From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mailserv2.iuinc.com (IDENT:qmailr@mailserv2.iuinc.com [206.245.164.55]) by puffin.external.hp.com (8.9.3/8.9.3) with SMTP id PAA15821 for ; Fri, 3 Mar 2000 15:59:37 -0700 Received: from hub-fue by rachael.franken.de via rmail with uucp id for thepuffingroup.com!parisc-linux; Fri, 3 Mar 2000 22:57:12 +0100 (MET) (Smail-3.2 1996-Jul-4 #4 built DST-Sep-8) Date: Fri, 3 Mar 2000 22:53:11 +0100 From: Thomas Bogendoerfer To: Philipp Rumpf Cc: Grant Grundler , willy@thepuffingroup.com, parisc-linux@thepuffingroup.com Subject: Re: [parisc-linux] code 28 trap Message-ID: <20000303225311.C27816@alpha.franken.de> References: <20000224224934.N9944@thepuffingroup.com> <200002252036.MAA04792@milano.cup.hp.com> <20000225230348.E812@abacus.local> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: <20000225230348.E812@abacus.local>; from Philipp Rumpf on Fri, Feb 25, 2000 at 11:03:48PM +0100 List-ID: On Fri, Feb 25, 2000 at 11:03:48PM +0100, Philipp Rumpf wrote: > > > Uh oh. We really need a kernel unaligned trap handler. Some of > > > the network protocols rely on that being handled right (yes, i know. > > > it sucks.) > > > > It really sucks. If any code in the performance path depends on this, > > Another vote for "it sucks". > > Which network drivers, protocols aso exactly are you using (and did you > check for the bug Matthew posted an URL for ?) ? I really don't think > we should write an unaligned handler until we find ourselves using weird > protocols (and hopefully not even then). the first person using IPX will need an unaligend trap handler. All the ethernet driver try to align the IP header to a 32bit boundary (that's the reason for the skb_reserve(skb, 2)), which messes up the alignment in IPX headers. And there are ethernet chips, which can only handle 32bit aligned receive buffer (tulip for example). You either have to copy the received frame to a proper aligned new skb (that's what we do at the moment) or handle the missalignment in an unaligned trap handler. Thomas. -- This device has completely bogus header. Compaq scores again :-| It's a host bridge, but it should be called ghost bridge instead ;^) [Martin `MJ' Mares on linux-kernel]