When flushing objects larger than the CPU cache it is preferrable to use
a single wbinvd() rather than overlapping clflush(). At runtime, we
avoid wbinvd() due to its system-wide latencies, but during
singlethreaded suspend, no one will observe the imposed latency and we
can opt for the faster wbinvd to clear all objects in a single hit.
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/i915_gem.c | 16 +++++-----------
1 file changed, 5 insertions(+), 11 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 17a4636ee542..21194ebfc31e 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1277,19 +1277,13 @@ int i915_gem_freeze_late(struct drm_i915_private *i915)
* the objects as well, see i915_gem_freeze()
*/
- wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
- i915_gem_shrink(i915, -1UL, NULL, ~0);
+ with_intel_runtime_pm(&i915->runtime_pm, wakeref)
+ i915_gem_shrink(i915, -1UL, NULL, ~0);
i915_gem_drain_freed_objects(i915);
- list_for_each_entry(obj, &i915->mm.shrink_list, mm.link) {
- i915_gem_object_lock(obj, NULL);
- drm_WARN_ON(&i915->drm,
- i915_gem_object_set_to_cpu_domain(obj, true));
- i915_gem_object_unlock(obj);
- }
-
- intel_runtime_pm_put(&i915->runtime_pm, wakeref);
+ wbinvd_on_all_cpus();
+ list_for_each_entry(obj, &i915->mm.shrink_list, mm.link)
+ __start_cpu_write(obj);
return 0;
}
--
2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
