linux-kernel - Re: [PATCH] x86: introduce and use percpu

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-next>] [day] [month] [year] [list]

Message-Id: <4BCFFA1B020000780005CBAE@vpn.id2.novell.com>
Date:	Thu, 22 Apr 2010 07:26:19 +0100
From:	"Jan Beulich" <jbeulich@...ell.com>
To:	<hpa@...or.com>
Cc:	<mingo@...e.hu>, <tglx@...utronix.de>,
	<linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] x86: introduce and use percpu_inc()

>>> "H. Peter Anvin"  04/21/10 7:57 PM >>>
>On 04/21/2010 07:21 AM, Jan Beulich wrote:
>> ... generating slightly smaller code.
>> 
>> Signed-off-by: Jan Beulich 
>
>How much smaller?

The percpu_add(..., 1) -> percpu_inc() conversion is just a single
byte reduction (the immediate operand of the add); the other one
(where percpu_...() wasn't even used) is certainly a bigger win
(most of which obviously could also be achieved using percpu_add()).

>Keep in mind that although INC is smaller than ADD,
>the former has flag dependencies that the latter doesn't...

Wasn't that a problem just on Pentium4-s, which when I submitted
another related patch a couple of months back I was told would
not be a primary target anymore?

Jan

--
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/