<feed xmlns='http://www.w3.org/2005/Atom'>
<title>kernel/linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c, branch v6.6.25</title>
<subtitle>Linux kernel stable tree (mirror)</subtitle>
<id>https://git.radix-linux.su/kernel/linux.git/atom?h=v6.6.25</id>
<link rel='self' href='https://git.radix-linux.su/kernel/linux.git/atom?h=v6.6.25'/>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/'/>
<updated>2024-04-03T13:28:37+00:00</updated>
<entry>
<title>drm/amdgpu: amdgpu_ttm_gart_bind set gtt bound flag</title>
<updated>2024-04-03T13:28:37+00:00</updated>
<author>
<name>Philip Yang</name>
<email>Philip.Yang@amd.com</email>
</author>
<published>2024-03-11T22:07:34+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=6fcd12cb90888ef2d8af8d4c04e913252eee4ef3'/>
<id>urn:sha1:6fcd12cb90888ef2d8af8d4c04e913252eee4ef3</id>
<content type='text'>
[ Upstream commit 6c6064cbe58b43533e3451ad6a8ba9736c109ac3 ]

Otherwise after the GTT bo is released, the GTT and gart space is freed
but amdgpu_ttm_backend_unbind will not clear the gart page table entry
and leave valid mapping entry pointing to the stale system page. Then
if GPU access the gart address mistakely, it will read undefined value
instead page fault, harder to debug and reproduce the real issue.

Cc: stable@vger.kernel.org
Signed-off-by: Philip Yang &lt;Philip.Yang@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Sasha Levin &lt;sashal@kernel.org&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: fix ftrace event amdgpu_bo_move always move on same heap</title>
<updated>2024-02-05T20:14:29+00:00</updated>
<author>
<name>Wang, Beyond</name>
<email>Wang.Beyond@amd.com</email>
</author>
<published>2023-12-12T13:03:04+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=e7a0ee45c653784edda5e36bae6ae3c75fd5e7a8'/>
<id>urn:sha1:e7a0ee45c653784edda5e36bae6ae3c75fd5e7a8</id>
<content type='text'>
[ Upstream commit 94aeb4117343d072e3a35b9595bcbfc0058ee724 ]

Issue: during evict or validate happened on amdgpu_bo, the 'from' and
'to' is always same in ftrace event of amdgpu_bo_move

where calling the 'trace_amdgpu_bo_move', the comment says move_notify
is called before move happens, but actually it is called after move
happens, here the new_mem is same as bo-&gt;resource

Fix: move trace_amdgpu_bo_move from move_notify to amdgpu_bo_move

Signed-off-by: Wang, Beyond &lt;Wang.Beyond@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Sasha Levin &lt;sashal@kernel.org&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: Replace ternary operator with min() in 'amdgpu_iomem_write'</title>
<updated>2023-08-15T22:08:30+00:00</updated>
<author>
<name>Srinivasan Shanmugam</name>
<email>srinivasan.shanmugam@amd.com</email>
</author>
<published>2023-08-12T14:50:31+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=b828e1004cce55a078ba7bb11e252c2499793025'/>
<id>urn:sha1:b828e1004cce55a078ba7bb11e252c2499793025</id>
<content type='text'>
Fixes the following coccicheck:

drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c:2482:16-17: WARNING opportunity for min()

min() macro is defined in include/linux/minmax.h. It avoids multiple
evaluations of the arguments when non-constant and performs strict
type-checking.

Cc: Guchun Chen &lt;guchun.chen@amd.com&gt;
Cc: Christian König &lt;christian.koenig@amd.com&gt;
Cc: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Cc: "Pan, Xinhui" &lt;Xinhui.Pan@amd.com&gt;
Signed-off-by: Srinivasan Shanmugam &lt;srinivasan.shanmugam@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: Remove duplicated includes</title>
<updated>2023-08-15T22:08:29+00:00</updated>
<author>
<name>GUO Zihua</name>
<email>guozihua@huawei.com</email>
</author>
<published>2023-08-10T11:56:12+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=e8b2ad875ffa1c213d047e02c9c1b7db5f149241'/>
<id>urn:sha1:e8b2ad875ffa1c213d047e02c9c1b7db5f149241</id>
<content type='text'>
Remove duplicated includes in amdgpu_amdkfd_gpuvm.c and amdgpu_ttm.c.
Resolves checkincludes message.

Signed-off-by: GUO Zihua &lt;guozihua@huawei.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: Replace ternary operator with min() in 'amdgpu_iomem_read'</title>
<updated>2023-08-15T22:08:28+00:00</updated>
<author>
<name>Srinivasan Shanmugam</name>
<email>srinivasan.shanmugam@amd.com</email>
</author>
<published>2023-08-12T14:47:24+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=44fd83e920e2ec0322ad82320ca575445b5e135e'/>
<id>urn:sha1:44fd83e920e2ec0322ad82320ca575445b5e135e</id>
<content type='text'>
Fixes the following coccicheck:

drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c:2427:16-17: WARNING opportunity for min()

min() macro is defined in include/linux/minmax.h. It avoids multiple
evaluations of the arguments when non-constant and performs strict
type-checking.

Cc: Guchun Chen &lt;guchun.chen@amd.com&gt;
Cc: Christian König &lt;christian.koenig@amd.com&gt;
Cc: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Cc: "Pan, Xinhui" &lt;Xinhui.Pan@amd.com&gt;
Signed-off-by: Srinivasan Shanmugam &lt;srinivasan.shanmugam@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: create kernel doorbell pages</title>
<updated>2023-08-07T21:14:06+00:00</updated>
<author>
<name>Shashank Sharma</name>
<email>shashank.sharma@amd.com</email>
</author>
<published>2023-07-14T13:19:54+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=54c30d2a8defeef631d0111477218fe4ceecb3da'/>
<id>urn:sha1:54c30d2a8defeef631d0111477218fe4ceecb3da</id>
<content type='text'>
This patch:
- creates a doorbell page for graphics driver usages.
- adds a few new varlables in adev-&gt;doorbell structure to
  keep track of kernel's doorbell-bo.
- removes the adev-&gt;doorbell.ptr variable, replaces it with
  kernel-doorbell-bo's cpu address.

V2: - Create doorbell BO directly, no wrappe functions (Alex)
    - no additional doorbell structure (Alex, Christian)
    - Use doorbell_cpu_ptr, remove ioremap (Christian, Alex)
    - Allocate one extra page of doorbells for MES (Alex)

V4: Move MES doorbell base init into MES related patch (Christian)

Cc: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Cc: Christian Koenig &lt;christian.koenig@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Shashank Sharma &lt;shashank.sharma@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: initialize ttm for doorbells</title>
<updated>2023-08-07T21:14:06+00:00</updated>
<author>
<name>Shashank Sharma</name>
<email>shashank.sharma@amd.com</email>
</author>
<published>2023-07-14T13:15:01+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=792b84fb903839a241f4dd2df92ea9851f3d2160'/>
<id>urn:sha1:792b84fb903839a241f4dd2df92ea9851f3d2160</id>
<content type='text'>
This patch initialzes the ttm resource manager for doorbells.

V2: Do not round up doorbell size (Alex)

Cc: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Cc: Christian Koenig &lt;christian.koenig@amd.com&gt;
Reviewed-by: Christian Koenig &lt;christian.koenig@amd.com&gt;
Signed-off-by: Shashank Sharma &lt;shashank.sharma@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: accommodate DOMAIN/PL_DOORBELL</title>
<updated>2023-08-07T21:14:06+00:00</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2023-07-14T13:11:26+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=dc3499c71d3618130d9c6675e4de1e3562c17125'/>
<id>urn:sha1:dc3499c71d3618130d9c6675e4de1e3562c17125</id>
<content type='text'>
This patch adds changes:
- to accommodate the new GEM domain for DOORBELLs
- to accommodate the new TTM PL for DOORBELLs

in order to manage doorbell pages as GEM object.

V2: Addressed reviwe comments from Christian
    - drop the doorbell changes for pinning/unpinning
    - drop the doorbell changes for dma-buf map
    - drop the doorbell changes for sgt
    - no need to handle TTM_PL_FLAG_CONTIGUOUS for doorbell
    - add caching type for doorbell

V3: - Removed unrelated empty line (Christian)
    - Add PL_DOORBELL in mem_type_to_domain() as well (Alex)

Cc: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Cc: Christian Koenig &lt;christian.koenig@amd.com&gt;
Reviewed-by: Christian Koenig &lt;christian.koenig@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Shashank Sharma &lt;shashank.sharma@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: Rename DRM schedulers in amdgpu TTM</title>
<updated>2023-06-15T14:42:33+00:00</updated>
<author>
<name>Mukul Joshi</name>
<email>mukul.joshi@amd.com</email>
</author>
<published>2023-05-23T15:55:54+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=41ce6d6d03d5e51420ea7732c83facc8a7f2e5da'/>
<id>urn:sha1:41ce6d6d03d5e51420ea7732c83facc8a7f2e5da</id>
<content type='text'>
Rename mman.entity to mman.high_pr to make the distinction
clearer that this is a high priority scheduler. Similarly,
rename the recently added mman.delayed to mman.low_pr to
make it clear it is a low priority scheduler.
No functional change in this patch.

Signed-off-by: Mukul Joshi &lt;mukul.joshi@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: bypass bios dependent operations</title>
<updated>2023-06-09T15:02:12+00:00</updated>
<author>
<name>Shiwu Zhang</name>
<email>shiwu.zhang@amd.com</email>
</author>
<published>2023-05-17T06:15:05+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=9535a86a4072babc37dc6bdadae52bdbb88166f5'/>
<id>urn:sha1:9535a86a4072babc37dc6bdadae52bdbb88166f5</id>
<content type='text'>
Since bios reading does not work currently so just bypass all operations
related to bios

v2: hardcode the vram info for APP_APU case (hawking)
v3: correct the vram_width with channel number * channel size (lijo)

Signed-off-by: Shiwu Zhang &lt;shiwu.zhang@amd.com&gt;
Reviewed-by: Yang Wang &lt;kevinyang.wang@amd.com&gt;
Reviewed-by: Hawking Zhang &lt;Hawking.Zhang@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
</feed>
