i965: Use the upload BO for push constants on Gen7.5-Gen8.

We can easily use the upload BO for push constants on Gen7.5/Gen8 too,
at the cost of a relocation when emitting 3DSTATE_CONSTANT_XS.  We can
simply switch to using constant buffer pointer 2 instead of pointer 0,
like we do on Gen9+.

Ivybridge and Baytrail can't do this trick because they require the
constant buffers to be enabled in order, starting with 0.  We'd have
to set the INSTPM bit to make the constant buffer pointer not relative
to dynamic state base address, which would need kernel command parser
support.

Improves performance in GLBenchmark 2.7/TRex Offscreen by:
- Broadwell GT2: 0.305608% +/- 0.19877% (n = 68)
- Braswell: No difference proven (n = 742)
- Haswell GT3e: 0.180755% +/- 0.0237505% (n = 30)

2 files changed, 2 insertions, 2 deletions

diff --git a/src/mesa/drivers/dri/i965/gen6_constant_state.c b/src/mesa/drivers/dri/i965/gen6_constant_state.c
index 749e77e958f..f3927c5dba2 100644
--- a/src/mesa/drivers/dri/i965/gen6_constant_state.c
+++ b/src/mesa/drivers/dri/i965/gen6_constant_state.c
@@ -64,7 +64,7 @@ gen6_upload_push_constants(struct brw_context *brw,
       int i;
       const int size = prog_data->nr_params * sizeof(gl_constant_value);
       gl_constant_value *param;
-      if (brw->gen >= 9) {
+      if (brw->gen >= 8 || brw->is_haswell) {
          param = intel_upload_space(brw, size, 32, &brw->curbe.curbe_bo,
                                     &stage_state->push_const_offset);
       } else {
diff --git a/src/mesa/drivers/dri/i965/genX_state_upload.c b/src/mesa/drivers/dri/i965/genX_state_upload.c
index f7128ae8960..5fad3b72e27 100644
--- a/src/mesa/drivers/dri/i965/genX_state_upload.c
+++ b/src/mesa/drivers/dri/i965/genX_state_upload.c
@@ -2597,7 +2597,7 @@ upload_constant_state(struct brw_context *brw,
    brw_batch_emit(brw, GENX(3DSTATE_CONSTANT_VS), pkt) {
       pkt._3DCommandSubOpcode = push_constant_opcodes[stage];
       if (active) {
-#if GEN_GEN >= 9
+#if GEN_GEN >= 8 || GEN_IS_HASWELL
          pkt.ConstantBody.ConstantBuffer2ReadLength =
             stage_state->push_const_size;
          pkt.ConstantBody.PointerToConstantBuffer2 =