intel: Throttle after doing copyregion/swapbuffers round trip

Before we would throttle in the flush callback prior to round-tripping
to the server to do copyregion or swapbuffer.  Now, instead just note
that we need to throttle and do it in intel_prepare_render(), which
will be called after receiving the response from the server but before
we start rendering the next frame.  Even if the server also throttles
us in swapbuffer, this just makes the throttling a no-op when we hit
intel_prepare_render().  With that we can drop the
using_dri2_swapbuffers hack and just always throttle.

src/mesa/drivers/dri/intel/intel_batchbuffer.c

@@ -130,8 +130,7 @@ _intel_batchbuffer_flush(struct intel_batchbuffer *batch, const char *file,
    struct intel_context *intel = batch->intel;
    GLuint used = batch->ptr - batch->map;
 
-   if (!intel->using_dri2_swapbuffers &&
+   if (intel->first_post_swapbuffers_batch == NULL) {
-       intel->first_post_swapbuffers_batch == NULL) {
       intel->first_post_swapbuffers_batch = intel->batch->buf;
       drm_intel_bo_reference(intel->first_post_swapbuffers_batch);
    }

src/mesa/drivers/dri/intel/intel_context.c

@@ -440,6 +440,28 @@ intel_prepare_render(struct intel_context *intel)
     */
    if (intel->is_front_buffer_rendering)
       intel->front_buffer_dirty = GL_TRUE;
+
+   /* Wait for the swapbuffers before the one we just emitted, so we
+    * don't get too many swaps outstanding for apps that are GPU-heavy
+    * but not CPU-heavy.
+    *
+    * We're using intelDRI2Flush (called from the loader before
+    * swapbuffer) and glFlush (for front buffer rendering) as the
+    * indicator that a frame is done and then throttle when we get
+    * here as we prepare to render the next frame.  At this point for
+    * round trips for swap/copy and getting new buffers are done and
+    * we'll spend less time waiting on the GPU.
+    *
+    * Unfortunately, we don't have a handle to the batch containing
+    * 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 && 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;
+   }
 }
 
 static void
@@ -451,8 +473,7 @@ intel_viewport(GLcontext *ctx, GLint x, GLint y, GLsizei w, GLsizei h)
     if (intel->saved_viewport)
 	intel->saved_viewport(ctx, x, y, w, h);
 
-    if (!intel->using_dri2_swapbuffers &&
+    if (!intel->meta.internal_viewport_call && ctx->DrawBuffer->Name == 0) {
-	!intel->meta.internal_viewport_call && ctx->DrawBuffer->Name == 0) {
        dri2InvalidateDrawable(driContext->driDrawablePriv);
        dri2InvalidateDrawable(driContext->driReadablePriv);
     }
@@ -530,27 +551,8 @@ intel_glFlush(GLcontext *ctx)
    struct intel_context *intel = intel_context(ctx);
 
    intel_flush(ctx);
-
    intel_flush_front(ctx);
-
+   intel->need_throttle = GL_TRUE;
-   /* We're using glFlush as an indicator that a frame is done, which is
-    * what DRI2 does before calling SwapBuffers (and means we should catch
-    * people doing front-buffer rendering, as well)..
-    *
-    * Wait for the swapbuffers before the one we just emitted, so we don't
-    * get too many swaps outstanding for apps that are GPU-heavy but not
-    * CPU-heavy.
-    *
-    * Unfortunately, we don't have a handle to the batch containing 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->using_dri2_swapbuffers &&
-       intel->first_post_swapbuffers_batch != NULL) {
-      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;
-   }
 }
 
 void

src/mesa/drivers/dri/intel/intel_context.h

@@ -150,8 +150,8 @@ struct intel_context
 
    struct intel_batchbuffer *batch;
    drm_intel_bo *first_post_swapbuffers_batch;
+   GLboolean need_throttle;
    GLboolean no_batch_wrap;
-   GLboolean using_dri2_swapbuffers;
 
    struct
    {

src/mesa/drivers/dri/intel/intel_screen.c

@@ -110,23 +110,16 @@ intelDRI2Flush(__DRIdrawable *drawable)
    if (intel->gen < 4)
       INTEL_FIREVERTICES(intel);
 
+   intel->need_throttle = GL_TRUE;
+
    if (intel->batch->map != intel->batch->ptr)
       intel_batchbuffer_flush(intel->batch);
 }
 
-static void
-intelDRI2Invalidate(__DRIdrawable *drawable)
-{
-   struct intel_context *intel = drawable->driContextPriv->driverPrivate;
-
-   intel->using_dri2_swapbuffers = GL_TRUE;
-   dri2InvalidateDrawable(drawable);
-}
-
 static const struct __DRI2flushExtensionRec intelFlushExtension = {
     { __DRI2_FLUSH, __DRI2_FLUSH_VERSION },
     intelDRI2Flush,
-    intelDRI2Invalidate,
+    dri2InvalidateDrawable,
 };
 
 static __DRIimage *