From: Filip Janiszewski <contact@filipjaniszewski.com>
To: "Van Haaren, Harry" <harry.van.haaren@intel.com>,
"Wiles, Keith" <keith.wiles@intel.com>
Cc: "users@dpdk.org" <users@dpdk.org>
Subject: Re: [dpdk-users] Segfault while running on older CPU
Date: Fri, 15 Feb 2019 06:45:06 +0100 [thread overview]
Message-ID: <c3d85797-65aa-947e-8b92-2370fb44d6e9@filipjaniszewski.com> (raw)
In-Reply-To: <E923DB57A917B54B9182A2E928D00FA6757E0F48@IRSMSX102.ger.corp.intel.com>
Il 14/02/19 15:46, Van Haaren, Harry ha scritto:
>> -----Original Message-----
>> From: users [mailto:users-bounces@dpdk.org] On Behalf Of Filip Janiszewski
>> Sent: Thursday, February 14, 2019 2:15 PM
>> To: Wiles, Keith <keith.wiles@intel.com>
>> Cc: users@dpdk.org
>> Subject: Re: [dpdk-users] Segfault while running on older CPU
>>
>> Hi,
>>
>> I prepared a simple test application with only a call to rte_eal_init
>> and it crashes, DPDK version is 18.05 and apparently the problem is with
>> the BMI2 instruction set, the faulty line is:
>>
>> .
>> │0x57fec9 <rte_cpu_get_flag_enabled+89> shrx %eax,%edx,%eax
>> .
>>
>> I'm attempting to disable those instructions by setting march to corei7
>> which according to gcc does not include BMI2, but still when opening the
>> asm list of the binary can see that instruction.
>>
>> If I understand correctly how the DPDK building process works then I
>> should be able to set this 'corei7' switch by just changing
>> mk/machine/default/rte.vars.mk and then setting
>> CONFIG_RTE_MACHINE="default" in the x86_64-native-linuxapp-gcc/.config
>> file, but I'm not sure whether it's picking it up while building (make
>> T=x86_64-native-linuxapp-gcc DESTDIR=. -j28).
>
>
> Possibly related crashing bugs;
>
> DPDK rte memcpy / binutils 2.30:
> https://bugs.dpdk.org/show_bug.cgi?id=97#c48
>
> Gcc bug report;
> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88096
> And a related/duplicate: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=86735
>
>
> Please check if you're using binutils 2.30, and if so try latest DPDK code which has
> merged a fix for disabling certain features as a workaround.
>
I'm running version 2.27, will try to upgrade to the latest DPDK code
and check if things are getting fixed.
> As Keith mentioned, what OS / Distro / Release, and what version of gcc / binutils is in use?
>
OS CentOS 7.5.1804 with 3.10.0-862.14.4.el7.x86_64, gcc 4.8.5 (20150623)
and binutils 2.27.
Thanks.
>
> Regards, -Harry
>
>
> <snip previous discussion>
>
--
BR, Filip
+48 666 369 823
prev parent reply other threads:[~2019-02-15 5:45 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-02-06 10:47 Filip Janiszewski
2019-02-14 13:04 ` Filip Janiszewski
2019-02-14 13:34 ` Wiles, Keith
2019-02-14 14:15 ` Filip Janiszewski
2019-02-14 14:46 ` Van Haaren, Harry
2019-02-15 5:45 ` Filip Janiszewski [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=c3d85797-65aa-947e-8b92-2370fb44d6e9@filipjaniszewski.com \
--to=contact@filipjaniszewski.com \
--cc=harry.van.haaren@intel.com \
--cc=keith.wiles@intel.com \
--cc=users@dpdk.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).