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

* 'tracing-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (105 commits)
  ring-buffer: only enable ring_buffer_swap_cpu when needed
  ring-buffer: check for swapped buffers in start of committing
  tracing: report error in trace if we fail to swap latency buffer
  tracing: add trace_array_printk for internal tracers to use
  tracing: pass around ring buffer instead of tracer
  tracing: make tracing_reset safe for external use
  tracing: use timestamp to determine start of latency traces
  tracing: Remove mentioning of legacy latency_trace file from documentation
  tracing/filters: Defer pred allocation, fix memory leak
  tracing: remove users of tracing_reset
  tracing: disable buffers and synchronize_sched before resetting
  tracing: disable update max tracer while reading trace
  tracing: print out start and stop in latency traces
  ring-buffer: disable all cpu buffers when one finds a problem
  ring-buffer: do not count discarded events
  ring-buffer: remove ring_buffer_event_discard
  ring-buffer: fix ring_buffer_read crossing pages
  ring-buffer: remove unnecessary cpu_relax
  ring-buffer: do not swap buffers during a commit
  ring-buffer: do not reset while in a commit
  ...

include/linux/ftrace_event.h

@@ -93,16 +93,22 @@ void tracing_generic_entry_update(struct trace_entry *entry,
 				  unsigned long flags,
 				  int pc);
 struct ring_buffer_event *
-trace_current_buffer_lock_reserve(int type, unsigned long len,
+trace_current_buffer_lock_reserve(struct ring_buffer **current_buffer,
+				  int type, unsigned long len,
 				  unsigned long flags, int pc);
-void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
+void trace_current_buffer_unlock_commit(struct ring_buffer *buffer,
+					struct ring_buffer_event *event,
 					unsigned long flags, int pc);
-void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
+void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer,
+				       struct ring_buffer_event *event,
 					unsigned long flags, int pc);
-void trace_current_buffer_discard_commit(struct ring_buffer_event *event);
+void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
+					 struct ring_buffer_event *event);
 
 void tracing_record_cmdline(struct task_struct *tsk);
 
+struct event_filter;
+
 struct ftrace_event_call {
 	struct list_head	list;
 	char			*name;
@@ -110,16 +116,18 @@ struct ftrace_event_call {
 	struct dentry		*dir;
 	struct trace_event	*event;
 	int			enabled;
-	int			(*regfunc)(void);
-	void			(*unregfunc)(void);
+	int			(*regfunc)(void *);
+	void			(*unregfunc)(void *);
 	int			id;
 	int			(*raw_init)(void);
-	int			(*show_format)(struct trace_seq *s);
-	int			(*define_fields)(void);
+	int			(*show_format)(struct ftrace_event_call *call,
+					       struct trace_seq *s);
+	int			(*define_fields)(struct ftrace_event_call *);
 	struct list_head	fields;
 	int			filter_active;
-	void			*filter;
+	struct event_filter	*filter;
 	void			*mod;
+	void			*data;
 
 	atomic_t		profile_count;
 	int			(*profile_enable)(struct ftrace_event_call *);
@@ -129,15 +137,25 @@ struct ftrace_event_call {
 #define MAX_FILTER_PRED		32
 #define MAX_FILTER_STR_VAL	128
 
-extern int init_preds(struct ftrace_event_call *call);
 extern void destroy_preds(struct ftrace_event_call *call);
 extern int filter_match_preds(struct ftrace_event_call *call, void *rec);
-extern int filter_current_check_discard(struct ftrace_event_call *call,
+extern int filter_current_check_discard(struct ring_buffer *buffer,
+					struct ftrace_event_call *call,
 					void *rec,
 					struct ring_buffer_event *event);
 
-extern int trace_define_field(struct ftrace_event_call *call, char *type,
-			      char *name, int offset, int size, int is_signed);
+enum {
+	FILTER_OTHER = 0,
+	FILTER_STATIC_STRING,
+	FILTER_DYN_STRING,
+	FILTER_PTR_STRING,
+};
+
+extern int trace_define_field(struct ftrace_event_call *call,
+			      const char *type, const char *name,
+			      int offset, int size, int is_signed,
+			      int filter_type);
+extern int trace_define_common_fields(struct ftrace_event_call *call);
 
 #define is_signed_type(type)	(((type)(-1)) < 0)
 
@@ -162,11 +180,4 @@ do {									\
 		__trace_printk(ip, fmt, ##args);			\
 } while (0)
 
-#define __common_field(type, item, is_signed)				\
-	ret = trace_define_field(event_call, #type, "common_" #item,	\
-				 offsetof(typeof(field.ent), item),	\
-				 sizeof(field.ent.item), is_signed);	\
-	if (ret)							\
-		return ret;
-
 #endif /* _LINUX_FTRACE_EVENT_H */

include/linux/module.h

@@ -17,10 +17,12 @@
 #include <linux/moduleparam.h>
 #include <linux/marker.h>
 #include <linux/tracepoint.h>
-#include <asm/local.h>
 
+#include <asm/local.h>
 #include <asm/module.h>
 
+#include <trace/events/module.h>
+
 /* Not Yet Implemented */
 #define MODULE_SUPPORTED_DEVICE(name)
 
@@ -462,7 +464,10 @@ static inline local_t *__module_ref_addr(struct module *mod, int cpu)
 static inline void __module_get(struct module *module)
 {
 	if (module) {
-		local_inc(__module_ref_addr(module, get_cpu()));
+		unsigned int cpu = get_cpu();
+		local_inc(__module_ref_addr(module, cpu));
+		trace_module_get(module, _THIS_IP_,
+				 local_read(__module_ref_addr(module, cpu)));
 		put_cpu();
 	}
 }
@@ -473,8 +478,11 @@ static inline int try_module_get(struct module *module)
 
 	if (module) {
 		unsigned int cpu = get_cpu();
-		if (likely(module_is_live(module)))
+		if (likely(module_is_live(module))) {
 			local_inc(__module_ref_addr(module, cpu));
+			trace_module_get(module, _THIS_IP_,
+				local_read(__module_ref_addr(module, cpu)));
+		}
 		else
 			ret = 0;
 		put_cpu();

include/linux/perf_counter.h

@@ -766,6 +766,8 @@ extern int sysctl_perf_counter_mlock;
 extern int sysctl_perf_counter_sample_rate;
 
 extern void perf_counter_init(void);
+extern void perf_tpcounter_event(int event_id, u64 addr, u64 count,
+				 void *record, int entry_size);
 
 #ifndef perf_misc_flags
 #define perf_misc_flags(regs)	(user_mode(regs) ? PERF_EVENT_MISC_USER : \

include/linux/ring_buffer.h

@@ -74,20 +74,6 @@ ring_buffer_event_time_delta(struct ring_buffer_event *event)
 	return event->time_delta;
 }
 
-/*
- * ring_buffer_event_discard can discard any event in the ring buffer.
- *   it is up to the caller to protect against a reader from
- *   consuming it or a writer from wrapping and replacing it.
- *
- * No external protection is needed if this is called before
- * the event is commited. But in that case it would be better to
- * use ring_buffer_discard_commit.
- *
- * Note, if an event that has not been committed is discarded
- * with ring_buffer_event_discard, it must still be committed.
- */
-void ring_buffer_event_discard(struct ring_buffer_event *event);
-
 /*
  * ring_buffer_discard_commit will remove an event that has not
  *   ben committed yet. If this is used, then ring_buffer_unlock_commit
@@ -154,8 +140,17 @@ unsigned long ring_buffer_size(struct ring_buffer *buffer);
 void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu);
 void ring_buffer_reset(struct ring_buffer *buffer);
 
+#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP
 int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
 			 struct ring_buffer *buffer_b, int cpu);
+#else
+static inline int
+ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
+		     struct ring_buffer *buffer_b, int cpu)
+{
+	return -ENODEV;
+}
+#endif
 
 int ring_buffer_empty(struct ring_buffer *buffer);
 int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu);
@@ -170,7 +165,6 @@ unsigned long ring_buffer_overruns(struct ring_buffer *buffer);
 unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu);
-unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu);
 
 u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu);
 void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,

include/linux/syscalls.h

@@ -64,6 +64,7 @@ struct perf_counter_attr;
 #include <linux/sem.h>
 #include <asm/siginfo.h>
 #include <asm/signal.h>
+#include <linux/unistd.h>
 #include <linux/quota.h>
 #include <linux/key.h>
 #include <trace/syscall.h>
@@ -97,6 +98,53 @@ struct perf_counter_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_EVENT_PROFILE
+#define TRACE_SYS_ENTER_PROFILE(sname)					       \
+static int prof_sysenter_enable_##sname(struct ftrace_event_call *event_call)  \
+{									       \
+	int ret = 0;							       \
+	if (!atomic_inc_return(&event_enter_##sname.profile_count))	       \
+		ret = reg_prof_syscall_enter("sys"#sname);		       \
+	return ret;							       \
+}									       \
+									       \
+static void prof_sysenter_disable_##sname(struct ftrace_event_call *event_call)\
+{									       \
+	if (atomic_add_negative(-1, &event_enter_##sname.profile_count))       \
+		unreg_prof_syscall_enter("sys"#sname);			       \
+}
+
+#define TRACE_SYS_EXIT_PROFILE(sname)					       \
+static int prof_sysexit_enable_##sname(struct ftrace_event_call *event_call)   \
+{									       \
+	int ret = 0;							       \
+	if (!atomic_inc_return(&event_exit_##sname.profile_count))	       \
+		ret = reg_prof_syscall_exit("sys"#sname);		       \
+	return ret;							       \
+}									       \
+									       \
+static void prof_sysexit_disable_##sname(struct ftrace_event_call *event_call) \
+{                                                                              \
+	if (atomic_add_negative(-1, &event_exit_##sname.profile_count))	       \
+		unreg_prof_syscall_exit("sys"#sname);			       \
+}
+
+#define TRACE_SYS_ENTER_PROFILE_INIT(sname)				       \
+	.profile_count = ATOMIC_INIT(-1),				       \
+	.profile_enable = prof_sysenter_enable_##sname,			       \
+	.profile_disable = prof_sysenter_disable_##sname,
+
+#define TRACE_SYS_EXIT_PROFILE_INIT(sname)				       \
+	.profile_count = ATOMIC_INIT(-1),				       \
+	.profile_enable = prof_sysexit_enable_##sname,			       \
+	.profile_disable = prof_sysexit_disable_##sname,
+#else
+#define TRACE_SYS_ENTER_PROFILE(sname)
+#define TRACE_SYS_ENTER_PROFILE_INIT(sname)
+#define TRACE_SYS_EXIT_PROFILE(sname)
+#define TRACE_SYS_EXIT_PROFILE_INIT(sname)
+#endif
+
 #ifdef CONFIG_FTRACE_SYSCALLS
 #define __SC_STR_ADECL1(t, a)		#a
 #define __SC_STR_ADECL2(t, a, ...)	#a, __SC_STR_ADECL1(__VA_ARGS__)
@@ -112,7 +160,81 @@ struct perf_counter_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__)
 
+#define SYSCALL_TRACE_ENTER_EVENT(sname)				\
+	static struct ftrace_event_call event_enter_##sname;		\
+	struct trace_event enter_syscall_print_##sname = {		\
+		.trace                  = print_syscall_enter,		\
+	};								\
+	static int init_enter_##sname(void)				\
+	{								\
+		int num, id;						\
+		num = syscall_name_to_nr("sys"#sname);			\
+		if (num < 0)						\
+			return -ENOSYS;					\
+		id = register_ftrace_event(&enter_syscall_print_##sname);\
+		if (!id)						\
+			return -ENODEV;					\
+		event_enter_##sname.id = id;				\
+		set_syscall_enter_id(num, id);				\
+		INIT_LIST_HEAD(&event_enter_##sname.fields);		\
+		return 0;						\
+	}								\
+	TRACE_SYS_ENTER_PROFILE(sname);					\
+	static struct ftrace_event_call __used				\
+	  __attribute__((__aligned__(4)))				\
+	  __attribute__((section("_ftrace_events")))			\
+	  event_enter_##sname = {					\
+		.name                   = "sys_enter"#sname,		\
+		.system                 = "syscalls",			\
+		.event                  = &event_syscall_enter,		\
+		.raw_init		= init_enter_##sname,		\
+		.show_format		= syscall_enter_format,		\
+		.define_fields		= syscall_enter_define_fields,	\
+		.regfunc		= reg_event_syscall_enter,	\
+		.unregfunc		= unreg_event_syscall_enter,	\
+		.data			= "sys"#sname,			\
+		TRACE_SYS_ENTER_PROFILE_INIT(sname)			\
+	}
+
+#define SYSCALL_TRACE_EXIT_EVENT(sname)					\
+	static struct ftrace_event_call event_exit_##sname;		\
+	struct trace_event exit_syscall_print_##sname = {		\
+		.trace                  = print_syscall_exit,		\
+	};								\
+	static int init_exit_##sname(void)				\
+	{								\
+		int num, id;						\
+		num = syscall_name_to_nr("sys"#sname);			\
+		if (num < 0)						\
+			return -ENOSYS;					\
+		id = register_ftrace_event(&exit_syscall_print_##sname);\
+		if (!id)						\
+			return -ENODEV;					\
+		event_exit_##sname.id = id;				\
+		set_syscall_exit_id(num, id);				\
+		INIT_LIST_HEAD(&event_exit_##sname.fields);		\
+		return 0;						\
+	}								\
+	TRACE_SYS_EXIT_PROFILE(sname);					\
+	static struct ftrace_event_call __used				\
+	  __attribute__((__aligned__(4)))				\
+	  __attribute__((section("_ftrace_events")))			\
+	  event_exit_##sname = {					\
+		.name                   = "sys_exit"#sname,		\
+		.system                 = "syscalls",			\
+		.event                  = &event_syscall_exit,		\
+		.raw_init		= init_exit_##sname,		\
+		.show_format		= syscall_exit_format,		\
+		.define_fields		= syscall_exit_define_fields,	\
+		.regfunc		= reg_event_syscall_exit,	\
+		.unregfunc		= unreg_event_syscall_exit,	\
+		.data			= "sys"#sname,			\
+		TRACE_SYS_EXIT_PROFILE_INIT(sname)			\
+	}
+
 #define SYSCALL_METADATA(sname, nb)				\
+	SYSCALL_TRACE_ENTER_EVENT(sname);			\
+	SYSCALL_TRACE_EXIT_EVENT(sname);			\
 	static const struct syscall_metadata __used		\
 	  __attribute__((__aligned__(4)))			\
 	  __attribute__((section("__syscalls_metadata")))	\
@@ -121,18 +243,23 @@ struct perf_counter_attr;
 		.nb_args 	= nb,				\
 		.types		= types_##sname,		\
 		.args		= args_##sname,			\
-	}
+		.enter_event	= &event_enter_##sname,		\
+		.exit_event	= &event_exit_##sname,		\
+	};
 
 #define SYSCALL_DEFINE0(sname)					\
+	SYSCALL_TRACE_ENTER_EVENT(_##sname);			\
+	SYSCALL_TRACE_EXIT_EVENT(_##sname);			\
 	static const struct syscall_metadata __used		\
 	  __attribute__((__aligned__(4)))			\
 	  __attribute__((section("__syscalls_metadata")))	\
 	  __syscall_meta_##sname = {				\
 		.name 		= "sys_"#sname,			\
 		.nb_args 	= 0,				\
+		.enter_event	= &event_enter__##sname,	\
+		.exit_event	= &event_exit__##sname,		\
 	};							\
 	asmlinkage long sys_##sname(void)
-
 #else
 #define SYSCALL_DEFINE0(name)	   asmlinkage long sys_##name(void)
 #endif

include/linux/tracepoint.h

@@ -23,6 +23,8 @@ struct tracepoint;
 struct tracepoint {
 	const char *name;		/* Tracepoint name */
 	int state;			/* State. */
+	void (*regfunc)(void);
+	void (*unregfunc)(void);
 	void **funcs;
 } __attribute__((aligned(32)));		/*
 					 * Aligned on 32 bytes because it is
@@ -78,12 +80,16 @@ struct tracepoint {
 		return tracepoint_probe_unregister(#name, (void *)probe);\
 	}
 
-#define DEFINE_TRACE(name)						\
+
+#define DEFINE_TRACE_FN(name, reg, unreg)				\
 	static const char __tpstrtab_##name[]				\
 	__attribute__((section("__tracepoints_strings"))) = #name;	\
 	struct tracepoint __tracepoint_##name				\
 	__attribute__((section("__tracepoints"), aligned(32))) =	\
-		{ __tpstrtab_##name, 0, NULL }
+		{ __tpstrtab_##name, 0, reg, unreg, NULL }
+
+#define DEFINE_TRACE(name)						\
+	DEFINE_TRACE_FN(name, NULL, NULL);
 
 #define EXPORT_TRACEPOINT_SYMBOL_GPL(name)				\
 	EXPORT_SYMBOL_GPL(__tracepoint_##name)
@@ -108,6 +114,7 @@ extern void tracepoint_update_probe_range(struct tracepoint *begin,
 		return -ENOSYS;						\
 	}
 
+#define DEFINE_TRACE_FN(name, reg, unreg)
 #define DEFINE_TRACE(name)
 #define EXPORT_TRACEPOINT_SYMBOL_GPL(name)
 #define EXPORT_TRACEPOINT_SYMBOL(name)
@@ -158,6 +165,15 @@ static inline void tracepoint_synchronize_unregister(void)
 
 #define PARAMS(args...) args
 
+#endif /* _LINUX_TRACEPOINT_H */
+
+/*
+ * Note: we keep the TRACE_EVENT outside the include file ifdef protection.
+ *  This is due to the way trace events work. If a file includes two
+ *  trace event headers under one "CREATE_TRACE_POINTS" the first include
+ *  will override the TRACE_EVENT and break the second include.
+ */
+
 #ifndef TRACE_EVENT
 /*
  * For use with the TRACE_EVENT macro:
@@ -259,10 +275,15 @@ static inline void tracepoint_synchronize_unregister(void)
  * can also by used by generic instrumentation like SystemTap), and
  * it is also used to expose a structured trace record in
  * /sys/kernel/debug/tracing/events/.
+ *
+ * A set of (un)registration functions can be passed to the variant
+ * TRACE_EVENT_FN to perform any (un)registration work.
  */
 
 #define TRACE_EVENT(name, proto, args, struct, assign, print)	\
 	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
-#endif
+#define TRACE_EVENT_FN(name, proto, args, struct,		\
+		assign, print, reg, unreg)			\
+	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
 
-#endif
+#endif /* ifdef TRACE_EVENT (see note above) */