mm: hugetlb: fix missing cache flush in hugetlb_mcopy_atomic_pte()

folio_copy() will copy the data from one page to the target page, then
the target page will be mapped to the user space address, which might
have an alias issue with the kernel address used to copy the data from
the page to.  There are 2 ways to fix this issue.

 1) insert flush_dcache_page() after folio_copy().

 2) replace folio_copy() with copy_user_huge_page() which already
    considers the cache maintenance.

We chose 2) way to fix the issue since architectures can optimize this
situation.  It is also make backports easier.

Link: https://lkml.kernel.org/r/[email protected]
Fixes: 8cc5fcbb5be8 ("mm, hugetlb: fix racy resv_huge_pages underflow on UFFDIO_COPY")
Signed-off-by: Muchun Song <[email protected]>
Reviewed-by: Mike Kravetz <[email protected]>
Cc: Axel Rasmussen <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: Fam Zheng <[email protected]>
Cc: Kirill A. Shutemov <[email protected]>
Cc: Lars Persson <[email protected]>
Cc: Peter Xu <[email protected]>
Cc: Xiongchun Duan <[email protected]>
Cc: Zi Yan <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

1 files changed, 2 insertions, 1 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a404af0b49a0..3d450f802823 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5816,7 +5816,8 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 			*pagep = NULL;
 			goto out;
 		}
-		folio_copy(page_folio(page), page_folio(*pagep));
+		copy_user_huge_page(page, *pagep, dst_addr, dst_vma,
+				    pages_per_huge_page(h));
 		put_page(*pagep);
 		*pagep = NULL;
 	}