diff --git a/tools/include/asm-generic/bitops.h b/tools/include/asm-generic/bitops.h
new file mode 100644
index 0000000000000000000000000000000000000000..6eedba1f773227d5df93bae06d7f3a0fcc1bd648
--- /dev/null
+++ b/tools/include/asm-generic/bitops.h
@@ -0,0 +1,27 @@
+#ifndef __TOOLS_ASM_GENERIC_BITOPS_H
+#define __TOOLS_ASM_GENERIC_BITOPS_H
+
+/*
+ * tools/ copied this from include/asm-generic/bitops.h, bit by bit as it needed
+ * some functions.
+ *
+ * For the benefit of those who are trying to port Linux to another
+ * architecture, here are some C-language equivalents.  You should
+ * recode these in the native assembly language, if at all possible.
+ *
+ * C language equivalents written by Theodore Ts'o, 9/26/92
+ */
+
+#include <asm-generic/bitops/__ffs.h>
+#include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/fls64.h>
+#include <asm-generic/bitops/find.h>
+
+#ifndef _TOOLS_LINUX_BITOPS_H_
+#error only <linux/bitops.h> can be included directly
+#endif
+
+#include <asm-generic/bitops/atomic.h>
+
+#endif /* __TOOLS_ASM_GENERIC_BITOPS_H */
diff --git a/tools/include/asm-generic/bitops/__ffs.h b/tools/include/asm-generic/bitops/__ffs.h
new file mode 100644
index 0000000000000000000000000000000000000000..c94175015a82a04a5c8fc7e9a323f1eeeaf820f2
--- /dev/null
+++ b/tools/include/asm-generic/bitops/__ffs.h
@@ -0,0 +1,43 @@
+#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_
+#define _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_
+
+#include <asm/types.h>
+
+/**
+ * __ffs - find first bit in word.
+ * @word: The word to search
+ *
+ * Undefined if no bit exists, so code should check against 0 first.
+ */
+static __always_inline unsigned long __ffs(unsigned long word)
+{
+	int num = 0;
+
+#if __BITS_PER_LONG == 64
+	if ((word & 0xffffffff) == 0) {
+		num += 32;
+		word >>= 32;
+	}
+#endif
+	if ((word & 0xffff) == 0) {
+		num += 16;
+		word >>= 16;
+	}
+	if ((word & 0xff) == 0) {
+		num += 8;
+		word >>= 8;
+	}
+	if ((word & 0xf) == 0) {
+		num += 4;
+		word >>= 4;
+	}
+	if ((word & 0x3) == 0) {
+		num += 2;
+		word >>= 2;
+	}
+	if ((word & 0x1) == 0)
+		num += 1;
+	return num;
+}
+
+#endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_ */
diff --git a/tools/include/asm-generic/bitops/__fls.h b/tools/include/asm-generic/bitops/__fls.h
new file mode 100644
index 0000000000000000000000000000000000000000..2218b9add4c1fdadf9927cdb2c165924ece1881b
--- /dev/null
+++ b/tools/include/asm-generic/bitops/__fls.h
@@ -0,0 +1 @@
+#include <../../../../include/asm-generic/bitops/__fls.h>
diff --git a/tools/include/asm-generic/bitops/atomic.h b/tools/include/asm-generic/bitops/atomic.h
new file mode 100644
index 0000000000000000000000000000000000000000..4bccd7c3d5d6572052d2206a2c09b6a5e57d3f86
--- /dev/null
+++ b/tools/include/asm-generic/bitops/atomic.h
@@ -0,0 +1,22 @@
+#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_
+#define _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_
+
+#include <asm/types.h>
+
+static inline void set_bit(int nr, unsigned long *addr)
+{
+	addr[nr / __BITS_PER_LONG] |= 1UL << (nr % __BITS_PER_LONG);
+}
+
+static inline void clear_bit(int nr, unsigned long *addr)
+{
+	addr[nr / __BITS_PER_LONG] &= ~(1UL << (nr % __BITS_PER_LONG));
+}
+
+static __always_inline int test_bit(unsigned int nr, const unsigned long *addr)
+{
+	return ((1UL << (nr % __BITS_PER_LONG)) &
+		(((unsigned long *)addr)[nr / __BITS_PER_LONG])) != 0;
+}
+
+#endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_ */
diff --git a/tools/include/asm-generic/bitops/find.h b/tools/include/asm-generic/bitops/find.h
new file mode 100644
index 0000000000000000000000000000000000000000..31f51547fcd4164f54a575c93b54b43e6a2f5ce9
--- /dev/null
+++ b/tools/include/asm-generic/bitops/find.h
@@ -0,0 +1,33 @@
+#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_
+#define _TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_
+
+#ifndef find_next_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 bitmap size in bits
+ *
+ * Returns the bit number for the next set bit
+ * If no bits are set, returns @size.
+ */
+extern unsigned long find_next_bit(const unsigned long *addr, unsigned long
+		size, unsigned long offset);
+#endif
+
+#ifndef find_first_bit
+
+/**
+ * find_first_bit - find the first set bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum number of bits to search
+ *
+ * Returns the bit number of the first set bit.
+ * If no bits are set, returns @size.
+ */
+extern unsigned long find_first_bit(const unsigned long *addr,
+				    unsigned long size);
+
+#endif /* find_first_bit */
+
+#endif /*_TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_ */
diff --git a/tools/include/asm-generic/bitops/fls.h b/tools/include/asm-generic/bitops/fls.h
new file mode 100644
index 0000000000000000000000000000000000000000..dbf711a28f712fc2fa549fe37338dbd38a94c6e1
--- /dev/null
+++ b/tools/include/asm-generic/bitops/fls.h
@@ -0,0 +1 @@
+#include <../../../../include/asm-generic/bitops/fls.h>
diff --git a/tools/include/asm-generic/bitops/fls64.h b/tools/include/asm-generic/bitops/fls64.h
new file mode 100644
index 0000000000000000000000000000000000000000..980b1f63c047d6d481012c6e60fd1cd63065c711
--- /dev/null
+++ b/tools/include/asm-generic/bitops/fls64.h
@@ -0,0 +1 @@
+#include <../../../../include/asm-generic/bitops/fls64.h>
diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h
new file mode 100644
index 0000000000000000000000000000000000000000..26005a15e7e29d34332b88e68a49fe223953913b
--- /dev/null
+++ b/tools/include/linux/bitops.h
@@ -0,0 +1,53 @@
+#ifndef _TOOLS_LINUX_BITOPS_H_
+#define _TOOLS_LINUX_BITOPS_H_
+
+#include <linux/kernel.h>
+#include <linux/compiler.h>
+#include <asm/hweight.h>
+
+#ifndef __WORDSIZE
+#define __WORDSIZE (__SIZEOF_LONG__ * 8)
+#endif
+
+#define BITS_PER_LONG __WORDSIZE
+
+#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
+#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
+#define BITS_PER_BYTE		8
+#define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
+#define BITS_TO_U64(nr)		DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
+#define BITS_TO_U32(nr)		DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
+#define BITS_TO_BYTES(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE)
+
+/*
+ * Include this here because some architectures need generic_ffs/fls in
+ * scope
+ *
+ * XXX: this needs to be asm/bitops.h, when we get to per arch optimizations
+ */
+#include <asm-generic/bitops.h>
+
+#define for_each_set_bit(bit, addr, size) \
+	for ((bit) = find_first_bit((addr), (size));		\
+	     (bit) < (size);					\
+	     (bit) = find_next_bit((addr), (size), (bit) + 1))
+
+/* same as for_each_set_bit() but use bit as value to start with */
+#define for_each_set_bit_from(bit, addr, size) \
+	for ((bit) = find_next_bit((addr), (size), (bit));	\
+	     (bit) < (size);					\
+	     (bit) = find_next_bit((addr), (size), (bit) + 1))
+
+static inline unsigned long hweight_long(unsigned long w)
+{
+	return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
+}
+
+static inline unsigned fls_long(unsigned long l)
+{
+	if (sizeof(l) == 4)
+		return fls(l);
+	return fls64(l);
+}
+
+#endif
diff --git a/tools/include/linux/log2.h b/tools/include/linux/log2.h
new file mode 100644
index 0000000000000000000000000000000000000000..41446668ccce18a6777f87f124f98eb715406f02
--- /dev/null
+++ b/tools/include/linux/log2.h
@@ -0,0 +1,185 @@
+/* Integer base 2 logarithm calculation
+ *
+ * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * 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
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _TOOLS_LINUX_LOG2_H
+#define _TOOLS_LINUX_LOG2_H
+
+/*
+ * deal with unrepresentable constant logarithms
+ */
+extern __attribute__((const, noreturn))
+int ____ilog2_NaN(void);
+
+/*
+ * non-constant log of base 2 calculators
+ * - the arch may override these in asm/bitops.h if they can be implemented
+ *   more efficiently than using fls() and fls64()
+ * - the arch is not required to handle n==0 if implementing the fallback
+ */
+static inline __attribute__((const))
+int __ilog2_u32(u32 n)
+{
+	return fls(n) - 1;
+}
+
+static inline __attribute__((const))
+int __ilog2_u64(u64 n)
+{
+	return fls64(n) - 1;
+}
+
+/*
+ *  Determine whether some value is a power of two, where zero is
+ * *not* considered a power of two.
+ */
+
+static inline __attribute__((const))
+bool is_power_of_2(unsigned long n)
+{
+	return (n != 0 && ((n & (n - 1)) == 0));
+}
+
+/*
+ * round up to nearest power of two
+ */
+static inline __attribute__((const))
+unsigned long __roundup_pow_of_two(unsigned long n)
+{
+	return 1UL << fls_long(n - 1);
+}
+
+/*
+ * round down to nearest power of two
+ */
+static inline __attribute__((const))
+unsigned long __rounddown_pow_of_two(unsigned long n)
+{
+	return 1UL << (fls_long(n) - 1);
+}
+
+/**
+ * ilog2 - log of base 2 of 32-bit or a 64-bit unsigned value
+ * @n - parameter
+ *
+ * constant-capable log of base 2 calculation
+ * - this can be used to initialise global variables from constant data, hence
+ *   the massive ternary operator construction
+ *
+ * selects the appropriately-sized optimised version depending on sizeof(n)
+ */
+#define ilog2(n)				\
+(						\
+	__builtin_constant_p(n) ? (		\
+		(n) < 1 ? ____ilog2_NaN() :	\
+		(n) & (1ULL << 63) ? 63 :	\
+		(n) & (1ULL << 62) ? 62 :	\
+		(n) & (1ULL << 61) ? 61 :	\
+		(n) & (1ULL << 60) ? 60 :	\
+		(n) & (1ULL << 59) ? 59 :	\
+		(n) & (1ULL << 58) ? 58 :	\
+		(n) & (1ULL << 57) ? 57 :	\
+		(n) & (1ULL << 56) ? 56 :	\
+		(n) & (1ULL << 55) ? 55 :	\
+		(n) & (1ULL << 54) ? 54 :	\
+		(n) & (1ULL << 53) ? 53 :	\
+		(n) & (1ULL << 52) ? 52 :	\
+		(n) & (1ULL << 51) ? 51 :	\
+		(n) & (1ULL << 50) ? 50 :	\
+		(n) & (1ULL << 49) ? 49 :	\
+		(n) & (1ULL << 48) ? 48 :	\
+		(n) & (1ULL << 47) ? 47 :	\
+		(n) & (1ULL << 46) ? 46 :	\
+		(n) & (1ULL << 45) ? 45 :	\
+		(n) & (1ULL << 44) ? 44 :	\
+		(n) & (1ULL << 43) ? 43 :	\
+		(n) & (1ULL << 42) ? 42 :	\
+		(n) & (1ULL << 41) ? 41 :	\
+		(n) & (1ULL << 40) ? 40 :	\
+		(n) & (1ULL << 39) ? 39 :	\
+		(n) & (1ULL << 38) ? 38 :	\
+		(n) & (1ULL << 37) ? 37 :	\
+		(n) & (1ULL << 36) ? 36 :	\
+		(n) & (1ULL << 35) ? 35 :	\
+		(n) & (1ULL << 34) ? 34 :	\
+		(n) & (1ULL << 33) ? 33 :	\
+		(n) & (1ULL << 32) ? 32 :	\
+		(n) & (1ULL << 31) ? 31 :	\
+		(n) & (1ULL << 30) ? 30 :	\
+		(n) & (1ULL << 29) ? 29 :	\
+		(n) & (1ULL << 28) ? 28 :	\
+		(n) & (1ULL << 27) ? 27 :	\
+		(n) & (1ULL << 26) ? 26 :	\
+		(n) & (1ULL << 25) ? 25 :	\
+		(n) & (1ULL << 24) ? 24 :	\
+		(n) & (1ULL << 23) ? 23 :	\
+		(n) & (1ULL << 22) ? 22 :	\
+		(n) & (1ULL << 21) ? 21 :	\
+		(n) & (1ULL << 20) ? 20 :	\
+		(n) & (1ULL << 19) ? 19 :	\
+		(n) & (1ULL << 18) ? 18 :	\
+		(n) & (1ULL << 17) ? 17 :	\
+		(n) & (1ULL << 16) ? 16 :	\
+		(n) & (1ULL << 15) ? 15 :	\
+		(n) & (1ULL << 14) ? 14 :	\
+		(n) & (1ULL << 13) ? 13 :	\
+		(n) & (1ULL << 12) ? 12 :	\
+		(n) & (1ULL << 11) ? 11 :	\
+		(n) & (1ULL << 10) ? 10 :	\
+		(n) & (1ULL <<  9) ?  9 :	\
+		(n) & (1ULL <<  8) ?  8 :	\
+		(n) & (1ULL <<  7) ?  7 :	\
+		(n) & (1ULL <<  6) ?  6 :	\
+		(n) & (1ULL <<  5) ?  5 :	\
+		(n) & (1ULL <<  4) ?  4 :	\
+		(n) & (1ULL <<  3) ?  3 :	\
+		(n) & (1ULL <<  2) ?  2 :	\
+		(n) & (1ULL <<  1) ?  1 :	\
+		(n) & (1ULL <<  0) ?  0 :	\
+		____ilog2_NaN()			\
+				   ) :		\
+	(sizeof(n) <= 4) ?			\
+	__ilog2_u32(n) :			\
+	__ilog2_u64(n)				\
+ )
+
+/**
+ * roundup_pow_of_two - round the given value up to nearest power of two
+ * @n - parameter
+ *
+ * round the given value up to the nearest power of two
+ * - the result is undefined when n == 0
+ * - this can be used to initialise global variables from constant data
+ */
+#define roundup_pow_of_two(n)			\
+(						\
+	__builtin_constant_p(n) ? (		\
+		(n == 1) ? 1 :			\
+		(1UL << (ilog2((n) - 1) + 1))	\
+				   ) :		\
+	__roundup_pow_of_two(n)			\
+ )
+
+/**
+ * rounddown_pow_of_two - round the given value down to nearest power of two
+ * @n - parameter
+ *
+ * round the given value down to the nearest power of two
+ * - the result is undefined when n == 0
+ * - this can be used to initialise global variables from constant data
+ */
+#define rounddown_pow_of_two(n)			\
+(						\
+	__builtin_constant_p(n) ? (		\
+		(1UL << ilog2(n))) :		\
+	__rounddown_pow_of_two(n)		\
+ )
+
+#endif /* _TOOLS_LINUX_LOG2_H */
diff --git a/tools/lib/util/find_next_bit.c b/tools/lib/util/find_next_bit.c
new file mode 100644
index 0000000000000000000000000000000000000000..41b44f65a79ebff526f7d8e5b6b8157aa9f65fbf
--- /dev/null
+++ b/tools/lib/util/find_next_bit.c
@@ -0,0 +1,89 @@
+/* find_next_bit.c: fallback find next bit implementation
+ *
+ * Copied from lib/find_next_bit.c to tools/lib/next_bit.c
+ *
+ * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * 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
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/bitops.h>
+#include <asm/types.h>
+#include <asm/byteorder.h>
+
+#define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)
+
+#ifndef find_next_bit
+/*
+ * Find the next set bit in a memory region.
+ */
+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);
+	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 (!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);
+}
+#endif
+
+#ifndef find_first_bit
+/*
+ * Find the first set bit in a memory region.
+ */
+unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
+{
+	const unsigned long *p = addr;
+	unsigned long result = 0;
+	unsigned long tmp;
+
+	while (size & ~(BITS_PER_LONG-1)) {
+		if ((tmp = *(p++)))
+			goto found;
+		result += BITS_PER_LONG;
+		size -= BITS_PER_LONG;
+	}
+	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);
+}
+#endif
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 344c4d3d0a4a7bb567b9d40c06175b0984b1a52a..83e2887f91a39200612290bd0b2b2fbd824e660a 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -4,17 +4,31 @@ tools/lib/traceevent
 tools/lib/api
 tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
+tools/lib/util/find_next_bit.c
 tools/include/asm/bug.h
+tools/include/asm-generic/bitops/atomic.h
+tools/include/asm-generic/bitops/__ffs.h
+tools/include/asm-generic/bitops/__fls.h
+tools/include/asm-generic/bitops/find.h
+tools/include/asm-generic/bitops/fls64.h
+tools/include/asm-generic/bitops/fls.h
+tools/include/asm-generic/bitops.h
+tools/include/linux/bitops.h
 tools/include/linux/compiler.h
-tools/include/linux/hash.h
 tools/include/linux/export.h
+tools/include/linux/hash.h
+tools/include/linux/log2.h
 tools/include/linux/types.h
+include/asm-generic/bitops/fls64.h
+include/asm-generic/bitops/__fls.h
+include/asm-generic/bitops/fls.h
 include/linux/const.h
 include/linux/perf_event.h
 include/linux/rbtree.h
 include/linux/list.h
 include/linux/hash.h
 include/linux/stringify.h
+lib/find_next_bit.c
 lib/rbtree.c
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 763e68fb57672eaf4ae96fdf9178295f704a31da..67a03a825b3c94bb894f0f557dac3bb520943e65 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -231,8 +231,16 @@ LIB_H += ../../include/uapi/linux/const.h
 LIB_H += ../include/linux/hash.h
 LIB_H += ../../include/linux/stringify.h
 LIB_H += util/include/linux/bitmap.h
-LIB_H += util/include/linux/bitops.h
+LIB_H += ../include/linux/bitops.h
+LIB_H += ../include/asm-generic/bitops/atomic.h
+LIB_H += ../include/asm-generic/bitops/find.h
+LIB_H += ../include/asm-generic/bitops/fls64.h
+LIB_H += ../include/asm-generic/bitops/fls.h
+LIB_H += ../include/asm-generic/bitops/__ffs.h
+LIB_H += ../include/asm-generic/bitops/__fls.h
+LIB_H += ../include/asm-generic/bitops.h
 LIB_H += ../include/linux/compiler.h
+LIB_H += ../include/linux/log2.h
 LIB_H += util/include/linux/const.h
 LIB_H += util/include/linux/ctype.h
 LIB_H += util/include/linux/kernel.h
@@ -335,6 +343,7 @@ LIB_OBJS += $(OUTPUT)util/event.o
 LIB_OBJS += $(OUTPUT)util/evlist.o
 LIB_OBJS += $(OUTPUT)util/evsel.o
 LIB_OBJS += $(OUTPUT)util/exec_cmd.o
+LIB_OBJS += $(OUTPUT)util/find_next_bit.o
 LIB_OBJS += $(OUTPUT)util/help.o
 LIB_OBJS += $(OUTPUT)util/kallsyms.o
 LIB_OBJS += $(OUTPUT)util/levenshtein.o
@@ -734,6 +743,9 @@ $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c $(OUTPUT)PERF-CFLAGS
 $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
+$(OUTPUT)util/find_next_bit.o: ../lib/util/find_next_bit.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+
 $(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-redundant-decls $<
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 327541e43c7ffaf7bcb2b20af02f90bb01d10e59..badfabc6a01f6f1a90d1988abc5ac6178021bb08 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2485,7 +2485,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 			.user_freq     = UINT_MAX,
 			.user_interval = ULLONG_MAX,
 			.no_buffering  = true,
-			.mmap_pages    = 1024,
+			.mmap_pages    = UINT_MAX,
 		},
 		.output = stdout,
 		.show_comm = true,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index bb5dfc5d1e7531596c7f05041383fe3765b79901..cbab1fb77b1d6c4efb8565144256e6f1c5a6d540 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -25,6 +25,7 @@
 
 #include <linux/bitops.h>
 #include <linux/hash.h>
+#include <linux/log2.h>
 
 static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx);
 static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx);
@@ -893,10 +894,24 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist,
 
 static size_t perf_evlist__mmap_size(unsigned long pages)
 {
-	/* 512 kiB: default amount of unprivileged mlocked memory */
-	if (pages == UINT_MAX)
-		pages = (512 * 1024) / page_size;
-	else if (!is_power_of_2(pages))
+	if (pages == UINT_MAX) {
+		int max;
+
+		if (sysctl__read_int("kernel/perf_event_mlock_kb", &max) < 0) {
+			/*
+			 * Pick a once upon a time good value, i.e. things look
+			 * strange since we can't read a sysctl value, but lets not
+			 * die yet...
+			 */
+			max = 512;
+		} else {
+			max -= (page_size / 1024);
+		}
+
+		pages = (max * 1024) / page_size;
+		if (!is_power_of_2(pages))
+			pages = rounddown_pow_of_two(pages);
+	} else if (!is_power_of_2(pages))
 		return 0;
 
 	return (pages + 1) * page_size;
@@ -933,7 +948,7 @@ static long parse_pages_arg(const char *str, unsigned long min,
 		/* leave number of pages at 0 */
 	} else if (!is_power_of_2(pages)) {
 		/* round pages up to next power of 2 */
-		pages = next_pow2_l(pages);
+		pages = roundup_pow_of_two(pages);
 		if (!pages)
 			return -EINVAL;
 		pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n",
@@ -1487,16 +1502,25 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
 int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size)
 {
 	char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
-	int value;
+	int pages_attempted = evlist->mmap_len / 1024, pages_max_per_user, printed = 0;
 
 	switch (err) {
 	case EPERM:
-		sysctl__read_int("kernel/perf_event_mlock_kb", &value);
-		scnprintf(buf, size, "Error:\t%s.\n"
+		sysctl__read_int("kernel/perf_event_mlock_kb", &pages_max_per_user);
+		printed += scnprintf(buf + printed, size - printed,
+				     "Error:\t%s.\n"
 				     "Hint:\tCheck /proc/sys/kernel/perf_event_mlock_kb (%d kB) setting.\n"
-				     "Hint:\tTried using %zd kB.\n"
-				     "Hint:\tTry using a bigger -m/--mmap-pages value.",
-				     emsg, value, evlist->mmap_len / 1024);
+				     "Hint:\tTried using %zd kB.\n",
+				     emsg, pages_max_per_user, pages_attempted);
+
+		if (pages_attempted >= pages_max_per_user) {
+			printed += scnprintf(buf + printed, size - printed,
+					     "Hint:\tTry 'sudo sh -c \"echo %d > /proc/sys/kernel/perf_event_mlock_kb\"', or\n",
+					     pages_max_per_user + pages_attempted);
+		}
+
+		printed += scnprintf(buf + printed, size - printed,
+				     "Hint:\tTry using a smaller -m/--mmap-pages value.");
 		break;
 	default:
 		scnprintf(buf, size, "%s", emsg);
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
deleted file mode 100644
index c3294163de1759b754e618105460829427d71a4a..0000000000000000000000000000000000000000
--- a/tools/perf/util/include/linux/bitops.h
+++ /dev/null
@@ -1,162 +0,0 @@
-#ifndef _PERF_LINUX_BITOPS_H_
-#define _PERF_LINUX_BITOPS_H_
-
-#include <linux/kernel.h>
-#include <linux/compiler.h>
-#include <asm/hweight.h>
-
-#ifndef __WORDSIZE
-#define __WORDSIZE (__SIZEOF_LONG__ * 8)
-#endif
-
-#define BITS_PER_LONG __WORDSIZE
-#define BITS_PER_BYTE           8
-#define BITS_TO_LONGS(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
-#define BITS_TO_U64(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
-#define BITS_TO_U32(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
-#define BITS_TO_BYTES(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE)
-#define BIT_WORD(nr)            ((nr) / BITS_PER_LONG)
-#define BIT_MASK(nr)            (1UL << ((nr) % BITS_PER_LONG))
-
-#define for_each_set_bit(bit, addr, size) \
-	for ((bit) = find_first_bit((addr), (size));		\
-	     (bit) < (size);					\
-	     (bit) = find_next_bit((addr), (size), (bit) + 1))
-
-/* same as for_each_set_bit() but use bit as value to start with */
-#define for_each_set_bit_from(bit, addr, size) \
-	for ((bit) = find_next_bit((addr), (size), (bit));	\
-	     (bit) < (size);					\
-	     (bit) = find_next_bit((addr), (size), (bit) + 1))
-
-static inline void set_bit(int nr, unsigned long *addr)
-{
-	addr[nr / BITS_PER_LONG] |= 1UL << (nr % BITS_PER_LONG);
-}
-
-static inline void clear_bit(int nr, unsigned long *addr)
-{
-	addr[nr / BITS_PER_LONG] &= ~(1UL << (nr % BITS_PER_LONG));
-}
-
-static __always_inline int test_bit(unsigned int nr, const unsigned long *addr)
-{
-	return ((1UL << (nr % BITS_PER_LONG)) &
-		(((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
-}
-
-static inline unsigned long hweight_long(unsigned long w)
-{
-	return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
-}
-
-#define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)
-
-/**
- * __ffs - find first bit in word.
- * @word: The word to search
- *
- * Undefined if no bit exists, so code should check against 0 first.
- */
-static __always_inline unsigned long __ffs(unsigned long word)
-{
-	int num = 0;
-
-#if BITS_PER_LONG == 64
-	if ((word & 0xffffffff) == 0) {
-		num += 32;
-		word >>= 32;
-	}
-#endif
-	if ((word & 0xffff) == 0) {
-		num += 16;
-		word >>= 16;
-	}
-	if ((word & 0xff) == 0) {
-		num += 8;
-		word >>= 8;
-	}
-	if ((word & 0xf) == 0) {
-		num += 4;
-		word >>= 4;
-	}
-	if ((word & 0x3) == 0) {
-		num += 2;
-		word >>= 2;
-	}
-	if ((word & 0x1) == 0)
-		num += 1;
-	return num;
-}
-
-typedef const unsigned long __attribute__((__may_alias__)) long_alias_t;
-
-/*
- * Find the first set bit in a memory region.
- */
-static inline unsigned long
-find_first_bit(const unsigned long *addr, unsigned long size)
-{
-	long_alias_t *p = (long_alias_t *) addr;
-	unsigned long result = 0;
-	unsigned long tmp;
-
-	while (size & ~(BITS_PER_LONG-1)) {
-		if ((tmp = *(p++)))
-			goto found;
-		result += BITS_PER_LONG;
-		size -= BITS_PER_LONG;
-	}
-	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);
-}
-
-/*
- * Find the next set bit in a memory region.
- */
-static inline 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);
-	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 (!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);
-}
-
-#endif
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index fa585c63f56adcf7dfb0afede3ee55cd5e37298e..d7efb03b3f9aab2d0382afb1d031790109462233 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -129,6 +129,7 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
 
 		for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) {
 			void *tmp;
+			long offset;
 
 			if (need_swap) {
 				phdr->p_type = bswap_32(phdr->p_type);
@@ -140,12 +141,13 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
 				continue;
 
 			buf_size = phdr->p_filesz;
+			offset = phdr->p_offset;
 			tmp = realloc(buf, buf_size);
 			if (tmp == NULL)
 				goto out_free;
 
 			buf = tmp;
-			fseek(fp, phdr->p_offset, SEEK_SET);
+			fseek(fp, offset, SEEK_SET);
 			if (fread(buf, buf_size, 1, fp) != 1)
 				goto out_free;
 
@@ -178,6 +180,7 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
 
 		for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) {
 			void *tmp;
+			long offset;
 
 			if (need_swap) {
 				phdr->p_type = bswap_32(phdr->p_type);
@@ -189,12 +192,13 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
 				continue;
 
 			buf_size = phdr->p_filesz;
+			offset = phdr->p_offset;
 			tmp = realloc(buf, buf_size);
 			if (tmp == NULL)
 				goto out_free;
 
 			buf = tmp;
-			fseek(fp, phdr->p_offset, SEEK_SET);
+			fseek(fp, offset, SEEK_SET);
 			if (fread(buf, buf_size, 1, fp) != 1)
 				goto out_free;
 
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 008b361b175882afcfda818b156624b8ca212cf3..be198ac27031501a914a26b7e230a23a3806b16d 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -269,35 +269,6 @@ void event_attr_init(struct perf_event_attr *attr);
 #define _STR(x) #x
 #define STR(x) _STR(x)
 
-/*
- *  Determine whether some value is a power of two, where zero is
- * *not* considered a power of two.
- */
-
-static inline __attribute__((const))
-bool is_power_of_2(unsigned long n)
-{
-	return (n != 0 && ((n & (n - 1)) == 0));
-}
-
-static inline unsigned next_pow2(unsigned x)
-{
-	if (!x)
-		return 1;
-	return 1ULL << (32 - __builtin_clz(x - 1));
-}
-
-static inline unsigned long next_pow2_l(unsigned long x)
-{
-#if BITS_PER_LONG == 64
-	if (x <= (1UL << 31))
-		return next_pow2(x);
-	return (unsigned long)next_pow2(x >> 32) << 32;
-#else
-	return next_pow2(x);
-#endif
-}
-
 size_t hex_width(u64 v);
 int hex2u64(const char *ptr, u64 *val);