[PATCH] mm/z3fold.c: Fix z3fold_destroy_pool() ordering

[PATCH] mm/z3fold.c: Fix z3fold_destroy_pool() ordering

[Henry Burns]

The constraint from the zpool use of z3fold_destroy_pool() is there are no
outstanding handles to memory (so no active allocations), but it is possible
for there to be outstanding work on either of the two wqs in the pool.

If there is work queued on pool->compact_workqueue when it is called,
z3fold_destroy_pool() will do:

   z3fold_destroy_pool()
     destroy_workqueue(pool->release_wq)
     destroy_workqueue(pool->compact_wq)
       drain_workqueue(pool->compact_wq)
         do_compact_page(zhdr)
           kref_put(&zhdr->refcount)
             __release_z3fold_page(zhdr, ...)
               queue_work_on(pool->release_wq, &pool->work) *BOOM*

So compact_wq needs to be destroyed before release_wq.

Fixes: 5d03a6613957 ("mm/z3fold.c: use kref to prevent page free/compact race")

Signed-off-by: Henry Burns <henryburns@google.com>
Cc: <stable@vger.kernel.org>
---
 mm/z3fold.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/mm/z3fold.c b/mm/z3fold.c
index 1a029a7432ee..43de92f52961 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -818,8 +818,15 @@ static void z3fold_destroy_pool(struct z3fold_pool *pool)
 {
 	kmem_cache_destroy(pool->c_handle);
 	z3fold_unregister_migration(pool);
-	destroy_workqueue(pool->release_wq);
+
+	/*
+	 * We need to destroy pool->compact_wq before pool->release_wq,
+	 * as any pending work on pool->compact_wq will call
+	 * queue_work(pool->release_wq, &pool->work).
+	 */
+
 	destroy_workqueue(pool->compact_wq);
+	destroy_workqueue(pool->release_wq);
 	kfree(pool);
 }
 
-- 
2.22.0.709.g102302147b-goog

[PATCH] mm/z3fold.c: Fix z3fold_destroy_pool() race condition

[Henry Burns]

The constraint from the zpool use of z3fold_destroy_pool() is there are no
outstanding handles to memory (so no active allocations), but it is possible
for there to be outstanding work on either of the two wqs in the pool.

Calling z3fold_deregister_migration() before the workqueues are drained
means that there can be allocated pages referencing a freed inode,
causing any thread in compaction to be able to trip over the bad
pointer in PageMovable().

Fixes: 1f862989b04a ("mm/z3fold.c: support page migration")

Signed-off-by: Henry Burns <henryburns@google.com>
Cc: <stable@vger.kernel.org>
---
 mm/z3fold.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/mm/z3fold.c b/mm/z3fold.c
index 43de92f52961..ed19d98c9dcd 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -817,16 +817,19 @@ static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp,
 static void z3fold_destroy_pool(struct z3fold_pool *pool)
 {
 	kmem_cache_destroy(pool->c_handle);
-	z3fold_unregister_migration(pool);
 
 	/*
 	 * We need to destroy pool->compact_wq before pool->release_wq,
 	 * as any pending work on pool->compact_wq will call
 	 * queue_work(pool->release_wq, &pool->work).
+	 *
+	 * There are still outstanding pages until both workqueues are drained,
+	 * so we cannot unregister migration until then.
 	 */
 
 	destroy_workqueue(pool->compact_wq);
 	destroy_workqueue(pool->release_wq);
+	z3fold_unregister_migration(pool);
 	kfree(pool);
 }
 
-- 
2.22.0.709.g102302147b-goog

Re: [PATCH] mm/z3fold.c: Fix z3fold_destroy_pool() ordering

[Shakeel Butt]

On Fri, Jul 26, 2019 at 3:48 PM Henry Burns <henryburns@google.com> wrote:
>
> The constraint from the zpool use of z3fold_destroy_pool() is there are no
> outstanding handles to memory (so no active allocations), but it is possible
> for there to be outstanding work on either of the two wqs in the pool.
>
> If there is work queued on pool->compact_workqueue when it is called,
> z3fold_destroy_pool() will do:
>
>    z3fold_destroy_pool()
>      destroy_workqueue(pool->release_wq)
>      destroy_workqueue(pool->compact_wq)
>        drain_workqueue(pool->compact_wq)
>          do_compact_page(zhdr)
>            kref_put(&zhdr->refcount)
>              __release_z3fold_page(zhdr, ...)
>                queue_work_on(pool->release_wq, &pool->work) *BOOM*
>
> So compact_wq needs to be destroyed before release_wq.
>
> Fixes: 5d03a6613957 ("mm/z3fold.c: use kref to prevent page free/compact race")
>
> Signed-off-by: Henry Burns <henryburns@google.com>

Reviewed-by: Shakeel Butt <shakeelb@google.com>

> Cc: <stable@vger.kernel.org>
> ---
>  mm/z3fold.c | 9 ++++++++-
>  1 file changed, 8 insertions(+), 1 deletion(-)
>
> diff --git a/mm/z3fold.c b/mm/z3fold.c
> index 1a029a7432ee..43de92f52961 100644
> --- a/mm/z3fold.c
> +++ b/mm/z3fold.c
> @@ -818,8 +818,15 @@ static void z3fold_destroy_pool(struct z3fold_pool *pool)
>  {
>         kmem_cache_destroy(pool->c_handle);
>         z3fold_unregister_migration(pool);
> -       destroy_workqueue(pool->release_wq);
> +
> +       /*
> +        * We need to destroy pool->compact_wq before pool->release_wq,
> +        * as any pending work on pool->compact_wq will call
> +        * queue_work(pool->release_wq, &pool->work).
> +        */
> +
>         destroy_workqueue(pool->compact_wq);
> +       destroy_workqueue(pool->release_wq);
>         kfree(pool);
>  }
>
> --
> 2.22.0.709.g102302147b-goog
>

Re: [PATCH] mm/z3fold.c: Fix z3fold_destroy_pool() race condition

[Shakeel Butt]

On Fri, Jul 26, 2019 at 3:48 PM Henry Burns <henryburns@google.com> wrote:
>
> The constraint from the zpool use of z3fold_destroy_pool() is there are no
> outstanding handles to memory (so no active allocations), but it is possible
> for there to be outstanding work on either of the two wqs in the pool.
>
> Calling z3fold_deregister_migration() before the workqueues are drained
> means that there can be allocated pages referencing a freed inode,
> causing any thread in compaction to be able to trip over the bad
> pointer in PageMovable().
>
> Fixes: 1f862989b04a ("mm/z3fold.c: support page migration")
>
> Signed-off-by: Henry Burns <henryburns@google.com>

Reviewed-by: Shakeel Butt <shakeelb@google.com>

> Cc: <stable@vger.kernel.org>
> ---
>  mm/z3fold.c | 5 ++++-
>  1 file changed, 4 insertions(+), 1 deletion(-)
>
> diff --git a/mm/z3fold.c b/mm/z3fold.c
> index 43de92f52961..ed19d98c9dcd 100644
> --- a/mm/z3fold.c
> +++ b/mm/z3fold.c
> @@ -817,16 +817,19 @@ static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp,
>  static void z3fold_destroy_pool(struct z3fold_pool *pool)
>  {
>         kmem_cache_destroy(pool->c_handle);
> -       z3fold_unregister_migration(pool);
>
>         /*
>          * We need to destroy pool->compact_wq before pool->release_wq,
>          * as any pending work on pool->compact_wq will call
>          * queue_work(pool->release_wq, &pool->work).
> +        *
> +        * There are still outstanding pages until both workqueues are drained,
> +        * so we cannot unregister migration until then.
>          */
>
>         destroy_workqueue(pool->compact_wq);
>         destroy_workqueue(pool->release_wq);
> +       z3fold_unregister_migration(pool);
>         kfree(pool);
>  }
>
> --
> 2.22.0.709.g102302147b-goog
>

Re: [PATCH] mm/z3fold.c: Fix z3fold_destroy_pool() ordering

[Jonathan Adams]

On Fri, Jul 26, 2019 at 3:48 PM Henry Burns <henryburns@google.com> wrote:
>
> The constraint from the zpool use of z3fold_destroy_pool() is there are no
> outstanding handles to memory (so no active allocations), but it is possible
> for there to be outstanding work on either of the two wqs in the pool.
>
> If there is work queued on pool->compact_workqueue when it is called,
> z3fold_destroy_pool() will do:
>
>    z3fold_destroy_pool()
>      destroy_workqueue(pool->release_wq)
>      destroy_workqueue(pool->compact_wq)
>        drain_workqueue(pool->compact_wq)
>          do_compact_page(zhdr)
>            kref_put(&zhdr->refcount)
>              __release_z3fold_page(zhdr, ...)
>                queue_work_on(pool->release_wq, &pool->work) *BOOM*
>
> So compact_wq needs to be destroyed before release_wq.
>
> Fixes: 5d03a6613957 ("mm/z3fold.c: use kref to prevent page free/compact race")
>
> Signed-off-by: Henry Burns <henryburns@google.com>

Reviewed-by: Jonathan Adams <jwadams@google.com>

> Cc: <stable@vger.kernel.org>
> ---
>  mm/z3fold.c | 9 ++++++++-
>  1 file changed, 8 insertions(+), 1 deletion(-)
>
> diff --git a/mm/z3fold.c b/mm/z3fold.c
> index 1a029a7432ee..43de92f52961 100644
> --- a/mm/z3fold.c
> +++ b/mm/z3fold.c
> @@ -818,8 +818,15 @@ static void z3fold_destroy_pool(struct z3fold_pool *pool)
>  {
>         kmem_cache_destroy(pool->c_handle);
>         z3fold_unregister_migration(pool);
> -       destroy_workqueue(pool->release_wq);
> +
> +       /*
> +        * We need to destroy pool->compact_wq before pool->release_wq,
> +        * as any pending work on pool->compact_wq will call
> +        * queue_work(pool->release_wq, &pool->work).
> +        */
> +
>         destroy_workqueue(pool->compact_wq);
> +       destroy_workqueue(pool->release_wq);
>         kfree(pool);
>  }
>
> --
> 2.22.0.709.g102302147b-goog
>

Re: [PATCH] mm/z3fold.c: Fix z3fold_destroy_pool() race condition

[Jonathan Adams]

On Fri, Jul 26, 2019 at 3:48 PM Henry Burns <henryburns@google.com> wrote:
>
> The constraint from the zpool use of z3fold_destroy_pool() is there are no
> outstanding handles to memory (so no active allocations), but it is possible
> for there to be outstanding work on either of the two wqs in the pool.
>
> Calling z3fold_deregister_migration() before the workqueues are drained
> means that there can be allocated pages referencing a freed inode,
> causing any thread in compaction to be able to trip over the bad
> pointer in PageMovable().
>
> Fixes: 1f862989b04a ("mm/z3fold.c: support page migration")
>
> Signed-off-by: Henry Burns <henryburns@google.com>

Reviewed-by: Jonathan Adams <jwadams@google.com>

> Cc: <stable@vger.kernel.org>
> ---
>  mm/z3fold.c | 5 ++++-
>  1 file changed, 4 insertions(+), 1 deletion(-)
>
> diff --git a/mm/z3fold.c b/mm/z3fold.c
> index 43de92f52961..ed19d98c9dcd 100644
> --- a/mm/z3fold.c
> +++ b/mm/z3fold.c
> @@ -817,16 +817,19 @@ static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp,
>  static void z3fold_destroy_pool(struct z3fold_pool *pool)
>  {
>         kmem_cache_destroy(pool->c_handle);
> -       z3fold_unregister_migration(pool);
>
>         /*
>          * We need to destroy pool->compact_wq before pool->release_wq,
>          * as any pending work on pool->compact_wq will call
>          * queue_work(pool->release_wq, &pool->work).
> +        *
> +        * There are still outstanding pages until both workqueues are drained,
> +        * so we cannot unregister migration until then.
>          */
>
>         destroy_workqueue(pool->compact_wq);
>         destroy_workqueue(pool->release_wq);
> +       z3fold_unregister_migration(pool);
>         kfree(pool);
>  }
>
> --
> 2.22.0.709.g102302147b-goog
>

Re: [PATCH] mm/z3fold.c: Fix z3fold_destroy_pool() ordering

[Henry Burns]

The constraint from the zpool use of z3fold_destroy_pool() is there
are no outstanding handles to memory (so no active allocations), but
it is possible for there to be outstanding work on either of the two
wqs in the pool.


If there is work queued on pool->compact_workqueue when it is called,
z3fold_destroy_pool() will do:

   z3fold_destroy_pool()
     destroy_workqueue(pool->release_wq)
     destroy_workqueue(pool->compact_wq)
       drain_workqueue(pool->compact_wq)
         do_compact_page(zhdr)
           kref_put(&zhdr->refcount)
             __release_z3fold_page(zhdr, ...)
               queue_work_on(pool->release_wq, &pool->work) *BOOM*

So compact_wq needs to be destroyed before release_wq.

Fixes: 5d03a6613957 ("mm/z3fold.c: use kref to prevent page free/compact race")

Signed-off-by: Henry Burns <henryburns@google.com>


> Reviewed-by: Shakeel Butt <shakeelb@google.com>
> Reviewed-by: Jonathan Adams <jwadams@google.com>
>
> > Cc: <stable@vger.kernel.org>
> > ---
> >  mm/z3fold.c | 9 ++++++++-
> >  1 file changed, 8 insertions(+), 1 deletion(-)
> >
> > diff --git a/mm/z3fold.c b/mm/z3fold.c
> > index 1a029a7432ee..43de92f52961 100644
> > --- a/mm/z3fold.c
> > +++ b/mm/z3fold.c
> > @@ -818,8 +818,15 @@ static void z3fold_destroy_pool(struct z3fold_pool *pool)
> >  {
> >         kmem_cache_destroy(pool->c_handle);
> >         z3fold_unregister_migration(pool);
> > -       destroy_workqueue(pool->release_wq);
> > +
> > +       /*
> > +        * We need to destroy pool->compact_wq before pool->release_wq,
> > +        * as any pending work on pool->compact_wq will call
> > +        * queue_work(pool->release_wq, &pool->work).
> > +        */
> > +
> >         destroy_workqueue(pool->compact_wq);
> > +       destroy_workqueue(pool->release_wq);
> >         kfree(pool);
> >  }
> >
> > --
> > 2.22.0.709.g102302147b-goog
> >

Re: [PATCH] mm/z3fold.c: Fix z3fold_destroy_pool() race condition

[Henry Burns]

The constraint from the zpool use of z3fold_destroy_pool() is there
are no outstanding handles to memory (so no active allocations), but
it is possible for there to be outstanding work on either of the two
wqs in the pool.

Calling z3fold_deregister_migration() before the workqueues are drained
means that there can be allocated pages referencing a freed inode,
causing any thread in compaction to be able to trip over the bad
pointer in PageMovable().

Fixes: 1f862989b04a ("mm/z3fold.c: support page migration")

Signed-off-by: Henry Burns <henryburns@google.com>

> Reviewed-by: Shakeel Butt <shakeelb@google.com>
> Reviewed-by: Jonathan Adams <jwadams@google.com>
>
> > Cc: <stable@vger.kernel.org>
> > ---
> >  mm/z3fold.c | 5 ++++-
> >  1 file changed, 4 insertions(+), 1 deletion(-)
> >
> > diff --git a/mm/z3fold.c b/mm/z3fold.c
> > index 43de92f52961..ed19d98c9dcd 100644
> > --- a/mm/z3fold.c
> > +++ b/mm/z3fold.c
> > @@ -817,16 +817,19 @@ static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp,
> >  static void z3fold_destroy_pool(struct z3fold_pool *pool)
> >  {
> >         kmem_cache_destroy(pool->c_handle);
> > -       z3fold_unregister_migration(pool);
> >
> >         /*
> >          * We need to destroy pool->compact_wq before pool->release_wq,
> >          * as any pending work on pool->compact_wq will call
> >          * queue_work(pool->release_wq, &pool->work).
> > +        *
> > +        * There are still outstanding pages until both workqueues are drained,
> > +        * so we cannot unregister migration until then.
> >          */
> >
> >         destroy_workqueue(pool->compact_wq);
> >         destroy_workqueue(pool->release_wq);
> > +       z3fold_unregister_migration(pool);
> >         kfree(pool);
> >  }
> >
> > --
> > 2.22.0.709.g102302147b-goog
> >