<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h, branch v6.17</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=v6.17</id>
<link rel='self' href='https://git.shady.money/linux/atom?h=v6.17'/>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/'/>
<updated>2025-07-16T20:16:58Z</updated>
<entry>
<title>drm/amdgpu/vcn: add a helper framework for engine resets</title>
<updated>2025-07-16T20:16:58Z</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2025-06-16T20:01:25Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=7b6cde7f4e85d29f39779ff9cb7ed0203ad7e153'/>
<id>urn:sha1:7b6cde7f4e85d29f39779ff9cb7ed0203ad7e153</id>
<content type='text'>
With engine resets we reset all queues on the engine rather
than just a single queue.  Add a framework to handle this
similar to SDMA.

Reviewed-by: Sathishkumar S &lt;sathishkumar.sundararaju@amd.com&gt;
Tested-by: Sathishkumar S &lt;sathishkumar.sundararaju@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu/vcn: using separate VCN1_AON_SOC offset</title>
<updated>2025-05-07T22:23:40Z</updated>
<author>
<name>Ruijing Dong</name>
<email>ruijing.dong@amd.com</email>
</author>
<published>2025-05-02T15:19:26Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=b7e84fb708392b37e5dbb2a95db9b94a0e3f0aa2'/>
<id>urn:sha1:b7e84fb708392b37e5dbb2a95db9b94a0e3f0aa2</id>
<content type='text'>
VCN1_AON_SOC_ADDRESS_3_0 offset varies on different
VCN generations, the issue in vcn4.0.5 is caused by
a different VCN1_AON_SOC_ADDRESS_3_0 offset.

This patch does the following:

    1. use the same offset for other VCN generations.
    2. use the vcn4.0.5 special offset
    3. update vcn_4_0 and vcn_5_0

Acked-by: Saleemkhan Jamadar &lt;saleemkhan.jamadar@amd.com&gt;
Reviewed-by: Leo Liu &lt;leo.liu@amd.com&gt;
Signed-off-by: Ruijing Dong &lt;ruijing.dong@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
(cherry picked from commit 5c89ceda9984498b28716944633a9a01cbb2c90d)
Cc: stable@vger.kernel.org
</content>
</entry>
<entry>
<title>drm/amdgpu/vcn: fix ref counting for ring based profile handling</title>
<updated>2025-03-19T19:54:36Z</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2025-03-12T13:48:47Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=ca6575a32a37c1a3ebab904792bb415249481992'/>
<id>urn:sha1:ca6575a32a37c1a3ebab904792bb415249481992</id>
<content type='text'>
We need to make sure the workload profile ref counts are
balanced.  This isn't currently the case because we can
increment the count on submissions, but the decrement may
be delayed as work comes in.  Track when we enable the
workload profile so the references are balanced.

v2: switch to a mutex and active flag
v3: fix mutex init

Fixes: 1443dd3c67f6 ("drm/amd/pm: fix and simplify workload handling")
Cc: Yang Wang &lt;kevinyang.wang@amd.com&gt;
Cc: Kenneth Feng &lt;kenneth.feng@amd.com&gt;
Reviewed-by: Kenneth Feng &lt;kenneth.feng@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu/vcn: optimize firmware storage</title>
<updated>2025-02-27T20:52:32Z</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2025-01-07T17:16:28Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=c51aa7923e28f30519a16bf89ed3c4f27460835c'/>
<id>urn:sha1:c51aa7923e28f30519a16bf89ed3c4f27460835c</id>
<content type='text'>
If each instance uses the same fw image, only store one
copy in the driver.

Acked-by: Boyuan Zhang &lt;Boyuan.Zhang@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu/vcn: add a generic helper for set_power_gating_state</title>
<updated>2025-02-27T20:52:31Z</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2024-11-26T17:30:30Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=a2cf2a883c24ed582d829fc8ea6b4f5f09dc7b49'/>
<id>urn:sha1:a2cf2a883c24ed582d829fc8ea6b4f5f09dc7b49</id>
<content type='text'>
It's common for all VCN variants.

Reviewed-by: Boyuan Zhang &lt;Boyuan.Zhang@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu/vcn: add new per instance callback for powergating</title>
<updated>2025-02-27T20:52:30Z</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2024-11-26T16:27:06Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=55945f08d9b7a13f92a6fb7f681b95c031627a1a'/>
<id>urn:sha1:55945f08d9b7a13f92a6fb7f681b95c031627a1a</id>
<content type='text'>
This is per instance so add a new function pointer for it.

Reviewed-by: Boyuan Zhang &lt;Boyuan.Zhang@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu/vcn: adjust pause_dpg_mode function signature</title>
<updated>2025-02-27T20:52:30Z</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2024-11-26T16:14:58Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=64303b72de787b61a7d295d6973f5fbd955b85a5'/>
<id>urn:sha1:64303b72de787b61a7d295d6973f5fbd955b85a5</id>
<content type='text'>
Change it to take a vcn instance rather than adev to align
with the vcn instance changes.

TODO: clean up the function internals to use the vinst state
directly rather than accessing it indirectly via adev-&gt;vcn.inst[].

Reviewed-by: Boyuan Zhang &lt;Boyuan.Zhang@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu/vcn: switch vcn helpers to be instance based</title>
<updated>2025-02-27T20:52:29Z</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2024-11-15T22:44:01Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=f98675638f0a818a2eb802103b1e140b091358c4'/>
<id>urn:sha1:f98675638f0a818a2eb802103b1e140b091358c4</id>
<content type='text'>
Pass the instance to the helpers.

Reviewed-by: Boyuan Zhang &lt;Boyuan.Zhang@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu/vcn: move more instanced data to vcn_instance</title>
<updated>2025-02-27T20:52:29Z</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2024-11-15T21:19:23Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=cb107271687d569c3b706b974bcae6b9fdcfe9d0'/>
<id>urn:sha1:cb107271687d569c3b706b974bcae6b9fdcfe9d0</id>
<content type='text'>
Move more per instance data into the per instance structure.

v2: index instances directly on vcn1.0 and 2.0 to make
it clear that they only support a single instance (Lijo)
v3: fix typo on vcn 2.5

Reviewed-by: Boyuan Zhang &lt;Boyuan.Zhang@amd.com&gt; (v2)
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu/vcn: make powergating status per instance</title>
<updated>2025-02-27T20:52:29Z</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2024-11-13T20:28:41Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=9bf9442051c0af835b683411d9ebc6a5036d4cbb'/>
<id>urn:sha1:9bf9442051c0af835b683411d9ebc6a5036d4cbb</id>
<content type='text'>
Store it per instance so we can track it per instance.

v2: index instances directly on vcn1.0 and 2.0 to make
it clear that they only support a single instance (Lijo)

Reviewed-by: Boyuan Zhang &lt;Boyuan.Zhang@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
</feed>
