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 <[email protected]>
Cc: <[email protected]>
---
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
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 <[email protected]>
Cc: <[email protected]>
---
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
On Fri, Jul 26, 2019 at 3:48 PM Henry Burns <[email protected]> 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 <[email protected]>
Reviewed-by: Shakeel Butt <[email protected]>
> Cc: <[email protected]>
> ---
> 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
>
On Fri, Jul 26, 2019 at 3:48 PM Henry Burns <[email protected]> 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 <[email protected]>
Reviewed-by: Jonathan Adams <[email protected]>
> Cc: <[email protected]>
> ---
> 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
>
On Fri, Jul 26, 2019 at 3:48 PM Henry Burns <[email protected]> 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 <[email protected]>
Reviewed-by: Jonathan Adams <[email protected]>
> Cc: <[email protected]>
> ---
> 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
>
On Fri, Jul 26, 2019 at 3:48 PM Henry Burns <[email protected]> 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 <[email protected]>
Reviewed-by: Shakeel Butt <[email protected]>
> Cc: <[email protected]>
> ---
> 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
>
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 <[email protected]>
> Reviewed-by: Shakeel Butt <[email protected]>
> Reviewed-by: Jonathan Adams <[email protected]>
>
> > Cc: <[email protected]>
> > ---
> > 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
> >
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 <[email protected]>
> Reviewed-by: Shakeel Butt <[email protected]>
> Reviewed-by: Jonathan Adams <[email protected]>
>
> > Cc: <[email protected]>
> > ---
> > 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
> >