From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id ABBF0A10DA for ; Wed, 31 Jul 2019 12:44:21 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 5C7CA1BF00; Wed, 31 Jul 2019 12:44:20 +0200 (CEST) Received: from mx0a-001b2d01.pphosted.com (mx0a-001b2d01.pphosted.com [148.163.156.1]) by dpdk.org (Postfix) with ESMTP id B43C41BEF8 for ; Wed, 31 Jul 2019 12:44:18 +0200 (CEST) Received: from pps.filterd (m0098399.ppops.net [127.0.0.1]) by mx0a-001b2d01.pphosted.com (8.16.0.27/8.16.0.27) with SMTP id x6VAhMcc139127 for ; Wed, 31 Jul 2019 06:44:17 -0400 Received: from smtp.notes.na.collabserv.com (smtp.notes.na.collabserv.com [158.85.210.114]) by mx0a-001b2d01.pphosted.com with ESMTP id 2u37j2nqfu-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT) for ; Wed, 31 Jul 2019 06:44:17 -0400 Received: from localhost by smtp.notes.na.collabserv.com with smtp.notes.na.collabserv.com ESMTP for from ; Wed, 31 Jul 2019 10:44:17 -0000 Received: from us1b3-smtp01.a3dr.sjc01.isc4sb.com (10.122.7.174) by smtp.notes.na.collabserv.com (10.122.47.58) with smtp.notes.na.collabserv.com ESMTP; Wed, 31 Jul 2019 10:44:13 -0000 Received: from us1b3-mail160.a3dr.sjc03.isc4sb.com ([10.160.174.150]) by us1b3-smtp01.a3dr.sjc01.isc4sb.com with ESMTP id 2019073110441330-383302 ; Wed, 31 Jul 2019 10:44:13 +0000 In-Reply-To: From: "Takeshi T Yoshimura" To: David Marchand Cc: dev Date: Wed, 31 Jul 2019 10:44:12 +0000 MIME-Version: 1.0 Sensitivity: Importance: Normal X-Priority: 3 (Normal) References: , <20190731033523.2482-1-tyos@jp.ibm.com> X-Mailer: IBM iNotes ($HaikuForm 1054) | IBM Domino Build SCN1812108_20180501T0841_FP55 May 22, 2019 at 11:09 X-KeepSent: 6FEB6022:2D33273A-00258448:003A6495; type=4; name=$KeepSent X-LLNOutbound: False X-Disclaimed: 31403 X-TNEFEvaluated: 1 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=UTF-8 x-cbid: 19073110-1639-0000-0000-000000120227 X-IBM-SpamModules-Scores: BY=0.283363; FL=0; FP=0; FZ=0; HX=0; KW=0; PH=0; SC=0.399202; ST=0; TS=0; UL=0; ISC=; MB=0.000053 X-IBM-SpamModules-Versions: BY=3.00011528; HX=3.00000242; KW=3.00000007; PH=3.00000004; SC=3.00000287; SDB=6.01240023; UDB=6.00653864; IPR=6.01021443; MB=3.00027974; MTD=3.00000008; XFM=3.00000015; UTC=2019-07-31 10:44:15 X-IBM-AV-DETECTION: SAVI=unsuspicious REMOTE=unsuspicious XFE=unused X-IBM-AV-VERSION: SAVI=2019-07-31 06:28:07 - 6.00010230 x-cbparentid: 19073110-1640-0000-0000-0000001E01CA Message-Id: X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:, , definitions=2019-07-31_04:, , signatures=0 X-Proofpoint-Spam-Reason: safe Subject: Re: [dpdk-dev] [PATCH] eal: forcing IOVA as PA in ppc X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" -----David Marchand wrote: ----- >To: Takeshi Yoshimura >From: David Marchand >Date: 07/31/2019 06:29PM >Cc: dev >Subject: [EXTERNAL] Re: [dpdk-dev] [PATCH] eal: forcing IOVA as PA in >ppc > >On Wed, Jul 31, 2019 at 5:36 AM Takeshi Yoshimura >wrote: >> >> Commit b76fafb174d2 ("eal: fix IOVA mode selection as VA for PCI >> drivers") breaks ppc apps with no IOVA configs (or RTE=5FIOVA=5FDC) >> because of the inconsistency of user's request and the result of >> device capability for IOVA mode. I updated the code to force IOVA >as >> PA in ppc as before because current ppc driver does not support VA >> mode. > >What is the "ppc driver" you are referring to? >Do you mean the vfio implementation for ppc? > >> >> Theoretically, ppc can support VA mode, but I suspect that ppc with >> VA mode may have performance issues to create a big DMA window >> (VA often uses higher addresses than PA). So, I didn't change the >> code to check device capability in ppc. > >Sorry, I am confused. >Is VA mode not working at all? or is it a performance issue? > > >--=20 >David Marchand > > Ah, I overlooked your first question. The "ppc driver" is in drivers/bus/pci/linux/pci.c. In pci.c, pci=5Fone=5Fdevice=5Fiommu=5Fsupport= =5Fva() always returns false in ppc. so, the driver does not allow VA mode in ppc. This return value is passed to rte=5Fpci=5Fprobe=5Fone=5Fdriver() in drivers/bus/pci/pci=5Fcommon.c. And the error log appeared like: EAL: PCI device 0000:01:00.0 on NUMA socket 0 EAL: probe driver: 144d:a822 spdk=5Fnvme EAL: Expecting 'PA' IOVA mode but current mode is 'VA', not initializing