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

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (163 commits)
  tracing: Fix compile issue for trace_sched_wakeup.c
  [S390] hardirq: remove pointless header file includes
  [IA64] Move local_softirq_pending() definition
  perf, powerpc: Fix power_pmu_event_init to not use event->ctx
  ftrace: Remove recursion between recordmcount and scripts/mod/empty
  jump_label: Add COND_STMT(), reducer wrappery
  perf: Optimize sw events
  perf: Use jump_labels to optimize the scheduler hooks
  jump_label: Add atomic_t interface
  jump_label: Use more consistent naming
  perf, hw_breakpoint: Fix crash in hw_breakpoint creation
  perf: Find task before event alloc
  perf: Fix task refcount bugs
  perf: Fix group moving
  irq_work: Add generic hardirq context callbacks
  perf_events: Fix transaction recovery in group_sched_in()
  perf_events: Fix bogus AMD64 generic TLB events
  perf_events: Fix bogus context time tracking
  tracing: Remove parent recording in latency tracer graph options
  tracing: Use one prologue for the preempt irqs off tracer function tracers
  ...

13 files changed, 348 insertions, 102 deletions

diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h
index 52c0da4bdd1..bef3cda44c4 100644
--- a/include/linux/dynamic_debug.h
+++ b/include/linux/dynamic_debug.h
@@ -1,6 +1,8 @@
 #ifndef _DYNAMIC_DEBUG_H
 #define _DYNAMIC_DEBUG_H
 
+#include <linux/jump_label.h>
+
 /* dynamic_printk_enabled, and dynamic_printk_enabled2 are bitmasks in which
  * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They
  * use independent hash functions, to reduce the chance of false positives.
@@ -22,8 +24,6 @@ struct _ddebug {
 	const char *function;
 	const char *filename;
 	const char *format;
-	char primary_hash;
-	char secondary_hash;
 	unsigned int lineno:24;
 	/*
  	 * The flags field controls the behaviour at the callsite.
@@ -33,6 +33,7 @@ struct _ddebug {
 #define _DPRINTK_FLAGS_PRINT   (1<<0)  /* printk() a message using the format */
 #define _DPRINTK_FLAGS_DEFAULT 0
 	unsigned int flags:8;
+	char enabled;
 } __attribute__((aligned(8)));
 
 
@@ -42,33 +43,35 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n,
 #if defined(CONFIG_DYNAMIC_DEBUG)
 extern int ddebug_remove_module(const char *mod_name);
 
-#define __dynamic_dbg_enabled(dd)  ({	     \
-	int __ret = 0;							     \
-	if (unlikely((dynamic_debug_enabled & (1LL << DEBUG_HASH)) &&	     \
-			(dynamic_debug_enabled2 & (1LL << DEBUG_HASH2))))   \
-				if (unlikely(dd.flags))			     \
-					__ret = 1;			     \
-	__ret; })
-
 #define dynamic_pr_debug(fmt, ...) do {					\
+	__label__ do_printk;						\
+	__label__ out;							\
 	static struct _ddebug descriptor				\
 	__used								\
 	__attribute__((section("__verbose"), aligned(8))) =		\
-	{ KBUILD_MODNAME, __func__, __FILE__, fmt, DEBUG_HASH,	\
-		DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT };	\
-	if (__dynamic_dbg_enabled(descriptor))				\
-		printk(KERN_DEBUG pr_fmt(fmt),	##__VA_ARGS__);		\
+	{ KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__,		\
+		_DPRINTK_FLAGS_DEFAULT };				\
+	JUMP_LABEL(&descriptor.enabled, do_printk);			\
+	goto out;							\
+do_printk:								\
+	printk(KERN_DEBUG pr_fmt(fmt),	##__VA_ARGS__);			\
+out:	;								\
 	} while (0)
 
 
 #define dynamic_dev_dbg(dev, fmt, ...) do {				\
+	__label__ do_printk;						\
+	__label__ out;							\
 	static struct _ddebug descriptor				\
 	__used								\
 	__attribute__((section("__verbose"), aligned(8))) =		\
-	{ KBUILD_MODNAME, __func__, __FILE__, fmt, DEBUG_HASH,	\
-		DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT };	\
-	if (__dynamic_dbg_enabled(descriptor))				\
-		dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__);	\
+	{ KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__,		\
+		_DPRINTK_FLAGS_DEFAULT };				\
+	JUMP_LABEL(&descriptor.enabled, do_printk);			\
+	goto out;							\
+do_printk:								\
+	dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__);		\
+out:	;								\
 	} while (0)
 
 #else
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 02b8b24f8f5..8beabb958f6 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -191,8 +191,8 @@ struct ftrace_event_call {
 	unsigned int		flags;
 
 #ifdef CONFIG_PERF_EVENTS
-	int			perf_refcount;
-	struct hlist_head	*perf_events;
+	int				perf_refcount;
+	struct hlist_head __percpu	*perf_events;
 #endif
 };
 
@@ -252,8 +252,8 @@ DECLARE_PER_CPU(struct pt_regs, perf_trace_regs);
 
 extern int  perf_trace_init(struct perf_event *event);
 extern void perf_trace_destroy(struct perf_event *event);
-extern int  perf_trace_enable(struct perf_event *event);
-extern void perf_trace_disable(struct perf_event *event);
+extern int  perf_trace_add(struct perf_event *event, int flags);
+extern void perf_trace_del(struct perf_event *event, int flags);
 extern int  ftrace_profile_set_filter(struct perf_event *event, int event_id,
 				     char *filter_str);
 extern void ftrace_profile_free_filter(struct perf_event *event);
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index a0384a4d1e6..531495db170 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -18,6 +18,7 @@
 #include <asm/atomic.h>
 #include <asm/ptrace.h>
 #include <asm/system.h>
+#include <trace/events/irq.h>
 
 /*
  * These correspond to the IORESOURCE_IRQ_* defines in
@@ -407,7 +408,12 @@ asmlinkage void do_softirq(void);
 asmlinkage void __do_softirq(void);
 extern void open_softirq(int nr, void (*action)(struct softirq_action *));
 extern void softirq_init(void);
-#define __raise_softirq_irqoff(nr) do { or_softirq_pending(1UL << (nr)); } while (0)
+static inline void __raise_softirq_irqoff(unsigned int nr)
+{
+	trace_softirq_raise((struct softirq_action *)(unsigned long)nr, NULL);
+	or_softirq_pending(1UL << nr);
+}
+
 extern void raise_softirq_irqoff(unsigned int nr);
 extern void raise_softirq(unsigned int nr);
 extern void wakeup_softirqd(void);
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
new file mode 100644
index 00000000000..4fa09d4d0b7
--- /dev/null
+++ b/include/linux/irq_work.h
@@ -0,0 +1,20 @@
+#ifndef _LINUX_IRQ_WORK_H
+#define _LINUX_IRQ_WORK_H
+
+struct irq_work {
+	struct irq_work *next;
+	void (*func)(struct irq_work *);
+};
+
+static inline
+void init_irq_work(struct irq_work *entry, void (*func)(struct irq_work *))
+{
+	entry->next = NULL;
+	entry->func = func;
+}
+
+bool irq_work_queue(struct irq_work *entry);
+void irq_work_run(void);
+void irq_work_sync(struct irq_work *entry);
+
+#endif /* _LINUX_IRQ_WORK_H */
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
new file mode 100644
index 00000000000..b67cb180e6e
--- /dev/null
+++ b/include/linux/jump_label.h
@@ -0,0 +1,74 @@
+#ifndef _LINUX_JUMP_LABEL_H
+#define _LINUX_JUMP_LABEL_H
+
+#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_HAVE_ARCH_JUMP_LABEL)
+# include <asm/jump_label.h>
+# define HAVE_JUMP_LABEL
+#endif
+
+enum jump_label_type {
+	JUMP_LABEL_ENABLE,
+	JUMP_LABEL_DISABLE
+};
+
+struct module;
+
+#ifdef HAVE_JUMP_LABEL
+
+extern struct jump_entry __start___jump_table[];
+extern struct jump_entry __stop___jump_table[];
+
+extern void arch_jump_label_transform(struct jump_entry *entry,
+				 enum jump_label_type type);
+extern void arch_jump_label_text_poke_early(jump_label_t addr);
+extern void jump_label_update(unsigned long key, enum jump_label_type type);
+extern void jump_label_apply_nops(struct module *mod);
+extern int jump_label_text_reserved(void *start, void *end);
+
+#define jump_label_enable(key) \
+	jump_label_update((unsigned long)key, JUMP_LABEL_ENABLE);
+
+#define jump_label_disable(key) \
+	jump_label_update((unsigned long)key, JUMP_LABEL_DISABLE);
+
+#else
+
+#define JUMP_LABEL(key, label)			\
+do {						\
+	if (unlikely(*key))			\
+		goto label;			\
+} while (0)
+
+#define jump_label_enable(cond_var)	\
+do {					\
+       *(cond_var) = 1;			\
+} while (0)
+
+#define jump_label_disable(cond_var)	\
+do {					\
+       *(cond_var) = 0;			\
+} while (0)
+
+static inline int jump_label_apply_nops(struct module *mod)
+{
+	return 0;
+}
+
+static inline int jump_label_text_reserved(void *start, void *end)
+{
+	return 0;
+}
+
+#endif
+
+#define COND_STMT(key, stmt)					\
+do {								\
+	__label__ jl_enabled;					\
+	JUMP_LABEL(key, jl_enabled);				\
+	if (0) {						\
+jl_enabled:							\
+		stmt;						\
+	}							\
+} while (0)
+
+#endif
diff --git a/include/linux/jump_label_ref.h b/include/linux/jump_label_ref.h
new file mode 100644
index 00000000000..e5d012ad92c
--- /dev/null
+++ b/include/linux/jump_label_ref.h
@@ -0,0 +1,44 @@
+#ifndef _LINUX_JUMP_LABEL_REF_H
+#define _LINUX_JUMP_LABEL_REF_H
+
+#include <linux/jump_label.h>
+#include <asm/atomic.h>
+
+#ifdef HAVE_JUMP_LABEL
+
+static inline void jump_label_inc(atomic_t *key)
+{
+	if (atomic_add_return(1, key) == 1)
+		jump_label_enable(key);
+}
+
+static inline void jump_label_dec(atomic_t *key)
+{
+	if (atomic_dec_and_test(key))
+		jump_label_disable(key);
+}
+
+#else /* !HAVE_JUMP_LABEL */
+
+static inline void jump_label_inc(atomic_t *key)
+{
+	atomic_inc(key);
+}
+
+static inline void jump_label_dec(atomic_t *key)
+{
+	atomic_dec(key);
+}
+
+#undef JUMP_LABEL
+#define JUMP_LABEL(key, label)						\
+do {									\
+	if (unlikely(__builtin_choose_expr(				\
+	      __builtin_types_compatible_p(typeof(key), atomic_t *),	\
+	      atomic_read((atomic_t *)(key)), *(key))))			\
+		goto label;						\
+} while (0)
+
+#endif /* HAVE_JUMP_LABEL */
+
+#endif /* _LINUX_JUMP_LABEL_REF_H */
diff --git a/include/linux/module.h b/include/linux/module.h
index aace066bad8..b29e7458b96 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -350,7 +350,10 @@ struct module
 	struct tracepoint *tracepoints;
 	unsigned int num_tracepoints;
 #endif
-
+#ifdef HAVE_JUMP_LABEL
+	struct jump_entry *jump_entries;
+	unsigned int num_jump_entries;
+#endif
 #ifdef CONFIG_TRACING
 	const char **trace_bprintk_fmt_start;
 	unsigned int num_trace_bprintk_fmt;
diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h
index 5171639ecf0..32fb81212fd 100644
--- a/include/linux/oprofile.h
+++ b/include/linux/oprofile.h
@@ -15,6 +15,7 @@
 
 #include <linux/types.h>
 #include <linux/spinlock.h>
+#include <linux/init.h>
 #include <asm/atomic.h>
  
 /* Each escaped entry is prefixed by ESCAPE_CODE
@@ -185,4 +186,10 @@ int oprofile_add_data(struct op_entry *entry, unsigned long val);
 int oprofile_add_data64(struct op_entry *entry, u64 val);
 int oprofile_write_commit(struct op_entry *entry);
 
+#ifdef CONFIG_PERF_EVENTS
+int __init oprofile_perf_init(struct oprofile_operations *ops);
+void oprofile_perf_exit(void);
+char *op_name_from_perf_id(void);
+#endif /* CONFIG_PERF_EVENTS */
+
 #endif /* OPROFILE_H */
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 49466b13c5c..0eb50832aa0 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -39,6 +39,15 @@
 	preempt_enable();				\
 } while (0)
 
+#define get_cpu_ptr(var) ({				\
+	preempt_disable();				\
+	this_cpu_ptr(var); })
+
+#define put_cpu_ptr(var) do {				\
+	(void)(var);					\
+	preempt_enable();				\
+} while (0)
+
 #ifdef CONFIG_SMP
 
 /* minimum unit size, also is the maximum supported allocation size */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 716f99b682c..057bf22a832 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -486,6 +486,8 @@ struct perf_guest_info_callbacks {
 #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>
 
@@ -529,16 +531,22 @@ struct hw_perf_event {
 			int		last_cpu;
 		};
 		struct { /* software */
-			s64		remaining;
 			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;
@@ -550,6 +558,13 @@ struct hw_perf_event {
 #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;
 
 /*
@@ -561,36 +576,70 @@ struct perf_event;
  * struct pmu - generic performance monitoring unit
  */
 struct pmu {
-	int (*enable)			(struct perf_event *event);
-	void (*disable)			(struct perf_event *event);
-	int (*start)			(struct perf_event *event);
-	void (*stop)			(struct perf_event *event);
-	void (*read)			(struct perf_event *event);
-	void (*unthrottle)		(struct perf_event *event);
+	struct list_head		entry;
+
+	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 */
 
 	/*
-	 * 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
+	 * 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 */
 
 	/*
-	 * Start the transaction, after this ->enable() doesn't need
-	 * to do schedulability tests.
+	 * Adds/Removes a counter to/from the PMU, can be done inside
+	 * a transaction, see the ->*_txn() methods.
 	 */
-	void (*start_txn)	(const struct pmu *pmu);
+	int  (*add)			(struct perf_event *event, int flags);
+	void (*del)			(struct perf_event *event, int flags);
+
 	/*
-	 * If ->start_txn() disabled the ->enable() schedulability test
+	 * 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)	(const struct pmu *pmu);
+	int  (*commit_txn)	(struct pmu *pmu); /* optional */
 	/*
-	 * Will cancel the transaction, assumes ->disable() is called for
-	 * each successfull ->enable() during the transaction.
+	 * Will cancel the transaction, assumes ->del() is called
+	 * for each successfull ->add() during the transaction.
 	 */
-	void (*cancel_txn)	(const struct pmu *pmu);
+	void (*cancel_txn)	(struct pmu *pmu); /* optional */
 };
 
 /**
@@ -631,11 +680,6 @@ struct perf_buffer {
 	void				*data_pages[0];
 };
 
-struct perf_pending_entry {
-	struct perf_pending_entry *next;
-	void (*func)(struct perf_pending_entry *);
-};
-
 struct perf_sample_data;
 
 typedef void (*perf_overflow_handler_t)(struct perf_event *, int,
@@ -656,6 +700,7 @@ struct swevent_hlist {
 
 #define PERF_ATTACH_CONTEXT	0x01
 #define PERF_ATTACH_GROUP	0x02
+#define PERF_ATTACH_TASK	0x04
 
 /**
  * struct perf_event - performance event kernel representation:
@@ -669,7 +714,7 @@ struct perf_event {
 	int				nr_siblings;
 	int				group_flags;
 	struct perf_event		*group_leader;
-	const struct pmu		*pmu;
+	struct pmu			*pmu;
 
 	enum perf_event_active_state	state;
 	unsigned int			attach_state;
@@ -743,7 +788,7 @@ struct perf_event {
 	int				pending_wakeup;
 	int				pending_kill;
 	int				pending_disable;
-	struct perf_pending_entry	pending;
+	struct irq_work			pending;
 
 	atomic_t			event_limit;
 
@@ -763,12 +808,19 @@ struct perf_event {
 #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:
@@ -808,6 +860,12 @@ struct perf_event_context {
 	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
  */
@@ -815,18 +873,9 @@ struct perf_cpu_context {
 	struct perf_event_context	ctx;
 	struct perf_event_context	*task_ctx;
 	int				active_oncpu;
-	int				max_pertask;
 	int				exclusive;
-	struct swevent_hlist		*swevent_hlist;
-	struct mutex			hlist_mutex;
-	int				hlist_refcount;
-
-	/*
-	 * Recursion avoidance:
-	 *
-	 * task, softirq, irq, nmi context
-	 */
-	int				recursion[4];
+	struct list_head		rotation_list;
+	int				jiffies_interval;
 };
 
 struct perf_output_handle {
@@ -842,26 +891,34 @@ struct perf_output_handle {
 
 #ifdef CONFIG_PERF_EVENTS
 
-/*
- * Set by architecture code:
- */
-extern int perf_max_events;
+extern int perf_pmu_register(struct pmu *pmu);
+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 const struct pmu *hw_perf_event_init(struct perf_event *event);
+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)
+{
+	COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next));
+}
 
-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 void perf_event_task_tick(struct task_struct *task);
 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 set_perf_event_pending(void);
-extern void perf_event_do_pending(void);
+extern void perf_event_delayed_put(struct task_struct *task);
 extern void perf_event_print_debug(void);
-extern void __perf_disable(void);
-extern bool __perf_enable(void);
-extern void perf_disable(void);
-extern void perf_enable(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);
@@ -869,7 +926,7 @@ 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,
-				pid_t pid,
+				struct task_struct *task,
 				perf_overflow_handler_t callback);
 extern u64 perf_event_read_value(struct perf_event *event,
 				 u64 *enabled, u64 *running);
@@ -920,14 +977,7 @@ extern int perf_event_overflow(struct perf_event *event, int nmi,
  */
 static inline int is_software_event(struct perf_event *event)
 {
-	switch (event->attr.type) {
-	case PERF_TYPE_SOFTWARE:
-	case PERF_TYPE_TRACEPOINT:
-	/* for now the breakpoint stuff also works as software event */
-	case PERF_TYPE_BREAKPOINT:
-		return 1;
-	}
-	return 0;
+	return event->pmu->task_ctx_nr == perf_sw_context;
 }
 
 extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
@@ -954,18 +1004,20 @@ static inline void perf_fetch_caller_regs(struct pt_regs *regs)
 	perf_arch_fetch_caller_regs(regs, CALLER_ADDR0);
 }
 
-static inline void
+static __always_inline void
 perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
 {
-	if (atomic_read(&perf_swevent_enabled[event_id])) {
-		struct pt_regs hot_regs;
-
-		if (!regs) {
-			perf_fetch_caller_regs(&hot_regs);
-			regs = &hot_regs;
-		}
-		__perf_sw_event(event_id, nr, nmi, regs, 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 void perf_event_mmap(struct vm_area_struct *vma);
@@ -976,7 +1028,21 @@ extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks
 extern void perf_event_comm(struct task_struct *tsk);
 extern void perf_event_fork(struct task_struct *tsk);
 
-extern struct perf_callchain_entry *perf_callchain(struct pt_regs *regs);
+/* 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;
@@ -1019,21 +1085,18 @@ 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 void
-perf_event_task_tick(struct task_struct *task)				{ }
 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_do_pending(void)				{ }
+static inline void perf_event_delayed_put(struct task_struct *task)	{ }
 static inline void perf_event_print_debug(void)				{ }
-static inline void perf_disable(void)					{ }
-static inline void perf_enable(void)					{ }
 static inline int perf_event_task_disable(void)				{ return -EINVAL; }
 static inline int perf_event_task_enable(void)				{ return -EINVAL; }
 
@@ -1056,6 +1119,7 @@ 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) \
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e18473f0eb7..61b4ecf1da5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1160,6 +1160,13 @@ struct sched_rt_entity {
 
 struct rcu_node;
 
+enum perf_event_task_context {
+	perf_invalid_context = -1,
+	perf_hw_context = 0,
+	perf_sw_context,
+	perf_nr_task_contexts,
+};
+
 struct task_struct {
 	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
 	void *stack;
@@ -1433,7 +1440,7 @@ struct task_struct {
 	struct futex_pi_state *pi_state_cache;
 #endif
 #ifdef CONFIG_PERF_EVENTS
-	struct perf_event_context *perf_event_ctxp;
+	struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts];
 	struct mutex perf_event_mutex;
 	struct list_head perf_event_list;
 #endif
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 6b524a0d02e..1808960c505 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -126,8 +126,8 @@ int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus);
 
 #else	 /* CONFIG_STOP_MACHINE && CONFIG_SMP */
 
-static inline int stop_machine(int (*fn)(void *), void *data,
-			       const struct cpumask *cpus)
+static inline int __stop_machine(int (*fn)(void *), void *data,
+				 const struct cpumask *cpus)
 {
 	int ret;
 	local_irq_disable();
@@ -136,5 +136,11 @@ static inline int stop_machine(int (*fn)(void *), void *data,
 	return ret;
 }
 
+static inline int stop_machine(int (*fn)(void *), void *data,
+			       const struct cpumask *cpus)
+{
+	return __stop_machine(fn, data, cpus);
+}
+
 #endif	/* CONFIG_STOP_MACHINE && CONFIG_SMP */
 #endif	/* _LINUX_STOP_MACHINE */
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 103d1b61aac..a4a90b6726c 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/rcupdate.h>
+#include <linux/jump_label.h>
 
 struct module;
 struct tracepoint;
@@ -145,7 +146,9 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
 	extern struct tracepoint __tracepoint_##name;			\
 	static inline void trace_##name(proto)				\
 	{								\
-		if (unlikely(__tracepoint_##name.state))		\
+		JUMP_LABEL(&__tracepoint_##name.state, do_trace);	\
+		return;							\
+do_trace:								\
 			__DO_TRACE(&__tracepoint_##name,		\
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args));			\