diff --git a/src/broadcom/ci/broadcom-rpi4-fails.txt b/src/broadcom/ci/broadcom-rpi4-fails.txt
index d4bbc72b7ea..49192c9db8e 100644
--- a/src/broadcom/ci/broadcom-rpi4-fails.txt
+++ b/src/broadcom/ci/broadcom-rpi4-fails.txt
@@ -418,7 +418,5 @@ dEQP-VK.api.external.semaphore.sync_fd.info_timeline,Fail
 
 dEQP-VK.draw.renderpass.inverted_depth_ranges.nodepthclamp_deltazero,Fail
 
-dEQP-VK.graphicsfuzz.cov-dfdx-dfdy-after-nested-loops,Fail
-
 # Works if using V3D_DEBUG=noloopunroll
 dEQP-VK.graphicsfuzz.cov-loop-condition-clamp-vec-of-ones,Crash
diff --git a/src/broadcom/compiler/vir_register_allocate.c b/src/broadcom/compiler/vir_register_allocate.c
index afd2cc89b0f..f7f177bdd62 100644
--- a/src/broadcom/compiler/vir_register_allocate.c
+++ b/src/broadcom/compiler/vir_register_allocate.c
@@ -343,10 +343,14 @@ v3d_emit_spill_tmua(struct v3d_compile *c,
         struct qreg offset = vir_uniform_ui(c, spill_offset);
         add_node(c, offset.index, CLASS_BITS_ANY);
 
-        struct qinst *inst =
-                vir_ADD_dest(c, vir_reg(QFILE_MAGIC, V3D_QPU_WADDR_TMUA),
-                             c->spill_base, offset);
+        /* We always enable per-quad on spills/fills to ensure we spill
+         * any channels involved with helper invocations.
+         */
+        struct qreg tmua = vir_reg(QFILE_MAGIC, V3D_QPU_WADDR_TMUAU);
+        struct qinst *inst = vir_ADD_dest(c, tmua, c->spill_base, offset);
         inst->qpu.flags.ac = cond;
+        inst->uniform = vir_get_uniform_index(c, QUNIFORM_CONSTANT,
+                                              0xffffff7f); /* per-quad */
 
         vir_emit_thrsw(c);