i965/fs: Always set channel 2 of texture headers in some stages

In the vertex and fragment stages, the hardware is nice to us and leaves
g0.2 zerod out for us so we can use it for headers.  However, in compute,
geometry, and tessellation stages, the hardware is not so nice.  In
particular, for compute shaders on BDW, the hardware places some debug bits
in 23:15.  As it happens, bit 15 is interpreted by the sampler as the alpha
channel mask.  This means that if you use a texturing instruction with a
header in a compute shader, you may randomly get the alpha channel
disabled.  Since channel masks affect the return length of the sampler
message, this can lead the GPU to expect a different mlen to the one you
specified in the shader and this, in turn, hangs your GPU.

Cc: "11.1" <[email protected]>
Reviewed-by: Jordan Justen <[email protected]>

1 files changed, 8 insertions, 0 deletions

diff --git a/src/mesa/drivers/dri/i965/brw_fs_generator.cpp b/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
index 741a77ba566..e05622ae7a8 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_generator.cpp
@@ -913,6 +913,14 @@ fs_generator::generate_tex(fs_inst *inst, struct brw_reg dst, struct brw_reg src
             /* Set the offset bits in DWord 2. */
             brw_MOV(p, get_element_ud(header_reg, 2),
                        brw_imm_ud(inst->offset));
+         } else if (stage != MESA_SHADER_VERTEX &&
+                    stage != MESA_SHADER_FRAGMENT) {
+            /* The vertex and fragment stages have g0.2 set to 0, so
+             * header0.2 is 0 when g0 is copied. Other stages may not, so we
+             * must set it to 0 to avoid setting undesirable bits in the
+             * message.
+             */
+            brw_MOV(p, get_element_ud(header_reg, 2), brw_imm_ud(0));
          }
 
          brw_adjust_sampler_state_pointer(p, header_reg, sampler_index);