SMARTT Release 0.5HEADmaster

19 files changed, 3022 insertions, 0 deletions

diff --git a/smartt-perf/util/include/linux/bitmap.h b/smartt-perf/util/include/linux/bitmap.h
new file mode 100644
index 0000000..eda4416
--- /dev/null
+++ b/smartt-perf/util/include/linux/bitmap.h
@@ -0,0 +1,35 @@
+#ifndef _PERF_BITOPS_H
+#define _PERF_BITOPS_H
+
+#include <string.h>
+#include <linux/bitops.h>
+
+int __bitmap_weight(const unsigned long *bitmap, int bits);
+
+#define BITMAP_LAST_WORD_MASK(nbits)					\
+(									\
+	((nbits) % BITS_PER_LONG) ?					\
+		(1UL<<((nbits) % BITS_PER_LONG))-1 : ~0UL		\
+)
+
+#define small_const_nbits(nbits) \
+	(__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG)
+
+static inline void bitmap_zero(unsigned long *dst, int nbits)
+{
+	if (small_const_nbits(nbits))
+		*dst = 0UL;
+	else {
+		int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+		memset(dst, 0, len);
+	}
+}
+
+static inline int bitmap_weight(const unsigned long *src, int nbits)
+{
+	if (small_const_nbits(nbits))
+		return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits));
+	return __bitmap_weight(src, nbits);
+}
+
+#endif /* _PERF_BITOPS_H */
diff --git a/smartt-perf/util/include/linux/bitops.h b/smartt-perf/util/include/linux/bitops.h
new file mode 100644
index 0000000..305c848
--- /dev/null
+++ b/smartt-perf/util/include/linux/bitops.h
@@ -0,0 +1,33 @@
+#ifndef _PERF_LINUX_BITOPS_H_
+#define _PERF_LINUX_BITOPS_H_
+
+#include <linux/kernel.h>
+#include <linux/compiler.h>
+#include <asm/hweight.h>
+
+#define BITS_PER_LONG __WORDSIZE
+#define BITS_PER_BYTE           8
+#define BITS_TO_LONGS(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
+
+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);
+}
+
+#endif
diff --git a/smartt-perf/util/include/linux/compiler.h b/smartt-perf/util/include/linux/compiler.h
new file mode 100644
index 0000000..791f9dd
--- /dev/null
+++ b/smartt-perf/util/include/linux/compiler.h
@@ -0,0 +1,12 @@
+#ifndef _PERF_LINUX_COMPILER_H_
+#define _PERF_LINUX_COMPILER_H_
+
+#ifndef __always_inline
+#define __always_inline	inline
+#endif
+#define __user
+#define __attribute_const__
+
+#define __used		__attribute__((__unused__))
+
+#endif
diff --git a/smartt-perf/util/include/linux/ctype.h b/smartt-perf/util/include/linux/ctype.h
new file mode 100644
index 0000000..a53d4ee
--- /dev/null
+++ b/smartt-perf/util/include/linux/ctype.h
@@ -0,0 +1 @@
+#include "../util.h"
diff --git a/smartt-perf/util/include/linux/hash.h b/smartt-perf/util/include/linux/hash.h
new file mode 100644
index 0000000..06d25c1
--- /dev/null
+++ b/smartt-perf/util/include/linux/hash.h
@@ -0,0 +1,70 @@
+#ifndef _LINUX_HASH_H
+#define _LINUX_HASH_H
+/* Fast hashing routine for ints,  longs and pointers.
+   (C) 2002 William Lee Irwin III, IBM */
+
+/*
+ * Knuth recommends primes in approximately golden ratio to the maximum
+ * integer representable by a machine word for multiplicative hashing.
+ * Chuck Lever verified the effectiveness of this technique:
+ * http://www.citi.umich.edu/techreports/reports/citi-tr-00-1.pdf
+ *
+ * These primes are chosen to be bit-sparse, that is operations on
+ * them can use shifts and additions instead of multiplications for
+ * machines where multiplications are slow.
+ */
+
+#include <asm/types.h>
+
+/* 2^31 + 2^29 - 2^25 + 2^22 - 2^19 - 2^16 + 1 */
+#define GOLDEN_RATIO_PRIME_32 0x9e370001UL
+/*  2^63 + 2^61 - 2^57 + 2^54 - 2^51 - 2^18 + 1 */
+#define GOLDEN_RATIO_PRIME_64 0x9e37fffffffc0001UL
+
+#if BITS_PER_LONG == 32
+#define GOLDEN_RATIO_PRIME GOLDEN_RATIO_PRIME_32
+#define hash_long(val, bits) hash_32(val, bits)
+#elif BITS_PER_LONG == 64
+#define hash_long(val, bits) hash_64(val, bits)
+#define GOLDEN_RATIO_PRIME GOLDEN_RATIO_PRIME_64
+#else
+#error Wordsize not 32 or 64
+#endif
+
+static inline u64 hash_64(u64 val, unsigned int bits)
+{
+	u64 hash = val;
+
+	/*  Sigh, gcc can't optimise this alone like it does for 32 bits. */
+	u64 n = hash;
+	n <<= 18;
+	hash -= n;
+	n <<= 33;
+	hash -= n;
+	n <<= 3;
+	hash += n;
+	n <<= 3;
+	hash -= n;
+	n <<= 4;
+	hash += n;
+	n <<= 2;
+	hash += n;
+
+	/* High bits are more random, so use them. */
+	return hash >> (64 - bits);
+}
+
+static inline u32 hash_32(u32 val, unsigned int bits)
+{
+	/* On some cpus multiply is faster, on others gcc will do shifts */
+	u32 hash = val * GOLDEN_RATIO_PRIME_32;
+
+	/* High bits are more random, so use them. */
+	return hash >> (32 - bits);
+}
+
+static inline unsigned long hash_ptr(void *ptr, unsigned int bits)
+{
+	return hash_long((unsigned long)ptr, bits);
+}
+#endif /* _LINUX_HASH_H */
diff --git a/smartt-perf/util/include/linux/hw_breakpoint.h b/smartt-perf/util/include/linux/hw_breakpoint.h
new file mode 100644
index 0000000..d1e55fe
--- /dev/null
+++ b/smartt-perf/util/include/linux/hw_breakpoint.h
@@ -0,0 +1,150 @@
+#ifndef _LINUX_HW_BREAKPOINT_H
+#define _LINUX_HW_BREAKPOINT_H
+
+enum {
+	HW_BREAKPOINT_LEN_1 = 1,
+	HW_BREAKPOINT_LEN_2 = 2,
+	HW_BREAKPOINT_LEN_4 = 4,
+	HW_BREAKPOINT_LEN_8 = 8,
+};
+
+enum {
+	HW_BREAKPOINT_EMPTY	= 0,
+	HW_BREAKPOINT_R		= 1,
+	HW_BREAKPOINT_W		= 2,
+	HW_BREAKPOINT_RW	= HW_BREAKPOINT_R | HW_BREAKPOINT_W,
+	HW_BREAKPOINT_X		= 4,
+	HW_BREAKPOINT_INVALID   = HW_BREAKPOINT_RW | HW_BREAKPOINT_X,
+};
+
+enum bp_type_idx {
+	TYPE_INST 	= 0,
+#ifdef CONFIG_HAVE_MIXED_BREAKPOINTS_REGS
+	TYPE_DATA	= 0,
+#else
+	TYPE_DATA	= 1,
+#endif
+	TYPE_MAX
+};
+
+#ifdef __KERNEL__
+
+#include <linux/perf_event.h>
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+
+extern int __init init_hw_breakpoint(void);
+
+static inline void hw_breakpoint_init(struct perf_event_attr *attr)
+{
+	memset(attr, 0, sizeof(*attr));
+
+	attr->type = PERF_TYPE_BREAKPOINT;
+	attr->size = sizeof(*attr);
+	/*
+	 * As it's for in-kernel or ptrace use, we want it to be pinned
+	 * and to call its callback every hits.
+	 */
+	attr->pinned = 1;
+	attr->sample_period = 1;
+}
+
+static inline void ptrace_breakpoint_init(struct perf_event_attr *attr)
+{
+	hw_breakpoint_init(attr);
+	attr->exclude_kernel = 1;
+}
+
+static inline unsigned long hw_breakpoint_addr(struct perf_event *bp)
+{
+	return bp->attr.bp_addr;
+}
+
+static inline int hw_breakpoint_type(struct perf_event *bp)
+{
+	return bp->attr.bp_type;
+}
+
+static inline unsigned long hw_breakpoint_len(struct perf_event *bp)
+{
+	return bp->attr.bp_len;
+}
+
+extern struct perf_event *
+register_user_hw_breakpoint(struct perf_event_attr *attr,
+			    perf_overflow_handler_t triggered,
+			    struct task_struct *tsk);
+
+/* FIXME: only change from the attr, and don't unregister */
+extern int
+modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr);
+
+/*
+ * Kernel breakpoints are not associated with any particular thread.
+ */
+extern struct perf_event *
+register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr,
+				perf_overflow_handler_t	triggered,
+				int cpu);
+
+extern struct perf_event * __percpu *
+register_wide_hw_breakpoint(struct perf_event_attr *attr,
+			    perf_overflow_handler_t triggered);
+
+extern int register_perf_hw_breakpoint(struct perf_event *bp);
+extern int __register_perf_hw_breakpoint(struct perf_event *bp);
+extern void unregister_hw_breakpoint(struct perf_event *bp);
+extern void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events);
+
+extern int dbg_reserve_bp_slot(struct perf_event *bp);
+extern int dbg_release_bp_slot(struct perf_event *bp);
+extern int reserve_bp_slot(struct perf_event *bp);
+extern void release_bp_slot(struct perf_event *bp);
+
+extern void flush_ptrace_hw_breakpoint(struct task_struct *tsk);
+
+static inline struct arch_hw_breakpoint *counter_arch_bp(struct perf_event *bp)
+{
+	return &bp->hw.info;
+}
+
+#else /* !CONFIG_HAVE_HW_BREAKPOINT */
+
+static inline int __init init_hw_breakpoint(void) { return 0; }
+
+static inline struct perf_event *
+register_user_hw_breakpoint(struct perf_event_attr *attr,
+			    perf_overflow_handler_t triggered,
+			    struct task_struct *tsk)	{ return NULL; }
+static inline int
+modify_user_hw_breakpoint(struct perf_event *bp,
+			  struct perf_event_attr *attr)	{ return -ENOSYS; }
+static inline struct perf_event *
+register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr,
+				perf_overflow_handler_t	 triggered,
+				int cpu)		{ return NULL; }
+static inline struct perf_event * __percpu *
+register_wide_hw_breakpoint(struct perf_event_attr *attr,
+			    perf_overflow_handler_t triggered)	{ return NULL; }
+static inline int
+register_perf_hw_breakpoint(struct perf_event *bp)	{ return -ENOSYS; }
+static inline int
+__register_perf_hw_breakpoint(struct perf_event *bp) 	{ return -ENOSYS; }
+static inline void unregister_hw_breakpoint(struct perf_event *bp)	{ }
+static inline void
+unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events)	{ }
+static inline int
+reserve_bp_slot(struct perf_event *bp)			{return -ENOSYS; }
+static inline void release_bp_slot(struct perf_event *bp) 		{ }
+
+static inline void flush_ptrace_hw_breakpoint(struct task_struct *tsk)	{ }
+
+static inline struct arch_hw_breakpoint *counter_arch_bp(struct perf_event *bp)
+{
+	return NULL;
+}
+
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+#endif /* __KERNEL__ */
+
+#endif /* _LINUX_HW_BREAKPOINT_H */
diff --git a/smartt-perf/util/include/linux/kernel.h b/smartt-perf/util/include/linux/kernel.h
new file mode 100644
index 0000000..1eb804f
--- /dev/null
+++ b/smartt-perf/util/include/linux/kernel.h
@@ -0,0 +1,111 @@
+#ifndef PERF_LINUX_KERNEL_H_
+#define PERF_LINUX_KERNEL_H_
+
+#include <stdarg.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <assert.h>
+
+#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
+
+#define ALIGN(x,a)		__ALIGN_MASK(x,(typeof(x))(a)-1)
+#define __ALIGN_MASK(x,mask)	(((x)+(mask))&~(mask))
+
+#ifndef offsetof
+#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)
+#endif
+
+#ifndef container_of
+/**
+ * container_of - cast a member of a structure out to the containing structure
+ * @ptr:	the pointer to the member.
+ * @type:	the type of the container struct this is embedded in.
+ * @member:	the name of the member within the struct.
+ *
+ */
+#define container_of(ptr, type, member) ({			\
+	const typeof(((type *)0)->member) * __mptr = (ptr);	\
+	(type *)((char *)__mptr - offsetof(type, member)); })
+#endif
+
+#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))
+
+#ifndef max
+#define max(x, y) ({				\
+	typeof(x) _max1 = (x);			\
+	typeof(y) _max2 = (y);			\
+	(void) (&_max1 == &_max2);		\
+	_max1 > _max2 ? _max1 : _max2; })
+#endif
+
+#ifndef min
+#define min(x, y) ({				\
+	typeof(x) _min1 = (x);			\
+	typeof(y) _min2 = (y);			\
+	(void) (&_min1 == &_min2);		\
+	_min1 < _min2 ? _min1 : _min2; })
+#endif
+
+#ifndef BUG_ON
+#define BUG_ON(cond) assert(!(cond))
+#endif
+
+/*
+ * Both need more care to handle endianness
+ * (Don't use bitmap_copy_le() for now)
+ */
+#define cpu_to_le64(x)	(x)
+#define cpu_to_le32(x)	(x)
+
+static inline int
+vscnprintf(char *buf, size_t size, const char *fmt, va_list args)
+{
+	int i;
+	ssize_t ssize = size;
+
+	i = vsnprintf(buf, size, fmt, args);
+
+	return (i >= ssize) ? (ssize - 1) : i;
+}
+
+static inline int scnprintf(char * buf, size_t size, const char * fmt, ...)
+{
+	va_list args;
+	ssize_t ssize = size;
+	int i;
+
+	va_start(args, fmt);
+	i = vsnprintf(buf, size, fmt, args);
+	va_end(args);
+
+	return (i >= ssize) ? (ssize - 1) : i;
+}
+
+static inline unsigned long
+simple_strtoul(const char *nptr, char **endptr, int base)
+{
+	return strtoul(nptr, endptr, base);
+}
+
+int eprintf(int level,
+	    const char *fmt, ...) __attribute__((format(printf, 2, 3)));
+
+#ifndef pr_fmt
+#define pr_fmt(fmt) fmt
+#endif
+
+#define pr_err(fmt, ...) \
+	eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_warning(fmt, ...) \
+	eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_info(fmt, ...) \
+	eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug(fmt, ...) \
+	eprintf(1, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debugN(n, fmt, ...) \
+	eprintf(n, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__)
+
+#endif
diff --git a/smartt-perf/util/include/linux/linkage.h b/smartt-perf/util/include/linux/linkage.h
new file mode 100644
index 0000000..06387cf
--- /dev/null
+++ b/smartt-perf/util/include/linux/linkage.h
@@ -0,0 +1,13 @@
+
+#ifndef PERF_LINUX_LINKAGE_H_
+#define PERF_LINUX_LINKAGE_H_
+
+/* linkage.h ... for including arch/x86/lib/memcpy_64.S */
+
+#define ENTRY(name)				\
+	.globl name;				\
+	name:
+
+#define ENDPROC(name)
+
+#endif	/* PERF_LINUX_LINKAGE_H_ */
diff --git a/smartt-perf/util/include/linux/list.h b/smartt-perf/util/include/linux/list.h
new file mode 100644
index 0000000..f86acef
--- /dev/null
+++ b/smartt-perf/util/include/linux/list.h
@@ -0,0 +1,751 @@
+#ifndef _LINUX_LIST_H
+#define _LINUX_LIST_H
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/poison.h>
+#include <linux/prefetch.h>
+
+/*
+ * Simple doubly linked list implementation.
+ *
+ * Some of the internal functions ("__xxx") are useful when
+ * manipulating whole lists rather than single entries, as
+ * sometimes we already know the next/prev entries and we can
+ * generate better code by using them directly rather than
+ * using the generic single-entry routines.
+ */
+
+#define LIST_HEAD_INIT(name) { &(name), &(name) }
+
+#define LIST_HEAD(name) \
+	struct list_head name = LIST_HEAD_INIT(name)
+
+static inline void INIT_LIST_HEAD(struct list_head *list)
+{
+	list->next = list;
+	list->prev = list;
+}
+
+/*
+ * Insert a new entry between two known consecutive entries.
+ *
+ * This is only for internal list manipulation where we know
+ * the prev/next entries already!
+ */
+#ifndef CONFIG_DEBUG_LIST
+static inline void __list_add(struct list_head *new,
+			      struct list_head *prev,
+			      struct list_head *next)
+{
+	next->prev = new;
+	new->next = next;
+	new->prev = prev;
+	prev->next = new;
+}
+#else
+extern void __list_add(struct list_head *new,
+			      struct list_head *prev,
+			      struct list_head *next);
+#endif
+
+/**
+ * list_add - add a new entry
+ * @new: new entry to be added
+ * @head: list head to add it after
+ *
+ * Insert a new entry after the specified head.
+ * This is good for implementing stacks.
+ */
+static inline void list_add(struct list_head *new, struct list_head *head)
+{
+	__list_add(new, head, head->next);
+}
+
+
+/**
+ * list_add_tail - add a new entry
+ * @new: new entry to be added
+ * @head: list head to add it before
+ *
+ * Insert a new entry before the specified head.
+ * This is useful for implementing queues.
+ */
+static inline void list_add_tail(struct list_head *new, struct list_head *head)
+{
+	__list_add(new, head->prev, head);
+}
+
+/*
+ * Delete a list entry by making the prev/next entries
+ * point to each other.
+ *
+ * This is only for internal list manipulation where we know
+ * the prev/next entries already!
+ */
+static inline void __list_del(struct list_head * prev, struct list_head * next)
+{
+	next->prev = prev;
+	prev->next = next;
+}
+
+/**
+ * list_del - deletes entry from list.
+ * @entry: the element to delete from the list.
+ * Note: list_empty() on entry does not return true after this, the entry is
+ * in an undefined state.
+ */
+#ifndef CONFIG_DEBUG_LIST
+static inline void __list_del_entry(struct list_head *entry)
+{
+	__list_del(entry->prev, entry->next);
+}
+
+static inline void list_del(struct list_head *entry)
+{
+	__list_del(entry->prev, entry->next);
+	entry->next = LIST_POISON1;
+	entry->prev = LIST_POISON2;
+}
+#else
+extern void __list_del_entry(struct list_head *entry);
+extern void list_del(struct list_head *entry);
+#endif
+
+/**
+ * list_replace - replace old entry by new one
+ * @old : the element to be replaced
+ * @new : the new element to insert
+ *
+ * If @old was empty, it will be overwritten.
+ */
+static inline void list_replace(struct list_head *old,
+				struct list_head *new)
+{
+	new->next = old->next;
+	new->next->prev = new;
+	new->prev = old->prev;
+	new->prev->next = new;
+}
+
+static inline void list_replace_init(struct list_head *old,
+					struct list_head *new)
+{
+	list_replace(old, new);
+	INIT_LIST_HEAD(old);
+}
+
+/**
+ * list_del_init - deletes entry from list and reinitialize it.
+ * @entry: the element to delete from the list.
+ */
+static inline void list_del_init(struct list_head *entry)
+{
+	__list_del_entry(entry);
+	INIT_LIST_HEAD(entry);
+}
+
+/**
+ * list_move - delete from one list and add as another's head
+ * @list: the entry to move
+ * @head: the head that will precede our entry
+ */
+static inline void list_move(struct list_head *list, struct list_head *head)
+{
+	__list_del_entry(list);
+	list_add(list, head);
+}
+
+/**
+ * list_move_tail - delete from one list and add as another's tail
+ * @list: the entry to move
+ * @head: the head that will follow our entry
+ */
+static inline void list_move_tail(struct list_head *list,
+				  struct list_head *head)
+{
+	__list_del_entry(list);
+	list_add_tail(list, head);
+}
+
+/**
+ * list_is_last - tests whether @list is the last entry in list @head
+ * @list: the entry to test
+ * @head: the head of the list
+ */
+static inline int list_is_last(const struct list_head *list,
+				const struct list_head *head)
+{
+	return list->next == head;
+}
+
+/**
+ * list_empty - tests whether a list is empty
+ * @head: the list to test.
+ */
+static inline int list_empty(const struct list_head *head)
+{
+	return head->next == head;
+}
+
+/**
+ * list_empty_careful - tests whether a list is empty and not being modified
+ * @head: the list to test
+ *
+ * Description:
+ * tests whether a list is empty _and_ checks that no other CPU might be
+ * in the process of modifying either member (next or prev)
+ *
+ * NOTE: using list_empty_careful() without synchronization
+ * can only be safe if the only activity that can happen
+ * to the list entry is list_del_init(). Eg. it cannot be used
+ * if another CPU could re-list_add() it.
+ */
+static inline int list_empty_careful(const struct list_head *head)
+{
+	struct list_head *next = head->next;
+	return (next == head) && (next == head->prev);
+}
+
+/**
+ * list_rotate_left - rotate the list to the left
+ * @head: the head of the list
+ */
+static inline void list_rotate_left(struct list_head *head)
+{
+	struct list_head *first;
+
+	if (!list_empty(head)) {
+		first = head->next;
+		list_move_tail(first, head);
+	}
+}
+
+/**
+ * list_is_singular - tests whether a list has just one entry.
+ * @head: the list to test.
+ */
+static inline int list_is_singular(const struct list_head *head)
+{
+	return !list_empty(head) && (head->next == head->prev);
+}
+
+static inline void __list_cut_position(struct list_head *list,
+		struct list_head *head, struct list_head *entry)
+{
+	struct list_head *new_first = entry->next;
+	list->next = head->next;
+	list->next->prev = list;
+	list->prev = entry;
+	entry->next = list;
+	head->next = new_first;
+	new_first->prev = head;
+}
+
+/**
+ * list_cut_position - cut a list into two
+ * @list: a new list to add all removed entries
+ * @head: a list with entries
+ * @entry: an entry within head, could be the head itself
+ *	and if so we won't cut the list
+ *
+ * This helper moves the initial part of @head, up to and
+ * including @entry, from @head to @list. You should
+ * pass on @entry an element you know is on @head. @list
+ * should be an empty list or a list you do not care about
+ * losing its data.
+ *
+ */
+static inline void list_cut_position(struct list_head *list,
+		struct list_head *head, struct list_head *entry)
+{
+	if (list_empty(head))
+		return;
+	if (list_is_singular(head) &&
+		(head->next != entry && head != entry))
+		return;
+	if (entry == head)
+		INIT_LIST_HEAD(list);
+	else
+		__list_cut_position(list, head, entry);
+}
+
+static inline void __list_splice(const struct list_head *list,
+				 struct list_head *prev,
+				 struct list_head *next)
+{
+	struct list_head *first = list->next;
+	struct list_head *last = list->prev;
+
+	first->prev = prev;
+	prev->next = first;
+
+	last->next = next;
+	next->prev = last;
+}
+
+/**
+ * list_splice - join two lists, this is designed for stacks
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ */
+static inline void list_splice(const struct list_head *list,
+				struct list_head *head)
+{
+	if (!list_empty(list))
+		__list_splice(list, head, head->next);
+}
+
+/**
+ * list_splice_tail - join two lists, each list being a queue
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ */
+static inline void list_splice_tail(struct list_head *list,
+				struct list_head *head)
+{
+	if (!list_empty(list))
+		__list_splice(list, head->prev, head);
+}
+
+/**
+ * list_splice_init - join two lists and reinitialise the emptied list.
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ *
+ * The list at @list is reinitialised
+ */
+static inline void list_splice_init(struct list_head *list,
+				    struct list_head *head)
+{
+	if (!list_empty(list)) {
+		__list_splice(list, head, head->next);
+		INIT_LIST_HEAD(list);
+	}
+}
+
+/**
+ * list_splice_tail_init - join two lists and reinitialise the emptied list
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ *
+ * Each of the lists is a queue.
+ * The list at @list is reinitialised
+ */
+static inline void list_splice_tail_init(struct list_head *list,
+					 struct list_head *head)
+{
+	if (!list_empty(list)) {
+		__list_splice(list, head->prev, head);
+		INIT_LIST_HEAD(list);
+	}
+}
+
+/**
+ * list_entry - get the struct for this entry
+ * @ptr:	the &struct list_head pointer.
+ * @type:	the type of the struct this is embedded in.
+ * @member:	the name of the list_struct within the struct.
+ */
+#define list_entry(ptr, type, member) \
+	container_of(ptr, type, member)
+
+/**
+ * list_first_entry - get the first element from a list
+ * @ptr:	the list head to take the element from.
+ * @type:	the type of the struct this is embedded in.
+ * @member:	the name of the list_struct within the struct.
+ *
+ * Note, that list is expected to be not empty.
+ */
+#define list_first_entry(ptr, type, member) \
+	list_entry((ptr)->next, type, member)
+
+/**
+ * list_for_each	-	iterate over a list
+ * @pos:	the &struct list_head to use as a loop cursor.
+ * @head:	the head for your list.
+ */
+#define list_for_each(pos, head) \
+	for (pos = (head)->next; prefetch(pos->next), pos != (head); \
+        	pos = pos->next)
+
+/**
+ * __list_for_each	-	iterate over a list
+ * @pos:	the &struct list_head to use as a loop cursor.
+ * @head:	the head for your list.
+ *
+ * This variant differs from list_for_each() in that it's the
+ * simplest possible list iteration code, no prefetching is done.
+ * Use this for code that knows the list to be very short (empty
+ * or 1 entry) most of the time.
+ */
+#define __list_for_each(pos, head) \
+	for (pos = (head)->next; pos != (head); pos = pos->next)
+
+/**
+ * list_for_each_prev	-	iterate over a list backwards
+ * @pos:	the &struct list_head to use as a loop cursor.
+ * @head:	the head for your list.
+ */
+#define list_for_each_prev(pos, head) \
+	for (pos = (head)->prev; prefetch(pos->prev), pos != (head); \
+        	pos = pos->prev)
+
+/**
+ * list_for_each_safe - iterate over a list safe against removal of list entry
+ * @pos:	the &struct list_head to use as a loop cursor.
+ * @n:		another &struct list_head to use as temporary storage
+ * @head:	the head for your list.
+ */
+#define list_for_each_safe(pos, n, head) \
+	for (pos = (head)->next, n = pos->next; pos != (head); \
+		pos = n, n = pos->next)
+
+/**
+ * list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry
+ * @pos:	the &struct list_head to use as a loop cursor.
+ * @n:		another &struct list_head to use as temporary storage
+ * @head:	the head for your list.
+ */
+#define list_for_each_prev_safe(pos, n, head) \
+	for (pos = (head)->prev, n = pos->prev; \
+	     prefetch(pos->prev), pos != (head); \
+	     pos = n, n = pos->prev)
+
+/**
+ * list_for_each_entry	-	iterate over list of given type
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the list_struct within the struct.
+ */
+#define list_for_each_entry(pos, head, member)				\
+	for (pos = list_entry((head)->next, typeof(*pos), member);	\
+	     prefetch(pos->member.next), &pos->member != (head); 	\
+	     pos = list_entry(pos->member.next, typeof(*pos), member))
+
+/**
+ * list_for_each_entry_reverse - iterate backwards over list of given type.
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the list_struct within the struct.
+ */
+#define list_for_each_entry_reverse(pos, head, member)			\
+	for (pos = list_entry((head)->prev, typeof(*pos), member);	\
+	     prefetch(pos->member.prev), &pos->member != (head); 	\
+	     pos = list_entry(pos->member.prev, typeof(*pos), member))
+
+/**
+ * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue()
+ * @pos:	the type * to use as a start point
+ * @head:	the head of the list
+ * @member:	the name of the list_struct within the struct.
+ *
+ * Prepares a pos entry for use as a start point in list_for_each_entry_continue().
+ */
+#define list_prepare_entry(pos, head, member) \
+	((pos) ? : list_entry(head, typeof(*pos), member))
+
+/**
+ * list_for_each_entry_continue - continue iteration over list of given type
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the list_struct within the struct.
+ *
+ * Continue to iterate over list of given type, continuing after
+ * the current position.
+ */
+#define list_for_each_entry_continue(pos, head, member) 		\
+	for (pos = list_entry(pos->member.next, typeof(*pos), member);	\
+	     prefetch(pos->member.next), &pos->member != (head);	\
+	     pos = list_entry(pos->member.next, typeof(*pos), member))
+
+/**
+ * list_for_each_entry_continue_reverse - iterate backwards from the given point
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the list_struct within the struct.
+ *
+ * Start to iterate over list of given type backwards, continuing after
+ * the current position.
+ */
+#define list_for_each_entry_continue_reverse(pos, head, member)		\
+	for (pos = list_entry(pos->member.prev, typeof(*pos), member);	\
+	     prefetch(pos->member.prev), &pos->member != (head);	\
+	     pos = list_entry(pos->member.prev, typeof(*pos), member))
+
+/**
+ * list_for_each_entry_from - iterate over list of given type from the current point
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the list_struct within the struct.
+ *
+ * Iterate over list of given type, continuing from current position.
+ */
+#define list_for_each_entry_from(pos, head, member) 			\
+	for (; prefetch(pos->member.next), &pos->member != (head);	\
+	     pos = list_entry(pos->member.next, typeof(*pos), member))
+
+/**
+ * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry
+ * @pos:	the type * to use as a loop cursor.
+ * @n:		another type * to use as temporary storage
+ * @head:	the head for your list.
+ * @member:	the name of the list_struct within the struct.
+ */
+#define list_for_each_entry_safe(pos, n, head, member)			\
+	for (pos = list_entry((head)->next, typeof(*pos), member),	\
+		n = list_entry(pos->member.next, typeof(*pos), member);	\
+	     &pos->member != (head); 					\
+	     pos = n, n = list_entry(n->member.next, typeof(*n), member))
+
+/**
+ * list_for_each_entry_safe_continue - continue list iteration safe against removal
+ * @pos:	the type * to use as a loop cursor.
+ * @n:		another type * to use as temporary storage
+ * @head:	the head for your list.
+ * @member:	the name of the list_struct within the struct.
+ *
+ * Iterate over list of given type, continuing after current point,
+ * safe against removal of list entry.
+ */
+#define list_for_each_entry_safe_continue(pos, n, head, member) 		\
+	for (pos = list_entry(pos->member.next, typeof(*pos), member), 		\
+		n = list_entry(pos->member.next, typeof(*pos), member);		\
+	     &pos->member != (head);						\
+	     pos = n, n = list_entry(n->member.next, typeof(*n), member))
+
+/**
+ * list_for_each_entry_safe_from - iterate over list from current point safe against removal
+ * @pos:	the type * to use as a loop cursor.
+ * @n:		another type * to use as temporary storage
+ * @head:	the head for your list.
+ * @member:	the name of the list_struct within the struct.
+ *
+ * Iterate over list of given type from current point, safe against
+ * removal of list entry.
+ */
+#define list_for_each_entry_safe_from(pos, n, head, member) 			\
+	for (n = list_entry(pos->member.next, typeof(*pos), member);		\
+	     &pos->member != (head);						\
+	     pos = n, n = list_entry(n->member.next, typeof(*n), member))
+
+/**
+ * list_for_each_entry_safe_reverse - iterate backwards over list safe against removal
+ * @pos:	the type * to use as a loop cursor.
+ * @n:		another type * to use as temporary storage
+ * @head:	the head for your list.
+ * @member:	the name of the list_struct within the struct.
+ *
+ * Iterate backwards over list of given type, safe against removal
+ * of list entry.
+ */
+#define list_for_each_entry_safe_reverse(pos, n, head, member)		\
+	for (pos = list_entry((head)->prev, typeof(*pos), member),	\
+		n = list_entry(pos->member.prev, typeof(*pos), member);	\
+	     &pos->member != (head); 					\
+	     pos = n, n = list_entry(n->member.prev, typeof(*n), member))
+
+/**
+ * list_safe_reset_next - reset a stale list_for_each_entry_safe loop
+ * @pos:	the loop cursor used in the list_for_each_entry_safe loop
+ * @n:		temporary storage used in list_for_each_entry_safe
+ * @member:	the name of the list_struct within the struct.
+ *
+ * list_safe_reset_next is not safe to use in general if the list may be
+ * modified concurrently (eg. the lock is dropped in the loop body). An
+ * exception to this is if the cursor element (pos) is pinned in the list,
+ * and list_safe_reset_next is called after re-taking the lock and before
+ * completing the current iteration of the loop body.
+ */
+#define list_safe_reset_next(pos, n, member)				\
+	n = list_entry(pos->member.next, typeof(*pos), member)
+
+/*
+ * Double linked lists with a single pointer list head.
+ * Mostly useful for hash tables where the two pointer list head is
+ * too wasteful.
+ * You lose the ability to access the tail in O(1).
+ */
+
+#define HLIST_HEAD_INIT { .first = NULL }
+#define HLIST_HEAD(name) struct hlist_head name = {  .first = NULL }
+#define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL)
+static inline void INIT_HLIST_NODE(struct hlist_node *h)
+{
+	h->next = NULL;
+	h->pprev = NULL;
+}
+
+static inline int hlist_unhashed(const struct hlist_node *h)
+{
+	return !h->pprev;
+}
+
+static inline int hlist_empty(const struct hlist_head *h)
+{
+	return !h->first;
+}
+
+static inline void __hlist_del(struct hlist_node *n)
+{
+	struct hlist_node *next = n->next;
+	struct hlist_node **pprev = n->pprev;
+	*pprev = next;
+	if (next)
+		next->pprev = pprev;
+}
+
+static inline void hlist_del(struct hlist_node *n)
+{
+	__hlist_del(n);
+	n->next = LIST_POISON1;
+	n->pprev = LIST_POISON2;
+}
+
+static inline void hlist_del_init(struct hlist_node *n)
+{
+	if (!hlist_unhashed(n)) {
+		__hlist_del(n);
+		INIT_HLIST_NODE(n);
+	}
+}
+
+static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h)
+{
+	struct hlist_node *first = h->first;
+	n->next = first;
+	if (first)
+		first->pprev = &n->next;
+	h->first = n;
+	n->pprev = &h->first;
+}
+
+/* next must be != NULL */
+static inline void hlist_add_before(struct hlist_node *n,
+					struct hlist_node *next)
+{
+	n->pprev = next->pprev;
+	n->next = next;
+	next->pprev = &n->next;
+	*(n->pprev) = n;
+}
+
+static inline void hlist_add_after(struct hlist_node *n,
+					struct hlist_node *next)
+{
+	next->next = n->next;
+	n->next = next;
+	next->pprev = &n->next;
+
+	if(next->next)
+		next->next->pprev  = &next->next;
+}
+
+/* after that we'll appear to be on some hlist and hlist_del will work */
+static inline void hlist_add_fake(struct hlist_node *n)
+{
+	n->pprev = &n->next;
+}
+
+/*
+ * Move a list from one list head to another. Fixup the pprev
+ * reference of the first entry if it exists.
+ */
+static inline void hlist_move_list(struct hlist_head *old,
+				   struct hlist_head *new)
+{
+	new->first = old->first;
+	if (new->first)
+		new->first->pprev = &new->first;
+	old->first = NULL;
+}
+
+#define hlist_entry(ptr, type, member) container_of(ptr,type,member)
+
+#define hlist_for_each(pos, head) \
+	for (pos = (head)->first; pos && ({ prefetch(pos->next); 1; }); \
+	     pos = pos->next)
+
+#define hlist_for_each_safe(pos, n, head) \
+	for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \
+	     pos = n)
+
+/**
+ * hlist_for_each_entry	- iterate over list of given type
+ * @tpos:	the type * to use as a loop cursor.
+ * @pos:	the &struct hlist_node to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry(tpos, pos, head, member)			 \
+	for (pos = (head)->first;					 \
+	     pos && ({ prefetch(pos->next); 1;}) &&			 \
+		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \
+	     pos = pos->next)
+
+/**
+ * hlist_for_each_entry_continue - iterate over a hlist continuing after current point
+ * @tpos:	the type * to use as a loop cursor.
+ * @pos:	the &struct hlist_node to use as a loop cursor.
+ * @member:	the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry_continue(tpos, pos, member)		 \
+	for (pos = (pos)->next;						 \
+	     pos && ({ prefetch(pos->next); 1;}) &&			 \
+		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \
+	     pos = pos->next)
+
+/**
+ * hlist_for_each_entry_from - iterate over a hlist continuing from current point
+ * @tpos:	the type * to use as a loop cursor.
+ * @pos:	the &struct hlist_node to use as a loop cursor.
+ * @member:	the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry_from(tpos, pos, member)			 \
+	for (; pos && ({ prefetch(pos->next); 1;}) &&			 \
+		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \
+	     pos = pos->next)
+
+/**
+ * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry
+ * @tpos:	the type * to use as a loop cursor.
+ * @pos:	the &struct hlist_node to use as a loop cursor.
+ * @n:		another &struct hlist_node to use as temporary storage
+ * @head:	the head for your list.
+ * @member:	the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry_safe(tpos, pos, n, head, member) 		 \
+	for (pos = (head)->first;					 \
+	     pos && ({ n = pos->next; 1; }) && 				 \
+		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \
+	     pos = n)
+
+#endif
+
+
+#ifndef PERF_LIST_H
+#define PERF_LIST_H
+/**
+ * list_del_range - deletes range of entries from list.
+ * @begin: first element in the range to delete from the list.
+ * @end: last element in the range to delete from the list.
+ * Note: list_empty on the range of entries does not return true after this,
+ * the entries is in an undefined state.
+ */
+static inline void list_del_range(struct list_head *begin,
+                                  struct list_head *end)
+{
+        begin->prev->next = end->next;
+        end->next->prev = begin->prev;
+}
+
+/**
+ * list_for_each_from   -       iterate over a list from one of its nodes
+ * @pos:  the &struct list_head to use as a loop cursor, from where to start
+ * @head: the head for your list.
+ */
+#define list_for_each_from(pos, head) \
+        for (; prefetch(pos->next), pos != (head); pos = pos->next)
+#endif
+
diff --git a/smartt-perf/util/include/linux/magic.h b/smartt-perf/util/include/linux/magic.h
new file mode 100644
index 0000000..62730ea
--- /dev/null
+++ b/smartt-perf/util/include/linux/magic.h
@@ -0,0 +1,63 @@
+#ifndef __LINUX_MAGIC_H__
+#define __LINUX_MAGIC_H__
+
+#define ADFS_SUPER_MAGIC	0xadf5
+#define AFFS_SUPER_MAGIC	0xadff
+#define AFS_SUPER_MAGIC                0x5346414F
+#define AUTOFS_SUPER_MAGIC	0x0187
+#define CODA_SUPER_MAGIC	0x73757245
+#define CRAMFS_MAGIC		0x28cd3d45	/* some random number */
+#define CRAMFS_MAGIC_WEND	0x453dcd28	/* magic number with the wrong endianess */
+#define DEBUGFS_MAGIC          0x64626720
+#define SYSFS_MAGIC		0x62656572
+#define SECURITYFS_MAGIC	0x73636673
+#define SELINUX_MAGIC		0xf97cff8c
+#define RAMFS_MAGIC		0x858458f6	/* some random number */
+#define TMPFS_MAGIC		0x01021994
+#define HUGETLBFS_MAGIC 	0x958458f6	/* some random number */
+#define SQUASHFS_MAGIC		0x73717368
+#define ECRYPTFS_SUPER_MAGIC	0xf15f
+#define EFS_SUPER_MAGIC		0x414A53
+#define EXT2_SUPER_MAGIC	0xEF53
+#define EXT3_SUPER_MAGIC	0xEF53
+#define XENFS_SUPER_MAGIC	0xabba1974
+#define EXT4_SUPER_MAGIC	0xEF53
+#define BTRFS_SUPER_MAGIC	0x9123683E
+#define HPFS_SUPER_MAGIC	0xf995e849
+#define ISOFS_SUPER_MAGIC	0x9660
+#define JFFS2_SUPER_MAGIC	0x72b6
+#define ANON_INODE_FS_MAGIC	0x09041934
+
+#define MINIX_SUPER_MAGIC	0x137F		/* original minix fs */
+#define MINIX_SUPER_MAGIC2	0x138F		/* minix fs, 30 char names */
+#define MINIX2_SUPER_MAGIC	0x2468		/* minix V2 fs */
+#define MINIX2_SUPER_MAGIC2	0x2478		/* minix V2 fs, 30 char names */
+#define MINIX3_SUPER_MAGIC	0x4d5a		/* minix V3 fs */
+
+#define MSDOS_SUPER_MAGIC	0x4d44		/* MD */
+#define NCP_SUPER_MAGIC		0x564c		/* Guess, what 0x564c is :-) */
+#define NFS_SUPER_MAGIC		0x6969
+#define OPENPROM_SUPER_MAGIC	0x9fa1
+#define PROC_SUPER_MAGIC	0x9fa0
+#define QNX4_SUPER_MAGIC	0x002f		/* qnx4 fs detection */
+
+#define REISERFS_SUPER_MAGIC	0x52654973	/* used by gcc */
+					/* used by file system utilities that
+	                                   look at the superblock, etc.  */
+#define REISERFS_SUPER_MAGIC_STRING	"ReIsErFs"
+#define REISER2FS_SUPER_MAGIC_STRING	"ReIsEr2Fs"
+#define REISER2FS_JR_SUPER_MAGIC_STRING	"ReIsEr3Fs"
+
+#define SMB_SUPER_MAGIC		0x517B
+#define USBDEVICE_SUPER_MAGIC	0x9fa2
+#define CGROUP_SUPER_MAGIC	0x27e0eb
+
+#define FUTEXFS_SUPER_MAGIC	0xBAD1DEA
+
+#define STACK_END_MAGIC		0x57AC6E9D
+
+#define DEVPTS_SUPER_MAGIC	0x1cd1
+#define SOCKFS_MAGIC		0x534F434B
+#define V9FS_MAGIC		0x01021997
+
+#endif /* __LINUX_MAGIC_H__ */
diff --git a/smartt-perf/util/include/linux/module.h b/smartt-perf/util/include/linux/module.h
new file mode 100644
index 0000000..b43e2dc
--- /dev/null
+++ b/smartt-perf/util/include/linux/module.h
@@ -0,0 +1,6 @@
+#ifndef PERF_LINUX_MODULE_H
+#define PERF_LINUX_MODULE_H
+
+#define EXPORT_SYMBOL(name)
+
+#endif
diff --git a/smartt-perf/util/include/linux/perf_event.h b/smartt-perf/util/include/linux/perf_event.h
new file mode 100644
index 0000000..dda5b0a
--- /dev/null
+++ b/smartt-perf/util/include/linux/perf_event.h
@@ -0,0 +1,1180 @@
+/*
+ * Performance events:
+ *
+ *    Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de>
+ *    Copyright (C) 2008-2009, Red Hat, Inc., Ingo Molnar
+ *    Copyright (C) 2008-2009, Red Hat, Inc., Peter Zijlstra
+ *
+ * Data type definitions, declarations, prototypes.
+ *
+ *    Started by: Thomas Gleixner and Ingo Molnar
+ *
+ * For licencing details see kernel-base/COPYING
+ */
+#ifndef _LINUX_PERF_EVENT_H
+#define _LINUX_PERF_EVENT_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+#include <asm/byteorder.h>
+
+/*
+ * User-space ABI bits:
+ */
+
+/*
+ * attr.type
+ */
+enum perf_type_id {
+	PERF_TYPE_HARDWARE			= 0,
+	PERF_TYPE_SOFTWARE			= 1,
+	PERF_TYPE_TRACEPOINT			= 2,
+	PERF_TYPE_HW_CACHE			= 3,
+	PERF_TYPE_RAW				= 4,
+	PERF_TYPE_BREAKPOINT			= 5,
+
+	PERF_TYPE_MAX,				/* non-ABI */
+};
+
+/*
+ * Generalized performance event event_id types, used by the
+ * attr.event_id parameter of the sys_perf_event_open()
+ * syscall:
+ */
+enum perf_hw_id {
+	/*
+	 * Common hardware events, generalized by the kernel:
+	 */
+	PERF_COUNT_HW_CPU_CYCLES		= 0,
+	PERF_COUNT_HW_INSTRUCTIONS		= 1,
+	PERF_COUNT_HW_CACHE_REFERENCES		= 2,
+	PERF_COUNT_HW_CACHE_MISSES		= 3,
+	PERF_COUNT_HW_BRANCH_INSTRUCTIONS	= 4,
+	PERF_COUNT_HW_BRANCH_MISSES		= 5,
+	PERF_COUNT_HW_BUS_CYCLES		= 6,
+
+	PERF_COUNT_HW_MAX,			/* non-ABI */
+};
+
+/*
+ * Generalized hardware cache events:
+ *
+ *       { L1-D, L1-I, LLC, ITLB, DTLB, BPU } x
+ *       { read, write, prefetch } x
+ *       { accesses, misses }
+ */
+enum perf_hw_cache_id {
+	PERF_COUNT_HW_CACHE_L1D			= 0,
+	PERF_COUNT_HW_CACHE_L1I			= 1,
+	PERF_COUNT_HW_CACHE_LL			= 2,
+	PERF_COUNT_HW_CACHE_DTLB		= 3,
+	PERF_COUNT_HW_CACHE_ITLB		= 4,
+	PERF_COUNT_HW_CACHE_BPU			= 5,
+
+	PERF_COUNT_HW_CACHE_MAX,		/* non-ABI */
+};
+
+enum perf_hw_cache_op_id {
+	PERF_COUNT_HW_CACHE_OP_READ		= 0,
+	PERF_COUNT_HW_CACHE_OP_WRITE		= 1,
+	PERF_COUNT_HW_CACHE_OP_PREFETCH		= 2,
+
+	PERF_COUNT_HW_CACHE_OP_MAX,		/* non-ABI */
+};
+
+enum perf_hw_cache_op_result_id {
+	PERF_COUNT_HW_CACHE_RESULT_ACCESS	= 0,
+	PERF_COUNT_HW_CACHE_RESULT_MISS		= 1,
+
+	PERF_COUNT_HW_CACHE_RESULT_MAX,		/* non-ABI */
+};
+
+/*
+ * Special "software" events provided by the kernel, even if the hardware
+ * does not support performance events. These events measure various
+ * physical and sw events of the kernel (and allow the profiling of them as
+ * well):
+ */
+enum perf_sw_ids {
+	PERF_COUNT_SW_CPU_CLOCK			= 0,
+	PERF_COUNT_SW_TASK_CLOCK		= 1,
+	PERF_COUNT_SW_PAGE_FAULTS		= 2,
+	PERF_COUNT_SW_CONTEXT_SWITCHES		= 3,
+	PERF_COUNT_SW_CPU_MIGRATIONS		= 4,
+	PERF_COUNT_SW_PAGE_FAULTS_MIN		= 5,
+	PERF_COUNT_SW_PAGE_FAULTS_MAJ		= 6,
+	PERF_COUNT_SW_ALIGNMENT_FAULTS		= 7,
+	PERF_COUNT_SW_EMULATION_FAULTS		= 8,
+
+	PERF_COUNT_SW_MAX,			/* non-ABI */
+};
+
+/*
+ * Bits that can be set in attr.sample_type to request information
+ * in the overflow packets.
+ */
+enum perf_event_sample_format {
+	PERF_SAMPLE_IP				= 1U << 0,
+	PERF_SAMPLE_TID				= 1U << 1,
+	PERF_SAMPLE_TIME			= 1U << 2,
+	PERF_SAMPLE_ADDR			= 1U << 3,
+	PERF_SAMPLE_READ			= 1U << 4,
+	PERF_SAMPLE_CALLCHAIN			= 1U << 5,
+	PERF_SAMPLE_ID				= 1U << 6,
+	PERF_SAMPLE_CPU				= 1U << 7,
+	PERF_SAMPLE_PERIOD			= 1U << 8,
+	PERF_SAMPLE_STREAM_ID			= 1U << 9,
+	PERF_SAMPLE_RAW				= 1U << 10,
+
+	PERF_SAMPLE_MAX = 1U << 11,		/* non-ABI */
+};
+
+/*
+ * The format of the data returned by read() on a perf event fd,
+ * as specified by attr.read_format:
+ *
+ * struct read_format {
+ *	{ u64		value;
+ *	  { u64		time_enabled; } && PERF_FORMAT_ENABLED
+ *	  { u64		time_running; } && PERF_FORMAT_RUNNING
+ *	  { u64		id;           } && PERF_FORMAT_ID
+ *	} && !PERF_FORMAT_GROUP
+ *
+ *	{ u64		nr;
+ *	  { u64		time_enabled; } && PERF_FORMAT_ENABLED
+ *	  { u64		time_running; } && PERF_FORMAT_RUNNING
+ *	  { u64		value;
+ *	    { u64	id;           } && PERF_FORMAT_ID
+ *	  }		cntr[nr];
+ *	} && PERF_FORMAT_GROUP
+ * };
+ */
+enum perf_event_read_format {
+	PERF_FORMAT_TOTAL_TIME_ENABLED		= 1U << 0,
+	PERF_FORMAT_TOTAL_TIME_RUNNING		= 1U << 1,
+	PERF_FORMAT_ID				= 1U << 2,
+	PERF_FORMAT_GROUP			= 1U << 3,
+
+	PERF_FORMAT_MAX = 1U << 4,		/* non-ABI */
+};
+
+#define PERF_ATTR_SIZE_VER0	64	/* sizeof first published struct */
+
+/*
+ * Hardware event_id to monitor via a performance monitoring event:
+ */
+struct perf_event_attr {
+
+	/*
+	 * Major type: hardware/software/tracepoint/etc.
+	 */
+	__u32			type;
+
+	/*
+	 * Size of the attr structure, for fwd/bwd compat.
+	 */
+	__u32			size;
+
+	/*
+	 * Type specific configuration information.
+	 */
+	__u64			config;
+
+	union {
+		__u64		sample_period;
+		__u64		sample_freq;
+	};
+
+	__u64			sample_type;
+	__u64			read_format;
+
+	__u64			disabled       :  1, /* off by default        */
+				inherit	       :  1, /* children inherit it   */
+				pinned	       :  1, /* must always be on PMU */
+				exclusive      :  1, /* only group on PMU     */
+				exclude_user   :  1, /* don't count user      */
+				exclude_kernel :  1, /* ditto kernel          */
+				exclude_hv     :  1, /* ditto hypervisor      */
+				exclude_idle   :  1, /* don't count when idle */
+				mmap           :  1, /* include mmap data     */
+				comm	       :  1, /* include comm data     */
+				freq           :  1, /* use freq, not period  */
+				inherit_stat   :  1, /* per task counts       */
+				enable_on_exec :  1, /* next exec enables     */
+				task           :  1, /* trace fork/exit       */
+				watermark      :  1, /* wakeup_watermark      */
+				/*
+				 * precise_ip:
+				 *
+				 *  0 - SAMPLE_IP can have arbitrary skid
+				 *  1 - SAMPLE_IP must have constant skid
+				 *  2 - SAMPLE_IP requested to have 0 skid
+				 *  3 - SAMPLE_IP must have 0 skid
+				 *
+				 *  See also PERF_RECORD_MISC_EXACT_IP
+				 */
+				precise_ip     :  2, /* skid constraint       */
+				mmap_data      :  1, /* non-exec mmap data    */
+				sample_id_all  :  1, /* sample_type all events */
+
+				__reserved_1   : 45;
+
+	union {
+		__u32		wakeup_events;	  /* wakeup every n events */
+		__u32		wakeup_watermark; /* bytes before wakeup   */
+	};
+
+	__u32			bp_type;
+	__u64			bp_addr;
+	__u64			bp_len;
+};
+
+/*
+ * Ioctls that can be done on a perf event fd:
+ */
+#define PERF_EVENT_IOC_ENABLE		_IO ('$', 0)
+#define PERF_EVENT_IOC_DISABLE		_IO ('$', 1)
+#define PERF_EVENT_IOC_REFRESH		_IO ('$', 2)
+#define PERF_EVENT_IOC_RESET		_IO ('$', 3)
+#define PERF_EVENT_IOC_PERIOD		_IOW('$', 4, __u64)
+#define PERF_EVENT_IOC_SET_OUTPUT	_IO ('$', 5)
+#define PERF_EVENT_IOC_SET_FILTER	_IOW('$', 6, char *)
+
+enum perf_event_ioc_flags {
+	PERF_IOC_FLAG_GROUP		= 1U << 0,
+};
+
+/*
+ * Structure of the page that can be mapped via mmap
+ */
+struct perf_event_mmap_page {
+	__u32	version;		/* version number of this structure */
+	__u32	compat_version;		/* lowest version this is compat with */
+
+	/*
+	 * Bits needed to read the hw events in user-space.
+	 *
+	 *   u32 seq;
+	 *   s64 count;
+	 *
+	 *   do {
+	 *     seq = pc->lock;
+	 *
+	 *     barrier()
+	 *     if (pc->index) {
+	 *       count = pmc_read(pc->index - 1);
+	 *       count += pc->offset;
+	 *     } else
+	 *       goto regular_read;
+	 *
+	 *     barrier();
+	 *   } while (pc->lock != seq);
+	 *
+	 * NOTE: for obvious reason this only works on self-monitoring
+	 *       processes.
+	 */
+	__u32	lock;			/* seqlock for synchronization */
+	__u32	index;			/* hardware event identifier */
+	__s64	offset;			/* add to hardware event value */
+	__u64	time_enabled;		/* time event active */
+	__u64	time_running;		/* time event on cpu */
+
+		/*
+		 * Hole for extension of the self monitor capabilities
+		 */
+
+	__u64	__reserved[123];	/* align to 1k */
+
+	/*
+	 * Control data for the mmap() data buffer.
+	 *
+	 * User-space reading the @data_head value should issue an rmb(), on
+	 * SMP capable platforms, after reading this value -- see
+	 * perf_event_wakeup().
+	 *
+	 * When the mapping is PROT_WRITE the @data_tail value should be
+	 * written by userspace to reflect the last read data. In this case
+	 * the kernel will not over-write unread data.
+	 */
+	__u64   data_head;		/* head in the data section */
+	__u64	data_tail;		/* user-space written tail */
+};
+
+#define PERF_RECORD_MISC_CPUMODE_MASK		(7 << 0)
+#define PERF_RECORD_MISC_CPUMODE_UNKNOWN	(0 << 0)
+#define PERF_RECORD_MISC_KERNEL			(1 << 0)
+#define PERF_RECORD_MISC_USER			(2 << 0)
+#define PERF_RECORD_MISC_HYPERVISOR		(3 << 0)
+#define PERF_RECORD_MISC_GUEST_KERNEL		(4 << 0)
+#define PERF_RECORD_MISC_GUEST_USER		(5 << 0)
+
+/*
+ * Indicates that the content of PERF_SAMPLE_IP points to
+ * the actual instruction that triggered the event. See also
+ * perf_event_attr::precise_ip.
+ */
+#define PERF_RECORD_MISC_EXACT_IP		(1 << 14)
+/*
+ * Reserve the last bit to indicate some extended misc field
+ */
+#define PERF_RECORD_MISC_EXT_RESERVED		(1 << 15)
+
+struct perf_event_header {
+	__u32	type;
+	__u16	misc;
+	__u16	size;
+};
+
+enum perf_event_type {
+
+	/*
+	 * If perf_event_attr.sample_id_all is set then all event types will
+	 * have the sample_type selected fields related to where/when
+	 * (identity) an event took place (TID, TIME, ID, CPU, STREAM_ID)
+	 * described in PERF_RECORD_SAMPLE below, it will be stashed just after
+	 * the perf_event_header and the fields already present for the existing
+	 * fields, i.e. at the end of the payload. That way a newer perf.data
+	 * file will be supported by older perf tools, with these new optional
+	 * fields being ignored.
+	 *
+	 * The MMAP events record the PROT_EXEC mappings so that we can
+	 * correlate userspace IPs to code. They have the following structure:
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	u64				addr;
+	 *	u64				len;
+	 *	u64				pgoff;
+	 *	char				filename[];
+	 * };
+	 */
+	PERF_RECORD_MMAP			= 1,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				id;
+	 *	u64				lost;
+	 * };
+	 */
+	PERF_RECORD_LOST			= 2,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	char				comm[];
+	 * };
+	 */
+	PERF_RECORD_COMM			= 3,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, ppid;
+	 *	u32				tid, ptid;
+	 *	u64				time;
+	 * };
+	 */
+	PERF_RECORD_EXIT			= 4,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				time;
+	 *	u64				id;
+	 *	u64				stream_id;
+	 * };
+	 */
+	PERF_RECORD_THROTTLE			= 5,
+	PERF_RECORD_UNTHROTTLE			= 6,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, ppid;
+	 *	u32				tid, ptid;
+	 *	u64				time;
+	 * };
+	 */
+	PERF_RECORD_FORK			= 7,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, tid;
+	 *
+	 *	struct read_format		values;
+	 * };
+	 */
+	PERF_RECORD_READ			= 8,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	{ u64			ip;	  } && PERF_SAMPLE_IP
+	 *	{ u32			pid, tid; } && PERF_SAMPLE_TID
+	 *	{ u64			time;     } && PERF_SAMPLE_TIME
+	 *	{ u64			addr;     } && PERF_SAMPLE_ADDR
+	 *	{ u64			id;	  } && PERF_SAMPLE_ID
+	 *	{ u64			stream_id;} && PERF_SAMPLE_STREAM_ID
+	 *	{ u32			cpu, res; } && PERF_SAMPLE_CPU
+	 *	{ u64			period;   } && PERF_SAMPLE_PERIOD
+	 *
+	 *	{ struct read_format	values;	  } && PERF_SAMPLE_READ
+	 *
+	 *	{ u64			nr,
+	 *	  u64			ips[nr];  } && PERF_SAMPLE_CALLCHAIN
+	 *
+	 *	#
+	 *	# The RAW record below is opaque data wrt the ABI
+	 *	#
+	 *	# That is, the ABI doesn't make any promises wrt to
+	 *	# the stability of its content, it may vary depending
+	 *	# on event, hardware, kernel version and phase of
+	 *	# the moon.
+	 *	#
+	 *	# In other words, PERF_SAMPLE_RAW contents are not an ABI.
+	 *	#
+	 *
+	 *	{ u32			size;
+	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
+	 * };
+	 */
+	PERF_RECORD_SAMPLE			= 9,
+
+	PERF_RECORD_MAX,			/* non-ABI */
+};
+
+enum perf_callchain_context {
+	PERF_CONTEXT_HV			= (__u64)-32,
+	PERF_CONTEXT_KERNEL		= (__u64)-128,
+	PERF_CONTEXT_USER		= (__u64)-512,
+
+	PERF_CONTEXT_GUEST		= (__u64)-2048,
+	PERF_CONTEXT_GUEST_KERNEL	= (__u64)-2176,
+	PERF_CONTEXT_GUEST_USER		= (__u64)-2560,
+
+	PERF_CONTEXT_MAX		= (__u64)-4095,
+};
+
+#define PERF_FLAG_FD_NO_GROUP	(1U << 0)
+#define PERF_FLAG_FD_OUTPUT	(1U << 1)
+
+#ifdef __KERNEL__
+/*
+ * Kernel-internal data types and definitions:
+ */
+
+#ifdef CONFIG_PERF_EVENTS
+# include <asm/perf_event.h>
+# include <asm/local64.h>
+#endif
+
+struct perf_guest_info_callbacks {
+	int (*is_in_guest) (void);
+	int (*is_user_mode) (void);
+	unsigned long (*get_guest_ip) (void);
+};
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+#include <asm/hw_breakpoint.h>
+#endif
+
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/spinlock.h>
+#include <linux/hrtimer.h>
+#include <linux/fs.h>
+#include <linux/pid_namespace.h>
+#include <linux/workqueue.h>
+#include <linux/ftrace.h>
+#include <linux/cpu.h>
+#include <linux/irq_work.h>
+#include <linux/jump_label_ref.h>
+#include <asm/atomic.h>
+#include <asm/local.h>
+
+#define PERF_MAX_STACK_DEPTH		255
+
+struct perf_callchain_entry {
+	__u64				nr;
+	__u64				ip[PERF_MAX_STACK_DEPTH];
+};
+
+struct perf_raw_record {
+	u32				size;
+	void				*data;
+};
+
+struct perf_branch_entry {
+	__u64				from;
+	__u64				to;
+	__u64				flags;
+};
+
+struct perf_branch_stack {
+	__u64				nr;
+	struct perf_branch_entry	entries[0];
+};
+
+struct task_struct;
+
+/**
+ * struct hw_perf_event - performance event hardware details:
+ */
+struct hw_perf_event {
+#ifdef CONFIG_PERF_EVENTS
+	union {
+		struct { /* hardware */
+			u64		config;
+			u64		last_tag;
+			unsigned long	config_base;
+			unsigned long	event_base;
+			int		idx;
+			int		last_cpu;
+		};
+		struct { /* software */
+			struct hrtimer	hrtimer;
+		};
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+		struct { /* breakpoint */
+			struct arch_hw_breakpoint	info;
+			struct list_head		bp_list;
+			/*
+			 * Crufty hack to avoid the chicken and egg
+			 * problem hw_breakpoint has with context
+			 * creation and event initalization.
+			 */
+			struct task_struct		*bp_target;
+		};
+#endif
+	};
+	int				state;
+	local64_t			prev_count;
+	u64				sample_period;
+	u64				last_period;
+	local64_t			period_left;
+	u64				interrupts;
+
+	u64				freq_time_stamp;
+	u64				freq_count_stamp;
+#endif
+};
+
+/*
+ * hw_perf_event::state flags
+ */
+#define PERF_HES_STOPPED	0x01 /* the counter is stopped */
+#define PERF_HES_UPTODATE	0x02 /* event->count up-to-date */
+#define PERF_HES_ARCH		0x04
+
+struct perf_event;
+
+/*
+ * Common implementation detail of pmu::{start,commit,cancel}_txn
+ */
+#define PERF_EVENT_TXN 0x1
+
+/**
+ * struct pmu - generic performance monitoring unit
+ */
+struct pmu {
+	struct list_head		entry;
+
+	struct device			*dev;
+	char				*name;
+	int				type;
+
+	int * __percpu			pmu_disable_count;
+	struct perf_cpu_context * __percpu pmu_cpu_context;
+	int				task_ctx_nr;
+
+	/*
+	 * Fully disable/enable this PMU, can be used to protect from the PMI
+	 * as well as for lazy/batch writing of the MSRs.
+	 */
+	void (*pmu_enable)		(struct pmu *pmu); /* optional */
+	void (*pmu_disable)		(struct pmu *pmu); /* optional */
+
+	/*
+	 * Try and initialize the event for this PMU.
+	 * Should return -ENOENT when the @event doesn't match this PMU.
+	 */
+	int (*event_init)		(struct perf_event *event);
+
+#define PERF_EF_START	0x01		/* start the counter when adding    */
+#define PERF_EF_RELOAD	0x02		/* reload the counter when starting */
+#define PERF_EF_UPDATE	0x04		/* update the counter when stopping */
+
+	/*
+	 * Adds/Removes a counter to/from the PMU, can be done inside
+	 * a transaction, see the ->*_txn() methods.
+	 */
+	int  (*add)			(struct perf_event *event, int flags);
+	void (*del)			(struct perf_event *event, int flags);
+
+	/*
+	 * Starts/Stops a counter present on the PMU. The PMI handler
+	 * should stop the counter when perf_event_overflow() returns
+	 * !0. ->start() will be used to continue.
+	 */
+	void (*start)			(struct perf_event *event, int flags);
+	void (*stop)			(struct perf_event *event, int flags);
+
+	/*
+	 * Updates the counter value of the event.
+	 */
+	void (*read)			(struct perf_event *event);
+
+	/*
+	 * Group events scheduling is treated as a transaction, add
+	 * group events as a whole and perform one schedulability test.
+	 * If the test fails, roll back the whole group
+	 *
+	 * Start the transaction, after this ->add() doesn't need to
+	 * do schedulability tests.
+	 */
+	void (*start_txn)	(struct pmu *pmu); /* optional */
+	/*
+	 * If ->start_txn() disabled the ->add() schedulability test
+	 * then ->commit_txn() is required to perform one. On success
+	 * the transaction is closed. On error the transaction is kept
+	 * open until ->cancel_txn() is called.
+	 */
+	int  (*commit_txn)	(struct pmu *pmu); /* optional */
+	/*
+	 * Will cancel the transaction, assumes ->del() is called
+	 * for each successfull ->add() during the transaction.
+	 */
+	void (*cancel_txn)	(struct pmu *pmu); /* optional */
+};
+
+/**
+ * enum perf_event_active_state - the states of a event
+ */
+enum perf_event_active_state {
+	PERF_EVENT_STATE_ERROR		= -2,
+	PERF_EVENT_STATE_OFF		= -1,
+	PERF_EVENT_STATE_INACTIVE	=  0,
+	PERF_EVENT_STATE_ACTIVE		=  1,
+};
+
+struct file;
+
+#define PERF_BUFFER_WRITABLE		0x01
+
+struct perf_buffer {
+	atomic_t			refcount;
+	struct rcu_head			rcu_head;
+#ifdef CONFIG_PERF_USE_VMALLOC
+	struct work_struct		work;
+	int				page_order;	/* allocation order  */
+#endif
+	int				nr_pages;	/* nr of data pages  */
+	int				writable;	/* are we writable   */
+
+	atomic_t			poll;		/* POLL_ for wakeups */
+
+	local_t				head;		/* write position    */
+	local_t				nest;		/* nested writers    */
+	local_t				events;		/* event limit       */
+	local_t				wakeup;		/* wakeup stamp      */
+	local_t				lost;		/* nr records lost   */
+
+	long				watermark;	/* wakeup watermark  */
+
+	struct perf_event_mmap_page	*user_page;
+	void				*data_pages[0];
+};
+
+struct perf_sample_data;
+
+typedef void (*perf_overflow_handler_t)(struct perf_event *, int,
+					struct perf_sample_data *,
+					struct pt_regs *regs);
+
+enum perf_group_flag {
+	PERF_GROUP_SOFTWARE = 0x1,
+};
+
+#define SWEVENT_HLIST_BITS	8
+#define SWEVENT_HLIST_SIZE	(1 << SWEVENT_HLIST_BITS)
+
+struct swevent_hlist {
+	struct hlist_head	heads[SWEVENT_HLIST_SIZE];
+	struct rcu_head		rcu_head;
+};
+
+#define PERF_ATTACH_CONTEXT	0x01
+#define PERF_ATTACH_GROUP	0x02
+#define PERF_ATTACH_TASK	0x04
+
+/**
+ * struct perf_event - performance event kernel representation:
+ */
+struct perf_event {
+#ifdef CONFIG_PERF_EVENTS
+	struct list_head		group_entry;
+	struct list_head		event_entry;
+	struct list_head		sibling_list;
+	struct hlist_node		hlist_entry;
+	int				nr_siblings;
+	int				group_flags;
+	struct perf_event		*group_leader;
+	struct pmu			*pmu;
+
+	enum perf_event_active_state	state;
+	unsigned int			attach_state;
+	local64_t			count;
+	atomic64_t			child_count;
+
+	/*
+	 * These are the total time in nanoseconds that the event
+	 * has been enabled (i.e. eligible to run, and the task has
+	 * been scheduled in, if this is a per-task event)
+	 * and running (scheduled onto the CPU), respectively.
+	 *
+	 * They are computed from tstamp_enabled, tstamp_running and
+	 * tstamp_stopped when the event is in INACTIVE or ACTIVE state.
+	 */
+	u64				total_time_enabled;
+	u64				total_time_running;
+
+	/*
+	 * These are timestamps used for computing total_time_enabled
+	 * and total_time_running when the event is in INACTIVE or
+	 * ACTIVE state, measured in nanoseconds from an arbitrary point
+	 * in time.
+	 * tstamp_enabled: the notional time when the event was enabled
+	 * tstamp_running: the notional time when the event was scheduled on
+	 * tstamp_stopped: in INACTIVE state, the notional time when the
+	 *	event was scheduled off.
+	 */
+	u64				tstamp_enabled;
+	u64				tstamp_running;
+	u64				tstamp_stopped;
+
+	/*
+	 * timestamp shadows the actual context timing but it can
+	 * be safely used in NMI interrupt context. It reflects the
+	 * context time as it was when the event was last scheduled in.
+	 *
+	 * ctx_time already accounts for ctx->timestamp. Therefore to
+	 * compute ctx_time for a sample, simply add perf_clock().
+	 */
+	u64				shadow_ctx_time;
+
+	struct perf_event_attr		attr;
+	u16				header_size;
+	u16				id_header_size;
+	u16				read_size;
+	struct hw_perf_event		hw;
+
+	struct perf_event_context	*ctx;
+	struct file			*filp;
+
+	/*
+	 * These accumulate total time (in nanoseconds) that children
+	 * events have been enabled and running, respectively.
+	 */
+	atomic64_t			child_total_time_enabled;
+	atomic64_t			child_total_time_running;
+
+	/*
+	 * Protect attach/detach and child_list:
+	 */
+	struct mutex			child_mutex;
+	struct list_head		child_list;
+	struct perf_event		*parent;
+
+	int				oncpu;
+	int				cpu;
+
+	struct list_head		owner_entry;
+	struct task_struct		*owner;
+
+	/* mmap bits */
+	struct mutex			mmap_mutex;
+	atomic_t			mmap_count;
+	int				mmap_locked;
+	struct user_struct		*mmap_user;
+	struct perf_buffer		*buffer;
+
+	/* poll related */
+	wait_queue_head_t		waitq;
+	struct fasync_struct		*fasync;
+
+	/* delayed work for NMIs and such */
+	int				pending_wakeup;
+	int				pending_kill;
+	int				pending_disable;
+	struct irq_work			pending;
+
+	atomic_t			event_limit;
+
+	void (*destroy)(struct perf_event *);
+	struct rcu_head			rcu_head;
+
+	struct pid_namespace		*ns;
+	u64				id;
+
+	perf_overflow_handler_t		overflow_handler;
+
+#ifdef CONFIG_EVENT_TRACING
+	struct ftrace_event_call	*tp_event;
+	struct event_filter		*filter;
+#endif
+
+#endif /* CONFIG_PERF_EVENTS */
+};
+
+enum perf_event_context_type {
+	task_context,
+	cpu_context,
+};
+
+/**
+ * struct perf_event_context - event context structure
+ *
+ * Used as a container for task events and CPU events as well:
+ */
+struct perf_event_context {
+	enum perf_event_context_type	type;
+	struct pmu			*pmu;
+	/*
+	 * Protect the states of the events in the list,
+	 * nr_active, and the list:
+	 */
+	raw_spinlock_t			lock;
+	/*
+	 * Protect the list of events.  Locking either mutex or lock
+	 * is sufficient to ensure the list doesn't change; to change
+	 * the list you need to lock both the mutex and the spinlock.
+	 */
+	struct mutex			mutex;
+
+	struct list_head		pinned_groups;
+	struct list_head		flexible_groups;
+	struct list_head		event_list;
+	int				nr_events;
+	int				nr_active;
+	int				is_active;
+	int				nr_stat;
+	int				rotate_disable;
+	atomic_t			refcount;
+	struct task_struct		*task;
+
+	/*
+	 * Context clock, runs when context enabled.
+	 */
+	u64				time;
+	u64				timestamp;
+
+	/*
+	 * These fields let us detect when two contexts have both
+	 * been cloned (inherited) from a common ancestor.
+	 */
+	struct perf_event_context	*parent_ctx;
+	u64				parent_gen;
+	u64				generation;
+	int				pin_count;
+	struct rcu_head			rcu_head;
+};
+
+/*
+ * Number of contexts where an event can trigger:
+ * 	task, softirq, hardirq, nmi.
+ */
+#define PERF_NR_CONTEXTS	4
+
+/**
+ * struct perf_event_cpu_context - per cpu event context structure
+ */
+struct perf_cpu_context {
+	struct perf_event_context	ctx;
+	struct perf_event_context	*task_ctx;
+	int				active_oncpu;
+	int				exclusive;
+	struct list_head		rotation_list;
+	int				jiffies_interval;
+	struct pmu			*active_pmu;
+};
+
+struct perf_output_handle {
+	struct perf_event		*event;
+	struct perf_buffer		*buffer;
+	unsigned long			wakeup;
+	unsigned long			size;
+	void				*addr;
+	int				page;
+	int				nmi;
+	int				sample;
+};
+
+#ifdef CONFIG_PERF_EVENTS
+
+extern int perf_pmu_register(struct pmu *pmu, char *name, int type);
+extern void perf_pmu_unregister(struct pmu *pmu);
+
+extern int perf_num_counters(void);
+extern const char *perf_pmu_name(void);
+extern void __perf_event_task_sched_in(struct task_struct *task);
+extern void __perf_event_task_sched_out(struct task_struct *task, struct task_struct *next);
+extern int perf_event_init_task(struct task_struct *child);
+extern void perf_event_exit_task(struct task_struct *child);
+extern void perf_event_free_task(struct task_struct *task);
+extern void perf_event_delayed_put(struct task_struct *task);
+extern void perf_event_print_debug(void);
+extern void perf_pmu_disable(struct pmu *pmu);
+extern void perf_pmu_enable(struct pmu *pmu);
+extern int perf_event_task_disable(void);
+extern int perf_event_task_enable(void);
+extern void perf_event_update_userpage(struct perf_event *event);
+extern int perf_event_release_kernel(struct perf_event *event);
+extern struct perf_event *
+perf_event_create_kernel_counter(struct perf_event_attr *attr,
+				int cpu,
+				struct task_struct *task,
+				perf_overflow_handler_t callback);
+extern u64 perf_event_read_value(struct perf_event *event,
+				 u64 *enabled, u64 *running);
+
+struct perf_sample_data {
+	u64				type;
+
+	u64				ip;
+	struct {
+		u32	pid;
+		u32	tid;
+	}				tid_entry;
+	u64				time;
+	u64				addr;
+	u64				id;
+	u64				stream_id;
+	struct {
+		u32	cpu;
+		u32	reserved;
+	}				cpu_entry;
+	u64				period;
+	struct perf_callchain_entry	*callchain;
+	struct perf_raw_record		*raw;
+};
+
+static inline
+void perf_sample_data_init(struct perf_sample_data *data, u64 addr)
+{
+	data->addr = addr;
+	data->raw  = NULL;
+}
+
+extern void perf_output_sample(struct perf_output_handle *handle,
+			       struct perf_event_header *header,
+			       struct perf_sample_data *data,
+			       struct perf_event *event);
+extern void perf_prepare_sample(struct perf_event_header *header,
+				struct perf_sample_data *data,
+				struct perf_event *event,
+				struct pt_regs *regs);
+
+extern int perf_event_overflow(struct perf_event *event, int nmi,
+				 struct perf_sample_data *data,
+				 struct pt_regs *regs);
+
+static inline bool is_sampling_event(struct perf_event *event)
+{
+	return event->attr.sample_period != 0;
+}
+
+/*
+ * Return 1 for a software event, 0 for a hardware event
+ */
+static inline int is_software_event(struct perf_event *event)
+{
+	return event->pmu->task_ctx_nr == perf_sw_context;
+}
+
+extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
+
+extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64);
+
+#ifndef perf_arch_fetch_caller_regs
+static inline void
+perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { }
+#endif
+
+/*
+ * Take a snapshot of the regs. Skip ip and frame pointer to
+ * the nth caller. We only need a few of the regs:
+ * - ip for PERF_SAMPLE_IP
+ * - cs for user_mode() tests
+ * - bp for callchains
+ * - eflags, for future purposes, just in case
+ */
+static inline void perf_fetch_caller_regs(struct pt_regs *regs)
+{
+	memset(regs, 0, sizeof(*regs));
+
+	perf_arch_fetch_caller_regs(regs, CALLER_ADDR0);
+}
+
+static __always_inline void
+perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
+{
+	struct pt_regs hot_regs;
+
+	JUMP_LABEL(&perf_swevent_enabled[event_id], have_event);
+	return;
+
+have_event:
+	if (!regs) {
+		perf_fetch_caller_regs(&hot_regs);
+		regs = &hot_regs;
+	}
+	__perf_sw_event(event_id, nr, nmi, regs, addr);
+}
+
+extern atomic_t perf_task_events;
+
+static inline void perf_event_task_sched_in(struct task_struct *task)
+{
+	COND_STMT(&perf_task_events, __perf_event_task_sched_in(task));
+}
+
+static inline
+void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next)
+{
+	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
+
+	COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next));
+}
+
+extern void perf_event_mmap(struct vm_area_struct *vma);
+extern struct perf_guest_info_callbacks *perf_guest_cbs;
+extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
+extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
+
+extern void perf_event_comm(struct task_struct *tsk);
+extern void perf_event_fork(struct task_struct *tsk);
+
+/* Callchains */
+DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
+
+extern void perf_callchain_user(struct perf_callchain_entry *entry,
+				struct pt_regs *regs);
+extern void perf_callchain_kernel(struct perf_callchain_entry *entry,
+				  struct pt_regs *regs);
+
+
+static inline void
+perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
+{
+	if (entry->nr < PERF_MAX_STACK_DEPTH)
+		entry->ip[entry->nr++] = ip;
+}
+
+extern int sysctl_perf_event_paranoid;
+extern int sysctl_perf_event_mlock;
+extern int sysctl_perf_event_sample_rate;
+
+static inline bool perf_paranoid_tracepoint_raw(void)
+{
+	return sysctl_perf_event_paranoid > -1;
+}
+
+static inline bool perf_paranoid_cpu(void)
+{
+	return sysctl_perf_event_paranoid > 0;
+}
+
+static inline bool perf_paranoid_kernel(void)
+{
+	return sysctl_perf_event_paranoid > 1;
+}
+
+extern void perf_event_init(void);
+extern void perf_tp_event(u64 addr, u64 count, void *record,
+			  int entry_size, struct pt_regs *regs,
+			  struct hlist_head *head, int rctx);
+extern void perf_bp_event(struct perf_event *event, void *data);
+
+#ifndef perf_misc_flags
+#define perf_misc_flags(regs)	(user_mode(regs) ? PERF_RECORD_MISC_USER : \
+				 PERF_RECORD_MISC_KERNEL)
+#define perf_instruction_pointer(regs)	instruction_pointer(regs)
+#endif
+
+extern int perf_output_begin(struct perf_output_handle *handle,
+			     struct perf_event *event, unsigned int size,
+			     int nmi, int sample);
+extern void perf_output_end(struct perf_output_handle *handle);
+extern void perf_output_copy(struct perf_output_handle *handle,
+			     const void *buf, unsigned int len);
+extern int perf_swevent_get_recursion_context(void);
+extern void perf_swevent_put_recursion_context(int rctx);
+extern void perf_event_enable(struct perf_event *event);
+extern void perf_event_disable(struct perf_event *event);
+extern void perf_event_task_tick(void);
+#else
+static inline void
+perf_event_task_sched_in(struct task_struct *task)			{ }
+static inline void
+perf_event_task_sched_out(struct task_struct *task,
+			    struct task_struct *next)			{ }
+static inline int perf_event_init_task(struct task_struct *child)	{ return 0; }
+static inline void perf_event_exit_task(struct task_struct *child)	{ }
+static inline void perf_event_free_task(struct task_struct *task)	{ }
+static inline void perf_event_delayed_put(struct task_struct *task)	{ }
+static inline void perf_event_print_debug(void)				{ }
+static inline int perf_event_task_disable(void)				{ return -EINVAL; }
+static inline int perf_event_task_enable(void)				{ return -EINVAL; }
+
+static inline void
+perf_sw_event(u32 event_id, u64 nr, int nmi,
+		     struct pt_regs *regs, u64 addr)			{ }
+static inline void
+perf_bp_event(struct perf_event *event, void *data)			{ }
+
+static inline int perf_register_guest_info_callbacks
+(struct perf_guest_info_callbacks *callbacks) { return 0; }
+static inline int perf_unregister_guest_info_callbacks
+(struct perf_guest_info_callbacks *callbacks) { return 0; }
+
+static inline void perf_event_mmap(struct vm_area_struct *vma)		{ }
+static inline void perf_event_comm(struct task_struct *tsk)		{ }
+static inline void perf_event_fork(struct task_struct *tsk)		{ }
+static inline void perf_event_init(void)				{ }
+static inline int  perf_swevent_get_recursion_context(void)		{ return -1; }
+static inline void perf_swevent_put_recursion_context(int rctx)		{ }
+static inline void perf_event_enable(struct perf_event *event)		{ }
+static inline void perf_event_disable(struct perf_event *event)		{ }
+static inline void perf_event_task_tick(void)				{ }
+#endif
+
+#define perf_output_put(handle, x) \
+	perf_output_copy((handle), &(x), sizeof(x))
+
+/*
+ * This has to have a higher priority than migration_notifier in sched.c.
+ */
+#define perf_cpu_notifier(fn)					\
+do {								\
+	static struct notifier_block fn##_nb __cpuinitdata =	\
+		{ .notifier_call = fn, .priority = CPU_PRI_PERF }; \
+	fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE,		\
+		(void *)(unsigned long)smp_processor_id());	\
+	fn(&fn##_nb, (unsigned long)CPU_STARTING,		\
+		(void *)(unsigned long)smp_processor_id());	\
+	fn(&fn##_nb, (unsigned long)CPU_ONLINE,			\
+		(void *)(unsigned long)smp_processor_id());	\
+	register_cpu_notifier(&fn##_nb);			\
+} while (0)
+
+#endif /* __KERNEL__ */
+#endif /* _LINUX_PERF_EVENT_H */
diff --git a/smartt-perf/util/include/linux/poison.h b/smartt-perf/util/include/linux/poison.h
new file mode 100644
index 0000000..2110a81
--- /dev/null
+++ b/smartt-perf/util/include/linux/poison.h
@@ -0,0 +1,89 @@
+#ifndef _LINUX_POISON_H
+#define _LINUX_POISON_H
+
+/********** include/linux/list.h **********/
+
+/*
+ * Architectures might want to move the poison pointer offset
+ * into some well-recognized area such as 0xdead000000000000,
+ * that is also not mappable by user-space exploits:
+ */
+#ifdef CONFIG_ILLEGAL_POINTER_VALUE
+# define POISON_POINTER_DELTA _AC(CONFIG_ILLEGAL_POINTER_VALUE, UL)
+#else
+# define POISON_POINTER_DELTA 0
+#endif
+
+/*
+ * These are non-NULL pointers that will result in page faults
+ * under normal circumstances, used to verify that nobody uses
+ * non-initialized list entries.
+ */
+#define LIST_POISON1  ((void *) 0x00100100 + POISON_POINTER_DELTA)
+#define LIST_POISON2  ((void *) 0x00200200 + POISON_POINTER_DELTA)
+
+/********** include/linux/timer.h **********/
+/*
+ * Magic number "tsta" to indicate a static timer initializer
+ * for the object debugging code.
+ */
+#define TIMER_ENTRY_STATIC	((void *) 0x74737461)
+
+/********** mm/debug-pagealloc.c **********/
+#define PAGE_POISON 0xaa
+
+/********** mm/slab.c **********/
+/*
+ * Magic nums for obj red zoning.
+ * Placed in the first word before and the first word after an obj.
+ */
+#define	RED_INACTIVE	0x09F911029D74E35BULL	/* when obj is inactive */
+#define	RED_ACTIVE	0xD84156C5635688C0ULL	/* when obj is active */
+
+#define SLUB_RED_INACTIVE	0xbb
+#define SLUB_RED_ACTIVE		0xcc
+
+/* ...and for poisoning */
+#define	POISON_INUSE	0x5a	/* for use-uninitialised poisoning */
+#define POISON_FREE	0x6b	/* for use-after-free poisoning */
+#define	POISON_END	0xa5	/* end-byte of poisoning */
+
+/********** arch/$ARCH/mm/init.c **********/
+#define POISON_FREE_INITMEM	0xcc
+
+/********** arch/ia64/hp/common/sba_iommu.c **********/
+/*
+ * arch/ia64/hp/common/sba_iommu.c uses a 16-byte poison string with a
+ * value of "SBAIOMMU POISON\0" for spill-over poisoning.
+ */
+
+/********** fs/jbd/journal.c **********/
+#define JBD_POISON_FREE		0x5b
+#define JBD2_POISON_FREE	0x5c
+
+/********** drivers/base/dmapool.c **********/
+#define	POOL_POISON_FREED	0xa7	/* !inuse */
+#define	POOL_POISON_ALLOCATED	0xa9	/* !initted */
+
+/********** drivers/atm/ **********/
+#define ATM_POISON_FREE		0x12
+#define ATM_POISON		0xdeadbeef
+
+/********** net/ **********/
+#define NEIGHBOR_DEAD		0xdeadbeef
+#define NETFILTER_LINK_POISON	0xdead57ac
+
+/********** kernel/mutexes **********/
+#define MUTEX_DEBUG_INIT	0x11
+#define MUTEX_DEBUG_FREE	0x22
+
+/********** lib/flex_array.c **********/
+#define FLEX_ARRAY_FREE	0x6c	/* for use-after-free poisoning */
+
+/********** security/ **********/
+#define KEY_DESTROY		0xbd
+
+/********** sound/oss/ **********/
+#define OSS_POISON_FREE		0xAB
+
+#endif
diff --git a/smartt-perf/util/include/linux/prefetch.h b/smartt-perf/util/include/linux/prefetch.h
new file mode 100644
index 0000000..7841e48
--- /dev/null
+++ b/smartt-perf/util/include/linux/prefetch.h
@@ -0,0 +1,6 @@
+#ifndef PERF_LINUX_PREFETCH_H
+#define PERF_LINUX_PREFETCH_H
+
+static inline void prefetch(void *a __attribute__((unused))) { }
+
+#endif
diff --git a/smartt-perf/util/include/linux/rbtree.h b/smartt-perf/util/include/linux/rbtree.h
new file mode 100644
index 0000000..7066acb
--- /dev/null
+++ b/smartt-perf/util/include/linux/rbtree.h
@@ -0,0 +1,169 @@
+/*
+  Red Black Trees
+  (C) 1999  Andrea Arcangeli <andrea@suse.de>
+  
+  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.
+
+  This program is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+  GNU General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with this program; if not, write to the Free Software
+  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+  linux/include/linux/rbtree.h
+
+  To use rbtrees you'll have to implement your own insert and search cores.
+  This will avoid us to use callbacks and to drop drammatically performances.
+  I know it's not the cleaner way,  but in C (not in C++) to get
+  performances and genericity...
+
+  Some example of insert and search follows here. The search is a plain
+  normal search over an ordered tree. The insert instead must be implemented
+  in two steps: First, the code must insert the element in order as a red leaf
+  in the tree, and then the support library function rb_insert_color() must
+  be called. Such function will do the not trivial work to rebalance the
+  rbtree, if necessary.
+
+-----------------------------------------------------------------------
+static inline struct page * rb_search_page_cache(struct inode * inode,
+						 unsigned long offset)
+{
+	struct rb_node * n = inode->i_rb_page_cache.rb_node;
+	struct page * page;
+
+	while (n)
+	{
+		page = rb_entry(n, struct page, rb_page_cache);
+
+		if (offset < page->offset)
+			n = n->rb_left;
+		else if (offset > page->offset)
+			n = n->rb_right;
+		else
+			return page;
+	}
+	return NULL;
+}
+
+static inline struct page * __rb_insert_page_cache(struct inode * inode,
+						   unsigned long offset,
+						   struct rb_node * node)
+{
+	struct rb_node ** p = &inode->i_rb_page_cache.rb_node;
+	struct rb_node * parent = NULL;
+	struct page * page;
+
+	while (*p)
+	{
+		parent = *p;
+		page = rb_entry(parent, struct page, rb_page_cache);
+
+		if (offset < page->offset)
+			p = &(*p)->rb_left;
+		else if (offset > page->offset)
+			p = &(*p)->rb_right;
+		else
+			return page;
+	}
+
+	rb_link_node(node, parent, p);
+
+	return NULL;
+}
+
+static inline struct page * rb_insert_page_cache(struct inode * inode,
+						 unsigned long offset,
+						 struct rb_node * node)
+{
+	struct page * ret;
+	if ((ret = __rb_insert_page_cache(inode, offset, node)))
+		goto out;
+	rb_insert_color(node, &inode->i_rb_page_cache);
+ out:
+	return ret;
+}
+-----------------------------------------------------------------------
+*/
+
+#ifndef	_LINUX_RBTREE_H
+#define	_LINUX_RBTREE_H
+
+#include <linux/kernel.h>
+#include <linux/stddef.h>
+
+struct rb_node
+{
+	unsigned long  rb_parent_color;
+#define	RB_RED		0
+#define	RB_BLACK	1
+	struct rb_node *rb_right;
+	struct rb_node *rb_left;
+} __attribute__((aligned(sizeof(long))));
+    /* The alignment might seem pointless, but allegedly CRIS needs it */
+
+struct rb_root
+{
+	struct rb_node *rb_node;
+};
+
+
+#define rb_parent(r)   ((struct rb_node *)((r)->rb_parent_color & ~3))
+#define rb_color(r)   ((r)->rb_parent_color & 1)
+#define rb_is_red(r)   (!rb_color(r))
+#define rb_is_black(r) rb_color(r)
+#define rb_set_red(r)  do { (r)->rb_parent_color &= ~1; } while (0)
+#define rb_set_black(r)  do { (r)->rb_parent_color |= 1; } while (0)
+
+static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p)
+{
+	rb->rb_parent_color = (rb->rb_parent_color & 3) | (unsigned long)p;
+}
+static inline void rb_set_color(struct rb_node *rb, int color)
+{
+	rb->rb_parent_color = (rb->rb_parent_color & ~1) | color;
+}
+
+#define RB_ROOT	(struct rb_root) { NULL, }
+#define	rb_entry(ptr, type, member) container_of(ptr, type, member)
+
+#define RB_EMPTY_ROOT(root)	((root)->rb_node == NULL)
+#define RB_EMPTY_NODE(node)	(rb_parent(node) == node)
+#define RB_CLEAR_NODE(node)	(rb_set_parent(node, node))
+
+extern void rb_insert_color(struct rb_node *, struct rb_root *);
+extern void rb_erase(struct rb_node *, struct rb_root *);
+
+typedef void (*rb_augment_f)(struct rb_node *node, void *data);
+
+extern void rb_augment_insert(struct rb_node *node,
+			      rb_augment_f func, void *data);
+extern struct rb_node *rb_augment_erase_begin(struct rb_node *node);
+extern void rb_augment_erase_end(struct rb_node *node,
+				 rb_augment_f func, void *data);
+
+/* Find logical next and previous nodes in a tree */
+extern struct rb_node *rb_next(const struct rb_node *);
+extern struct rb_node *rb_prev(const struct rb_node *);
+extern struct rb_node *rb_first(const struct rb_root *);
+extern struct rb_node *rb_last(const struct rb_root *);
+
+/* Fast replacement of a single node without remove/rebalance/add/rebalance */
+extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, 
+			    struct rb_root *root);
+
+static inline void rb_link_node(struct rb_node * node, struct rb_node * parent,
+				struct rb_node ** rb_link)
+{
+	node->rb_parent_color = (unsigned long )parent;
+	node->rb_left = node->rb_right = NULL;
+
+	*rb_link = node;
+}
+
+#endif	/* _LINUX_RBTREE_H */
diff --git a/smartt-perf/util/include/linux/string.h b/smartt-perf/util/include/linux/string.h
new file mode 100644
index 0000000..3b2f590
--- /dev/null
+++ b/smartt-perf/util/include/linux/string.h
@@ -0,0 +1 @@
+#include <string.h>
diff --git a/smartt-perf/util/include/linux/stringify.h b/smartt-perf/util/include/linux/stringify.h
new file mode 100644
index 0000000..841cec8
--- /dev/null
+++ b/smartt-perf/util/include/linux/stringify.h
@@ -0,0 +1,12 @@
+#ifndef __LINUX_STRINGIFY_H
+#define __LINUX_STRINGIFY_H
+
+/* Indirect stringification.  Doing two levels allows the parameter to be a
+ * macro itself.  For example, compile with -DFOO=bar, __stringify(FOO)
+ * converts to "bar".
+ */
+
+#define __stringify_1(x...)	#x
+#define __stringify(x...)	__stringify_1(x)
+
+#endif	/* !__LINUX_STRINGIFY_H */
diff --git a/smartt-perf/util/include/linux/swab.h b/smartt-perf/util/include/linux/swab.h
new file mode 100644
index 0000000..ea0c02f
--- /dev/null
+++ b/smartt-perf/util/include/linux/swab.h
@@ -0,0 +1,299 @@
+#ifndef _LINUX_SWAB_H
+#define _LINUX_SWAB_H
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <asm/swab.h>
+
+/*
+ * casts are necessary for constants, because we never know how for sure
+ * how U/UL/ULL map to __u16, __u32, __u64. At least not in a portable way.
+ */
+#define ___constant_swab16(x) ((__u16)(				\
+	(((__u16)(x) & (__u16)0x00ffU) << 8) |			\
+	(((__u16)(x) & (__u16)0xff00U) >> 8)))
+
+#define ___constant_swab32(x) ((__u32)(				\
+	(((__u32)(x) & (__u32)0x000000ffUL) << 24) |		\
+	(((__u32)(x) & (__u32)0x0000ff00UL) <<  8) |		\
+	(((__u32)(x) & (__u32)0x00ff0000UL) >>  8) |		\
+	(((__u32)(x) & (__u32)0xff000000UL) >> 24)))
+
+#define ___constant_swab64(x) ((__u64)(				\
+	(((__u64)(x) & (__u64)0x00000000000000ffULL) << 56) |	\
+	(((__u64)(x) & (__u64)0x000000000000ff00ULL) << 40) |	\
+	(((__u64)(x) & (__u64)0x0000000000ff0000ULL) << 24) |	\
+	(((__u64)(x) & (__u64)0x00000000ff000000ULL) <<  8) |	\
+	(((__u64)(x) & (__u64)0x000000ff00000000ULL) >>  8) |	\
+	(((__u64)(x) & (__u64)0x0000ff0000000000ULL) >> 24) |	\
+	(((__u64)(x) & (__u64)0x00ff000000000000ULL) >> 40) |	\
+	(((__u64)(x) & (__u64)0xff00000000000000ULL) >> 56)))
+
+#define ___constant_swahw32(x) ((__u32)(			\
+	(((__u32)(x) & (__u32)0x0000ffffUL) << 16) |		\
+	(((__u32)(x) & (__u32)0xffff0000UL) >> 16)))
+
+#define ___constant_swahb32(x) ((__u32)(			\
+	(((__u32)(x) & (__u32)0x00ff00ffUL) << 8) |		\
+	(((__u32)(x) & (__u32)0xff00ff00UL) >> 8)))
+
+/*
+ * Implement the following as inlines, but define the interface using
+ * macros to allow constant folding when possible:
+ * ___swab16, ___swab32, ___swab64, ___swahw32, ___swahb32
+ */
+
+static inline __attribute_const__ __u16 __fswab16(__u16 val)
+{
+#ifdef __arch_swab16
+	return __arch_swab16(val);
+#else
+	return ___constant_swab16(val);
+#endif
+}
+
+static inline __attribute_const__ __u32 __fswab32(__u32 val)
+{
+#ifdef __arch_swab32
+	return __arch_swab32(val);
+#else
+	return ___constant_swab32(val);
+#endif
+}
+
+static inline __attribute_const__ __u64 __fswab64(__u64 val)
+{
+#ifdef __arch_swab64
+	return __arch_swab64(val);
+#elif defined(__SWAB_64_THRU_32__)
+	__u32 h = val >> 32;
+	__u32 l = val & ((1ULL << 32) - 1);
+	return (((__u64)__fswab32(l)) << 32) | ((__u64)(__fswab32(h)));
+#else
+	return ___constant_swab64(val);
+#endif
+}
+
+static inline __attribute_const__ __u32 __fswahw32(__u32 val)
+{
+#ifdef __arch_swahw32
+	return __arch_swahw32(val);
+#else
+	return ___constant_swahw32(val);
+#endif
+}
+
+static inline __attribute_const__ __u32 __fswahb32(__u32 val)
+{
+#ifdef __arch_swahb32
+	return __arch_swahb32(val);
+#else
+	return ___constant_swahb32(val);
+#endif
+}
+
+/**
+ * __swab16 - return a byteswapped 16-bit value
+ * @x: value to byteswap
+ */
+#define __swab16(x)				\
+	(__builtin_constant_p((__u16)(x)) ?	\
+	___constant_swab16(x) :			\
+	__fswab16(x))
+
+/**
+ * __swab32 - return a byteswapped 32-bit value
+ * @x: value to byteswap
+ */
+#define __swab32(x)				\
+	(__builtin_constant_p((__u32)(x)) ?	\
+	___constant_swab32(x) :			\
+	__fswab32(x))
+
+/**
+ * __swab64 - return a byteswapped 64-bit value
+ * @x: value to byteswap
+ */
+#define __swab64(x)				\
+	(__builtin_constant_p((__u64)(x)) ?	\
+	___constant_swab64(x) :			\
+	__fswab64(x))
+
+/**
+ * __swahw32 - return a word-swapped 32-bit value
+ * @x: value to wordswap
+ *
+ * __swahw32(0x12340000) is 0x00001234
+ */
+#define __swahw32(x)				\
+	(__builtin_constant_p((__u32)(x)) ?	\
+	___constant_swahw32(x) :		\
+	__fswahw32(x))
+
+/**
+ * __swahb32 - return a high and low byte-swapped 32-bit value
+ * @x: value to byteswap
+ *
+ * __swahb32(0x12345678) is 0x34127856
+ */
+#define __swahb32(x)				\
+	(__builtin_constant_p((__u32)(x)) ?	\
+	___constant_swahb32(x) :		\
+	__fswahb32(x))
+
+/**
+ * __swab16p - return a byteswapped 16-bit value from a pointer
+ * @p: pointer to a naturally-aligned 16-bit value
+ */
+static inline __u16 __swab16p(const __u16 *p)
+{
+#ifdef __arch_swab16p
+	return __arch_swab16p(p);
+#else
+	return __swab16(*p);
+#endif
+}
+
+/**
+ * __swab32p - return a byteswapped 32-bit value from a pointer
+ * @p: pointer to a naturally-aligned 32-bit value
+ */
+static inline __u32 __swab32p(const __u32 *p)
+{
+#ifdef __arch_swab32p
+	return __arch_swab32p(p);
+#else
+	return __swab32(*p);
+#endif
+}
+
+/**
+ * __swab64p - return a byteswapped 64-bit value from a pointer
+ * @p: pointer to a naturally-aligned 64-bit value
+ */
+static inline __u64 __swab64p(const __u64 *p)
+{
+#ifdef __arch_swab64p
+	return __arch_swab64p(p);
+#else
+	return __swab64(*p);
+#endif
+}
+
+/**
+ * __swahw32p - return a wordswapped 32-bit value from a pointer
+ * @p: pointer to a naturally-aligned 32-bit value
+ *
+ * See __swahw32() for details of wordswapping.
+ */
+static inline __u32 __swahw32p(const __u32 *p)
+{
+#ifdef __arch_swahw32p
+	return __arch_swahw32p(p);
+#else
+	return __swahw32(*p);
+#endif
+}
+
+/**
+ * __swahb32p - return a high and low byteswapped 32-bit value from a pointer
+ * @p: pointer to a naturally-aligned 32-bit value
+ *
+ * See __swahb32() for details of high/low byteswapping.
+ */
+static inline __u32 __swahb32p(const __u32 *p)
+{
+#ifdef __arch_swahb32p
+	return __arch_swahb32p(p);
+#else
+	return __swahb32(*p);
+#endif
+}
+
+/**
+ * __swab16s - byteswap a 16-bit value in-place
+ * @p: pointer to a naturally-aligned 16-bit value
+ */
+static inline void __swab16s(__u16 *p)
+{
+#ifdef __arch_swab16s
+	__arch_swab16s(p);
+#else
+	*p = __swab16p(p);
+#endif
+}
+/**
+ * __swab32s - byteswap a 32-bit value in-place
+ * @p: pointer to a naturally-aligned 32-bit value
+ */
+static inline void __swab32s(__u32 *p)
+{
+#ifdef __arch_swab32s
+	__arch_swab32s(p);
+#else
+	*p = __swab32p(p);
+#endif
+}
+
+/**
+ * __swab64s - byteswap a 64-bit value in-place
+ * @p: pointer to a naturally-aligned 64-bit value
+ */
+static inline void __swab64s(__u64 *p)
+{
+#ifdef __arch_swab64s
+	__arch_swab64s(p);
+#else
+	*p = __swab64p(p);
+#endif
+}
+
+/**
+ * __swahw32s - wordswap a 32-bit value in-place
+ * @p: pointer to a naturally-aligned 32-bit value
+ *
+ * See __swahw32() for details of wordswapping
+ */
+static inline void __swahw32s(__u32 *p)
+{
+#ifdef __arch_swahw32s
+	__arch_swahw32s(p);
+#else
+	*p = __swahw32p(p);
+#endif
+}
+
+/**
+ * __swahb32s - high and low byteswap a 32-bit value in-place
+ * @p: pointer to a naturally-aligned 32-bit value
+ *
+ * See __swahb32() for details of high and low byte swapping
+ */
+static inline void __swahb32s(__u32 *p)
+{
+#ifdef __arch_swahb32s
+	__arch_swahb32s(p);
+#else
+	*p = __swahb32p(p);
+#endif
+}
+
+#ifdef __KERNEL__
+# define swab16 __swab16
+# define swab32 __swab32
+# define swab64 __swab64
+# define swahw32 __swahw32
+# define swahb32 __swahb32
+# define swab16p __swab16p
+# define swab32p __swab32p
+# define swab64p __swab64p
+# define swahw32p __swahw32p
+# define swahb32p __swahb32p
+# define swab16s __swab16s
+# define swab32s __swab32s
+# define swab64s __swab64s
+# define swahw32s __swahw32s
+# define swahb32s __swahb32s
+#endif /* __KERNEL__ */
+
+#endif /* _LINUX_SWAB_H */
diff --git a/smartt-perf/util/include/linux/types.h b/smartt-perf/util/include/linux/types.h
new file mode 100644
index 0000000..12de3b8
--- /dev/null
+++ b/smartt-perf/util/include/linux/types.h
@@ -0,0 +1,21 @@
+#ifndef _PERF_LINUX_TYPES_H_
+#define _PERF_LINUX_TYPES_H_
+
+#include <asm/types.h>
+
+#define DECLARE_BITMAP(name,bits) \
+	unsigned long name[BITS_TO_LONGS(bits)]
+
+struct list_head {
+	struct list_head *next, *prev;
+};
+
+struct hlist_head {
+	struct hlist_node *first;
+};
+
+struct hlist_node {
+	struct hlist_node *next, **pprev;
+};
+
+#endif