Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756651Ab1FQDo6 (ORCPT ); Thu, 16 Jun 2011 23:44:58 -0400 Received: from vm4.telegraphics.com.au ([98.124.60.149]:59326 "EHLO vps4.telegraphics.com.au" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756214Ab1FQDo5 (ORCPT ); Thu, 16 Jun 2011 23:44:57 -0400 Date: Fri, 17 Jun 2011 13:45:24 +1000 (EST) From: Finn Thain To: Geert Uytterhoeven cc: Linux/m68k , Thomas Gleixner , Linux Kernel Development Subject: Re: m68k: Convert to genirq (WIP) In-Reply-To: Message-ID: References: User-Agent: Alpine 2.00 (OSX 1167 2008-08-23) MIME-Version: 1.0 Content-Type: MULTIPART/MIXED; BOUNDARY="0-915750856-1308282324=:191" Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1905 Lines: 58 This message is in MIME format. The first part should be readable text, while the remaining parts are likely unreadable without MIME-aware tools. --0-915750856-1308282324=:191 Content-Type: TEXT/PLAIN; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE On Thu, 16 Jun 2011, Geert Uytterhoeven wrote: > On Wed, Jun 15, 2011 at 21:44, Geert Uytterhoeven = wrote: > > On Sat, Jun 4, 2011 at 19:56, Geert Uytterhoeven = wrote: > >> On Sat, May 28, 2011 at 20:32, Geert Uytterhoeven wrote: > >> > >> It works on Amiga now, too. It can still use some optimizations in=20 > >> the irq_{enable,disable,ack,mask,mask_ack,unmask} area, as my=20 > >> BogoMIPS rating dropped by ca 2.5% and is now under 16, for a 25 MHz= =20 > >> 68040. > > > > Seems like everything (Atari/ARAnyM and Amiga) still works when using= =20 > > handle_simple_irq instead of handle_level_irq. As a bonus, BogoMIPS is= =20 > > above 16 again. Your bogomips benchmark would be the best-case penalty, right? Have you tried say, sending a ping flood to measure throughput and=20 latency? >=20 > With handle_simple_irq(), we no longer need to define irq_{,un}mask()=20 > methods in our irq_chips. Hence the "old" m68k platform interrupt code=20 > seems to be much closer to genirq than I thought... >=20 > Does this make sense? If the simple irq model gets us closer to the goal and doesn't kill=20 performance then it makes sense to me. Finn >=20 > Gr{oetje,eeting}s, >=20 > =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 Geert >=20 --0-915750856-1308282324=:191-- -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/