word-at-a-time: make the interfaces truly generic

This changes the interfaces in <asm/word-at-a-time.h> to be a bit more
complicated, but a lot more generic.

In particular, it allows us to really do the operations efficiently on
both little-endian and big-endian machines, pretty much regardless of
machine details.  For example, if you can rely on a fast population
count instruction on your architecture, this will allow you to make your
optimized <asm/word-at-a-time.h> file with that.

NOTE! The "generic" version in include/asm-generic/word-at-a-time.h is
not truly generic, it actually only works on big-endian.  Why? Because
on little-endian the generic algorithms are wasteful, since you can
inevitably do better. The x86 implementation is an example of that.

(The only truly non-generic part of the asm-generic implementation is
the "find_zero()" function, and you could make a little-endian version
of it.  And if the Kbuild infrastructure allowed us to pick a particular
header file, that would be lovely)

The <asm/word-at-a-time.h> functions are as follows:

 - WORD_AT_A_TIME_CONSTANTS: specific constants that the algorithm
   uses.

 - has_zero(): take a word, and determine if it has a zero byte in it.
   It gets the word, the pointer to the constant pool, and a pointer to
   an intermediate "data" field it can set.

   This is the "quick-and-dirty" zero tester: it's what is run inside
   the hot loops.

 - "prep_zero_mask()": take the word, the data that has_zero() produced,
   and the constant pool, and generate an *exact* mask of which byte had
   the first zero.  This is run directly *outside* the loop, and allows
   the "has_zero()" function to answer the "is there a zero byte"
   question without necessarily getting exactly *which* byte is the
   first one to contain a zero.

   If you do multiple byte lookups concurrently (eg "hash_name()", which
   looks for both NUL and '/' bytes), after you've done the prep_zero_mask()
   phase, the result of those can be or'ed together to get the "either
   or" case.

 - The result from "prep_zero_mask()" can then be fed into "find_zero()"
   (to find the byte offset of the first byte that was zero) or into
   "zero_bytemask()" (to find the bytemask of the bytes preceding the
   zero byte).

   The existence of zero_bytemask() is optional, and is not necessary
   for the normal string routines.  But dentry name hashing needs it, so
   if you enable DENTRY_WORD_AT_A_TIME you need to expose it.

This changes the generic strncpy_from_user() function and the dentry
hashing functions to use these modified word-at-a-time interfaces.  This
gets us back to the optimized state of the x86 strncpy that we lost in
the previous commit when moving over to the generic version.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/openrisc/include/asm/Kbuild

@@ -66,3 +66,4 @@ generic-y += topology.h
 generic-y += types.h
 generic-y += ucontext.h
 generic-y += user.h
+generic-y += word-at-a-time.h

arch/sparc/include/asm/Kbuild

@@ -21,3 +21,4 @@ generic-y += div64.h
 generic-y += local64.h
 generic-y += irq_regs.h
 generic-y += local.h
+generic-y += word-at-a-time.h

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

@@ -10,6 +10,11 @@
  * bit count instruction, that might be better than the multiply
  * and shift, for example.
  */
+struct word_at_a_time {
+	const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
 
 #ifdef CONFIG_64BIT
 
@@ -37,10 +42,31 @@ static inline long count_masked_bytes(long mask)
 
 #endif
 
-/* Return the high bit set in the first byte that is a zero */
-static inline unsigned long has_zero(unsigned long a)
+/* Return nonzero if it has a zero */
+static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c)
+{
+	unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits;
+	*bits = mask;
+	return mask;
+}
+
+static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c)
+{
+	return bits;
+}
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+	bits = (bits - 1) & ~bits;
+	return bits >> 7;
+}
+
+/* The mask we created is directly usable as a bytemask */
+#define zero_bytemask(mask) (mask)
+
+static inline unsigned long find_zero(unsigned long mask)
 {
-	return ((a - REPEAT_BYTE(0x01)) & ~a) & REPEAT_BYTE(0x80);
+	return count_masked_bytes(mask);
 }
 
 /*

fs/namei.c

@@ -1452,7 +1452,8 @@ EXPORT_SYMBOL(full_name_hash);
  */
 static inline unsigned long hash_name(const char *name, unsigned int *hashp)
 {
-	unsigned long a, mask, hash, len;
+	unsigned long a, b, adata, bdata, mask, hash, len;
+	const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
 
 	hash = a = 0;
 	len = -sizeof(unsigned long);
@@ -1460,17 +1461,18 @@ static inline unsigned long hash_name(const char *name, unsigned int *hashp)
 		hash = (hash + a) * 9;
 		len += sizeof(unsigned long);
 		a = load_unaligned_zeropad(name+len);
-		/* Do we have any NUL or '/' bytes in this word? */
-		mask = has_zero(a) | has_zero(a ^ REPEAT_BYTE('/'));
-	} while (!mask);
-
-	/* The mask *below* the first high bit set */
-	mask = (mask - 1) & ~mask;
-	mask >>= 7;
-	hash += a & mask;
+		b = a ^ REPEAT_BYTE('/');
+	} while (!(has_zero(a, &adata, &constants) | has_zero(b, &bdata, &constants)));
+
+	adata = prep_zero_mask(a, adata, &constants);
+	bdata = prep_zero_mask(b, bdata, &constants);
+
+	mask = create_zero_mask(adata | bdata);
+
+	hash += a & zero_bytemask(mask);
 	*hashp = fold_hash(hash);
 
-	return len + count_masked_bytes(mask);
+	return len + find_zero(mask);
 }
 
 #else

include/asm-generic/word-at-a-time.h

+#ifndef _ASM_WORD_AT_A_TIME_H
+#define _ASM_WORD_AT_A_TIME_H
+
+/*
+ * This says "generic", but it's actually big-endian only.
+ * Little-endian can use more efficient versions of these
+ * interfaces, see for example
+ *	 arch/x86/include/asm/word-at-a-time.h
+ * for those.
+ */
+
+#include <linux/kernel.h>
+
+struct word_at_a_time {
+	const unsigned long high_bits, low_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0xfe) + 1, REPEAT_BYTE(0x7f) }
+
+/* Bit set in the bytes that have a zero */
+static inline long prep_zero_mask(unsigned long val, unsigned long rhs, const struct word_at_a_time *c)
+{
+	unsigned long mask = (val & c->low_bits) + c->low_bits;
+	return ~(mask | rhs);
+}
+
+#define create_zero_mask(mask) (mask)
+
+static inline long find_zero(unsigned long mask)
+{
+	long byte = 0;
+#ifdef CONFIG_64BIT
+	if (mask >> 32)
+		mask >>= 32;
+	else
+		byte = 4;
+#endif
+	if (mask >> 16)
+		mask >>= 16;
+	else
+		byte += 2;
+	return (mask >> 8) ? byte : byte + 1;
+}
+
+static inline bool has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c)
+{
+	unsigned long rhs = val | c->low_bits;
+	*data = rhs;
+	return (val + c->high_bits) & ~rhs;
+}
+
+#endif /* _ASM_WORD_AT_A_TIME_H */

lib/strncpy_from_user.c

@@ -4,37 +4,7 @@
 #include <linux/errno.h>
 
 #include <asm/byteorder.h>
-
-static inline long find_zero(unsigned long mask)
-{
-	long byte = 0;
-
-#ifdef __BIG_ENDIAN
-#ifdef CONFIG_64BIT
-	if (mask >> 32)
-		mask >>= 32;
-	else
-		byte = 4;
-#endif
-	if (mask >> 16)
-		mask >>= 16;
-	else
-		byte += 2;
-	return (mask >> 8) ? byte : byte + 1;
-#else
-#ifdef CONFIG_64BIT
-	if (!((unsigned int) mask)) {
-		mask >>= 32;
-		byte = 4;
-	}
-#endif
-	if (!(mask & 0xffff)) {
-		mask >>= 16;
-		byte += 2;
-	}
-	return (mask & 0xff) ? byte : byte + 1;
-#endif
-}
+#include <asm/word-at-a-time.h>
 
 #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 #define IS_UNALIGNED(src, dst)	0
@@ -51,8 +21,7 @@ static inline long find_zero(unsigned long mask)
  */
 static inline long do_strncpy_from_user(char *dst, const char __user *src, long count, unsigned long max)
 {
-	const unsigned long high_bits = REPEAT_BYTE(0xfe) + 1;
-	const unsigned long low_bits = REPEAT_BYTE(0x7f);
+	const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
 	long res = 0;
 
 	/*
@@ -66,18 +35,16 @@ static inline long do_strncpy_from_user(char *dst, const char __user *src, long
 		goto byte_at_a_time;
 
 	while (max >= sizeof(unsigned long)) {
-		unsigned long c, v, rhs;
+		unsigned long c, data;
 
 		/* Fall back to byte-at-a-time if we get a page fault */
 		if (unlikely(__get_user(c,(unsigned long __user *)(src+res))))
 			break;
-		rhs = c | low_bits;
-		v = (c + high_bits) & ~rhs;
 		*(unsigned long *)(dst+res) = c;
-		if (v) {
-			v = (c & low_bits) + low_bits;
-			v = ~(v | rhs);
-			return res + find_zero(v);
+		if (has_zero(c, &data, &constants)) {
+			data = prep_zero_mask(c, data, &constants);
+			data = create_zero_mask(data);
+			return res + find_zero(data);
 		}
 		res += sizeof(unsigned long);
 		max -= sizeof(unsigned long);