From bcd5cff7216f9b2de0a148cc355eac199dc6f1cf Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 17 Oct 2011 11:50:30 +0200 Subject: cputimer: Cure lock inversion There's a lock inversion between the cputimer->lock and rq->lock; notably the two callchains involved are: update_rlimit_cpu() sighand->siglock set_process_cpu_timer() cpu_timer_sample_group() thread_group_cputimer() cputimer->lock thread_group_cputime() task_sched_runtime() ->pi_lock rq->lock scheduler_tick() rq->lock task_tick_fair() update_curr() account_group_exec() cputimer->lock Where the first one is enabling a CLOCK_PROCESS_CPUTIME_ID timer, and the second one is keeping up-to-date. This problem was introduced by e8abccb7193 ("posix-cpu-timers: Cure SMP accounting oddities"). Cure the problem by removing the cputimer->lock and rq->lock nesting, this leaves concurrent enablers doing duplicate work, but the time wasted should be on the same order otherwise wasted spinning on the lock and the greater-than assignment filter should ensure we preserve monotonicity. Reported-by: Dave Jones Reported-by: Simon Kirby Signed-off-by: Peter Zijlstra Cc: stable@kernel.org Cc: Linus Torvalds Cc: Martin Schwidefsky Link: http://lkml.kernel.org/r/1318928713.21167.4.camel@twins Signed-off-by: Thomas Gleixner --- kernel/posix-cpu-timers.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'kernel/posix-cpu-timers.c') diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index c8008dd58ef2..640ded8f5c48 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -274,9 +274,7 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times) struct task_cputime sum; unsigned long flags; - spin_lock_irqsave(&cputimer->lock, flags); if (!cputimer->running) { - cputimer->running = 1; /* * The POSIX timer interface allows for absolute time expiry * values through the TIMER_ABSTIME flag, therefore we have @@ -284,8 +282,11 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times) * it. */ thread_group_cputime(tsk, &sum); + spin_lock_irqsave(&cputimer->lock, flags); + cputimer->running = 1; update_gt_cputime(&cputimer->cputime, &sum); - } + } else + spin_lock_irqsave(&cputimer->lock, flags); *times = cputimer->cputime; spin_unlock_irqrestore(&cputimer->lock, flags); } -- cgit v1.2.3