linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c, branch v7.3-rc2

drm/amdgpu: recover user queues in the shared priv-fault helper

2026-08-06T13:30:39+00:00

If a priv/bad-op fault does not match a kernel queue slot, it belongs to a
MES-scheduled user queue. Extend the shared amdgpu_gfx_handle_priv_fault()
helper introduced by commit d8ab7636160e ("drm/amd/amdgpu: remove
duplicated code in gfx_v11 and gfx_v12") to recover it: gate on
adev->gfx.disable_uq, reset a compute user queue directly from its
doorbell, and for a gfx user queue (whose IV carries no doorbell) record
the HW slot and schedule the per-IP recovery worker.

v2:
 - gate on adev->gfx.disable_uq instead of !adev->enable_mes (Alex)
 - document why both the doorbell (compute) and HW-slot (gfx) reset
   paths are needed (Alex)

v3:
 - rebase amd-staging-drm-next. adapt to the
   commit 9243cf4777fc ("drm/amd/amdgpu: remove duplicated code in gfx_v11 and gfx_v12");
   no functional change

Reviewed-by: Alex Deucher 
Suggested-by: Mario Sopena-Novales 
Signed-off-by: Jesse Zhang 
Signed-off-by: Alex Deucher

drm/amd/amdgpu: remove duplicated code in gfx_v11 and gfx_v12

2026-07-29T21:56:28+00:00

The functions gfx_v11_0_handle_priv_fault and
gfx_v12_0_handle_priv_fault share the same logic for searching and
triggering a scheduler fault on a ring. This patch moves the shared
ring-searching logic to a common function, amdgpu_gfx_handle_priv_fault,
in amdgpu_gfx.c. The hardware-specific decoding of ring IDs remains in
the version-specific files to maintain proper architectural separation.

Signed-off-by: Ulisses Paixao 
Co-developed-by: Felipe Sousa 
Signed-off-by: Felipe Sousa 
Reviewed-by: Christian König 
Signed-off-by: Alex Deucher

drm/amdgpu/gfx7: Make amdgpu_gfx_mqd_sw_init() usable on GFX7

2026-07-29T21:55:28+00:00

GFX7 supports KIQ, but amdgpu doesn't use it.
Change amdgpu_gfx_mqd_sw_init() to only allocate the MQD BO
for the KIQ on GFX8 and newer (that is, TOPAZ and newer).

This makes amdgpu_gfx_mqd_sw_init() usable on GFX7 without
any further changes to its functionality.

Signed-off-by: Timur Kristóf 
Reviewed-by: Tvrtko Ursulin 
Signed-off-by: Alex Deucher

drm/amdgpu: move job parameter to the end in amdgpu_job_alloc() and *_with_ib()

2026-07-16T22:26:04+00:00

Move the job output parameter to be the last parameter in the
amdgpu_job_alloc() and amdgpu_job_alloc_with_ib() function signature. This
aligns with the common kernel coding convention where output parameters
typically come last.

Assisted-by: Claude:Sonnet 4
Signed-off-by: Christian König 
Reviewed-by: Timur Kristóf 
Signed-off-by: Alex Deucher

drm/amdgpu: move struct amdgpu_wb and helpers into separate files

2026-07-08T18:20:30+00:00

Move struct amdgpu_wb and helpers out of the monolithic header amdgpu.h
into its own dedicated header amdgpu_wb.h.

Add amdgpu_wb_init() and amdgpu_wb_fini() into amdgpu_wb.h.

Move functions amdgpu_device_wb_get(), amdgpu_device_wb_free(),
amdgpu_device_wb_init(), and amdgpu_device_wb_fini() out of
amdgpu_device.c into new dedicated amdgpu_wb.c file.

Removed static from functions amdgpu_device_wb_init() and amdgpu_device_wb_fini().

Rename functions amdgpu_device_wb_get(), amdgpu_device_wb_free(),
amdgpu_device_wb_init(), and amdgpu_device_wb_fini() into
amdgpu_wb_get(), amdgpu_wb_free(), amdgpu_wb_init(), and amdgpu_wb_fini().

Update amdgpu/Makefile to build amdgpu_wb.o.

This is part of the ongoing effort to reduce the size of amdgpu.h into
their own respective separate headers.

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

drm/amdgpu: Do not fiddle with the idle workers too much

2026-07-01T15:56:47+00:00

Idle workers only need to be canceled or pushed back if we are potentially
idle. Make the both operations conditional on the pre-increment and post-
decrement status of the in-flight job counter.

Reviewed-by: Timur Kristóf 
Signed-off-by: Tvrtko Ursulin 
Cc: Alex Deucher 
Cc: Christian König 
Cc: Timur Kristóf 
Signed-off-by: Alex Deucher

drm/amdgpu: Fix false error return to non-KCQ

2026-07-01T15:41:10+00:00

amdgpu_gfx_reset_mes_compute is used to coordinate suspend_all, reset,
and resume_all between KCQ and compute user queues. When a hung queue
comes from the compute user queues and the reset is successful, the KCQ
failure after reset should be sent to KCQ only and not the compute user
queues. Compute user queues can operate after a successful reset without
a mode reset.

Fixes: a4e4d945cba8 ("drm/amdgpu/gfx: defer per-queue helper_end until after MES resume")
Signed-off-by: Amber Lin 
Acked-by: Jesse Zhang 
Signed-off-by: Alex Deucher

Revert "drm/amdgpu: defer KCQ remap until after MES resume in reset flow"

2026-07-01T15:30:04+00:00

This reverts commit 36b6c723d82c07dbbeae95d5883d4ecf0a643727.

It introduced a regression on gfx11: the kfd negative test failed.

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

drm/amdgpu: defer KCQ remap until after MES resume in reset flow

2026-07-01T15:15:47+00:00

Split amdgpu_gfx_mes_reset_queue_start() into reset+unmap now and queue
reinit later, and do the remap only after amdgpu_mes_resume(). Avoids
re-adding legacy queues while MES gangs are still suspended.

Suggested-by: Shaoyun Liu 
Acked-by: Alex Deucher 
Signed-off-by: Jesse Zhang 
Signed-off-by: Alex Deucher

drm/amdgpu: Fix mes remove_hw_queue lock

2026-07-01T15:07:40+00:00

down_read/up_read adev->reset_domain semaphore should be placed around
remove queue.

v2: remove the empty function, recover_bad_queue_mes to avoid compile
error on rhel

Fixes: f401a2633e02 ("drm/amdgpu: Remove faulty queue before resume")
Signed-off-by: Amber Lin 
Reviewed-by: Jesse Zhang 
Signed-off-by: Alex Deucher