From c0feea594e058223973db94c1c32a830c9807c86 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Fri, 29 Jul 2022 13:30:23 +0900 Subject: workqueue: don't skip lockdep work dependency in cancel_work_sync() Like Hillf Danton mentioned syzbot should have been able to catch cancel_work_sync() in work context by checking lockdep_map in __flush_work() for both flush and cancel. in [1], being unable to report an obvious deadlock scenario shown below is broken. From locking dependency perspective, sync version of cancel request should behave as if flush request, for it waits for completion of work if that work has already started execution. ---------- #include #include static DEFINE_MUTEX(mutex); static void work_fn(struct work_struct *work) { schedule_timeout_uninterruptible(HZ / 5); mutex_lock(&mutex); mutex_unlock(&mutex); } static DECLARE_WORK(work, work_fn); static int __init test_init(void) { schedule_work(&work); schedule_timeout_uninterruptible(HZ / 10); mutex_lock(&mutex); cancel_work_sync(&work); mutex_unlock(&mutex); return -EINVAL; } module_init(test_init); MODULE_LICENSE("GPL"); ---------- The check this patch restores was added by commit 0976dfc1d0cd80a4 ("workqueue: Catch more locking problems with flush_work()"). Then, lockdep's crossrelease feature was added by commit b09be676e0ff25bd ("locking/lockdep: Implement the 'crossrelease' feature"). As a result, this check was once removed by commit fd1a5b04dfb899f8 ("workqueue: Remove now redundant lock acquisitions wrt. workqueue flushes"). But lockdep's crossrelease feature was removed by commit e966eaeeb623f099 ("locking/lockdep: Remove the cross-release locking checks"). At this point, this check should have been restored. Then, commit d6e89786bed977f3 ("workqueue: skip lockdep wq dependency in cancel_work_sync()") introduced a boolean flag in order to distinguish flush_work() and cancel_work_sync(), for checking "struct workqueue_struct" dependency when called from cancel_work_sync() was causing false positives. Then, commit 87915adc3f0acdf0 ("workqueue: re-add lockdep dependencies for flushing") tried to restore "struct work_struct" dependency check, but by error checked this boolean flag. Like an example shown above indicates, "struct work_struct" dependency needs to be checked for both flush_work() and cancel_work_sync(). Link: https://lkml.kernel.org/r/20220504044800.4966-1-hdanton@sina.com [1] Reported-by: Hillf Danton Suggested-by: Lai Jiangshan Fixes: 87915adc3f0acdf0 ("workqueue: re-add lockdep dependencies for flushing") Cc: Johannes Berg Signed-off-by: Tetsuo Handa Signed-off-by: Tejun Heo --- kernel/workqueue.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'kernel/workqueue.c') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index aeea9731ef80..39060a5d0905 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3066,10 +3066,8 @@ static bool __flush_work(struct work_struct *work, bool from_cancel) if (WARN_ON(!work->func)) return false; - if (!from_cancel) { - lock_map_acquire(&work->lockdep_map); - lock_map_release(&work->lockdep_map); - } + lock_map_acquire(&work->lockdep_map); + lock_map_release(&work->lockdep_map); if (start_flush_work(work, &barr, from_cancel)) { wait_for_completion(&barr.done); -- cgit v1.2.3 From 4b24356312fbe1bace72f9905d529b14fc34c1c3 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Thu, 8 Sep 2022 14:54:56 -0700 Subject: treewide: Drop WARN_ON_FUNCTION_MISMATCH CONFIG_CFI_CLANG no longer breaks cross-module function address equality, which makes WARN_ON_FUNCTION_MISMATCH unnecessary. Remove the definition and switch back to WARN_ON_ONCE. Signed-off-by: Sami Tolvanen Reviewed-by: Kees Cook Tested-by: Kees Cook Tested-by: Nathan Chancellor Acked-by: Peter Zijlstra (Intel) Tested-by: Peter Zijlstra (Intel) Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220908215504.3686827-15-samitolvanen@google.com --- include/asm-generic/bug.h | 16 ---------------- kernel/kthread.c | 3 +-- kernel/workqueue.c | 2 +- 3 files changed, 2 insertions(+), 19 deletions(-) (limited to 'kernel/workqueue.c') diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index ba1f860af38b..4050b191e1a9 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -220,22 +220,6 @@ extern __printf(1, 2) void __warn_printk(const char *fmt, ...); # define WARN_ON_SMP(x) ({0;}) #endif -/* - * WARN_ON_FUNCTION_MISMATCH() warns if a value doesn't match a - * function address, and can be useful for catching issues with - * callback functions, for example. - * - * With CONFIG_CFI_CLANG, the warning is disabled because the - * compiler replaces function addresses taken in C code with - * local jump table addresses, which breaks cross-module function - * address equality. - */ -#if defined(CONFIG_CFI_CLANG) && defined(CONFIG_MODULES) -# define WARN_ON_FUNCTION_MISMATCH(x, fn) ({ 0; }) -#else -# define WARN_ON_FUNCTION_MISMATCH(x, fn) WARN_ON_ONCE((x) != (fn)) -#endif - #endif /* __ASSEMBLY__ */ #endif diff --git a/kernel/kthread.c b/kernel/kthread.c index 3c677918d8f2..28a6b7ab4a0f 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -1050,8 +1050,7 @@ static void __kthread_queue_delayed_work(struct kthread_worker *worker, struct timer_list *timer = &dwork->timer; struct kthread_work *work = &dwork->work; - WARN_ON_FUNCTION_MISMATCH(timer->function, - kthread_delayed_work_timer_fn); + WARN_ON_ONCE(timer->function != kthread_delayed_work_timer_fn); /* * If @delay is 0, queue @dwork->work immediately. This is for diff --git a/kernel/workqueue.c b/kernel/workqueue.c index aeea9731ef80..16df315d2a3d 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1651,7 +1651,7 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, struct work_struct *work = &dwork->work; WARN_ON_ONCE(!wq); - WARN_ON_FUNCTION_MISMATCH(timer->function, delayed_work_timer_fn); + WARN_ON_ONCE(timer->function != delayed_work_timer_fn); WARN_ON_ONCE(timer_pending(timer)); WARN_ON_ONCE(!list_empty(&work->entry)); -- cgit v1.2.3