drm/xe: Split TLB invalidation code in frontend and backend

Browse source

The frontend exposes an API to the driver to send invalidations, handles
sequence number assignment, synchronization (fences), and provides a
timeout mechanism. The backend issues the actual invalidation to the
hardware (or firmware).

The new layering easily allows issuing TLB invalidations to different
hardware or firmware interfaces.

Normalize some naming while here too.

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250826182911.392550-10-stuart.summers@intel.com

...

This commit is contained in:

Matthew Brost 2025-08-26 18:29:11 +00:00

parent 8443e8c448

commit db16f9d90c

8 changed files with 500 additions and 385 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

1

drivers/gpu/drm/xe/Makefile

View file

2

drivers/gpu/drm/xe/xe_gt.c

View file

2

drivers/gpu/drm/xe/xe_guc_ct.c

View file

242

drivers/gpu/drm/xe/xe_guc_tlb_inval.c

View file

19

drivers/gpu/drm/xe/xe_guc_tlb_inval.h

View file

537

drivers/gpu/drm/xe/xe_tlb_inval.c

View file

15

drivers/gpu/drm/xe/xe_tlb_inval.h

View file

67

drivers/gpu/drm/xe/xe_tlb_inval_types.h

View file