linux-kernel - Re: [RFC 00/15] x86_64: Optimize percpu accesses

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: <48750C6C.5090606@goop.org>
Date:	Wed, 09 Jul 2008 12:07:24 -0700
From:	Jeremy Fitzhardinge <jeremy@...p.org>
To:	Christoph Lameter <cl@...ux-foundation.org>
CC:	Mike Travis <travis@....com>, Ingo Molnar <mingo@...e.hu>,
	Andrew Morton <akpm@...ux-foundation.org>,
	"Eric W. Biederman" <ebiederm@...ssion.com>,
	"H. Peter Anvin" <hpa@...or.com>, Jack Steiner <steiner@....com>,
	linux-kernel@...r.kernel.org
Subject: Re: [RFC 00/15] x86_64: Optimize percpu accesses

Christoph Lameter wrote:
> Well yes I agree these could be better if the fields would be moved out of the pda
> structure itself but then it wont be mechanical anymore and require more
> review.

Yes, but they'll have more value.  And if you do it as one variable per 
patch, then it should be easy to bisect should any problems arise.

>  But these are an important step because they allow us to get rid of the
> pda operations that do not exist for 32 bit.
>   

No, they don't help at all, because they convert X_pda(Y) (which doesn't 
exist) into x86_X_percpu(pda.Y) (which also doesn't exist).  They don't 
remove any #ifdef CONFIG_X86_64's.  If you're going to tromp all over 
the source, you may as well do the most useful thing in the first step.

    J
--
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/