From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from pentafluge.infradead.org (pentafluge.infradead.org [213.146.154.40]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by ozlabs.org (Postfix) with ESMTP id EB634DDE06 for ; Mon, 15 Jan 2007 13:39:27 +1100 (EST) Subject: Re: [PATCH] Fix performance monitor exception in 2.6.20-series From: David Woodhouse To: Benjamin Herrenschmidt In-Reply-To: <1168734544.5011.78.camel@localhost.localdomain> References: <20070113154029.GA32292@eecg.toronto.edu> <1168734544.5011.78.camel@localhost.localdomain> Content-Type: text/plain Date: Mon, 15 Jan 2007 10:40:07 +0800 Message-Id: <1168828808.9415.278.camel@shinybook.infradead.org> Mime-Version: 1.0 Cc: linuxppc-dev@ozlabs.org, Livio Soares List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Sun, 2007-01-14 at 11:29 +1100, Benjamin Herrenschmidt wrote: > > Well, are you absolutely sure that nothing will break as a result of > having a PMU interrupt happening right when it's not expected to ? > > You are basically turning the PMU interrupt into an NMI... I'm not sure > how safe that is. If we can _make_ it safe, and in doing so avoid the failure mode where the machine locks up with interrupts disabled and then the PMU resets itself entirely (including the date), that might be a good thing... -- dwmw2