<feed xmlns='http://www.w3.org/2005/Atom'>
<title>user/sven/linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h, branch v4.18.8</title>
<subtitle>Linux Kernel
</subtitle>
<id>https://git.stealer.net/cgit.cgi/user/sven/linux.git/atom?h=v4.18.8</id>
<link rel='self' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/atom?h=v4.18.8'/>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/'/>
<updated>2018-05-24T15:07:54Z</updated>
<entry>
<title>drm/amdgpu: move VM BOs on LRU again</title>
<updated>2018-05-24T15:07:54Z</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2018-04-19T13:01:12Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/commit/?id=806f043f0253a76248c554ce9f7303bc25e43314'/>
<id>urn:sha1:806f043f0253a76248c554ce9f7303bc25e43314</id>
<content type='text'>
Move all BOs belonging to a VM on the LRU with every submission.

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>
</entry>
<entry>
<title>drm/amdgpu: rework VM state machine lock handling v2</title>
<updated>2018-05-24T15:07:52Z</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2018-04-19T08:56:02Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/commit/?id=af4c0f650b563c7b30c1d8cd2bb926247ceb19cc'/>
<id>urn:sha1:af4c0f650b563c7b30c1d8cd2bb926247ceb19cc</id>
<content type='text'>
Only the moved state needs a separate spin lock protection. All other
states are protected by reserving the VM anyway.

v2: fix some more incorrect cases

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>
</entry>
<entry>
<title>drm/amdgpu: remove unused member</title>
<updated>2018-05-18T21:08:17Z</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2018-04-19T07:57:21Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/commit/?id=b9245b949885f24e84ae16d99d3898a5f1e0ba24'/>
<id>urn:sha1:b9245b949885f24e84ae16d99d3898a5f1e0ba24</id>
<content type='text'>
This lock isn't used any more.

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>
</entry>
<entry>
<title>drm/amdgpu: Add support to change mtype for 2nd part of gart BOs on GFX9</title>
<updated>2018-05-15T18:44:26Z</updated>
<author>
<name>Yong Zhao</name>
<email>yong.zhao@amd.com</email>
</author>
<published>2018-05-14T16:15:27Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/commit/?id=959a2091fae0fa498c79e095a4f6cbbb202a1194'/>
<id>urn:sha1:959a2091fae0fa498c79e095a4f6cbbb202a1194</id>
<content type='text'>
This change prepares for a workaround in amdkfd for a GFX9 HW bug. It
requires the control stack memory of compute queues, which is allocated
from the second page of MQD gart BOs, to have mtype NC, rather than
the default UC.

Signed-off-by: Yong Zhao &lt;yong.zhao@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: Add helper to turn an existing VM into a compute VM</title>
<updated>2018-03-15T21:27:42Z</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2018-03-15T21:27:42Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/commit/?id=b236fa1d339670cc997b68c31be57855bbabc126'/>
<id>urn:sha1:b236fa1d339670cc997b68c31be57855bbabc126</id>
<content type='text'>
v2: Removed updating and checking of vm-&gt;vm_context
v3: Enable amdgpu_vm_clear_bo in amdgpu_vm_make_compute

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: Move KFD-specific fields into struct amdgpu_vm</title>
<updated>2018-03-15T21:27:40Z</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2018-03-15T21:27:40Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/commit/?id=5b21d3e5fd2110df5a57a508188308351e698a5a'/>
<id>urn:sha1:5b21d3e5fd2110df5a57a508188308351e698a5a</id>
<content type='text'>
Remove struct amdkfd_vm and move the fields into struct amdgpu_vm.
This will allow turning a VM created by a DRM render node into a
KFD VM.

v2: Removed vm_context field

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: Fix header file dependencies</title>
<updated>2018-02-07T01:32:32Z</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2018-02-07T01:32:32Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/commit/?id=61b100e98f16e02df44862bba7798c7654b565f2'/>
<id>urn:sha1:61b100e98f16e02df44862bba7798c7654b565f2</id>
<content type='text'>
Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: reduce reserved VA size</title>
<updated>2018-02-19T19:18:29Z</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2018-01-22T10:17:18Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/commit/?id=18d09e63e09354f4ee3230ce2c9366de4e960476'/>
<id>urn:sha1:18d09e63e09354f4ee3230ce2c9366de4e960476</id>
<content type='text'>
1MB should be more than enough, currently we use about 8K.

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Acked-by: Monk Liu &lt;monk.liu@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: drop client_id from VM</title>
<updated>2017-12-27T16:34:09Z</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2017-12-18T16:10:01Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/commit/?id=0e36b9b2f99b17f2bfbf1d2dab1c2808f658d634'/>
<id>urn:sha1:0e36b9b2f99b17f2bfbf1d2dab1c2808f658d634</id>
<content type='text'>
Use the fence context from the scheduler entity.

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>
</entry>
<entry>
<title>drm/amdgpu: separate VMID and PASID handling</title>
<updated>2017-12-27T16:33:52Z</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2017-12-18T15:53:03Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/commit/?id=620f774f4687d86c420152309eefb0ef0fcc7e51'/>
<id>urn:sha1:620f774f4687d86c420152309eefb0ef0fcc7e51</id>
<content type='text'>
Move both into the new files amdgpu_ids.[ch]. No functional change.

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>
</entry>
</feed>
