<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>T-SeriesのトピックRe: PCIe Peer(SSD) to Peer(FPGA) Communication Error</title>
    <link>https://community.nxp.com/t5/T-Series/PCIe-Peer-SSD-to-Peer-FPGA-Communication-Error/m-p/894603#M3081</link>
    <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Please refer to "PCI Express error detect register (ERR_DR)", "PCI Express error capture status register (ERR_CAP_STAT)" and "PCI Express error capture register n (ERR_CAP_R0)" in T2080 Reference Manual.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;The PCI Express error detect register contains error status bits that are detected by hardware, it is &lt;SPAN&gt;0x80100000&lt;/SPAN&gt; indicates that Multiple errors were detected and A no-map transaction was detected in RC mode.&lt;/P&gt;&lt;P&gt;PCI Express no map. An inbound transaction that is not mapped to any inbound windows was detected.&lt;BR /&gt;In RC mode, a posted transaction will be dropped silently and this bit will be set. A nonposted transaction&lt;BR /&gt;will return a completion without data (Cpl) packet with a UR completion status to the requester and this bit&lt;BR /&gt;is set. For EP mode, a Cpl packet with a UR completion status is sent back to the requester but does not&lt;BR /&gt;set this bit.This bit is also set when an IO Write or IO Read transaction is received in RC mode and the&lt;BR /&gt;transaction is not hitting into IO Base/Limit registers.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Thanks,&lt;/P&gt;&lt;P&gt;Yiping&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
    <pubDate>Sun, 07 Jul 2019 10:51:06 GMT</pubDate>
    <dc:creator>yipingwang</dc:creator>
    <dc:date>2019-07-07T10:51:06Z</dc:date>
    <item>
      <title>PCIe Peer(SSD) to Peer(FPGA) Communication Error</title>
      <link>https://community.nxp.com/t5/T-Series/PCIe-Peer-SSD-to-Peer-FPGA-Communication-Error/m-p/894602#M3080</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;We make a T2080 custom board refer to T2080RDB-PC, we use PEX4 in RC mode and we have a PLX PCIe Switch PEX8764 in board,&amp;nbsp;&lt;A href="https://blog.csdn.net/Zhu_Zhu_2009/article/details/89084729"&gt;follow&amp;nbsp;is our pcie subsystem diagram&lt;/A&gt;:&lt;/P&gt;&lt;BLOCKQUOTE class="jive_macro_quote jive-quote jive_text_macro"&gt;&lt;P&gt;root@t2080rdb:~# lspci -tv&lt;BR /&gt;-[0000:00]---00.0-[01-0f]----00.0-[02-0f]--+-01.0-[03]--&lt;BR /&gt; +-02.0-[04]--&lt;BR /&gt; +-03.0-[05]--&lt;BR /&gt; +-04.0-[06]----00.0 Device 0731:8000&lt;BR /&gt; +-05.0-[07]----00.0 Device 0731:8000&lt;BR /&gt; +-08.0-[08]--&lt;BR /&gt; +-09.0-[09]----00.0 Samsung Electronics Co Ltd Device a808&lt;BR /&gt; +-0a.0-[0a]----00.0 Samsung Electronics Co Ltd Device a808&lt;BR /&gt; +-0b.0-[0b]--&lt;BR /&gt; +-0c.0-[0c]--&lt;BR /&gt; +-0d.0-[0d]--&lt;BR /&gt; +-0e.0-[0e]----00.0 Samsung Electronics Co Ltd Device a804&lt;BR /&gt; \-0f.0-[0f]----00.0 Samsung Electronics Co Ltd Device a804&lt;/P&gt;&lt;/BLOCKQUOTE&gt;&lt;P&gt;&lt;SPAN&gt;Device 0731:8000 is Xilinx Vertex7 FPGA, which has a 64MB BAR0, the other four devices is&amp;nbsp;Samsung NVMe SSD, follow are our system memory space allocation:&amp;nbsp;&lt;/SPAN&gt;&lt;/P&gt;&lt;BLOCKQUOTE&gt;&lt;P&gt;c40000000-c4fffffff : /pcie@ffe270000 c40000000-c4fffffff : PCI Bus 0000:01&lt;BR /&gt; c40000000-c407fffff : PCI Bus 0000:02&lt;BR /&gt; c40000000-c401fffff : PCI Bus 0000:03&lt;BR /&gt; c40200000-c403fffff : PCI Bus 0000:07&lt;BR /&gt; c40400000-c405fffff : PCI Bus 0000:09&lt;BR /&gt; c40600000-c407fffff : PCI Bus 0000:0d&lt;BR /&gt; c41000000-c4103ffff : 0000:01:00.0&lt;BR /&gt; c41100000-c463fffff : PCI Bus 0000:02&lt;BR /&gt; c41100000-c43ffffff : PCI Bus 0000:06&lt;BR /&gt; c42000000-c43ffffff : 0000:06:00.0&lt;BR /&gt; c42000000-c43ffffff : pcie_ep&lt;BR /&gt; c44000000-c45ffffff : PCI Bus 0000:07&lt;BR /&gt; c44000000-c45ffffff : 0000:07:00.0&lt;BR /&gt; c44000000-c45ffffff : pcie_ep&lt;BR /&gt; c46000000-c460fffff : PCI Bus 0000:09&lt;BR /&gt; c46000000-c46003fff : 0000:09:00.0&lt;BR /&gt; c46000000-c46003fff : nvme&lt;BR /&gt; c46100000-c461fffff : PCI Bus 0000:0a&lt;BR /&gt; c46100000-c46103fff : 0000:0a:00.0&lt;BR /&gt; c46100000-c46103fff : nvme&lt;BR /&gt; c46200000-c462fffff : PCI Bus 0000:0e&lt;BR /&gt; c46200000-c46203fff : 0000:0e:00.0&lt;BR /&gt; c46200000-c46203fff : nvme&lt;BR /&gt; c46300000-c463fffff : PCI Bus 0000:0f&lt;BR /&gt; c46300000-c46303fff : 0000:0f:00.0&lt;BR /&gt; c46300000-c46303fff : nvme&lt;/P&gt;&lt;/BLOCKQUOTE&gt;&lt;P&gt;&lt;SPAN&gt;now we want to&amp;nbsp;put Xilinx Vertex7 FPGA BAR0's data into SSD, BAR0's physical address is 0xc42000000, so we fire NVMe DMA&amp;nbsp;request to read 0x&lt;SPAN&gt;c42000000, we got follow message in T2080 console:&lt;/SPAN&gt;&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;BLOCKQUOTE class="jive_macro_quote jive-quote jive_text_macro"&gt;&lt;SPAN&gt;PCIe error(s) detected&lt;BR /&gt;PCIe ERR_DR register: 0x80100000&lt;BR /&gt;PCIe ERR_CAP_STAT register: 0x80000001&lt;BR /&gt;PCIe ERR_CAP_R0 register: 0x00000800&lt;BR /&gt;PCIe ERR_CAP_R1 register: 0x00000000&lt;BR /&gt;PCIe ERR_CAP_R2 register: 0x00000000&lt;BR /&gt;PCIe ERR_CAP_R3 register: 0x00000000&lt;/SPAN&gt;&lt;/BLOCKQUOTE&gt;&lt;P&gt;&lt;SPAN&gt;&lt;BR /&gt;When we write&amp;nbsp;0x&lt;SPAN&gt;c42000000,&amp;nbsp;we got follow message in T2080 console:&lt;/SPAN&gt;&lt;BR /&gt;&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;BLOCKQUOTE class="jive_macro_quote jive-quote jive_text_macro"&gt;&lt;SPAN&gt;PCIe error(s) detected&lt;BR /&gt;nvme 0000:09:00.0: async event result 00010300&lt;BR /&gt;PCIe ERR_DR register: 0x80100000&lt;BR /&gt;PCIe ERR_CAP_STAT register: 0x80000001&lt;BR /&gt;PCIe ERR_CAP_R0 register: 0x00000800&lt;BR /&gt;PCIe ERR_CAP_R1 register: 0x00000000&lt;BR /&gt;PCIe ERR_CAP_R2 register: 0x00000000&lt;BR /&gt;PCIe ERR_CAP_R3 register: 0x00000000&lt;BR /&gt;nvme 0000:09:00.0: Failed status: 3, reset controller&lt;BR /&gt;nvme 0000:09:00.0: Cancelling I/O 4 QID 2&lt;/SPAN&gt;&lt;/BLOCKQUOTE&gt;&lt;P&gt;&lt;SPAN&gt;&lt;BR /&gt;Then we check the T2080RM section&amp;nbsp;&lt;SPAN style="color: #4f4f4f; background-color: #ffffff;"&gt;20.4.36.4&lt;/SPAN&gt;, we got:&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;&lt;SPAN&gt;&lt;SPAN&gt;&lt;IMG alt="T2080" class="image-1 jive-image j-img-original" src="https://img-blog.csdnimg.cn/20190425160643826.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L1podV9aaHVfMjAwOQ==,size_16,color_FFFFFF,t_70" /&gt;&lt;/SPAN&gt;&lt;/SPAN&gt;&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;it seems like the PCIe&amp;nbsp;P2P Communication is failed, this is our question.&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Mon, 29 Apr 2019 03:28:53 GMT</pubDate>
      <guid>https://community.nxp.com/t5/T-Series/PCIe-Peer-SSD-to-Peer-FPGA-Communication-Error/m-p/894602#M3080</guid>
      <dc:creator>cezhu</dc:creator>
      <dc:date>2019-04-29T03:28:53Z</dc:date>
    </item>
    <item>
      <title>Re: PCIe Peer(SSD) to Peer(FPGA) Communication Error</title>
      <link>https://community.nxp.com/t5/T-Series/PCIe-Peer-SSD-to-Peer-FPGA-Communication-Error/m-p/894603#M3081</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;Please refer to "PCI Express error detect register (ERR_DR)", "PCI Express error capture status register (ERR_CAP_STAT)" and "PCI Express error capture register n (ERR_CAP_R0)" in T2080 Reference Manual.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;The PCI Express error detect register contains error status bits that are detected by hardware, it is &lt;SPAN&gt;0x80100000&lt;/SPAN&gt; indicates that Multiple errors were detected and A no-map transaction was detected in RC mode.&lt;/P&gt;&lt;P&gt;PCI Express no map. An inbound transaction that is not mapped to any inbound windows was detected.&lt;BR /&gt;In RC mode, a posted transaction will be dropped silently and this bit will be set. A nonposted transaction&lt;BR /&gt;will return a completion without data (Cpl) packet with a UR completion status to the requester and this bit&lt;BR /&gt;is set. For EP mode, a Cpl packet with a UR completion status is sent back to the requester but does not&lt;BR /&gt;set this bit.This bit is also set when an IO Write or IO Read transaction is received in RC mode and the&lt;BR /&gt;transaction is not hitting into IO Base/Limit registers.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Thanks,&lt;/P&gt;&lt;P&gt;Yiping&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Sun, 07 Jul 2019 10:51:06 GMT</pubDate>
      <guid>https://community.nxp.com/t5/T-Series/PCIe-Peer-SSD-to-Peer-FPGA-Communication-Error/m-p/894603#M3081</guid>
      <dc:creator>yipingwang</dc:creator>
      <dc:date>2019-07-07T10:51:06Z</dc:date>
    </item>
  </channel>
</rss>

