Merge branch 'perfcounters-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perfcounters-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (574 commits)
  perf_counter: Turn off by default
  perf_counter: Add counter->id to the throttle event
  perf_counter: Better align code
  perf_counter: Rename L2 to LL cache
  perf_counter: Standardize event names
  perf_counter: Rename enums
  perf_counter tools: Clean up u64 usage
  perf_counter: Rename perf_counter_limit sysctl
  perf_counter: More paranoia settings
  perf_counter: powerpc: Implement generalized cache events for POWER processors
  perf_counters: powerpc: Add support for POWER7 processors
  perf_counter: Accurate period data
  perf_counter: Introduce struct for sample data
  perf_counter tools: Normalize data using per sample period data
  perf_counter: Annotate exit ctx recursion
  perf_counter tools: Propagate signals properly
  perf_counter tools: Small frequency related fixes
  perf_counter: More aggressive frequency adjustment
  perf_counter/x86: Fix the model number of Intel Core2 processors
  perf_counter, x86: Correct some event and umask values for Intel processors
  ...

7 files changed, 741 insertions, 2 deletions

diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index 3673a13b670..81d3be459ef 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -134,7 +134,7 @@ static inline long atomic_long_add_unless(atomic_long_t *l, long a, long u)
 #define atomic_long_cmpxchg(l, old, new) \
 	(atomic64_cmpxchg((atomic64_t *)(l), (old), (new)))
 #define atomic_long_xchg(v, new) \
-	(atomic64_xchg((atomic64_t *)(l), (new)))
+	(atomic64_xchg((atomic64_t *)(v), (new)))
 
 #else  /*  BITS_PER_LONG == 64  */
 
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 6646bfc7b89..28b1f30601b 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -108,6 +108,15 @@ extern struct group_info init_groups;
 
 extern struct cred init_cred;
 
+#ifdef CONFIG_PERF_COUNTERS
+# define INIT_PERF_COUNTERS(tsk)					\
+	.perf_counter_mutex = 						\
+		 __MUTEX_INITIALIZER(tsk.perf_counter_mutex),		\
+	.perf_counter_list = LIST_HEAD_INIT(tsk.perf_counter_list),
+#else
+# define INIT_PERF_COUNTERS(tsk)
+#endif
+
 /*
  *  INIT_TASK is used to set up the first task table, touch at
  * your own risk!. Base=0, limit=0x1fffff (=2MB)
@@ -171,6 +180,7 @@ extern struct cred init_cred;
 	},								\
 	.dirties = INIT_PROP_LOCAL_SINGLE(dirties),			\
 	INIT_IDS							\
+	INIT_PERF_COUNTERS(tsk)						\
 	INIT_TRACE_IRQFLAGS						\
 	INIT_LOCKDEP							\
 	INIT_FTRACE_GRAPH						\
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 0c8b89f28a9..a77c6007dc9 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -81,7 +81,12 @@ static inline unsigned int kstat_irqs(unsigned int irq)
 	return sum;
 }
 
+
+/*
+ * Lock/unlock the current runqueue - to extract task statistics:
+ */
 extern unsigned long long task_delta_exec(struct task_struct *);
+
 extern void account_user_time(struct task_struct *, cputime_t, cputime_t);
 extern void account_system_time(struct task_struct *, int, cputime_t, cputime_t);
 extern void account_steal_time(cputime_t);
diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
new file mode 100644
index 00000000000..6e133954e2e
--- /dev/null
+++ b/include/linux/perf_counter.h
@@ -0,0 +1,697 @@
+/*
+ *  Performance counters:
+ *
+ *    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_COUNTER_H
+#define _LINUX_PERF_COUNTER_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_MAX,				/* non-ABI */
+};
+
+/*
+ * Generalized performance counter event types, used by the
+ * attr.event_id parameter of the sys_perf_counter_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 counters:
+ *
+ *       { 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" counters provided by the kernel, even if the hardware
+ * does not support performance counters. These counters 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_MAX,			/* non-ABI */
+};
+
+/*
+ * Bits that can be set in attr.sample_type to request information
+ * in the overflow packets.
+ */
+enum perf_counter_sample_format {
+	PERF_SAMPLE_IP				= 1U << 0,
+	PERF_SAMPLE_TID				= 1U << 1,
+	PERF_SAMPLE_TIME			= 1U << 2,
+	PERF_SAMPLE_ADDR			= 1U << 3,
+	PERF_SAMPLE_GROUP			= 1U << 4,
+	PERF_SAMPLE_CALLCHAIN			= 1U << 5,
+	PERF_SAMPLE_ID				= 1U << 6,
+	PERF_SAMPLE_CPU				= 1U << 7,
+	PERF_SAMPLE_PERIOD			= 1U << 8,
+};
+
+/*
+ * Bits that can be set in attr.read_format to request that
+ * reads on the counter should return the indicated quantities,
+ * in increasing order of bit value, after the counter value.
+ */
+enum perf_counter_read_format {
+	PERF_FORMAT_TOTAL_TIME_ENABLED		= 1U << 0,
+	PERF_FORMAT_TOTAL_TIME_RUNNING		= 1U << 1,
+	PERF_FORMAT_ID				= 1U << 2,
+};
+
+/*
+ * Hardware event to monitor via a performance monitoring counter:
+ */
+struct perf_counter_attr {
+	/*
+	 * Major type: hardware/software/tracepoint/etc.
+	 */
+	__u32			type;
+	__u32			__reserved_1;
+
+	/*
+	 * 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  */
+
+				__reserved_2   : 53;
+
+	__u32			wakeup_events;	/* wakeup every n events */
+	__u32			__reserved_3;
+
+	__u64			__reserved_4;
+};
+
+/*
+ * Ioctls that can be done on a perf counter fd:
+ */
+#define PERF_COUNTER_IOC_ENABLE		_IO ('$', 0)
+#define PERF_COUNTER_IOC_DISABLE	_IO ('$', 1)
+#define PERF_COUNTER_IOC_REFRESH	_IO ('$', 2)
+#define PERF_COUNTER_IOC_RESET		_IO ('$', 3)
+#define PERF_COUNTER_IOC_PERIOD		_IOW('$', 4, u64)
+
+enum perf_counter_ioc_flags {
+	PERF_IOC_FLAG_GROUP		= 1U << 0,
+};
+
+/*
+ * Structure of the page that can be mapped via mmap
+ */
+struct perf_counter_mmap_page {
+	__u32	version;		/* version number of this structure */
+	__u32	compat_version;		/* lowest version this is compat with */
+
+	/*
+	 * Bits needed to read the hw counters 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 counter identifier */
+	__s64	offset;			/* add to hardware counter value */
+
+	/*
+	 * Control data for the mmap() data buffer.
+	 *
+	 * User-space reading this value should issue an rmb(), on SMP capable
+	 * platforms, after reading this value -- see perf_counter_wakeup().
+	 */
+	__u64   data_head;		/* head in the data section */
+};
+
+#define PERF_EVENT_MISC_CPUMODE_MASK		(3 << 0)
+#define PERF_EVENT_MISC_CPUMODE_UNKNOWN		(0 << 0)
+#define PERF_EVENT_MISC_KERNEL			(1 << 0)
+#define PERF_EVENT_MISC_USER			(2 << 0)
+#define PERF_EVENT_MISC_HYPERVISOR		(3 << 0)
+#define PERF_EVENT_MISC_OVERFLOW		(1 << 2)
+
+struct perf_event_header {
+	__u32	type;
+	__u16	misc;
+	__u16	size;
+};
+
+enum perf_event_type {
+
+	/*
+	 * 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_EVENT_MMAP			= 1,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	char				comm[];
+	 * };
+	 */
+	PERF_EVENT_COMM			= 3,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				time;
+	 *	u64				id;
+	 *	u64				sample_period;
+	 * };
+	 */
+	PERF_EVENT_PERIOD		= 4,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				time;
+	 *	u64				id;
+	 * };
+	 */
+	PERF_EVENT_THROTTLE		= 5,
+	PERF_EVENT_UNTHROTTLE		= 6,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, ppid;
+	 * };
+	 */
+	PERF_EVENT_FORK			= 7,
+
+	/*
+	 * When header.misc & PERF_EVENT_MISC_OVERFLOW the event_type field
+	 * will be PERF_RECORD_*
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	{ u64			ip;	  } && PERF_RECORD_IP
+	 *	{ u32			pid, tid; } && PERF_RECORD_TID
+	 *	{ u64			time;     } && PERF_RECORD_TIME
+	 *	{ u64			addr;     } && PERF_RECORD_ADDR
+	 *	{ u64			config;   } && PERF_RECORD_CONFIG
+	 *	{ u32			cpu, res; } && PERF_RECORD_CPU
+	 *
+	 *	{ u64			nr;
+	 *	  { u64 id, val; }	cnt[nr];  } && PERF_RECORD_GROUP
+	 *
+	 *	{ u16			nr,
+	 *				hv,
+	 *				kernel,
+	 *				user;
+	 *	  u64			ips[nr];  } && PERF_RECORD_CALLCHAIN
+	 * };
+	 */
+};
+
+#ifdef __KERNEL__
+/*
+ * Kernel-internal data types and definitions:
+ */
+
+#ifdef CONFIG_PERF_COUNTERS
+# include <asm/perf_counter.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 <asm/atomic.h>
+
+struct task_struct;
+
+/**
+ * struct hw_perf_counter - performance counter hardware details:
+ */
+struct hw_perf_counter {
+#ifdef CONFIG_PERF_COUNTERS
+	union {
+		struct { /* hardware */
+			u64		config;
+			unsigned long	config_base;
+			unsigned long	counter_base;
+			int		idx;
+		};
+		union { /* software */
+			atomic64_t	count;
+			struct hrtimer	hrtimer;
+		};
+	};
+	atomic64_t			prev_count;
+	u64				sample_period;
+	u64				last_period;
+	atomic64_t			period_left;
+	u64				interrupts;
+
+	u64				freq_count;
+	u64				freq_interrupts;
+	u64				freq_stamp;
+#endif
+};
+
+struct perf_counter;
+
+/**
+ * struct pmu - generic performance monitoring unit
+ */
+struct pmu {
+	int (*enable)			(struct perf_counter *counter);
+	void (*disable)			(struct perf_counter *counter);
+	void (*read)			(struct perf_counter *counter);
+	void (*unthrottle)		(struct perf_counter *counter);
+};
+
+/**
+ * enum perf_counter_active_state - the states of a counter
+ */
+enum perf_counter_active_state {
+	PERF_COUNTER_STATE_ERROR	= -2,
+	PERF_COUNTER_STATE_OFF		= -1,
+	PERF_COUNTER_STATE_INACTIVE	=  0,
+	PERF_COUNTER_STATE_ACTIVE	=  1,
+};
+
+struct file;
+
+struct perf_mmap_data {
+	struct rcu_head			rcu_head;
+	int				nr_pages;	/* nr of data pages  */
+	int				nr_locked;	/* nr pages mlocked  */
+
+	atomic_t			poll;		/* POLL_ for wakeups */
+	atomic_t			events;		/* event limit       */
+
+	atomic_long_t			head;		/* write position    */
+	atomic_long_t			done_head;	/* completed head    */
+
+	atomic_t			lock;		/* concurrent writes */
+
+	atomic_t			wakeup;		/* needs a wakeup    */
+
+	struct perf_counter_mmap_page   *user_page;
+	void				*data_pages[0];
+};
+
+struct perf_pending_entry {
+	struct perf_pending_entry *next;
+	void (*func)(struct perf_pending_entry *);
+};
+
+/**
+ * struct perf_counter - performance counter kernel representation:
+ */
+struct perf_counter {
+#ifdef CONFIG_PERF_COUNTERS
+	struct list_head		list_entry;
+	struct list_head		event_entry;
+	struct list_head		sibling_list;
+	int				nr_siblings;
+	struct perf_counter		*group_leader;
+	const struct pmu		*pmu;
+
+	enum perf_counter_active_state	state;
+	atomic64_t			count;
+
+	/*
+	 * These are the total time in nanoseconds that the counter
+	 * has been enabled (i.e. eligible to run, and the task has
+	 * been scheduled in, if this is a per-task counter)
+	 * and running (scheduled onto the CPU), respectively.
+	 *
+	 * They are computed from tstamp_enabled, tstamp_running and
+	 * tstamp_stopped when the counter 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 counter is in INACTIVE or
+	 * ACTIVE state, measured in nanoseconds from an arbitrary point
+	 * in time.
+	 * tstamp_enabled: the notional time when the counter was enabled
+	 * tstamp_running: the notional time when the counter was scheduled on
+	 * tstamp_stopped: in INACTIVE state, the notional time when the
+	 *	counter was scheduled off.
+	 */
+	u64				tstamp_enabled;
+	u64				tstamp_running;
+	u64				tstamp_stopped;
+
+	struct perf_counter_attr	attr;
+	struct hw_perf_counter		hw;
+
+	struct perf_counter_context	*ctx;
+	struct file			*filp;
+
+	/*
+	 * These accumulate total time (in nanoseconds) that children
+	 * counters 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_counter		*parent;
+
+	int				oncpu;
+	int				cpu;
+
+	struct list_head		owner_entry;
+	struct task_struct		*owner;
+
+	/* mmap bits */
+	struct mutex			mmap_mutex;
+	atomic_t			mmap_count;
+	struct perf_mmap_data		*data;
+
+	/* 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 perf_pending_entry	pending;
+
+	atomic_t			event_limit;
+
+	void (*destroy)(struct perf_counter *);
+	struct rcu_head			rcu_head;
+
+	struct pid_namespace		*ns;
+	u64				id;
+#endif
+};
+
+/**
+ * struct perf_counter_context - counter context structure
+ *
+ * Used as a container for task counters and CPU counters as well:
+ */
+struct perf_counter_context {
+	/*
+	 * Protect the states of the counters in the list,
+	 * nr_active, and the list:
+	 */
+	spinlock_t			lock;
+	/*
+	 * Protect the list of counters.  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		counter_list;
+	struct list_head		event_list;
+	int				nr_counters;
+	int				nr_active;
+	int				is_active;
+	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_counter_context	*parent_ctx;
+	u64				parent_gen;
+	u64				generation;
+	int				pin_count;
+	struct rcu_head			rcu_head;
+};
+
+/**
+ * struct perf_counter_cpu_context - per cpu counter context structure
+ */
+struct perf_cpu_context {
+	struct perf_counter_context	ctx;
+	struct perf_counter_context	*task_ctx;
+	int				active_oncpu;
+	int				max_pertask;
+	int				exclusive;
+
+	/*
+	 * Recursion avoidance:
+	 *
+	 * task, softirq, irq, nmi context
+	 */
+	int				recursion[4];
+};
+
+#ifdef CONFIG_PERF_COUNTERS
+
+/*
+ * Set by architecture code:
+ */
+extern int perf_max_counters;
+
+extern const struct pmu *hw_perf_counter_init(struct perf_counter *counter);
+
+extern void perf_counter_task_sched_in(struct task_struct *task, int cpu);
+extern void perf_counter_task_sched_out(struct task_struct *task,
+					struct task_struct *next, int cpu);
+extern void perf_counter_task_tick(struct task_struct *task, int cpu);
+extern int perf_counter_init_task(struct task_struct *child);
+extern void perf_counter_exit_task(struct task_struct *child);
+extern void perf_counter_free_task(struct task_struct *task);
+extern void perf_counter_do_pending(void);
+extern void perf_counter_print_debug(void);
+extern void __perf_disable(void);
+extern bool __perf_enable(void);
+extern void perf_disable(void);
+extern void perf_enable(void);
+extern int perf_counter_task_disable(void);
+extern int perf_counter_task_enable(void);
+extern int hw_perf_group_sched_in(struct perf_counter *group_leader,
+	       struct perf_cpu_context *cpuctx,
+	       struct perf_counter_context *ctx, int cpu);
+extern void perf_counter_update_userpage(struct perf_counter *counter);
+
+struct perf_sample_data {
+	struct pt_regs			*regs;
+	u64				addr;
+	u64				period;
+};
+
+extern int perf_counter_overflow(struct perf_counter *counter, int nmi,
+				 struct perf_sample_data *data);
+
+/*
+ * Return 1 for a software counter, 0 for a hardware counter
+ */
+static inline int is_software_counter(struct perf_counter *counter)
+{
+	return (counter->attr.type != PERF_TYPE_RAW) &&
+		(counter->attr.type != PERF_TYPE_HARDWARE);
+}
+
+extern void perf_swcounter_event(u32, u64, int, struct pt_regs *, u64);
+
+extern void __perf_counter_mmap(struct vm_area_struct *vma);
+
+static inline void perf_counter_mmap(struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_EXEC)
+		__perf_counter_mmap(vma);
+}
+
+extern void perf_counter_comm(struct task_struct *tsk);
+extern void perf_counter_fork(struct task_struct *tsk);
+
+extern void perf_counter_task_migration(struct task_struct *task, int cpu);
+
+#define MAX_STACK_DEPTH			255
+
+struct perf_callchain_entry {
+	u16				nr;
+	u16				hv;
+	u16				kernel;
+	u16				user;
+	u64				ip[MAX_STACK_DEPTH];
+};
+
+extern struct perf_callchain_entry *perf_callchain(struct pt_regs *regs);
+
+extern int sysctl_perf_counter_paranoid;
+extern int sysctl_perf_counter_mlock;
+extern int sysctl_perf_counter_sample_rate;
+
+extern void perf_counter_init(void);
+
+#ifndef perf_misc_flags
+#define perf_misc_flags(regs)	(user_mode(regs) ? PERF_EVENT_MISC_USER : \
+				 PERF_EVENT_MISC_KERNEL)
+#define perf_instruction_pointer(regs)	instruction_pointer(regs)
+#endif
+
+#else
+static inline void
+perf_counter_task_sched_in(struct task_struct *task, int cpu)		{ }
+static inline void
+perf_counter_task_sched_out(struct task_struct *task,
+			    struct task_struct *next, int cpu)		{ }
+static inline void
+perf_counter_task_tick(struct task_struct *task, int cpu)		{ }
+static inline int perf_counter_init_task(struct task_struct *child)	{ return 0; }
+static inline void perf_counter_exit_task(struct task_struct *child)	{ }
+static inline void perf_counter_free_task(struct task_struct *task)	{ }
+static inline void perf_counter_do_pending(void)			{ }
+static inline void perf_counter_print_debug(void)			{ }
+static inline void perf_disable(void)					{ }
+static inline void perf_enable(void)					{ }
+static inline int perf_counter_task_disable(void)	{ return -EINVAL; }
+static inline int perf_counter_task_enable(void)	{ return -EINVAL; }
+
+static inline void
+perf_swcounter_event(u32 event, u64 nr, int nmi,
+		     struct pt_regs *regs, u64 addr)			{ }
+
+static inline void perf_counter_mmap(struct vm_area_struct *vma)	{ }
+static inline void perf_counter_comm(struct task_struct *tsk)		{ }
+static inline void perf_counter_fork(struct task_struct *tsk)		{ }
+static inline void perf_counter_init(void)				{ }
+static inline void perf_counter_task_migration(struct task_struct *task,
+					       int cpu)			{ }
+#endif
+
+#endif /* __KERNEL__ */
+#endif /* _LINUX_PERF_COUNTER_H */
diff --git a/include/linux/prctl.h b/include/linux/prctl.h
index 48d887e3c6e..b00df4c79c6 100644
--- a/include/linux/prctl.h
+++ b/include/linux/prctl.h
@@ -85,4 +85,7 @@
 #define PR_SET_TIMERSLACK 29
 #define PR_GET_TIMERSLACK 30
 
+#define PR_TASK_PERF_COUNTERS_DISABLE		31
+#define PR_TASK_PERF_COUNTERS_ENABLE		32
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 42bf2766111..4896fdfec91 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -99,6 +99,7 @@ struct robust_list_head;
 struct bio;
 struct fs_struct;
 struct bts_context;
+struct perf_counter_context;
 
 /*
  * List of flags we want to share for kernel threads,
@@ -139,6 +140,7 @@ extern unsigned long nr_running(void);
 extern unsigned long nr_uninterruptible(void);
 extern unsigned long nr_iowait(void);
 extern void calc_global_load(void);
+extern u64 cpu_nr_migrations(int cpu);
 
 extern unsigned long get_parent_ip(unsigned long addr);
 
@@ -674,6 +676,10 @@ struct user_struct {
 	struct work_struct work;
 #endif
 #endif
+
+#ifdef CONFIG_PERF_COUNTERS
+	atomic_long_t locked_vm;
+#endif
 };
 
 extern int uids_sysfs_init(void);
@@ -1073,9 +1079,10 @@ struct sched_entity {
 	u64			last_wakeup;
 	u64			avg_overlap;
 
+	u64			nr_migrations;
+
 	u64			start_runtime;
 	u64			avg_wakeup;
-	u64			nr_migrations;
 
 #ifdef CONFIG_SCHEDSTATS
 	u64			wait_start;
@@ -1396,6 +1403,11 @@ struct task_struct {
 	struct list_head pi_state_list;
 	struct futex_pi_state *pi_state_cache;
 #endif
+#ifdef CONFIG_PERF_COUNTERS
+	struct perf_counter_context *perf_counter_ctxp;
+	struct mutex perf_counter_mutex;
+	struct list_head perf_counter_list;
+#endif
 #ifdef CONFIG_NUMA
 	struct mempolicy *mempolicy;
 	short il_next;
@@ -2410,6 +2422,13 @@ static inline void inc_syscw(struct task_struct *tsk)
 #define TASK_SIZE_OF(tsk)	TASK_SIZE
 #endif
 
+/*
+ * Call the function if the target task is executing on a CPU right now:
+ */
+extern void task_oncpu_function_call(struct task_struct *p,
+				     void (*func) (void *info), void *info);
+
+
 #ifdef CONFIG_MM_OWNER
 extern void mm_update_next_owner(struct mm_struct *mm);
 extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 30520844b8d..c6c84ad8bd7 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -55,6 +55,7 @@ struct compat_timeval;
 struct robust_list_head;
 struct getcpu_cache;
 struct old_linux_dirent;
+struct perf_counter_attr;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -755,4 +756,8 @@ asmlinkage long sys_pipe(int __user *);
 
 int kernel_execve(const char *filename, char *const argv[], char *const envp[]);
 
+
+asmlinkage long sys_perf_counter_open(
+		const struct perf_counter_attr __user *attr_uptr,
+		pid_t pid, int cpu, int group_fd, unsigned long flags);
 #endif