drm/xe: Wedge the entire device

Browse source

Wedge the entire device, not just GT which may have triggered the wedge.
To implement this, cleanup the layering so xe_device_declare_wedged()
calls into the lower layers (GT) to ensure entire device is wedged.

While we are here, also signal any pending GT TLB invalidations upon
wedging device.

Lastly, short circuit reset wait if device is wedged.

v2:
 - Short circuit reset wait if device is wedged (Local testing)

Fixes: 8ed9aaae39 ("drm/xe: Force wedged state and block GT reset upon any GPU hang")
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240716063902.1390130-1-matthew.brost@intel.com

...

This commit is contained in:

Matthew Brost 2024-07-15 23:39:01 -07:00

parent e02cea83d3

commit 7dbe8af13c

9 changed files with 80 additions and 13 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

6

drivers/gpu/drm/xe/xe_device.c

View file

15

drivers/gpu/drm/xe/xe_gt.c

View file

1

drivers/gpu/drm/xe/xe_gt.h

View file

16

drivers/gpu/drm/xe/xe_guc.c

View file

1

drivers/gpu/drm/xe/xe_guc.h

View file

48

drivers/gpu/drm/xe/xe_guc_submit.c

View file

1

drivers/gpu/drm/xe/xe_guc_submit.h

View file

14

drivers/gpu/drm/xe/xe_uc.c

View file

1

drivers/gpu/drm/xe/xe_uc.h

View file