drm/xe: Convert GT stats to per-cpu counters

Browse source

Current GT statistics use atomic64_t counters. Atomic operations incur
a global coherency penalty.

Transition to dynamic per-cpu counters using alloc_percpu(). This allows
stats to be incremented via this_cpu_add(), which compiles to a single
non-locking instruction. This approach keeps the hot-path updates local
to the CPU, avoiding expensive cross-core cache invalidation traffic.

Use for_each_possible_cpu() during aggregation and clear operations to
ensure data consistency across CPU hotplug events.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://patch.msgid.link/20260217200552.596718-1-matthew.brost@intel.com

...

This commit is contained in:

Matthew Brost 2026-02-17 12:05:52 -08:00

parent 48eb073c7d

commit 9ff885ef8b

5 changed files with 82 additions and 16 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

5

drivers/gpu/drm/xe/xe_gt.c

View file

63

drivers/gpu/drm/xe/xe_gt_stats.c

View file

6

drivers/gpu/drm/xe/xe_gt_stats.h

View file

19

drivers/gpu/drm/xe/xe_gt_stats_types.h

View file

5

drivers/gpu/drm/xe/xe_gt_types.h

View file