[PATCH] bdi: Fix another oops in wb_workfn()

[Jan Kara]

syzbot is reporting NULL pointer dereference at wb_workfn() [1] due to
wb->bdi->dev being NULL. And Dmitry confirmed that wb->state was
WB_shutting_down after wb->bdi->dev became NULL. This indicates that
unregister_bdi() failed to call wb_shutdown() on one of wb objects.

The problem is in cgwb_bdi_unregister() which does cgwb_kill() and thus
drops bdi's reference to wb structures before going through the list of
wbs again and calling wb_shutdown() on each of them. This way the loop
iterating through all wbs can easily miss a wb if that wb has already
passed through cgwb_remove_from_bdi_list() called from wb_shutdown()
from cgwb_release_workfn() and as a result fully shutdown bdi although
wb_workfn() for this wb structure is still running. In fact there are
also other ways cgwb_bdi_unregister() can race with
cgwb_release_workfn() leading e.g. to use-after-free issues:

CPU1                            CPU2
                                cgwb_bdi_unregister()
                                  cgwb_kill(*slot);

cgwb_release()
  queue_work(cgwb_release_wq, &wb->release_work);
cgwb_release_workfn()
                                  wb = list_first_entry(&bdi->wb_list, ...)
                                  spin_unlock_irq(&cgwb_lock);
  wb_shutdown(wb);
  ...
  kfree_rcu(wb, rcu);
                                  wb_shutdown(wb); -> oops use-after-free

We solve these issues by synchronizing writeback structure shutdown from
cgwb_bdi_unregister() with cgwb_release_workfn() using a new mutex.

Signed-off-by: Jan Kara <jack@xxxxxxx>
---
 include/linux/backing-dev-defs.h | 1 +
 mm/backing-dev.c                 | 7 +++++++
 2 files changed, 8 insertions(+)

diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index 0bd432a4d7bd..661e3121e580 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -189,6 +189,7 @@ struct backing_dev_info {
 #ifdef CONFIG_CGROUP_WRITEBACK
 	struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */
 	struct rb_root cgwb_congested_tree; /* their congested states */
+	struct mutex cgwb_release_mutex;  /* protect shutdown of wb structs */
 #else
 	struct bdi_writeback_congested *wb_congested;
 #endif
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 347cc834c04a..078cb4e0fb62 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -508,10 +508,12 @@ static void cgwb_release_workfn(struct work_struct *work)
 	struct bdi_writeback *wb = container_of(work, struct bdi_writeback,
 						release_work);
 
+	mutex_lock(&wb->bdi->cgwb_release_mutex);
 	wb_shutdown(wb);
 
 	css_put(wb->memcg_css);
 	css_put(wb->blkcg_css);
+	mutex_unlock(&wb->bdi->cgwb_release_mutex);
 
 	fprop_local_destroy_percpu(&wb->memcg_completions);
 	percpu_ref_exit(&wb->refcnt);
@@ -697,6 +699,7 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
 
 	INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC);
 	bdi->cgwb_congested_tree = RB_ROOT;
+	mutex_init(&bdi->cgwb_release_mutex);
 
 	ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL);
 	if (!ret) {
@@ -717,7 +720,10 @@ static void cgwb_bdi_unregister(struct backing_dev_info *bdi)
 	spin_lock_irq(&cgwb_lock);
 	radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0)
 		cgwb_kill(*slot);
+	spin_unlock_irq(&cgwb_lock);
 
+	mutex_lock(&bdi->cgwb_release_mutex);
+	spin_lock_irq(&cgwb_lock);
 	while (!list_empty(&bdi->wb_list)) {
 		wb = list_first_entry(&bdi->wb_list, struct bdi_writeback,
 				      bdi_node);
@@ -726,6 +732,7 @@ static void cgwb_bdi_unregister(struct backing_dev_info *bdi)
 		spin_lock_irq(&cgwb_lock);
 	}
 	spin_unlock_irq(&cgwb_lock);
+	mutex_unlock(&bdi->cgwb_release_mutex);
 }
 
 /**
-- 
2.16.4


--scbfshupznc5roe3--