drm/i915: Perform object clflushing asynchronously
Flushing the cachelines for an object is slow, can be as much as 100ms
for a large framebuffer. We currently do this under the struct_mutex BKL
on execution or on pageflip. But now with the ability to add fences to
obj->resv for both flips and execbuf (and we naturally wait on the fence
before CPU access), we can move the clflush operation to a workqueue and
signal a fence for completion, thereby doing the work asynchronously and
not blocking the driver or its clients.
v2: Introduce i915_gem_clflush.h and use a new name, split out some
extras into separate patches.
Suggested-by: Akash Goel <akash.goel@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170222114049.28456-5-chris@chris-wilson.co.uk
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 4d67cbb..2806d6b 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -37,6 +37,7 @@
#include "intel_frontbuffer.h"
#include <drm/i915_drm.h>
#include "i915_drv.h"
+#include "i915_gem_clflush.h"
#include "intel_dsi.h"
#include "i915_trace.h"
#include <drm/drm_atomic.h>
@@ -13188,6 +13189,29 @@ intel_prepare_plane_fb(struct drm_plane *plane,
struct drm_i915_gem_object *old_obj = intel_fb_obj(plane->state->fb);
int ret;
+ if (obj) {
+ if (plane->type == DRM_PLANE_TYPE_CURSOR &&
+ INTEL_INFO(dev_priv)->cursor_needs_physical) {
+ const int align = IS_I830(dev_priv) ? 16 * 1024 : 256;
+
+ ret = i915_gem_object_attach_phys(obj, align);
+ if (ret) {
+ DRM_DEBUG_KMS("failed to attach phys object\n");
+ return ret;
+ }
+ } else {
+ struct i915_vma *vma;
+
+ vma = intel_pin_and_fence_fb_obj(fb, new_state->rotation);
+ if (IS_ERR(vma)) {
+ DRM_DEBUG_KMS("failed to pin object\n");
+ return PTR_ERR(vma);
+ }
+
+ to_intel_plane_state(new_state)->vma = vma;
+ }
+ }
+
if (!obj && !old_obj)
return 0;
@@ -13240,26 +13264,6 @@ intel_prepare_plane_fb(struct drm_plane *plane,
i915_gem_object_wait_priority(obj, 0, I915_PRIORITY_DISPLAY);
}
- if (plane->type == DRM_PLANE_TYPE_CURSOR &&
- INTEL_INFO(dev_priv)->cursor_needs_physical) {
- int align = IS_I830(dev_priv) ? 16 * 1024 : 256;
- ret = i915_gem_object_attach_phys(obj, align);
- if (ret) {
- DRM_DEBUG_KMS("failed to attach phys object\n");
- return ret;
- }
- } else {
- struct i915_vma *vma;
-
- vma = intel_pin_and_fence_fb_obj(fb, new_state->rotation);
- if (IS_ERR(vma)) {
- DRM_DEBUG_KMS("failed to pin object\n");
- return PTR_ERR(vma);
- }
-
- to_intel_plane_state(new_state)->vma = vma;
- }
-
return 0;
}