+#ifdef __NO_LWSYNC__
+#define LWSYNC_OPCODE "sync\n"
+#else
+#define LWSYNC_OPCODE "lwsync\n"
+#endif
+
+/*
+ * Use sync for all cmm_mb/rmb/wmb barriers because lwsync does not
+ * preserve ordering of cacheable vs. non-cacheable accesses, so it
+ * should not be used to order with respect to MMIO operations. An
+ * eieio+lwsync pair is also not enough for cmm_rmb, because it will
+ * order cacheable and non-cacheable memory operations separately---i.e.
+ * not the latter against the former.
+ */
+#define cmm_mb() __asm__ __volatile__ ("sync":::"memory")
+
+/*
+ * lwsync orders loads in cacheable memory with respect to other loads,
+ * and stores in cacheable memory with respect to other stores.
+ * Therefore, use it for barriers ordering accesses to cacheable memory
+ * only.
+ */
+#define cmm_smp_rmb() __asm__ __volatile__ (LWSYNC_OPCODE:::"memory")
+#define cmm_smp_wmb() __asm__ __volatile__ (LWSYNC_OPCODE:::"memory")