From mboxrd@z Thu Jan 1 00:00:00 1970 From: Matthew Wilcox Subject: Re: [parisc-linux] Latest palinux crash -- VM problem? Date: Sun, 3 Sep 2006 00:30:16 -0600 Message-ID: <20060903063015.GB2558@parisc-linux.org> References: <20060903050051.GA2558@parisc-linux.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii To: parisc-linux@parisc-linux.org Return-Path: In-Reply-To: <20060903050051.GA2558@parisc-linux.org> List-Id: parisc-linux developers list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: parisc-linux-bounces@lists.parisc-linux.org On Sat, Sep 02, 2006 at 11:00:52PM -0600, Matthew Wilcox wrote: > The memory error log indicates an uncorrectable error, unfortuantely I > don't understand it enough to decode what it's saying. > > Could it be a different manifestation of the same problem that bites > PA8800? That is, do we have the same address mapped twice and we're > upsetting Astro by writing back cachelines that are supposed to be on > the other CPU? > > I should probably try to find Astro docs at some point so I can find out > how much it cares about this kind of thing. OK, got the Astro docs. > Error Status Reg = 0x0000000000000010 This bit says that Astro observed a BROAD_ERROR transaction on the Runway bus. ie Astro didn't cause the error, it only noticed it and went fatal in response. It looks like CPU 0 sent the broadcast error, so I need to try to figure out what made CPU 0 go funny. _______________________________________________ parisc-linux mailing list parisc-linux@lists.parisc-linux.org http://lists.parisc-linux.org/mailman/listinfo/parisc-linux