From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760215Ab0FRKVd (ORCPT ); Fri, 18 Jun 2010 06:21:33 -0400 Received: from hera.kernel.org ([140.211.167.34]:55191 "EHLO hera.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757833Ab0FRKVb (ORCPT ); Fri, 18 Jun 2010 06:21:31 -0400 Date: Fri, 18 Jun 2010 10:21:03 GMT From: tip-bot for Oleg Nesterov Cc: linux-kernel@vger.kernel.org, hpa@zytor.com, mingo@redhat.com, a.p.zijlstra@chello.nl, oleg@redhat.com, tglx@linutronix.de, mingo@elte.hu Reply-To: mingo@redhat.com, hpa@zytor.com, linux-kernel@vger.kernel.org, a.p.zijlstra@chello.nl, tglx@linutronix.de, oleg@redhat.com, mingo@elte.hu In-Reply-To: <20100611180446.GA13025@redhat.com> References: <20100611180446.GA13025@redhat.com> To: linux-tip-commits@vger.kernel.org Subject: [tip:sched/core] sched: Fix the racy usage of thread_group_cputimer() in fastpath_timer_check() Message-ID: Git-Commit-ID: 8d1f431cbec115a780cd551ab1b4955c125f8d31 X-Mailer: tip-git-log-daemon MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Disposition: inline X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.2.3 (hera.kernel.org [127.0.0.1]); Fri, 18 Jun 2010 10:21:03 +0000 (UTC) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Commit-ID: 8d1f431cbec115a780cd551ab1b4955c125f8d31 Gitweb: http://git.kernel.org/tip/8d1f431cbec115a780cd551ab1b4955c125f8d31 Author: Oleg Nesterov AuthorDate: Fri, 11 Jun 2010 20:04:46 +0200 Committer: Ingo Molnar CommitDate: Fri, 18 Jun 2010 10:46:57 +0200 sched: Fix the racy usage of thread_group_cputimer() in fastpath_timer_check() fastpath_timer_check()->thread_group_cputimer() is racy and unneeded. It is racy because another thread can clear ->running before thread_group_cputimer() takes cputimer->lock. In this case thread_group_cputimer() will set ->running = true again and call thread_group_cputime(). But since we do not hold tasklist or siglock, we can race with fork/exit and copy the wrong results into cputimer->cputime. It is unneeded because if ->running == true we can just use the numbers in cputimer->cputime we already have. Change fastpath_timer_check() to copy cputimer->cputime into the local variable under cputimer->lock. We do not re-check ->running under cputimer->lock, run_posix_cpu_timers() does this check later. Note: we can add more optimizations on top of this change. Signed-off-by: Oleg Nesterov Signed-off-by: Peter Zijlstra LKML-Reference: <20100611180446.GA13025@redhat.com> Signed-off-by: Ingo Molnar --- kernel/posix-cpu-timers.c | 5 ++++- 1 files changed, 4 insertions(+), 1 deletions(-) diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index d5dbef5..f66bdd3 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -1287,7 +1287,10 @@ static inline int fastpath_timer_check(struct task_struct *tsk) if (sig->cputimer.running) { struct task_cputime group_sample; - thread_group_cputimer(tsk, &group_sample); + spin_lock(&sig->cputimer.lock); + group_sample = sig->cputimer.cputime; + spin_unlock(&sig->cputimer.lock); + if (task_cputime_expired(&group_sample, &sig->cputime_expires)) return 1; }