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: (146 commits)
  tools, perf: Documentation for the power events API
  perf: Add calls to suspend trace point
  perf script: Make some lists static
  perf script: Use the default lost event handler
  perf session: Warn about errors when processing pipe events too
  perf tools: Fix perf_event.h header usage
  perf test: Clarify some error reports in the open syscall test
  x86, NMI: Add touch_nmi_watchdog to io_check_error delay
  x86: Avoid calling arch_trigger_all_cpu_backtrace() at the same time
  x86: Only call smp_processor_id in non-preempt cases
  perf timechart: Adjust perf timechart to the new power events
  perf: Clean up power events by introducing new, more generic ones
  perf: Do not export power_frequency, but power_start event
  perf test: Add test for counting open syscalls
  perf evsel: Auto allocate resources needed for some methods
  perf evsel: Use {cpu,thread}_map to shorten list of parameters
  perf tools: Refactor all_tids to hold nr and the map
  perf tools: Refactor cpumap to hold nr and the map
  perf evsel: Introduce per cpu and per thread open helpers
  perf evsel: Steal the counter reading routines from stat
  ...

include/linux/ftrace_event.h

@@ -154,12 +154,14 @@ enum {
 	TRACE_EVENT_FL_ENABLED_BIT,
 	TRACE_EVENT_FL_FILTERED_BIT,
 	TRACE_EVENT_FL_RECORDED_CMD_BIT,
+	TRACE_EVENT_FL_CAP_ANY_BIT,
 };
 
 enum {
 	TRACE_EVENT_FL_ENABLED		= (1 << TRACE_EVENT_FL_ENABLED_BIT),
 	TRACE_EVENT_FL_FILTERED		= (1 << TRACE_EVENT_FL_FILTERED_BIT),
 	TRACE_EVENT_FL_RECORDED_CMD	= (1 << TRACE_EVENT_FL_RECORDED_CMD_BIT),
+	TRACE_EVENT_FL_CAP_ANY		= (1 << TRACE_EVENT_FL_CAP_ANY_BIT),
 };
 
 struct ftrace_event_call {
@@ -196,6 +198,14 @@ struct ftrace_event_call {
 #endif
 };
 
+#define __TRACE_EVENT_FLAGS(name, value)				\
+	static int __init trace_init_flags_##name(void)			\
+	{								\
+		event_##name.flags = value;				\
+		return 0;						\
+	}								\
+	early_initcall(trace_init_flags_##name);
+
 #define PERF_MAX_TRACE_SIZE	2048
 
 #define MAX_FILTER_PRED		32
@@ -215,6 +225,10 @@ enum {
 	FILTER_PTR_STRING,
 };
 
+#define EVENT_STORAGE_SIZE 128
+extern struct mutex event_storage_mutex;
+extern char event_storage[EVENT_STORAGE_SIZE];
+
 extern int trace_event_raw_init(struct ftrace_event_call *call);
 extern int trace_define_field(struct ftrace_event_call *call, const char *type,
 			      const char *name, int offset, int size,

include/linux/kprobes.h

@@ -275,7 +275,9 @@ extern int arch_prepared_optinsn(struct arch_optimized_insn *optinsn);
 extern int arch_check_optimized_kprobe(struct optimized_kprobe *op);
 extern int arch_prepare_optimized_kprobe(struct optimized_kprobe *op);
 extern void arch_remove_optimized_kprobe(struct optimized_kprobe *op);
-extern int  arch_optimize_kprobe(struct optimized_kprobe *op);
+extern void arch_optimize_kprobes(struct list_head *oplist);
+extern void arch_unoptimize_kprobes(struct list_head *oplist,
+				    struct list_head *done_list);
 extern void arch_unoptimize_kprobe(struct optimized_kprobe *op);
 extern kprobe_opcode_t *get_optinsn_slot(void);
 extern void free_optinsn_slot(kprobe_opcode_t *slot, int dirty);

include/linux/nmi.h

@@ -14,22 +14,14 @@
  * may be used to reset the timeout - for code which intentionally
  * disables interrupts for a long time. This call is stateless.
  */
-#ifdef ARCH_HAS_NMI_WATCHDOG
+#if defined(ARCH_HAS_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
 #include <asm/nmi.h>
 extern void touch_nmi_watchdog(void);
-extern void acpi_nmi_disable(void);
-extern void acpi_nmi_enable(void);
 #else
-#ifndef CONFIG_HARDLOCKUP_DETECTOR
 static inline void touch_nmi_watchdog(void)
 {
 	touch_softlockup_watchdog();
 }
-#else
-extern void touch_nmi_watchdog(void);
-#endif
-static inline void acpi_nmi_disable(void) { }
-static inline void acpi_nmi_enable(void) { }
 #endif
 
 /*

include/linux/perf_event.h

@@ -215,8 +215,9 @@ struct perf_event_attr {
 				 */
 				precise_ip     :  2, /* skid constraint       */
 				mmap_data      :  1, /* non-exec mmap data    */
+				sample_id_all  :  1, /* sample_type all events */
 
-				__reserved_1   : 46;
+				__reserved_1   : 45;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -327,6 +328,15 @@ struct perf_event_header {
 enum perf_event_type {
 
 	/*
+	 * If perf_event_attr.sample_id_all is set then all event types will
+	 * have the sample_type selected fields related to where/when
+	 * (identity) an event took place (TID, TIME, ID, CPU, STREAM_ID)
+	 * described in PERF_RECORD_SAMPLE below, it will be stashed just after
+	 * the perf_event_header and the fields already present for the existing
+	 * fields, i.e. at the end of the payload. That way a newer perf.data
+	 * file will be supported by older perf tools, with these new optional
+	 * fields being ignored.
+	 *
 	 * The MMAP events record the PROT_EXEC mappings so that we can
 	 * correlate userspace IPs to code. They have the following structure:
 	 *
@@ -578,6 +588,10 @@ struct perf_event;
 struct pmu {
 	struct list_head		entry;
 
+	struct device			*dev;
+	char				*name;
+	int				type;
+
 	int * __percpu			pmu_disable_count;
 	struct perf_cpu_context * __percpu pmu_cpu_context;
 	int				task_ctx_nr;
@@ -758,6 +772,9 @@ struct perf_event {
 	u64				shadow_ctx_time;
 
 	struct perf_event_attr		attr;
+	u16				header_size;
+	u16				id_header_size;
+	u16				read_size;
 	struct hw_perf_event		hw;
 
 	struct perf_event_context	*ctx;
@@ -903,7 +920,7 @@ struct perf_output_handle {
 
 #ifdef CONFIG_PERF_EVENTS
 
-extern int perf_pmu_register(struct pmu *pmu);
+extern int perf_pmu_register(struct pmu *pmu, char *name, int type);
 extern void perf_pmu_unregister(struct pmu *pmu);
 
 extern int perf_num_counters(void);
@@ -970,6 +987,11 @@ extern int perf_event_overflow(struct perf_event *event, int nmi,
 				 struct perf_sample_data *data,
 				 struct pt_regs *regs);
 
+static inline bool is_sampling_event(struct perf_event *event)
+{
+	return event->attr.sample_period != 0;
+}
+
 /*
  * Return 1 for a software event, 0 for a hardware event
  */

include/linux/sched.h

@@ -316,6 +316,7 @@ extern int proc_dowatchdog_thresh(struct ctl_table *table, int write,
 				  size_t *lenp, loff_t *ppos);
 extern unsigned int  softlockup_panic;
 extern int softlockup_thresh;
+void lockup_detector_init(void);
 #else
 static inline void touch_softlockup_watchdog(void)
 {
@@ -326,6 +327,9 @@ static inline void touch_softlockup_watchdog_sync(void)
 static inline void touch_all_softlockup_watchdogs(void)
 {
 }
+static inline void lockup_detector_init(void)
+{
+}
 #endif
 
 #ifdef CONFIG_DETECT_HUNG_TASK

include/linux/stacktrace.h

@@ -2,6 +2,7 @@
 #define __LINUX_STACKTRACE_H
 
 struct task_struct;
+struct pt_regs;
 
 #ifdef CONFIG_STACKTRACE
 struct task_struct;
@@ -13,7 +14,8 @@ struct stack_trace {
 };
 
 extern void save_stack_trace(struct stack_trace *trace);
-extern void save_stack_trace_bp(struct stack_trace *trace, unsigned long bp);
+extern void save_stack_trace_regs(struct stack_trace *trace,
+				  struct pt_regs *regs);
 extern void save_stack_trace_tsk(struct task_struct *tsk,
 				struct stack_trace *trace);
 

include/linux/syscalls.h

@@ -127,8 +127,6 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 #define SYSCALL_TRACE_ENTER_EVENT(sname)				\
 	static struct syscall_metadata					\
 	__attribute__((__aligned__(4))) __syscall_meta_##sname;		\
-	static struct ftrace_event_call					\
-	__attribute__((__aligned__(4))) event_enter_##sname;		\
 	static struct ftrace_event_call __used				\
 	  __attribute__((__aligned__(4)))				\
 	  __attribute__((section("_ftrace_events")))			\
@@ -137,13 +135,12 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.class			= &event_class_syscall_enter,	\
 		.event.funcs            = &enter_syscall_print_funcs,	\
 		.data			= (void *)&__syscall_meta_##sname,\
-	}
+	};								\
+	__TRACE_EVENT_FLAGS(enter_##sname, TRACE_EVENT_FL_CAP_ANY)
 
 #define SYSCALL_TRACE_EXIT_EVENT(sname)					\
 	static struct syscall_metadata					\
 	__attribute__((__aligned__(4))) __syscall_meta_##sname;		\
-	static struct ftrace_event_call					\
-	__attribute__((__aligned__(4))) event_exit_##sname;		\
 	static struct ftrace_event_call __used				\
 	  __attribute__((__aligned__(4)))				\
 	  __attribute__((section("_ftrace_events")))			\
@@ -152,7 +149,8 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.class			= &event_class_syscall_exit,	\
 		.event.funcs		= &exit_syscall_print_funcs,	\
 		.data			= (void *)&__syscall_meta_##sname,\
-	}
+	};								\
+	__TRACE_EVENT_FLAGS(exit_##sname, TRACE_EVENT_FL_CAP_ANY)
 
 #define SYSCALL_METADATA(sname, nb)				\
 	SYSCALL_TRACE_ENTER_EVENT(sname);			\

include/linux/tracepoint.h

@@ -106,6 +106,7 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
 
 #define TP_PROTO(args...)	args
 #define TP_ARGS(args...)	args
+#define TP_CONDITION(args...)	args
 
 #ifdef CONFIG_TRACEPOINTS
 
@@ -119,12 +120,14 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
  * 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)					\
+#define __DO_TRACE(tp, proto, args, cond)				\
 	do {								\
 		struct tracepoint_func *it_func_ptr;			\
 		void *it_func;						\
 		void *__data;						\
 									\
+		if (!(cond))						\
+			return;						\
 		rcu_read_lock_sched_notrace();				\
 		it_func_ptr = rcu_dereference_sched((tp)->funcs);	\
 		if (it_func_ptr) {					\
@@ -142,7 +145,7 @@ 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, data_proto, data_args)	\
+#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args)	\
 	extern struct tracepoint __tracepoint_##name;			\
 	static inline void trace_##name(proto)				\
 	{								\
@@ -151,7 +154,8 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
 do_trace:								\
 			__DO_TRACE(&__tracepoint_##name,		\
 				TP_PROTO(data_proto),			\
-				TP_ARGS(data_args));			\
+				TP_ARGS(data_args),			\
+				TP_CONDITION(cond));			\
 	}								\
 	static inline int						\
 	register_trace_##name(void (*probe)(data_proto), void *data)	\
@@ -186,7 +190,7 @@ do_trace:								\
 	EXPORT_SYMBOL(__tracepoint_##name)
 
 #else /* !CONFIG_TRACEPOINTS */
-#define __DECLARE_TRACE(name, proto, args, data_proto, data_args)	\
+#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args)	\
 	static inline void trace_##name(proto)				\
 	{ }								\
 	static inline int						\
@@ -227,13 +231,20 @@ do_trace:								\
  * "void *__data, proto" as the callback prototype.
  */
 #define DECLARE_TRACE_NOARGS(name)					\
-		__DECLARE_TRACE(name, void, , void *__data, __data)
+		__DECLARE_TRACE(name, void, , 1, void *__data, __data)
 
 #define DECLARE_TRACE(name, proto, args)				\
-		__DECLARE_TRACE(name, PARAMS(proto), PARAMS(args),	\
+		__DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), 1,	\
 				PARAMS(void *__data, proto),		\
 				PARAMS(__data, args))
 
+#define DECLARE_TRACE_CONDITION(name, proto, args, cond)		\
+	__DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), PARAMS(cond), \
+			PARAMS(void *__data, proto),			\
+			PARAMS(__data, args))
+
+#define TRACE_EVENT_FLAGS(event, flag)
+
 #endif /* DECLARE_TRACE */
 
 #ifndef TRACE_EVENT
@@ -347,11 +358,21 @@ do_trace:								\
 	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
 #define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
 	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
+#define DEFINE_EVENT_CONDITION(template, name, proto,		\
+			       args, cond)			\
+	DECLARE_TRACE_CONDITION(name, PARAMS(proto),		\
+				PARAMS(args), PARAMS(cond))
 
 #define TRACE_EVENT(name, proto, args, struct, assign, print)	\
 	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
 #define TRACE_EVENT_FN(name, proto, args, struct,		\
 		assign, print, reg, unreg)			\
 	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
+#define TRACE_EVENT_CONDITION(name, proto, args, cond,		\
+			      struct, assign, print)		\
+	DECLARE_TRACE_CONDITION(name, PARAMS(proto),		\
+				PARAMS(args), PARAMS(cond))
+
+#define TRACE_EVENT_FLAGS(event, flag)
 
 #endif /* ifdef TRACE_EVENT (see note above) */

include/trace/define_trace.h

@@ -26,6 +26,15 @@
 #define TRACE_EVENT(name, proto, args, tstruct, assign, print)	\
 	DEFINE_TRACE(name)
 
+#undef TRACE_EVENT_CONDITION
+#define TRACE_EVENT_CONDITION(name, proto, args, cond, tstruct, assign, print) \
+	TRACE_EVENT(name,						\
+		PARAMS(proto),						\
+		PARAMS(args),						\
+		PARAMS(tstruct),					\
+		PARAMS(assign),						\
+		PARAMS(print))
+
 #undef TRACE_EVENT_FN
 #define TRACE_EVENT_FN(name, proto, args, tstruct,		\
 		assign, print, reg, unreg)			\
@@ -39,6 +48,10 @@
 #define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
 	DEFINE_TRACE(name)
 
+#undef DEFINE_EVENT_CONDITION
+#define DEFINE_EVENT_CONDITION(template, name, proto, args, cond) \
+	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+
 #undef DECLARE_TRACE
 #define DECLARE_TRACE(name, proto, args)	\
 	DEFINE_TRACE(name)
@@ -75,9 +88,11 @@
 
 #undef TRACE_EVENT
 #undef TRACE_EVENT_FN
+#undef TRACE_EVENT_CONDITION
 #undef DECLARE_EVENT_CLASS
 #undef DEFINE_EVENT
 #undef DEFINE_EVENT_PRINT
+#undef DEFINE_EVENT_CONDITION
 #undef TRACE_HEADER_MULTI_READ
 #undef DECLARE_TRACE
 

include/trace/events/power.h

@@ -7,16 +7,67 @@
 #include <linux/ktime.h>
 #include <linux/tracepoint.h>
 
-#ifndef _TRACE_POWER_ENUM_
-#define _TRACE_POWER_ENUM_
-enum {
-	POWER_NONE	= 0,
-	POWER_CSTATE	= 1,	/* C-State */
-	POWER_PSTATE	= 2,	/* Fequency change or DVFS */
-	POWER_SSTATE	= 3,	/* Suspend */
-};
+DECLARE_EVENT_CLASS(cpu,
+
+	TP_PROTO(unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(state, cpu_id),
+
+	TP_STRUCT__entry(
+		__field(	u32,		state		)
+		__field(	u32,		cpu_id		)
+	),
+
+	TP_fast_assign(
+		__entry->state = state;
+		__entry->cpu_id = cpu_id;
+	),
+
+	TP_printk("state=%lu cpu_id=%lu", (unsigned long)__entry->state,
+		  (unsigned long)__entry->cpu_id)
+);
+
+DEFINE_EVENT(cpu, cpu_idle,
+
+	TP_PROTO(unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(state, cpu_id)
+);
+
+/* This file can get included multiple times, TRACE_HEADER_MULTI_READ at top */
+#ifndef _PWR_EVENT_AVOID_DOUBLE_DEFINING
+#define _PWR_EVENT_AVOID_DOUBLE_DEFINING
+
+#define PWR_EVENT_EXIT -1
 #endif
 
+DEFINE_EVENT(cpu, cpu_frequency,
+
+	TP_PROTO(unsigned int frequency, unsigned int cpu_id),
+
+	TP_ARGS(frequency, cpu_id)
+);
+
+TRACE_EVENT(machine_suspend,
+
+	TP_PROTO(unsigned int state),
+
+	TP_ARGS(state),
+
+	TP_STRUCT__entry(
+		__field(	u32,		state		)
+	),
+
+	TP_fast_assign(
+		__entry->state = state;
+	),
+
+	TP_printk("state=%lu", (unsigned long)__entry->state)
+);
+
+/* This code will be removed after deprecation time exceeded (2.6.41) */
+#ifdef CONFIG_EVENT_POWER_TRACING_DEPRECATED
+
 /*
  * The power events are used for cpuidle & suspend (power_start, power_end)
  *  and for cpufreq (power_frequency)
@@ -75,6 +126,36 @@ TRACE_EVENT(power_end,
 
 );
 
+/* Deprecated dummy functions must be protected against multi-declartion */
+#ifndef _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED
+#define _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED
+
+enum {
+	POWER_NONE = 0,
+	POWER_CSTATE = 1,
+	POWER_PSTATE = 2,
+};
+#endif /* _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED */
+
+#else /* CONFIG_EVENT_POWER_TRACING_DEPRECATED */
+
+#ifndef _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED
+#define _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED
+enum {
+       POWER_NONE = 0,
+       POWER_CSTATE = 1,
+       POWER_PSTATE = 2,
+};
+
+/* These dummy declaration have to be ripped out when the deprecated
+   events get removed */
+static inline void trace_power_start(u64 type, u64 state, u64 cpuid) {};
+static inline void trace_power_end(u64 cpuid) {};
+static inline void trace_power_frequency(u64 type, u64 state, u64 cpuid) {};
+#endif /* _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED */
+
+#endif /* CONFIG_EVENT_POWER_TRACING_DEPRECATED */
+
 /*
  * The clock events are used for clock enable/disable and for
  *  clock rate change
@@ -153,7 +234,6 @@ DEFINE_EVENT(power_domain, power_domain_target,
 
 	TP_ARGS(name, state, cpu_id)
 );
-
 #endif /* _TRACE_POWER_H */
 
 /* This part must be outside protection */

include/trace/events/syscalls.h

@@ -40,6 +40,8 @@ TRACE_EVENT_FN(sys_enter,
 	syscall_regfunc, syscall_unregfunc
 );
 
+TRACE_EVENT_FLAGS(sys_enter, TRACE_EVENT_FL_CAP_ANY)
+
 TRACE_EVENT_FN(sys_exit,
 
 	TP_PROTO(struct pt_regs *regs, long ret),
@@ -62,6 +64,8 @@ TRACE_EVENT_FN(sys_exit,
 	syscall_regfunc, syscall_unregfunc
 );
 
+TRACE_EVENT_FLAGS(sys_exit, TRACE_EVENT_FL_CAP_ANY)
+
 #endif /* CONFIG_HAVE_SYSCALL_TRACEPOINTS */
 
 #endif /* _TRACE_EVENTS_SYSCALLS_H */

include/trace/ftrace.h

@@ -82,6 +82,10 @@
 	TRACE_EVENT(name, PARAMS(proto), PARAMS(args),			\
 		PARAMS(tstruct), PARAMS(assign), PARAMS(print))		\
 
+#undef TRACE_EVENT_FLAGS
+#define TRACE_EVENT_FLAGS(name, value)					\
+	__TRACE_EVENT_FLAGS(name, value)
+
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 
@@ -129,6 +133,9 @@
 #define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
 	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
 
+#undef TRACE_EVENT_FLAGS
+#define TRACE_EVENT_FLAGS(event, flag)
+
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 /*
@@ -289,13 +296,19 @@ static struct trace_event_functions ftrace_event_type_funcs_##call = {	\
 
 #undef __array
 #define __array(type, item, len)					\
-	BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);				\
-	ret = trace_define_field(event_call, #type "[" #len "]", #item,	\
+	do {								\
+		mutex_lock(&event_storage_mutex);			\
+		BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);			\
+		snprintf(event_storage, sizeof(event_storage),		\
+			 "%s[%d]", #type, len);				\
+		ret = trace_define_field(event_call, event_storage, #item, \
 				 offsetof(typeof(field), item),		\
 				 sizeof(field.item),			\
 				 is_signed_type(type), FILTER_OTHER);	\
-	if (ret)							\
-		return ret;
+		mutex_unlock(&event_storage_mutex);			\
+		if (ret)						\
+			return ret;					\
+	} while (0);
 
 #undef __dynamic_array
 #define __dynamic_array(type, item, len)				       \