drm/amdgpu/userq: reset a hung SDMA user queue over MMIO

Browse source

A hung SDMA user queue wedges MES, so the MES packet reset times out and
falls back to a full MODE1 reset - once per in-flight job, a reset storm.

The queue is still on its HW slot at the first hang-detect, so use
detect_hung_queue to recover its slot from the doorbell and reset it over
MMIO, which does not need MES. Mark it HUNG (not UNMAPPED) so the restore
worker does not re-map and re-run the guilty job, and short-circuit the
per-fence hang-detect re-entry once the queue is already reset.

Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

...

This commit is contained in:

Jesse Zhang 2026-09-03 17:36:37 +08:00 • committed by Alex Deucher

parent 6537bd2108

commit 4a263bc340

1 changed files with 38 additions and 9 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

47

drivers/gpu/drm/amd/amdgpu/mes_userqueue.c

View file