iommufd/iova_bitmap: Ensure that iova_bitmap_set() handles the full IOVA

Generally userspace is going to step the dirty bitmap through the IOVA
space. However if the bitmap ends in the middle of a large PTE this is
problematic. The first step will clear the dirty bit and report dirty to
the end of its bitmap while the second step will see the clear'd dirty and
report clean for the start of the bitmap. If it happens this ends up
losing dirties.

Further this function is missing bounds checking so if this does happen
ther is a good chance it will write memory beyond what the userspace was
expecting.

Return an error code if this illegal condition happens.

Fixes: 58ccf0190d19 ("vfio: Add an IOVA bitmap support")
Cc: stable@vger.kernel.org
Assisted-by: LLM
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Link: https://patch.msgid.link/20260925161142.189813-2-parri.andrea@gmail.com
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

1 files changed, 6 insertions, 0 deletions

diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
index b4c7194cb08d..010f47f7d3d2 100644
--- a/include/uapi/linux/iommufd.h
+++ b/include/uapi/linux/iommufd.h
@@ -871,6 +871,12 @@ enum iommufd_hwpt_get_dirty_bitmap_flags {
  * Walk the IOMMU pagetables for a given IOVA range to return a bitmap
  * with the dirty IOVAs. In doing so it will also by default clear any
  * dirty bit metadata set in the IOPTE.
+ *
+ * The IOVA range given must fully enclose any IOPTE. If the range starts or
+ * ends inside a dirty IOPTE then the ioctl will fail. This avoids partially
+ * reporting a dirty range.
+ *
+ * On failure the dirty state becomes unknown and the userspace must restart.
  */
 struct iommu_hwpt_get_dirty_bitmap {
 	__u32 size;