From 30f1e3dd8c72abda343bcf415f7d8894a02b4290 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 15 Jun 2006 20:11:43 +0400 Subject: [PATCH] run_posix_cpu_timers: remove a bogus BUG_ON() do_exit() clears ->it_##clock##_expires, but nothing prevents another cpu to attach the timer to exiting process after that. arm_timer() tries to protect against this race, but the check is racy. After exit_notify() does 'write_unlock_irq(&tasklist_lock)' and before do_exit() calls 'schedule() local timer interrupt can find tsk->exit_state != 0. If that state was EXIT_DEAD (or another cpu does sys_wait4) interrupted task has ->signal == NULL. At this moment exiting task has no pending cpu timers, they were cleanuped in __exit_signal()->posix_cpu_timers_exit{,_group}(), so we can just return from irq. John Stultz recently confirmed this bug, see http://marc.theaimsgroup.com/?l=linux-kernel&m=115015841413687 Signed-off-by: Oleg Nesterov Signed-off-by: Linus Torvalds --- kernel/exit.c | 8 -------- kernel/posix-cpu-timers.c | 36 ++++++++++++++++++------------------ 2 files changed, 18 insertions(+), 26 deletions(-) diff --git a/kernel/exit.c b/kernel/exit.c index e95b9328221..e06d0c10a24 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -881,14 +881,6 @@ fastcall NORET_TYPE void do_exit(long code) tsk->flags |= PF_EXITING; - /* - * Make sure we don't try to process any timer firings - * while we are already exiting. - */ - tsk->it_virt_expires = cputime_zero; - tsk->it_prof_expires = cputime_zero; - tsk->it_sched_expires = 0; - if (unlikely(in_atomic())) printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n", current->comm, current->pid, diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 9d9169aa2e2..4882bf1e094 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -1288,30 +1288,30 @@ void run_posix_cpu_timers(struct task_struct *tsk) #undef UNEXPIRED - BUG_ON(tsk->exit_state); - /* * Double-check with locks held. */ read_lock(&tasklist_lock); - spin_lock(&tsk->sighand->siglock); + if (likely(tsk->signal != NULL)) { + spin_lock(&tsk->sighand->siglock); - /* - * Here we take off tsk->cpu_timers[N] and tsk->signal->cpu_timers[N] - * all the timers that are firing, and put them on the firing list. - */ - check_thread_timers(tsk, &firing); - check_process_timers(tsk, &firing); + /* + * Here we take off tsk->cpu_timers[N] and tsk->signal->cpu_timers[N] + * all the timers that are firing, and put them on the firing list. + */ + check_thread_timers(tsk, &firing); + check_process_timers(tsk, &firing); - /* - * We must release these locks before taking any timer's lock. - * There is a potential race with timer deletion here, as the - * siglock now protects our private firing list. We have set - * the firing flag in each timer, so that a deletion attempt - * that gets the timer lock before we do will give it up and - * spin until we've taken care of that timer below. - */ - spin_unlock(&tsk->sighand->siglock); + /* + * We must release these locks before taking any timer's lock. + * There is a potential race with timer deletion here, as the + * siglock now protects our private firing list. We have set + * the firing flag in each timer, so that a deletion attempt + * that gets the timer lock before we do will give it up and + * spin until we've taken care of that timer below. + */ + spin_unlock(&tsk->sighand->siglock); + } read_unlock(&tasklist_lock); /* -- cgit v1.2.3