<feed xmlns='http://www.w3.org/2005/Atom'>
<title>kernel/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c, branch linux-5.1.y</title>
<subtitle>Hosts the 0x221E linux distro kernel.</subtitle>
<id>https://universe.0xinfinity.dev/distro/kernel/atom?h=linux-5.1.y</id>
<link rel='self' href='https://universe.0xinfinity.dev/distro/kernel/atom?h=linux-5.1.y'/>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/'/>
<updated>2018-09-12T21:28:28Z</updated>
<entry>
<title>drm/amdgpu: try allocating VRAM as power of two</title>
<updated>2018-09-12T21:28:28Z</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2018-09-07T12:27:05Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=433ca054949a6c9daac0ace1be5c33b25092bffa'/>
<id>urn:sha1:433ca054949a6c9daac0ace1be5c33b25092bffa</id>
<content type='text'>
Try to allocate VRAM in power of two sizes and only fallback to vram
split sizes if that fails.

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Felix Kuehling &lt;felix.kuehling@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: Keep track of amount of pinned CPU visible VRAM</title>
<updated>2018-07-13T19:46:11Z</updated>
<author>
<name>Michel Dänzer</name>
<email>michel.daenzer@amd.com</email>
</author>
<published>2018-07-11T10:06:31Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=ddc21af4d0f37f42b33c54cb69b215997fe5b082'/>
<id>urn:sha1:ddc21af4d0f37f42b33c54cb69b215997fe5b082</id>
<content type='text'>
Instead of CPU invisible VRAM. Preparation for the following, no
functional change intended.

v2:
* Also change amdgpu_vram_mgr_bo_invisible_size to
  amdgpu_vram_mgr_bo_visible_size, allowing further simplification
  (Christian König)

Cc: stable@vger.kernel.org
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>
</entry>
<entry>
<title>drm/amdgpu: Use gmc_vram_full_visible in vram_mgr_bo_invisible_size</title>
<updated>2018-07-05T21:39:49Z</updated>
<author>
<name>Michel Dänzer</name>
<email>michel.daenzer@amd.com</email>
</author>
<published>2018-06-15T14:37:03Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=9735bf1930e658b074d72ea46bb317ad12483692'/>
<id>urn:sha1:9735bf1930e658b074d72ea46bb317ad12483692</id>
<content type='text'>
Signed-off-by: Michel Dänzer &lt;michel.daenzer@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: Make amdgpu_vram_mgr_bo_invisible_size always accurate</title>
<updated>2018-06-19T18:51:45Z</updated>
<author>
<name>Michel Dänzer</name>
<email>michel.daenzer@amd.com</email>
</author>
<published>2018-06-14T11:02:07Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=7303b39e46b2f523334591f05fd9566cf929eb26'/>
<id>urn:sha1:7303b39e46b2f523334591f05fd9566cf929eb26</id>
<content type='text'>
Even BOs with AMDGPU_GEM_CREATE_NO_CPU_ACCESS may end up at least
partially in CPU visible VRAM, in particular when all VRAM is visible.

v2:
* Don't take VRAM mgr spinlock, not needed (Christian König)
* Make loop logic simpler and clearer.

Cc: stable@vger.kernel.org
Signed-off-by: Michel Dänzer &lt;michel.daenzer@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: Refactor amdgpu_vram_mgr_bo_invisible_size helper</title>
<updated>2018-06-19T18:51:22Z</updated>
<author>
<name>Michel Dänzer</name>
<email>michel.daenzer@amd.com</email>
</author>
<published>2018-06-12T10:07:33Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=5e9244ff585239630f15f8ad8e676bc91a94ca9e'/>
<id>urn:sha1:5e9244ff585239630f15f8ad8e676bc91a94ca9e</id>
<content type='text'>
Preparation for the following fix, no functional change intended.

Cc: stable@vger.kernel.org
Signed-off-by: Michel Dänzer &lt;michel.daenzer@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: Use kvmalloc_array for allocating VRAM manager nodes array</title>
<updated>2018-06-19T17:43:27Z</updated>
<author>
<name>Michel Dänzer</name>
<email>michel.daenzer@amd.com</email>
</author>
<published>2018-06-08T10:58:15Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=6fa39bc1e01dab8b4f54b23e95a181a2ed5a2d38'/>
<id>urn:sha1:6fa39bc1e01dab8b4f54b23e95a181a2ed5a2d38</id>
<content type='text'>
It can be quite big, and there's no need for it to be physically
contiguous. This is less likely to fail under memory pressure (has
actually happened while running piglit).

Cc: stable@vger.kernel.org
Signed-off-by: Michel Dänzer &lt;michel.daenzer@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: move struct amdgpu_mc into amdgpu_gmc.h</title>
<updated>2018-02-19T19:17:43Z</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2018-01-12T13:52:22Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=770d13b19fdf365a99e559f1d47f1380910a947d'/>
<id>urn:sha1:770d13b19fdf365a99e559f1d47f1380910a947d</id>
<content type='text'>
And rename it to amdgpu_gmc as well.

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Samuel Li &lt;Samuel.Li@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu:fix memleak in takedown</title>
<updated>2017-11-16T18:35:48Z</updated>
<author>
<name>Monk Liu</name>
<email>Monk.Liu@amd.com</email>
</author>
<published>2017-11-14T08:48:06Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=9ee8ecbb3eafeb1a899eaba1329ba3c4c092b754'/>
<id>urn:sha1:9ee8ecbb3eafeb1a899eaba1329ba3c4c092b754</id>
<content type='text'>
this can fix the memory leak under the case that not all
BO are freed during "takedown" stage, because originally
it blocks following kfree on mgr.

Signed-off-by: Monk Liu &lt;Monk.Liu@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: move vram usage tracking into the vram manager v2</title>
<updated>2017-08-17T19:46:03Z</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2017-08-07T15:46:49Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=3c848bb38aca1f7fd23edeb867b89d714a2e6ce2'/>
<id>urn:sha1:3c848bb38aca1f7fd23edeb867b89d714a2e6ce2</id>
<content type='text'>
Looks like a better place for this.

v2: use atomic64_t members instead

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>
</entry>
<entry>
<title>drm/amdgpu: move debug print into the MM managers</title>
<updated>2017-08-17T19:46:01Z</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2017-08-07T13:47:51Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=97cbb28451c21212cc20f2a5e6c074ba33150c3d'/>
<id>urn:sha1:97cbb28451c21212cc20f2a5e6c074ba33150c3d</id>
<content type='text'>
Instead of the separate switch/case in the calling function.

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>
</entry>
</feed>
