<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux.git/drivers/gpu/drm/amd/amdgpu/tonga_ih.c, branch v4.20</title>
<subtitle>Linux kernel source tree</subtitle>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/'/>
<entry>
<title>drm/amdgpu: move more defines into amdgpu_irq.h</title>
<updated>2018-09-27T02:09:22+00:00</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2018-09-17T13:29:28+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=1ffdeca64856e0149e7fb341617f47cb038df543'/>
<id>1ffdeca64856e0149e7fb341617f47cb038df543</id>
<content type='text'>
Everything that isn't related to the IH ring.

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Huang Rui &lt;ray.huang@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Everything that isn't related to the IH ring.

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Huang Rui &lt;ray.huang@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: cleanup amdgpu_ih.c</title>
<updated>2018-09-27T02:09:21+00:00</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2018-09-16T18:13:21+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=425c31437f26436e17bdb3041a26e9864d18ba13'/>
<id>425c31437f26436e17bdb3041a26e9864d18ba13</id>
<content type='text'>
Cleanup amdgpu_ih.c to be able to handle multiple interrupt rings.

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Huang Rui &lt;ray.huang@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Cleanup amdgpu_ih.c to be able to handle multiple interrupt rings.

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Huang Rui &lt;ray.huang@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: make function pointers mandatory</title>
<updated>2018-09-27T02:09:21+00:00</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2018-09-17T13:41:45+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=f54b30d70bc606f7a154edba5883c7fa23838e9f'/>
<id>f54b30d70bc606f7a154edba5883c7fa23838e9f</id>
<content type='text'>
We always want those to be setup correctly.

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Huang Rui &lt;ray.huang@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
We always want those to be setup correctly.

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Huang Rui &lt;ray.huang@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: use the TTM dummy page instead of allocating one</title>
<updated>2018-02-27T04:09:36+00:00</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2018-02-22T07:35:11+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=92e71b0676447fff40c1e747b2585a9d11c5fca2'/>
<id>92e71b0676447fff40c1e747b2585a9d11c5fca2</id>
<content type='text'>
We have a global dummy page in TTM, use that one instead of allocating a
new one.

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Michel Dänzer &lt;michel.daenzer@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
We have a global dummy page in TTM, use that one instead of allocating a
new one.

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Michel Dänzer &lt;michel.daenzer@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: rename pas_id to pasid</title>
<updated>2018-02-19T19:17:41+00:00</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2018-01-09T18:47:37+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=3816e42f5f5ec6b96634b8ede3eaa77dbe4574fd'/>
<id>3816e42f5f5ec6b96634b8ede3eaa77dbe4574fd</id>
<content type='text'>
sed -i "s/pas_id/pasid/g" drivers/gpu/drm/amd/amdgpu/*.c
sed -i "s/pas_id/pasid/g" drivers/gpu/drm/amd/amdgpu/*.h

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Chunming Zhou &lt;david1.zhou@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
sed -i "s/pas_id/pasid/g" drivers/gpu/drm/amd/amdgpu/*.c
sed -i "s/pas_id/pasid/g" drivers/gpu/drm/amd/amdgpu/*.h

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Chunming Zhou &lt;david1.zhou@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: rename vm_id to vmid</title>
<updated>2017-12-27T16:34:02+00:00</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2017-12-18T16:08:25+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=c4f46f22c448ff571eb8fdbe4ab71a25805228d1'/>
<id>c4f46f22c448ff571eb8fdbe4ab71a25805228d1</id>
<content type='text'>
sed -i "s/vm_id/vmid/g" drivers/gpu/drm/amd/amdgpu/*.c
sed -i "s/vm_id/vmid/g" drivers/gpu/drm/amd/amdgpu/*.h

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Chunming Zhou &lt;david1.zhou@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
sed -i "s/vm_id/vmid/g" drivers/gpu/drm/amd/amdgpu/*.c
sed -i "s/vm_id/vmid/g" drivers/gpu/drm/amd/amdgpu/*.h

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Chunming Zhou &lt;david1.zhou@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: Handle GPUVM fault storms</title>
<updated>2017-09-28T20:03:30+00:00</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2017-09-21T20:26:41+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=c98171ccf6580407d07a3b5dc8188ce9e1f4f7ca'/>
<id>c98171ccf6580407d07a3b5dc8188ce9e1f4f7ca</id>
<content type='text'>
When many wavefronts cause VM faults at the same time, it can
overwhelm the interrupt handler and cause IH ring overflows before
the driver can notify or kill the faulting application.

As a workaround I'm introducing limited per-VM fault credit. After
that number of VM faults have occurred, further VM faults are
filtered out at the prescreen stage of processing.

This depends on the PASID in the interrupt packet, so it currently
only works for KFD contexts.

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
When many wavefronts cause VM faults at the same time, it can
overwhelm the interrupt handler and cause IH ring overflows before
the driver can notify or kill the faulting application.

As a workaround I'm introducing limited per-VM fault credit. After
that number of VM faults have occurred, further VM faults are
filtered out at the prescreen stage of processing.

This depends on the PASID in the interrupt packet, so it currently
only works for KFD contexts.

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: Add prescreening stage in IH processing (v2)</title>
<updated>2017-09-26T17:07:04+00:00</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2017-08-26T06:40:45+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=00ecd8a27c03b6dd463ab8755dd6d58751d76297'/>
<id>00ecd8a27c03b6dd463ab8755dd6d58751d76297</id>
<content type='text'>
To filter out high-frequency interrupts that can be safely ignored.

v2: squash in trivial typo fix for si (Alex)

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
To filter out high-frequency interrupts that can be safely ignored.

v2: squash in trivial typo fix for si (Alex)

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amd: fix include notation and remove -Iinclude/drm flag</title>
<updated>2017-05-16T15:17:41+00:00</updated>
<author>
<name>Masahiro Yamada</name>
<email>yamada.masahiro@socionext.com</email>
</author>
<published>2017-04-24T04:50:21+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=248a1d6f1ac410d3ed3907c1be2502e286f59bb8'/>
<id>248a1d6f1ac410d3ed3907c1be2502e286f59bb8</id>
<content type='text'>
Include &lt;drm/*.h&gt; instead of relative path from include/drm, then
remove the -Iinclude/drm compiler flag.

Signed-off-by: Masahiro Yamada &lt;yamada.masahiro@socionext.com&gt;
Reviewed-by: Michel Dänzer &lt;michel.daenzer@amd.com&gt;
Signed-off-by: Daniel Vetter &lt;daniel.vetter@ffwll.ch&gt;
Link: http://patchwork.freedesktop.org/patch/msgid/1493009447-31524-4-git-send-email-yamada.masahiro@socionext.com
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Include &lt;drm/*.h&gt; instead of relative path from include/drm, then
remove the -Iinclude/drm compiler flag.

Signed-off-by: Masahiro Yamada &lt;yamada.masahiro@socionext.com&gt;
Reviewed-by: Michel Dänzer &lt;michel.daenzer@amd.com&gt;
Signed-off-by: Daniel Vetter &lt;daniel.vetter@ffwll.ch&gt;
Link: http://patchwork.freedesktop.org/patch/msgid/1493009447-31524-4-git-send-email-yamada.masahiro@socionext.com
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: increase IH ring buffer size to avoid overflow</title>
<updated>2017-03-30T03:53:53+00:00</updated>
<author>
<name>Roger.He</name>
<email>Hongbo.He@amd.com</email>
</author>
<published>2017-03-14T08:47:30+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=8fb6e528c399e54e5e2621d71a1037ab8ed89478'/>
<id>8fb6e528c399e54e5e2621d71a1037ab8ed89478</id>
<content type='text'>
We originally limited the IH to 4k on tonga since it
uses bus addresses directly rather than GPU MC addresses,
so it needs contigous physical memory.  This brings it
inline with other asics.

Signed-off-by: Roger.He &lt;Hongbo.He@amd.com&gt;
Acked-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
We originally limited the IH to 4k on tonga since it
uses bus addresses directly rather than GPU MC addresses,
so it needs contigous physical memory.  This brings it
inline with other asics.

Signed-off-by: Roger.He &lt;Hongbo.He@amd.com&gt;
Acked-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
</feed>
