Make the "word-at-a-time" helper functions more commonly usable

I have a new optimized x86 "strncpy_from_user()" that will use these
same helper functions for all the same reasons the name lookup code uses
them. This is preparation for that.

This moves them into an architecture-specific header file. It's
architecture-specific for two reasons:

- some of the functions are likely to want architecture-specific
implementations. Even if the current code happens to be "generic" in
the sense that it should work on any little-endian machine, it's
likely that the "multiply by a big constant and shift" implementation
is less than optimal for an architecture that has a guaranteed fast
bit count instruction, for example.

- I expect that if architectures like sparc want to start playing
around with this, we'll need to abstract out a few more details (in
particular the actual unaligned accesses). So we're likely to have
more architecture-specific stuff if non-x86 architectures start using
this.

(and if it turns out that non-x86 architectures don't start using
this, then having it in an architecture-specific header is still the
right thing to do, of course)

Signed-off-by: Linus Torvalds <[e-mail]>

arch/x86/include/asm/word-at-a-time.h

···
+#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 */

fs/namei.c

···
  */
 #ifdef CONFIG_DCACHE_WORD_ACCESS
 
-#ifdef CONFIG_64BIT
+#include <asm/word-at-a-time.h>
 
-/*
- * 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;
-}
+#ifdef CONFIG_64BIT
 
 static inline unsigned int fold_hash(unsigned long hash)
 {
···
 }
 
 #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;
-}
 
 #define fold_hash(x) (x)
 
···
 }
 EXPORT_SYMBOL(full_name_hash);
 
-#define REPEAT_BYTE(x)	((~0ul / 0xff) * (x))
-#define ONEBYTES	REPEAT_BYTE(0x01)
-#define SLASHBYTES	REPEAT_BYTE('/')
-#define HIGHBITS	REPEAT_BYTE(0x80)
-
-/* Return the high bit set in the first byte that is a zero */
-static inline unsigned long has_zero(unsigned long a)
-{
-	return ((a - ONEBYTES) & ~a) & HIGHBITS;
-}
-
 /*
  * Calculate the length and hash of the path component, and
  * return the length of the component;
···
 		len += sizeof(unsigned long);
 		a = *(unsigned long *)(name+len);
 		/* Do we have any NUL or '/' bytes in this word? */
-		mask = has_zero(a) | has_zero(a ^ SLASHBYTES);
+		mask = has_zero(a) | has_zero(a ^ REPEAT_BYTE('/'));
 	} while (!mask);
 
 	/* The mask *below* the first high bit set */