iris: Report use of any in-flight buffers on first draw call after sync boundary.

This is the main performance trade-off of this cache tracking
mechanism: In order for the seqno vector of buffer objects to be
accurate, they need to be marked as used again every time the batch is
split into a new synchronization section if they remain bound to the
pipeline.  This can be achieved easily by re-using
iris_restore_render_saved_bos() and iris_restore_compute_saved_bos(),
which currently serve a similar purpose across batch buffer
boundaries.

The impact on Piglit drawoverhead results seems to be within a
standard deviation of the current results.

XXX - It might be possible to completely remove the current
      iris_batch::contains_draw flag at a small additional performance
      cost.

Reviewed-by: Kenneth Graunke <[email protected]>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3875>

1 files changed, 4 insertions, 0 deletions

diff --git a/src/gallium/drivers/iris/iris_batch.h b/src/gallium/drivers/iris/iris_batch.h
index bfea20d268c..00f62f2fb6f 100644
--- a/src/gallium/drivers/iris/iris_batch.h
+++ b/src/gallium/drivers/iris/iris_batch.h
@@ -153,6 +153,9 @@ struct iris_batch {
    /** Have we emitted any draw calls to this batch? */
    bool contains_draw;
 
+   /** Have we emitted any draw calls with next_seqno? */
+   bool contains_draw_with_next_seqno;
+
    /**
     * Number of times iris_batch_sync_region_start() has been called without a
     * matching iris_batch_sync_region_end() on this batch.
@@ -304,6 +307,7 @@ static inline void
 iris_batch_sync_boundary(struct iris_batch *batch)
 {
    if (!batch->sync_region_depth) {
+      batch->contains_draw_with_next_seqno = false;
       batch->next_seqno = p_atomic_inc_return(&batch->screen->last_seqno);
       assert(batch->next_seqno > 0);
    }