From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755927Ab3A0Ohj (ORCPT ); Sun, 27 Jan 2013 09:37:39 -0500 Received: from terminus.zytor.com ([198.137.202.10]:60246 "EHLO terminus.zytor.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754965Ab3A0Ohg (ORCPT ); Sun, 27 Jan 2013 09:37:36 -0500 Date: Sun, 27 Jan 2013 06:37:00 -0800 From: tip-bot for Frederic Weisbecker Message-ID: Cc: linux-kernel@vger.kernel.org, hpa@zytor.com, mingo@kernel.org, peterz@infradead.org, fweisbec@gmail.com, akpm@linux-foundation.org, tglx@linutronix.de, oleg@redhat.com, sgruszka@redhat.com Reply-To: mingo@kernel.org, hpa@zytor.com, linux-kernel@vger.kernel.org, peterz@infradead.org, fweisbec@gmail.com, akpm@linux-foundation.org, tglx@linutronix.de, oleg@redhat.com, sgruszka@redhat.com In-Reply-To: <1359217182-25184-1-git-send-email-fweisbec@gmail.com> References: <1359217182-25184-1-git-send-email-fweisbec@gmail.com> To: linux-tip-commits@vger.kernel.org Subject: [tip:sched/core] cputime: Avoid multiplication overflow on utime scaling Git-Commit-ID: 62188451f0d63add7ad0cd2a1ae269d600c1663d X-Mailer: tip-git-log-daemon Robot-ID: Robot-Unsubscribe: Contact to get blacklisted from these emails MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset=UTF-8 Content-Disposition: inline X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.2.7 (terminus.zytor.com [127.0.0.1]); Sun, 27 Jan 2013 06:37:06 -0800 (PST) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Commit-ID: 62188451f0d63add7ad0cd2a1ae269d600c1663d Gitweb: http://git.kernel.org/tip/62188451f0d63add7ad0cd2a1ae269d600c1663d Author: Frederic Weisbecker AuthorDate: Sat, 26 Jan 2013 17:19:42 +0100 Committer: Ingo Molnar CommitDate: Sun, 27 Jan 2013 14:04:44 +0100 cputime: Avoid multiplication overflow on utime scaling We scale stime, utime values based on rtime (sum_exec_runtime converted to jiffies). During scaling we multiple rtime * utime, which seems to be fine, since both values are converted to u64, but it's not. Let assume HZ is 1000 - 1ms tick. Process consist of 64 threads, run for 1 day, threads utilize 100% cpu on user space. Machine has 64 cpus. Process rtime = utime will be 64 * 24 * 60 * 60 * 1000 jiffies, which is 0x149970000. Multiplication rtime * utime result is 0x1a855771100000000, which can not be covered in 64 bits. Result of overflow is stall of utime values visible in user space (prev_utime in kernel), even if application still consume lot of CPU time. A solution to solve this is to perform the multiplication on stime instead of utime. It's easy to grow the utime value fast with a CPU bound thread in userspace for example. Now we assume that doing so with stime is much harder. In most cases a task shouldn't ever spend much time in kernel space as it tends to sleep waiting for jobs completion when they take long to achieve. IO is the typical example of that. Hence scaling the cputime by performing the multiplication on stime instead of utime should considerably reduce the chances of an overflow on most workloads. This is largely inspired by a patch from Stanislaw Gruszka: http://lkml.kernel.org/r/20130107113144.GA7544@redhat.com Inspired-by: Stanislaw Gruszka Reported-by: Stanislaw Gruszka Acked-by: Stanislaw Gruszka Signed-off-by: Frederic Weisbecker Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Andrew Morton Link: http://lkml.kernel.org/r/1359217182-25184-1-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- kernel/sched/cputime.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 293b202..825a956 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -509,11 +509,11 @@ EXPORT_SYMBOL_GPL(vtime_account); # define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs) #endif -static cputime_t scale_utime(cputime_t utime, cputime_t rtime, cputime_t total) +static cputime_t scale_stime(cputime_t stime, cputime_t rtime, cputime_t total) { u64 temp = (__force u64) rtime; - temp *= (__force u64) utime; + temp *= (__force u64) stime; if (sizeof(cputime_t) == 4) temp = div_u64(temp, (__force u32) total); @@ -531,10 +531,10 @@ static void cputime_adjust(struct task_cputime *curr, struct cputime *prev, cputime_t *ut, cputime_t *st) { - cputime_t rtime, utime, total; + cputime_t rtime, stime, total; - utime = curr->utime; - total = utime + curr->stime; + stime = curr->stime; + total = stime + curr->utime; /* * Tick based cputime accounting depend on random scheduling @@ -549,17 +549,17 @@ static void cputime_adjust(struct task_cputime *curr, rtime = nsecs_to_cputime(curr->sum_exec_runtime); if (total) - utime = scale_utime(utime, rtime, total); + stime = scale_stime(stime, rtime, total); else - utime = rtime; + stime = rtime; /* * If the tick based count grows faster than the scheduler one, * the result of the scaling may go backward. * Let's enforce monotonicity. */ - prev->utime = max(prev->utime, utime); - prev->stime = max(prev->stime, rtime - prev->utime); + prev->stime = max(prev->stime, stime); + prev->utime = max(prev->utime, rtime - prev->stime); *ut = prev->utime; *st = prev->stime;