+static inline uint16_t
+virtqueue_fetch_flags_packed(struct vring_packed_desc *dp,
+ uint8_t weak_barriers)
+{
+ uint16_t flags;
+
+ if (weak_barriers) {
+/* x86 prefers to using rte_smp_rmb over __atomic_load_n as it reports
+ * a better perf(~1.5%), which comes from the saved branch by the compiler.
+ * The if and else branch are identical with the smp and cio barriers both
+ * defined as compiler barriers on x86.
+ */
+#ifdef RTE_ARCH_X86_64
+ flags = dp->flags;
+ rte_smp_rmb();
+#else
+ flags = __atomic_load_n(&dp->flags, __ATOMIC_ACQUIRE);
+#endif
+ } else {
+ flags = dp->flags;
+ rte_cio_rmb();
+ }
+
+ return flags;
+}
+