<html>
    <head>
      <base href="https://bugs.freedesktop.org/">
    </head>
    <body><span class="vcard"><a class="email" href="mailto:yann.argotti@intel.com" title="yann <yann.argotti@intel.com>"> <span class="fn">yann</span></a>
</span> changed
          <a class="bz_bug_link 
          bz_status_NEW "
   title="NEW - [drm] GPU HANG: ecode 9:0:0x87f9bffb"
   href="https://bugs.freedesktop.org/show_bug.cgi?id=94022">bug 94022</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;">Product</td>
           <td>DRI
           </td>
           <td>Mesa
           </td>
         </tr>

         <tr>
           <td style="text-align:right;">Component</td>
           <td>DRM/Intel
           </td>
           <td>Drivers/DRI/i915
           </td>
         </tr>

         <tr>
           <td style="text-align:right;">Assignee</td>
           <td>intel-gfx-bugs@lists.freedesktop.org
           </td>
           <td>idr@freedesktop.org
           </td>
         </tr>

         <tr>
           <td style="text-align:right;">QA Contact</td>
           <td>intel-gfx-bugs@lists.freedesktop.org
           </td>
           <td>
                
           </td>
         </tr></table>
      <p>
        <div>
            <b><a class="bz_bug_link 
          bz_status_NEW "
   title="NEW - [drm] GPU HANG: ecode 9:0:0x87f9bffb"
   href="https://bugs.freedesktop.org/show_bug.cgi?id=94022#c6">Comment # 6</a>
              on <a class="bz_bug_link 
          bz_status_NEW "
   title="NEW - [drm] GPU HANG: ecode 9:0:0x87f9bffb"
   href="https://bugs.freedesktop.org/show_bug.cgi?id=94022">bug 94022</a>
              from <span class="vcard"><a class="email" href="mailto:yann.argotti@intel.com" title="yann <yann.argotti@intel.com>"> <span class="fn">yann</span></a>
</span></b>
        <pre>There were workarounds on SKL pushed in kernel (since the one you are using
4.5.0-994-generic), so please re-test with latest kernel and without using
i915.preliminary_hw_support=1 to see if it has some benefits on that work.

In parallel, assigning to Mesa product (please let me know if I am mistaken
with this GPU Hang).

>From this error dump, hung is happening in render ring batch with active head
at 0xfd47559c, with 0x78260000 (3DSTATE_BINDING_TABLE_POINTERS_VS) as IPEHR.

Batch extract (around 0xfd47559c):

0xfd475568:      0x78170009: 3D UNKNOWN: 3d_965 opcode = 0x7817
0xfd47556c:      0x00000000: MI_NOOP
0xfd475570:      0x00000001: MI_NOOP
0xfd475574:      0x00000000: MI_NOOP
0xfd475578:      0x00000000: MI_NOOP
0xfd47557c:      0x00000000: MI_NOOP
0xfd475580:      0x00000000: MI_NOOP
0xfd475584:      0xfd476960: UNKNOWN
0xfd475588:      0x00000000: MI_NOOP
0xfd47558c:      0x00000000: MI_NOOP
0xfd475590:      0x00000000: MI_NOOP
0xfd475594:      0x78260000: 3DSTATE_BINDING_TABLE_POINTERS_VS
0xfd475598:      0x000048e0:    dword 1
0xfd47559c:      0x782a0000: 3DSTATE_BINDING_TABLE_POINTERS_PS
0xfd4755a0:      0x000048c0:    dword 1
0xfd4755a4:      0x784a0000: 3D UNKNOWN: 3d_965 opcode = 0x784a
0xfd4755a8:      0x00000000: MI_NOOP
0xfd4755ac:      0x78080003: 3DSTATE_VERTEX_BUFFERS
0xfd4755b0:      0x00044018:    buffer 0: sequential, pitch 24b
0xfd4755b4:      0xfdd22000:    buffer address
0xfd4755b8:      0x00000000:    max index
0xfd4755bc:      0x00001000:    mbz</pre>
        </div>
        <div>
            <b><a class="bz_bug_link 
          bz_status_NEW "
   title="NEW - [drm] GPU HANG: ecode 9:0:0x87f9bffb"
   href="https://bugs.freedesktop.org/show_bug.cgi?id=94022#c5">Comment # 5</a>
              on <a class="bz_bug_link 
          bz_status_NEW "
   title="NEW - [drm] GPU HANG: ecode 9:0:0x87f9bffb"
   href="https://bugs.freedesktop.org/show_bug.cgi?id=94022">bug 94022</a>
              from <span class="vcard"><a class="email" href="mailto:yann.argotti@intel.com" title="yann <yann.argotti@intel.com>"> <span class="fn">yann</span></a>
</span></b>
        <pre>(In reply to Yuval Adam from <a href="show_bug.cgi?id=94022#c3">comment #3</a>)
<span class="quote">> This is likely a duplicate of ticket 94002 but it's good to get confirmation
> this is a widespread problem with Skylake graphics + hardware acceleration.

> FYI, i915.preliminary_hw_support=1 is useless in kernel >= 4.3.x since
> Skylake is no longer considered preliminary in those versions.</span >

right i915.preliminary_hw_support=1 shouldn't be used for SKL, but even both
94022 and 94002 have hung in batch render ring, it is happening on different
instruction and sequences.</pre>
        </div>
      </p>


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

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