linux-kernel - Re: [thisops uV2 06/10] vmstat: Use this_cpu_inc

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: <AANLkTi=6wVzEQwuMZTgL8WWhFMnNoYgsYv9hZk1jB4jw@mail.gmail.com>
Date:	Sat, 27 Nov 2010 10:09:35 +0200
From:	Pekka Enberg <penberg@...nel.org>
To:	Christoph Lameter <cl@...ux.com>
Cc:	akpm@...ux-foundation.org, Pekka Enberg <penberg@...helsinki.fi>,
	linux-kernel@...r.kernel.org,
	Eric Dumazet <eric.dumazet@...il.com>,
	Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
	Tejun Heo <tj@...nel.org>
Subject: Re: [thisops uV2 06/10] vmstat: Use this_cpu_inc_return for vm statistics

On Fri, Nov 26, 2010 at 11:09 PM, Christoph Lameter <cl@...ux.com> wrote:
> this_cpu_inc_return() saves us a memory access there. Code
> size does not change.
>
> V1->V2:
>        - Fixed the location of the __per_cpu pointer attributes
>        - Sparse checked
>
> Signed-off-by: Christoph Lameter <cl@...ux.com>
>
> ---
>  mm/vmstat.c |   20 ++++++++------------
>  1 file changed, 8 insertions(+), 12 deletions(-)
>
> Index: linux-2.6/mm/vmstat.c
> ===================================================================
> --- linux-2.6.orig/mm/vmstat.c  2010-11-26 10:35:45.000000000 -0600
> +++ linux-2.6/mm/vmstat.c       2010-11-26 10:45:49.000000000 -0600
> @@ -167,8 +167,8 @@ static void refresh_zone_stat_thresholds
>  void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
>                                int delta)
>  {
> -       struct per_cpu_pageset * __percpu pcp = zone->pageset;
> -       s8 * __percpu p = pcp->vm_stat_diff + item;
> +       struct per_cpu_pageset __percpu *pcp = zone->pageset;
> +       s8 __percpu *p = pcp->vm_stat_diff + item;
>        long x;
>        long t;
>

Shouldn't this hunk be in the other vmstat patch?

> @@ -223,13 +223,11 @@ EXPORT_SYMBOL(mod_zone_page_state);
>  */
>  void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
>  {
> -       struct per_cpu_pageset * __percpu pcp = zone->pageset;
> -       s8 * __percpu p = pcp->vm_stat_diff + item;
> +       struct per_cpu_pageset __percpu *pcp = zone->pageset;
> +       s8 __percpu *p = pcp->vm_stat_diff + item;
>        s8 v, t;
>
> -       __this_cpu_inc(*p);
> -
> -       v = __this_cpu_read(*p);
> +       v = __this_cpu_inc_return(*p);
>        t = __this_cpu_read(pcp->stat_threshold);
>        if (unlikely(v > t)) {
>                s8 overstep = t >> 1;
> @@ -247,13 +245,11 @@ EXPORT_SYMBOL(__inc_zone_page_state);
>
>  void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
>  {
> -       struct per_cpu_pageset * __percpu pcp = zone->pageset;
> -       s8 * __percpu p = pcp->vm_stat_diff + item;
> +       struct per_cpu_pageset __percpu *pcp = zone->pageset;
> +       s8 __percpu *p = pcp->vm_stat_diff + item;
>        s8 v, t;
>
> -       __this_cpu_dec(*p);
> -
> -       v = __this_cpu_read(*p);
> +       v = __this_cpu_dec_return(*p);
>        t = __this_cpu_read(pcp->stat_threshold);
>        if (unlikely(v < - t)) {
>                s8 overstep = t >> 1;

For the rest of this patch:

Reviewed-by: Pekka Enberg <penberg@...nel.org>
--
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/