<feed xmlns='http://www.w3.org/2005/Atom'>
<title>kernel.git/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c, branch linux-6.14.y</title>
<subtitle>Hosts the 0x221E linux distro kernel.
</subtitle>
<id>https://git.0xinfinity.dev/distro/kernel.git/atom?h=linux-6.14.y</id>
<link rel='self' href='https://git.0xinfinity.dev/distro/kernel.git/atom?h=linux-6.14.y'/>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/'/>
<updated>2025-05-29T09:12:30Z</updated>
<entry>
<title>drm/amdgpu: use GFP_NOWAIT for memory allocations</title>
<updated>2025-05-29T09:12:30Z</updated>
<author>
<name>Christian König</name>
</author>
<published>2025-01-15T14:10:13Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=af233078494ec48952a975febd88792a3a324579'/>
<id>urn:sha1:af233078494ec48952a975febd88792a3a324579</id>
<content type='text'>
[ Upstream commit 16590745b571c07869ef8958e0bbe44ab6f08d1f ]

In the critical submission path memory allocations can't wait for
reclaim since that can potentially wait for submissions to finish.

Finally clean that up and mark most memory allocations in the critical
path with GFP_NOWAIT. The only exception left is the dma_fence_array()
used when no VMID is available, but that will be cleaned up later on.

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Acked-by: Srinivasan Shanmugam &lt;srinivasan.shanmugam@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: rework how isolation is enforced v2</title>
<updated>2025-05-29T09:12:30Z</updated>
<author>
<name>Christian König</name>
</author>
<published>2025-01-15T12:44:26Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=4277dc1942a8979abe1ef2b55069f42497f885c0'/>
<id>urn:sha1:4277dc1942a8979abe1ef2b55069f42497f885c0</id>
<content type='text'>
[ Upstream commit bd22e44ad415ac22e3a4f9a983d2a085f6cb4427 ]

Limiting the number of available VMIDs to enforce isolation causes some
issues with gang submit and applying certain HW workarounds which
require multiple VMIDs to work correctly.

So instead start to track all submissions to the relevant engines in a
per partition data structure and use the dma_fences of the submissions
to enforce isolation similar to what a VMID limit does.

v2: use ~0l for jobs without isolation to distinct it from kernel
    submissions which uses NULL for the owner. Add some warning when we
    are OOM.

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Acked-by: Srinivasan Shanmugam &lt;srinivasan.shanmugam@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: sync to KFD fences before clearing PTEs</title>
<updated>2024-09-25T16:55:44Z</updated>
<author>
<name>Christian König</name>
</author>
<published>2024-08-21T11:55:41Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=126be9b2bef9c7068fdd464790d82e6d70f9d8e6'/>
<id>urn:sha1:126be9b2bef9c7068fdd464790d82e6d70f9d8e6</id>
<content type='text'>
This patch tries to solve the basic problem we also need to sync to
the KFD fences of the BO because otherwise it can be that we clear
PTEs while the KFD queues are still running.

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Acked-by: Felix Kuehling &lt;felix.kuehling@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: Simplify the allocation of sync slab caches</title>
<updated>2024-02-22T17:05:16Z</updated>
<author>
<name>Kunwu Chan</name>
</author>
<published>2024-02-21T09:59:07Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=a5fc4e5014cde7b4abd5a95eb1f6ec487de42a9c'/>
<id>urn:sha1:a5fc4e5014cde7b4abd5a95eb1f6ec487de42a9c</id>
<content type='text'>
Use the new KMEM_CACHE() macro instead of direct kmem_cache_create
to simplify the creation of SLAB caches.

Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Kunwu Chan &lt;chentao@kylinos.cn&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: Let KFD sync with VM fences</title>
<updated>2024-01-03T15:46:13Z</updated>
<author>
<name>Felix Kuehling</name>
</author>
<published>2023-12-18T21:17:23Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=ec9ba4821fa52b5efdbc4cdf0a77497990655231'/>
<id>urn:sha1:ec9ba4821fa52b5efdbc4cdf0a77497990655231</id>
<content type='text'>
Change the rules for amdgpu_sync_resv to let KFD synchronize with VM
fences on page table reservations. This fixes intermittent memory
corruption after evictions when using amdgpu_vm_handle_moved to update
page tables for VM mappings managed through render nodes.

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@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: fix missing dma_fence_put in error path</title>
<updated>2023-01-05T19:34:58Z</updated>
<author>
<name>Christian König</name>
</author>
<published>2023-01-05T10:27:16Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=41cc108b2451e0c65e8c9c9f6a3e103b62b60bb3'/>
<id>urn:sha1:41cc108b2451e0c65e8c9c9f6a3e103b62b60bb3</id>
<content type='text'>
When the fence can't be added we need to drop the reference.

Suggested-by: Bert Karwatzki &lt;spasswolf@web.de&gt;
Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20230105111703.52695-2-christian.koenig@amd.com
Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Reviewed-by: Luben Tuikov &lt;luben.tuikov@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: use scheduler dependencies for VM updates</title>
<updated>2022-11-03T11:45:20Z</updated>
<author>
<name>Christian König</name>
</author>
<published>2022-09-29T11:34:34Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=aab9cf7b6954136f4339136a1a7fc0602a2c4d8b'/>
<id>urn:sha1:aab9cf7b6954136f4339136a1a7fc0602a2c4d8b</id>
<content type='text'>
Instead of putting that into the job sync object.

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Luben Tuikov &lt;luben.tuikov@amd.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20221014084641.128280-9-christian.koenig@amd.com
</content>
</entry>
<entry>
<title>drm/amdgpu: cleanup coding style in amdgpu_sync.c file</title>
<updated>2022-09-13T18:32:58Z</updated>
<author>
<name>Jingyu Wang</name>
</author>
<published>2022-09-04T18:33:07Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=826f03b8ac7a9c4660de9b65a81e8926c60b3b97'/>
<id>urn:sha1:826f03b8ac7a9c4660de9b65a81e8926c60b3b97</id>
<content type='text'>
This is a patch to the amdgpu_sync.c file that fixes some warnings found by the checkpatch.pl tool

Signed-off-by: Jingyu Wang &lt;jingyuwang_vip@163.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>Merge tag 'amd-drm-next-5.19-2022-04-15' of https://gitlab.freedesktop.org/agd5f/linux into drm-next</title>
<updated>2022-04-28T04:33:20Z</updated>
<author>
<name>Dave Airlie</name>
</author>
<published>2022-04-28T04:33:20Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=dbe946287e0825f0e9cd4cbeacfcde9d9b2dd168'/>
<id>urn:sha1:dbe946287e0825f0e9cd4cbeacfcde9d9b2dd168</id>
<content type='text'>
amd-drm-next-5.19-2022-04-15:

amdgpu:
- USB-C updates
- GPUVM updates
- TMZ fixes for RV
- DCN 3.1 pstate fixes
- Display z state fixes
- RAS fixes
- Misc code cleanups and spelling fixes
- More DC FP rework
- GPUVM TLB handling rework
- Power management sysfs code cleanup
- Add RAS support for VCN
- Backlight fix
- Add unique id support for more asics
- Misc display updates
- SR-IOV fixes
- Extend CG and PG flags to 64 bits
- Enable VCN clk sysfs nodes for navi12

amdkfd:
- Fix IO link cleanup during device removal
- RAS fixes
- Retry fault fixes
- Asynchronously free events
- SVM fixes

radeon:
- Drop some dead code
- Misc code cleanups

From: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20220415135144.5700-1-alexander.deucher@amd.com
Signed-off-by: Dave Airlie &lt;airlied@redhat.com&gt;
</content>
</entry>
<entry>
<title>dma-buf: add DMA_RESV_USAGE_BOOKKEEP v3</title>
<updated>2022-04-07T10:53:54Z</updated>
<author>
<name>Christian König</name>
</author>
<published>2021-11-09T10:08:18Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=0cc848a75b742c3f9800e643cd2c03b9cfdc3d69'/>
<id>urn:sha1:0cc848a75b742c3f9800e643cd2c03b9cfdc3d69</id>
<content type='text'>
Add an usage for submissions independent of implicit sync but still
interesting for memory management.

v2: cleanup the kerneldoc a bit
v3: separate amdgpu changes from this

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Daniel Vetter &lt;daniel.vetter@ffwll.ch&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20220407085946.744568-10-christian.koenig@amd.com
</content>
</entry>
</feed>
