drm/i915/gem: Almagamate clflushes on suspend

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@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210119214336.1463-1-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/gem/i915_gem_pm.c

@@ -11,6 +11,13 @@
 
 #include "i915_drv.h"
 
+#if defined(CONFIG_X86)
+#include <asm/smp.h>
+#else
+#define wbinvd_on_all_cpus() \
+	pr_warn(DRIVER_NAME ": Missing cache flush in %s\n", __func__)
+#endif
+
 void i915_gem_suspend(struct drm_i915_private *i915)
 {
 	GEM_TRACE("%s\n", dev_name(i915->drm.dev));
@@ -32,13 +39,6 @@ void i915_gem_suspend(struct drm_i915_private *i915)
 	i915_gem_drain_freed_objects(i915);
 }
 
-static struct drm_i915_gem_object *first_mm_object(struct list_head *list)
-{
-	return list_first_entry_or_null(list,
-					struct drm_i915_gem_object,
-					mm.link);
-}
-
 void i915_gem_suspend_late(struct drm_i915_private *i915)
 {
 	struct drm_i915_gem_object *obj;
@@ -48,6 +48,7 @@ void i915_gem_suspend_late(struct drm_i915_private *i915)
 		NULL
 	}, **phase;
 	unsigned long flags;
+	bool flush = false;
 
 	/*
 	 * Neither the BIOS, ourselves or any other kernel
@@ -73,29 +74,15 @@ void i915_gem_suspend_late(struct drm_i915_private *i915)
 
 	spin_lock_irqsave(&i915->mm.obj_lock, flags);
 	for (phase = phases; *phase; phase++) {
-		LIST_HEAD(keep);
-
-		while ((obj = first_mm_object(*phase))) {
-			list_move_tail(&obj->mm.link, &keep);
-
-			/* Beware the background _i915_gem_free_objects */
-			if (!kref_get_unless_zero(&obj->base.refcount))
-				continue;
-
-			spin_unlock_irqrestore(&i915->mm.obj_lock, flags);
-
-			i915_gem_object_lock(obj, NULL);
-			drm_WARN_ON(&i915->drm,
-			    i915_gem_object_set_to_gtt_domain(obj, false));
-			i915_gem_object_unlock(obj);
-			i915_gem_object_put(obj);
-
-			spin_lock_irqsave(&i915->mm.obj_lock, flags);
+		list_for_each_entry(obj, *phase, mm.link) {
+			if (!(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ))
+				flush |= (obj->read_domains & I915_GEM_DOMAIN_CPU) == 0;
+			__start_cpu_write(obj); /* presume auto-hibernate */
 		}
-
-		list_splice_tail(&keep, *phase);
 	}
 	spin_unlock_irqrestore(&i915->mm.obj_lock, flags);
+	if (flush)
+		wbinvd_on_all_cpus();
 }
 
 void i915_gem_resume(struct drm_i915_private *i915)