diff --git a/src/broadcom/compiler/vir_register_allocate.c b/src/broadcom/compiler/vir_register_allocate.c
index 66fe35371df..b22f915d1df 100644
--- a/src/broadcom/compiler/vir_register_allocate.c
+++ b/src/broadcom/compiler/vir_register_allocate.c
@@ -294,10 +294,6 @@ v3d_choose_spill_node(struct v3d_compile *c)
                         if (inst->is_last_thrsw)
                                 started_last_seg = true;
 
-                        if (v3d_qpu_writes_vpm(&inst->qpu) ||
-                            v3d_qpu_uses_tlb(&inst->qpu))
-                                started_last_seg = true;
-
                         /* Track when we're in between a TMU setup and the
                          * final LDTMU or TMUWT from that TMU setup.  We
                          * penalize spills during that time.
@@ -310,6 +306,11 @@ v3d_choose_spill_node(struct v3d_compile *c)
                 }
         }
 
+        /* We always emit a "last thrsw" to ensure all our spilling occurs
+         * before the last thread section. See vir_emit_last_thrsw.
+         */
+        assert(started_last_seg);
+
         for (unsigned i = 0; i < c->num_temps; i++) {
                 if (BITSET_TEST(c->spillable, i)) {
                         ra_set_node_spill_cost(c->g, temp_to_node(i),