i965/fs: Consult brw_wm_prog_data::num_varying_inputs when setting up WM state.

Previously, we assumed that the number of varying inputs consumed by
the fragment shader was equal to the number of bits set in
gl_program::InputsRead.  However, we'll soon be making two changes
that will cause that not to be true:

- We'll stop wasting varying input space for gl_FragCoord and
  gl_FrontFacing, which aren't varyings.

- For fragment shaders that have more than 16 varying inputs, we'll
  adjust the layout of the inputs to account for the fact that the
  SF/SBE pipeline stage can't reorder inputs beyond the first 16; if
  there are GS outputs that the FS doens't use (or vice versa) this
  may cause the number of FS varying inputs to change.

So, instead of trying to guess the number of FS inputs from
gl_program::InputsRead, simply read it from
brw_wm_prog_data:num_varying_inputs, which is guaranteed to be correct
since it's populated by fs_visitor::calculate_urb_setup().

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>

diff --git a/src/mesa/drivers/dri/i965/gen6_wm_state.c b/src/mesa/drivers/dri/i965/gen6_wm_state.c
index 2b9f19c629b136a417bd6052b9b582185a12f23d..af1c044589aeae0bec9c079b7d716e259bf195c6 100644 (file)
--- a/src/mesa/drivers/dri/i965/gen6_wm_state.c
+++ b/src/mesa/drivers/dri/i965/gen6_wm_state.c
@@ -188,7 +188,8 @@ upload_wm_state(struct brw_context *brw)
       dw5 |= GEN6_WM_DISPATCH_ENABLE;
    }
 
-   dw6 |= _mesa_bitcount_64(brw->fragment_program->Base.InputsRead) <<
+   /* CACHE_NEW_WM_PROG */
+   dw6 |= brw->wm.prog_data->num_varying_inputs <<
       GEN6_WM_NUM_SF_OUTPUTS_SHIFT;
    if (multisampled_fbo) {
       /* _NEW_MULTISAMPLE */

diff --git a/src/mesa/drivers/dri/i965/gen7_wm_state.c b/src/mesa/drivers/dri/i965/gen7_wm_state.c
index e7bb861d5d49931e68b9fa4139b07d1aecc73fb4..e9fe95f1f1ee756ab3eb53081cf5237be7067c6b 100644 (file)
--- a/src/mesa/drivers/dri/i965/gen7_wm_state.c
+++ b/src/mesa/drivers/dri/i965/gen7_wm_state.c
@@ -168,6 +168,7 @@ upload_ps_state(struct brw_context *brw)
     * rendering, CurrentFragmentProgram is used for this check to
     * differentiate between the GLSL and non-GLSL cases.
     */
+   /* BRW_NEW_FRAGMENT_PROGRAM */
    if (ctx->Shader.CurrentFragmentProgram == NULL)
       dw2 |= GEN7_PS_FLOATING_POINT_MODE_ALT;
 
@@ -191,8 +192,8 @@ upload_ps_state(struct brw_context *brw)
       dw4 |= GEN7_PS_DUAL_SOURCE_BLEND_ENABLE;
    }
 
-   /* BRW_NEW_FRAGMENT_PROGRAM */
-   if (brw->fragment_program->Base.InputsRead != 0)
+   /* CACHE_NEW_WM_PROG */
+   if (brw->wm.prog_data->num_varying_inputs != 0)
       dw4 |= GEN7_PS_ATTRIBUTE_ENABLE;
 
    dw4 |= GEN7_PS_8_DISPATCH_ENABLE;