[PATCH v17 Kernel 5/7] vfio iommu: Update UNMAP_DMA ioctl to get dirty bitmap before unmap

[Kirti Wankhede]

DMA mapped pages, including those pinned by mdev vendor drivers, might
get unpinned and unmapped while migration is active and device is still
running. For example, in pre-copy phase while guest driver could access
those pages, host device or vendor driver can dirty these mapped pages.
Such pages should be marked dirty so as to maintain memory consistency
for a user making use of dirty page tracking.

To get bitmap during unmap, user should allocate memory for bitmap, set
size of allocated memory, set page size to be considered for bitmap and
set flag VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP.

Signed-off-by: Kirti Wankhede <address@hidden>
Reviewed-by: Neo Jia <address@hidden>
---
 drivers/vfio/vfio_iommu_type1.c | 55 ++++++++++++++++++++++++++++++++++++++---
 include/uapi/linux/vfio.h       | 10 ++++++++
 2 files changed, 61 insertions(+), 4 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 5efebc2b60e1..266550bd7307 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -983,7 +983,8 @@ static int verify_bitmap_size(uint64_t npages, uint64_t 
bitmap_size)
 }
 
 static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
-                            struct vfio_iommu_type1_dma_unmap *unmap)
+                            struct vfio_iommu_type1_dma_unmap *unmap,
+                            struct vfio_bitmap *bitmap)
 {
        uint64_t mask;
        struct vfio_dma *dma, *dma_last = NULL;
@@ -1034,6 +1035,10 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
         * will be returned if these conditions are not met.  The v2 interface
         * will only return success and a size of zero if there were no
         * mappings within the range.
+        *
+        * When VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP flag is set, unmap request
+        * must be for single mapping. Multiple mappings with this flag set is
+        * not supported.
         */
        if (iommu->v2) {
                dma = vfio_find_dma(iommu, unmap->iova, 1);
@@ -1041,6 +1046,14 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
                        ret = -EINVAL;
                        goto unlock;
                }
+
+               if ((unmap->flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) &&
+                   dma &&
+                   (dma->iova != unmap->iova || dma->size != unmap->size)) {
+                       ret = -EINVAL;
+                       goto unlock;
+               }
+
                dma = vfio_find_dma(iommu, unmap->iova + unmap->size - 1, 0);
                if (dma && dma->iova + dma->size != unmap->iova + unmap->size) {
                        ret = -EINVAL;
@@ -1058,6 +1071,11 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
                if (dma->task->mm != current->mm)
                        break;
 
+               if ((unmap->flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) &&
+                    iommu->dirty_page_tracking)
+                       vfio_iova_dirty_bitmap(iommu, dma->iova, dma->size,
+                                               bitmap->pgsize, bitmap->data);
+
                if (!RB_EMPTY_ROOT(&dma->pfn_list)) {
                        struct vfio_iommu_type1_dma_unmap nb_unmap;
 
@@ -2419,17 +2437,46 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
 
        } else if (cmd == VFIO_IOMMU_UNMAP_DMA) {
                struct vfio_iommu_type1_dma_unmap unmap;
-               long ret;
+               struct vfio_bitmap bitmap = { 0 };
+               int ret;
 
                minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, size);
 
                if (copy_from_user(&unmap, (void __user *)arg, minsz))
                        return -EFAULT;
 
-               if (unmap.argsz < minsz || unmap.flags)
+               if (unmap.argsz < minsz ||
+                   unmap.flags & ~VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP)
                        return -EINVAL;
 
-               ret = vfio_dma_do_unmap(iommu, &unmap);
+               if (unmap.flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) {
+                       unsigned long pgshift;
+                       size_t iommu_pgsize =
+                               (size_t)1 << __ffs(vfio_pgsize_bitmap(iommu));
+
+                       if (unmap.argsz < (minsz + sizeof(bitmap)))
+                               return -EINVAL;
+
+                       if (copy_from_user(&bitmap,
+                                          (void __user *)(arg + minsz),
+                                          sizeof(bitmap)))
+                               return -EFAULT;
+
+                       /* allow only min supported pgsize */
+                       if (bitmap.pgsize != iommu_pgsize)
+                               return -EINVAL;
+                       if (!access_ok((void __user *)bitmap.data, bitmap.size))
+                               return -EINVAL;
+
+                       pgshift = __ffs(bitmap.pgsize);
+                       ret = verify_bitmap_size(unmap.size >> pgshift,
+                                                bitmap.size);
+                       if (ret)
+                               return ret;
+
+               }
+
+               ret = vfio_dma_do_unmap(iommu, &unmap, &bitmap);
                if (ret)
                        return ret;
 
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 5f359c63f5ef..e3cbf8b78623 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -1048,12 +1048,22 @@ struct vfio_bitmap {
  * 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 and must set size of allocated memory in vfio_bitmap.size field.
+ * A bit in bitmap represents one 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)
-- 
2.7.0