#endif
#endif
+
+/*
+ * Performance might be improved if the CPU architecture is OK with
+ * unaligned 32-bit loads and a fast ntohl() is available.
+ * Otherwise fall back to byte loads and shifts which is portable,
+ * and is faster on architectures with memory alignment issues.
+ */
+
+#if defined(__i386__) || defined(__x86_64__) || \
+ defined(_M_IX86) || defined(_M_X64) || \
+ defined(__ppc__) || defined(__ppc64__) || \
+ defined(__powerpc__) || defined(__powerpc64__) || \
+ defined(__s390__) || defined(__s390x__)
+
+#define get_be16(p) ntohs(*(unsigned short *)(p))
+#define get_be32(p) ntohl(*(unsigned int *)(p))
+#define put_be32(p, v) do { *(unsigned int *)(p) = htonl(v); } while (0)
+
+#else
+
+#define get_be16(p) ( \
+ (*((unsigned char *)(p) + 0) << 8) | \
+ (*((unsigned char *)(p) + 1) << 0) )
+#define get_be32(p) ( \
+ (*((unsigned char *)(p) + 0) << 24) | \
+ (*((unsigned char *)(p) + 1) << 16) | \
+ (*((unsigned char *)(p) + 2) << 8) | \
+ (*((unsigned char *)(p) + 3) << 0) )
+#define put_be32(p, v) do { \
+ unsigned int __v = (v); \
+ *((unsigned char *)(p) + 0) = __v >> 24; \
+ *((unsigned char *)(p) + 1) = __v >> 16; \
+ *((unsigned char *)(p) + 2) = __v >> 8; \
+ *((unsigned char *)(p) + 3) = __v >> 0; } while (0)
+
+#endif