From mboxrd@z Thu Jan 1 00:00:00 1970 From: Linus Torvalds Subject: Re: More prefetch fall-out Date: Sun, 22 May 2011 11:38:44 -0700 Message-ID: References: <1306088626.12435.27.camel@edumazet-laptop> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Cc: David Miller , Network Development To: Eric Dumazet Return-path: Received: from smtp1.linux-foundation.org ([140.211.169.13]:36545 "EHLO smtp1.linux-foundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752141Ab1EVSjN (ORCPT ); Sun, 22 May 2011 14:39:13 -0400 Received: from mail-ey0-f174.google.com (mail-ey0-f174.google.com [209.85.215.174]) (authenticated bits=0) by smtp1.linux-foundation.org (8.14.2/8.13.5/Debian-3ubuntu1.1) with ESMTP id p4MId7ec007673 (version=TLSv1/SSLv3 cipher=RC4-SHA bits=128 verify=FAIL) for ; Sun, 22 May 2011 11:39:08 -0700 Received: by eyx24 with SMTP id 24so1617333eyx.19 for ; Sun, 22 May 2011 11:39:04 -0700 (PDT) In-Reply-To: <1306088626.12435.27.camel@edumazet-laptop> Sender: netdev-owner@vger.kernel.org List-ID: On Sun, May 22, 2011 at 11:23 AM, Eric Dumazet wrote: > > Taking a look at various skb_queue_walk* call sites, I think prefetches > are not a clear win, I would just remove them all from skbuff.h Hmm. I did that, and it turns out that we also have: - *lots* of network drivers that use "prefetch" (without including prefetch.h) - net/netlabel/netlabel_addrlist.h doing the same. and fixing that up is annoying "grunt work". So for now, I think I'll just do the "add the to " thing, and leave networking alone. That makes everything compile ("allyesconfig") even with my "you *have* to include " test-patch. Linus