<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c, branch v4.8-rc2</title>
<subtitle>Linux kernel source tree</subtitle>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/'/>
<entry>
<title>drm/ttm: Wait for a BO to become idle before unbinding it from GTT</title>
<updated>2016-08-05T17:37:02+00:00</updated>
<author>
<name>Michel Dänzer</name>
<email>michel.daenzer@amd.com</email>
</author>
<published>2016-08-05T09:36:10+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=34b58355ad1d9987267f071265a7de6c8e00662a'/>
<id>34b58355ad1d9987267f071265a7de6c8e00662a</id>
<content type='text'>
Fixes hangs under memory pressure, e.g. running the piglit test
tex3d-maxsize concurrently with other tests.

Fixes: 17d33bc9d6ef ("drm/ttm: drop waiting for idle in ttm_bo_evict.")
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-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>
Fixes hangs under memory pressure, e.g. running the piglit test
tex3d-maxsize concurrently with other tests.

Fixes: 17d33bc9d6ef ("drm/ttm: drop waiting for idle in ttm_bo_evict.")
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-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: add eviction counter</title>
<updated>2016-07-07T18:54:49+00:00</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2016-06-21T14:28:14+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=dbd5ed60ac856632609491229e6d7ad70115fb09'/>
<id>dbd5ed60ac856632609491229e6d7ad70115fb09</id>
<content type='text'>
Keep track of the number of evictions since boot.

Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Christian König &lt;christian.koenig@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>
Keep track of the number of evictions since boot.

Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: pipeline evictions as well</title>
<updated>2016-07-07T18:54:42+00:00</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2016-06-15T11:44:05+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=ce64bc25ef2542296d9bf905994c1647442d65d6'/>
<id>ce64bc25ef2542296d9bf905994c1647442d65d6</id>
<content type='text'>
This boosts Xonotic from 38fps to 47fps when artificially limiting VRAM to
256MB for testing. It should improve all CPU bound rendering situations
where we have a lot of swapping to/from VRAM.

Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Christian König &lt;christian.koenig@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>
This boosts Xonotic from 38fps to 47fps when artificially limiting VRAM to
256MB for testing. It should improve all CPU bound rendering situations
where we have a lot of swapping to/from VRAM.

Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/ttm: remove no_gpu_wait param from ttm_bo_move_accel_cleanup</title>
<updated>2016-07-07T18:54:39+00:00</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2016-06-15T11:44:00+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=74561cd4f128091f41ab698277cde2542dcc5cad'/>
<id>74561cd4f128091f41ab698277cde2542dcc5cad</id>
<content type='text'>
It isn't used and not waiting for the GPU after scheduling a move is
actually quite dangerous.

Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Christian König &lt;christian.koenig@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>
It isn't used and not waiting for the GPU after scheduling a move is
actually quite dangerous.

Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: remove pre move wait</title>
<updated>2016-07-07T18:54:38+00:00</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2016-06-06T08:17:59+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=99c44632d42c077ddd648025ad43f943fa034a43'/>
<id>99c44632d42c077ddd648025ad43f943fa034a43</id>
<content type='text'>
Not needed any more.

Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Christian König &lt;christian.koenig@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>
Not needed any more.

Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/ttm: wait for BO idle in ttm_bo_move_memcpy</title>
<updated>2016-07-07T18:54:35+00:00</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2016-06-06T08:17:54+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=77dfc28bad2c75493125ba8660e4c27c2dcdab57'/>
<id>77dfc28bad2c75493125ba8660e4c27c2dcdab57</id>
<content type='text'>
When we want to pipeline accelerated moves we need to wait in the fallback path.

Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Christian König &lt;christian.koenig@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 we want to pipeline accelerated moves we need to wait in the fallback path.

Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/ttm: add wait for idle in all drivers bo_move functions</title>
<updated>2016-07-07T18:54:35+00:00</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2016-06-06T08:17:53+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=88932a7be27d892aef21ff05428a55fefa091716'/>
<id>88932a7be27d892aef21ff05428a55fefa091716</id>
<content type='text'>
Wait for idle before moving the BO in all drivers implementing
an accelerated move function.

This should keep the current behavior when removing the pre move wait.

Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Christian König &lt;christian.koenig@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>
Wait for idle before moving the BO in all drivers implementing
an accelerated move function.

This should keep the current behavior when removing the pre move wait.

Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>Merge tag 'v4.6-rc7' into drm-next</title>
<updated>2016-05-09T03:49:56+00:00</updated>
<author>
<name>Dave Airlie</name>
<email>airlied@redhat.com</email>
</author>
<published>2016-05-09T03:49:56+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=bafb86f5bc3173479002555dea7f31d943b12332'/>
<id>bafb86f5bc3173479002555dea7f31d943b12332</id>
<content type='text'>
Merge this back as we've built up a fair few conflicts, and I have
some newer trees to pull in.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Merge this back as we've built up a fair few conflicts, and I have
some newer trees to pull in.
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: group BOs by log2 of the size on the LRU v2</title>
<updated>2016-05-05T00:23:08+00:00</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2016-04-15T15:19:16+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=29b3259a3ab98f4823f3227de1ae695f3f7bc751'/>
<id>29b3259a3ab98f4823f3227de1ae695f3f7bc751</id>
<content type='text'>
This allows us to have small BOs on the LRU before big ones.

v2: fix of by one and list corruption bug

Signed-off-by: Christian König &lt;christian.koenig@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>
This allows us to have small BOs on the LRU before big ones.

v2: fix of by one and list corruption bug

Signed-off-by: Christian König &lt;christian.koenig@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/ttm: implement LRU add callbacks v2</title>
<updated>2016-05-05T00:21:38+00:00</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2016-04-06T09:12:07+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=98c2872ae99bb7c9e8e4369cf48154f41dd6a109'/>
<id>98c2872ae99bb7c9e8e4369cf48154f41dd6a109</id>
<content type='text'>
This allows fine grained control for the driver where to add a BO into the LRU.

v2: fix typo in comment

Reviewed-by: Sinclair Yeh &lt;syeh@vmware.com&gt;
Signed-off-by: Christian König &lt;christian.koenig@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>
This allows fine grained control for the driver where to add a BO into the LRU.

v2: fix typo in comment

Reviewed-by: Sinclair Yeh &lt;syeh@vmware.com&gt;
Signed-off-by: Christian König &lt;christian.koenig@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>
</feed>
