<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux-toradex.git/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c, branch v6.16-rc5</title>
<subtitle>Linux kernel for Apalis and Colibri modules</subtitle>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/'/>
<entry>
<title>drm/amdgpu: disable workload profile switching when OD is enabled</title>
<updated>2025-06-03T19:04:24+00:00</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2025-05-27T14:13:31+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=5cccf10f652122a17b40df9d672ccf2ed69cd82f'/>
<id>5cccf10f652122a17b40df9d672ccf2ed69cd82f</id>
<content type='text'>
Users have reported that they have to reduce the level of undervolting
to acheive stability when dynamic workload profiles are enabled on
GC 10.3.x. Disable dynamic workload profiles if the user has enabled
OD.

Fixes: b9467983b774 ("drm/amdgpu: add dynamic workload profile switching for gfx10")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4262
Reviewed-by: Kenneth Feng &lt;kenneth.feng@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Cc: stable@vger.kernel.org # 6.15.x
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Users have reported that they have to reduce the level of undervolting
to acheive stability when dynamic workload profiles are enabled on
GC 10.3.x. Disable dynamic workload profiles if the user has enabled
OD.

Fixes: b9467983b774 ("drm/amdgpu: add dynamic workload profile switching for gfx10")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4262
Reviewed-by: Kenneth Feng &lt;kenneth.feng@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Cc: stable@vger.kernel.org # 6.15.x
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: Add Support for enforcing isolation without Cleaner Shader</title>
<updated>2025-05-05T17:29:53+00:00</updated>
<author>
<name>Srinivasan Shanmugam</name>
<email>srinivasan.shanmugam@amd.com</email>
</author>
<published>2025-04-28T10:46:34+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=68071eb0ae64c076ed93897be644ebbd1c89a278'/>
<id>68071eb0ae64c076ed93897be644ebbd1c89a278</id>
<content type='text'>
Adjusted the enforce isolation setting handling to include the ability
to disable the cleaner shader without affecting isolation between tasks.

v2: Updated enforce isolation documentation and parameters. (Alex)

Cc: Christian König &lt;christian.koenig@amd.com&gt;
Cc: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Srinivasan Shanmugam &lt;srinivasan.shanmugam@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>
Adjusted the enforce isolation setting handling to include the ability
to disable the cleaner shader without affecting isolation between tasks.

v2: Updated enforce isolation documentation and parameters. (Alex)

Cc: Christian König &lt;christian.koenig@amd.com&gt;
Cc: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Srinivasan Shanmugam &lt;srinivasan.shanmugam@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/amdgpu: remove DRM_AMDGPU_NAVI3X_USERQ config for UQ</title>
<updated>2025-04-30T22:06:00+00:00</updated>
<author>
<name>Arvind Yadav</name>
<email>Arvind.Yadav@amd.com</email>
</author>
<published>2025-04-22T13:59:03+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=56801cb83c8c95ae23ea576570c75a01c1f07774'/>
<id>56801cb83c8c95ae23ea576570c75a01c1f07774</id>
<content type='text'>
DRM_AMDGPU_NAVI3X_USERQ config support is not required for
usermode queue.

v2: rebase.

Cc: Arunpravin Paneer Selvam &lt;Arunpravin.PaneerSelvam@amd.com&gt;
Reviewed-by: Sunil Khatri &lt;sunil.khatri@amd.com&gt;
Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Arvind Yadav &lt;Arvind.Yadav@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>
DRM_AMDGPU_NAVI3X_USERQ config support is not required for
usermode queue.

v2: rebase.

Cc: Arunpravin Paneer Selvam &lt;Arunpravin.PaneerSelvam@amd.com&gt;
Reviewed-by: Sunil Khatri &lt;sunil.khatri@amd.com&gt;
Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Arvind Yadav &lt;Arvind.Yadav@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu/gfx: Introduce helpers handling CSB manipulation</title>
<updated>2025-04-30T22:04:29+00:00</updated>
<author>
<name>Rodrigo Siqueira</name>
<email>siqueira@igalia.com</email>
</author>
<published>2025-04-21T22:12:18+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=9718f7457dba2e98dab256217814296b5ad47ee4'/>
<id>9718f7457dba2e98dab256217814296b5ad47ee4</id>
<content type='text'>
From GFX6 to GFX11, there is a function for getting the CSB buffer to be
put into the hardware. Three common parts are duplicated in all of these
GFX functions:

1. Prepare the CSB preamble.
2. Parser the CS data.
3. End the CSB preamble.

This commit creates helpers to be used from GFX6 to GFX11.

Signed-off-by: Rodrigo Siqueira &lt;siqueira@igalia.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>
From GFX6 to GFX11, there is a function for getting the CSB buffer to be
put into the hardware. Three common parts are duplicated in all of these
GFX functions:

1. Prepare the CSB preamble.
2. Parser the CS data.
3. End the CSB preamble.

This commit creates helpers to be used from GFX6 to GFX11.

Signed-off-by: Rodrigo Siqueira &lt;siqueira@igalia.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: Disallow partition query during reset</title>
<updated>2025-04-30T22:03:02+00:00</updated>
<author>
<name>Lijo Lazar</name>
<email>lijo.lazar@amd.com</email>
</author>
<published>2025-04-16T06:53:44+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=75f138db48c5c493f0ac198c2579d52fc6a4c4a0'/>
<id>75f138db48c5c493f0ac198c2579d52fc6a4c4a0</id>
<content type='text'>
Reject queries to get current partition modes during reset. Also, don't
accept sysfs interface requests to switch compute partition mode while
in reset.

Signed-off-by: Lijo Lazar &lt;lijo.lazar@amd.com&gt;
Reviewed-by: Hawking Zhang &lt;Hawking.Zhang@amd.com&gt;
Reviewed-by: Asad Kamal &lt;asad.kamal@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>
Reject queries to get current partition modes during reset. Also, don't
accept sysfs interface requests to switch compute partition mode while
in reset.

Signed-off-by: Lijo Lazar &lt;lijo.lazar@amd.com&gt;
Reviewed-by: Hawking Zhang &lt;Hawking.Zhang@amd.com&gt;
Reviewed-by: Asad Kamal &lt;asad.kamal@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu/userq: integrate with enforce isolation</title>
<updated>2025-04-21T14:56:11+00:00</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2025-04-14T17:11:10+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=8f23a97907d92e16d34d4a2a9dc793398afa34a6'/>
<id>8f23a97907d92e16d34d4a2a9dc793398afa34a6</id>
<content type='text'>
Enforce isolation serializes access to the GFX IP.  User
queues are isolated in the MES scheduler, but we still
need to serialize between kernel queues and user queues.
For enforce isolation, group KGD user queues with KFD user
queues.

v2: split out variable renaming, add config guards
v3: use new function names

Reviewed-by: Sunil Khatri &lt;sunil.khatri@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>
Enforce isolation serializes access to the GFX IP.  User
queues are isolated in the MES scheduler, but we still
need to serialize between kernel queues and user queues.
For enforce isolation, group KGD user queues with KFD user
queues.

v2: split out variable renaming, add config guards
v3: use new function names

Reviewed-by: Sunil Khatri &lt;sunil.khatri@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: rename enforce isolation variables</title>
<updated>2025-04-21T14:56:06+00:00</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2025-02-21T20:20:45+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=28fc3172e4204c8cdd8c70226ea02b0ae9930b69'/>
<id>28fc3172e4204c8cdd8c70226ea02b0ae9930b69</id>
<content type='text'>
Since they will be used for both KFD and KGD user queues,
rename them from kfd to userq.  No intended functional
change.

Acked-by: Sunil Khatri &lt;sunil.khatri@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>
Since they will be used for both KFD and KGD user queues,
rename them from kfd to userq.  No intended functional
change.

Acked-by: Sunil Khatri &lt;sunil.khatri@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: adjust enforce_isolation handling</title>
<updated>2025-04-11T20:58:15+00:00</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2025-04-08T14:39:06+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=2e0454b730648e9349ca54eb4a8142d77e8e7008'/>
<id>2e0454b730648e9349ca54eb4a8142d77e8e7008</id>
<content type='text'>
Switch from a bool to an enum and allow more options
for enforce isolation.  There are now 3 modes of operation:
- Disabled (0)
- Enabled (serialization and cleaner shader) (1)
- Enabled in legacy mode (no serialization or cleaner shader) (2)
This provides better flexibility for more use cases.

Acked-by: Srinivasan Shanmugam &lt;srinivasan.shanmugam@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>
Switch from a bool to an enum and allow more options
for enforce isolation.  There are now 3 modes of operation:
- Disabled (0)
- Enabled (serialization and cleaner shader) (1)
- Enabled in legacy mode (no serialization or cleaner shader) (2)
This provides better flexibility for more use cases.

Acked-by: Srinivasan Shanmugam &lt;srinivasan.shanmugam@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: use a dummy owner for sysfs triggered cleaner shaders v4</title>
<updated>2025-04-11T20:52:33+00:00</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2025-03-28T17:58:17+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=8b2ae7d492675e8af8902f103364bef59382b935'/>
<id>8b2ae7d492675e8af8902f103364bef59382b935</id>
<content type='text'>
Otherwise triggering sysfs multiple times without other submissions in
between only runs the shader once.

v2: add some comment
v3: re-add missing cast
v4: squash in semicolon fix

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Srinivasan Shanmugam &lt;srinivasan.shanmugam@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>
Otherwise triggering sysfs multiple times without other submissions in
between only runs the shader once.

v2: add some comment
v3: re-add missing cast
v4: squash in semicolon fix

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Srinivasan Shanmugam &lt;srinivasan.shanmugam@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu/gfx: add generic handling for disable_kq</title>
<updated>2025-04-08T20:48:22+00:00</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2025-02-18T17:07:48+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=f091fa777b24c189523db1ea626434ad6ff29799'/>
<id>f091fa777b24c189523db1ea626434ad6ff29799</id>
<content type='text'>
Add proper checks for disable_kq functionality in
gfx helper functions.  Add special logic for families
that require the clear state setup.

v2: use ring count as per Felix suggestion
v3: fix num_gfx_rings handling in amdgpu_gfx_graphics_queue_acquire()
v4: fix error code (Alex)

Reviewed-by: Prike Liang &lt;Prike.Liang@amd.com&gt;
Reviewed-by: Sunil Khatri &lt;sunil.khatri@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>
Add proper checks for disable_kq functionality in
gfx helper functions.  Add special logic for families
that require the clear state setup.

v2: use ring count as per Felix suggestion
v3: fix num_gfx_rings handling in amdgpu_gfx_graphics_queue_acquire()
v4: fix error code (Alex)

Reviewed-by: Prike Liang &lt;Prike.Liang@amd.com&gt;
Reviewed-by: Sunil Khatri &lt;sunil.khatri@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</pre>
</div>
</content>
</entry>
</feed>
