khugepaged: fix use-after-free in collapse_huge_page()
hugepage_vma_revalidate() tries to re-check if we still should try to
collapse small pages into huge one after the re-acquiring mmap_sem.
The problem Dmitry Vyukov reported[1] is that the vma found by
hugepage_vma_revalidate() can be suitable for huge pages, but not the
same vma we had before dropping mmap_sem. And dereferencing original
vma can lead to fun results..
Let's use vma hugepage_vma_revalidate() found instead of assuming it's the
same as what we had before the lock was dropped.
[1] http://lkml.kernel.org/r/CACT4Y+Z3gigBvhca9kRJFcjX0G70V_nRhbwKBU+yGoESBDKi9Q@mail.gmail.com
Link: http://lkml.kernel.org/r/20160907122559.GA6542@black.fi.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Ebru Akagunduz <ebru.akagunduz@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vegard Nossum <vegard.nossum@oracle.com>
Cc: Sasha Levin <levinsasha928@gmail.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: syzkaller <syzkaller@googlegroups.com>
Cc: Kostya Serebryany <kcc@google.com>
Cc: Alexander Potapenko <glider@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 79c52d0..62339bf 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -838,7 +838,8 @@
* value (scan code).
*/
-static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address)
+static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
+ struct vm_area_struct **vmap)
{
struct vm_area_struct *vma;
unsigned long hstart, hend;
@@ -846,7 +847,7 @@
if (unlikely(khugepaged_test_exit(mm)))
return SCAN_ANY_PROCESS;
- vma = find_vma(mm, address);
+ *vmap = vma = find_vma(mm, address);
if (!vma)
return SCAN_VMA_NULL;
@@ -898,7 +899,7 @@
/* do_swap_page returns VM_FAULT_RETRY with released mmap_sem */
if (ret & VM_FAULT_RETRY) {
down_read(&mm->mmap_sem);
- if (hugepage_vma_revalidate(mm, address)) {
+ if (hugepage_vma_revalidate(mm, address, &fe.vma)) {
/* vma is no longer available, don't continue to swapin */
trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
return false;
@@ -923,7 +924,6 @@
static void collapse_huge_page(struct mm_struct *mm,
unsigned long address,
struct page **hpage,
- struct vm_area_struct *vma,
int node, int referenced)
{
pmd_t *pmd, _pmd;
@@ -933,6 +933,7 @@
spinlock_t *pmd_ptl, *pte_ptl;
int isolated = 0, result = 0;
struct mem_cgroup *memcg;
+ struct vm_area_struct *vma;
unsigned long mmun_start; /* For mmu_notifiers */
unsigned long mmun_end; /* For mmu_notifiers */
gfp_t gfp;
@@ -961,7 +962,7 @@
}
down_read(&mm->mmap_sem);
- result = hugepage_vma_revalidate(mm, address);
+ result = hugepage_vma_revalidate(mm, address, &vma);
if (result) {
mem_cgroup_cancel_charge(new_page, memcg, true);
up_read(&mm->mmap_sem);
@@ -994,7 +995,7 @@
* handled by the anon_vma lock + PG_lock.
*/
down_write(&mm->mmap_sem);
- result = hugepage_vma_revalidate(mm, address);
+ result = hugepage_vma_revalidate(mm, address, &vma);
if (result)
goto out;
/* check if the pmd is still valid */
@@ -1202,7 +1203,7 @@
if (ret) {
node = khugepaged_find_target_node();
/* collapse_huge_page will return with the mmap_sem released */
- collapse_huge_page(mm, address, hpage, vma, node, referenced);
+ collapse_huge_page(mm, address, hpage, node, referenced);
}
out:
trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced,