From fb3bbcfe344e64a46574a638b051ffd78762c12d Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 6 Feb 2025 16:23:14 +0100 Subject: [PATCH 1/2] exit: change the release_task() paths to call flush_sigqueue() lockless A task can block a signal, accumulate up to RLIMIT_SIGPENDING sigqueues, and exit. In this case __exit_signal()->flush_sigqueue() called with irqs disabled can trigger a hard lockup, see https://lore.kernel.org/all/20190322114917.GC28876@redhat.com/ Fortunately, after the recent posixtimer changes sys_timer_delete() paths no longer try to clear SIGQUEUE_PREALLOC and/or free tmr->sigq, and after the exiting task passes __exit_signal() lock_task_sighand() can't succeed and pid_task(tmr->it_pid) will return NULL. This means that after __exit_signal(tsk) nobody can play with tsk->pending or (if group_dead) with tsk->signal->shared_pending, so release_task() can safely call flush_sigqueue() after write_unlock_irq(&tasklist_lock). TODO: - we can probably shift posix_cpu_timers_exit() as well - do_sigaction() can hit the similar problem Signed-off-by: Oleg Nesterov Link: https://lore.kernel.org/r/20250206152314.GA14620@redhat.com Reviewed-by: Frederic Weisbecker Signed-off-by: Christian Brauner --- kernel/exit.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/kernel/exit.c b/kernel/exit.c index 3485e5fc499e..2d7444da743d 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -200,20 +200,13 @@ static void __exit_signal(struct task_struct *tsk) __unhash_process(tsk, group_dead); write_sequnlock(&sig->stats_lock); - /* - * Do this under ->siglock, we can race with another thread - * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. - */ - flush_sigqueue(&tsk->pending); tsk->sighand = NULL; spin_unlock(&sighand->siglock); __cleanup_sighand(sighand); clear_tsk_thread_flag(tsk, TIF_SIGPENDING); - if (group_dead) { - flush_sigqueue(&sig->shared_pending); + if (group_dead) tty_kref_put(tty); - } } static void delayed_put_task_struct(struct rcu_head *rhp) @@ -279,6 +272,16 @@ repeat: proc_flush_pid(thread_pid); put_pid(thread_pid); release_thread(p); + /* + * This task was already removed from the process/thread/pid lists + * and lock_task_sighand(p) can't succeed. Nobody else can touch + * ->pending or, if group dead, signal->shared_pending. We can call + * flush_sigqueue() lockless. + */ + flush_sigqueue(&p->pending); + if (thread_group_leader(p)) + flush_sigqueue(&p->signal->shared_pending); + put_task_struct_rcu_user(p); p = leader; From 43966114b49988ebca6b7d17eb68bad7740e9fb2 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 6 Feb 2025 16:23:34 +0100 Subject: [PATCH 2/2] exit: kill the pointless __exit_signal()->clear_tsk_thread_flag(TIF_SIGPENDING) It predates the git history and most probably it was never needed. It doesn't really hurt, but it looks confusing because its purpose is not clear at all. release_task(p) is called when this task has already passed exit_notify() so signal_pending(p) == T shouldn't make any difference. And even _if_ there were a subtle reason to clear TIF_SIGPENDING after exit_notify(), this clear_tsk_thread_flag() can't help anyway. If the exiting task is a group leader or if it is ptraced, release_task() will be likely called when this task has already done its last schedule() from do_task_dead(). Signed-off-by: Oleg Nesterov Link: https://lore.kernel.org/r/20250206152334.GB14620@redhat.com Acked-by: Frederic Weisbecker Signed-off-by: Christian Brauner --- kernel/exit.c | 1 - 1 file changed, 1 deletion(-) diff --git a/kernel/exit.c b/kernel/exit.c index 2d7444da743d..0acb94b17caa 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -204,7 +204,6 @@ static void __exit_signal(struct task_struct *tsk) spin_unlock(&sighand->siglock); __cleanup_sighand(sighand); - clear_tsk_thread_flag(tsk, TIF_SIGPENDING); if (group_dead) tty_kref_put(tty); }