linux-kernel - Re: [PATCH 09/10] sched: task_sched_runtime introduce micro optimization

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Wed, 1 May 2013 04:50:12 -0700
From:	Paul Turner <pjt@...gle.com>
To:	Peter Zijlstra <peterz@...radead.org>
Cc:	KOSAKI Motohiro <kosaki.motohiro@...il.com>,
	LKML <linux-kernel@...r.kernel.org>,
	Olivier Langlois <olivier@...llion01.com>,
	Martin Schwidefsky <schwidefsky@...ibm.com>,
	Steven Rostedt <rostedt@...dmis.org>,
	David Miller <davem@...emloft.net>,
	Thomas Gleixner <tglx@...utronix.de>,
	Frederic Weisbecker <fweisbec@...il.com>,
	Ingo Molnar <mingo@...nel.org>,
	KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
Subject: Re: [PATCH 09/10] sched: task_sched_runtime introduce micro optimization

On Wed, May 1, 2013 at 4:00 AM, Peter Zijlstra <peterz@...radead.org> wrote:
> On Mon, Apr 29, 2013 at 11:17:17PM -0400, kosaki.motohiro@...il.com wrote:
>> From: KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
>>
>> rq lock in task_sched_runtime() is necessary for two reasons. 1)
>> accessing se.sum_exec_runtime is inatomic on 32bit and 2)
>> do_task_delta_exec() require it.
>>
>> And then, 64bit can avoid holds rq lock when add_delta is false.
>>
>> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
>> ---
>>  kernel/sched/core.c |    6 ++++++
>>  1 files changed, 6 insertions(+), 0 deletions(-)
>>
>> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
>> index b817e6d..24ba1c6 100644
>> --- a/kernel/sched/core.c
>> +++ b/kernel/sched/core.c
>> @@ -2657,6 +2657,12 @@ unsigned long long task_sched_runtime(struct task_struct *p, bool add_delta)
>>       struct rq *rq;
>>       u64 ns = 0;
>>
>> +     /* Micro optimization. */
>
> Instead of the above; how about something like:
>
>   /* 64-bit doesn't need locks to atomically read a 64bit value */
>
>> +#ifdef CONFIG_64BIT
>> +     if (!add_delta)
>> +             return p->se.sum_exec_runtime;
>> +#endif


Stronger:

+#ifdef CONFIG_64BIT
+       if (!p->on_cpu)
+               return p->se.sum_exec_runtime;
+#endif

[ Or !p->on_cpu || !add_delta ].

We can take the racy read versus p->on_cpu since:
  If we race with it leaving cpu: we take lock, we're correct
  If we race with it entering cpu: unaccounted time ---> 0, this is
indistinguishable from the read occurring a few cycles earlier.

>>
>>       rq = task_rq_lock(p, &flags);
>>       ns = p->se.sum_exec_runtime;
>>       if (add_delta)
>> --
>> 1.7.1
>>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@...r.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/