<html>
    <head>
      <base href="https://bugs.freedesktop.org/">
    </head>
    <body><span class="vcard"><a class="email" href="mailto:christian.ehrhardt@canonical.com" title="Christian Ehrhardt <christian.ehrhardt@canonical.com>"> <span class="fn">Christian Ehrhardt</span></a>
</span> changed
          <a class="bz_bug_link 
          bz_status_RESOLVED  bz_closed"
   title="RESOLVED FIXED - Crashes when using MDEV passthrough on i915"
   href="https://bugs.freedesktop.org/show_bug.cgi?id=110238">bug 110238</a>
          <br>
             <table border="1" cellspacing="0" cellpadding="8">
          <tr>
            <th>What</th>
            <th>Removed</th>
            <th>Added</th>
          </tr>

         <tr>
           <td style="text-align:right;">Status</td>
           <td>NEW
           </td>
           <td>RESOLVED
           </td>
         </tr>

         <tr>
           <td style="text-align:right;">Resolution</td>
           <td>---
           </td>
           <td>FIXED
           </td>
         </tr></table>
      <p>
        <div>
            <b><a class="bz_bug_link 
          bz_status_RESOLVED  bz_closed"
   title="RESOLVED FIXED - Crashes when using MDEV passthrough on i915"
   href="https://bugs.freedesktop.org/show_bug.cgi?id=110238#c4">Comment # 4</a>
              on <a class="bz_bug_link 
          bz_status_RESOLVED  bz_closed"
   title="RESOLVED FIXED - Crashes when using MDEV passthrough on i915"
   href="https://bugs.freedesktop.org/show_bug.cgi?id=110238">bug 110238</a>
              from <span class="vcard"><a class="email" href="mailto:christian.ehrhardt@canonical.com" title="Christian Ehrhardt <christian.ehrhardt@canonical.com>"> <span class="fn">Christian Ehrhardt</span></a>
</span></b>
        <pre>Hi,
thanks for your feedback.

I was experimenting more on the case actually and I found that sometimes it
just doesn not show up even after quite some time. But there was a way to
"force" the issue (which is on the host) from the guest.
To do so install opencl bits and try to use it, that would be:
 $ sudo apt install ocl-icd-libopencl1
 $ sudo apt install opencl-headers
 $ sudo apt install clinfo
 $ sudo apt install beignet
And then run clinfo
 $ clinfo
So far this triggered the bug immediately in all my tests.


With that set up to ensure I can actively trigger it I tried the suggested
intel_iommu=igfx_off.

That works like a charm in my setup - thanks!
With intel_iommu=igfx_off I can even run accelerated opencl load in the guest
on the mdev.

But since [1] states about that "If this fixes anything, please ensure you file
a bug reporting the problem." I think I might need to file a bug in a different
place - maybe for iommu itself then.

Thanks - we can close this bug and I'll look for a place to file that iommu
bug.

[1]: <a href="https://www.kernel.org/doc/Documentation/Intel-IOMMU.txt">https://www.kernel.org/doc/Documentation/Intel-IOMMU.txt</a></pre>
        </div>
      </p>


      <hr>
      <span>You are receiving this mail because:</span>

      <ul>
          <li>You are on the CC list for the bug.</li>
      </ul>
    </body>
</html>