From mboxrd@z Thu Jan 1 00:00:00 1970 From: Arnd Bergmann Subject: Re: [patch 5/6] ps3: BD/DVD/CD-ROM Storage Driver Date: Fri, 13 Jul 2007 16:19:54 +0200 Message-ID: <200707131619.54898.arnd@arndb.de> References: <20070704132212.726923000@pademelon.sonytel.be> <1184335333.3402.20.camel@localhost.localdomain> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: Received: from moutng.kundenserver.de ([212.227.126.188]:56544 "EHLO moutng.kundenserver.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1761021AbXGMOiR convert rfc822-to-8bit (ORCPT ); Fri, 13 Jul 2007 10:38:17 -0400 In-Reply-To: <1184335333.3402.20.camel@localhost.localdomain> Content-Disposition: inline Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: linuxppc-dev@ozlabs.org Cc: James Bottomley , Geert Uytterhoeven , linux-scsi@vger.kernel.org, linux-kernel@vger.kernel.org, Alessandro Rubini , Paul Mackerras , Jens Axboe On Friday 13 July 2007, James Bottomley wrote: >=20 > > IC. > >=20 > > =A0 - flush_kernel_dcache_page() is a no-op on ppc64 > > =A0 =A0 (ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE is defined on parisc onl= y). > >=20 > > =A0 - For reference, drivers/scsi/ipr.c (another ppc64 driver) just= uses a plain > > =A0 =A0 kmap/memcpy/kunmap sequence > >=20 > > So what should I do? >=20 > Ask someone who knows the architecture ... Anton, Paulus or Benh ... = I'm > fairly certain PPC is VIPT and will need some kind of alias > resolution ... perhaps its associative enough not to let the aliases = be > a problem. I'm pretty sure that no ppc64 machine needs alias resolution in the ker= nel, although some are VIPT. Last time we discussed this, Segher explained i= t to me, but I don't remember which way Cell does it. IIRC, it automatica= lly flushes cache lines that are accessed through aliases. It's probably a good idea to have the flush_kernel_dcache_page() in the= re anyway, if only to serve as an example for people that copy it into architecture-independent drivers, same as what we do for the k{,un}map_atomic() that is also not required on ppc64. Arnd <>< - To unsubscribe from this list: send the line "unsubscribe linux-scsi" i= n the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from moutng.kundenserver.de (moutng.kundenserver.de [212.227.126.188]) by ozlabs.org (Postfix) with ESMTP id 316A2DDD05 for ; Sat, 14 Jul 2007 00:37:52 +1000 (EST) From: Arnd Bergmann To: linuxppc-dev@ozlabs.org Subject: Re: [patch 5/6] ps3: BD/DVD/CD-ROM Storage Driver Date: Fri, 13 Jul 2007 16:19:54 +0200 References: <20070704132212.726923000@pademelon.sonytel.be> <1184335333.3402.20.camel@localhost.localdomain> In-Reply-To: <1184335333.3402.20.camel@localhost.localdomain> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Message-Id: <200707131619.54898.arnd@arndb.de> Cc: James Bottomley , linux-scsi@vger.kernel.org, linux-kernel@vger.kernel.org, Alessandro Rubini , Paul Mackerras , Jens Axboe , Geert Uytterhoeven List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Friday 13 July 2007, James Bottomley wrote: >=20 > > IC. > >=20 > > =A0 - flush_kernel_dcache_page() is a no-op on ppc64 > > =A0 =A0 (ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE is defined on parisc only). > >=20 > > =A0 - For reference, drivers/scsi/ipr.c (another ppc64 driver) just use= s a plain > > =A0 =A0 kmap/memcpy/kunmap sequence > >=20 > > So what should I do? >=20 > Ask someone who knows the architecture ... Anton, Paulus or Benh ... I'm > fairly certain PPC is VIPT and will need some kind of alias > resolution ... perhaps its associative enough not to let the aliases be > a problem. I'm pretty sure that no ppc64 machine needs alias resolution in the kernel, although some are VIPT. Last time we discussed this, Segher explained it to me, but I don't remember which way Cell does it. IIRC, it automatically flushes cache lines that are accessed through aliases. It's probably a good idea to have the flush_kernel_dcache_page() in there anyway, if only to serve as an example for people that copy it into architecture-independent drivers, same as what we do for the k{,un}map_atomic() that is also not required on ppc64. Arnd <>< From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760624AbXGMOio (ORCPT ); Fri, 13 Jul 2007 10:38:44 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S933960AbXGMOiT (ORCPT ); Fri, 13 Jul 2007 10:38:19 -0400 Received: from moutng.kundenserver.de ([212.227.126.188]:56544 "EHLO moutng.kundenserver.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1761021AbXGMOiR convert rfc822-to-8bit (ORCPT ); Fri, 13 Jul 2007 10:38:17 -0400 From: Arnd Bergmann To: linuxppc-dev@ozlabs.org Subject: Re: [patch 5/6] ps3: BD/DVD/CD-ROM Storage Driver Date: Fri, 13 Jul 2007 16:19:54 +0200 User-Agent: KMail/1.9.6 Cc: James Bottomley , Geert Uytterhoeven , linux-scsi@vger.kernel.org, linux-kernel@vger.kernel.org, Alessandro Rubini , Paul Mackerras , Jens Axboe References: <20070704132212.726923000@pademelon.sonytel.be> <1184335333.3402.20.camel@localhost.localdomain> In-Reply-To: <1184335333.3402.20.camel@localhost.localdomain> X-Face: >j"dOR3XO=^3iw?0`(E1wZ/&le9!.ok[JrI=S~VlsF~}"P\+jx.GT@=?utf-8?q?=0A=09-oaEG?=,9Ba>v;3>:kcw#yO5?B:l{(Ln.2)=?utf-8?q?=27=7Dfw07+4-=26=5E=7CScOpE=3F=5D=5EXdv=5B/zWkA7=60=25M!DxZ=0A=09?= =?utf-8?q?8MJ=2EU5?="hi+2yT(k`PF~Zt;tfT,i,JXf=x@eLP{7B:"GyA\=UnN) =?utf-8?q?=26=26qdaA=3A=7D-Y*=7D=3A3YvzV9=0A=09=7E=273a=7E7I=7CWQ=5D?=<50*%U-6Ewmxfzdn/CK_E/ouMU(r?FAQG/ev^JyuX.%(By`" =?utf-8?q?L=5F=0A=09H=3Dbj?=)"y7*XOqz|SS"mrZ$`Q_syCd MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 8BIT Content-Disposition: inline Message-Id: <200707131619.54898.arnd@arndb.de> X-Provags-ID: V01U2FsdGVkX18iulA2NcYJrcpOV973qVDnaa7PncCC/nZmYkd B/K2XeXEUqbol3EFf+P/T3tOEogntuhh49LssmJQ12CILkYphD W/eqANSlIMlZDHOp54LXQ== Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Friday 13 July 2007, James Bottomley wrote: > > > IC. > > > >   - flush_kernel_dcache_page() is a no-op on ppc64 > >     (ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE is defined on parisc only). > > > >   - For reference, drivers/scsi/ipr.c (another ppc64 driver) just uses a plain > >     kmap/memcpy/kunmap sequence > > > > So what should I do? > > Ask someone who knows the architecture ... Anton, Paulus or Benh ... I'm > fairly certain PPC is VIPT and will need some kind of alias > resolution ... perhaps its associative enough not to let the aliases be > a problem. I'm pretty sure that no ppc64 machine needs alias resolution in the kernel, although some are VIPT. Last time we discussed this, Segher explained it to me, but I don't remember which way Cell does it. IIRC, it automatically flushes cache lines that are accessed through aliases. It's probably a good idea to have the flush_kernel_dcache_page() in there anyway, if only to serve as an example for people that copy it into architecture-independent drivers, same as what we do for the k{,un}map_atomic() that is also not required on ppc64. Arnd <><