[PATCH v4 1/3] lib: find_*_bit reimplementation

[Yury Norov <yury.norov@gmail.com>]

The new implementation takes less space in the sources
(see diffstat) and in the object. For me it's 710 vs 453
bytes of text. It also shows a better performance.

find_last_bit description fixed due to obvious typo.

In this patch 2 macros were introduced: {LOW,HIGH}_BITS_MASK,
that are doing almost the same as BITMAP_{FIRST,LAST}_WORD_MASK
in include/linux/bitmap.h. But 'LAST' macro is potentially less
effective, because it issues a conditional branch that can be
omitted.  If it is replaced one day by a more effective
implementation, {LOW,HIGH}_BITS_MASK can be removed.

Signed-off-by: Yury Norov <yury.norov@gmail.com>
---
 include/linux/bitops.h |   4 +-
 lib/find_last_bit.c    |  37 +++----
 lib/find_next_bit.c    | 269 ++++++++++++++-----------------------------------
 3 files changed, 94 insertions(+), 216 deletions(-)

diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 5d858e0..297f5bd 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -218,9 +218,9 @@ static inline unsigned long __ffs64(u64 word)
 /**
  * find_last_bit - find the last set bit in a memory region
  * @addr: The address to start the search at
- * @size: The maximum size to search
+ * @size: The number of bits to search
  *
- * Returns the bit number of the first set bit, or size.
+ * Returns the bit number of the last set bit, or size.
  */
 extern unsigned long find_last_bit(const unsigned long *addr,
 				   unsigned long size);
diff --git a/lib/find_last_bit.c b/lib/find_last_bit.c
index 91ca09f..edbb281 100644
--- a/lib/find_last_bit.c
+++ b/lib/find_last_bit.c
@@ -4,6 +4,9 @@
  * Written by Rusty Russell <rusty@rustcorp.com.au>
  * (Inspired by David Howell's find_next_bit implementation)
  *
+ * Rewritten by Yury Norov <yury.norov@gmail.com> to decrease
+ * size and improve performance, 2015.
+ *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
  * as published by the Free Software Foundation; either version
@@ -12,36 +15,26 @@
 
 #include <linux/bitops.h>
 #include <linux/export.h>
-#include <asm/types.h>
-#include <asm/byteorder.h>
+#include <linux/kernel.h>
+
+#define LOW_BITS_MASK(nr) (~0UL >> -(nr))
 
 #ifndef find_last_bit
 
 unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
 {
-	unsigned long words;
-	unsigned long tmp;
+	if (size) {
+		unsigned long val = LOW_BITS_MASK(size % BITS_PER_LONG);
+		unsigned long idx = (size-1) / BITS_PER_LONG;
 
-	/* Start at final word. */
-	words = size / BITS_PER_LONG;
+		do {
+			val &= addr[idx];
+			if (val)
+				return idx * BITS_PER_LONG + __fls(val);
 
-	/* Partial final word? */
-	if (size & (BITS_PER_LONG-1)) {
-		tmp = (addr[words] & (~0UL >> (BITS_PER_LONG
-					 - (size & (BITS_PER_LONG-1)))));
-		if (tmp)
-			goto found;
+			val = ~0ul;
+		} while (idx--);
 	}
-
-	while (words) {
-		tmp = addr[--words];
-		if (tmp) {
-found:
-			return words * BITS_PER_LONG + __fls(tmp);
-		}
-	}
-
-	/* Not found */
 	return size;
 }
 EXPORT_SYMBOL(find_last_bit);
diff --git a/lib/find_next_bit.c b/lib/find_next_bit.c
index 0cbfc0b..1f5f108 100644
--- a/lib/find_next_bit.c
+++ b/lib/find_next_bit.c
@@ -3,6 +3,9 @@
  * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
  *
+ * Rewritten by Yury Norov <yury.norov@gmail.com> to decrease
+ * size and improve performance, 2015.
+ *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
  * as published by the Free Software Foundation; either version
@@ -11,98 +14,60 @@
 
 #include <linux/bitops.h>
 #include <linux/export.h>
-#include <asm/types.h>
-#include <asm/byteorder.h>
+#include <linux/kernel.h>
 
-#define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)
+#define HIGH_BITS_MASK(nr)		(~0UL << (nr))
+
+#if !defined(find_next_bit) || !defined(find_next_zero_bit)
 
-#ifndef find_next_bit
 /*
- * Find the next set bit in a memory region.
+ * This is a common helper function for find_next_bit and
+ * find_next_zero_bit.  The difference is the "invert" argument, which
+ * is XORed with each fetched word before searching it for one bits.
  */
-unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
-			    unsigned long offset)
+static unsigned long _find_next_bit(const unsigned long *addr,
+		unsigned long nbits, unsigned long start, unsigned long invert)
 {
-	const unsigned long *p = addr + BITOP_WORD(offset);
-	unsigned long result = offset & ~(BITS_PER_LONG-1);
 	unsigned long tmp;
 
-	if (offset >= size)
-		return size;
-	size -= result;
-	offset %= BITS_PER_LONG;
-	if (offset) {
-		tmp = *(p++);
-		tmp &= (~0UL << offset);
-		if (size < BITS_PER_LONG)
-			goto found_first;
-		if (tmp)
-			goto found_middle;
-		size -= BITS_PER_LONG;
-		result += BITS_PER_LONG;
-	}
-	while (size & ~(BITS_PER_LONG-1)) {
-		if ((tmp = *(p++)))
-			goto found_middle;
-		result += BITS_PER_LONG;
-		size -= BITS_PER_LONG;
+	if (!nbits || start >= nbits)
+		return nbits;
+
+	tmp = addr[start / BITS_PER_LONG] ^ invert;
+
+	/* Handle 1st word. */
+	tmp &= HIGH_BITS_MASK(start % BITS_PER_LONG);
+	start = round_down(start, BITS_PER_LONG);
+
+	while (!tmp) {
+		start += BITS_PER_LONG;
+		if (start >= nbits)
+			return nbits;
+
+		tmp = addr[start / BITS_PER_LONG] ^ invert;
 	}
-	if (!size)
-		return result;
-	tmp = *p;
 
-found_first:
-	tmp &= (~0UL >> (BITS_PER_LONG - size));
-	if (tmp == 0UL)		/* Are any bits set? */
-		return result + size;	/* Nope. */
-found_middle:
-	return result + __ffs(tmp);
+	return min(start + __ffs(tmp), nbits);
 }
-EXPORT_SYMBOL(find_next_bit);
 #endif
 
-#ifndef find_next_zero_bit
+#ifndef find_next_bit
 /*
- * This implementation of find_{first,next}_zero_bit was stolen from
- * Linus' asm-alpha/bitops.h.
+ * Find the next set bit in a memory region.
  */
+unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
+			    unsigned long offset)
+{
+	return _find_next_bit(addr, size, offset, 0UL);
+}
+EXPORT_SYMBOL(find_next_bit);
+#endif
+
+#ifndef find_next_zero_bit
 unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
 				 unsigned long offset)
 {
-	const unsigned long *p = addr + BITOP_WORD(offset);
-	unsigned long result = offset & ~(BITS_PER_LONG-1);
-	unsigned long tmp;
-
-	if (offset >= size)
-		return size;
-	size -= result;
-	offset %= BITS_PER_LONG;
-	if (offset) {
-		tmp = *(p++);
-		tmp |= ~0UL >> (BITS_PER_LONG - offset);
-		if (size < BITS_PER_LONG)
-			goto found_first;
-		if (~tmp)
-			goto found_middle;
-		size -= BITS_PER_LONG;
-		result += BITS_PER_LONG;
-	}
-	while (size & ~(BITS_PER_LONG-1)) {
-		if (~(tmp = *(p++)))
-			goto found_middle;
-		result += BITS_PER_LONG;
-		size -= BITS_PER_LONG;
-	}
-	if (!size)
-		return result;
-	tmp = *p;
-
-found_first:
-	tmp |= ~0UL << size;
-	if (tmp == ~0UL)	/* Are any bits zero? */
-		return result + size;	/* Nope. */
-found_middle:
-	return result + ffz(tmp);
+	return _find_next_bit(addr, size, offset, ~0UL);
 }
 EXPORT_SYMBOL(find_next_zero_bit);
 #endif
@@ -113,24 +78,14 @@ EXPORT_SYMBOL(find_next_zero_bit);
  */
 unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
 {
-	const unsigned long *p = addr;
-	unsigned long result = 0;
-	unsigned long tmp;
+	unsigned long idx;
 
-	while (size & ~(BITS_PER_LONG-1)) {
-		if ((tmp = *(p++)))
-			goto found;
-		result += BITS_PER_LONG;
-		size -= BITS_PER_LONG;
+	for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
+		if (addr[idx])
+			return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size);
 	}
-	if (!size)
-		return result;
 
-	tmp = (*p) & (~0UL >> (BITS_PER_LONG - size));
-	if (tmp == 0UL)		/* Are any bits set? */
-		return result + size;	/* Nope. */
-found:
-	return result + __ffs(tmp);
+	return size;
 }
 EXPORT_SYMBOL(find_first_bit);
 #endif
@@ -141,24 +96,14 @@ EXPORT_SYMBOL(find_first_bit);
  */
 unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
 {
-	const unsigned long *p = addr;
-	unsigned long result = 0;
-	unsigned long tmp;
+	unsigned long idx;
 
-	while (size & ~(BITS_PER_LONG-1)) {
-		if (~(tmp = *(p++)))
-			goto found;
-		result += BITS_PER_LONG;
-		size -= BITS_PER_LONG;
+	for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
+		if (addr[idx] != ~0UL)
+			return min(idx * BITS_PER_LONG + ffz(addr[idx]), size);
 	}
-	if (!size)
-		return result;
 
-	tmp = (*p) | (~0UL << size);
-	if (tmp == ~0UL)	/* Are any bits zero? */
-		return result + size;	/* Nope. */
-found:
-	return result + ffz(tmp);
+	return size;
 }
 EXPORT_SYMBOL(find_first_zero_bit);
 #endif
@@ -166,18 +111,6 @@ EXPORT_SYMBOL(find_first_zero_bit);
 #ifdef __BIG_ENDIAN
 
 /* include/linux/byteorder does not support "unsigned long" type */
-static inline unsigned long ext2_swabp(const unsigned long * x)
-{
-#if BITS_PER_LONG == 64
-	return (unsigned long) __swab64p((u64 *) x);
-#elif BITS_PER_LONG == 32
-	return (unsigned long) __swab32p((u32 *) x);
-#else
-#error BITS_PER_LONG not defined
-#endif
-}
-
-/* include/linux/byteorder doesn't support "unsigned long" type */
 static inline unsigned long ext2_swab(const unsigned long y)
 {
 #if BITS_PER_LONG == 64
@@ -189,48 +122,38 @@ static inline unsigned long ext2_swab(const unsigned long y)
 #endif
 }
 
-#ifndef find_next_zero_bit_le
-unsigned long find_next_zero_bit_le(const void *addr, unsigned
-		long size, unsigned long offset)
+#if !defined(find_next_bit_le) || !defined(find_next_zero_bit_le)
+static unsigned long _find_next_bit_le(const unsigned long *addr,
+		unsigned long nbits, unsigned long start, unsigned long invert)
 {
-	const unsigned long *p = addr;
-	unsigned long result = offset & ~(BITS_PER_LONG - 1);
 	unsigned long tmp;
 
-	if (offset >= size)
-		return size;
-	p += BITOP_WORD(offset);
-	size -= result;
-	offset &= (BITS_PER_LONG - 1UL);
-	if (offset) {
-		tmp = ext2_swabp(p++);
-		tmp |= (~0UL >> (BITS_PER_LONG - offset));
-		if (size < BITS_PER_LONG)
-			goto found_first;
-		if (~tmp)
-			goto found_middle;
-		size -= BITS_PER_LONG;
-		result += BITS_PER_LONG;
-	}
+	if (!nbits || start >= nbits)
+		return nbits;
+
+	tmp = addr[start / BITS_PER_LONG] ^ invert;
+
+	/* Handle 1st word. */
+	tmp &= ext2_swab(HIGH_BITS_MASK(start % BITS_PER_LONG));
+	start = round_down(start, BITS_PER_LONG);
 
-	while (size & ~(BITS_PER_LONG - 1)) {
-		if (~(tmp = *(p++)))
-			goto found_middle_swap;
-		result += BITS_PER_LONG;
-		size -= BITS_PER_LONG;
+	while (!tmp) {
+		start += BITS_PER_LONG;
+		if (start >= nbits)
+			return nbits;
+
+		tmp = addr[start / BITS_PER_LONG] ^ invert;
 	}
-	if (!size)
-		return result;
-	tmp = ext2_swabp(p);
-found_first:
-	tmp |= ~0UL << size;
-	if (tmp == ~0UL)	/* Are any bits zero? */
-		return result + size; /* Nope. Skip ffz */
-found_middle:
-	return result + ffz(tmp);
 
-found_middle_swap:
-	return result + ffz(ext2_swab(tmp));
+	return min(start + __ffs(ext2_swab(tmp)), nbits);
+}
+#endif
+
+#ifndef find_next_zero_bit_le
+unsigned long find_next_zero_bit_le(const void *addr, unsigned
+		long size, unsigned long offset)
+{
+	return _find_next_bit_le(addr, size, offset, ~0UL);
 }
 EXPORT_SYMBOL(find_next_zero_bit_le);
 #endif
@@ -239,45 +162,7 @@ EXPORT_SYMBOL(find_next_zero_bit_le);
 unsigned long find_next_bit_le(const void *addr, unsigned
 		long size, unsigned long offset)
 {
-	const unsigned long *p = addr;
-	unsigned long result = offset & ~(BITS_PER_LONG - 1);
-	unsigned long tmp;
-
-	if (offset >= size)
-		return size;
-	p += BITOP_WORD(offset);
-	size -= result;
-	offset &= (BITS_PER_LONG - 1UL);
-	if (offset) {
-		tmp = ext2_swabp(p++);
-		tmp &= (~0UL << offset);
-		if (size < BITS_PER_LONG)
-			goto found_first;
-		if (tmp)
-			goto found_middle;
-		size -= BITS_PER_LONG;
-		result += BITS_PER_LONG;
-	}
-
-	while (size & ~(BITS_PER_LONG - 1)) {
-		tmp = *(p++);
-		if (tmp)
-			goto found_middle_swap;
-		result += BITS_PER_LONG;
-		size -= BITS_PER_LONG;
-	}
-	if (!size)
-		return result;
-	tmp = ext2_swabp(p);
-found_first:
-	tmp &= (~0UL >> (BITS_PER_LONG - size));
-	if (tmp == 0UL)		/* Are any bits set? */
-		return result + size; /* Nope. */
-found_middle:
-	return result + __ffs(tmp);
-
-found_middle_swap:
-	return result + __ffs(ext2_swab(tmp));
+	return _find_next_bit_le(addr, size, offset, 0UL);
 }
 EXPORT_SYMBOL(find_next_bit_le);
 #endif
-- 
2.1.0