mm/shmem: take care of UFFDIO_COPY_MODE_WP

Pass wp_copy into shmem_mfill_atomic_pte() through the stack, then apply
the UFFD_WP bit properly when the UFFDIO_COPY on shmem is with
UFFDIO_COPY_MODE_WP.  wp_copy lands mfill_atomic_install_pte() finally.

Note: we must do pte_wrprotect() if !writable in
mfill_atomic_install_pte(), as mk_pte() could return a writable pte (e.g.,
when VM_SHARED on a shmem file).

Link: https://lkml.kernel.org/r/20220405014841.14185-1-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>
This commit is contained in:
Peter Xu 2022-05-12 20:22:52 -07:00 committed by Andrew Morton
parent 1db9dbc2ef
commit 8ee79edff6
3 changed files with 22 additions and 9 deletions

View file

@ -145,11 +145,11 @@ extern int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
struct vm_area_struct *dst_vma,
unsigned long dst_addr,
unsigned long src_addr,
bool zeropage,
bool zeropage, bool wp_copy,
struct page **pagep);
#else /* !CONFIG_SHMEM */
#define shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, \
src_addr, zeropage, pagep) ({ BUG(); 0; })
src_addr, zeropage, wp_copy, pagep) ({ BUG(); 0; })
#endif /* CONFIG_SHMEM */
#endif /* CONFIG_USERFAULTFD */

View file

@ -2319,7 +2319,7 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
struct vm_area_struct *dst_vma,
unsigned long dst_addr,
unsigned long src_addr,
bool zeropage,
bool zeropage, bool wp_copy,
struct page **pagep)
{
struct inode *inode = file_inode(dst_vma->vm_file);
@ -2392,7 +2392,7 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
goto out_release;
ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
page, true, false);
page, true, wp_copy);
if (ret)
goto out_delete_from_cache;

View file

@ -78,10 +78,19 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
* Always mark a PTE as write-protected when needed, regardless of
* VM_WRITE, which the user might change.
*/
if (wp_copy)
if (wp_copy) {
_dst_pte = pte_mkuffd_wp(_dst_pte);
else if (writable)
writable = false;
}
if (writable)
_dst_pte = pte_mkwrite(_dst_pte);
else
/*
* We need this to make sure write bit removed; as mk_pte()
* could return a pte with write bit set.
*/
_dst_pte = pte_wrprotect(_dst_pte);
dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
@ -96,7 +105,12 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
}
ret = -EEXIST;
if (!pte_none(*dst_pte))
/*
* We allow to overwrite a pte marker: consider when both MISSING|WP
* registered, we firstly wr-protect a none pte which has no page cache
* page backing it, then access the page.
*/
if (!pte_none_mostly(*dst_pte))
goto out_unlock;
if (page_in_cache) {
@ -480,11 +494,10 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm,
err = mfill_zeropage_pte(dst_mm, dst_pmd,
dst_vma, dst_addr);
} else {
VM_WARN_ON_ONCE(wp_copy);
err = shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma,
dst_addr, src_addr,
mode != MCOPY_ATOMIC_NORMAL,
page);
wp_copy, page);
}
return err;