lock_vma_under_rcu() tries to guarantee that __anon_vma_prepare() can't
be called in the VMA-locked page fault path by ensuring that
vma->anon_vma is set.
However, this check happens before the VMA is locked, which means a
concurrent move_vma() can concurrently call unlink_anon_vmas(), which
disassociates the VMA's anon_vma.
This means we can get UAF in the following scenario:
THREAD 1 THREAD 2
======== ========
<page fault>
lock_vma_under_rcu()
rcu_read_lock()
mas_walk()
check vma->anon_vma
mremap() syscall
move_vma()
vma_start_write()
unlink_anon_vmas()
<syscall end>
handle_mm_fault()
__handle_mm_fault()
handle_pte_fault()
do_pte_missing()
do_anonymous_page()
anon_vma_prepare()
__anon_vma_prepare()
find_mergeable_anon_vma()
mas_walk() [looks up VMA X]
munmap() syscall (deletes VMA X)
reusable_anon_vma() [called on freed VMA X]
This is a security bug if you can hit it, although an attacker would
have to win two races at once where the first race window is only a
few instructions wide.
This patch is based on some previous discussion with Linus Torvalds on
the security list.
Cc: stable@xxxxxxxxxxxxxxx
Fixes: 5e31275cc997 ("mm: add per-VMA lock and helper functions to control it")
Signed-off-by: Jann Horn <jannh@xxxxxxxxxx>
---
mm/memory.c | 28 ++++++++++++++++------------
1 file changed, 16 insertions(+), 12 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index 01f39e8144ef..603b2f419948 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5393,27 +5393,28 @@ struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
if (!vma_is_anonymous(vma) && !vma_is_tcp(vma))
goto inval;
- /* find_mergeable_anon_vma uses adjacent vmas which are not locked */
- if (!vma->anon_vma && !vma_is_tcp(vma))
- goto inval;
-
if (!vma_start_read(vma))
goto inval;
+ /*
+ * find_mergeable_anon_vma uses adjacent vmas which are not locked.
+ * This check must happen after vma_start_read(); otherwise, a
+ * concurrent mremap() with MREMAP_DONTUNMAP could dissociate the VMA
+ * from its anon_vma.
+ */
+ if (unlikely(!vma->anon_vma && !vma_is_tcp(vma)))
+ goto inval_end_read;
+
/*
* Due to the possibility of userfault handler dropping mmap_lock, avoid
* it for now and fall back to page fault handling under mmap_lock.
*/
- if (userfaultfd_armed(vma)) {
- vma_end_read(vma);
- goto inval;
- }
+ if (userfaultfd_armed(vma))
+ goto inval_end_read;
/* Check since vm_start/vm_end might change before we lock the VMA */
- if (unlikely(address < vma->vm_start || address >= vma->vm_end)) {
- vma_end_read(vma);
- goto inval;
- }
+ if (unlikely(address < vma->vm_start || address >= vma->vm_end))
+ goto inval_end_read;
/* Check if the VMA got isolated after we found it */
if (vma->detached) {
@@ -5425,6 +5426,9 @@ struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
rcu_read_unlock();
return vma;
+
+inval_end_read:
+ vma_end_read(vma);
inval:
rcu_read_unlock();
count_vm_vma_lock_event(VMA_LOCK_ABORT);
--
2.41.0.487.g6d72f3e995-goog
