From mboxrd@z Thu Jan 1 00:00:00 1970 From: James Chapman Subject: Re: [PATCH 1/2 2.6] e100: fix NAPI race with watchdog Date: Thu, 23 Sep 2004 10:08:48 +0100 Sender: netdev-bounce@oss.sgi.com Message-ID: <1095930528.415292a0cd16a@www.katalix.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit Cc: jgarzik@pobox.com, netdev@oss.sgi.com Return-path: To: jesse.brandeburg@intel.com Errors-to: netdev-bounce@oss.sgi.com List-Id: netdev.vger.kernel.org > While polling in NAPI mode, we were occassionally getting interrupts > re-enabled by the watchdog trying to generate a software interrupt. > Fix is to add a spinlock around that shared hardware register to > allow a read-modify-write operation. This was nasty nasty. I don't > like the spinlock in the hot path but i see no other way. Comments > are welcome. While working with NAPI on the e100 a while ago, I seriously considered removing the generation of the sw interrupt altogether for the NAPI case. Does it serve any purpose? NAPI is polling the driver already anyway. /james