linux-mips
[Top] [All Lists]

Re: [PATCH] vr41xx: fix problem with vr41xx_cpu_wait

To: ricmm@gentoo.org
Subject: Re: [PATCH] vr41xx: fix problem with vr41xx_cpu_wait
From: Atsushi Nemoto <anemo@mba.ocn.ne.jp>
Date: Thu, 07 Aug 2008 02:10:57 +0900 (JST)
Cc: yoichi_yuasa@tripeaks.co.jp, linux-mips@linux-mips.org, ralf@linux-mips.org
In-reply-to: <20080806161710.GA22957@woodpecker.gentoo.org>
Original-recipient: rfc822;linux-mips@linux-mips.org
References: <200808060440.m764eF9I021783@po-mbox303.hop.2iij.net> <20080806.223033.128619389.anemo@mba.ocn.ne.jp> <20080806161710.GA22957@woodpecker.gentoo.org>
Sender: linux-mips-bounce@linux-mips.org
On Wed, 6 Aug 2008 16:17:10 +0000, Ricardo Mendoza <ricmm@gentoo.org> wrote:
> I see, I hadn't read that thread before. Yoichi's rev of the patch
> should go in but we should put some effort in finding a better route for
> CPUs that are not forcefully aware by hardware of interrupts in their
> wait call.
> 
> Was some work ever done on Ralf's idea in the "WAIT vs. tickless kernel"
> ML thread? Regarding patching the return from exception code to contain
> a check for this particular loop.

Yes.  My last proposal is:

http://www.linux-mips.org/archives/linux-mips/2007-11/msg00123.html

To support vr41's standby instruction in same way, we might have to
synthesise rollback_handle_int, etc. or r4k_wait at runtime...

---
Atsushi Nemoto

<Prev in Thread] Current Thread [Next in Thread>