mm: userfaultfd: correct dirty flags set for both present and swap pte

commit 75cb1cca2c880179a11c7dd9380b6f14e41a06a4 upstream.

As David pointed out, what truly matters for mremap and userfaultfd move
operations is the soft dirty bit.  The current comment and
implementation—which always sets the dirty bit for present PTEs and
fails to set the soft dirty bit for swap PTEs—are incorrect.  This could
break features like Checkpoint-Restore in Userspace (CRIU).

This patch updates the behavior to correctly set the soft dirty bit for
both present and swap PTEs in accordance with mremap.

Link: https://lkml.kernel.org/r/20250508220912.7275-1-21cnbao@gmail.com
Fixes: adef440691ba ("userfaultfd: UFFDIO_MOVE uABI")
Signed-off-by: Barry Song <v-songbaohua@oppo.com>
Reported-by: David Hildenbrand <david@redhat.com>
Closes: https://lore.kernel.org/linux-mm/02f14ee1-923f-47e3-a994-4950afb9afcc@redhat.com/
Acked-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 4295a599d714948a7941cfe908085406a70e8d15..30f7c96b0de2495aed187dc614bac77ba1fae02d 100644 (file)
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1068,8 +1068,13 @@ static int move_present_pte(struct mm_struct *mm,
        src_folio->index = linear_page_index(dst_vma, dst_addr);
 
        orig_dst_pte = mk_pte(&src_folio->page, dst_vma->vm_page_prot);
-       /* Follow mremap() behavior and treat the entry dirty after the move */
-       orig_dst_pte = pte_mkwrite(pte_mkdirty(orig_dst_pte), dst_vma);
+       /* Set soft dirty bit so userspace can notice the pte was moved */
+#ifdef CONFIG_MEM_SOFT_DIRTY
+       orig_dst_pte = pte_mksoft_dirty(orig_dst_pte);
+#endif
+       if (pte_dirty(orig_src_pte))
+               orig_dst_pte = pte_mkdirty(orig_dst_pte);
+       orig_dst_pte = pte_mkwrite(orig_dst_pte, dst_vma);
 
        set_pte_at(mm, dst_addr, dst_pte, orig_dst_pte);
 out:
@@ -1104,6 +1109,9 @@ static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma,
        }
 
        orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte);
+#ifdef CONFIG_MEM_SOFT_DIRTY
+       orig_src_pte = pte_swp_mksoft_dirty(orig_src_pte);
+#endif
        set_pte_at(mm, dst_addr, dst_pte, orig_src_pte);
        double_pt_unlock(dst_ptl, src_ptl);