From mboxrd@z Thu Jan 1 00:00:00 1970 From: Benjamin Herrenschmidt Subject: Re: [Bug #11875] radeonfb lockup in .28-rc (bisected) Date: Fri, 14 Nov 2008 14:29:11 +1100 Message-ID: <1226633351.7178.107.camel@pasglop> References: <20081113.151116.139760511.davem@davemloft.net> <1226624060.7178.100.camel@pasglop> <20081113.185059.154690040.davem@davemloft.net> <20081113.190447.252605555.davem@davemloft.net> Mime-Version: 1.0 Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20081113.190447.252605555.davem-fT/PcQaiUtIeIZ0/mPfg9Q@public.gmane.org> Sender: kernel-testers-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-ID: Content-Type: text/plain; charset="us-ascii" To: David Miller Cc: rjw-KKrjLPT3xs0@public.gmane.org, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, kernel-testers-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org, cloos-GRsvFm/Gh/pBDgjK7y7TUQ@public.gmane.org, paul-dsjeNyW6Qm/D+ROgJ3VA+kB+6BGkLq7r@public.gmane.org, torvalds-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org > It makes a huge difference, with the acceleration patch: > > commit b1ee26bab14886350ba12a5c10cbc0696ac679bf > Author: Benjamin Herrenschmidt > Date: Wed Oct 15 22:03:46 2008 -0700 > > radeonfb: accelerate imageblit and other improvements > > reverted, the test case takes 25 seconds or more instead of > the 7 or 8 seconds we're seeing now. Ok, thanks a lot for those tests ! So I consider the loss of perfs due to the workaround to be minor enough here. I'll submit the patch for inclusion. I might look at not doing the clipping in cases things are already aligned later but I doubt it's going to be worth the pain, Cheers, Ben.