vc4: Make sure that we don't overwrite the signal for PROG_END.

We should have already emitted a NOP due to the last instruction being a
TLB or VPM write.  However, if you disable dead code elimination then you
might get dead code at the end, and that dead code might have the signal
bits set to something non-default, at which point you die in assertion
failure.

src/gallium/drivers/vc4/vc4_qpu_emit.c

@@ -510,6 +510,14 @@ vc4_generate_code(struct vc4_context *vc4, struct vc4_compile *c)
         if (qpu_inst_is_tlb(c->qpu_insts[c->qpu_inst_count - 1]))
                 qpu_serialize_one_inst(c, qpu_NOP());
 
+        /* Make sure there's no existing signal set (like for a small
+         * immediate)
+         */
+        if (QPU_GET_FIELD(c->qpu_insts[c->qpu_inst_count - 1],
+                          QPU_SIG) != QPU_SIG_NONE) {
+                qpu_serialize_one_inst(c, qpu_NOP());
+        }
+
         c->qpu_insts[c->qpu_inst_count - 1] =
                 qpu_set_sig(c->qpu_insts[c->qpu_inst_count - 1],
                             QPU_SIG_PROG_END);