linux-kernel - Re: [PATCH tip/sched/core] introduce task_times() to replace task

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]

Message-ID: <20091123102806.GD25978@dhcp-lab-161.englab.brq.redhat.com>
Date:	Mon, 23 Nov 2009 11:28:07 +0100
From:	Stanislaw Gruszka <sgruszka@...hat.com>
To:	Hidetoshi Seto <seto.hidetoshi@...fujitsu.com>
Cc:	linux-kernel@...r.kernel.org, Ingo Molnar <mingo@...e.hu>,
	Peter Zijlstra <peterz@...radead.org>,
	Spencer Candland <spencer@...ehost.com>,
	Oleg Nesterov <oleg@...hat.com>,
	Balbir Singh <balbir@...ibm.com>,
	Américo Wang <xiyou.wangcong@...il.com>
Subject: Re: [PATCH tip/sched/core] introduce task_times() to replace
	task_[us]time() pair

On Fri, Nov 20, 2009 at 01:44:10PM +0900, Hidetoshi Seto wrote:
> Function task_[us]times() are called consecutively in almost all
> cases.  However task_stime() is implemented to call task_utime()
> from its inside, so such paired calls run task_utime() twice.
> 
> It means we do heavy divisions (div_u64 + do_div) twice to get
> stime and utime which can be obtained at same time by one set
> of divisions.
> 
> This patch introduces task_times(*tsk, *utime, *stime) to get
> stime and utime at once, in better, optimized way.
> 
> Signed-off-by: Hidetoshi Seto <seto.hidetoshi@...fujitsu.com>

[snip]

> @@ -5155,6 +5155,14 @@ cputime_t task_stime(struct task_struct *p)
>  {
>  	return p->stime;
>  }
> +
> +void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
> +{
> +	if (ut)
> +		*ut = task_utime(p);
> +	if (st)
> +		*st = task_stime(p);
> +}
>  #else

I think task_{u,s}time are not needed anymore. Can we just fully get
rid of them and only use task_times() ?

>  #ifndef nsecs_to_cputime
> @@ -5162,41 +5170,48 @@ cputime_t task_stime(struct task_struct *p)
>  	msecs_to_cputime(div_u64((__nsecs), NSEC_PER_MSEC))
>  #endif

Could we furhter optimize this? Perhaps we can use below code
(taken from timespec_to_jiffies()):

	cputime = (nsec * NSEC_CONVERSION) >>
                 (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;


Stanislaw
--
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/