commit 30960841be23f271ec578ebedb699b419a86b7d2
Author: Nicolai Hähnle <nicolai.haehnle@amd.com>
Date:   Mon Jun 12 10:53:07 2017 +0200

    st/glsl_to_tgsi: use correct writemask when converting generic intrinsics
    
    This fixes a bug when lowering ballotARB: previously, using writemask 0xf,
    emit_asm would create TGSI_OPCODE_BALLOT instructions that span two registers
    to cover 4 64-bit channels. This could trample over other a neighbouring
    temporary.
    
    Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=101360
    Cc: 17.1 <mesa-stable@lists.freedesktop.org>

diff --git a/src/mesa/state_tracker/st_glsl_to_tgsi.cpp b/src/mesa/state_tracker/st_glsl_to_tgsi.cpp
index a7ca4f2..43654d2 100644
--- a/src/mesa/state_tracker/st_glsl_to_tgsi.cpp
+++ b/src/mesa/state_tracker/st_glsl_to_tgsi.cpp
@@ -3914,20 +3914,22 @@ glsl_to_tgsi_visitor::visit_image_intrinsic(ir_call *ir)
    if (imgvar->data.memory_volatile)
       inst->buffer_access |= TGSI_MEMORY_VOLATILE;
 }
 
 void
 glsl_to_tgsi_visitor::visit_generic_intrinsic(ir_call *ir, unsigned op)
 {
    ir->return_deref->accept(this);
    st_dst_reg dst = st_dst_reg(this->result);
 
+   dst.writemask = u_bit_consecutive(0, ir->return_deref->var->type->vector_elements);
+
    st_src_reg src[4] = { undef_src, undef_src, undef_src, undef_src };
    unsigned num_src = 0;
    foreach_in_list(ir_rvalue, param, &ir->actual_parameters) {
       assert(num_src < ARRAY_SIZE(src));
 
       this->result.file = PROGRAM_UNDEFINED;
       param->accept(this);
       assert(this->result.file != PROGRAM_UNDEFINED);
 
       src[num_src] = this->result;