<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body>
+ <a rel="noreferrer noopener" id="OWAAM000001" href="mailto:akozyrev@nvidia.com">
@Alexander Kozyrev</a> to suggest.
<div><br>
</div>
<div id="ms-outlook-mobile-signature" dir="rtl">קבל <a href="https://aka.ms/AAb9ysg">
Outlook עבור Android</a></div>
<hr style="display:inline-block;width:98%" tabindex="-1">
<div id="divRplyFwdMsg" dir="ltr"><font face="Calibri, sans-serif" style="font-size:11pt" color="#000000"><b>From:</b> Xiaoping Yan (NSB) <xiaoping.yan@nokia-sbell.com><br>
<b>Sent:</b> Monday, July 3, 2023 4:18:22 AM<br>
<b>To:</b> users@dpdk.org <users@dpdk.org>; Matan Azrad <matan@nvidia.com>; dekelp@nvidia.com <dekelp@nvidia.com><br>
<b>Subject:</b> RE: dpdk mlx5 driver crash in rxq_cq_decompress_v</font>
<div> </div>
</div>
<style>
<!--
@font-face
{font-family:宋体}
@font-face
{font-family:"Cambria Math"}
@font-face
{font-family:等线}
@font-face
{font-family:Calibri}
@font-face
{}
@font-face
{}
p.x_MsoNormal, li.x_MsoNormal, div.x_MsoNormal
{margin:0cm;
text-align:justify;
text-justify:inter-ideograph;
font-size:10.5pt;
font-family:等线}
a:link, span.x_MsoHyperlink
{color:#0563C1;
text-decoration:underline}
span.x_EmailStyle19
{font-family:等线;
color:windowtext}
.x_MsoChpDefault
{font-size:10.0pt}
@page WordSection1
{margin:72.0pt 90.0pt 72.0pt 90.0pt}
div.x_WordSection1
{}
-->
</style>
<div lang="ZH-CN" link="#0563C1" vlink="#954F72" style="word-wrap:break-word">
<table bgcolor="#FFEB9C" border="1">
<tbody>
<tr>
<td><font face="verdana" color="black" size="1"><b>External email: Use caution opening links or attachments</b>
</font></td>
</tr>
</tbody>
</table>
<br>
<div>
<div class="x_WordSection1">
<p class="x_MsoNormal"><span lang="EN-US">Hi,</span></p>
<p class="x_MsoNormal"><span lang="EN-US"> </span></p>
<p class="x_MsoNormal"><span lang="EN-US"><a id="OWAAM4F32193598C54B96899A7C78B433AACA" href="mailto:dekelp@nvidia.com"><span style="font-family:等线; text-decoration:none">@'dekelp@nvidia.com'</span></a><a id="OWAAM72C297E17CCC489B9901E36573FE6073" href="mailto:matan@nvidia.com"><span style="font-family:等线; text-decoration:none">@'Matan
Azrad'</span></a> Can you kindly suggest?</span></p>
<p class="x_MsoNormal"><span lang="EN-US">Thank you.</span></p>
<p class="x_MsoNormal"><span lang="EN-US"> </span></p>
<div>
<p class="x_MsoNormal"><span lang="EN-US">Br, Xiaoping</span></p>
</div>
<p class="x_MsoNormal"><span lang="EN-US"> </span></p>
<div>
<div style="border:none; border-top:solid #E1E1E1 1.0pt; padding:3.0pt 0cm 0cm 0cm">
<p class="x_MsoNormal" align="left" style="text-align:left"><b><span lang="EN-US" style="font-size:11.0pt; font-family:"Calibri",sans-serif">From:</span></b><span lang="EN-US" style="font-size:11.0pt; font-family:"Calibri",sans-serif"> Xiaoping Yan (NSB)
<br>
<b>Sent:</b> 2023</span><span style="font-size:11.0pt; font-family:宋体">年</span><span lang="EN-US" style="font-size:11.0pt; font-family:"Calibri",sans-serif">6</span><span style="font-size:11.0pt; font-family:宋体">月</span><span lang="EN-US" style="font-size:11.0pt; font-family:"Calibri",sans-serif">27</span><span style="font-size:11.0pt; font-family:宋体">日</span><span lang="EN-US" style="font-size:11.0pt; font-family:"Calibri",sans-serif">
12:11<br>
<b>To:</b> users@dpdk.org; 'Matan Azrad' <matan@nvidia.com>; 'dekelp@nvidia.com' <dekelp@nvidia.com><br>
<b>Subject:</b> dpdk mlx5 driver crash in rxq_cq_decompress_v</span></p>
</div>
</div>
<p class="x_MsoNormal" align="left" style="text-align:left"><span lang="EN-US"> </span></p>
<p class="x_MsoNormal"><span lang="EN-US">Hi,</span></p>
<p class="x_MsoNormal"><span lang="EN-US"> </span></p>
<p class="x_MsoNormal"><span lang="EN-US">dpdk version in use: 21.11.2</span></p>
<p class="x_MsoNormal"><span lang="EN-US"> </span></p>
<p class="x_MsoNormal"><span lang="EN-US">Mlx5 driver crashes in rxq_cq_decompress_v in traffic test after several minutes.</span></p>
<p class="x_MsoNormal"><span lang="EN-US">Stack trace:</span></p>
<p class="x_MsoNormal" style="margin-left:10.5pt"><i><span lang="EN-US">(gdb) bt</span></i></p>
<p class="x_MsoNormal" style="margin-left:10.5pt"><i><span lang="EN-US">#0 0x00007ffff58612bc in _mm_storeu_si128 (__B=..., __P=<optimized out>)</span></i></p>
<p class="x_MsoNormal" style="margin-left:10.5pt"><i><span lang="EN-US"> at /usr/lib/gcc/x86_64-redhat-linux/12/include/emmintrin.h:739</span></i></p>
<p class="x_MsoNormal" style="margin-left:10.5pt"><i><span lang="EN-US">#1 rxq_cq_decompress_v (rxq=rxq@entry=0x2abe5592f40, cq=cq@entry=0x2abe54fdb00, elts=elts@entry=0x2abe5594638)</span></i></p>
<p class="x_MsoNormal" style="margin-left:10.5pt"><i><span lang="EN-US"> at ../dpdk-21.11/drivers/net/mlx5/mlx5_rxtx_vec_sse.h:142</span></i></p>
<p class="x_MsoNormal" style="margin-left:10.5pt"><i><span lang="EN-US">#2 0x00007ffff5862c84 in rxq_burst_v (no_cq=<synthetic pointer>, err=0x7fffffffb848, pkts_n=4, pkts=<optimized out>,
</span></i></p>
<p class="x_MsoNormal" style="margin-left:10.5pt"><i><span lang="EN-US"> rxq=0x2abe5592f40) at ../dpdk-21.11/drivers/net/mlx5/mlx5_rxtx_vec.c:349</span></i></p>
<p class="x_MsoNormal" style="margin-left:10.5pt"><i><span lang="EN-US">#3 mlx5_rx_burst_vec (dpdk_rxq=0x2abe5592f40, pkts=0x7fffffffbf80, pkts_n=32) at ../dpdk-21.11/drivers/net/mlx5/mlx5_rxtx_vec.c:393</span></i></p>
<p class="x_MsoNormal" style="margin-left:10.5pt"><i><span lang="EN-US">#4 0x00005555556a0f41 in rte_eth_rx_burst (nb_pkts=32, rx_pkts=0x7fffffffbf80, queue_id=0, port_id=1)</span></i></p>
<p class="x_MsoNormal" style="margin-left:10.5pt"><i><span lang="EN-US"> at /usr/include/rte_ethdev.h:5721</span></i></p>
<p class="x_MsoNormal" style="margin-left:10.5pt"><i>…</i><span lang="EN-US"></span></p>
<p class="x_MsoNormal"><span lang="EN-US">Attached is the error log </span>“<span lang="EN-US">Unexpected CQE error syndrome</span>…”<span lang="EN-US"> and dump file</span></p>
<p class="x_MsoNormal"><span lang="EN-US"> </span></p>
<p class="x_MsoNormal"><span lang="EN-US">I found there was a similar bug here: <a href="https://bugs.dpdk.org/show_bug.cgi?id=334">
https://bugs.dpdk.org/show_bug.cgi?id=334</a></span></p>
<p class="x_MsoNormal"><span lang="EN-US">But the fix (88c0733535d6 extend Rx completion with error handling) should already been included, as I</span>’<span lang="EN-US">m using 21.11.2</span></p>
<p class="x_MsoNormal"><span lang="EN-US">Also below commit (fix to 88c0733535d6) is already included in my dpdk version.</span></p>
<p class="x_MsoNormal" style="margin-left:10.5pt"><i><span lang="EN-US">commit 60b254e3923d007bcadbb8d410f95ad89a2f13fa</span></i></p>
<p class="x_MsoNormal" style="margin-left:10.5pt"><i><span lang="EN-US">Author: Matan Azrad
<a href="mailto:matan@nvidia.com">matan@nvidia.com</a></span></i></p>
<p class="x_MsoNormal" style="margin-left:10.5pt"><i><span lang="EN-US">Date: Thu Aug 11 19:51:55 2022 +0300</span></i></p>
<p class="x_MsoNormal" style="margin-left:10.5pt"><i><span lang="EN-US"> </span></i></p>
<p class="x_MsoNormal" style="margin-left:10.5pt"><i><span lang="EN-US"> net/mlx5: fix Rx queue recovery mechanism</span></i><span lang="EN-US"></span></p>
<p class="x_MsoNormal"><span lang="EN-US"> </span></p>
<p class="x_MsoNormal"><span lang="EN-US">Any suggestion?</span></p>
<p class="x_MsoNormal"><span lang="EN-US">Thank you.</span></p>
<p class="x_MsoNormal"><span lang="EN-US"> </span></p>
<p class="x_MsoNormal"><span lang="EN-US">Br, Xiaoping</span></p>
<p class="x_MsoNormal"><span lang="EN-US"> </span></p>
</div>
</div>
</div>
</body>
</html>