From mboxrd@z Thu Jan 1 00:00:00 1970
Return-Path: <bjorn.topel@intel.com>
Received: from mga04.intel.com (mga04.intel.com [192.55.52.120])
by dpdk.org (Postfix) with ESMTP id B4285275D
for <dev@dpdk.org>; Fri, 22 Apr 2016 07:17:21 +0200 (CEST)
Received: from orsmga002.jf.intel.com ([10.7.209.21])
by fmsmga104.fm.intel.com with ESMTP; 21 Apr 2016 22:17:21 -0700
X-ExtLoop1: 1
X-IronPort-AV: E=Sophos;i="5.24,516,1455004800"; d="scan'208";a="960332001"
Received: from irsmsx101.ger.corp.intel.com ([163.33.3.153])
by orsmga002.jf.intel.com with ESMTP; 21 Apr 2016 22:17:19 -0700
Received: from irsmsx103.ger.corp.intel.com ([169.254.3.12]) by
IRSMSX101.ger.corp.intel.com ([169.254.1.157]) with mapi id 14.03.0248.002;
Fri, 22 Apr 2016 06:17:19 +0100
From: "Topel, Bjorn" <bjorn.topel@intel.com>
To: "Zhang, Helin" <helin.zhang@intel.com>, "dev@dpdk.org" <dev@dpdk.org>
CC: "david.marchand@6wind.com" <david.marchand@6wind.com>, "Wu, Jingjing"
<jingjing.wu@intel.com>
Thread-Topic: [PATCH v2] i40evf: Report error if HW CRC strip is disabled
for Linux PF hosts
Thread-Index: AQHRm98LDhmGny7Wv0WR8Mo3S18aPJ+VKp2AgABA1Ef///W/AIAAEUgC
Date: Fri, 22 Apr 2016 05:17:17 +0000
Message-ID: <6B5F13689D63284BBB0B66A5B315C82DBAC621@IRSMSX103.ger.corp.intel.com>
References: <1460645904-19565-1-git-send-email-bjorn.topel@intel.com>
<1461250975-14437-1-git-send-email-bjorn.topel@intel.com>,
<F35DEAC7BCE34641BA9FAC6BCA4A12E70AA12288@SHSMSX103.ccr.corp.intel.com>
<6B5F13689D63284BBB0B66A5B315C82DBAC5E2@IRSMSX103.ger.corp.intel.com>,
<F35DEAC7BCE34641BA9FAC6BCA4A12E70AA1235E@SHSMSX103.ccr.corp.intel.com>
In-Reply-To: <F35DEAC7BCE34641BA9FAC6BCA4A12E70AA1235E@SHSMSX103.ccr.corp.intel.com>
Accept-Language: en-US
Content-Language: en-US
X-MS-Has-Attach:
X-MS-TNEF-Correlator:
x-originating-ip: [10.19.9.42]
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
Subject: Re: [dpdk-dev] [PATCH v2] i40evf: Report error if HW CRC strip is
disabled for Linux PF hosts
X-BeenThere: dev@dpdk.org
X-Mailman-Version: 2.1.15
Precedence: list
List-Id: patches and discussions about DPDK <dev.dpdk.org>
List-Unsubscribe: <http://dpdk.org/ml/options/dev>,
<mailto:dev-request@dpdk.org?subject=unsubscribe>
List-Archive: <http://dpdk.org/ml/archives/dev/>
List-Post: <mailto:dev@dpdk.org>
List-Help: <mailto:dev-request@dpdk.org?subject=help>
List-Subscribe: <http://dpdk.org/ml/listinfo/dev>,
<mailto:dev-request@dpdk.org?subject=subscribe>
X-List-Received-Date: Fri, 22 Apr 2016 05:17:22 -0000
>> >> + /* For Linux PF hosts, VF has no ability to disable HW CRC stri=
p,=0A=
>> >> + * and is implicitly enabled by the PF.=0A=
>> >> + */=0A=
>> >> + if (!conf->rxmode.hw_strip_crc) {=0A=
>> >> + vf =3D I40EVF_DEV_PRIVATE_TO_VF(dev->data->dev_private)=
;=0A=
>> >> + if ((vf->version_major =3D=3D I40E_VIRTCHNL_VERSION_MAJ=
OR) &&=0A=
>> >> + (vf->version_minor <=3D I40E_VIRTCHNL_VERSION_MINOR=
)) {=0A=
>> >> + /* Peer is Linux PF host. */=0A=
>> > Can you reword above comments?=0A=
>> > It just means the host is not DPDK PF host driver, it could be Linux=
=0A=
>> > driver, and possible others (e.g. FreeBSD, VMWARE?).=0A=
>>=0A=
>> Sure, I'll reword it! The broader question, however, is this correct for=
non-=0A=
>> Linux/non-DPDK PF drivers?=0A=
>> For FreeBSD I'll dig into the code, but for VMWARE (and I'd assume Micro=
soft=0A=
>> Windows) it'll be harder.=0A=
>>=0A=
>> Do you have any insights on the behavior for the non-open i40e PF driver=
s?=0A=
>>=0A=
>> From the documentation [1], it's unclear whether non-Linux/non-DPDK PF=
=0A=
>> drivers are supported. My interpretation was that only DPDK and Linux PF=
=0A=
>> hosts are supported for Fortville NICs.=0A=
> I guess only DPDK is different, though I am not sure.=0A=
> As all other NIC drivers were developped by the same organization.=0A=
> Even assuming that FreeBSD supports both configuration, it will not be a =
problem,=0A=
> as DPDK just doesn't support, and nothing wrong.=0A=
=0A=
I verified against the FreeBSD ixl-1.4.27 driver, and it=0A=
behaves (in terms of rxq crcstrip) the same way.=0A=
=0A=
It would be a problem if the non-Linux/non-DPDK drivers had=0A=
it (rx crcstrip) *disabled* by default. (Further, being able to=0A=
actually change the setting from a VF would be nice as well. :-))=0A=
This doesn't seem to be case, though.=0A=
=0A=
So, I'll change the wording from "Linux PF hosts" to "non-DPDK PF=0A=
host". Would that be OK?=0A=
=0A=
=0A=
Bj=F6rn=0A=