_DIRTY_PGS (1 << 2) /* supports dirty page tracking */
__u64 iova_pgsizes; /* Bitmap of supported page sizes */
__u32 cap_offset; /* Offset within info struct of first cap */
};
@@ -768,6 +996,12 @@ struct vfio_iommu_type1_dma_map {
#define VFIO_IOMMU_MAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 13)
+struct vfio_bitmap {
+ __u64 pgsize; /* page size for bitmap */
+ __u64 size; /* in bytes */
+ __u64 *data; /* one bit per page */
+};
+
/**
* VFIO_IOMMU_UNMAP_DMA - _IOWR(VFIO_TYPE, VFIO_BASE + 14,
* struct vfio_dma_unmap)
@@ -777,12 +1011,23 @@ struct vfio_iommu_type1_dma_map {
* field. No guarantee is made to the user that arbitrary unmaps of iova
* or size different from those used in the original mapping call will
* succeed.
+ * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP should be set to get dirty bitmap
+ * before unmapping IO virtual addresses. When this flag is set, user must
+ * provide data[] as structure vfio_bitmap. User must allocate memory to get
+ * bitmap, clear the bitmap memory by setting zero and must set size of
+ * allocated memory in vfio_bitmap.size field. One bit in bitmap
+ * represents per page, page of user provided page size in 'pgsize',
+ * consecutively starting from iova offset. Bit set indicates page at that
+ * offset from iova is dirty. Bitmap of pages in the range of unmapped size is
+ * returned in vfio_bitmap.data
*/
struct vfio_iommu_type1_dma_unmap {
__u32 argsz;
__u32 flags;
+#define VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP (1 << 0)
__u64 iova; /* IO virtual address */
__u64 size; /* Size of mapping (bytes) */
+ __u8 data[];
};
#define VFIO_IOMMU_UNMAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 14)
@@ -794,6 +1039,54 @@ struct vfio_iommu_type1_dma_unmap {
#define VFIO_IOMMU_ENABLE _IO(VFIO_TYPE, VFIO_BASE + 15)
#define VFIO_IOMMU_DISABLE _IO(VFIO_TYPE, VFIO_BASE + 16)
+/**
+ * VFIO_IOMMU_DIRTY_PAGES - _IOWR(VFIO_TYPE, VFIO_BASE + 17,
+ * struct vfio_iommu_type1_dirty_bitmap)
+ * IOCTL is used for dirty pages tracking. Caller sets argsz, which is size of
+ * struct vfio_iommu_type1_dirty_bitmap. Caller set flag depend on which
+ * operation to perform, details as below:
+ *
+ * When IOCTL is called with VFIO_IOMMU_DIRTY_PAGES_FLAG_START set, indicates
+ * migration is active and IOMMU module should track pages which are pinned and
+ * could be dirtied by device.
+ * Dirty pages are tracked until tracking is stopped by user application by
+ * setting VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP flag.
+ *
+ * When IOCTL is called with VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP set, indicates
+ * IOMMU should stop tracking pinned pages.
+ *
+ * When IOCTL is called with VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP flag set,
+ * IOCTL returns dirty pages bitmap for IOMMU container during migration for
+ * given IOVA range. User must provide data[] as the structure
+ * vfio_iommu_type1_dirty_bitmap_get through which user provides IOVA range and
+ * pgsize. This interface supports to get bitmap of smallest supported pgsize
+ * only and can be modified in future to get bitmap of specified pgsize.
+ * User must allocate memory for bitmap, zero the bitmap memory and set size
+ * of allocated memory in bitmap_size field. One bit is used to represent one
+ * page consecutively starting from iova offset. User should provide page size
+ * in 'pgsize'. Bit set in bitmap indicates page at that offset from iova is
+ * dirty. Caller must set argsz including size of structure
+ * vfio_iommu_type1_dirty_bitmap_get.
+ *
+ * Only one flag should be set at a time.
+ */
+struct vfio_iommu_type1_dirty_bitmap {
+ __u32 argsz;
+ __u32 flags;
+#define VFIO_IOMMU_DIRTY_PAGES_FLAG_START (1 << 0)
+#define VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP (1 << 1)
+#define VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP (1 << 2)
+ __u8 data[];
+};
+
+struct vfio_iommu_type1_dirty_bitmap_get {
+ __u64 iova; /* IO virtual address */
+ __u64 size; /* Size of iova range */
+ struct vfio_bitmap bitmap;
+};
+
+#define VFIO_IOMMU_DIRTY_PAGES _IO(VFIO_TYPE, VFIO_BASE + 17)
+
/* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
/*