From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: [BNX2X RESUBMIT][PATCH 0/8] New driver for Broadcom 10Gb Ethernet, take two. Date: Mon, 08 Oct 2007 14:28:01 -0700 (PDT) Message-ID: <20071008.142801.82028532.davem@davemloft.net> References: <20071008120855.758d10e7@freepuppy.rosehill> <1191879622.5277.11.camel@dell> <20071008140301.3e69d01d@freepuppy.rosehill> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: mchan@broadcom.com, eliezert@broadcom.com, jeff@garzik.org, netdev@vger.kernel.org, eilong@broadcom.com, vladz@broadcom.com, gertner@broadcom.com To: shemminger@linux-foundation.org Return-path: Received: from 74-93-104-97-Washington.hfc.comcastbusiness.net ([74.93.104.97]:56110 "EHLO sunset.davemloft.net" rhost-flags-OK-FAIL-OK-OK) by vger.kernel.org with ESMTP id S1752603AbXJHV2Q (ORCPT ); Mon, 8 Oct 2007 17:28:16 -0400 In-Reply-To: <20071008140301.3e69d01d@freepuppy.rosehill> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org From: Stephen Hemminger Date: Mon, 8 Oct 2007 14:03:01 -0700 > On Mon, 08 Oct 2007 14:40:22 -0700 > "Michael Chan" wrote: > > > On Mon, 2007-10-08 at 12:08 -0700, Stephen Hemminger wrote: > > > On Mon, 08 Oct 2007 20:34:41 +0200 > > > "Eliezer" wrote: > > > > > > > > * The MACRO's for 64 bit stats look like they could be done with > > > > > u64 and/or turned into inline's. > > > > > > > > The MACRO's modify some of their arguments, plus they need to work on 32 > > > > bit machines (are 64 bit counters always available on 32 bit machines?). > > > > so using an inline would allow the inline to be more readable but > > > > calling it would get ugly. > > > > I'm open to suggestions. > > > > > > > > > > u64 exists on all platforms (including 32 bit). > > > > > > > I think the biggest problem with these 64-bits counters (and 64-bit > > addresses) is that the hardware treats them as big endian and they get > > DMA'ed in big endian format. We control the byte swap so that 32-bit > > quantities will have the correct endianness, but the high and low 32-bit > > words will be in the wrong spots on little endian machines. That's why > > we need to separate the high and the low words and convert them back and > > forth. > > > There are types and tools for checking endianness see be64, etc. It's not a be64 Stephen, Michael is trying to explain this. They configure the hardware to swap the bytes within a 32-bit word into cpu endianness, but the chip doesn't swap the 32-bit words within a 64-bit word properly, which is why the macros are necessary.