<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux/drivers/gpu/drm/amd, branch v5.10</title>
<subtitle>Mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/
</subtitle>
<id>https://git.shady.money/linux/atom?h=v5.10</id>
<link rel='self' href='https://git.shady.money/linux/atom?h=v5.10'/>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/'/>
<updated>2020-12-10T03:38:10Z</updated>
<entry>
<title>drm/amd/pm: typo fix (CUSTOM -&gt; COMPUTE)</title>
<updated>2020-12-10T03:38:10Z</updated>
<author>
<name>Evan Quan</name>
<email>evan.quan@amd.com</email>
</author>
<published>2020-12-09T08:34:22Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=c5b58c8c860db330c0b8b891b69014ee9d470dab'/>
<id>urn:sha1:c5b58c8c860db330c0b8b891b69014ee9d470dab</id>
<content type='text'>
The "COMPUTE" was wrongly spelled as "CUSTOM".

Signed-off-by: Evan Quan &lt;evan.quan@amd.com&gt;
Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Cc: stable@vger.kernel.org # 5.9.x
</content>
</entry>
<entry>
<title>drm/amdgpu: Initialise drm_gem_object_funcs for imported BOs</title>
<updated>2020-12-09T15:06:40Z</updated>
<author>
<name>Andrey Grodzovsky</name>
<email>andrey.grodzovsky@amd.com</email>
</author>
<published>2020-12-08T20:16:15Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=ab43234d0bafcf2accd9db4fc4d193180b752f94'/>
<id>urn:sha1:ab43234d0bafcf2accd9db4fc4d193180b752f94</id>
<content type='text'>
For BOs imported from outside of amdgpu, setting of amdgpu_gem_object_funcs
was missing in amdgpu_dma_buf_create_obj. Fix by refactoring BO creation
and amdgpu_gem_object_funcs setting into single function called
from both code paths.

Fixes: d693def4fd1c ("drm: Remove obsolete GEM and PRIME callbacks from struct drm_driver")

v2: Use use amdgpu_gem_object_create() directly
v3: fix warning

Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Andrey Grodzovsky &lt;andrey.grodzovsky@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: fix size calculation with stolen vga memory</title>
<updated>2020-12-09T15:06:40Z</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2020-12-07T18:12:29Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=157fe68d74c2ad2db438c91af9ed3d3a51de4ed7'/>
<id>urn:sha1:157fe68d74c2ad2db438c91af9ed3d3a51de4ed7</id>
<content type='text'>
If we need to keep the stolen vga memory, make sure it is
at least as big as the legacy vga size.

Acked-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Cc: stable@vger.kernel.org
</content>
</entry>
<entry>
<title>drm/amd/pm: update smu10.h WORKLOAD_PPLIB setting for raven</title>
<updated>2020-12-09T15:06:40Z</updated>
<author>
<name>Changfeng</name>
<email>Changfeng.Zhu@amd.com</email>
</author>
<published>2020-12-07T07:42:29Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=c9918d1f63a3e77ec20997a77c997a6fa7282f2f'/>
<id>urn:sha1:c9918d1f63a3e77ec20997a77c997a6fa7282f2f</id>
<content type='text'>
When using old WORKLOAD_PPLIB setting in smu10.h, there is problem that
it can't be able to switch to mak gpu clk during compute workload.
It needs to update WORKLOAD_PPLIB setting to fix this issue.

Signed-off-by: Changfeng &lt;Changfeng.Zhu@amd.com&gt;
Reviewed-by: Huang Rui &lt;ray.huang@amd.com&gt;
Acked-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Cc: stable@vger.kernel.org
</content>
</entry>
<entry>
<title>drm/amdkfd: Fix leak in dmabuf import</title>
<updated>2020-12-09T15:06:39Z</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2020-12-08T17:23:15Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=ab6e4e9de8dd7febfdf6719741f10dc6693d8ce9'/>
<id>urn:sha1:ab6e4e9de8dd7febfdf6719741f10dc6693d8ce9</id>
<content type='text'>
Release dmabuf reference before returning from kfd_ioctl_import_dmabuf.
amdgpu_amdkfd_gpuvm_import_dmabuf takes a reference to the underlying
GEM BO and doesn't keep the reference to the dmabuf wrapper.

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Kent Russell &lt;kent.russell@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: fix sdma instance fw version and feature version init</title>
<updated>2020-12-09T15:06:39Z</updated>
<author>
<name>Stanley.Yang</name>
<email>Stanley.Yang@amd.com</email>
</author>
<published>2020-12-07T06:38:33Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=6896887b8676d8fb445c85ea56333b9661a6a8aa'/>
<id>urn:sha1:6896887b8676d8fb445c85ea56333b9661a6a8aa</id>
<content type='text'>
each sdma instance fw_version and feature_version
should be set right value when asic type isn't
between SIENNA_CICHILD and CHIP_DIMGREY_CAVEFISH

Signed-off-by: Stanley.Yang &lt;Stanley.Yang@amd.com&gt;
Reviewed-by: Tao Zhou &lt;tao.zhou1@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Cc: stable@vger.kernel.org
</content>
</entry>
<entry>
<title>drm/amd/display: Add wm table for Renoir</title>
<updated>2020-12-09T15:06:39Z</updated>
<author>
<name>Sung Lee</name>
<email>sung.lee@amd.com</email>
</author>
<published>2020-11-23T20:38:54Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=369b7ebe1792b620b7a9404e7b71daaae13ebfd6'/>
<id>urn:sha1:369b7ebe1792b620b7a9404e7b71daaae13ebfd6</id>
<content type='text'>
[Why]
Without additional HostVM Latency, Renoir takes 2us longer to exit
self-refresh. This causes underflow in certain cases.

[How]
Add table for Renoir with updated sr exit latencies for WM set A.

Signed-off-by: Sung Lee &lt;sung.lee@amd.com&gt;
Reviewed-by: Yongqiang Sun &lt;yongqiang.sun@amd.com&gt;
Reviewed-by: Roman Li &lt;Roman.Li@amd.com&gt;
Acked-by: Eryk Brol &lt;eryk.brol@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amd/display: Prevent bandwidth overflow</title>
<updated>2020-12-09T15:06:39Z</updated>
<author>
<name>Chris Park</name>
<email>Chris.Park@amd.com</email>
</author>
<published>2020-11-25T01:11:25Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=c2ffe78b8b1354603a7d5afb719b2a6dfbb582da'/>
<id>urn:sha1:c2ffe78b8b1354603a7d5afb719b2a6dfbb582da</id>
<content type='text'>
[Why]
At very high pixel clock, bandwidth calculation exceeds 32 bit size
and overflow value. This causes the resulting selection of link rate
to be inaccurate.

[How]
Change order of operation and use fixed point to deal with integer
accuracy. Also address bug found when forcing link rate.

Signed-off-by: Chris Park &lt;Chris.Park@amd.com&gt;
Reviewed-by: Wenjing Liu &lt;Wenjing.Liu@amd.com&gt;
Acked-by: Eryk Brol &lt;eryk.brol@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: fix debugfs creation/removal, again</title>
<updated>2020-12-09T15:06:39Z</updated>
<author>
<name>Arnd Bergmann</name>
<email>arnd@arndb.de</email>
</author>
<published>2020-12-03T23:06:43Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=2343e9d2c5a94459b9de92649f1650e36eb79a10'/>
<id>urn:sha1:2343e9d2c5a94459b9de92649f1650e36eb79a10</id>
<content type='text'>
There is still a warning when CONFIG_DEBUG_FS is disabled:

drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c:1145:13: error: 'amdgpu_ras_debugfs_create_ctrl_node' defined but not used [-Werror=unused-function]
 1145 | static void amdgpu_ras_debugfs_create_ctrl_node(struct amdgpu_device *adev)

Change the code again to make the compiler actually drop
this code but not warn about it.

Fixes: ae2bf61ff39e ("drm/amdgpu: guard ras debugfs creation/removal based on CONFIG_DEBUG_FS")
Reviewed-by: Tao Zhou &lt;tao.zhou1@amd.com&gt;
Signed-off-by: Arnd Bergmann &lt;arnd@arndb.de&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu/disply: set num_crtc earlier</title>
<updated>2020-12-09T15:03:59Z</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2020-12-03T21:06:26Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=578b6c487899179fed730e710ffec0b069917971'/>
<id>urn:sha1:578b6c487899179fed730e710ffec0b069917971</id>
<content type='text'>
To avoid a recently added warning:
 Bogus possible_crtcs: [ENCODER:65:TMDS-65] possible_crtcs=0xf (full crtc mask=0x7)
 WARNING: CPU: 3 PID: 439 at drivers/gpu/drm/drm_mode_config.c:617 drm_mode_config_validate+0x178/0x200 [drm]
In this case the warning is harmless, but confusing to users.

Fixes: 0df108237433 ("drm: Validate encoder-&gt;possible_crtcs")
Bug: https://bugzilla.kernel.org/show_bug.cgi?id=209123
Reviewed-by: Daniel Vetter &lt;daniel@ffwll.ch&gt;
Reviewed-by: Nicholas Kazlauskas &lt;nicholas.kazlauskas@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Cc: stable@vger.kernel.org
</content>
</entry>
</feed>
