<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
</head>
<body>
Well you could remove it locally if it solves your problem at hand.<br>
<br>
But keep in mind that a lot of ARM boards are simply not compliant
to the PCIe specification and the hardware won't work correctly on
those in general.<br>
<br>
I'm pretty sure you have one of those cases here.<br>
<br>
Christian.<br>
<br>
<div class="moz-cite-prefix">Am 30.09.21 um 03:26 schrieb 李真能:<br>
</div>
<blockquote type="cite"
cite="mid:dc3c0e5c-a1cf-4d98-030a-967bad2c8d01@kylinos.cn">
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<p>So, Can I remove suspend process in amdgpu_pci_shutdown if I
don't use amdgpu driver in vm?</p>
<p><span id="tran_0_0" class="">Thank you so much for</span><span>
your </span><span id="tran_0_1" class="">reply</span><span>!</span></p>
<div class="moz-cite-prefix">在 2021/9/30 上午5:12, Alex Deucher 写道:<br>
</div>
<blockquote type="cite"
cite="mid:CADnq5_MC4XPWcgT0FE5mmghZD9+YPaaAXPAkzUjFEO-hxr20Eg@mail.gmail.com">
<pre class="moz-quote-pre" wrap="">On Wed, Sep 29, 2021 at 3:25 AM 李真能 <a class="moz-txt-link-rfc2396E" href="mailto:lizhenneng@kylinos.cn" moz-do-not-send="true"><lizhenneng@kylinos.cn></a> wrote:
</pre>
<blockquote type="cite">
<pre class="moz-quote-pre" wrap="">Hello:
When I do loop auto test of reboot, I found kernel may halt
on memcpy_fromio of amdgpu's amdgpu_uvd_suspend, so I remove suspend
process in amdgpu_pci_shutdown, and it will fix this bug.
I have 3 questions to ask:
1. In amdgpu_pci_shutdown, the comment explains why we must execute
suspend, so I know VM will call amdgpu driver in which situations, as I
know, VM's graphics card is a virtual card;
2. I see a path that is commited by Alex Deucher, the commit message is
as follows:
drm/amdgpu: just suspend the hw on pci shutdown
We can't just reuse pci_remove as there may be userspace still
doing things.
My question is:In which situations, there may be userspace till doing
things.
3. Why amdgpu driver is halted on memcpy_fromio of amdgpu_uvd_suspend, I
haven't launch any video app during reboot test, is it the bug of pci bus?
Test environment:
CPU: arm64
</pre>
</blockquote>
<pre class="moz-quote-pre" wrap="">I suspect the problem is something ARM specific. IIRC, we added the
memcpy_fromio() to work around a limitation in ARM related to CPU
mappings of PCI BAR memory. The whole point of the PCI shutdown
callback is to put the device into a quiescent state (e.g., stop all
DMAs and asynchronous engines, etc.). Some of that tear down requires
access to PCI BARs.
Alex
</pre>
<blockquote type="cite">
<pre class="moz-quote-pre" wrap="">Graphics card: r7340(amdgpu), rx550
OS: ubuntu 2004
</pre>
</blockquote>
</blockquote>
</blockquote>
<br>
</body>
</html>