From owner-freebsd-net@FreeBSD.ORG Thu Apr 28 16:50:33 2005 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id ECBF216A4CE; Thu, 28 Apr 2005 16:50:32 +0000 (GMT) Received: from arginine.spc.org (arginine.spc.org [83.167.185.2]) by mx1.FreeBSD.org (Postfix) with ESMTP id A4B1C43D5A; Thu, 28 Apr 2005 16:50:32 +0000 (GMT) (envelope-from bms@spc.org) Received: from localhost (localhost [127.0.0.1]) by arginine.spc.org (Postfix) with ESMTP id 01235651F7; Thu, 28 Apr 2005 17:49:44 +0100 (BST) Received: from arginine.spc.org ([127.0.0.1]) by localhost (arginine.spc.org [127.0.0.1]) (amavisd-new, port 10024) with LMTP id 27909-02; Thu, 28 Apr 2005 17:49:43 +0100 (BST) Received: from empiric.dek.spc.org (host81-134-198-100.in-addr.btopenworld.com [81.134.198.100]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by arginine.spc.org (Postfix) with ESMTP id EBE20651F4; Thu, 28 Apr 2005 17:49:39 +0100 (BST) Received: by empiric.dek.spc.org (Postfix, from userid 1001) id B0BBF623B; Thu, 28 Apr 2005 17:50:26 +0100 (BST) Date: Thu, 28 Apr 2005 17:50:26 +0100 From: Bruce M Simpson To: Maksim Yevmenkin Message-ID: <20050428165026.GG747@empiric.icir.org> References: <20050428135120.GB21428@cell.sick.ru> <427111BF.2050607@savvis.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <427111BF.2050607@savvis.net> cc: jmg@FreeBSD.org cc: Sten Spans cc: Gleb Smirnoff cc: harti@FreeBSD.org cc: net@FreeBSD.org Subject: Re: if_tap unaligned access problem X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 28 Apr 2005 16:50:33 -0000 On Thu, Apr 28, 2005 at 09:39:27AM -0700, Maksim Yevmenkin wrote: > you probably should file pr. (1) and (2) above are quick fixes. (3) is > more complicated and, maybe, not desirable. 3) may be good. I have an ATM driver which may need this behaviour. I haven't had a chance to get test coverage on a non-i386 platform so it's entirely possible that unaligned accesses are happening further up in netinet land (after coming up from the driver, into netnatm, and into IP land). jmg's suggestion of bringing in the NetBSD patches to allow the entire network stack to be compiled with unaligned accesses (for those platforms which support it) is interesting because it can simplify or eliminate some of the acrobatics needed in network drivers to deal with the mbuf alignment. Though I'd like to know what Harti thinks re netnatm. Regards, BMS