linux-kernel - Re: hardwired VMI crap

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: <45F08EDC.30003@vmware.com>
Date:	Thu, 08 Mar 2007 14:31:56 -0800
From:	Zachary Amsden <zach@...are.com>
To:	Jeremy Fitzhardinge <jeremy@...p.org>
CC:	tglx@...utronix.de, Ingo Molnar <mingo@...e.hu>,
	john stultz <johnstul@...ibm.com>, akpm@...ux-foundation.org,
	Linus Torvalds <torvalds@...ux-foundation.org>,
	LKML <linux-kernel@...r.kernel.org>,
	Pratap Subrahmanyam <pratap@...are.com>,
	Rusty Russell <rusty@...tcorp.com.au>, Andi Kleen <ak@...e.de>,
	Daniel Hecht <dhecht@...are.com>,
	Daniel Arai <arai@...are.com>,
	Chris Wright <chrisw@...s-sol.org>,
	Virtualization Mailing List <virtualization@...ts.osdl.org>
Subject: Re: hardwired VMI crap

Jeremy Fitzhardinge wrote:
> Zachary Amsden wrote:
>   
>> We faithfully emulate lapic, io_apic, the pit, pic, and a normal
>> interrupt subsystem.
>>     
>
> Can you not just use the apic clock driver directly then?  Do you need
> to do anything special?
>   

The apic clock driver is going to program the apic, not our virtual 
clock, which tracks real time, available and stolen time.  APIC has no 
idea about any of this.

We want an APIC, just purely as a local interrupt controller, and a 
separate, paravirt timer device.  It is not very complicated.

The problem is that we are not supposed to fiddle with APIC internals, 
so we shouldn't be using their clock events, so we can't use their low 
level local timer interrupt, and we are not supposed to write our own.  
So we need a weird hack somewhere because we are not allowed to use any 
of the paths that currently work for our code, because of the 
maintenance burden it imposes by misusing the interfaces.

The larger problem I am having is that nobody wants to give productive 
feedback on how to fix the problem, just sit around and fling muck.

Zach
-
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/