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: (61 commits)
  tracing: Add __used annotation to event variable
  perf, trace: Fix !x86 build bug
  perf report: Support multiple events on the TUI
  perf annotate: Fix up usage of the build id cache
  x86/mmiotrace: Remove redundant instruction prefix checks
  perf annotate: Add TUI interface
  perf tui: Remove annotate from popup menu after failure
  perf report: Don't start the TUI if -D is used
  perf: Fix getline undeclared
  perf: Optimize perf_tp_event_match()
  perf: Remove more code from the fastpath
  perf: Optimize the !vmalloc backed buffer
  perf: Optimize perf_output_copy()
  perf: Fix wakeup storm for RO mmap()s
  perf-record: Share per-cpu buffers
  perf-record: Remove -M
  perf: Ensure that IOC_OUTPUT isn't used to create multi-writer buffers
  perf, trace: Optimize tracepoints by using per-tracepoint-per-cpu hlist to track events
  perf, trace: Optimize tracepoints by removing IRQ-disable from perf/tracepoint interaction
  perf tui: Allow disabling the TUI on a per command basis in ~/.perfconfig
  ...

4 files changed, 183 insertions, 103 deletions

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index c082f223e2f..3167f2df412 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -73,18 +73,25 @@ struct trace_iterator {
 };
 
 
+struct trace_event;
+
 typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter,
-					      int flags);
-struct trace_event {
-	struct hlist_node	node;
-	struct list_head	list;
-	int			type;
+				      int flags, struct trace_event *event);
+
+struct trace_event_functions {
 	trace_print_func	trace;
 	trace_print_func	raw;
 	trace_print_func	hex;
 	trace_print_func	binary;
 };
 
+struct trace_event {
+	struct hlist_node		node;
+	struct list_head		list;
+	int				type;
+	struct trace_event_functions	*funcs;
+};
+
 extern int register_ftrace_event(struct trace_event *event);
 extern int unregister_ftrace_event(struct trace_event *event);
 
@@ -116,28 +123,70 @@ void tracing_record_cmdline(struct task_struct *tsk);
 
 struct event_filter;
 
+enum trace_reg {
+	TRACE_REG_REGISTER,
+	TRACE_REG_UNREGISTER,
+	TRACE_REG_PERF_REGISTER,
+	TRACE_REG_PERF_UNREGISTER,
+};
+
+struct ftrace_event_call;
+
+struct ftrace_event_class {
+	char			*system;
+	void			*probe;
+#ifdef CONFIG_PERF_EVENTS
+	void			*perf_probe;
+#endif
+	int			(*reg)(struct ftrace_event_call *event,
+				       enum trace_reg type);
+	int			(*define_fields)(struct ftrace_event_call *);
+	struct list_head	*(*get_fields)(struct ftrace_event_call *);
+	struct list_head	fields;
+	int			(*raw_init)(struct ftrace_event_call *);
+};
+
+enum {
+	TRACE_EVENT_FL_ENABLED_BIT,
+	TRACE_EVENT_FL_FILTERED_BIT,
+};
+
+enum {
+	TRACE_EVENT_FL_ENABLED	= (1 << TRACE_EVENT_FL_ENABLED_BIT),
+	TRACE_EVENT_FL_FILTERED	= (1 << TRACE_EVENT_FL_FILTERED_BIT),
+};
+
 struct ftrace_event_call {
 	struct list_head	list;
+	struct ftrace_event_class *class;
 	char			*name;
-	char			*system;
 	struct dentry		*dir;
-	struct trace_event	*event;
-	int			enabled;
-	int			(*regfunc)(struct ftrace_event_call *);
-	void			(*unregfunc)(struct ftrace_event_call *);
-	int			id;
+	struct trace_event	event;
 	const char		*print_fmt;
-	int			(*raw_init)(struct ftrace_event_call *);
-	int			(*define_fields)(struct ftrace_event_call *);
-	struct list_head	fields;
-	int			filter_active;
 	struct event_filter	*filter;
 	void			*mod;
 	void			*data;
 
+	/*
+	 * 32 bit flags:
+	 *   bit 1:		enabled
+	 *   bit 2:		filter_active
+	 *
+	 * Changes to flags must hold the event_mutex.
+	 *
+	 * Note: Reads of flags do not hold the event_mutex since
+	 * they occur in critical sections. But the way flags
+	 * is currently used, these changes do no affect the code
+	 * except that when a change is made, it may have a slight
+	 * delay in propagating the changes to other CPUs due to
+	 * caching and such.
+	 */
+	unsigned int		flags;
+
+#ifdef CONFIG_PERF_EVENTS
 	int			perf_refcount;
-	int			(*perf_event_enable)(struct ftrace_event_call *);
-	void			(*perf_event_disable)(struct ftrace_event_call *);
+	struct hlist_head	*perf_events;
+#endif
 };
 
 #define PERF_MAX_TRACE_SIZE	2048
@@ -194,24 +243,22 @@ struct perf_event;
 
 DECLARE_PER_CPU(struct pt_regs, perf_trace_regs);
 
-extern int perf_trace_enable(int event_id);
-extern void perf_trace_disable(int event_id);
-extern int ftrace_profile_set_filter(struct perf_event *event, int event_id,
+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  ftrace_profile_set_filter(struct perf_event *event, int event_id,
 				     char *filter_str);
 extern void ftrace_profile_free_filter(struct perf_event *event);
-extern void *
-perf_trace_buf_prepare(int size, unsigned short type, int *rctxp,
-			 unsigned long *irq_flags);
+extern void *perf_trace_buf_prepare(int size, unsigned short type,
+				    struct pt_regs *regs, int *rctxp);
 
 static inline void
 perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr,
-		       u64 count, unsigned long irq_flags, struct pt_regs *regs)
+		       u64 count, struct pt_regs *regs, void *head)
 {
-	struct trace_entry *entry = raw_data;
-
-	perf_tp_event(entry->type, addr, count, raw_data, size, regs);
+	perf_tp_event(addr, count, raw_data, size, regs, head);
 	perf_swevent_put_recursion_context(rctx);
-	local_irq_restore(irq_flags);
 }
 #endif
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 3fd5c82e0e1..fb6c91eac7e 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -485,6 +485,7 @@ struct perf_guest_info_callbacks {
 #include <linux/ftrace.h>
 #include <linux/cpu.h>
 #include <asm/atomic.h>
+#include <asm/local.h>
 
 #define PERF_MAX_STACK_DEPTH		255
 
@@ -587,21 +588,19 @@ struct perf_mmap_data {
 	struct rcu_head			rcu_head;
 #ifdef CONFIG_PERF_USE_VMALLOC
 	struct work_struct		work;
+	int				page_order;	/* allocation order  */
 #endif
-	int				data_order;
 	int				nr_pages;	/* nr of data pages  */
 	int				writable;	/* are we writable   */
 	int				nr_locked;	/* nr pages mlocked  */
 
 	atomic_t			poll;		/* POLL_ for wakeups */
-	atomic_t			events;		/* event_id 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    */
-	atomic_t			lost;		/* nr records lost   */
+	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  */
 
@@ -728,6 +727,7 @@ struct perf_event {
 	perf_overflow_handler_t		overflow_handler;
 
 #ifdef CONFIG_EVENT_TRACING
+	struct ftrace_event_call	*tp_event;
 	struct event_filter		*filter;
 #endif
 
@@ -803,11 +803,12 @@ struct perf_cpu_context {
 struct perf_output_handle {
 	struct perf_event		*event;
 	struct perf_mmap_data		*data;
-	unsigned long			head;
-	unsigned long			offset;
+	unsigned long			wakeup;
+	unsigned long			size;
+	void				*addr;
+	int				page;
 	int				nmi;
 	int				sample;
-	int				locked;
 };
 
 #ifdef CONFIG_PERF_EVENTS
@@ -993,8 +994,9 @@ static inline bool perf_paranoid_kernel(void)
 }
 
 extern void perf_event_init(void);
-extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
-			  int entry_size, struct pt_regs *regs);
+extern void perf_tp_event(u64 addr, u64 count, void *record,
+			  int entry_size, struct pt_regs *regs,
+			  struct hlist_head *head);
 extern void perf_bp_event(struct perf_event *event, void *data);
 
 #ifndef perf_misc_flags
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 057929b0a65..a1a86a53bc7 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -103,22 +103,6 @@ struct perf_event_attr;
 #define __SC_TEST5(t5, a5, ...)	__SC_TEST(t5); __SC_TEST4(__VA_ARGS__)
 #define __SC_TEST6(t6, a6, ...)	__SC_TEST(t6); __SC_TEST5(__VA_ARGS__)
 
-#ifdef CONFIG_PERF_EVENTS
-
-#define TRACE_SYS_ENTER_PERF_INIT(sname)				       \
-	.perf_event_enable = perf_sysenter_enable,			       \
-	.perf_event_disable = perf_sysenter_disable,
-
-#define TRACE_SYS_EXIT_PERF_INIT(sname)					       \
-	.perf_event_enable = perf_sysexit_enable,			       \
-	.perf_event_disable = perf_sysexit_disable,
-#else
-#define TRACE_SYS_ENTER_PERF(sname)
-#define TRACE_SYS_ENTER_PERF_INIT(sname)
-#define TRACE_SYS_EXIT_PERF(sname)
-#define TRACE_SYS_EXIT_PERF_INIT(sname)
-#endif /* CONFIG_PERF_EVENTS */
-
 #ifdef CONFIG_FTRACE_SYSCALLS
 #define __SC_STR_ADECL1(t, a)		#a
 #define __SC_STR_ADECL2(t, a, ...)	#a, __SC_STR_ADECL1(__VA_ARGS__)
@@ -134,54 +118,43 @@ struct perf_event_attr;
 #define __SC_STR_TDECL5(t, a, ...)	#t, __SC_STR_TDECL4(__VA_ARGS__)
 #define __SC_STR_TDECL6(t, a, ...)	#t, __SC_STR_TDECL5(__VA_ARGS__)
 
+extern struct ftrace_event_class event_class_syscall_enter;
+extern struct ftrace_event_class event_class_syscall_exit;
+extern struct trace_event_functions enter_syscall_print_funcs;
+extern struct trace_event_functions exit_syscall_print_funcs;
+
 #define SYSCALL_TRACE_ENTER_EVENT(sname)				\
-	static const struct syscall_metadata __syscall_meta_##sname;	\
+	static struct syscall_metadata __syscall_meta_##sname;		\
 	static struct ftrace_event_call					\
 	__attribute__((__aligned__(4))) event_enter_##sname;		\
-	static struct trace_event enter_syscall_print_##sname = {	\
-		.trace                  = print_syscall_enter,		\
-	};								\
 	static struct ftrace_event_call __used				\
 	  __attribute__((__aligned__(4)))				\
 	  __attribute__((section("_ftrace_events")))			\
 	  event_enter_##sname = {					\
 		.name                   = "sys_enter"#sname,		\
-		.system                 = "syscalls",			\
-		.event                  = &enter_syscall_print_##sname,	\
-		.raw_init		= init_syscall_trace,		\
-		.define_fields		= syscall_enter_define_fields,	\
-		.regfunc		= reg_event_syscall_enter,	\
-		.unregfunc		= unreg_event_syscall_enter,	\
+		.class			= &event_class_syscall_enter,	\
+		.event.funcs            = &enter_syscall_print_funcs,	\
 		.data			= (void *)&__syscall_meta_##sname,\
-		TRACE_SYS_ENTER_PERF_INIT(sname)			\
 	}
 
 #define SYSCALL_TRACE_EXIT_EVENT(sname)					\
-	static const struct syscall_metadata __syscall_meta_##sname;	\
+	static struct syscall_metadata __syscall_meta_##sname;		\
 	static struct ftrace_event_call					\
 	__attribute__((__aligned__(4))) event_exit_##sname;		\
-	static struct trace_event exit_syscall_print_##sname = {	\
-		.trace                  = print_syscall_exit,		\
-	};								\
 	static struct ftrace_event_call __used				\
 	  __attribute__((__aligned__(4)))				\
 	  __attribute__((section("_ftrace_events")))			\
 	  event_exit_##sname = {					\
 		.name                   = "sys_exit"#sname,		\
-		.system                 = "syscalls",			\
-		.event                  = &exit_syscall_print_##sname,	\
-		.raw_init		= init_syscall_trace,		\
-		.define_fields		= syscall_exit_define_fields,	\
-		.regfunc		= reg_event_syscall_exit,	\
-		.unregfunc		= unreg_event_syscall_exit,	\
+		.class			= &event_class_syscall_exit,	\
+		.event.funcs		= &exit_syscall_print_funcs,	\
 		.data			= (void *)&__syscall_meta_##sname,\
-		TRACE_SYS_EXIT_PERF_INIT(sname)			\
 	}
 
 #define SYSCALL_METADATA(sname, nb)				\
 	SYSCALL_TRACE_ENTER_EVENT(sname);			\
 	SYSCALL_TRACE_EXIT_EVENT(sname);			\
-	static const struct syscall_metadata __used		\
+	static struct syscall_metadata __used			\
 	  __attribute__((__aligned__(4)))			\
 	  __attribute__((section("__syscalls_metadata")))	\
 	  __syscall_meta_##sname = {				\
@@ -191,12 +164,14 @@ struct perf_event_attr;
 		.args		= args_##sname,			\
 		.enter_event	= &event_enter_##sname,		\
 		.exit_event	= &event_exit_##sname,		\
+		.enter_fields	= LIST_HEAD_INIT(__syscall_meta_##sname.enter_fields), \
+		.exit_fields	= LIST_HEAD_INIT(__syscall_meta_##sname.exit_fields), \
 	};
 
 #define SYSCALL_DEFINE0(sname)					\
 	SYSCALL_TRACE_ENTER_EVENT(_##sname);			\
 	SYSCALL_TRACE_EXIT_EVENT(_##sname);			\
-	static const struct syscall_metadata __used		\
+	static struct syscall_metadata __used			\
 	  __attribute__((__aligned__(4)))			\
 	  __attribute__((section("__syscalls_metadata")))	\
 	  __syscall_meta__##sname = {				\
@@ -204,6 +179,8 @@ struct perf_event_attr;
 		.nb_args 	= 0,				\
 		.enter_event	= &event_enter__##sname,	\
 		.exit_event	= &event_exit__##sname,		\
+		.enter_fields	= LIST_HEAD_INIT(__syscall_meta__##sname.enter_fields), \
+		.exit_fields	= LIST_HEAD_INIT(__syscall_meta__##sname.exit_fields), \
 	};							\
 	asmlinkage long sys_##sname(void)
 #else
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 1d85f9a6a19..9a59d1f98cd 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -20,12 +20,17 @@
 struct module;
 struct tracepoint;
 
+struct tracepoint_func {
+	void *func;
+	void *data;
+};
+
 struct tracepoint {
 	const char *name;		/* Tracepoint name */
 	int state;			/* State. */
 	void (*regfunc)(void);
 	void (*unregfunc)(void);
-	void **funcs;
+	struct tracepoint_func *funcs;
 } __attribute__((aligned(32)));		/*
 					 * Aligned on 32 bytes because it is
 					 * globally visible and gcc happily
@@ -37,16 +42,19 @@ struct tracepoint {
  * Connect a probe to a tracepoint.
  * Internal API, should not be used directly.
  */
-extern int tracepoint_probe_register(const char *name, void *probe);
+extern int tracepoint_probe_register(const char *name, void *probe, void *data);
 
 /*
  * Disconnect a probe from a tracepoint.
  * Internal API, should not be used directly.
  */
-extern int tracepoint_probe_unregister(const char *name, void *probe);
+extern int
+tracepoint_probe_unregister(const char *name, void *probe, void *data);
 
-extern int tracepoint_probe_register_noupdate(const char *name, void *probe);
-extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe);
+extern int tracepoint_probe_register_noupdate(const char *name, void *probe,
+					      void *data);
+extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe,
+						void *data);
 extern void tracepoint_probe_update_all(void);
 
 struct tracepoint_iter {
@@ -102,17 +110,27 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
 /*
  * it_func[0] is never NULL because there is at least one element in the array
  * when the array itself is non NULL.
+ *
+ * Note, the proto and args passed in includes "__data" as the first parameter.
+ * The reason for this is to handle the "void" prototype. If a tracepoint
+ * has a "void" prototype, then it is invalid to declare a function
+ * as "(void *, void)". The DECLARE_TRACE_NOARGS() will pass in just
+ * "void *data", where as the DECLARE_TRACE() will pass in "void *data, proto".
  */
 #define __DO_TRACE(tp, proto, args)					\
 	do {								\
-		void **it_func;						\
+		struct tracepoint_func *it_func_ptr;			\
+		void *it_func;						\
+		void *__data;						\
 									\
 		rcu_read_lock_sched_notrace();				\
-		it_func = rcu_dereference_sched((tp)->funcs);		\
-		if (it_func) {						\
+		it_func_ptr = rcu_dereference_sched((tp)->funcs);	\
+		if (it_func_ptr) {					\
 			do {						\
-				((void(*)(proto))(*it_func))(args);	\
-			} while (*(++it_func));				\
+				it_func = (it_func_ptr)->func;		\
+				__data = (it_func_ptr)->data;		\
+				((void(*)(proto))(it_func))(args);	\
+			} while ((++it_func_ptr)->func);		\
 		}							\
 		rcu_read_unlock_sched_notrace();			\
 	} while (0)
@@ -122,24 +140,32 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
  * not add unwanted padding between the beginning of the section and the
  * structure. Force alignment to the same alignment as the section start.
  */
-#define DECLARE_TRACE(name, proto, args)				\
+#define __DECLARE_TRACE(name, proto, args, data_proto, data_args)	\
 	extern struct tracepoint __tracepoint_##name;			\
 	static inline void trace_##name(proto)				\
 	{								\
 		if (unlikely(__tracepoint_##name.state))		\
 			__DO_TRACE(&__tracepoint_##name,		\
-				TP_PROTO(proto), TP_ARGS(args));	\
+				TP_PROTO(data_proto),			\
+				TP_ARGS(data_args));			\
+	}								\
+	static inline int						\
+	register_trace_##name(void (*probe)(data_proto), void *data)	\
+	{								\
+		return tracepoint_probe_register(#name, (void *)probe,	\
+						 data);			\
 	}								\
-	static inline int register_trace_##name(void (*probe)(proto))	\
+	static inline int						\
+	unregister_trace_##name(void (*probe)(data_proto), void *data)	\
 	{								\
-		return tracepoint_probe_register(#name, (void *)probe);	\
+		return tracepoint_probe_unregister(#name, (void *)probe, \
+						   data);		\
 	}								\
-	static inline int unregister_trace_##name(void (*probe)(proto))	\
+	static inline void						\
+	check_trace_callback_type_##name(void (*cb)(data_proto))	\
 	{								\
-		return tracepoint_probe_unregister(#name, (void *)probe);\
 	}
 
-
 #define DEFINE_TRACE_FN(name, reg, unreg)				\
 	static const char __tpstrtab_##name[]				\
 	__attribute__((section("__tracepoints_strings"))) = #name;	\
@@ -156,18 +182,23 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
 	EXPORT_SYMBOL(__tracepoint_##name)
 
 #else /* !CONFIG_TRACEPOINTS */
-#define DECLARE_TRACE(name, proto, args)				\
-	static inline void _do_trace_##name(struct tracepoint *tp, proto) \
-	{ }								\
+#define __DECLARE_TRACE(name, proto, args, data_proto, data_args)	\
 	static inline void trace_##name(proto)				\
 	{ }								\
-	static inline int register_trace_##name(void (*probe)(proto))	\
+	static inline int						\
+	register_trace_##name(void (*probe)(data_proto),		\
+			      void *data)				\
 	{								\
 		return -ENOSYS;						\
 	}								\
-	static inline int unregister_trace_##name(void (*probe)(proto))	\
+	static inline int						\
+	unregister_trace_##name(void (*probe)(data_proto),		\
+				void *data)				\
 	{								\
 		return -ENOSYS;						\
+	}								\
+	static inline void check_trace_callback_type_##name(void (*cb)(data_proto)) \
+	{								\
 	}
 
 #define DEFINE_TRACE_FN(name, reg, unreg)
@@ -176,6 +207,29 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
 #define EXPORT_TRACEPOINT_SYMBOL(name)
 
 #endif /* CONFIG_TRACEPOINTS */
+
+/*
+ * The need for the DECLARE_TRACE_NOARGS() is to handle the prototype
+ * (void). "void" is a special value in a function prototype and can
+ * not be combined with other arguments. Since the DECLARE_TRACE()
+ * macro adds a data element at the beginning of the prototype,
+ * we need a way to differentiate "(void *data, proto)" from
+ * "(void *data, void)". The second prototype is invalid.
+ *
+ * DECLARE_TRACE_NOARGS() passes "void" as the tracepoint prototype
+ * and "void *__data" as the callback prototype.
+ *
+ * DECLARE_TRACE() passes "proto" as the tracepoint protoype and
+ * "void *__data, proto" as the callback prototype.
+ */
+#define DECLARE_TRACE_NOARGS(name)					\
+		__DECLARE_TRACE(name, void, , void *__data, __data)
+
+#define DECLARE_TRACE(name, proto, args)				\
+		__DECLARE_TRACE(name, PARAMS(proto), PARAMS(args),	\
+				PARAMS(void *__data, proto),		\
+				PARAMS(__data, args))
+
 #endif /* DECLARE_TRACE */
 
 #ifndef TRACE_EVENT