FUSE has a bug where it fails to clear congestion states if a
connection gets aborted while congested, which can leave
nr_wb_congested[] stuck until reboot causing wait_iff_congested() to
wait spuriously.

While the bdi owner, FUSE, is primarily responsible for clearing
congestion states before destroying bdi_writebacks, bdi layer can
ensure that congestion states are not leaked beyond bdi_writeback
lifecycle.

Signed-off-by: Tejun Heo <t...@kernel.org>
Reported-by: Joshua Miller <joshmil...@fb.com>
Cc: Johannes Weiner <han...@cmpxchg.org>
Cc: Jan Kara <j...@suse.cz>
Cc: sta...@vger.kernel.org
---
 include/linux/backing-dev.h |   14 +++++++++++++-
 mm/backing-dev.c            |    2 +-
 2 files changed, 14 insertions(+), 2 deletions(-)

--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -220,6 +220,18 @@ static inline int bdi_sched_wait(void *w
        return 0;
 }
 
+static inline void __wb_congested_free(struct bdi_writeback_congested 
*congested)
+{
+       /*
+        * Make sure congestion states are cleared before freeing to avoid
+        * nr_wb_congested() corruption which can lead to misbehaving
+        * wait_iff_congested().
+        */
+       clear_wb_congested(congested, BLK_RW_SYNC);
+       clear_wb_congested(congested, BLK_RW_ASYNC);
+       kfree(congested);
+}
+
 #ifdef CONFIG_CGROUP_WRITEBACK
 
 struct bdi_writeback_congested *
@@ -409,7 +421,7 @@ wb_congested_get_create(struct backing_d
 static inline void wb_congested_put(struct bdi_writeback_congested *congested)
 {
        if (atomic_dec_and_test(&congested->refcnt))
-               kfree(congested);
+               __wb_congested_free(congested);
 }
 
 static inline struct bdi_writeback *wb_find_current(struct backing_dev_info 
*bdi)
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -509,7 +509,7 @@ void wb_congested_put(struct bdi_writeba
        }
 
        spin_unlock_irqrestore(&cgwb_lock, flags);
-       kfree(congested);
+       __wb_congested_free(congested);
 }
 
 static void cgwb_release_workfn(struct work_struct *work)

Reply via email to