linux-kernel - Re: REGRESSION: the new i386 timer code fails to sync CPUs

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:	Sun, 30 Jul 2006 02:03:46 -0700
From:	Andrew Morton <akpm@...l.org>
To:	john stultz <johnstul@...ibm.com>
Cc:	ak@....de, smurf@...rf.noris.de, linux-kernel@...r.kernel.org,
	torvalds@...l.org, bunk@...sta.de, lethal@...ux-sh.org,
	hirofumi@...l.parknet.co.jp, asit.k.mallick@...el.com
Subject: Re: REGRESSION: the new i386 timer code fails to sync CPUs

On Mon, 24 Jul 2006 13:54:03 -0700
john stultz <johnstul@...ibm.com> wrote:

> On Mon, 2006-07-24 at 19:51 +0200, Andi Kleen wrote:
> > On Mon, Jul 24, 2006 at 07:17:11PM +0200, Matthias Urlichs wrote:
> > > You can probably assume that they're synced on systems with no more
> > > than one dual-core / hyperthreaded CPU.
> > > 
> > > My system obviously has two of those.
> > 
> > According to Intel on all of their chipsets/motherboard reference
> > designs all the sockets run from a single clock crystal.
> > 
> > I've confirmed this for a long time on 64bit and even to some
> > extent on 32bit on distro kernels.
> 
> Andi: Which 32bit distro patch are you referring to here?
> 
> > Maybe you got a broken BIOS or similar though.
> > 
> > > > Matthias: "clock=pmtmr" is probably the best workaround in the short
> > > > term. Could you send me your dmesg and dmidecode output? We'll try to
> > > > find something to key off of so it will mark the tsc as unstable by
> > > > default on your system.
> > > > 
> > > I'd assume that finding (and, possibly, being unable to correct) TSC skew 
> > 
> > The BIOS normally guarantee it at boot. However maybe you got a broken one.
> > 
> > We used to do TSC sync correction at boot on Intel, but stopped doing 
> > that when we found out that the TSC sync code adds an error
> > To an already perfectly synchronized system.
> > 
> > Actually I think i386 still does it, just x86-64 stopped 
> 
> Indeed i386 still does it. I knew x86-64 had a new ia64 inspired
> algorithm, but I didn't realize that they didn't even try to call it in
> most cases.
> 
> The (untested) patch below will disable it on i386. Matthias, mind
> trying it out to see if the TSC sync code is causing the problem?
> 
> 
> > My first assumption would be that you hit a bug somewhere in the new
> > clock code. What happens when you boot an older kernel (like 2.6.17)
> > with clock=tsc ? 
> 
> Yes, that would be good to confirm the issue. :)
> 
> thanks
> -john
> 
> 
> Hack out the i386 TSC sync code.
> 
> 
> diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
> index 6f5fea0..cd28914 100644
> --- a/arch/i386/kernel/smpboot.c
> +++ b/arch/i386/kernel/smpboot.c
> @@ -435,7 +435,7 @@ static void __devinit smp_callin(void)
>  	/*
>  	 *      Synchronize the TSC with the BP
>  	 */
> -	if (cpu_has_tsc && cpu_khz && !tsc_sync_disabled)
> +	if (0 && cpu_has_tsc && cpu_khz && !tsc_sync_disabled)
>  		synchronize_tsc_ap();
>  }
>  
> @@ -1305,7 +1305,7 @@ static void __init smp_boot_cpus(unsigne
>  	/*
>  	 * Synchronize the TSC with the AP
>  	 */
> -	if (cpu_has_tsc && cpucount && cpu_khz)
> +	if (0 && cpu_has_tsc && cpucount && cpu_khz)
>  		synchronize_tsc_bp();
>  }

I guess Matthias didn't test this patch.  Can we get some obviously-correct
fix in place for 2.6.18?

Also, I was rather hoping we'd be able to work out why write_tsc() isn't
working on this CPU.  If that's fixable, that would be the best fix for
this bug, no?

It is a "CPU0: Intel(R) Xeon(TM) CPU 3.00GHz stepping 03".

-
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/