kernel/linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h, branch v6.18.21

drm/amdgpu: set an error on all fences from a bad context

2025-10-13T18:14:15+00:00

When we backup ring contents to reemit after a queue reset, we don't backup ring contents from the bad context. When we signal the fences, we should set an error on those fences as well. v2: misc cleanups v3: add locking for fence error, fix comment (Christian) v4: fix wrap around, locking (Christian) Fixes: 77cc0da39c7c ("drm/amdgpu: track ring state associated with a fence") Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: Use memset32 for ring clearing

2025-09-15T20:55:22+00:00

Use memset32 instead of open coding it, just because it is a tiny bit nicer. Reviewed-by: Christian König Signed-off-by: Tvrtko Ursulin Signed-off-by: Alex Deucher

drm/amdgpu: Fix allocating extra dwords for rings (v2)

2025-09-15T20:52:52+00:00

Rename extra_dw to extra_bytes and document what it's for. The value is already used as if it were bytes in vcn_v4_0.c and in amdgpu_ring_init. Just adjust the dword count in jpeg_v1_0.c so that it becomes a byte count. v2: Rename extra_dw to extra_bytes as discussed during review. Fixes: c8c1a1d2ef04 ("drm/amdgpu: define and add extra dword for jpeg ring") Signed-off-by: Timur Kristóf Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: Remove volatile from ring manipulation

2025-09-15T20:51:15+00:00

None of the pointer operations handled by the ring file requires volatile, for this reason, this commit removes all occurrences of volatile associated with rings. Reviewed-by: Christian König Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher

drm/amdgpu: move reset support type checks into the caller

2025-07-17T16:36:56+00:00

Rather than checking in the callbacks, check if the reset type is supported in the caller. Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher

drm/amdgpu: track ring state associated with a fence

2025-07-16T20:14:11+00:00

We need to know the wptr and sequence number associated with a fence so that we can re-emit the unprocessed state after a ring reset. Pre-allocate storage space for the ring buffer contents and add helpers to save off and re-emit the unprocessed state so that it can be re-emitted after the queue is reset. Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: move guilty handling into ring resets

2025-06-30T15:57:36+00:00

Move guilty logic into the ring reset callbacks. This allows each ring reset callback to better handle fence errors and force completions in line with the reset behavior for each IP. It also allows us to remove the ring guilty callback since that logic now lives in the reset callback. Acked-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: update ring reset function signature

2025-06-30T15:57:16+00:00

Going forward, we'll need more than just the vmid. Add the guilty amdgpu_fence. Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: remove job parameter from amdgpu_fence_emit()

2025-06-30T15:57:06+00:00

What we actually care about is the amdgpu_fence object so pass that in explicitly to avoid possible mistakes in the future. The job_run_counter handling can be safely removed at this point as we no longer support job resubmission. Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: switch job hw_fence to amdgpu_fence

2025-06-18T16:19:21+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