From mboxrd@z Thu Jan 1 00:00:00 1970 From: Lennert Buytenhek Subject: Re: [PATCH] b44: power down PHY when interface down Date: Sun, 1 Jul 2007 00:03:01 +0200 Message-ID: <20070630220301.GD2553@xi.wantstofly.org> References: <4354d3270706300447ladcda4by987b1f87963112f9@mail.gmail.com> <200706302353.25426.mb@bu3sch.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: =?iso-8859-1?B?VPZy9ms=?= Edvin , zambrano@broadcom.com, netdev@vger.kernel.org, linux-kernel@vger.kernel.org, power@bughost.org To: Michael Buesch Return-path: Received: from alephnull.demon.nl ([83.160.184.112]:45482 "EHLO xi.wantstofly.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752500AbXF3WDE (ORCPT ); Sat, 30 Jun 2007 18:03:04 -0400 Content-Disposition: inline In-Reply-To: <200706302353.25426.mb@bu3sch.de> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Sat, Jun 30, 2007 at 11:53:25PM +0200, Michael Buesch wrote: > > When the interface is down (or driver removed), the BroadCom 44xx card remains > > powered on, and both its MAC and PHY is using up power. > > This patch makes the driver issue a MAC_CTRL_PHY_PDOWN when the interface > > is halted, and does a partial chip reset turns off the activity LEDs too. > > > > Applies to 2.6.22-rc6, or current git head. > > > > Tested on a Broadcom BCM4401-B0 card, it saves ~0.5W (measured using powertop). > > Hm, I was going to measure the real power advantage with a > PCI-extender card. But my B44B0 card doesn't seem to work in > that extender card. It works perfectly fine sticked directly into > the motherboard, though, and other cards like a BCM4318 work in > the extender, too. > Not sure what this is. > The extender has an application note about nonworking cards in the > extender and a too big resistor on the board IDSEL pin being the > cause of this. Does the card show up in lspci at all? IDSEL drive strength issues should only affect config space accesses. Does the extender board have a PCI-PCI bridge on it? (If not, there's not really any reason to resistively couple the IDSEL line to the host, since the host should take care of that.) > Maybe I can try with another machine tomorrow. That would only make a difference if there is no PCI-PCI bridge on the extender board. If the extender resistively couples the host's IDSEL line, you might see different results on a different host bridge, since different host bridges can use different numbers of IDSEL stepping cycles.