From mboxrd@z Thu Jan 1 00:00:00 1970 From: Stephen Hemminger Subject: Re: Mystery packet killing tg3 Date: Wed, 4 May 2005 15:51:43 -0700 Message-ID: <20050504155143.1a78cb7a@dxpl.pdx.osdl.net> References: Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: "David S. Miller" , jgarzik@pobox.com, netdev@oss.sgi.com Return-path: To: "Michael Chan" In-Reply-To: Sender: netdev-bounce@oss.sgi.com Errors-to: netdev-bounce@oss.sgi.com List-Id: netdev.vger.kernel.org On Tue, 3 May 2005 23:27:38 -0700 "Michael Chan" wrote: > Stephen Hemminger wrote: > > > Initially, it reproduced everytime link came up, we > > reconfigured the VLAN to > > have a mirror port into a laptop to try and capture what was > > happening, but when > > we did that the bootup problem went away. It was in the tg3_reset_hw > > during initial dev_open. > > > > During initial dev_open, the TG3_FLAG_INIT_COMPLETE flag is not set so > tg3_reset_hw() should not call tg3_abort_hw() where the stop_block calls are > made. So there should be no stop_block errors. > > I think stop_block errors can only happen during dev_close, suspend, netdev > watchdog, or ethtool "set" calls. It seems that dhclient was failing on bootup then taking the device down. When the device down happened it got the tg3_stop_block from Call Trace:{:tg3:tg3_stop_block+185} {:tg3:tg3_abort_hw+605} {:tg3:tg3_halt+40} {:tg3:tg3_close+71} {dev_close+100} {dev_change_flags+104} {devinet_ioctl+773} {inet_ioctl+92} {sock_ioctl+556} {do_ioctl+58} {vfs_ioctl+715} {sys_ioctl+77} {system_call+126}