diff --git a/include/asm-generic/bitops/find.h b/include/asm-generic/bitops/find.h
index 72a51e5a12ef1b3738f25249eeed3417745788c1..1914e9742512db6d9bd5e9be5bc9be30ad510c0f 100644
--- a/include/asm-generic/bitops/find.h
+++ b/include/asm-generic/bitops/find.h
@@ -1,11 +1,13 @@
 #ifndef _ASM_GENERIC_BITOPS_FIND_H_
 #define _ASM_GENERIC_BITOPS_FIND_H_
 
+#ifndef CONFIG_GENERIC_FIND_NEXT_BIT
 extern unsigned long find_next_bit(const unsigned long *addr, unsigned long
 		size, unsigned long offset);
 
 extern unsigned long find_next_zero_bit(const unsigned long *addr, unsigned
 		long size, unsigned long offset);
+#endif
 
 #define find_first_bit(addr, size) find_next_bit((addr), (size), 0)
 #define find_first_zero_bit(addr, size) find_next_zero_bit((addr), (size), 0)
diff --git a/include/asm-x86/bitops.h b/include/asm-x86/bitops.h
index 31e408de90c677735b95c016a45e388c5df02073..1ae7b270a1efe8d1cc9abe8c4260d54d714ecc0f 100644
--- a/include/asm-x86/bitops.h
+++ b/include/asm-x86/bitops.h
@@ -306,12 +306,6 @@ static int test_bit(int nr, const volatile unsigned long *addr);
 #undef BIT_ADDR
 #undef ADDR
 
-unsigned long find_next_bit(const unsigned long *addr,
-		unsigned long size, unsigned long offset);
-unsigned long find_next_zero_bit(const unsigned long *addr,
-		unsigned long size, unsigned long offset);
-
-
 #ifdef CONFIG_X86_32
 # include "bitops_32.h"
 #else
diff --git a/include/asm-x86/bitops_64.h b/include/asm-x86/bitops_64.h
index 65b20fb2ae78a0a9fffc5daa42477f3fb55b1e4e..7118ef2cc4ec34a4b9f74c9c3d8d35be082ce98c 100644
--- a/include/asm-x86/bitops_64.h
+++ b/include/asm-x86/bitops_64.h
@@ -15,16 +15,6 @@ static inline long __scanbit(unsigned long val, unsigned long max)
 	return val;
 }
 
-#define find_next_bit(addr,size,off) \
-((__builtin_constant_p(size) && (size) <= BITS_PER_LONG ? 	  \
-  ((off) + (__scanbit((*(unsigned long *)addr) >> (off),(size)-(off)))) : \
-	find_next_bit(addr,size,off)))
-
-#define find_next_zero_bit(addr,size,off) \
-((__builtin_constant_p(size) && (size) <= BITS_PER_LONG ? 	  \
-  ((off)+(__scanbit(~(((*(unsigned long *)addr)) >> (off)),(size)-(off)))) : \
-	find_next_zero_bit(addr,size,off)))
-
 #define find_first_bit(addr, size)					\
 	((__builtin_constant_p((size)) && (size) <= BITS_PER_LONG	\
 	  ? (__scanbit(*(unsigned long *)(addr), (size)))		\
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 40d54731de7e0b9fb6b44ebf7db983ea58fc1ac2..3865f2c93bd8282e02bee4880d382a7448703d16 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -112,4 +112,81 @@ static inline unsigned fls_long(unsigned long l)
 	return fls64(l);
 }
 
+#ifdef __KERNEL__
+#ifdef CONFIG_GENERIC_FIND_NEXT_BIT
+extern unsigned long __find_next_bit(const unsigned long *addr,
+		unsigned long size, unsigned long offset);
+
+/**
+ * find_next_bit - find the next set bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The bitmap size in bits
+ */
+static __always_inline unsigned long
+find_next_bit(const unsigned long *addr, unsigned long size,
+		unsigned long offset)
+{
+	unsigned long value;
+
+	/* Avoid a function call if the bitmap size is a constant */
+	/* and not bigger than BITS_PER_LONG. */
+
+	/* insert a sentinel so that __ffs returns size if there */
+	/* are no set bits in the bitmap */
+	if (__builtin_constant_p(size) && (size < BITS_PER_LONG)) {
+		value = (*addr) & ((~0ul) << offset);
+		value |= (1ul << size);
+		return __ffs(value);
+	}
+
+	/* the result of __ffs(0) is undefined, so it needs to be */
+	/* handled separately */
+	if (__builtin_constant_p(size) && (size == BITS_PER_LONG)) {
+		value = (*addr) & ((~0ul) << offset);
+		return (value == 0) ? BITS_PER_LONG : __ffs(value);
+	}
+
+	/* size is not constant or too big */
+	return __find_next_bit(addr, size, offset);
+}
+
+extern unsigned long __find_next_zero_bit(const unsigned long *addr,
+		unsigned long size, unsigned long offset);
+
+/**
+ * find_next_zero_bit - find the next cleared bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The bitmap size in bits
+ */
+static __always_inline unsigned long
+find_next_zero_bit(const unsigned long *addr, unsigned long size,
+		unsigned long offset)
+{
+	unsigned long value;
+
+	/* Avoid a function call if the bitmap size is a constant */
+	/* and not bigger than BITS_PER_LONG. */
+
+	/* insert a sentinel so that __ffs returns size if there */
+	/* are no set bits in the bitmap */
+	if (__builtin_constant_p(size) && (size < BITS_PER_LONG)) {
+		value = (~(*addr)) & ((~0ul) << offset);
+		value |= (1ul << size);
+		return __ffs(value);
+	}
+
+	/* the result of __ffs(0) is undefined, so it needs to be */
+	/* handled separately */
+	if (__builtin_constant_p(size) && (size == BITS_PER_LONG)) {
+		value = (~(*addr)) & ((~0ul) << offset);
+		return (value == 0) ? BITS_PER_LONG : __ffs(value);
+	}
+
+	/* size is not constant or too big */
+	return __find_next_zero_bit(addr, size, offset);
+}
+#endif /* CONFIG_GENERIC_FIND_NEXT_BIT */
+#endif /* __KERNEL__ */
 #endif
diff --git a/lib/find_next_bit.c b/lib/find_next_bit.c
index 5820e072b890269984dcfc7a5dec1cb10ed61930..ce94c4c92d10c0ec3720528811a48ac7508bd8fd 100644
--- a/lib/find_next_bit.c
+++ b/lib/find_next_bit.c
@@ -15,17 +15,12 @@
 #include <asm/byteorder.h>
 
 #define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)
-#undef find_next_bit
-#undef find_next_zero_bit
-
-/**
- * find_next_bit - find the next set bit in a memory region
- * @addr: The address to base the search on
- * @offset: The bitnumber to start searching at
- * @size: The maximum size to search
+
+/*
+ * Find the next set bit in a memory region.
  */
-unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
-		unsigned long offset)
+unsigned long __find_next_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);
@@ -62,15 +57,14 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
 found_middle:
 	return result + __ffs(tmp);
 }
-
-EXPORT_SYMBOL(find_next_bit);
+EXPORT_SYMBOL(__find_next_bit);
 
 /*
  * This implementation of find_{first,next}_zero_bit was stolen from
  * Linus' asm-alpha/bitops.h.
  */
-unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
-		unsigned long offset)
+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);
@@ -107,8 +101,7 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
 found_middle:
 	return result + ffz(tmp);
 }
-
-EXPORT_SYMBOL(find_next_zero_bit);
+EXPORT_SYMBOL(__find_next_zero_bit);
 
 #ifdef __BIG_ENDIAN