drm/i915: Force CPU synchronisation even if userspace requests ASYNC

The goal here was to minimise doing any thing or any check inside the
kernel that was not strictly required. For a userspace that assumes
complete control over the cache domains, the kernel is usually using
outdated information and may trigger clflushes where none were
required.

However, swapping is a situation where userspace has no knowledge of the
domain transfer, and will leave the object in the CPU cache. The kernel
must flush this out to the backing storage prior to use with the GPU. As
we use an asynchronous task tracked by an implicit fence for this, we
also need to cancel the ASYNC flag on the object so that the object will
wait for the clflush to complete before being executed. This also absolves
userspace of the responsibility imposed by commit 77ae9957897d ("drm/i915:
Enable userspace to opt-out of implicit fencing") that its needed to ensure
that the object was out of the CPU cache prior to use on the GPU.

Fixes: 77ae9957897d ("drm/i915: Enable userspace to opt-out of implicit fencing")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=101571
Signed-off-by: Chris Wilson <[e-mail]>
Cc: Joonas Lahtinen <[e-mail]>
Cc: Jason Ekstrand <[e-mail]>
Reviewed-by: Jason Ekstrand <[e-mail]>
Link: https://patchwork.freedesktop.org/patch/msgid/[e-mail]
Reviewed-by: Joonas Lahtinen <[e-mail]>
Signed-off-by: Daniel Vetter <[e-mail]>
(cherry picked from commit 0f46daa1a273779a0b73d768a788ca3f04238f9c)
Cc: [e-mail]
Signed-off-by: Daniel Vetter <[e-mail]>

drivers/gpu/drm/i915/i915_gem_clflush.c

···
 	return NOTIFY_DONE;
 }
 
-void i915_gem_clflush_object(struct drm_i915_gem_object *obj,
+bool i915_gem_clflush_object(struct drm_i915_gem_object *obj,
 			     unsigned int flags)
 {
 	struct clflush *clflush;
···
 	 */
 	if (!i915_gem_object_has_struct_page(obj)) {
 		obj->cache_dirty = false;
-		return;
+		return false;
 	}
 
 	/* If the GPU is snooping the contents of the CPU cache,
···
 	 * tracking.
 	 */
 	if (!(flags & I915_CLFLUSH_FORCE) && obj->cache_coherent)
-		return;
+		return false;
 
 	trace_i915_gem_object_clflush(obj);
 
···
 	}
 
 	obj->cache_dirty = false;
+	return true;
 }

drivers/gpu/drm/i915/i915_gem_clflush.h

···
 struct drm_i915_private;
 struct drm_i915_gem_object;
 
-void i915_gem_clflush_object(struct drm_i915_gem_object *obj,
+bool i915_gem_clflush_object(struct drm_i915_gem_object *obj,
 			     unsigned int flags);
 #define I915_CLFLUSH_FORCE BIT(0)
 #define I915_CLFLUSH_SYNC BIT(1)

drivers/gpu/drm/i915/i915_gem_execbuffer.c

···
 	int err;
 
 	for (i = 0; i < count; i++) {
-		const struct drm_i915_gem_exec_object2 *entry = &eb->exec[i];
+		struct drm_i915_gem_exec_object2 *entry = &eb->exec[i];
 		struct i915_vma *vma = exec_to_vma(entry);
 		struct drm_i915_gem_object *obj = vma->obj;
 
···
 			eb->request->capture_list = capture;
 		}
 
+		if (unlikely(obj->cache_dirty && !obj->cache_coherent)) {
+			if (i915_gem_clflush_object(obj, 0))
+				entry->flags &= ~EXEC_OBJECT_ASYNC;
+		}
+
 		if (entry->flags & EXEC_OBJECT_ASYNC)
 			goto skip_flushes;
-
-		if (unlikely(obj->cache_dirty && !obj->cache_coherent))
-			i915_gem_clflush_object(obj, 0);
 
 		err = i915_gem_request_await_object
 			(eb->request, obj, entry->flags & EXEC_OBJECT_WRITE);