linux-kernel - Re: x86: tsc: make TSC calibration more immune to interrupts

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]

Date:	Wed, 20 Apr 2011 21:44:52 +0200
From:	Kasper Pedersen <kernel@...perkp.dk>
To:	john stultz <johnstul@...ibm.com>
CC:	linux-kernel@...r.kernel.org, Thomas Gleixner <tglx@...utronix.de>,
	Ingo Molnar <mingo@...hat.com>,
	"H. Peter Anvin" <hpa@...or.com>, x86@...nel.org,
	Peter Zijlstra <a.p.zijlstra@...llo.nl>,
	Suresh Siddha <suresh.b.siddha@...el.com>
Subject: Re: x86: tsc: make TSC calibration more immune to interrupts

On 04/20/2011 09:15 PM, john stultz wrote:
> On Wed, 2011-04-20 at 20:52 +0200, Kasper Pedersen wrote:
>> When a SMI or plain interrupt occurs during the delayed part
>> of TSC calibration, and the SMI/irq handler is good and fast
>> so that is does not exceed SMI_TRESHOLD, tsc_khz can be a bit
>> off (10-30ppm).

> I guess I'm curious how useful this is with the refined TSC calibration
> that was added not too long ago:
> http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commitdiff;h=08ec0c58fb8a05d3191d5cb6f5d6f81adb419798
> 
> Are you saying that you see the same 10-30ppm variance in the dmesg
> line: "Refined TSC clocksource calibration: XXXX.XXX MHz" ?
>

Yes, I do.
With the delayed workqueue patch, I see a wonderful 0.4ppm
offset _almost_ all of the time.

Very rarely though (about 1 in 3000) the value output by
"Refined TSC .." jumps. It can jump no further than
50000/F_TSC/delayed_time, so on a modern machine it jumps
no further than 20ppm.

This can happen when a short irq occurs between
*p = hpet_readl(HPET_COUNTER) & 0xFFFFFFFF;
and
t2 = get_cycles();


Without the delayed workqueue patch 30ppm is insignificant.

/Kasper Pederen
--
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/