linux-toradex.git/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c, branch v6.16-rc5

drm/amdgpu: switch job hw_fence to amdgpu_fence

2025-06-18T17:15:26+00:00

Use the amdgpu fence container so we can store additional
data in the fence.  This also fixes the start_time handling
for MCBP since we were casting the fence to an amdgpu_fence
and it wasn't.

Fixes: 3f4c175d62d8 ("drm/amdgpu: MCBP based on DRM scheduler (v9)")
Reviewed-by: Christian König 
Signed-off-by: Alex Deucher 
(cherry picked from commit bf1cd14f9e2e1fdf981eed273ddd595863f5288c)
Cc: stable@vger.kernel.org

drm/amdgpu: rework how isolation is enforced v2

2025-03-21T16:16:34+00:00

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 
Acked-by: Srinivasan Shanmugam 
Signed-off-by: Alex Deucher

drm/amdgpu: Trigger a wedged event for ring reset

2025-03-10T18:56:25+00:00

Instead of only triggering a wedged event for complete GPU resets,
trigger for ring resets. Regardless of the reset, it's useful for
userspace to know that it happened because the kernel will reject
further submissions from that app.

Reviewed-by: Christian König 
Signed-off-by: André Almeida 
Signed-off-by: Alex Deucher

Merge tag 'amd-drm-next-6.15-2025-03-07' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

2025-03-09T23:04:52+00:00

amdgpu:
- Fix spelling typos
- RAS updates
- VCN 5.0.1 updates
- SubVP fixes
- DCN 4.0.1 fixes
- MSO DPCD fixes
- DIO encoder refactor
- PCON fixes
- Misc cleanups
- DMCUB fixes
- USB4 DP fixes
- DM cleanups
- Backlight cleanups and fixes
- Support platform backlight curves
- Misc code cleanups
- SMU 14 fixes
- JPEG 4.0.3 reset updates
- SR-IOV fixes
- SVM fixes
- GC 12 DCC fixes
- DC DCE 6.x fix
- Hiberation fix

amdkfd:
- Fix possible NULL pointer in queue validation
- Remove unnecessary CP domain validation
- SDMA queue reset support
- Add per process flags

radeon:
- Fix spelling typos
- RS400 hyperZ fix

UAPI:
- Add KFD per process flags for setting precision
  Proposed user space: https://github.com/ROCm/ROCR-Runtime/commit/2a64fa5e06e80e0af36df4ce0c76ae52eeec0a9d

Signed-off-by: Dave Airlie 

From: Alex Deucher 
Link: https://patchwork.freedesktop.org/patch/msgid/20250307211051.1880472-1-alexander.deucher@amd.com

drm/amdgpu: Create a debug option to disable ring reset

2025-02-27T21:50:04+00:00

Prior to the addition of ring reset, the debug option
`debug_disable_soft_recovery` could be used to force a full device
reset. Now that we have ring reset, create a debug option to disable
them in amdgpu, forcing the driver to go with the full device
reset path again when both options are combined.

This option is useful for testing and debugging purposes when one wants
to test the full reset from userspace.

Signed-off-by: André Almeida 
Signed-off-by: Alex Deucher

drm/amdgpu: Log after a successful ring reset

2025-02-25T16:44:00+00:00

When a ring reset happens, the kernel log shows only "amdgpu: Starting
 ring reset", but when it finishes nothing appears in the
log. Explicitly write in the log that the reset has finished correctly.

Reviewed-by: Christian König 
Signed-off-by: André Almeida 
Signed-off-by: Alex Deucher

drm/amdgpu: Update amdgpu_job_timedout to check if the ring is guilty

2025-02-25T16:43:59+00:00

This patch updates the `amdgpu_job_timedout` function to check if
the ring is actually guilty of causing the timeout. If not, it
skips error handling and fence completion.

v2: move the is_guilty check down into the queue reset area (Alex)
v3: need to call is_guilty before reset (Alex)
v4: squash in is_guilty logic fixes (Alex)

Signed-off-by: Alex Deucher 
Signed-off-by: Jesse Zhang 
Reviewed-by: Alex Deucher 
Signed-off-by: Alex Deucher

drm/amdgpu: Pop jobs from the queue more robustly

2025-02-24T09:17:40+00:00

Replace a copy of DRM scheduler's to_drm_sched_job with a copy of a newly
added drm_sched_entity_queue_pop.

This allows breaking the hidden dependency that queue_node has to be the
first element in struct drm_sched_job.

A comment is also added with a reference to the mailing list discussion
explaining the copied helper will be removed when the whole broken
amdgpu_job_stop_all_jobs_on_sched is removed.

Signed-off-by: Tvrtko Ursulin 
Cc: Christian König 
Cc: Danilo Krummrich 
Cc: Matthew Brost 
Cc: Philipp Stanner 
Cc: Zhang, Hawking 
Reviewed-by: Christian König 
Signed-off-by: Philipp Stanner 
Link: https://patchwork.freedesktop.org/patch/msgid/20250221105038.79665-3-tvrtko.ursulin@igalia.com

drm/amdgpu: partially revert "reduce reset time"

2024-12-18T17:39:07+00:00

This partially reverts commit 194eb174cbe4fe2b3376ac30acca2dc8c8beca00.

This commit introduced a new state variable into adev without even
remotely worrying about CPU barriers.

Since we already have the amdgpu_in_reset() function exactly for this
use case partially revert that.

Signed-off-by: Christian König 
Reviewed-by: Alex Deucher 
Signed-off-by: Alex Deucher

drm/amdgpu: set the VM pointer to NULL in amdgpu_job_prepare

2024-12-18T17:39:07+00:00

As soon as the prepare phase is completed the VM might be released,
better set it to NULL.

Signed-off-by: Christian König 
Reviewed-by: Alex Deucher 
Signed-off-by: Alex Deucher