mm/hugetlb: fix uffd-wp during fork()

Patch series "mm/hugetlb: More fixes around uffd-wp vs fork() / RO pins",
v2.

This patch (of 6):

There're a bunch of things that were wrong:

  - Reading uffd-wp bit from a swap entry should use pte_swp_uffd_wp()
    rather than huge_pte_uffd_wp().

  - When copying over a pte, we should drop uffd-wp bit when
    !EVENT_FORK (aka, when !userfaultfd_wp(dst_vma)).

  - When doing early CoW for private hugetlb (e.g. when the parent page was
    pinned), uffd-wp bit should be properly carried over if necessary.

No bug reported probably because most people do not even care about these
corner cases, but they are still bugs and can be exposed by the recent unit
tests introduced, so fix all of them in one shot.

Link: https://lkml.kernel.org/r/20230417195317.898696-1-peterx@redhat.com
Link: https://lkml.kernel.org/r/20230417195317.898696-2-peterx@redhat.com
Fixes: bc70fbf269fd ("mm/hugetlb: handle uffd-wp during fork()")
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Mika Penttilä <mpenttil@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a08fb47..d105b0b 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4953,11 +4953,15 @@ static bool is_hugetlb_entry_hwpoisoned(pte_t pte)
 
 static void
 hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr,
-                    struct folio *new_folio)
+                     struct folio *new_folio, pte_t old)
 {
+       pte_t newpte = make_huge_pte(vma, &new_folio->page, 1);
+
        __folio_mark_uptodate(new_folio);
        hugepage_add_new_anon_rmap(new_folio, vma, addr);
-       set_huge_pte_at(vma->vm_mm, addr, ptep, make_huge_pte(vma, &new_folio->page, 1));
+       if (userfaultfd_wp(vma) && huge_pte_uffd_wp(old))
+               newpte = huge_pte_mkuffd_wp(newpte);
+       set_huge_pte_at(vma->vm_mm, addr, ptep, newpte);
        hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm);
        folio_set_hugetlb_migratable(new_folio);
 }
@@ -5032,14 +5036,12 @@ again:
                         */
                        ;
                } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) {
-                       bool uffd_wp = huge_pte_uffd_wp(entry);
-
-                       if (!userfaultfd_wp(dst_vma) && uffd_wp)
+                       if (!userfaultfd_wp(dst_vma))
                                entry = huge_pte_clear_uffd_wp(entry);
                        set_huge_pte_at(dst, addr, dst_pte, entry);
                } else if (unlikely(is_hugetlb_entry_migration(entry))) {
                        swp_entry_t swp_entry = pte_to_swp_entry(entry);
-                       bool uffd_wp = huge_pte_uffd_wp(entry);
+                       bool uffd_wp = pte_swp_uffd_wp(entry);
 
                        if (!is_readable_migration_entry(swp_entry) && cow) {
                                /*
@@ -5050,10 +5052,10 @@ again:
                                                        swp_offset(swp_entry));
                                entry = swp_entry_to_pte(swp_entry);
                                if (userfaultfd_wp(src_vma) && uffd_wp)
-                                       entry = huge_pte_mkuffd_wp(entry);
+                                       entry = pte_swp_mkuffd_wp(entry);
                                set_huge_pte_at(src, addr, src_pte, entry);
                        }
-                       if (!userfaultfd_wp(dst_vma) && uffd_wp)
+                       if (!userfaultfd_wp(dst_vma))
                                entry = huge_pte_clear_uffd_wp(entry);
                        set_huge_pte_at(dst, addr, dst_pte, entry);
                } else if (unlikely(is_pte_marker(entry))) {
@@ -5118,7 +5120,8 @@ again:
                                        /* huge_ptep of dst_pte won't change as in child */
                                        goto again;
                                }
-                               hugetlb_install_folio(dst_vma, dst_pte, addr, new_folio);
+                               hugetlb_install_folio(dst_vma, dst_pte, addr,
+                                                     new_folio, src_pte_old);
                                spin_unlock(src_ptl);
                                spin_unlock(dst_ptl);
                                continue;
@@ -5136,6 +5139,9 @@ again:
                                entry = huge_pte_wrprotect(entry);
                        }
 
+                       if (!userfaultfd_wp(dst_vma))
+                               entry = huge_pte_clear_uffd_wp(entry);
+
                        set_huge_pte_at(dst, addr, dst_pte, entry);
                        hugetlb_count_add(npages, dst);
                }