<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c, branch v6.14</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=v6.14</id>
<link rel='self' href='https://git.shady.money/linux/atom?h=v6.14'/>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/'/>
<updated>2025-01-09T05:48:50Z</updated>
<entry>
<title>Merge tag 'drm-misc-next-2025-01-06' of https://gitlab.freedesktop.org/drm/misc/kernel into drm-next</title>
<updated>2025-01-09T05:48:50Z</updated>
<author>
<name>Dave Airlie</name>
<email>airlied@redhat.com</email>
</author>
<published>2025-01-09T05:48:33Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=0739b8ba82276f6caac3e544eb6cc21c16d1ca9e'/>
<id>urn:sha1:0739b8ba82276f6caac3e544eb6cc21c16d1ca9e</id>
<content type='text'>
drm-misc-next for 6.14:

UAPI Changes:
- Clarify drm memory stats documentation

Cross-subsystem Changes:

Core Changes:
 - sched: Documentation fixes,

Driver Changes:
 - amdgpu: Track BO memory stats at runtime
 - amdxdna: Various fixes
 - hisilicon: New HIBMC driver
 - bridges:
   - Provide default implementation of atomic_check for HDMI bridges
   - it605: HDCP improvements, MCCS Support

Signed-off-by: Dave Airlie &lt;airlied@redhat.com&gt;

From: Maxime Ripard &lt;mripard@redhat.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20250106-augmented-kakapo-of-action-0cf000@houat
</content>
</entry>
<entry>
<title>drm/amdgpu: track bo memory stats at runtime</title>
<updated>2024-12-19T15:56:28Z</updated>
<author>
<name>Yunxiang Li</name>
<email>Yunxiang.Li@amd.com</email>
</author>
<published>2024-12-19T15:14:11Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=74ef9527bd87ead62deabe749a6d867af748d448'/>
<id>urn:sha1:74ef9527bd87ead62deabe749a6d867af748d448</id>
<content type='text'>
Before, every time fdinfo is queried we try to lock all the BOs in the
VM and calculate memory usage from scratch. This works okay if the
fdinfo is rarely read and the VMs don't have a ton of BOs. If either of
these conditions is not true, we get a massive performance hit.

In this new revision, we track the BOs as they change states. This way
when the fdinfo is queried we only need to take the status lock and copy
out the usage stats with minimal impact to the runtime performance. With
this new approach however, we would no longer be able to track active
buffers.

Signed-off-by: Yunxiang Li &lt;Yunxiang.Li@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20241219151411.1150-6-Yunxiang.Li@amd.com
Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: remove unused function parameter</title>
<updated>2024-12-19T15:56:25Z</updated>
<author>
<name>Yunxiang Li</name>
<email>Yunxiang.Li@amd.com</email>
</author>
<published>2024-12-19T15:14:10Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=a541a6e865ecd8dfd8df6eeb134cc20e7139d329'/>
<id>urn:sha1:a541a6e865ecd8dfd8df6eeb134cc20e7139d329</id>
<content type='text'>
amdgpu_vm_bo_invalidate doesn't use the adev parameter and not all
callers have a reference to adev handy, so remove it for cleanliness.

Signed-off-by: Yunxiang Li &lt;Yunxiang.Li@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20241219151411.1150-5-Yunxiang.Li@amd.com
Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: Update the variable name to dma_buf</title>
<updated>2024-12-10T15:26:48Z</updated>
<author>
<name>Sunil Khatri</name>
<email>sunil.khatri@amd.com</email>
</author>
<published>2024-11-21T17:32:11Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=093bbeb994af5ac3f3affdfd73983dcbd19d9a17'/>
<id>urn:sha1:093bbeb994af5ac3f3affdfd73983dcbd19d9a17</id>
<content type='text'>
Instead of fixing the warning for missing variable
its better to update the variable name to match
with the style followed in the code.

This will fix the below mentioned warning:
warning: Function parameter or struct member 'dbuf' not described in 'amdgpu_bo_create_isp_user'
warning: Excess function parameter 'dma_buf' description in 'amdgpu_bo_create_isp_user'

Signed-off-by: Sunil Khatri &lt;sunil.khatri@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/amd/amdgpu: Add support for isp buffers</title>
<updated>2024-12-10T15:26:45Z</updated>
<author>
<name>Pratap Nirujogi</name>
<email>pratap.nirujogi@amd.com</email>
</author>
<published>2024-11-19T23:03:15Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=ebbe34edc0a90be85b620b85eb97f8ff3356e38c'/>
<id>urn:sha1:ebbe34edc0a90be85b620b85eb97f8ff3356e38c</id>
<content type='text'>
Add support to create user BOs with MC address for isp using the dma-buf handle
exported for the buffers allocated from system memory in isp driver.

Export amdgpu_bo_create_kernel() and amdgpu_bo_free_kernel() as well for isp to
allocate GTT internal buffers required for fw to run.

Signed-off-by: Pratap Nirujogi &lt;pratap.nirujogi@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: enable GTT fallback handling for dGPUs only</title>
<updated>2024-11-12T22:10:05Z</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2024-06-04T16:05:00Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=e8fc090d322346e5ce4c4cfe03a8100e31f61c3c'/>
<id>urn:sha1:e8fc090d322346e5ce4c4cfe03a8100e31f61c3c</id>
<content type='text'>
That is just a waste of time on APUs.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3704
Fixes: 216c1282dde3 ("drm/amdgpu: use GTT only as fallback for VRAM|GTT")
Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-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: Stop reporting special chip memory pools as CPU memory in fdinfo</title>
<updated>2024-11-04T16:32:47Z</updated>
<author>
<name>Tvrtko Ursulin</name>
<email>tvrtko.ursulin@igalia.com</email>
</author>
<published>2024-10-24T09:23:40Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=cd3037f3fce5bf1556ad1a078cf458ebe52b12e8'/>
<id>urn:sha1:cd3037f3fce5bf1556ad1a078cf458ebe52b12e8</id>
<content type='text'>
So far these specialized on chip memory pools were reported as system
memory (aka 'cpu') which is not correct and misleading. Lets remove that
and consider later making them visible as their own thing.

Signed-off-by: Tvrtko Ursulin &lt;tvrtko.ursulin@igalia.com&gt;
Suggested-by: Christian König &lt;christian.koenig@amd.com&gt;
Cc: Yunxiang Li &lt;Yunxiang.Li@amd.com&gt;
Cc: Alex Deucher &lt;alexdeucher@gmail.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: stop tracking visible memory stats</title>
<updated>2024-11-04T16:32:40Z</updated>
<author>
<name>Yunxiang Li</name>
<email>Yunxiang.Li@amd.com</email>
</author>
<published>2024-10-24T09:23:39Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=fdee0872a29fe86e8450ab00838b9c0533388733'/>
<id>urn:sha1:fdee0872a29fe86e8450ab00838b9c0533388733</id>
<content type='text'>
Since on modern systems all of vram can be made visible anyways, to
simplify the new implementation, drops tracking how much memory is
visible for now. If this is really needed we can add it back on top of
the new implementation, or just report all the BOs as visible.

Signed-off-by: Yunxiang Li &lt;Yunxiang.Li@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Tvrtko Ursulin &lt;tvrtko.ursulin@igalia.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: make drm-memory-* report resident memory</title>
<updated>2024-11-04T16:30:58Z</updated>
<author>
<name>Yunxiang Li</name>
<email>Yunxiang.Li@amd.com</email>
</author>
<published>2024-10-24T09:23:38Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=f2863650384b32f1a511e338f102b819044ca930'/>
<id>urn:sha1:f2863650384b32f1a511e338f102b819044ca930</id>
<content type='text'>
The old behavior reports the resident memory usage for this key and the
documentation say so as well. However this was accidentally changed to
include buffers that was evicted.

Fixes: 04bdba46542c ("drm/amdgpu: Use drm_print_memory_stats helper from fdinfo")
Signed-off-by: Yunxiang Li &lt;Yunxiang.Li@amd.com&gt;
Reviewed-by: Tvrtko Ursulin &lt;tvrtko.ursulin@igalia.com&gt;
Acked-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Tvrtko Ursulin &lt;tvrtko.ursulin@igalia.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: Use drm_print_memory_stats helper from fdinfo</title>
<updated>2024-10-08T13:43:25Z</updated>
<author>
<name>Tvrtko Ursulin</name>
<email>tvrtko.ursulin@igalia.com</email>
</author>
<published>2024-05-20T11:13:38Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=04bdba46542c953e26f3ba4ac84dd65fbb4e7382'/>
<id>urn:sha1:04bdba46542c953e26f3ba4ac84dd65fbb4e7382</id>
<content type='text'>
Convert fdinfo memory stats to use the common drm_print_memory_stats
helper.

This achieves alignment with the common keys as documented in
drm-usage-stats.rst, adding specifically drm-total- key the driver was
missing until now.

Additionally I made the code stop skipping total size for objects which
currently do not have a backing store, and I added resident, active and
purgeable reporting.

Legacy keys have been preserved, with the outlook of only potentially
removing only the drm-memory- when the time gets right.

The example output now looks like this:

 pos:	0
 flags:	02100002
 mnt_id:	24
 ino:	1239
 drm-driver:	amdgpu
 drm-client-id:	4
 drm-pdev:	0000:04:00.0
 pasid:	32771
 drm-total-cpu:	0
 drm-shared-cpu:	0
 drm-active-cpu:	0
 drm-resident-cpu:	0
 drm-purgeable-cpu:	0
 drm-total-gtt:	2392 KiB
 drm-shared-gtt:	0
 drm-active-gtt:	0
 drm-resident-gtt:	2392 KiB
 drm-purgeable-gtt:	0
 drm-total-vram:	44564 KiB
 drm-shared-vram:	31952 KiB
 drm-active-vram:	0
 drm-resident-vram:	44564 KiB
 drm-purgeable-vram:	0
 drm-memory-vram:	44564 KiB
 drm-memory-gtt: 	2392 KiB
 drm-memory-cpu: 	0 KiB
 amd-memory-visible-vram:	44564 KiB
 amd-evicted-vram:	0 KiB
 amd-evicted-visible-vram:	0 KiB
 amd-requested-vram:	44564 KiB
 amd-requested-visible-vram:	11952 KiB
 amd-requested-gtt:	2392 KiB
 drm-engine-compute:	46464671 ns

v2:
 * Track purgeable via AMDGPU_GEM_CREATE_DISCARDABLE.

Acked-by: Daniel Vetter &lt;daniel.vetter@ffwll.ch&gt;
Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Tvrtko Ursulin &lt;tvrtko.ursulin@igalia.com&gt;
Cc: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Cc: Christian König &lt;christian.koenig@amd.com&gt;
Cc: Daniel Vetter &lt;daniel@ffwll.ch&gt;
Cc: Rob Clark &lt;robdclark@chromium.org&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
</feed>
