linux-kernel - Re: [patch 4/4] x86: apic_is_clustered_box to indicate unsynched TSC's on multiboard vSMP systems

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: <20080321091542.GE20420@elte.hu>
Date:	Fri, 21 Mar 2008 10:15:42 +0100
From:	Ingo Molnar <mingo@...e.hu>
To:	Ravikiran G Thirumalai <kiran@...lex86.org>
Cc:	Yinghai Lu <yhlu.kernel@...il.com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	linux-kernel@...r.kernel.org,
	Glauber de Oliveira Costa <gcosta@...hat.com>,
	Andi Kleen <ak@...e.de>, shai@...lex86.org
Subject: Re: [patch 4/4] x86: apic_is_clustered_box to indicate unsynched
	TSC's on multiboard vSMP systems


* Ravikiran G Thirumalai <kiran@...lex86.org> wrote:

> >>  -       if (!is_vsmp_box() && (boot_cpu_data.x86_vendor == X86_VENDOR_AMD))
> >>  +       if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && !is_vsmp_box())
> >>                 return 0;

> Yes.  The first call is to state that TSC's are synced if it is an AMD 
> box and if it is _not_ a vSMPowered box (for the apic id lifting case 
> on Sun boxes), the second call is for _any_ vSMPowered system with 
> more than one board -- TSC's are not guaranteed to be synched in that 
> case.  Both these calls are needed.

i suspect there are two questions here: firstly, your change only flips 
the condition around which should not have any effect _normally_. But 
the thing is that is_vsmp_box() has side-effects: it reads the PCI 
config space and sets a flag. It would be cleaner if there was a 
separate, explicit detect_vsmp_box() call early during bootup which did 
the PCI config space access, and is_vsmp_box() would only return the 
current state of the vsmp flag. Then your above change would be 
unnecessary.

	Ingo
--
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/