[PATCH -mm] mm, gup: prevent pmd checking race in follow_pmd_mask()

From: Huang, Ying
Date: Tue Apr 03 2018 - 23:23:16 EST

From: Huang Ying <ying.huang@xxxxxxxxx>

mmap_sem will be read locked when calling follow_pmd_mask(). But this
cannot prevent PMD from being changed for all cases when PTL is
unlocked, for example, from pmd_trans_huge() to pmd_none() via
MADV_DONTNEED. So it is possible for the pmd_present() check in
follow_pmd_mask() encounter a none PMD. This may cause incorrect
VM_BUG_ON() or infinite loop. Fixed this via reading PMD entry again
but only once and checking the local variable and pmd_none() in the
retry loop.

As Kirill pointed out, with PTL unlocked, the *pmd may be changed
under us, so read it directly again and again may incur weird bugs.
So although using *pmd directly other than pmd_present() checking may
be safe, it is still better to replace them to read *pmd once and
check the local variable for multiple times.

Signed-off-by: "Huang, Ying" <ying.huang@xxxxxxxxx>
# When PTL unlocked, replace all *pmd with local variable
Suggested-by: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Zi Yan <zi.yan@xxxxxxxxxxxxxx>
mm/gup.c | 30 +++++++++++++++++++-----------
1 file changed, 19 insertions(+), 11 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index 2e2df7f3e92d..51734292839b 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -213,53 +213,61 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
unsigned long address, pud_t *pudp,
unsigned int flags, unsigned int *page_mask)
- pmd_t *pmd;
+ pmd_t *pmd, pmdval;
spinlock_t *ptl;
struct page *page;
struct mm_struct *mm = vma->vm_mm;

pmd = pmd_offset(pudp, address);
- if (pmd_none(*pmd))
+ pmdval = READ_ONCE(*pmd);
+ if (pmd_none(pmdval))
return no_page_table(vma, flags);
- if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
+ if (pmd_huge(pmdval) && vma->vm_flags & VM_HUGETLB) {
page = follow_huge_pmd(mm, address, pmd, flags);
if (page)
return page;
return no_page_table(vma, flags);
- if (is_hugepd(__hugepd(pmd_val(*pmd)))) {
+ if (is_hugepd(__hugepd(pmd_val(pmdval)))) {
page = follow_huge_pd(vma, address,
- __hugepd(pmd_val(*pmd)), flags,
+ __hugepd(pmd_val(pmdval)), flags,
if (page)
return page;
return no_page_table(vma, flags);
- if (!pmd_present(*pmd)) {
+ if (!pmd_present(pmdval)) {
if (likely(!(flags & FOLL_MIGRATION)))
return no_page_table(vma, flags);
VM_BUG_ON(thp_migration_supported() &&
- !is_pmd_migration_entry(*pmd));
- if (is_pmd_migration_entry(*pmd))
+ !is_pmd_migration_entry(pmdval));
+ if (is_pmd_migration_entry(pmdval))
pmd_migration_entry_wait(mm, pmd);
+ pmdval = READ_ONCE(*pmd);
+ if (pmd_none(pmdval))
+ return no_page_table(vma, flags);
goto retry;
- if (pmd_devmap(*pmd)) {
+ if (pmd_devmap(pmdval)) {
ptl = pmd_lock(mm, pmd);
page = follow_devmap_pmd(vma, address, pmd, flags);
if (page)
return page;
- if (likely(!pmd_trans_huge(*pmd)))
+ if (likely(!pmd_trans_huge(pmdval)))
return follow_page_pte(vma, address, pmd, flags);

- if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
+ if ((flags & FOLL_NUMA) && pmd_protnone(pmdval))
return no_page_table(vma, flags);

ptl = pmd_lock(mm, pmd);
+ if (unlikely(pmd_none(*pmd))) {
+ spin_unlock(ptl);
+ return no_page_table(vma, flags);
+ }
if (unlikely(!pmd_present(*pmd))) {
if (likely(!(flags & FOLL_MIGRATION)))