linux-kernel - Re: [PATCH] i386: fix TSC clock source calibration error [part 2]

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: <18200.63696.399763.437303@zeus.sw.starentnetworks.com>
Date:	Fri, 19 Oct 2007 14:34:56 -0400
From:	Dave Johnson <djohnson+linux-kernel@...starentnetworks.com>
To:	Hiroshi Shimamoto <h-shimamoto@...jp.nec.com>
Cc:	Ingo Molnar <mingo@...e.hu>, linux-kernel@...r.kernel.org,
	Thomas Gleixner <tglx@...utronix.de>, Greg KH <gregkh@...e.de>,
	Chris Wright <chrisw@...s-sol.org>
Subject: Re: [PATCH] i386: fix TSC clock source calibration error [part 2]

Hiroshi Shimamoto writes:
> Dave Johnson wrote:
> >  		mach_prepare_counter();
> 
> It's a really rare case, but if SMI interrupt takes CPU here, just after
> prepare and before rdtscll, it makes delta64 shorter than expected one.
> Is it possible? And how about moving rdtscll before mach_prepare_counter()?
> 
> >  		rdtscll(start);

Yep, rare indeed (about 1 instruction). Moving the start read before
the prepare call should solve that one too providing the setup doesn't
take any real measurable time.

-- 
Dave Johnson
Starent Networks

-
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/