i965: Use a WC map and memcpy for the batch instead of pwrite.

We'd like to eliminate the malloc'd shadow copy eventually, but there
are still unresolved performance problems.  In the meantime, let's at
least get rid of pwrite.

On Apollolake, improves Synmark OglBatch6 performance by:
1.53581% +/- 0.269589% (n=108).

Reviewed-by: Matt Turner <[email protected]>
Reviewed-by: Chris Wilson <[email protected]>

1 files changed, 8 insertions, 10 deletions

diff --git a/src/mesa/drivers/dri/i965/intel_batchbuffer.c b/src/mesa/drivers/dri/i965/intel_batchbuffer.c
index 276fe458a13..9cd491b5ace 100644
--- a/src/mesa/drivers/dri/i965/intel_batchbuffer.c
+++ b/src/mesa/drivers/dri/i965/intel_batchbuffer.c
@@ -629,18 +629,16 @@ do_flush_locked(struct brw_context *brw, int in_fence_fd, int *out_fence_fd)
    struct intel_batchbuffer *batch = &brw->batch;
    int ret = 0;
 
-   if (devinfo->has_llc) {
-      brw_bo_unmap(batch->bo);
-   } else {
-      ret = brw_bo_subdata(batch->bo, 0, 4 * USED_BATCH(*batch), batch->map);
-      if (ret == 0 && batch->state_batch_offset != batch->bo->size) {
-         ret = brw_bo_subdata(batch->bo,
-                              batch->state_batch_offset,
-                              batch->bo->size - batch->state_batch_offset,
-                              (char *)batch->map + batch->state_batch_offset);
-      }
+   if (batch->cpu_map) {
+      void *bo_map = brw_bo_map(brw, batch->bo, MAP_WRITE);
+      memcpy(bo_map, batch->cpu_map, 4 * USED_BATCH(*batch));
+      memcpy(bo_map + batch->state_batch_offset,
+             (char *) batch->cpu_map + batch->state_batch_offset,
+             batch->bo->size - batch->state_batch_offset);
    }
 
+   brw_bo_unmap(batch->bo);
+
    if (!brw->screen->no_hw) {
       /* The requirement for using I915_EXEC_NO_RELOC are:
        *