diff options
author | Tetsuo Handa | 2022-06-01 16:32:47 +0900 |
---|---|---|
committer | Tejun Heo | 2022-06-07 07:07:14 -1000 |
commit | c4f135d643823a869becfa87539f7820ef9d5bfa (patch) | |
tree | 68fe8edba4e07ba6da1dd2a293104dcfbbfd53e7 /include/linux | |
parent | e71e60cd74df9386c3f684c54888f2367050b831 (diff) |
workqueue: Wrap flush_workqueue() using a macro
Since flush operation synchronously waits for completion, flushing
system-wide WQs (e.g. system_wq) might introduce possibility of deadlock
due to unexpected locking dependency. Tejun Heo commented at [1] that it
makes no sense at all to call flush_workqueue() on the shared WQs as the
caller has no idea what it's gonna end up waiting for.
Although there is flush_scheduled_work() which flushes system_wq WQ with
"Think twice before calling this function! It's very easy to get into
trouble if you don't take great care." warning message, syzbot found a
circular locking dependency caused by flushing system_wq WQ [2].
Therefore, let's change the direction to that developers had better use
their local WQs if flush_scheduled_work()/flush_workqueue(system_*_wq) is
inevitable.
Steps for converting system-wide WQs into local WQs are explained at [3],
and a conversion to stop flushing system-wide WQs is in progress. Now we
want some mechanism for preventing developers who are not aware of this
conversion from again start flushing system-wide WQs.
Since I found that WARN_ON() is complete but awkward approach for teaching
developers about this problem, let's use __compiletime_warning() for
incomplete but handy approach. For completeness, we will also insert
WARN_ON() into __flush_workqueue() after all in-tree users stopped calling
flush_scheduled_work().
Link: https://lore.kernel.org/all/YgnQGZWT%2Fn3VAITX@slm.duckdns.org/ [1]
Link: https://syzkaller.appspot.com/bug?extid=bde0f89deacca7c765b8 [2]
Link: https://lkml.kernel.org/r/49925af7-78a8-a3dd-bce6-cfc02e1a9236@I-love.SAKURA.ne.jp [3]
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Tejun Heo <tj@kernel.org>
Diffstat (limited to 'include/linux')
-rw-r--r-- | include/linux/workqueue.h | 64 |
1 files changed, 56 insertions, 8 deletions
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 7fee9b6cfede..e1f1c8b1121b 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -445,7 +445,7 @@ extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay); extern bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork); -extern void flush_workqueue(struct workqueue_struct *wq); +extern void __flush_workqueue(struct workqueue_struct *wq); extern void drain_workqueue(struct workqueue_struct *wq); extern int schedule_on_each_cpu(work_func_t func); @@ -563,15 +563,23 @@ static inline bool schedule_work(struct work_struct *work) return queue_work(system_wq, work); } +/* + * Detect attempt to flush system-wide workqueues at compile time when possible. + * + * See https://lkml.kernel.org/r/49925af7-78a8-a3dd-bce6-cfc02e1a9236@I-love.SAKURA.ne.jp + * for reasons and steps for converting system-wide workqueues into local workqueues. + */ +extern void __warn_flushing_systemwide_wq(void) + __compiletime_warning("Please avoid flushing system-wide workqueues."); + /** * flush_scheduled_work - ensure that any scheduled work has run to completion. * * Forces execution of the kernel-global workqueue and blocks until its * completion. * - * Think twice before calling this function! It's very easy to get into - * trouble if you don't take great care. Either of the following situations - * will lead to deadlock: + * It's very easy to get into trouble if you don't take great care. + * Either of the following situations will lead to deadlock: * * One of the work items currently on the workqueue needs to acquire * a lock held by your code or its caller. @@ -586,11 +594,51 @@ static inline bool schedule_work(struct work_struct *work) * need to know that a particular work item isn't queued and isn't running. * In such cases you should use cancel_delayed_work_sync() or * cancel_work_sync() instead. + * + * Please stop calling this function! A conversion to stop flushing system-wide + * workqueues is in progress. This function will be removed after all in-tree + * users stopped calling this function. */ -static inline void flush_scheduled_work(void) -{ - flush_workqueue(system_wq); -} +/* + * The background of commit 771c035372a036f8 ("deprecate the + * '__deprecated' attribute warnings entirely and for good") is that, + * since Linus builds all modules between every single pull he does, + * the standard kernel build needs to be _clean_ in order to be able to + * notice when new problems happen. Therefore, don't emit warning while + * there are in-tree users. + */ +#define flush_scheduled_work() \ +({ \ + if (0) \ + __warn_flushing_systemwide_wq(); \ + __flush_workqueue(system_wq); \ +}) + +/* + * Although there is no longer in-tree caller, for now just emit warning + * in order to give out-of-tree callers time to update. + */ +#define flush_workqueue(wq) \ +({ \ + struct workqueue_struct *_wq = (wq); \ + \ + if ((__builtin_constant_p(_wq == system_wq) && \ + _wq == system_wq) || \ + (__builtin_constant_p(_wq == system_highpri_wq) && \ + _wq == system_highpri_wq) || \ + (__builtin_constant_p(_wq == system_long_wq) && \ + _wq == system_long_wq) || \ + (__builtin_constant_p(_wq == system_unbound_wq) && \ + _wq == system_unbound_wq) || \ + (__builtin_constant_p(_wq == system_freezable_wq) && \ + _wq == system_freezable_wq) || \ + (__builtin_constant_p(_wq == system_power_efficient_wq) && \ + _wq == system_power_efficient_wq) || \ + (__builtin_constant_p(_wq == system_freezable_power_efficient_wq) && \ + _wq == system_freezable_power_efficient_wq)) \ + __warn_flushing_systemwide_wq(); \ + __flush_workqueue(_wq); \ +}) /** * schedule_delayed_work_on - queue work in global workqueue on CPU after delay |