mm/shmem: handle uffd-wp during fork()

Normally we skip copy page when fork() for VM_SHARED shmem, but we can't
skip it anymore if uffd-wp is enabled on dst vma.  This should only happen
when the src uffd has UFFD_FEATURE_EVENT_FORK enabled on uffd-wp shmem
vma, so that VM_UFFD_WP will be propagated onto dst vma too, then we
should copy the pgtables with uffd-wp bit and pte markers, because these
information will be lost otherwise.

Since the condition checks will become even more complicated for deciding
"whether a vma needs to copy the pgtable during fork()", introduce a
helper vma_needs_copy() for it, so everything will be clearer.

Link: https://lkml.kernel.org/r/20220405014855.14468-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/memory.c b/mm/memory.c
index ecb1d58dcaef61918050d0db33c8b58abf653237..8827157cf3928d76894c49035c95557a8888e4c8 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -867,6 +867,14 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
                if (try_restore_exclusive_pte(src_pte, src_vma, addr))
                        return -EBUSY;
                return -ENOENT;
+       } else if (is_pte_marker_entry(entry)) {
+               /*
+                * We're copying the pgtable should only because dst_vma has
+                * uffd-wp enabled, do sanity check.
+                */
+               WARN_ON_ONCE(!userfaultfd_wp(dst_vma));
+               set_pte_at(dst_mm, addr, dst_pte, pte);
+               return 0;
        }
        if (!userfaultfd_wp(dst_vma))
                pte = pte_swp_clear_uffd_wp(pte);
@@ -1221,6 +1229,38 @@ copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
        return 0;
 }
 
+/*
+ * Return true if the vma needs to copy the pgtable during this fork().  Return
+ * false when we can speed up fork() by allowing lazy page faults later until
+ * when the child accesses the memory range.
+ */
+bool
+vma_needs_copy(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
+{
+       /*
+        * Always copy pgtables when dst_vma has uffd-wp enabled even if it's
+        * file-backed (e.g. shmem). Because when uffd-wp is enabled, pgtable
+        * contains uffd-wp protection information, that's something we can't
+        * retrieve from page cache, and skip copying will lose those info.
+        */
+       if (userfaultfd_wp(dst_vma))
+               return true;
+
+       if (src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP))
+               return true;
+
+       if (src_vma->anon_vma)
+               return true;
+
+       /*
+        * Don't copy ptes where a page fault will fill them correctly.  Fork
+        * becomes much lighter when there are big shared or private readonly
+        * mappings. The tradeoff is that copy_page_range is more efficient
+        * than faulting.
+        */
+       return false;
+}
+
 int
 copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 {
@@ -1234,14 +1274,7 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
        bool is_cow;
        int ret;
 
-       /*
-        * Don't copy ptes where a page fault will fill them correctly.
-        * Fork becomes much lighter when there are big shared or private
-        * readonly mappings. The tradeoff is that copy_page_range is more
-        * efficient than faulting.
-        */
-       if (!(src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) &&
-           !src_vma->anon_vma)
+       if (!vma_needs_copy(dst_vma, src_vma))
                return 0;
 
        if (is_vm_hugetlb_page(src_vma))