<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux/drivers/gpu/drm/amd, 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>2025-09-23T17:54:50Z</updated>
<entry>
<title>drm/amd/display: remove output_tf_change flag</title>
<updated>2025-09-23T17:54:50Z</updated>
<author>
<name>Melissa Wen</name>
<email>mwen@igalia.com</email>
</author>
<published>2025-09-01T21:51:05Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=41b1f9fcba62b06195e625bb88c1031102892439'/>
<id>urn:sha1:41b1f9fcba62b06195e625bb88c1031102892439</id>
<content type='text'>
Remove this flag as the driver stopped managing it individually since
commit a4056c2a6344 ("drm/amd/display: use HW hdr mult for brightness
boost"). After some back and forth it was reintroduced as a condition to
`set_output_transfer_func()` in [1]. Without direct management, this
flag only changes value when all surface update flags are set true on
UPDATE_TYPE_FULL with no output TF status meaning.

Fixes: bb622e0c0044 ("drm/amd/display: program output tf when required") [1]
Signed-off-by: Melissa Wen &lt;mwen@igalia.com&gt;
Reviewed-by: Alex Hung &lt;alex.hung@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
(cherry picked from commit 752e6f283ec59ae007aa15a93d5a4b2eefa8cec9)
</content>
</entry>
<entry>
<title>drm/amd/display: Init DCN35 clocks from pre-os HW values</title>
<updated>2025-09-23T17:54:43Z</updated>
<author>
<name>Leo Li</name>
<email>sunpeng.li@amd.com</email>
</author>
<published>2025-09-12T15:01:50Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=361ee85e980c16c9b9e236ccfac33014e8602485'/>
<id>urn:sha1:361ee85e980c16c9b9e236ccfac33014e8602485</id>
<content type='text'>
[Why]
We did not initialize dc clocks with boot-time hw values during init.
This lead to incorrect clock values in dc, causing `dcn35_update_clocks`
to make incorrect updates.

[How]
Correctly initialize DC with pre-os clk values from HW.
s/dump/save/ as that accurately reflects the purpose of the functions.

Fixes: 8774029f76b9 ("drm/amd/display: Add DCN35 CLK_MGR")
Reviewed-by: Aurabindo Pillai &lt;aurabindo.pillai@amd.com&gt;
Signed-off-by: Leo Li &lt;sunpeng.li@amd.com&gt;
Signed-off-by: Fangzhi Zuo &lt;Jerry.Zuo@amd.com&gt;
Signed-off-by: Ivan Lipski &lt;ivan.lipski@amd.com&gt;
Tested-by: Dan Wheeler &lt;daniel.wheeler@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
(cherry picked from commit d43cc4ea1f9d720ab4bf06806f79260bfe981508)
</content>
</entry>
<entry>
<title>drm/amd/display: Use mpc.preblend flag to indicate preblend</title>
<updated>2025-09-23T17:51:37Z</updated>
<author>
<name>Alvin Lee</name>
<email>Alvin.Lee2@amd.com</email>
</author>
<published>2025-09-09T20:03:08Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=1c3217dd557d4f04eb4c2afcd7c76de6b4d66ccb'/>
<id>urn:sha1:1c3217dd557d4f04eb4c2afcd7c76de6b4d66ccb</id>
<content type='text'>
[Description]
Modifications in per asic capability means mpc.preblend flag should be used
to indicate preblend. Update relevant paths to use this flag.

Fixes: 39923050615c ("drm/amd/display: Clear DPP 3DLUT Cap")
Reviewed-by: Dillon Varone &lt;dillon.varone@amd.com&gt;
Signed-off-by: Alvin Lee &lt;Alvin.Lee2@amd.com&gt;
Signed-off-by: Ivan Lipski &lt;ivan.lipski@amd.com&gt;
Tested-by: Dan Wheeler &lt;daniel.wheeler@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
(cherry picked from commit 9e5d4a5e27c6dc4e1b4fc9d654d13de12b8ce156)
Cc: stable@vger.kernel.org
</content>
</entry>
<entry>
<title>drm/amd/display: Only restore backlight after amdgpu_dm_init or dm_resume</title>
<updated>2025-09-23T17:51:20Z</updated>
<author>
<name>Matthew Schwartz</name>
<email>matthew.schwartz@linux.dev</email>
</author>
<published>2025-09-11T17:48:51Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=44b0fed0a5947f54fd14255cd0766df952267bc5'/>
<id>urn:sha1:44b0fed0a5947f54fd14255cd0766df952267bc5</id>
<content type='text'>
On clients that utilize AMD_PRIVATE_COLOR properties for HDR support,
brightness sliders can include a hardware controlled portion and a
gamma-based portion. This is the case on the Steam Deck OLED when using
gamescope with Steam as a client.

When a user sets a brightness level while HDR is active, the gamma-based
portion and/or hardware portion are adjusted to achieve the desired
brightness. However, when a modeset takes place while the gamma-based
portion is in-use, restoring the hardware brightness level overrides the
user's overall brightness level and results in a mismatch between what
the slider reports and the display's current brightness.

To avoid overriding gamma-based brightness, only restore HW backlight
level after boot or resume. This ensures that the backlight level is
set correctly after the DC layer resets it while avoiding interference
with subsequent modesets.

Fixes: 7875afafba84 ("drm/amd/display: Fix brightness level not retained over reboot")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4551
Signed-off-by: Matthew Schwartz &lt;matthew.schwartz@linux.dev&gt;
Reviewed-by: Mario Limonciello &lt;mario.limonciello@amd.com&gt;
Signed-off-by: Mario Limonciello &lt;mario.limonciello@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
(cherry picked from commit a490c8d77d500b5981e739be3d59c60cfe382536)
Cc: stable@vger.kernel.org
</content>
</entry>
<entry>
<title>drm/amdgpu: suspend KFD and KGD user queues for S0ix</title>
<updated>2025-09-18T18:59:41Z</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2025-09-17T16:42:11Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=9272bb34b066993f5f468b219b4a26ba3f2b25a1'/>
<id>urn:sha1:9272bb34b066993f5f468b219b4a26ba3f2b25a1</id>
<content type='text'>
We need to make sure the user queues are preempted so
GFX can enter gfxoff.

Reviewed-by: Mario Limonciello (AMD) &lt;superm1@kernel.org&gt;
Tested-by: David Perry &lt;david.perry@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
(cherry picked from commit f8b367e6fa1716cab7cc232b9e3dff29187fc99d)
Cc: stable@vger.kernel.org
</content>
</entry>
<entry>
<title>drm/amdkfd: add proper handling for S0ix</title>
<updated>2025-09-18T18:59:24Z</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2025-09-17T16:42:09Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=2ade36eaa9ac05e4913e9785df19c2cde8f912fb'/>
<id>urn:sha1:2ade36eaa9ac05e4913e9785df19c2cde8f912fb</id>
<content type='text'>
When in S0i3, the GFX state is retained, so all we need to do
is stop the runlist so GFX can enter gfxoff.

Reviewed-by: Mario Limonciello (AMD) &lt;superm1@kernel.org&gt;
Tested-by: David Perry &lt;david.perry@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
(cherry picked from commit 4bfa8609934dbf39bbe6e75b4f971469384b50b1)
Cc: stable@vger.kernel.org
</content>
</entry>
<entry>
<title>drm/amd: Only restore cached manual clock settings in restore if OD enabled</title>
<updated>2025-09-16T21:58:34Z</updated>
<author>
<name>Mario Limonciello</name>
<email>mario.limonciello@amd.com</email>
</author>
<published>2025-09-16T01:59:02Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=f9b80514a7227c589291792cb6743b0ddf41c2bc'/>
<id>urn:sha1:f9b80514a7227c589291792cb6743b0ddf41c2bc</id>
<content type='text'>
If OD is not enabled then restoring cached clock settings doesn't make
sense and actually leads to errors in resume.

Check if enabled before restoring settings.

Fixes: 4e9526924d09 ("drm/amd: Restore cached manual clock settings during resume")
Reported-by: Jérôme Lécuyer &lt;jerome.4a4c@gmail.com&gt;
Closes: https://lore.kernel.org/amd-gfx/0ffe2692-7bfa-4821-856e-dd0f18e2c32b@amd.com/T/#me6db8ddb192626360c462b7570ed7eba0c6c9733
Suggested-by: Jérôme Lécuyer &lt;jerome.4a4c@gmail.com&gt;
Acked-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Mario Limonciello &lt;mario.limonciello@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
(cherry picked from commit 1a4dd33cc6e1baaa81efdbe68227a19f51c50f20)
Cc: stable@vger.kernel.org
</content>
</entry>
<entry>
<title>drm/amd/display: Allow RX6xxx &amp; RX7700 to invoke amdgpu_irq_get/put</title>
<updated>2025-09-15T21:24:42Z</updated>
<author>
<name>Ivan Lipski</name>
<email>ivan.lipski@amd.com</email>
</author>
<published>2025-09-02T20:20:09Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=29a2f430475357f760679b249f33e7282688e292'/>
<id>urn:sha1:29a2f430475357f760679b249f33e7282688e292</id>
<content type='text'>
[Why&amp;How]
As reported on https://gitlab.freedesktop.org/drm/amd/-/issues/3936,
SMU hang can occur if the interrupts are not enabled appropriately,
causing a vblank timeout.

This patch reverts commit 5009628d8509 ("drm/amd/display: Remove unnecessary
amdgpu_irq_get/put"), but only for RX6xxx &amp; RX7700 GPUs, on which the
issue was observed.

This will re-enable interrupts regardless of whether the user space needed
it or not.

Fixes: 5009628d8509 ("drm/amd/display: Remove unnecessary amdgpu_irq_get/put")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3936
Suggested-by: Sun peng Li &lt;sunpeng.li@amd.com&gt;
Reviewed-by: Sun peng Li &lt;sunpeng.li@amd.com&gt;
Signed-off-by: Ivan Lipski &lt;ivan.lipski@amd.com&gt;
Signed-off-by: Ray Wu &lt;ray.wu@amd.com&gt;
Tested-by: Daniel Wheeler &lt;daniel.wheeler@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
(cherry picked from commit 95d168b367aa28a59f94fc690ff76ebf69312c6d)
Cc: stable@vger.kernel.org
</content>
</entry>
<entry>
<title>drm/amdgpu/gfx11: Add Cleaner Shader Support for GFX11.0.1/11.0.4 GPUs</title>
<updated>2025-09-15T21:23:42Z</updated>
<author>
<name>Srinivasan Shanmugam</name>
<email>srinivasan.shanmugam@amd.com</email>
</author>
<published>2025-09-10T06:57:05Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=c1b6b8c7706354b73196649c46b5e6d4d61c2f5c'/>
<id>urn:sha1:c1b6b8c7706354b73196649c46b5e6d4d61c2f5c</id>
<content type='text'>
Enable the cleaner shader for additional GFX11.0.1/11.0.4 series GPUs to
ensure data isolation among GPU tasks. The cleaner shader is tasked with
clearing the Local Data Store (LDS), Vector General Purpose Registers
(VGPRs), and Scalar General Purpose Registers (SGPRs), which helps avoid
data leakage and guarantees the accuracy of computational results.

This update extends cleaner shader support to GFX11.0.1/11.0.4 GPUs,
previously available for GFX11.0.3. It enhances security by clearing GPU
memory between processes and maintains a consistent GPU state across KGD
and KFD workloads.

Cc: Wasee Alam &lt;wasee.alam@amd.com&gt;
Cc: Mario Sopena-Novales &lt;mario.novales@amd.com&gt;
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;
Acked-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
(cherry picked from commit 0a71ceb27f88a944c2de2808b67b2f46ac75076b)
</content>
</entry>
<entry>
<title>drm/amdgpu/vcn: Allow limiting ctx to instance 0 for AV1 at any time</title>
<updated>2025-09-09T20:42:26Z</updated>
<author>
<name>David Rosca</name>
<email>david.rosca@amd.com</email>
</author>
<published>2025-08-18T07:18:37Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=3318f2d20ce48849855df5e190813826d0bc3653'/>
<id>urn:sha1:3318f2d20ce48849855df5e190813826d0bc3653</id>
<content type='text'>
There is no reason to require this to happen on first submitted IB only.
We need to wait for the queue to be idle, but it can be done at any
time (including when there are multiple video sessions active).

Signed-off-by: David Rosca &lt;david.rosca@amd.com&gt;
Reviewed-by: Leo Liu &lt;leo.liu@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
(cherry picked from commit 8908fdce0634a623404e9923ed2f536101a39db5)
Cc: stable@vger.kernel.org
</content>
</entry>
</feed>
