+/*
+ * Portable strlen() for 32-bit and 64-bit systems.
+ *
+ * Rationale: it is generally much more efficient to do word length
+ * operations and avoid branches on modern computer systems, as
+ * compared to byte-length operations with a lot of branches.
+ *
+ * The expression:
+ *
+ * ((x - 0x01....01) & ~x & 0x80....80)
+ *
+ * would evaluate to a non-zero value iff any of the bytes in the
+ * original word is zero. However, we can further reduce ~1/3 of
+ * time if we consider that strlen() usually operate on 7-bit ASCII
+ * by employing the following expression, which allows false positive
+ * when high bit of 1 and use the tail case to catch these case:
+ *
+ * ((x - 0x01....01) & 0x80....80)
+ *
+ * This is more than 5.2 times as fast as the raw implementation on
+ * Intel T7300 under long mode for strings longer than word length.
+ */
+
+/* Magic numbers for the algorithm */
+#if LONG_BIT == 32
+static const unsigned long mask01 = 0x01010101;
+static const unsigned long mask80 = 0x80808080;
+#elif LONG_BIT == 64
+static const unsigned long mask01 = 0x0101010101010101;
+static const unsigned long mask80 = 0x8080808080808080;
+#else
+#error Unsupported word size
+#endif
+
+#define LONGPTR_MASK (sizeof(long) - 1)
+
+/*
+ * Helper macro to return string length if we caught the zero
+ * byte.
+ */
+#define testbyte(x) \
+ do { \
+ if (p[x] == '\0') \
+ return (p - str + x); \
+ } while (0)
+