From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <mhall@mhcomputing.net>
Received: from mail.mhcomputing.net (master.mhcomputing.net [74.208.46.186])
 by dpdk.org (Postfix) with ESMTP id 5CE23B38D
 for <dev@dpdk.org>; Wed,  1 Jul 2015 07:49:30 +0200 (CEST)
Received: from [192.168.1.160] (99-34-229-174.lightspeed.sntcca.sbcglobal.net
 [99.34.229.174])
 by mail.mhcomputing.net (Postfix) with ESMTPSA id E821280B7BF;
 Tue, 30 Jun 2015 22:46:44 -0700 (PDT)
Content-Type: text/plain; charset=us-ascii
Mime-Version: 1.0 (Mac OS X Mail 7.3 \(1878.6\))
From: Matthew Hall <mhall@mhcomputing.net>
In-Reply-To: <C0759555-9A77-4AE2-B00F-79C123C0606C@mhcomputing.net>
Date: Tue, 30 Jun 2015 22:49:26 -0700
Content-Transfer-Encoding: quoted-printable
Message-Id: <E58B86F0-1853-4A30-AF1E-6FEF78CAEC48@mhcomputing.net>
References: <1A87AD2E-38CD-4C61-A9FD-C52608FF9DAC@mhcomputing.net>
 <39879033.dIVnPGkh8l@xps13> <386858255.20150629121137@intel.com>
 <2576181.dRfjlrHRWI@xps13>
 <F9A7424C-CB3A-44C2-9D2A-794C6E31B660@mhcomputing.net>
 <C0759555-9A77-4AE2-B00F-79C123C0606C@mhcomputing.net>
To: Thomas Monjalon <thomas.monjalon@6wind.com>
X-Mailer: Apple Mail (2.1878.6)
Cc: dev@dpdk.org
Subject: Re: [dpdk-dev] RTM instruction compile failure for XABORT when AVX
	is active
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: Wed, 01 Jul 2015 05:49:30 -0000

With those two items commented out, and these CFLAGS:

"-g -O0 -fPIC -msse4.2"

it looks like I can reproduce the issue in clang 2.6 series:

/vagrant/external/dpdk/build/include/rte_rtm.h:56:15: error: invalid =
operand for inline asm constraint 'i'
        asm volatile(".byte 0xc6,0xf8,%P0" :: "i" (status) : "memory");

So there are definitely some corner cases that seem to be able to =
trigger it.

On Jun 30, 2015, at 10:17 PM, Matthew Hall <mhall@mhcomputing.net> =
wrote:

> To be a bit more specific, this is what I had to do to fix it for =
clang 3.6 SVN snapshot release.
>=20
> I am not sure if there is a better way of handling this situation. I'd =
love to know where I could improve it.
>=20
> Matthew.
>=20
> diff --git a/mk/rte.cpuflags.mk b/mk/rte.cpuflags.mk
> index f595cd0..8c883ee 100644
> --- a/mk/rte.cpuflags.mk
> +++ b/mk/rte.cpuflags.mk
> @@ -77,13 +77,13 @@ ifneq ($(filter $(AUTO_CPUFLAGS),__RDRND__),)
> CPUFLAGS +=3D RDRAND
> endif
>=20
> -ifneq ($(filter $(AUTO_CPUFLAGS),__FSGSBASE__),)
> -CPUFLAGS +=3D FSGSBASE
> -endif
> +#ifneq ($(filter $(AUTO_CPUFLAGS),__FSGSBASE__),)
> +#CPUFLAGS +=3D FSGSBASE
> +#endif
>=20
> -ifneq ($(filter $(AUTO_CPUFLAGS),__F16C__),)
> -CPUFLAGS +=3D F16C
> -endif
> +#ifneq ($(filter $(AUTO_CPUFLAGS),__F16C__),)
> +#CPUFLAGS +=3D F16C
> +#endif
>=20
> ifneq ($(filter $(AUTO_CPUFLAGS),__AVX2__),)
> CPUFLAGS +=3D AVX2