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: (107 commits)
  perf stat: Add more cache-miss percentage printouts
  perf stat: Add -d -d and -d -d -d options to show more CPU events
  ftrace/kbuild: Add recordmcount files to force full build
  ftrace: Add self-tests for multiple function trace users
  ftrace: Modify ftrace_set_filter/notrace to take ops
  ftrace: Allow dynamically allocated function tracers
  ftrace: Implement separate user function filtering
  ftrace: Free hash with call_rcu_sched()
  ftrace: Have global_ops store the functions that are to be traced
  ftrace: Add ops parameter to ftrace_startup/shutdown functions
  ftrace: Add enabled_functions file
  ftrace: Use counters to enable functions to trace
  ftrace: Separate hash allocation and assignment
  ftrace: Create a global_ops to hold the filter and notrace hashes
  ftrace: Use hash instead for FTRACE_FL_FILTER
  ftrace: Replace FTRACE_FL_NOTRACE flag with a hash of ignored functions
  perf bench, x86: Add alternatives-asm.h wrapper
  x86, 64-bit: Fix copy_[to/from]_user() checks for the userspace address limit
  x86, mem: memset_64.S: Optimize memset by enhanced REP MOVSB/STOSB
  x86, mem: memmove_64.S: Optimize memmove by enhanced REP MOVSB/STOSB
  ...

8 files changed, 157 insertions, 171 deletions

diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h
index 0c9653f..e747ecd 100644
--- a/include/linux/dynamic_debug.h
+++ b/include/linux/dynamic_debug.h
@@ -1,8 +1,6 @@
 #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.
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index ca29e03..9d88e1c 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -29,9 +29,22 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
 typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip);
 
+struct ftrace_hash;
+
+enum {
+	FTRACE_OPS_FL_ENABLED		= 1 << 0,
+	FTRACE_OPS_FL_GLOBAL		= 1 << 1,
+	FTRACE_OPS_FL_DYNAMIC		= 1 << 2,
+};
+
 struct ftrace_ops {
-	ftrace_func_t	  func;
-	struct ftrace_ops *next;
+	ftrace_func_t			func;
+	struct ftrace_ops		*next;
+	unsigned long			flags;
+#ifdef CONFIG_DYNAMIC_FTRACE
+	struct ftrace_hash		*notrace_hash;
+	struct ftrace_hash		*filter_hash;
+#endif
 };
 
 extern int function_trace_stop;
@@ -146,14 +159,13 @@ extern void unregister_ftrace_function_probe_all(char *glob);
 extern int ftrace_text_reserved(void *start, void *end);
 
 enum {
-	FTRACE_FL_FREE		= (1 << 0),
-	FTRACE_FL_FAILED	= (1 << 1),
-	FTRACE_FL_FILTER	= (1 << 2),
-	FTRACE_FL_ENABLED	= (1 << 3),
-	FTRACE_FL_NOTRACE	= (1 << 4),
-	FTRACE_FL_CONVERTED	= (1 << 5),
+	FTRACE_FL_ENABLED	= (1 << 30),
+	FTRACE_FL_FREE		= (1 << 31),
 };
 
+#define FTRACE_FL_MASK		(0x3UL << 30)
+#define FTRACE_REF_MAX		((1 << 30) - 1)
+
 struct dyn_ftrace {
 	union {
 		unsigned long		ip; /* address of mcount call-site */
@@ -167,7 +179,12 @@ struct dyn_ftrace {
 };
 
 int ftrace_force_update(void);
-void ftrace_set_filter(unsigned char *buf, int len, int reset);
+void ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
+		       int len, int reset);
+void ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
+			int len, int reset);
+void ftrace_set_global_filter(unsigned char *buf, int len, int reset);
+void ftrace_set_global_notrace(unsigned char *buf, int len, int reset);
 
 int register_ftrace_command(struct ftrace_func_command *cmd);
 int unregister_ftrace_command(struct ftrace_func_command *cmd);
diff --git a/include/linux/init.h b/include/linux/init.h
index 577671c..9146f39 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -79,29 +79,29 @@
 #define __exitused  __used
 #endif
 
-#define __exit          __section(.exit.text) __exitused __cold
+#define __exit          __section(.exit.text) __exitused __cold notrace
 
 /* Used for HOTPLUG */
-#define __devinit        __section(.devinit.text) __cold
+#define __devinit        __section(.devinit.text) __cold notrace
 #define __devinitdata    __section(.devinit.data)
 #define __devinitconst   __section(.devinit.rodata)
-#define __devexit        __section(.devexit.text) __exitused __cold
+#define __devexit        __section(.devexit.text) __exitused __cold notrace
 #define __devexitdata    __section(.devexit.data)
 #define __devexitconst   __section(.devexit.rodata)
 
 /* Used for HOTPLUG_CPU */
-#define __cpuinit        __section(.cpuinit.text) __cold
+#define __cpuinit        __section(.cpuinit.text) __cold notrace
 #define __cpuinitdata    __section(.cpuinit.data)
 #define __cpuinitconst   __section(.cpuinit.rodata)
-#define __cpuexit        __section(.cpuexit.text) __exitused __cold
+#define __cpuexit        __section(.cpuexit.text) __exitused __cold notrace
 #define __cpuexitdata    __section(.cpuexit.data)
 #define __cpuexitconst   __section(.cpuexit.rodata)
 
 /* Used for MEMORY_HOTPLUG */
-#define __meminit        __section(.meminit.text) __cold
+#define __meminit        __section(.meminit.text) __cold notrace
 #define __meminitdata    __section(.meminit.data)
 #define __meminitconst   __section(.meminit.rodata)
-#define __memexit        __section(.memexit.text) __exitused __cold
+#define __memexit        __section(.memexit.text) __exitused __cold notrace
 #define __memexitdata    __section(.memexit.data)
 #define __memexitconst   __section(.memexit.rodata)
 
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 7880f18..83e745f 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -1,20 +1,43 @@
 #ifndef _LINUX_JUMP_LABEL_H
 #define _LINUX_JUMP_LABEL_H
 
+#include <linux/types.h>
+#include <linux/compiler.h>
+
 #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL)
+
+struct jump_label_key {
+	atomic_t enabled;
+	struct jump_entry *entries;
+#ifdef CONFIG_MODULES
+	struct jump_label_mod *next;
+#endif
+};
+
 # include <asm/jump_label.h>
 # define HAVE_JUMP_LABEL
 #endif
 
 enum jump_label_type {
+	JUMP_LABEL_DISABLE = 0,
 	JUMP_LABEL_ENABLE,
-	JUMP_LABEL_DISABLE
 };
 
 struct module;
 
 #ifdef HAVE_JUMP_LABEL
 
+#ifdef CONFIG_MODULES
+#define JUMP_LABEL_INIT {{ 0 }, NULL, NULL}
+#else
+#define JUMP_LABEL_INIT {{ 0 }, NULL}
+#endif
+
+static __always_inline bool static_branch(struct jump_label_key *key)
+{
+	return arch_static_branch(key);
+}
+
 extern struct jump_entry __start___jump_table[];
 extern struct jump_entry __stop___jump_table[];
 
@@ -23,37 +46,37 @@ extern void jump_label_unlock(void);
 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);
+extern void jump_label_inc(struct jump_label_key *key);
+extern void jump_label_dec(struct jump_label_key *key);
+extern bool jump_label_enabled(struct jump_label_key *key);
+extern void jump_label_apply_nops(struct module *mod);
 
-#define jump_label_enable(key) \
-	jump_label_update((unsigned long)key, JUMP_LABEL_ENABLE);
+#else
 
-#define jump_label_disable(key) \
-	jump_label_update((unsigned long)key, JUMP_LABEL_DISABLE);
+#include <asm/atomic.h>
 
-#else
+#define JUMP_LABEL_INIT {ATOMIC_INIT(0)}
 
-#define JUMP_LABEL(key, label)			\
-do {						\
-	if (unlikely(*key))			\
-		goto label;			\
-} while (0)
+struct jump_label_key {
+	atomic_t enabled;
+};
 
-#define jump_label_enable(cond_var)	\
-do {					\
-       *(cond_var) = 1;			\
-} while (0)
+static __always_inline bool static_branch(struct jump_label_key *key)
+{
+	if (unlikely(atomic_read(&key->enabled)))
+		return true;
+	return false;
+}
 
-#define jump_label_disable(cond_var)	\
-do {					\
-       *(cond_var) = 0;			\
-} while (0)
+static inline void jump_label_inc(struct jump_label_key *key)
+{
+	atomic_inc(&key->enabled);
+}
 
-static inline int jump_label_apply_nops(struct module *mod)
+static inline void jump_label_dec(struct jump_label_key *key)
 {
-	return 0;
+	atomic_dec(&key->enabled);
 }
 
 static inline int jump_label_text_reserved(void *start, void *end)
@@ -64,16 +87,16 @@ static inline int jump_label_text_reserved(void *start, void *end)
 static inline void jump_label_lock(void) {}
 static inline void jump_label_unlock(void) {}
 
-#endif
+static inline bool jump_label_enabled(struct jump_label_key *key)
+{
+	return !!atomic_read(&key->enabled);
+}
 
-#define COND_STMT(key, stmt)					\
-do {								\
-	__label__ jl_enabled;					\
-	JUMP_LABEL(key, jl_enabled);				\
-	if (0) {						\
-jl_enabled:							\
-		stmt;						\
-	}							\
-} while (0)
+static inline int jump_label_apply_nops(struct module *mod)
+{
+	return 0;
+}
+
+#endif
 
 #endif
diff --git a/include/linux/jump_label_ref.h b/include/linux/jump_label_ref.h
deleted file mode 100644
index e5d012a..0000000
--- a/include/linux/jump_label_ref.h
+++ /dev/null
@@ -1,44 +0,0 @@
-#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/kernel.h b/include/linux/kernel.h
index 00cec4d..f37ba71 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -283,6 +283,7 @@ extern char *get_options(const char *str, int nints, int *ints);
 extern unsigned long long memparse(const char *ptr, char **retptr);
 
 extern int core_kernel_text(unsigned long addr);
+extern int core_kernel_data(unsigned long addr);
 extern int __kernel_text_address(unsigned long addr);
 extern int kernel_text_address(unsigned long addr);
 extern int func_ptr_is_kernel_text(void *ptr);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index ee9f1e7..3412684 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -2,8 +2,8 @@
  * 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
+ *    Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar
+ *    Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra
  *
  * Data type definitions, declarations, prototypes.
  *
@@ -52,6 +52,8 @@ enum perf_hw_id {
 	PERF_COUNT_HW_BRANCH_INSTRUCTIONS	= 4,
 	PERF_COUNT_HW_BRANCH_MISSES		= 5,
 	PERF_COUNT_HW_BUS_CYCLES		= 6,
+	PERF_COUNT_HW_STALLED_CYCLES_FRONTEND	= 7,
+	PERF_COUNT_HW_STALLED_CYCLES_BACKEND	= 8,
 
 	PERF_COUNT_HW_MAX,			/* non-ABI */
 };
@@ -468,9 +470,9 @@ enum perf_callchain_context {
 	PERF_CONTEXT_MAX		= (__u64)-4095,
 };
 
-#define PERF_FLAG_FD_NO_GROUP	(1U << 0)
-#define PERF_FLAG_FD_OUTPUT	(1U << 1)
-#define PERF_FLAG_PID_CGROUP	(1U << 2) /* pid=cgroup id, per-cpu mode only */
+#define PERF_FLAG_FD_NO_GROUP		(1U << 0)
+#define PERF_FLAG_FD_OUTPUT		(1U << 1)
+#define PERF_FLAG_PID_CGROUP		(1U << 2) /* pid=cgroup id, per-cpu mode only */
 
 #ifdef __KERNEL__
 /*
@@ -484,9 +486,9 @@ enum perf_callchain_context {
 #endif
 
 struct perf_guest_info_callbacks {
-	int (*is_in_guest) (void);
-	int (*is_user_mode) (void);
-	unsigned long (*get_guest_ip) (void);
+	int				(*is_in_guest)(void);
+	int				(*is_user_mode)(void);
+	unsigned long			(*get_guest_ip)(void);
 };
 
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
@@ -505,7 +507,7 @@ struct perf_guest_info_callbacks {
 #include <linux/ftrace.h>
 #include <linux/cpu.h>
 #include <linux/irq_work.h>
-#include <linux/jump_label_ref.h>
+#include <linux/jump_label.h>
 #include <asm/atomic.h>
 #include <asm/local.h>
 
@@ -652,19 +654,19 @@ struct pmu {
 	 * Start the transaction, after this ->add() doesn't need to
 	 * do schedulability tests.
 	 */
-	void (*start_txn)	(struct pmu *pmu); /* optional */
+	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 */
+	int  (*commit_txn)		(struct pmu *pmu); /* optional */
 	/*
 	 * Will cancel the transaction, assumes ->del() is called
 	 * for each successful ->add() during the transaction.
 	 */
-	void (*cancel_txn)	(struct pmu *pmu); /* optional */
+	void (*cancel_txn)		(struct pmu *pmu); /* optional */
 };
 
 /**
@@ -712,15 +714,15 @@ typedef void (*perf_overflow_handler_t)(struct perf_event *, int,
 					struct pt_regs *regs);
 
 enum perf_group_flag {
-	PERF_GROUP_SOFTWARE = 0x1,
+	PERF_GROUP_SOFTWARE		= 0x1,
 };
 
-#define SWEVENT_HLIST_BITS	8
-#define SWEVENT_HLIST_SIZE	(1 << SWEVENT_HLIST_BITS)
+#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;
+	struct hlist_head		heads[SWEVENT_HLIST_SIZE];
+	struct rcu_head			rcu_head;
 };
 
 #define PERF_ATTACH_CONTEXT	0x01
@@ -733,13 +735,13 @@ struct swevent_hlist {
  * This is a per-cpu dynamically allocated data structure.
  */
 struct perf_cgroup_info {
-	u64 time;
-	u64 timestamp;
+	u64				time;
+	u64				timestamp;
 };
 
 struct perf_cgroup {
-	struct cgroup_subsys_state css;
-	struct perf_cgroup_info *info;	/* timing info, one per cpu */
+	struct				cgroup_subsys_state css;
+	struct				perf_cgroup_info *info;	/* timing info, one per cpu */
 };
 #endif
 
@@ -923,7 +925,7 @@ struct perf_event_context {
 
 /*
  * Number of contexts where an event can trigger:
- * 	task, softirq, hardirq, nmi.
+ *	task, softirq, hardirq, nmi.
  */
 #define PERF_NR_CONTEXTS	4
 
@@ -1001,8 +1003,7 @@ struct perf_sample_data {
 	struct perf_raw_record		*raw;
 };
 
-static inline
-void perf_sample_data_init(struct perf_sample_data *data, u64 addr)
+static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr)
 {
 	data->addr = addr;
 	data->raw  = NULL;
@@ -1034,13 +1035,12 @@ 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 struct jump_label_key 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) { }
+static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { }
 #endif
 
 /*
@@ -1063,26 +1063,24 @@ 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;
+	if (static_branch(&perf_swevent_enabled[event_id])) {
+		if (!regs) {
+			perf_fetch_caller_regs(&hot_regs);
+			regs = &hot_regs;
+		}
+		__perf_sw_event(event_id, nr, nmi, regs, addr);
 	}
-	__perf_sw_event(event_id, nr, nmi, regs, addr);
 }
 
-extern atomic_t perf_sched_events;
+extern struct jump_label_key perf_sched_events;
 
 static inline void perf_event_task_sched_in(struct task_struct *task)
 {
-	COND_STMT(&perf_sched_events, __perf_event_task_sched_in(task));
+	if (static_branch(&perf_sched_events))
+		__perf_event_task_sched_in(task);
 }
 
-static inline
-void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next)
+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);
 
@@ -1100,14 +1098,10 @@ 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);
-
+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)
+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;
@@ -1143,9 +1137,9 @@ extern void perf_tp_event(u64 addr, u64 count, void *record,
 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)
+# 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,
@@ -1180,9 +1174,9 @@ 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; }
+(struct perf_guest_info_callbacks *callbacks)				{ return 0; }
 static inline int perf_unregister_guest_info_callbacks
-(struct perf_guest_info_callbacks *callbacks) { return 0; }
+(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)		{ }
@@ -1195,23 +1189,22 @@ 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))
+#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);			\
+#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__ */
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 97c84a5..d530a44 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -29,7 +29,7 @@ struct tracepoint_func {
 
 struct tracepoint {
 	const char *name;		/* Tracepoint name */
-	int state;			/* State. */
+	struct jump_label_key key;
 	void (*regfunc)(void);
 	void (*unregfunc)(void);
 	struct tracepoint_func __rcu *funcs;
@@ -146,9 +146,7 @@ void tracepoint_update_probe_range(struct tracepoint * const *begin,
 	extern struct tracepoint __tracepoint_##name;			\
 	static inline void trace_##name(proto)				\
 	{								\
-		JUMP_LABEL(&__tracepoint_##name.state, do_trace);	\
-		return;							\
-do_trace:								\
+		if (static_branch(&__tracepoint_##name.key))		\
 			__DO_TRACE(&__tracepoint_##name,		\
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
@@ -176,14 +174,14 @@ do_trace:								\
  * structures, so we create an array of pointers that will be used for iteration
  * on the tracepoints.
  */
-#define DEFINE_TRACE_FN(name, reg, unreg)				\
-	static const char __tpstrtab_##name[]				\
-	__attribute__((section("__tracepoints_strings"))) = #name;	\
-	struct tracepoint __tracepoint_##name				\
-	__attribute__((section("__tracepoints"))) =			\
-		{ __tpstrtab_##name, 0, reg, unreg, NULL };		\
-	static struct tracepoint * const __tracepoint_ptr_##name __used	\
-	__attribute__((section("__tracepoints_ptrs"))) =		\
+#define DEFINE_TRACE_FN(name, reg, unreg)				 \
+	static const char __tpstrtab_##name[]				 \
+	__attribute__((section("__tracepoints_strings"))) = #name;	 \
+	struct tracepoint __tracepoint_##name				 \
+	__attribute__((section("__tracepoints"))) =			 \
+		{ __tpstrtab_##name, JUMP_LABEL_INIT, reg, unreg, NULL };\
+	static struct tracepoint * const __tracepoint_ptr_##name __used	 \
+	__attribute__((section("__tracepoints_ptrs"))) =		 \
 		&__tracepoint_##name;
 
 #define DEFINE_TRACE(name)						\