IOMMU container maintains a list of all pages pinned by vfio_pin_pages API.
All pages pinned by vendor driver through this API should be considered as
dirty during migration. When container consists of IOMMU capable device and
all pages are pinned and mapped, then all pages are marked dirty.
Added support to start/stop pinned and unpinned pages tracking and to get
bitmap of all dirtied pages for requested IO virtual address range.
Signed-off-by: Kirti Wankhede <kwankhede@xxxxxxxxxx>
Reviewed-by: Neo Jia <cjia@xxxxxxxxxx>
---
include/uapi/linux/vfio.h | 51 +++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 51 insertions(+)
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index be34ec278710..02d555cc7036 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -1021,6 +1021,57 @@ 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 being
+ * unpinned. Unpinned 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 unpinned pages and also free previously tracked
+ * unpinned pages data.
+ *
+ * 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 */
+ __u64 pgsize; /* page size for bitmap */
+ __u64 bitmap_size; /* in bytes */
+ __u64 __user *bitmap; /* one bit per page */
+};
+
+#define VFIO_IOMMU_DIRTY_PAGES _IO(VFIO_TYPE, VFIO_BASE + 17)
+
/* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
/*
--
2.7.0
