1 files changed, 46 insertions, 0 deletions

diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
new file mode 100644
index 000000000000..6fe6767b7124
--- /dev/null
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -0,0 +1,46 @@
+#ifndef _ASM_WORD_AT_A_TIME_H
+#define _ASM_WORD_AT_A_TIME_H
+
+/*
+ * This is largely generic for little-endian machines, but the
+ * optimal byte mask counting is probably going to be something
+ * that is architecture-specific. If you have a reliably fast
+ * bit count instruction, that might be better than the multiply
+ * and shift, for example.
+ */
+
+#ifdef CONFIG_64BIT
+
+/*
+ * Jan Achrenius on G+: microoptimized version of
+ * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56"
+ * that works for the bytemasks without having to
+ * mask them first.
+ */
+static inline long count_masked_bytes(unsigned long mask)
+{
+        return mask*0x0001020304050608ul >> 56;
+}
+
+#else   /* 32-bit case */
+
+/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
+static inline long count_masked_bytes(long mask)
+{
+        /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+        long a = (0x0ff0001+mask) >> 23;
+        /* Fix the 1 for 00 case */
+        return a & mask;
+}
+
+#endif
+
+#define REPEAT_BYTE(x)  ((~0ul / 0xff) * (x))
+
+/* Return the high bit set in the first byte that is a zero */
+static inline unsigned long has_zero(unsigned long a)
+{
+        return ((a - REPEAT_BYTE(0x01)) & ~a) & REPEAT_BYTE(0x80);
+}
+
+#endif /* _ASM_WORD_AT_A_TIME_H */