Pagefault handlers might need to fire MMU notifications while a new
notifier is being registered. Modify mm_take_all_locks to mark all VMAs
as locked and prevent this race with fault handlers that would hold VMA
locks.
Signed-off-by: Suren Baghdasaryan <[email protected]>
---
mm/mmap.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/mm/mmap.c b/mm/mmap.c
index b31cc97c2803..1edfcd384f5e 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -3538,6 +3538,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping)
* hugetlb mapping);
* - all i_mmap_rwsem locks;
* - all anon_vma->rwseml
+ * - all vmas marked locked
*
* We can take all locks within these types randomly because the VM code
* doesn't nest them and we protected from parallel mm_take_all_locks() by
@@ -3579,6 +3580,7 @@ int mm_take_all_locks(struct mm_struct *mm)
if (vma->anon_vma)
list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
vm_lock_anon_vma(mm, avc->anon_vma);
+ vma_mark_locked(vma);
}
return 0;
@@ -3636,6 +3638,7 @@ void mm_drop_all_locks(struct mm_struct *mm)
mmap_assert_write_locked(mm);
BUG_ON(!mutex_is_locked(&mm_all_locks_mutex));
+ vma_mark_unlocked_all(mm);
for (vma = mm->mmap; vma; vma = vma->vm_next) {
if (vma->anon_vma)
list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
--
2.37.2.789.g6183377224-goog
Le 01/09/2022 à 19:35, Suren Baghdasaryan a écrit :
> Pagefault handlers might need to fire MMU notifications while a new
> notifier is being registered. Modify mm_take_all_locks to mark all VMAs
> as locked and prevent this race with fault handlers that would hold VMA
> locks.
>
> Signed-off-by: Suren Baghdasaryan <[email protected]>
> ---
> mm/mmap.c | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/mm/mmap.c b/mm/mmap.c
> index b31cc97c2803..1edfcd384f5e 100644
> --- a/mm/mmap.c
> +++ b/mm/mmap.c
> @@ -3538,6 +3538,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping)
> * hugetlb mapping);
> * - all i_mmap_rwsem locks;
> * - all anon_vma->rwseml
> + * - all vmas marked locked
IIRC, the anon_vma may be locked during the page fault handling, and this
happens after the VMA is read lock. I think the same applies to
i_mmap_rwsem lock.
Thus, the VMA should be marked locked first.
> *
> * We can take all locks within these types randomly because the VM code
> * doesn't nest them and we protected from parallel mm_take_all_locks() by
> @@ -3579,6 +3580,7 @@ int mm_take_all_locks(struct mm_struct *mm)
> if (vma->anon_vma)
> list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
> vm_lock_anon_vma(mm, avc->anon_vma);
> + vma_mark_locked(vma);
> }
>
> return 0;
> @@ -3636,6 +3638,7 @@ void mm_drop_all_locks(struct mm_struct *mm)
> mmap_assert_write_locked(mm);
> BUG_ON(!mutex_is_locked(&mm_all_locks_mutex));
>
> + vma_mark_unlocked_all(mm);
> for (vma = mm->mmap; vma; vma = vma->vm_next) {
> if (vma->anon_vma)
> list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
On Fri, Sep 9, 2022 at 7:20 AM Laurent Dufour <[email protected]> wrote:
>
> Le 01/09/2022 à 19:35, Suren Baghdasaryan a écrit :
> > Pagefault handlers might need to fire MMU notifications while a new
> > notifier is being registered. Modify mm_take_all_locks to mark all VMAs
> > as locked and prevent this race with fault handlers that would hold VMA
> > locks.
> >
> > Signed-off-by: Suren Baghdasaryan <[email protected]>
> > ---
> > mm/mmap.c | 3 +++
> > 1 file changed, 3 insertions(+)
> >
> > diff --git a/mm/mmap.c b/mm/mmap.c
> > index b31cc97c2803..1edfcd384f5e 100644
> > --- a/mm/mmap.c
> > +++ b/mm/mmap.c
> > @@ -3538,6 +3538,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping)
> > * hugetlb mapping);
> > * - all i_mmap_rwsem locks;
> > * - all anon_vma->rwseml
> > + * - all vmas marked locked
>
> IIRC, the anon_vma may be locked during the page fault handling, and this
> happens after the VMA is read lock. I think the same applies to
> i_mmap_rwsem lock.
>
> Thus, the VMA should be marked locked first.
I see. I'll double check and move the locking order. Thanks!
>
> > *
> > * We can take all locks within these types randomly because the VM code
> > * doesn't nest them and we protected from parallel mm_take_all_locks() by
> > @@ -3579,6 +3580,7 @@ int mm_take_all_locks(struct mm_struct *mm)
> > if (vma->anon_vma)
> > list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
> > vm_lock_anon_vma(mm, avc->anon_vma);
> > + vma_mark_locked(vma);
> > }
> >
> > return 0;
> > @@ -3636,6 +3638,7 @@ void mm_drop_all_locks(struct mm_struct *mm)
> > mmap_assert_write_locked(mm);
> > BUG_ON(!mutex_is_locked(&mm_all_locks_mutex));
> >
> > + vma_mark_unlocked_all(mm);
> > for (vma = mm->mmap; vma; vma = vma->vm_next) {
> > if (vma->anon_vma)
> > list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
>