Revert "intel: use throttle ioctl for throttling"

This reverts commit 50ade6ea697953bb17e3ca7210515fbd0411cd1e.

Fixes jerky rendering again on apps that don't block on the GPU per
frame and are GPU bound (e.g. 3DMMES on Ironlake).  The whole point of
this complicated throttle scheme is to wait on frame n-1 to have
started rendering before starting frame n's rendering.  Otherwise, the
GPU-bound app will race ahead and call the GL to draw many
nearly-identical frames, then >0ms later get stuck waiting for them
(all dispatched at about the same time) to retire, then render a new
batch of nearly-identical frames.

3 files changed, 13 insertions, 3 deletions

diff --git a/src/mesa/drivers/dri/intel/intel_batchbuffer.c b/src/mesa/drivers/dri/intel/intel_batchbuffer.c
index 53d6e7c6acc..377989bcc14 100644
--- a/src/mesa/drivers/dri/intel/intel_batchbuffer.c
+++ b/src/mesa/drivers/dri/intel/intel_batchbuffer.c
@@ -128,6 +128,11 @@ _intel_batchbuffer_flush(struct intel_context *intel,
    if (intel->batch.used == 0)
       return;
 
+   if (intel->first_post_swapbuffers_batch == NULL) {
+      intel->first_post_swapbuffers_batch = intel->batch.bo;
+      drm_intel_bo_reference(intel->first_post_swapbuffers_batch);
+   }
+
    if (unlikely(INTEL_DEBUG & DEBUG_BATCH))
       fprintf(stderr, "%s:%d: Batchbuffer flush with %db used\n", file, line,
 	      4*intel->batch.used);
diff --git a/src/mesa/drivers/dri/intel/intel_context.c b/src/mesa/drivers/dri/intel/intel_context.c
index 447fbe5bae1..acdf35fc71b 100644
--- a/src/mesa/drivers/dri/intel/intel_context.c
+++ b/src/mesa/drivers/dri/intel/intel_context.c
@@ -466,9 +466,11 @@ intel_prepare_render(struct intel_context *intel)
     * the swap, and getting our hands on that doesn't seem worth it,
     * so we just us the first batch we emitted after the last swap.
     */
-   if (intel->need_throttle) {
-       drmCommandNone(intel->driFd, DRM_I915_GEM_THROTTLE);
-       intel->need_throttle = GL_FALSE;
+   if (intel->need_throttle && intel->first_post_swapbuffers_batch) {
+      drm_intel_bo_wait_rendering(intel->first_post_swapbuffers_batch);
+      drm_intel_bo_unreference(intel->first_post_swapbuffers_batch);
+      intel->first_post_swapbuffers_batch = NULL;
+      intel->need_throttle = GL_FALSE;
    }
 }
 
@@ -938,6 +940,8 @@ intelDestroyContext(__DRIcontext * driContextPriv)
       intel->prim.vb = NULL;
       drm_intel_bo_unreference(intel->prim.vb_bo);
       intel->prim.vb_bo = NULL;
+      drm_intel_bo_unreference(intel->first_post_swapbuffers_batch);
+      intel->first_post_swapbuffers_batch = NULL;
 
       driDestroyOptionCache(&intel->optionCache);
 
diff --git a/src/mesa/drivers/dri/intel/intel_context.h b/src/mesa/drivers/dri/intel/intel_context.h
index c59119373da..d3a8a659caa 100644
--- a/src/mesa/drivers/dri/intel/intel_context.h
+++ b/src/mesa/drivers/dri/intel/intel_context.h
@@ -182,6 +182,7 @@ struct intel_context
       bool is_blit;
    } batch;
 
+   drm_intel_bo *first_post_swapbuffers_batch;
    GLboolean need_throttle;
    GLboolean no_batch_wrap;