Merge tag 'trace-v4.4' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracking updates from Steven Rostedt:
 "Most of the changes are clean ups and small fixes.  Some of them have
  stable tags to them.  I searched through my INBOX just as the merge
  window opened and found lots of patches to pull.  I ran them through
  all my tests and they were in linux-next for a few days.

  Features added this release:
  ----------------------------

   - Module globbing.  You can now filter function tracing to several
     modules.  # echo '*:mod:*snd*' > set_ftrace_filter (Dmitry Safonov)

   - Tracer specific options are now visible even when the tracer is not
     active.  It was rather annoying that you can only see and modify
     tracer options after enabling the tracer.  Now they are in the
     options/ directory even when the tracer is not active.  Although
     they are still only visible when the tracer is active in the
     trace_options file.

   - Trace options are now per instance (although some of the tracer
     specific options are global)

   - New tracefs file: set_event_pid.  If any pid is added to this file,
     then all events in the instance will filter out events that are not
     part of this pid.  sched_switch and sched_wakeup events handle next
     and the wakee pids"

* tag 'trace-v4.4' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (68 commits)
  tracefs: Fix refcount imbalance in start_creating()
  tracing: Put back comma for empty fields in boot string parsing
  tracing: Apply tracer specific options from kernel command line.
  tracing: Add some documentation about set_event_pid
  ring_buffer: Remove unneeded smp_wmb() before wakeup of reader benchmark
  tracing: Allow dumping traces without tracking trace started cpus
  ring_buffer: Fix more races when terminating the producer in the benchmark
  ring_buffer: Do no not complete benchmark reader too early
  tracing: Remove redundant TP_ARGS redefining
  tracing: Rename max_stack_lock to stack_trace_max_lock
  tracing: Allow arch-specific stack tracer
  recordmcount: arm64: Replace the ignored mcount call into nop
  recordmcount: Fix endianness handling bug for nop_mcount
  tracepoints: Fix documentation of RCU lockdep checks
  tracing: ftrace_event_is_function() can return boolean
  tracing: is_legal_op() can return boolean
  ring-buffer: rb_event_is_commit() can return boolean
  ring-buffer: rb_per_cpu_empty() can return boolean
  ring_buffer: ring_buffer_empty{cpu}() can return boolean
  ring-buffer: rb_is_reader_page() can return boolean
  ...

Documentation/trace/events.txt

@@ -288,6 +288,24 @@ prev_pid == 0
 # cat sched_wakeup/filter
 common_pid == 0
 
+5.4 PID filtering
+-----------------
+
+The set_event_pid file in the same directory as the top events directory
+exists, will filter all events from tracing any task that does not have the
+PID listed in the set_event_pid file.
+
+# cd /sys/kernel/debug/tracing
+# echo $$ > set_event_pid
+# echo 1 > events/enabled
+
+Will only trace events for the current task.
+
+To add more PIDs without losing the PIDs already included, use '>>'.
+
+# echo 123 244 1 >> set_event_pid
+
+
 6. Event triggers
 =================
 

Documentation/trace/ftrace.txt

@@ -204,6 +204,12 @@ of ftrace. Here is a list of some of the key files:
 
 	Have the function tracer only trace a single thread.
 
+  set_event_pid:
+
+	Have the events only trace a task with a PID listed in this file.
+	Note, sched_switch and sched_wake_up will also trace events
+	listed in this file.
+
   set_graph_function:
 
 	Set a "trigger" function where tracing should start
@@ -2437,6 +2443,23 @@ The following commands are supported:
 
    echo '!writeback*:mod:ext3' >> set_ftrace_filter
 
+  Mod command supports module globbing. Disable tracing for all
+  functions except a specific module:
+
+   echo '!*:mod:!ext3' >> set_ftrace_filter
+
+  Disable tracing for all modules, but still trace kernel:
+
+   echo '!*:mod:*' >> set_ftrace_filter
+
+  Enable filter only for kernel:
+
+   echo '*write*:mod:!*' >> set_ftrace_filter
+
+  Enable filter for module globbing:
+
+   echo '*write*:mod:*snd*' >> set_ftrace_filter
+
 - traceon/traceoff
   These commands turn tracing on and off when the specified
   functions are hit. The parameter determines how many times the

arch/x86/kernel/ftrace.c

@@ -556,6 +556,7 @@ void ftrace_replace_code(int enable)
 	run_sync();
 
 	report = "updating code";
+	count = 0;
 
 	for_ftrace_rec_iter(iter) {
 		rec = ftrace_rec_iter_record(iter);
@@ -563,11 +564,13 @@ void ftrace_replace_code(int enable)
 		ret = add_update(rec, enable);
 		if (ret)
 			goto remove_breakpoints;
+		count++;
 	}
 
 	run_sync();
 
 	report = "removing breakpoints";
+	count = 0;
 
 	for_ftrace_rec_iter(iter) {
 		rec = ftrace_rec_iter_record(iter);
@@ -575,6 +578,7 @@ void ftrace_replace_code(int enable)
 		ret = finish_update(rec, enable);
 		if (ret)
 			goto remove_breakpoints;
+		count++;
 	}
 
 	run_sync();

fs/tracefs/inode.c

@@ -340,8 +340,12 @@ static struct dentry *start_creating(const char *name, struct dentry *parent)
 		dput(dentry);
 		dentry = ERR_PTR(-EEXIST);
 	}
-	if (IS_ERR(dentry))
+
+	if (IS_ERR(dentry)) {
 		mutex_unlock(&parent->d_inode->i_mutex);
+		simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+	}
+
 	return dentry;
 }
 

include/linux/ftrace.h

@@ -263,7 +263,18 @@ static inline void ftrace_kill(void) { }
 #endif /* CONFIG_FUNCTION_TRACER */
 
 #ifdef CONFIG_STACK_TRACER
+
+#define STACK_TRACE_ENTRIES 500
+
+struct stack_trace;
+
+extern unsigned stack_trace_index[];
+extern struct stack_trace stack_trace_max;
+extern unsigned long stack_trace_max_size;
+extern arch_spinlock_t stack_trace_max_lock;
+
 extern int stack_tracer_enabled;
+void stack_trace_print(void);
 int
 stack_trace_sysctl(struct ctl_table *table, int write,
 		   void __user *buffer, size_t *lenp,

include/linux/ring_buffer.h

@@ -154,8 +154,8 @@ ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
 }
 #endif
 
-int ring_buffer_empty(struct ring_buffer *buffer);
-int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu);
+bool ring_buffer_empty(struct ring_buffer *buffer);
+bool ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu);
 
 void ring_buffer_record_disable(struct ring_buffer *buffer);
 void ring_buffer_record_enable(struct ring_buffer *buffer);

include/linux/trace_events.h

@@ -168,13 +168,12 @@ struct ring_buffer_event *
 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 *buffer,
-					struct ring_buffer_event *event,
-					unsigned long flags, int pc);
-void trace_buffer_unlock_commit(struct ring_buffer *buffer,
+void trace_buffer_unlock_commit(struct trace_array *tr,
+				struct ring_buffer *buffer,
 				struct ring_buffer_event *event,
 				unsigned long flags, int pc);
-void trace_buffer_unlock_commit_regs(struct ring_buffer *buffer,
+void trace_buffer_unlock_commit_regs(struct trace_array *tr,
+				     struct ring_buffer *buffer,
 				     struct ring_buffer_event *event,
 				     unsigned long flags, int pc,
 				     struct pt_regs *regs);
@@ -329,6 +328,7 @@ enum {
 	EVENT_FILE_FL_SOFT_DISABLED_BIT,
 	EVENT_FILE_FL_TRIGGER_MODE_BIT,
 	EVENT_FILE_FL_TRIGGER_COND_BIT,
+	EVENT_FILE_FL_PID_FILTER_BIT,
 };
 
 /*
@@ -342,6 +342,7 @@ enum {
  *                   tracepoint may be enabled)
  *  TRIGGER_MODE  - When set, invoke the triggers associated with the event
  *  TRIGGER_COND  - When set, one or more triggers has an associated filter
+ *  PID_FILTER    - When set, the event is filtered based on pid
  */
 enum {
 	EVENT_FILE_FL_ENABLED		= (1 << EVENT_FILE_FL_ENABLED_BIT),
@@ -352,6 +353,7 @@ enum {
 	EVENT_FILE_FL_SOFT_DISABLED	= (1 << EVENT_FILE_FL_SOFT_DISABLED_BIT),
 	EVENT_FILE_FL_TRIGGER_MODE	= (1 << EVENT_FILE_FL_TRIGGER_MODE_BIT),
 	EVENT_FILE_FL_TRIGGER_COND	= (1 << EVENT_FILE_FL_TRIGGER_COND_BIT),
+	EVENT_FILE_FL_PID_FILTER	= (1 << EVENT_FILE_FL_PID_FILTER_BIT),
 };
 
 struct trace_event_file {
@@ -430,6 +432,8 @@ extern enum event_trigger_type event_triggers_call(struct trace_event_file *file
 extern void event_triggers_post_call(struct trace_event_file *file,
 				     enum event_trigger_type tt);
 
+bool trace_event_ignore_this_pid(struct trace_event_file *trace_file);
+
 /**
  * trace_trigger_soft_disabled - do triggers and test if soft disabled
  * @file: The file pointer of the event to test
@@ -449,6 +453,8 @@ trace_trigger_soft_disabled(struct trace_event_file *file)
 			event_triggers_call(file, NULL);
 		if (eflags & EVENT_FILE_FL_SOFT_DISABLED)
 			return true;
+		if (eflags & EVENT_FILE_FL_PID_FILTER)
+			return trace_event_ignore_this_pid(file);
 	}
 	return false;
 }
@@ -508,7 +514,7 @@ event_trigger_unlock_commit(struct trace_event_file *file,
 	enum event_trigger_type tt = ETT_NONE;
 
 	if (!__event_trigger_test_discard(file, buffer, event, entry, &tt))
-		trace_buffer_unlock_commit(buffer, event, irq_flags, pc);
+		trace_buffer_unlock_commit(file->tr, buffer, event, irq_flags, pc);
 
 	if (tt)
 		event_triggers_post_call(file, tt);
@@ -540,7 +546,7 @@ event_trigger_unlock_commit_regs(struct trace_event_file *file,
 	enum event_trigger_type tt = ETT_NONE;
 
 	if (!__event_trigger_test_discard(file, buffer, event, entry, &tt))
-		trace_buffer_unlock_commit_regs(buffer, event,
+		trace_buffer_unlock_commit_regs(file->tr, buffer, event,
 						irq_flags, pc, regs);
 
 	if (tt)

include/linux/tracepoint.h

@@ -26,6 +26,7 @@ struct notifier_block;
 struct tracepoint_func {
 	void *func;
 	void *data;
+	int prio;
 };
 
 struct tracepoint {
@@ -42,9 +43,14 @@ struct trace_enum_map {
 	unsigned long		enum_value;
 };
 
+#define TRACEPOINT_DEFAULT_PRIO	10
+
 extern int
 tracepoint_probe_register(struct tracepoint *tp, void *probe, void *data);
 extern int
+tracepoint_probe_register_prio(struct tracepoint *tp, void *probe, void *data,
+			       int prio);
+extern int
 tracepoint_probe_unregister(struct tracepoint *tp, void *probe, void *data);
 extern void
 for_each_kernel_tracepoint(void (*fct)(struct tracepoint *tp, void *priv),
@@ -111,7 +117,18 @@ extern void syscall_unregfunc(void);
 #define TP_ARGS(args...)	args
 #define TP_CONDITION(args...)	args
 
-#ifdef CONFIG_TRACEPOINTS
+/*
+ * Individual subsystem my have a separate configuration to
+ * enable their tracepoints. By default, this file will create
+ * the tracepoints if CONFIG_TRACEPOINT is defined. If a subsystem
+ * wants to be able to disable its tracepoints from being created
+ * it can define NOTRACE before including the tracepoint headers.
+ */
+#if defined(CONFIG_TRACEPOINTS) && !defined(NOTRACE)
+#define TRACEPOINTS_ENABLED
+#endif
+
+#ifdef TRACEPOINTS_ENABLED
 
 /*
  * it_func[0] is never NULL because there is at least one element in the array
@@ -167,10 +184,11 @@ extern void syscall_unregfunc(void);
  * structure. Force alignment to the same alignment as the section start.
  *
  * When lockdep is enabled, we make sure to always do the RCU portions of
- * the tracepoint code, regardless of whether tracing is on or we match the
- * condition.  This lets us find RCU issues triggered with tracepoints even
- * when this tracepoint is off.  This code has no purpose other than poking
- * RCU a bit.
+ * the tracepoint code, regardless of whether tracing is on. However,
+ * don't check if the condition is false, due to interaction with idle
+ * instrumentation. This lets us find RCU issues triggered with tracepoints
+ * even when this tracepoint is off. This code has no purpose other than
+ * poking RCU a bit.
  */
 #define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \
 	extern struct tracepoint __tracepoint_##name;			\
@@ -196,6 +214,13 @@ extern void syscall_unregfunc(void);
 						(void *)probe, data);	\
 	}								\
 	static inline int						\
+	register_trace_prio_##name(void (*probe)(data_proto), void *data,\
+				   int prio)				\
+	{								\
+		return tracepoint_probe_register_prio(&__tracepoint_##name, \
+					      (void *)probe, data, prio); \
+	}								\
+	static inline int						\
 	unregister_trace_##name(void (*probe)(data_proto), void *data)	\
 	{								\
 		return tracepoint_probe_unregister(&__tracepoint_##name,\
@@ -234,7 +259,7 @@ extern void syscall_unregfunc(void);
 #define EXPORT_TRACEPOINT_SYMBOL(name)					\
 	EXPORT_SYMBOL(__tracepoint_##name)
 
-#else /* !CONFIG_TRACEPOINTS */
+#else /* !TRACEPOINTS_ENABLED */
 #define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \
 	static inline void trace_##name(proto)				\
 	{ }								\
@@ -266,7 +291,7 @@ extern void syscall_unregfunc(void);
 #define EXPORT_TRACEPOINT_SYMBOL_GPL(name)
 #define EXPORT_TRACEPOINT_SYMBOL(name)
 
-#endif /* CONFIG_TRACEPOINTS */
+#endif /* TRACEPOINTS_ENABLED */
 
 #ifdef CONFIG_TRACING
 /**

include/trace/define_trace.h

@@ -86,7 +86,7 @@
 #undef DECLARE_TRACE
 #define DECLARE_TRACE(name, proto, args)
 
-#ifdef CONFIG_EVENT_TRACING
+#ifdef TRACEPOINTS_ENABLED
 #include <trace/trace_events.h>
 #include <trace/perf.h>
 #endif

include/trace/events/gpio.h

@@ -1,6 +1,10 @@
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM gpio
 
+#ifndef CONFIG_TRACING_EVENTS_GPIO
+#define NOTRACE
+#endif
+
 #if !defined(_TRACE_GPIO_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_GPIO_H
 

include/trace/perf.h

@@ -1,261 +1,3 @@
-/*
- * Stage 4 of the trace events.
- *
- * Override the macros in <trace/trace_events.h> to include the following:
- *
- * For those macros defined with TRACE_EVENT:
- *
- * static struct trace_event_call event_<call>;
- *
- * static void trace_event_raw_event_<call>(void *__data, proto)
- * {
- *	struct trace_event_file *trace_file = __data;
- *	struct trace_event_call *event_call = trace_file->event_call;
- *	struct trace_event_data_offsets_<call> __maybe_unused __data_offsets;
- *	unsigned long eflags = trace_file->flags;
- *	enum event_trigger_type __tt = ETT_NONE;
- *	struct ring_buffer_event *event;
- *	struct trace_event_raw_<call> *entry; <-- defined in stage 1
- *	struct ring_buffer *buffer;
- *	unsigned long irq_flags;
- *	int __data_size;
- *	int pc;
- *
- *	if (!(eflags & EVENT_FILE_FL_TRIGGER_COND)) {
- *		if (eflags & EVENT_FILE_FL_TRIGGER_MODE)
- *			event_triggers_call(trace_file, NULL);
- *		if (eflags & EVENT_FILE_FL_SOFT_DISABLED)
- *			return;
- *	}
- *
- *	local_save_flags(irq_flags);
- *	pc = preempt_count();
- *
- *	__data_size = trace_event_get_offsets_<call>(&__data_offsets, args);
- *
- *	event = trace_event_buffer_lock_reserve(&buffer, trace_file,
- *				  event_<call>->event.type,
- *				  sizeof(*entry) + __data_size,
- *				  irq_flags, pc);
- *	if (!event)
- *		return;
- *	entry	= ring_buffer_event_data(event);
- *
- *	{ <assign>; }  <-- Here we assign the entries by the __field and
- *			   __array macros.
- *
- *	if (eflags & EVENT_FILE_FL_TRIGGER_COND)
- *		__tt = event_triggers_call(trace_file, entry);
- *
- *	if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT,
- *		     &trace_file->flags))
- *		ring_buffer_discard_commit(buffer, event);
- *	else if (!filter_check_discard(trace_file, entry, buffer, event))
- *		trace_buffer_unlock_commit(buffer, event, irq_flags, pc);
- *
- *	if (__tt)
- *		event_triggers_post_call(trace_file, __tt);
- * }
- *
- * static struct trace_event ftrace_event_type_<call> = {
- *	.trace			= trace_raw_output_<call>, <-- stage 2
- * };
- *
- * static char print_fmt_<call>[] = <TP_printk>;
- *
- * static struct trace_event_class __used event_class_<template> = {
- *	.system			= "<system>",
- *	.define_fields		= trace_event_define_fields_<call>,
- *	.fields			= LIST_HEAD_INIT(event_class_##call.fields),
- *	.raw_init		= trace_event_raw_init,
- *	.probe			= trace_event_raw_event_##call,
- *	.reg			= trace_event_reg,
- * };
- *
- * static struct trace_event_call event_<call> = {
- *	.class			= event_class_<template>,
- *	{
- *		.tp			= &__tracepoint_<call>,
- *	},
- *	.event			= &ftrace_event_type_<call>,
- *	.print_fmt		= print_fmt_<call>,
- *	.flags			= TRACE_EVENT_FL_TRACEPOINT,
- * };
- * // its only safe to use pointers when doing linker tricks to
- * // create an array.
- * static struct trace_event_call __used
- * __attribute__((section("_ftrace_events"))) *__event_<call> = &event_<call>;
- *
- */
-
-#ifdef CONFIG_PERF_EVENTS
-
-#define _TRACE_PERF_PROTO(call, proto)					\
-	static notrace void						\
-	perf_trace_##call(void *__data, proto);
-
-#define _TRACE_PERF_INIT(call)						\
-	.perf_probe		= perf_trace_##call,
-
-#else
-#define _TRACE_PERF_PROTO(call, proto)
-#define _TRACE_PERF_INIT(call)
-#endif /* CONFIG_PERF_EVENTS */
-
-#undef __entry
-#define __entry entry
-
-#undef __field
-#define __field(type, item)
-
-#undef __field_struct
-#define __field_struct(type, item)
-
-#undef __array
-#define __array(type, item, len)
-
-#undef __dynamic_array
-#define __dynamic_array(type, item, len)				\
-	__entry->__data_loc_##item = __data_offsets.item;
-
-#undef __string
-#define __string(item, src) __dynamic_array(char, item, -1)
-
-#undef __assign_str
-#define __assign_str(dst, src)						\
-	strcpy(__get_str(dst), (src) ? (const char *)(src) : "(null)");
-
-#undef __bitmask
-#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1)
-
-#undef __get_bitmask
-#define __get_bitmask(field) (char *)__get_dynamic_array(field)
-
-#undef __assign_bitmask
-#define __assign_bitmask(dst, src, nr_bits)					\
-	memcpy(__get_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits))
-
-#undef TP_fast_assign
-#define TP_fast_assign(args...) args
-
-#undef __perf_addr
-#define __perf_addr(a)	(a)
-
-#undef __perf_count
-#define __perf_count(c)	(c)
-
-#undef __perf_task
-#define __perf_task(t)	(t)
-
-#undef DECLARE_EVENT_CLASS
-#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
-									\
-static notrace void							\
-trace_event_raw_event_##call(void *__data, proto)			\
-{									\
-	struct trace_event_file *trace_file = __data;			\
-	struct trace_event_data_offsets_##call __maybe_unused __data_offsets;\
-	struct trace_event_buffer fbuffer;				\
-	struct trace_event_raw_##call *entry;				\
-	int __data_size;						\
-									\
-	if (trace_trigger_soft_disabled(trace_file))			\
-		return;							\
-									\
-	__data_size = trace_event_get_offsets_##call(&__data_offsets, args); \
-									\
-	entry = trace_event_buffer_reserve(&fbuffer, trace_file,	\
-				 sizeof(*entry) + __data_size);		\
-									\
-	if (!entry)							\
-		return;							\
-									\
-	tstruct								\
-									\
-	{ assign; }							\
-									\
-	trace_event_buffer_commit(&fbuffer);				\
-}
-/*
- * The ftrace_test_probe is compiled out, it is only here as a build time check
- * to make sure that if the tracepoint handling changes, the ftrace probe will
- * fail to compile unless it too is updated.
- */
-
-#undef DEFINE_EVENT
-#define DEFINE_EVENT(template, call, proto, args)			\
-static inline void ftrace_test_probe_##call(void)			\
-{									\
-	check_trace_callback_type_##call(trace_event_raw_event_##template); \
-}
-
-#undef DEFINE_EVENT_PRINT
-#define DEFINE_EVENT_PRINT(template, name, proto, args, print)
-
-#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
-
-#undef __entry
-#define __entry REC
-
-#undef __print_flags
-#undef __print_symbolic
-#undef __print_hex
-#undef __get_dynamic_array
-#undef __get_dynamic_array_len
-#undef __get_str
-#undef __get_bitmask
-#undef __print_array
-
-#undef TP_printk
-#define TP_printk(fmt, args...) "\"" fmt "\", "  __stringify(args)
-
-#undef DECLARE_EVENT_CLASS
-#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
-_TRACE_PERF_PROTO(call, PARAMS(proto));					\
-static char print_fmt_##call[] = print;					\
-static struct trace_event_class __used __refdata event_class_##call = { \
-	.system			= TRACE_SYSTEM_STRING,			\
-	.define_fields		= trace_event_define_fields_##call,	\
-	.fields			= LIST_HEAD_INIT(event_class_##call.fields),\
-	.raw_init		= trace_event_raw_init,			\
-	.probe			= trace_event_raw_event_##call,		\
-	.reg			= trace_event_reg,			\
-	_TRACE_PERF_INIT(call)						\
-};
-
-#undef DEFINE_EVENT
-#define DEFINE_EVENT(template, call, proto, args)			\
-									\
-static struct trace_event_call __used event_##call = {			\
-	.class			= &event_class_##template,		\
-	{								\
-		.tp			= &__tracepoint_##call,		\
-	},								\
-	.event.funcs		= &trace_event_type_funcs_##template,	\
-	.print_fmt		= print_fmt_##template,			\
-	.flags			= TRACE_EVENT_FL_TRACEPOINT,		\
-};									\
-static struct trace_event_call __used					\
-__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
-
-#undef DEFINE_EVENT_PRINT
-#define DEFINE_EVENT_PRINT(template, call, proto, args, print)		\
-									\
-static char print_fmt_##call[] = print;					\
-									\
-static struct trace_event_call __used event_##call = {			\
-	.class			= &event_class_##template,		\
-	{								\
-		.tp			= &__tracepoint_##call,		\
-	},								\
-	.event.funcs		= &trace_event_type_funcs_##call,	\
-	.print_fmt		= print_fmt_##call,			\
-	.flags			= TRACE_EVENT_FL_TRACEPOINT,		\
-};									\
-static struct trace_event_call __used					\
-__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
-
-#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 #undef TRACE_SYSTEM_VAR
 

include/trace/trace_events.h

@@ -506,3 +506,261 @@ static inline notrace int trace_event_get_offsets_##call(		\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
+/*
+ * Stage 4 of the trace events.
+ *
+ * Override the macros in <trace/trace_events.h> to include the following:
+ *
+ * For those macros defined with TRACE_EVENT:
+ *
+ * static struct trace_event_call event_<call>;
+ *
+ * static void trace_event_raw_event_<call>(void *__data, proto)
+ * {
+ *	struct trace_event_file *trace_file = __data;
+ *	struct trace_event_call *event_call = trace_file->event_call;
+ *	struct trace_event_data_offsets_<call> __maybe_unused __data_offsets;
+ *	unsigned long eflags = trace_file->flags;
+ *	enum event_trigger_type __tt = ETT_NONE;
+ *	struct ring_buffer_event *event;
+ *	struct trace_event_raw_<call> *entry; <-- defined in stage 1
+ *	struct ring_buffer *buffer;
+ *	unsigned long irq_flags;
+ *	int __data_size;
+ *	int pc;
+ *
+ *	if (!(eflags & EVENT_FILE_FL_TRIGGER_COND)) {
+ *		if (eflags & EVENT_FILE_FL_TRIGGER_MODE)
+ *			event_triggers_call(trace_file, NULL);
+ *		if (eflags & EVENT_FILE_FL_SOFT_DISABLED)
+ *			return;
+ *	}
+ *
+ *	local_save_flags(irq_flags);
+ *	pc = preempt_count();
+ *
+ *	__data_size = trace_event_get_offsets_<call>(&__data_offsets, args);
+ *
+ *	event = trace_event_buffer_lock_reserve(&buffer, trace_file,
+ *				  event_<call>->event.type,
+ *				  sizeof(*entry) + __data_size,
+ *				  irq_flags, pc);
+ *	if (!event)
+ *		return;
+ *	entry	= ring_buffer_event_data(event);
+ *
+ *	{ <assign>; }  <-- Here we assign the entries by the __field and
+ *			   __array macros.
+ *
+ *	if (eflags & EVENT_FILE_FL_TRIGGER_COND)
+ *		__tt = event_triggers_call(trace_file, entry);
+ *
+ *	if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT,
+ *		     &trace_file->flags))
+ *		ring_buffer_discard_commit(buffer, event);
+ *	else if (!filter_check_discard(trace_file, entry, buffer, event))
+ *		trace_buffer_unlock_commit(buffer, event, irq_flags, pc);
+ *
+ *	if (__tt)
+ *		event_triggers_post_call(trace_file, __tt);
+ * }
+ *
+ * static struct trace_event ftrace_event_type_<call> = {
+ *	.trace			= trace_raw_output_<call>, <-- stage 2
+ * };
+ *
+ * static char print_fmt_<call>[] = <TP_printk>;
+ *
+ * static struct trace_event_class __used event_class_<template> = {
+ *	.system			= "<system>",
+ *	.define_fields		= trace_event_define_fields_<call>,
+ *	.fields			= LIST_HEAD_INIT(event_class_##call.fields),
+ *	.raw_init		= trace_event_raw_init,
+ *	.probe			= trace_event_raw_event_##call,
+ *	.reg			= trace_event_reg,
+ * };
+ *
+ * static struct trace_event_call event_<call> = {
+ *	.class			= event_class_<template>,
+ *	{
+ *		.tp			= &__tracepoint_<call>,
+ *	},
+ *	.event			= &ftrace_event_type_<call>,
+ *	.print_fmt		= print_fmt_<call>,
+ *	.flags			= TRACE_EVENT_FL_TRACEPOINT,
+ * };
+ * // its only safe to use pointers when doing linker tricks to
+ * // create an array.
+ * static struct trace_event_call __used
+ * __attribute__((section("_ftrace_events"))) *__event_<call> = &event_<call>;
+ *
+ */
+
+#ifdef CONFIG_PERF_EVENTS
+
+#define _TRACE_PERF_PROTO(call, proto)					\
+	static notrace void						\
+	perf_trace_##call(void *__data, proto);
+
+#define _TRACE_PERF_INIT(call)						\
+	.perf_probe		= perf_trace_##call,
+
+#else
+#define _TRACE_PERF_PROTO(call, proto)
+#define _TRACE_PERF_INIT(call)
+#endif /* CONFIG_PERF_EVENTS */
+
+#undef __entry
+#define __entry entry
+
+#undef __field
+#define __field(type, item)
+
+#undef __field_struct
+#define __field_struct(type, item)
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)				\
+	__entry->__data_loc_##item = __data_offsets.item;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef __assign_str
+#define __assign_str(dst, src)						\
+	strcpy(__get_str(dst), (src) ? (const char *)(src) : "(null)");
+
+#undef __bitmask
+#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1)
+
+#undef __get_bitmask
+#define __get_bitmask(field) (char *)__get_dynamic_array(field)
+
+#undef __assign_bitmask
+#define __assign_bitmask(dst, src, nr_bits)					\
+	memcpy(__get_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits))
+
+#undef TP_fast_assign
+#define TP_fast_assign(args...) args
+
+#undef __perf_addr
+#define __perf_addr(a)	(a)
+
+#undef __perf_count
+#define __perf_count(c)	(c)
+
+#undef __perf_task
+#define __perf_task(t)	(t)
+
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
+									\
+static notrace void							\
+trace_event_raw_event_##call(void *__data, proto)			\
+{									\
+	struct trace_event_file *trace_file = __data;			\
+	struct trace_event_data_offsets_##call __maybe_unused __data_offsets;\
+	struct trace_event_buffer fbuffer;				\
+	struct trace_event_raw_##call *entry;				\
+	int __data_size;						\
+									\
+	if (trace_trigger_soft_disabled(trace_file))			\
+		return;							\
+									\
+	__data_size = trace_event_get_offsets_##call(&__data_offsets, args); \
+									\
+	entry = trace_event_buffer_reserve(&fbuffer, trace_file,	\
+				 sizeof(*entry) + __data_size);		\
+									\
+	if (!entry)							\
+		return;							\
+									\
+	tstruct								\
+									\
+	{ assign; }							\
+									\
+	trace_event_buffer_commit(&fbuffer);				\
+}
+/*
+ * The ftrace_test_probe is compiled out, it is only here as a build time check
+ * to make sure that if the tracepoint handling changes, the ftrace probe will
+ * fail to compile unless it too is updated.
+ */
+
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, call, proto, args)			\
+static inline void ftrace_test_probe_##call(void)			\
+{									\
+	check_trace_callback_type_##call(trace_event_raw_event_##template); \
+}
+
+#undef DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#undef __entry
+#define __entry REC
+
+#undef __print_flags
+#undef __print_symbolic
+#undef __print_hex
+#undef __get_dynamic_array
+#undef __get_dynamic_array_len
+#undef __get_str
+#undef __get_bitmask
+#undef __print_array
+
+#undef TP_printk
+#define TP_printk(fmt, args...) "\"" fmt "\", "  __stringify(args)
+
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
+_TRACE_PERF_PROTO(call, PARAMS(proto));					\
+static char print_fmt_##call[] = print;					\
+static struct trace_event_class __used __refdata event_class_##call = { \
+	.system			= TRACE_SYSTEM_STRING,			\
+	.define_fields		= trace_event_define_fields_##call,	\
+	.fields			= LIST_HEAD_INIT(event_class_##call.fields),\
+	.raw_init		= trace_event_raw_init,			\
+	.probe			= trace_event_raw_event_##call,		\
+	.reg			= trace_event_reg,			\
+	_TRACE_PERF_INIT(call)						\
+};
+
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, call, proto, args)			\
+									\
+static struct trace_event_call __used event_##call = {			\
+	.class			= &event_class_##template,		\
+	{								\
+		.tp			= &__tracepoint_##call,		\
+	},								\
+	.event.funcs		= &trace_event_type_funcs_##template,	\
+	.print_fmt		= print_fmt_##template,			\
+	.flags			= TRACE_EVENT_FL_TRACEPOINT,		\
+};									\
+static struct trace_event_call __used					\
+__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
+
+#undef DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, call, proto, args, print)		\
+									\
+static char print_fmt_##call[] = print;					\
+									\
+static struct trace_event_call __used event_##call = {			\
+	.class			= &event_class_##template,		\
+	{								\
+		.tp			= &__tracepoint_##call,		\
+	},								\
+	.event.funcs		= &trace_event_type_funcs_##call,	\
+	.print_fmt		= print_fmt_##call,			\
+	.flags			= TRACE_EVENT_FL_TRACEPOINT,		\
+};									\
+static struct trace_event_call __used					\
+__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)

kernel/trace/Kconfig

@@ -635,6 +635,13 @@ config TRACE_ENUM_MAP_FILE
 
 	If unsure, say N
 
+config TRACING_EVENTS_GPIO
+	bool "Trace gpio events"
+	depends on GPIOLIB
+	default y
+	help
+	  Enable tracing events for gpio subsystem
+
 endif # FTRACE
 
 endif # TRACING_SUPPORT

kernel/trace/blktrace.c

@@ -103,7 +103,7 @@ record_it:
 		memcpy((void *) t + sizeof(*t), data, len);
 
 		if (blk_tracer)
-			trace_buffer_unlock_commit(buffer, event, 0, pc);
+			trace_buffer_unlock_commit(blk_tr, buffer, event, 0, pc);
 	}
 }
 
@@ -278,7 +278,7 @@ record_it:
 			memcpy((void *) t + sizeof(*t), pdu_data, pdu_len);
 
 		if (blk_tracer) {
-			trace_buffer_unlock_commit(buffer, event, 0, pc);
+			trace_buffer_unlock_commit(blk_tr, buffer, event, 0, pc);
 			return;
 		}
 	}
@@ -1340,6 +1340,7 @@ static const struct {
 static enum print_line_t print_one_line(struct trace_iterator *iter,
 					bool classic)
 {
+	struct trace_array *tr = iter->tr;
 	struct trace_seq *s = &iter->seq;
 	const struct blk_io_trace *t;
 	u16 what;
@@ -1348,7 +1349,7 @@ static enum print_line_t print_one_line(struct trace_iterator *iter,
 
 	t	   = te_blk_io_trace(iter->ent);
 	what	   = t->action & ((1 << BLK_TC_SHIFT) - 1);
-	long_act   = !!(trace_flags & TRACE_ITER_VERBOSE);
+	long_act   = !!(tr->trace_flags & TRACE_ITER_VERBOSE);
 	log_action = classic ? &blk_log_action_classic : &blk_log_action;
 
 	if (t->action == BLK_TN_MESSAGE) {
@@ -1410,9 +1411,9 @@ blk_tracer_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 	/* don't output context-info for blk_classic output */
 	if (bit == TRACE_BLK_OPT_CLASSIC) {
 		if (set)
-			trace_flags &= ~TRACE_ITER_CONTEXT_INFO;
+			tr->trace_flags &= ~TRACE_ITER_CONTEXT_INFO;
 		else
-			trace_flags |= TRACE_ITER_CONTEXT_INFO;
+			tr->trace_flags |= TRACE_ITER_CONTEXT_INFO;
 	}
 	return 0;
 }

kernel/trace/ftrace.c

@@ -243,6 +243,11 @@ static void ftrace_sync_ipi(void *data)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 static void update_function_graph_func(void);
+
+/* Both enabled by default (can be cleared by function_graph tracer flags */
+static bool fgraph_sleep_time = true;
+static bool fgraph_graph_time = true;
+
 #else
 static inline void update_function_graph_func(void) { }
 #endif
@@ -917,7 +922,7 @@ static void profile_graph_return(struct ftrace_graph_ret *trace)
 
 	calltime = trace->rettime - trace->calltime;
 
-	if (!(trace_flags & TRACE_ITER_GRAPH_TIME)) {
+	if (!fgraph_graph_time) {
 		int index;
 
 		index = trace->depth;
@@ -3420,27 +3425,35 @@ ftrace_notrace_open(struct inode *inode, struct file *file)
 				 inode, file);
 }
 
-static int ftrace_match(char *str, char *regex, int len, int type)
+/* Type for quick search ftrace basic regexes (globs) from filter_parse_regex */
+struct ftrace_glob {
+	char *search;
+	unsigned len;
+	int type;
+};
+
+static int ftrace_match(char *str, struct ftrace_glob *g)
 {
 	int matched = 0;
 	int slen;
 
-	switch (type) {
+	switch (g->type) {
 	case MATCH_FULL:
-		if (strcmp(str, regex) == 0)
+		if (strcmp(str, g->search) == 0)
 			matched = 1;
 		break;
 	case MATCH_FRONT_ONLY:
-		if (strncmp(str, regex, len) == 0)
+		if (strncmp(str, g->search, g->len) == 0)
 			matched = 1;
 		break;
 	case MATCH_MIDDLE_ONLY:
-		if (strstr(str, regex))
+		if (strstr(str, g->search))
 			matched = 1;
 		break;
 	case MATCH_END_ONLY:
 		slen = strlen(str);
-		if (slen >= len && memcmp(str + slen - len, regex, len) == 0)
+		if (slen >= g->len &&
+		    memcmp(str + slen - g->len, g->search, g->len) == 0)
 			matched = 1;
 		break;
 	}
@@ -3449,13 +3462,13 @@ static int ftrace_match(char *str, char *regex, int len, int type)
 }
 
 static int
-enter_record(struct ftrace_hash *hash, struct dyn_ftrace *rec, int not)
+enter_record(struct ftrace_hash *hash, struct dyn_ftrace *rec, int clear_filter)
 {
 	struct ftrace_func_entry *entry;
 	int ret = 0;
 
 	entry = ftrace_lookup_ip(hash, rec->ip);
-	if (not) {
+	if (clear_filter) {
 		/* Do nothing if it doesn't exist */
 		if (!entry)
 			return 0;
@@ -3472,42 +3485,68 @@ enter_record(struct ftrace_hash *hash, struct dyn_ftrace *rec, int not)
 }
 
 static int
-ftrace_match_record(struct dyn_ftrace *rec, char *mod,
-		    char *regex, int len, int type)
+ftrace_match_record(struct dyn_ftrace *rec, struct ftrace_glob *func_g,
+		struct ftrace_glob *mod_g, int exclude_mod)
 {
 	char str[KSYM_SYMBOL_LEN];
 	char *modname;
 
 	kallsyms_lookup(rec->ip, NULL, NULL, &modname, str);
 
-	if (mod) {
-		/* module lookup requires matching the module */
-		if (!modname || strcmp(modname, mod))
+	if (mod_g) {
+		int mod_matches = (modname) ? ftrace_match(modname, mod_g) : 0;
+
+		/* blank module name to match all modules */
+		if (!mod_g->len) {
+			/* blank module globbing: modname xor exclude_mod */
+			if ((!exclude_mod) != (!modname))
+				goto func_match;
+			return 0;
+		}
+
+		/* not matching the module */
+		if (!modname || !mod_matches) {
+			if (exclude_mod)
+				goto func_match;
+			else
+				return 0;
+		}
+
+		if (mod_matches && exclude_mod)
 			return 0;
 
+func_match:
 		/* blank search means to match all funcs in the mod */
-		if (!len)
+		if (!func_g->len)
 			return 1;
 	}
 
-	return ftrace_match(str, regex, len, type);
+	return ftrace_match(str, func_g);
 }
 
 static int
-match_records(struct ftrace_hash *hash, char *buff,
-	      int len, char *mod, int not)
+match_records(struct ftrace_hash *hash, char *func, int len, char *mod)
 {
-	unsigned search_len = 0;
 	struct ftrace_page *pg;
 	struct dyn_ftrace *rec;
-	int type = MATCH_FULL;
-	char *search = buff;
+	struct ftrace_glob func_g = { .type = MATCH_FULL };
+	struct ftrace_glob mod_g = { .type = MATCH_FULL };
+	struct ftrace_glob *mod_match = (mod) ? &mod_g : NULL;
+	int exclude_mod = 0;
 	int found = 0;
 	int ret;
+	int clear_filter;
+
+	if (func) {
+		func_g.type = filter_parse_regex(func, len, &func_g.search,
+						 &clear_filter);
+		func_g.len = strlen(func_g.search);
+	}
 
-	if (len) {
-		type = filter_parse_regex(buff, len, &search, &not);
-		search_len = strlen(search);
+	if (mod) {
+		mod_g.type = filter_parse_regex(mod, strlen(mod),
+				&mod_g.search, &exclude_mod);
+		mod_g.len = strlen(mod_g.search);
 	}
 
 	mutex_lock(&ftrace_lock);
@@ -3516,8 +3555,8 @@ match_records(struct ftrace_hash *hash, char *buff,
 		goto out_unlock;
 
 	do_for_each_ftrace_rec(pg, rec) {
-		if (ftrace_match_record(rec, mod, search, search_len, type)) {
-			ret = enter_record(hash, rec, not);
+		if (ftrace_match_record(rec, &func_g, mod_match, exclude_mod)) {
+			ret = enter_record(hash, rec, clear_filter);
 			if (ret < 0) {
 				found = ret;
 				goto out_unlock;
@@ -3534,26 +3573,9 @@ match_records(struct ftrace_hash *hash, char *buff,
 static int
 ftrace_match_records(struct ftrace_hash *hash, char *buff, int len)
 {
-	return match_records(hash, buff, len, NULL, 0);
+	return match_records(hash, buff, len, NULL);
 }
 
-static int
-ftrace_match_module_records(struct ftrace_hash *hash, char *buff, char *mod)
-{
-	int not = 0;
-
-	/* blank or '*' mean the same */
-	if (strcmp(buff, "*") == 0)
-		buff[0] = 0;
-
-	/* handle the case of 'dont filter this module' */
-	if (strcmp(buff, "!") == 0 || strcmp(buff, "!*") == 0) {
-		buff[0] = 0;
-		not = 1;
-	}
-
-	return match_records(hash, buff, strlen(buff), mod, not);
-}
 
 /*
  * We register the module command as a template to show others how
@@ -3562,10 +3584,9 @@ ftrace_match_module_records(struct ftrace_hash *hash, char *buff, char *mod)
 
 static int
 ftrace_mod_callback(struct ftrace_hash *hash,
-		    char *func, char *cmd, char *param, int enable)
+		    char *func, char *cmd, char *module, int enable)
 {
-	char *mod;
-	int ret = -EINVAL;
+	int ret;
 
 	/*
 	 * cmd == 'mod' because we only registered this func
@@ -3574,21 +3595,11 @@ ftrace_mod_callback(struct ftrace_hash *hash,
 	 * you can tell which command was used by the cmd
 	 * parameter.
 	 */
-
-	/* we must have a module name */
-	if (!param)
-		return ret;
-
-	mod = strsep(&param, ":");
-	if (!strlen(mod))
-		return ret;
-
-	ret = ftrace_match_module_records(hash, func, mod);
+	ret = match_records(hash, func, strlen(func), module);
 	if (!ret)
-		ret = -EINVAL;
+		return -EINVAL;
 	if (ret < 0)
 		return ret;
-
 	return 0;
 }
 
@@ -3699,19 +3710,20 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 {
 	struct ftrace_ops_hash old_hash_ops;
 	struct ftrace_func_probe *entry;
+	struct ftrace_glob func_g;
 	struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash;
 	struct ftrace_hash *old_hash = *orig_hash;
 	struct ftrace_hash *hash;
 	struct ftrace_page *pg;
 	struct dyn_ftrace *rec;
-	int type, len, not;
+	int not;
 	unsigned long key;
 	int count = 0;
-	char *search;
 	int ret;
 
-	type = filter_parse_regex(glob, strlen(glob), &search, &not);
-	len = strlen(search);
+	func_g.type = filter_parse_regex(glob, strlen(glob),
+			&func_g.search, &not);
+	func_g.len = strlen(func_g.search);
 
 	/* we do not support '!' for function probes */
 	if (WARN_ON(not))
@@ -3738,7 +3750,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 
 	do_for_each_ftrace_rec(pg, rec) {
 
-		if (!ftrace_match_record(rec, NULL, search, len, type))
+		if (!ftrace_match_record(rec, &func_g, NULL, 0))
 			continue;
 
 		entry = kmalloc(sizeof(*entry), GFP_KERNEL);
@@ -3811,24 +3823,24 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	struct ftrace_func_entry *rec_entry;
 	struct ftrace_func_probe *entry;
 	struct ftrace_func_probe *p;
+	struct ftrace_glob func_g;
 	struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash;
 	struct ftrace_hash *old_hash = *orig_hash;
 	struct list_head free_list;
 	struct ftrace_hash *hash;
 	struct hlist_node *tmp;
 	char str[KSYM_SYMBOL_LEN];
-	int type = MATCH_FULL;
-	int i, len = 0;
-	char *search;
-	int ret;
+	int i, ret;
 
 	if (glob && (strcmp(glob, "*") == 0 || !strlen(glob)))
-		glob = NULL;
+		func_g.search = NULL;
 	else if (glob) {
 		int not;
 
-		type = filter_parse_regex(glob, strlen(glob), &search, &not);
-		len = strlen(search);
+		func_g.type = filter_parse_regex(glob, strlen(glob),
+						 &func_g.search, &not);
+		func_g.len = strlen(func_g.search);
+		func_g.search = glob;
 
 		/* we do not support '!' for function probes */
 		if (WARN_ON(not))
@@ -3857,10 +3869,10 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 				continue;
 
 			/* do this last, since it is the most expensive */
-			if (glob) {
+			if (func_g.search) {
 				kallsyms_lookup(entry->ip, NULL, NULL,
 						NULL, str);
-				if (!ftrace_match(str, glob, len, type))
+				if (!ftrace_match(str, &func_g))
 					continue;
 			}
 
@@ -3889,7 +3901,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 		ftrace_free_entry(entry);
 	}
 	mutex_unlock(&ftrace_lock);
-		
+
  out_unlock:
 	mutex_unlock(&trace_probe_ops.func_hash->regex_lock);
 	free_ftrace_hash(hash);
@@ -4605,21 +4617,21 @@ ftrace_graph_release(struct inode *inode, struct file *file)
 static int
 ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer)
 {
+	struct ftrace_glob func_g;
 	struct dyn_ftrace *rec;
 	struct ftrace_page *pg;
-	int search_len;
 	int fail = 1;
-	int type, not;
-	char *search;
+	int not;
 	bool exists;
 	int i;
 
 	/* decode regex */
-	type = filter_parse_regex(buffer, strlen(buffer), &search, &not);
+	func_g.type = filter_parse_regex(buffer, strlen(buffer),
+					 &func_g.search, &not);
 	if (!not && *idx >= size)
 		return -EBUSY;
 
-	search_len = strlen(search);
+	func_g.len = strlen(func_g.search);
 
 	mutex_lock(&ftrace_lock);
 
@@ -4630,7 +4642,7 @@ ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer)
 
 	do_for_each_ftrace_rec(pg, rec) {
 
-		if (ftrace_match_record(rec, NULL, search, search_len, type)) {
+		if (ftrace_match_record(rec, &func_g, NULL, 0)) {
 			/* if it is in the array */
 			exists = false;
 			for (i = 0; i < *idx; i++) {
@@ -4783,17 +4795,6 @@ static int ftrace_cmp_ips(const void *a, const void *b)
 	return 0;
 }
 
-static void ftrace_swap_ips(void *a, void *b, int size)
-{
-	unsigned long *ipa = a;
-	unsigned long *ipb = b;
-	unsigned long t;
-
-	t = *ipa;
-	*ipa = *ipb;
-	*ipb = t;
-}
-
 static int ftrace_process_locs(struct module *mod,
 			       unsigned long *start,
 			       unsigned long *end)
@@ -4813,7 +4814,7 @@ static int ftrace_process_locs(struct module *mod,
 		return 0;
 
 	sort(start, count, sizeof(*start),
-	     ftrace_cmp_ips, ftrace_swap_ips);
+	     ftrace_cmp_ips, NULL);
 
 	start_pg = ftrace_allocate_pages(count);
 	if (!start_pg)
@@ -5639,6 +5640,16 @@ static struct ftrace_ops graph_ops = {
 	ASSIGN_OPS_HASH(graph_ops, &global_ops.local_hash)
 };
 
+void ftrace_graph_sleep_time_control(bool enable)
+{
+	fgraph_sleep_time = enable;
+}
+
+void ftrace_graph_graph_time_control(bool enable)
+{
+	fgraph_graph_time = enable;
+}
+
 int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
 {
 	return 0;
@@ -5707,7 +5718,7 @@ ftrace_graph_probe_sched_switch(void *ignore, bool preempt,
 	 * Does the user want to count the time a function was asleep.
 	 * If so, do not update the time stamps.
 	 */
-	if (trace_flags & TRACE_ITER_SLEEP_TIME)
+	if (fgraph_sleep_time)
 		return;
 
 	timestamp = trace_clock_local();

kernel/trace/ring_buffer.c

@@ -829,7 +829,7 @@ rb_is_head_page(struct ring_buffer_per_cpu *cpu_buffer,
  * writer is ever on it, the previous pointer never points
  * back to the reader page.
  */
-static int rb_is_reader_page(struct buffer_page *page)
+static bool rb_is_reader_page(struct buffer_page *page)
 {
 	struct list_head *list = page->list.prev;
 
@@ -2270,7 +2270,7 @@ rb_add_time_stamp(struct ring_buffer_event *event, u64 delta)
 	return skip_time_extend(event);
 }
 
-static inline int rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
+static inline bool rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
 				     struct ring_buffer_event *event);
 
 /**
@@ -2498,7 +2498,7 @@ static inline void rb_event_discard(struct ring_buffer_event *event)
 		event->time_delta = 1;
 }
 
-static inline int
+static inline bool
 rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
 		   struct ring_buffer_event *event)
 {
@@ -3039,7 +3039,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_write);
 
-static int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
+static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	struct buffer_page *reader = cpu_buffer->reader_page;
 	struct buffer_page *head = rb_set_head_page(cpu_buffer);
@@ -3047,7 +3047,7 @@ static int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
 
 	/* In case of error, head will be NULL */
 	if (unlikely(!head))
-		return 1;
+		return true;
 
 	return reader->read == rb_page_commit(reader) &&
 		(commit == reader ||
@@ -4267,7 +4267,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_reset);
  * rind_buffer_empty - is the ring buffer empty?
  * @buffer: The ring buffer to test
  */
-int ring_buffer_empty(struct ring_buffer *buffer)
+bool ring_buffer_empty(struct ring_buffer *buffer)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	unsigned long flags;
@@ -4285,10 +4285,10 @@ int ring_buffer_empty(struct ring_buffer *buffer)
 		local_irq_restore(flags);
 
 		if (!ret)
-			return 0;
+			return false;
 	}
 
-	return 1;
+	return true;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_empty);
 
@@ -4297,7 +4297,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_empty);
  * @buffer: The ring buffer
  * @cpu: The CPU buffer to test
  */
-int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu)
+bool ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	unsigned long flags;
@@ -4305,7 +4305,7 @@ int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu)
 	int ret;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
-		return 1;
+		return true;
 
 	cpu_buffer = buffer->buffers[cpu];
 	local_irq_save(flags);

kernel/trace/ring_buffer_benchmark.c

@@ -24,8 +24,8 @@ struct rb_page {
 static int wakeup_interval = 100;
 
 static int reader_finish;
-static struct completion read_start;
-static struct completion read_done;
+static DECLARE_COMPLETION(read_start);
+static DECLARE_COMPLETION(read_done);
 
 static struct ring_buffer *buffer;
 static struct task_struct *producer;
@@ -60,12 +60,12 @@ MODULE_PARM_DESC(consumer_fifo, "fifo prio for consumer");
 
 static int read_events;
 
-static int kill_test;
+static int test_error;
 
-#define KILL_TEST()				\
+#define TEST_ERROR()				\
 	do {					\
-		if (!kill_test) {		\
-			kill_test = 1;		\
+		if (!test_error) {		\
+			test_error = 1;		\
 			WARN_ON(1);		\
 		}				\
 	} while (0)
@@ -75,6 +75,11 @@ enum event_status {
 	EVENT_DROPPED,
 };
 
+static bool break_test(void)
+{
+	return test_error || kthread_should_stop();
+}
+
 static enum event_status read_event(int cpu)
 {
 	struct ring_buffer_event *event;
@@ -87,7 +92,7 @@ static enum event_status read_event(int cpu)
 
 	entry = ring_buffer_event_data(event);
 	if (*entry != cpu) {
-		KILL_TEST();
+		TEST_ERROR();
 		return EVENT_DROPPED;
 	}
 
@@ -115,10 +120,10 @@ static enum event_status read_page(int cpu)
 		rpage = bpage;
 		/* The commit may have missed event flags set, clear them */
 		commit = local_read(&rpage->commit) & 0xfffff;
-		for (i = 0; i < commit && !kill_test; i += inc) {
+		for (i = 0; i < commit && !test_error ; i += inc) {
 
 			if (i >= (PAGE_SIZE - offsetof(struct rb_page, data))) {
-				KILL_TEST();
+				TEST_ERROR();
 				break;
 			}
 
@@ -128,7 +133,7 @@ static enum event_status read_page(int cpu)
 			case RINGBUF_TYPE_PADDING:
 				/* failed writes may be discarded events */
 				if (!event->time_delta)
-					KILL_TEST();
+					TEST_ERROR();
 				inc = event->array[0] + 4;
 				break;
 			case RINGBUF_TYPE_TIME_EXTEND:
@@ -137,12 +142,12 @@ static enum event_status read_page(int cpu)
 			case 0:
 				entry = ring_buffer_event_data(event);
 				if (*entry != cpu) {
-					KILL_TEST();
+					TEST_ERROR();
 					break;
 				}
 				read++;
 				if (!event->array[0]) {
-					KILL_TEST();
+					TEST_ERROR();
 					break;
 				}
 				inc = event->array[0] + 4;
@@ -150,17 +155,17 @@ static enum event_status read_page(int cpu)
 			default:
 				entry = ring_buffer_event_data(event);
 				if (*entry != cpu) {
-					KILL_TEST();
+					TEST_ERROR();
 					break;
 				}
 				read++;
 				inc = ((event->type_len + 1) * 4);
 			}
-			if (kill_test)
+			if (test_error)
 				break;
 
 			if (inc <= 0) {
-				KILL_TEST();
+				TEST_ERROR();
 				break;
 			}
 		}
@@ -178,10 +183,14 @@ static void ring_buffer_consumer(void)
 	read_events ^= 1;
 
 	read = 0;
-	while (!reader_finish && !kill_test) {
-		int found;
+	/*
+	 * Continue running until the producer specifically asks to stop
+	 * and is ready for the completion.
+	 */
+	while (!READ_ONCE(reader_finish)) {
+		int found = 1;
 
-		do {
+		while (found && !test_error) {
 			int cpu;
 
 			found = 0;
@@ -193,19 +202,25 @@ static void ring_buffer_consumer(void)
 				else
 					stat = read_page(cpu);
 
-				if (kill_test)
+				if (test_error)
 					break;
+
 				if (stat == EVENT_FOUND)
 					found = 1;
+
 			}
-		} while (found && !kill_test);
+		}
 
+		/* Wait till the producer wakes us up when there is more data
+		 * available or when the producer wants us to finish reading.
+		 */
 		set_current_state(TASK_INTERRUPTIBLE);
 		if (reader_finish)
 			break;
 
 		schedule();
 	}
+	__set_current_state(TASK_RUNNING);
 	reader_finish = 0;
 	complete(&read_done);
 }
@@ -263,10 +278,7 @@ static void ring_buffer_producer(void)
 		if (cnt % wakeup_interval)
 			cond_resched();
 #endif
-		if (kthread_should_stop())
-			kill_test = 1;
-
-	} while (ktime_before(end_time, timeout) && !kill_test);
+	} while (ktime_before(end_time, timeout) && !break_test());
 	trace_printk("End ring buffer hammer\n");
 
 	if (consumer) {
@@ -276,8 +288,6 @@ static void ring_buffer_producer(void)
 		/* the completions must be visible before the finish var */
 		smp_wmb();
 		reader_finish = 1;
-		/* finish var visible before waking up the consumer */
-		smp_wmb();
 		wake_up_process(consumer);
 		wait_for_completion(&read_done);
 	}
@@ -287,7 +297,7 @@ static void ring_buffer_producer(void)
 	entries = ring_buffer_entries(buffer);
 	overruns = ring_buffer_overruns(buffer);
 
-	if (kill_test && !kthread_should_stop())
+	if (test_error)
 		trace_printk("ERROR!\n");
 
 	if (!disable_reader) {
@@ -368,15 +378,14 @@ static void wait_to_die(void)
 
 static int ring_buffer_consumer_thread(void *arg)
 {
-	while (!kthread_should_stop() && !kill_test) {
+	while (!break_test()) {
 		complete(&read_start);
 
 		ring_buffer_consumer();
 
 		set_current_state(TASK_INTERRUPTIBLE);
-		if (kthread_should_stop() || kill_test)
+		if (break_test())
 			break;
-
 		schedule();
 	}
 	__set_current_state(TASK_RUNNING);
@@ -389,27 +398,27 @@ static int ring_buffer_consumer_thread(void *arg)
 
 static int ring_buffer_producer_thread(void *arg)
 {
-	init_completion(&read_start);
-
-	while (!kthread_should_stop() && !kill_test) {
+	while (!break_test()) {
 		ring_buffer_reset(buffer);
 
 		if (consumer) {
-			smp_wmb();
 			wake_up_process(consumer);
 			wait_for_completion(&read_start);
 		}
 
 		ring_buffer_producer();
-		if (kill_test)
+		if (break_test())
 			goto out_kill;
 
 		trace_printk("Sleeping for 10 secs\n");
 		set_current_state(TASK_INTERRUPTIBLE);
+		if (break_test())
+			goto out_kill;
 		schedule_timeout(HZ * SLEEP_TIME);
 	}
 
 out_kill:
+	__set_current_state(TASK_RUNNING);
 	if (!kthread_should_stop())
 		wait_to_die();
 

kernel/trace/trace.c

@@ -214,12 +214,10 @@ __setup("alloc_snapshot", boot_alloc_snapshot);
 
 
 static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata;
-static char *trace_boot_options __initdata;
 
 static int __init set_trace_boot_options(char *str)
 {
 	strlcpy(trace_boot_options_buf, str, MAX_TRACER_SIZE);
-	trace_boot_options = trace_boot_options_buf;
 	return 0;
 }
 __setup("trace_options=", set_trace_boot_options);
@@ -250,6 +248,19 @@ unsigned long long ns2usecs(cycle_t nsec)
 	return nsec;
 }
 
+/* trace_flags holds trace_options default values */
+#define TRACE_DEFAULT_FLAGS						\
+	(FUNCTION_DEFAULT_FLAGS |					\
+	 TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |			\
+	 TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO |		\
+	 TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE |			\
+	 TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS)
+
+/* trace_options that are only supported by global_trace */
+#define TOP_LEVEL_TRACE_FLAGS (TRACE_ITER_PRINTK |			\
+	       TRACE_ITER_PRINTK_MSGONLY | TRACE_ITER_RECORD_CMD)
+
+
 /*
  * The global_trace is the descriptor that holds the tracing
  * buffers for the live tracing. For each CPU, it contains
@@ -262,7 +273,9 @@ unsigned long long ns2usecs(cycle_t nsec)
  * pages for the buffer for that CPU. Each CPU has the same number
  * of pages allocated for its buffer.
  */
-static struct trace_array	global_trace;
+static struct trace_array global_trace = {
+	.trace_flags = TRACE_DEFAULT_FLAGS,
+};
 
 LIST_HEAD(ftrace_trace_arrays);
 
@@ -468,11 +481,29 @@ static inline void trace_access_lock_init(void)
 
 #endif
 
-/* trace_flags holds trace_options default values */
-unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
-	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
-	TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE |
-	TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS | TRACE_ITER_FUNCTION;
+#ifdef CONFIG_STACKTRACE
+static void __ftrace_trace_stack(struct ring_buffer *buffer,
+				 unsigned long flags,
+				 int skip, int pc, struct pt_regs *regs);
+static inline void ftrace_trace_stack(struct trace_array *tr,
+				      struct ring_buffer *buffer,
+				      unsigned long flags,
+				      int skip, int pc, struct pt_regs *regs);
+
+#else
+static inline void __ftrace_trace_stack(struct ring_buffer *buffer,
+					unsigned long flags,
+					int skip, int pc, struct pt_regs *regs)
+{
+}
+static inline void ftrace_trace_stack(struct trace_array *tr,
+				      struct ring_buffer *buffer,
+				      unsigned long flags,
+				      int skip, int pc, struct pt_regs *regs)
+{
+}
+
+#endif
 
 static void tracer_tracing_on(struct trace_array *tr)
 {
@@ -518,7 +549,7 @@ int __trace_puts(unsigned long ip, const char *str, int size)
 	int alloc;
 	int pc;
 
-	if (!(trace_flags & TRACE_ITER_PRINTK))
+	if (!(global_trace.trace_flags & TRACE_ITER_PRINTK))
 		return 0;
 
 	pc = preempt_count();
@@ -548,7 +579,7 @@ int __trace_puts(unsigned long ip, const char *str, int size)
 		entry->buf[size] = '\0';
 
 	__buffer_unlock_commit(buffer, event);
-	ftrace_trace_stack(buffer, irq_flags, 4, pc);
+	ftrace_trace_stack(&global_trace, buffer, irq_flags, 4, pc, NULL);
 
 	return size;
 }
@@ -568,7 +599,7 @@ int __trace_bputs(unsigned long ip, const char *str)
 	int size = sizeof(struct bputs_entry);
 	int pc;
 
-	if (!(trace_flags & TRACE_ITER_PRINTK))
+	if (!(global_trace.trace_flags & TRACE_ITER_PRINTK))
 		return 0;
 
 	pc = preempt_count();
@@ -588,7 +619,7 @@ int __trace_bputs(unsigned long ip, const char *str)
 	entry->str			= str;
 
 	__buffer_unlock_commit(buffer, event);
-	ftrace_trace_stack(buffer, irq_flags, 4, pc);
+	ftrace_trace_stack(&global_trace, buffer, irq_flags, 4, pc, NULL);
 
 	return 1;
 }
@@ -834,34 +865,18 @@ unsigned long nsecs_to_usecs(unsigned long nsecs)
 	return nsecs / 1000;
 }
 
+/*
+ * TRACE_FLAGS is defined as a tuple matching bit masks with strings.
+ * It uses C(a, b) where 'a' is the enum name and 'b' is the string that
+ * matches it. By defining "C(a, b) b", TRACE_FLAGS becomes a list
+ * of strings in the order that the enums were defined.
+ */
+#undef C
+#define C(a, b) b
+
 /* These must match the bit postions in trace_iterator_flags */
 static const char *trace_options[] = {
-	"print-parent",
-	"sym-offset",
-	"sym-addr",
-	"verbose",
-	"raw",
-	"hex",
-	"bin",
-	"block",
-	"stacktrace",
-	"trace_printk",
-	"ftrace_preempt",
-	"branch",
-	"annotate",
-	"userstacktrace",
-	"sym-userobj",
-	"printk-msg-only",
-	"context-info",
-	"latency-format",
-	"sleep-time",
-	"graph-time",
-	"record-cmd",
-	"overwrite",
-	"disable_on_free",
-	"irq-info",
-	"markers",
-	"function-trace",
+	TRACE_FLAGS
 	NULL
 };
 
@@ -1204,13 +1219,17 @@ static inline int run_tracer_selftest(struct tracer *type)
 }
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
 
+static void add_tracer_options(struct trace_array *tr, struct tracer *t);
+
+static void __init apply_trace_boot_options(void);
+
 /**
  * register_tracer - register a tracer with the ftrace system.
  * @type - the plugin for the tracer
  *
  * Register a new plugin tracer.
  */
-int register_tracer(struct tracer *type)
+int __init register_tracer(struct tracer *type)
 {
 	struct tracer *t;
 	int ret = 0;
@@ -1253,6 +1272,7 @@ int register_tracer(struct tracer *type)
 
 	type->next = trace_types;
 	trace_types = type;
+	add_tracer_options(&global_trace, type);
 
  out:
 	tracing_selftest_running = false;
@@ -1268,6 +1288,9 @@ int register_tracer(struct tracer *type)
 	/* Do we want this tracer to start on bootup? */
 	tracing_set_tracer(&global_trace, type->name);
 	default_bootup_tracer = NULL;
+
+	apply_trace_boot_options();
+
 	/* disable other selftests, since this will break it. */
 	tracing_selftest_disabled = true;
 #ifdef CONFIG_FTRACE_STARTUP_TEST
@@ -1671,23 +1694,16 @@ __buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *eve
 	ring_buffer_unlock_commit(buffer, event);
 }
 
-static inline void
-__trace_buffer_unlock_commit(struct ring_buffer *buffer,
-			     struct ring_buffer_event *event,
-			     unsigned long flags, int pc)
+void trace_buffer_unlock_commit(struct trace_array *tr,
+				struct ring_buffer *buffer,
+				struct ring_buffer_event *event,
+				unsigned long flags, int pc)
 {
 	__buffer_unlock_commit(buffer, event);
 
-	ftrace_trace_stack(buffer, flags, 6, pc);
+	ftrace_trace_stack(tr, buffer, flags, 6, pc, NULL);
 	ftrace_trace_userstack(buffer, flags, pc);
 }
-
-void trace_buffer_unlock_commit(struct ring_buffer *buffer,
-				struct ring_buffer_event *event,
-				unsigned long flags, int pc)
-{
-	__trace_buffer_unlock_commit(buffer, event, flags, pc);
-}
 EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit);
 
 static struct ring_buffer *temp_buffer;
@@ -1729,22 +1745,15 @@ trace_current_buffer_lock_reserve(struct ring_buffer **current_rb,
 }
 EXPORT_SYMBOL_GPL(trace_current_buffer_lock_reserve);
 
-void trace_current_buffer_unlock_commit(struct ring_buffer *buffer,
-					struct ring_buffer_event *event,
-					unsigned long flags, int pc)
-{
-	__trace_buffer_unlock_commit(buffer, event, flags, pc);
-}
-EXPORT_SYMBOL_GPL(trace_current_buffer_unlock_commit);
-
-void trace_buffer_unlock_commit_regs(struct ring_buffer *buffer,
+void trace_buffer_unlock_commit_regs(struct trace_array *tr,
+				     struct ring_buffer *buffer,
 				     struct ring_buffer_event *event,
 				     unsigned long flags, int pc,
 				     struct pt_regs *regs)
 {
 	__buffer_unlock_commit(buffer, event);
 
-	ftrace_trace_stack_regs(buffer, flags, 0, pc, regs);
+	ftrace_trace_stack(tr, buffer, flags, 6, pc, regs);
 	ftrace_trace_userstack(buffer, flags, pc);
 }
 EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit_regs);
@@ -1873,24 +1882,17 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
 
 }
 
-void ftrace_trace_stack_regs(struct ring_buffer *buffer, unsigned long flags,
-			     int skip, int pc, struct pt_regs *regs)
+static inline void ftrace_trace_stack(struct trace_array *tr,
+				      struct ring_buffer *buffer,
+				      unsigned long flags,
+				      int skip, int pc, struct pt_regs *regs)
 {
-	if (!(trace_flags & TRACE_ITER_STACKTRACE))
+	if (!(tr->trace_flags & TRACE_ITER_STACKTRACE))
 		return;
 
 	__ftrace_trace_stack(buffer, flags, skip, pc, regs);
 }
 
-void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
-			int skip, int pc)
-{
-	if (!(trace_flags & TRACE_ITER_STACKTRACE))
-		return;
-
-	__ftrace_trace_stack(buffer, flags, skip, pc, NULL);
-}
-
 void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
 		   int pc)
 {
@@ -1929,7 +1931,7 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 	struct userstack_entry *entry;
 	struct stack_trace trace;
 
-	if (!(trace_flags & TRACE_ITER_USERSTACKTRACE))
+	if (!(global_trace.trace_flags & TRACE_ITER_USERSTACKTRACE))
 		return;
 
 	/*
@@ -2173,7 +2175,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	memcpy(entry->buf, tbuffer, sizeof(u32) * len);
 	if (!call_filter_check_discard(call, entry, buffer, event)) {
 		__buffer_unlock_commit(buffer, event);
-		ftrace_trace_stack(buffer, flags, 6, pc);
+		ftrace_trace_stack(tr, buffer, flags, 6, pc, NULL);
 	}
 
 out:
@@ -2225,7 +2227,7 @@ __trace_array_vprintk(struct ring_buffer *buffer,
 	memcpy(&entry->buf, tbuffer, len + 1);
 	if (!call_filter_check_discard(call, entry, buffer, event)) {
 		__buffer_unlock_commit(buffer, event);
-		ftrace_trace_stack(buffer, flags, 6, pc);
+		ftrace_trace_stack(&global_trace, buffer, flags, 6, pc, NULL);
 	}
  out:
 	preempt_enable_notrace();
@@ -2246,7 +2248,7 @@ int trace_array_printk(struct trace_array *tr,
 	int ret;
 	va_list ap;
 
-	if (!(trace_flags & TRACE_ITER_PRINTK))
+	if (!(global_trace.trace_flags & TRACE_ITER_PRINTK))
 		return 0;
 
 	va_start(ap, fmt);
@@ -2261,7 +2263,7 @@ int trace_array_printk_buf(struct ring_buffer *buffer,
 	int ret;
 	va_list ap;
 
-	if (!(trace_flags & TRACE_ITER_PRINTK))
+	if (!(global_trace.trace_flags & TRACE_ITER_PRINTK))
 		return 0;
 
 	va_start(ap, fmt);
@@ -2602,7 +2604,7 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file
 void
 print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 {
-	unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
+	unsigned long sym_flags = (global_trace.trace_flags & TRACE_ITER_SYM_MASK);
 	struct trace_buffer *buf = iter->trace_buffer;
 	struct trace_array_cpu *data = per_cpu_ptr(buf->data, buf->cpu);
 	struct tracer *type = iter->trace;
@@ -2664,20 +2666,22 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 static void test_cpu_buff_start(struct trace_iterator *iter)
 {
 	struct trace_seq *s = &iter->seq;
+	struct trace_array *tr = iter->tr;
 
-	if (!(trace_flags & TRACE_ITER_ANNOTATE))
+	if (!(tr->trace_flags & TRACE_ITER_ANNOTATE))
 		return;
 
 	if (!(iter->iter_flags & TRACE_FILE_ANNOTATE))
 		return;
 
-	if (cpumask_test_cpu(iter->cpu, iter->started))
+	if (iter->started && cpumask_test_cpu(iter->cpu, iter->started))
 		return;
 
 	if (per_cpu_ptr(iter->trace_buffer->data, iter->cpu)->skipped_entries)
 		return;
 
-	cpumask_set_cpu(iter->cpu, iter->started);
+	if (iter->started)
+		cpumask_set_cpu(iter->cpu, iter->started);
 
 	/* Don't print started cpu buffer for the first entry of the trace */
 	if (iter->idx > 1)
@@ -2687,8 +2691,9 @@ static void test_cpu_buff_start(struct trace_iterator *iter)
 
 static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
 {
+	struct trace_array *tr = iter->tr;
 	struct trace_seq *s = &iter->seq;
-	unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
+	unsigned long sym_flags = (tr->trace_flags & TRACE_ITER_SYM_MASK);
 	struct trace_entry *entry;
 	struct trace_event *event;
 
@@ -2698,7 +2703,7 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
 
 	event = ftrace_find_event(entry->type);
 
-	if (trace_flags & TRACE_ITER_CONTEXT_INFO) {
+	if (tr->trace_flags & TRACE_ITER_CONTEXT_INFO) {
 		if (iter->iter_flags & TRACE_FILE_LAT_FMT)
 			trace_print_lat_context(iter);
 		else
@@ -2718,13 +2723,14 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
 
 static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
 {
+	struct trace_array *tr = iter->tr;
 	struct trace_seq *s = &iter->seq;
 	struct trace_entry *entry;
 	struct trace_event *event;
 
 	entry = iter->ent;
 
-	if (trace_flags & TRACE_ITER_CONTEXT_INFO)
+	if (tr->trace_flags & TRACE_ITER_CONTEXT_INFO)
 		trace_seq_printf(s, "%d %d %llu ",
 				 entry->pid, iter->cpu, iter->ts);
 
@@ -2742,6 +2748,7 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
 
 static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
 {
+	struct trace_array *tr = iter->tr;
 	struct trace_seq *s = &iter->seq;
 	unsigned char newline = '\n';
 	struct trace_entry *entry;
@@ -2749,7 +2756,7 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
 
 	entry = iter->ent;
 
-	if (trace_flags & TRACE_ITER_CONTEXT_INFO) {
+	if (tr->trace_flags & TRACE_ITER_CONTEXT_INFO) {
 		SEQ_PUT_HEX_FIELD(s, entry->pid);
 		SEQ_PUT_HEX_FIELD(s, iter->cpu);
 		SEQ_PUT_HEX_FIELD(s, iter->ts);
@@ -2771,13 +2778,14 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
 
 static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
 {
+	struct trace_array *tr = iter->tr;
 	struct trace_seq *s = &iter->seq;
 	struct trace_entry *entry;
 	struct trace_event *event;
 
 	entry = iter->ent;
 
-	if (trace_flags & TRACE_ITER_CONTEXT_INFO) {
+	if (tr->trace_flags & TRACE_ITER_CONTEXT_INFO) {
 		SEQ_PUT_FIELD(s, entry->pid);
 		SEQ_PUT_FIELD(s, iter->cpu);
 		SEQ_PUT_FIELD(s, iter->ts);
@@ -2826,6 +2834,8 @@ int trace_empty(struct trace_iterator *iter)
 /*  Called with trace_event_read_lock() held. */
 enum print_line_t print_trace_line(struct trace_iterator *iter)
 {
+	struct trace_array *tr = iter->tr;
+	unsigned long trace_flags = tr->trace_flags;
 	enum print_line_t ret;
 
 	if (iter->lost_events) {
@@ -2871,6 +2881,7 @@ enum print_line_t print_trace_line(struct trace_iterator *iter)
 void trace_latency_header(struct seq_file *m)
 {
 	struct trace_iterator *iter = m->private;
+	struct trace_array *tr = iter->tr;
 
 	/* print nothing if the buffers are empty */
 	if (trace_empty(iter))
@@ -2879,13 +2890,15 @@ void trace_latency_header(struct seq_file *m)
 	if (iter->iter_flags & TRACE_FILE_LAT_FMT)
 		print_trace_header(m, iter);
 
-	if (!(trace_flags & TRACE_ITER_VERBOSE))
+	if (!(tr->trace_flags & TRACE_ITER_VERBOSE))
 		print_lat_help_header(m);
 }
 
 void trace_default_header(struct seq_file *m)
 {
 	struct trace_iterator *iter = m->private;
+	struct trace_array *tr = iter->tr;
+	unsigned long trace_flags = tr->trace_flags;
 
 	if (!(trace_flags & TRACE_ITER_CONTEXT_INFO))
 		return;
@@ -3230,7 +3243,7 @@ static int tracing_open(struct inode *inode, struct file *file)
 		iter = __tracing_open(inode, file, false);
 		if (IS_ERR(iter))
 			ret = PTR_ERR(iter);
-		else if (trace_flags & TRACE_ITER_LATENCY_FMT)
+		else if (tr->trace_flags & TRACE_ITER_LATENCY_FMT)
 			iter->iter_flags |= TRACE_FILE_LAT_FMT;
 	}
 
@@ -3477,7 +3490,7 @@ static int tracing_trace_options_show(struct seq_file *m, void *v)
 	trace_opts = tr->current_trace->flags->opts;
 
 	for (i = 0; trace_options[i]; i++) {
-		if (trace_flags & (1 << i))
+		if (tr->trace_flags & (1 << i))
 			seq_printf(m, "%s\n", trace_options[i]);
 		else
 			seq_printf(m, "no%s\n", trace_options[i]);
@@ -3542,7 +3555,7 @@ int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set)
 int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
 {
 	/* do nothing if flag is already set */
-	if (!!(trace_flags & mask) == !!enabled)
+	if (!!(tr->trace_flags & mask) == !!enabled)
 		return 0;
 
 	/* Give the tracer a chance to approve the change */
@@ -3551,9 +3564,9 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
 			return -EINVAL;
 
 	if (enabled)
-		trace_flags |= mask;
+		tr->trace_flags |= mask;
 	else
-		trace_flags &= ~mask;
+		tr->trace_flags &= ~mask;
 
 	if (mask == TRACE_ITER_RECORD_CMD)
 		trace_event_enable_cmd_record(enabled);
@@ -3565,8 +3578,10 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
 #endif
 	}
 
-	if (mask == TRACE_ITER_PRINTK)
+	if (mask == TRACE_ITER_PRINTK) {
 		trace_printk_start_stop_comm(enabled);
+		trace_printk_control(enabled);
+	}
 
 	return 0;
 }
@@ -3577,6 +3592,7 @@ static int trace_set_options(struct trace_array *tr, char *option)
 	int neg = 0;
 	int ret = -ENODEV;
 	int i;
+	size_t orig_len = strlen(option);
 
 	cmp = strstrip(option);
 
@@ -3600,9 +3616,36 @@ static int trace_set_options(struct trace_array *tr, char *option)
 
 	mutex_unlock(&trace_types_lock);
 
+	/*
+	 * If the first trailing whitespace is replaced with '\0' by strstrip,
+	 * turn it back into a space.
+	 */
+	if (orig_len > strlen(option))
+		option[strlen(option)] = ' ';
+
 	return ret;
 }
 
+static void __init apply_trace_boot_options(void)
+{
+	char *buf = trace_boot_options_buf;
+	char *option;
+
+	while (true) {
+		option = strsep(&buf, ",");
+
+		if (!option)
+			break;
+
+		if (*option)
+			trace_set_options(&global_trace, option);
+
+		/* Put back the comma to allow this to be called again */
+		if (buf)
+			*(buf - 1) = ',';
+	}
+}
+
 static ssize_t
 tracing_trace_options_write(struct file *filp, const char __user *ubuf,
 			size_t cnt, loff_t *ppos)
@@ -4297,11 +4340,8 @@ int tracing_update_buffers(void)
 
 struct trace_option_dentry;
 
-static struct trace_option_dentry *
-create_trace_option_files(struct trace_array *tr, struct tracer *tracer);
-
 static void
-destroy_trace_option_files(struct trace_option_dentry *topts);
+create_trace_option_files(struct trace_array *tr, struct tracer *tracer);
 
 /*
  * Used to clear out the tracer before deletion of an instance.
@@ -4320,20 +4360,13 @@ static void tracing_set_nop(struct trace_array *tr)
 	tr->current_trace = &nop_trace;
 }
 
-static void update_tracer_options(struct trace_array *tr, struct tracer *t)
+static void add_tracer_options(struct trace_array *tr, struct tracer *t)
 {
-	static struct trace_option_dentry *topts;
-
 	/* Only enable if the directory has been created already. */
 	if (!tr->dir)
 		return;
 
-	/* Currently, only the top instance has options */
-	if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL))
-		return;
-
-	destroy_trace_option_files(topts);
-	topts = create_trace_option_files(tr, t);
+	create_trace_option_files(tr, t);
 }
 
 static int tracing_set_tracer(struct trace_array *tr, const char *buf)
@@ -4402,7 +4435,6 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf)
 		free_snapshot(tr);
 	}
 #endif
-	update_tracer_options(tr, t);
 
 #ifdef CONFIG_TRACER_MAX_TRACE
 	if (t->use_max_tr && !had_max_tr) {
@@ -4569,7 +4601,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 	/* trace pipe does not show start of buffer */
 	cpumask_setall(iter->started);
 
-	if (trace_flags & TRACE_ITER_LATENCY_FMT)
+	if (tr->trace_flags & TRACE_ITER_LATENCY_FMT)
 		iter->iter_flags |= TRACE_FILE_LAT_FMT;
 
 	/* Output in nanoseconds only if we are using a clock in nanoseconds. */
@@ -4626,11 +4658,13 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 static unsigned int
 trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_table)
 {
+	struct trace_array *tr = iter->tr;
+
 	/* Iterators are static, they should be filled or empty */
 	if (trace_buffer_iter(iter, iter->cpu_file))
 		return POLLIN | POLLRDNORM;
 
-	if (trace_flags & TRACE_ITER_BLOCK)
+	if (tr->trace_flags & TRACE_ITER_BLOCK)
 		/*
 		 * Always select as readable when in blocking mode
 		 */
@@ -5047,7 +5081,7 @@ tracing_free_buffer_release(struct inode *inode, struct file *filp)
 	struct trace_array *tr = inode->i_private;
 
 	/* disable tracing ? */
-	if (trace_flags & TRACE_ITER_STOP_ON_FREE)
+	if (tr->trace_flags & TRACE_ITER_STOP_ON_FREE)
 		tracer_tracing_off(tr);
 	/* resize the ring buffer to 0 */
 	tracing_resize_ring_buffer(tr, 0, RING_BUFFER_ALL_CPUS);
@@ -5080,7 +5114,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	if (tracing_disabled)
 		return -EINVAL;
 
-	if (!(trace_flags & TRACE_ITER_MARKERS))
+	if (!(tr->trace_flags & TRACE_ITER_MARKERS))
 		return -EINVAL;
 
 	if (cnt > TRACE_BUF_SIZE)
@@ -6132,13 +6166,6 @@ tracing_init_tracefs_percpu(struct trace_array *tr, long cpu)
 #include "trace_selftest.c"
 #endif
 
-struct trace_option_dentry {
-	struct tracer_opt		*opt;
-	struct tracer_flags		*flags;
-	struct trace_array		*tr;
-	struct dentry			*entry;
-};
-
 static ssize_t
 trace_options_read(struct file *filp, char __user *ubuf, size_t cnt,
 			loff_t *ppos)
@@ -6191,14 +6218,51 @@ static const struct file_operations trace_options_fops = {
 	.llseek	= generic_file_llseek,
 };
 
+/*
+ * In order to pass in both the trace_array descriptor as well as the index
+ * to the flag that the trace option file represents, the trace_array
+ * has a character array of trace_flags_index[], which holds the index
+ * of the bit for the flag it represents. index[0] == 0, index[1] == 1, etc.
+ * The address of this character array is passed to the flag option file
+ * read/write callbacks.
+ *
+ * In order to extract both the index and the trace_array descriptor,
+ * get_tr_index() uses the following algorithm.
+ *
+ *   idx = *ptr;
+ *
+ * As the pointer itself contains the address of the index (remember
+ * index[1] == 1).
+ *
+ * Then to get the trace_array descriptor, by subtracting that index
+ * from the ptr, we get to the start of the index itself.
+ *
+ *   ptr - idx == &index[0]
+ *
+ * Then a simple container_of() from that pointer gets us to the
+ * trace_array descriptor.
+ */
+static void get_tr_index(void *data, struct trace_array **ptr,
+			 unsigned int *pindex)
+{
+	*pindex = *(unsigned char *)data;
+
+	*ptr = container_of(data - *pindex, struct trace_array,
+			    trace_flags_index);
+}
+
 static ssize_t
 trace_options_core_read(struct file *filp, char __user *ubuf, size_t cnt,
 			loff_t *ppos)
 {
-	long index = (long)filp->private_data;
+	void *tr_index = filp->private_data;
+	struct trace_array *tr;
+	unsigned int index;
 	char *buf;
 
-	if (trace_flags & (1 << index))
+	get_tr_index(tr_index, &tr, &index);
+
+	if (tr->trace_flags & (1 << index))
 		buf = "1\n";
 	else
 		buf = "0\n";
@@ -6210,11 +6274,14 @@ static ssize_t
 trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
 			 loff_t *ppos)
 {
-	struct trace_array *tr = &global_trace;
-	long index = (long)filp->private_data;
+	void *tr_index = filp->private_data;
+	struct trace_array *tr;
+	unsigned int index;
 	unsigned long val;
 	int ret;
 
+	get_tr_index(tr_index, &tr, &index);
+
 	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
 	if (ret)
 		return ret;
@@ -6298,21 +6365,39 @@ create_trace_option_file(struct trace_array *tr,
 
 }
 
-static struct trace_option_dentry *
+static void
 create_trace_option_files(struct trace_array *tr, struct tracer *tracer)
 {
 	struct trace_option_dentry *topts;
+	struct trace_options *tr_topts;
 	struct tracer_flags *flags;
 	struct tracer_opt *opts;
 	int cnt;
+	int i;
 
 	if (!tracer)
-		return NULL;
+		return;
 
 	flags = tracer->flags;
 
 	if (!flags || !flags->opts)
-		return NULL;
+		return;
+
+	/*
+	 * If this is an instance, only create flags for tracers
+	 * the instance may have.
+	 */
+	if (!trace_ok_for_array(tracer, tr))
+		return;
+
+	for (i = 0; i < tr->nr_topts; i++) {
+		/*
+		 * Check if these flags have already been added.
+		 * Some tracers share flags.
+		 */
+		if (tr->topts[i].tracer->flags == tracer->flags)
+			return;
+	}
 
 	opts = flags->opts;
 
@@ -6321,27 +6406,27 @@ create_trace_option_files(struct trace_array *tr, struct tracer *tracer)
 
 	topts = kcalloc(cnt + 1, sizeof(*topts), GFP_KERNEL);
 	if (!topts)
-		return NULL;
-
-	for (cnt = 0; opts[cnt].name; cnt++)
-		create_trace_option_file(tr, &topts[cnt], flags,
-					 &opts[cnt]);
-
-	return topts;
-}
-
-static void
-destroy_trace_option_files(struct trace_option_dentry *topts)
-{
-	int cnt;
+		return;
 
-	if (!topts)
+	tr_topts = krealloc(tr->topts, sizeof(*tr->topts) * (tr->nr_topts + 1),
+			    GFP_KERNEL);
+	if (!tr_topts) {
+		kfree(topts);
 		return;
+	}
 
-	for (cnt = 0; topts[cnt].opt; cnt++)
-		tracefs_remove(topts[cnt].entry);
+	tr->topts = tr_topts;
+	tr->topts[tr->nr_topts].tracer = tracer;
+	tr->topts[tr->nr_topts].topts = topts;
+	tr->nr_topts++;
 
-	kfree(topts);
+	for (cnt = 0; opts[cnt].name; cnt++) {
+		create_trace_option_file(tr, &topts[cnt], flags,
+					 &opts[cnt]);
+		WARN_ONCE(topts[cnt].entry == NULL,
+			  "Failed to create trace option: %s",
+			  opts[cnt].name);
+	}
 }
 
 static struct dentry *
@@ -6354,21 +6439,26 @@ create_trace_option_core_file(struct trace_array *tr,
 	if (!t_options)
 		return NULL;
 
-	return trace_create_file(option, 0644, t_options, (void *)index,
-				    &trace_options_core_fops);
+	return trace_create_file(option, 0644, t_options,
+				 (void *)&tr->trace_flags_index[index],
+				 &trace_options_core_fops);
 }
 
-static __init void create_trace_options_dir(struct trace_array *tr)
+static void create_trace_options_dir(struct trace_array *tr)
 {
 	struct dentry *t_options;
+	bool top_level = tr == &global_trace;
 	int i;
 
 	t_options = trace_options_init_dentry(tr);
 	if (!t_options)
 		return;
 
-	for (i = 0; trace_options[i]; i++)
-		create_trace_option_core_file(tr, trace_options[i], i);
+	for (i = 0; trace_options[i]; i++) {
+		if (top_level ||
+		    !((1 << i) & TOP_LEVEL_TRACE_FLAGS))
+			create_trace_option_core_file(tr, trace_options[i], i);
+	}
 }
 
 static ssize_t
@@ -6435,7 +6525,7 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size
 {
 	enum ring_buffer_flags rb_flags;
 
-	rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0;
+	rb_flags = tr->trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0;
 
 	buf->tr = tr;
 
@@ -6505,6 +6595,30 @@ static void free_trace_buffers(struct trace_array *tr)
 #endif
 }
 
+static void init_trace_flags_index(struct trace_array *tr)
+{
+	int i;
+
+	/* Used by the trace options files */
+	for (i = 0; i < TRACE_FLAGS_MAX_SIZE; i++)
+		tr->trace_flags_index[i] = i;
+}
+
+static void __update_tracer_options(struct trace_array *tr)
+{
+	struct tracer *t;
+
+	for (t = trace_types; t; t = t->next)
+		add_tracer_options(tr, t);
+}
+
+static void update_tracer_options(struct trace_array *tr)
+{
+	mutex_lock(&trace_types_lock);
+	__update_tracer_options(tr);
+	mutex_unlock(&trace_types_lock);
+}
+
 static int instance_mkdir(const char *name)
 {
 	struct trace_array *tr;
@@ -6530,6 +6644,8 @@ static int instance_mkdir(const char *name)
 	if (!alloc_cpumask_var(&tr->tracing_cpumask, GFP_KERNEL))
 		goto out_free_tr;
 
+	tr->trace_flags = global_trace.trace_flags;
+
 	cpumask_copy(tr->tracing_cpumask, cpu_all_mask);
 
 	raw_spin_lock_init(&tr->start_lock);
@@ -6555,6 +6671,8 @@ static int instance_mkdir(const char *name)
 	}
 
 	init_tracer_tracefs(tr, tr->dir);
+	init_trace_flags_index(tr);
+	__update_tracer_options(tr);
 
 	list_add(&tr->list, &ftrace_trace_arrays);
 
@@ -6580,6 +6698,7 @@ static int instance_rmdir(const char *name)
 	struct trace_array *tr;
 	int found = 0;
 	int ret;
+	int i;
 
 	mutex_lock(&trace_types_lock);
 
@@ -6602,9 +6721,14 @@ static int instance_rmdir(const char *name)
 	tracing_set_nop(tr);
 	event_trace_del_tracer(tr);
 	ftrace_destroy_function_files(tr);
-	debugfs_remove_recursive(tr->dir);
+	tracefs_remove_recursive(tr->dir);
 	free_trace_buffers(tr);
 
+	for (i = 0; i < tr->nr_topts; i++) {
+		kfree(tr->topts[i].topts);
+	}
+	kfree(tr->topts);
+
 	kfree(tr->name);
 	kfree(tr);
 
@@ -6666,6 +6790,8 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 	trace_create_file("tracing_on", 0644, d_tracer,
 			  tr, &rb_simple_fops);
 
+	create_trace_options_dir(tr);
+
 #ifdef CONFIG_TRACER_MAX_TRACE
 	trace_create_file("tracing_max_latency", 0644, d_tracer,
 			&tr->max_latency, &tracing_max_lat_fops);
@@ -6861,11 +6987,7 @@ static __init int tracer_init_tracefs(void)
 
 	create_trace_instances(d_tracer);
 
-	create_trace_options_dir(&global_trace);
-
-	/* If the tracer was started via cmdline, create options for it here */
-	if (global_trace.current_trace != &nop_trace)
-		update_tracer_options(&global_trace, global_trace.current_trace);
+	update_tracer_options(&global_trace);
 
 	return 0;
 }
@@ -6964,6 +7086,7 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 	/* use static because iter can be a bit big for the stack */
 	static struct trace_iterator iter;
 	static atomic_t dump_running;
+	struct trace_array *tr = &global_trace;
 	unsigned int old_userobj;
 	unsigned long flags;
 	int cnt = 0, cpu;
@@ -6993,10 +7116,10 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 		atomic_inc(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled);
 	}
 
-	old_userobj = trace_flags & TRACE_ITER_SYM_USEROBJ;
+	old_userobj = tr->trace_flags & TRACE_ITER_SYM_USEROBJ;
 
 	/* don't look at user memory in panic mode */
-	trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
+	tr->trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
 
 	switch (oops_dump_mode) {
 	case DUMP_ALL:
@@ -7059,7 +7182,7 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 		printk(KERN_TRACE "---------------------------------\n");
 
  out_enable:
-	trace_flags |= old_userobj;
+	tr->trace_flags |= old_userobj;
 
 	for_each_tracing_cpu(cpu) {
 		atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled);
@@ -7074,6 +7197,12 @@ __init static int tracer_alloc_buffers(void)
 	int ring_buf_size;
 	int ret = -ENOMEM;
 
+	/*
+	 * Make sure we don't accidently add more trace options
+	 * than we have bits for.
+	 */
+	BUILD_BUG_ON(TRACE_ITER_LAST_BIT > TRACE_FLAGS_MAX_SIZE);
+
 	if (!alloc_cpumask_var(&tracing_buffer_mask, GFP_KERNEL))
 		goto out;
 
@@ -7132,6 +7261,8 @@ __init static int tracer_alloc_buffers(void)
 
 	ftrace_init_global_array_ops(&global_trace);
 
+	init_trace_flags_index(&global_trace);
+
 	register_tracer(&nop_trace);
 
 	/* All seems OK, enable tracing */
@@ -7148,12 +7279,7 @@ __init static int tracer_alloc_buffers(void)
 	INIT_LIST_HEAD(&global_trace.events);
 	list_add(&global_trace.list, &ftrace_trace_arrays);
 
-	while (trace_boot_options) {
-		char *option;
-
-		option = strsep(&trace_boot_options, ",");
-		trace_set_options(&global_trace, option);
-	}
+	apply_trace_boot_options();
 
 	register_snapshot_cmd();
 

kernel/trace/trace.h

@@ -71,9 +71,6 @@ enum trace_type {
 		tstruct							\
 	}
 
-#undef TP_ARGS
-#define TP_ARGS(args...)	args
-
 #undef FTRACE_ENTRY_DUP
 #define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk, filter)
 
@@ -156,9 +153,12 @@ struct trace_array_cpu {
 	pid_t			pid;
 	kuid_t			uid;
 	char			comm[TASK_COMM_LEN];
+
+	bool			ignore_pid;
 };
 
 struct tracer;
+struct trace_option_dentry;
 
 struct trace_buffer {
 	struct trace_array		*tr;
@@ -168,6 +168,19 @@ struct trace_buffer {
 	int				cpu;
 };
 
+#define TRACE_FLAGS_MAX_SIZE		32
+
+struct trace_options {
+	struct tracer			*tracer;
+	struct trace_option_dentry	*topts;
+};
+
+struct trace_pid_list {
+	unsigned int			nr_pids;
+	int				order;
+	pid_t				*pids;
+};
+
 /*
  * The trace array - an array of per-CPU trace arrays. This is the
  * highest level data structure that individual tracers deal with.
@@ -193,6 +206,7 @@ struct trace_array {
 	bool			allocated_snapshot;
 	unsigned long		max_latency;
 #endif
+	struct trace_pid_list	__rcu *filtered_pids;
 	/*
 	 * max_lock is used to protect the swapping of buffers
 	 * when taking a max snapshot. The buffers themselves are
@@ -216,13 +230,17 @@ struct trace_array {
 #endif
 	int			stop_count;
 	int			clock_id;
+	int			nr_topts;
 	struct tracer		*current_trace;
+	unsigned int		trace_flags;
+	unsigned char		trace_flags_index[TRACE_FLAGS_MAX_SIZE];
 	unsigned int		flags;
 	raw_spinlock_t		start_lock;
 	struct dentry		*dir;
 	struct dentry		*options;
 	struct dentry		*percpu_dir;
 	struct dentry		*event_dir;
+	struct trace_options	*topts;
 	struct list_head	systems;
 	struct list_head	events;
 	cpumask_var_t		tracing_cpumask; /* only trace on set CPUs */
@@ -333,6 +351,13 @@ struct tracer_flags {
 #define TRACER_OPT(s, b)	.name = #s, .bit = b
 
 
+struct trace_option_dentry {
+	struct tracer_opt		*opt;
+	struct tracer_flags		*flags;
+	struct trace_array		*tr;
+	struct dentry			*entry;
+};
+
 /**
  * struct tracer - a specific tracer and its callbacks to interact with tracefs
  * @name: the name chosen to select it on the available_tracers file
@@ -611,29 +636,12 @@ void update_max_tr_single(struct trace_array *tr,
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
 #ifdef CONFIG_STACKTRACE
-void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
-			int skip, int pc);
-
-void ftrace_trace_stack_regs(struct ring_buffer *buffer, unsigned long flags,
-			     int skip, int pc, struct pt_regs *regs);
-
 void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags,
 			    int pc);
 
 void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
 		   int pc);
 #else
-static inline void ftrace_trace_stack(struct ring_buffer *buffer,
-				      unsigned long flags, int skip, int pc)
-{
-}
-
-static inline void ftrace_trace_stack_regs(struct ring_buffer *buffer,
-					   unsigned long flags, int skip,
-					   int pc, struct pt_regs *regs)
-{
-}
-
 static inline void ftrace_trace_userstack(struct ring_buffer *buffer,
 					  unsigned long flags, int pc)
 {
@@ -707,8 +715,6 @@ int trace_array_printk_buf(struct ring_buffer *buffer,
 void trace_printk_seq(struct trace_seq *s);
 enum print_line_t print_trace_line(struct trace_iterator *iter);
 
-extern unsigned long trace_flags;
-
 extern char trace_find_mark(unsigned long long duration);
 
 /* Standard output formatting function used for function return traces */
@@ -723,9 +729,14 @@ extern char trace_find_mark(unsigned long long duration);
 #define TRACE_GRAPH_PRINT_ABS_TIME      0x20
 #define TRACE_GRAPH_PRINT_IRQS          0x40
 #define TRACE_GRAPH_PRINT_TAIL          0x80
+#define TRACE_GRAPH_SLEEP_TIME		0x100
+#define TRACE_GRAPH_GRAPH_TIME		0x200
 #define TRACE_GRAPH_PRINT_FILL_SHIFT	28
 #define TRACE_GRAPH_PRINT_FILL_MASK	(0x3 << TRACE_GRAPH_PRINT_FILL_SHIFT)
 
+extern void ftrace_graph_sleep_time_control(bool enable);
+extern void ftrace_graph_graph_time_control(bool enable);
+
 extern enum print_line_t
 print_graph_function_flags(struct trace_iterator *iter, u32 flags);
 extern void print_graph_headers_flags(struct seq_file *s, u32 flags);
@@ -859,7 +870,7 @@ void ftrace_destroy_filter_files(struct ftrace_ops *ops);
 #define ftrace_destroy_filter_files(ops) do { } while (0)
 #endif /* CONFIG_FUNCTION_TRACER && CONFIG_DYNAMIC_FTRACE */
 
-int ftrace_event_is_function(struct trace_event_call *call);
+bool ftrace_event_is_function(struct trace_event_call *call);
 
 /*
  * struct trace_parser - servers for reading the user input separated by spaces
@@ -896,42 +907,94 @@ extern void trace_parser_put(struct trace_parser *parser);
 extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 	size_t cnt, loff_t *ppos);
 
+/*
+ * Only create function graph options if function graph is configured.
+ */
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+# define FGRAPH_FLAGS						\
+		C(DISPLAY_GRAPH,	"display-graph"),
+#else
+# define FGRAPH_FLAGS
+#endif
+
+#ifdef CONFIG_BRANCH_TRACER
+# define BRANCH_FLAGS					\
+		C(BRANCH,		"branch"),
+#else
+# define BRANCH_FLAGS
+#endif
+
+#ifdef CONFIG_FUNCTION_TRACER
+# define FUNCTION_FLAGS						\
+		C(FUNCTION,		"function-trace"),
+# define FUNCTION_DEFAULT_FLAGS		TRACE_ITER_FUNCTION
+#else
+# define FUNCTION_FLAGS
+# define FUNCTION_DEFAULT_FLAGS		0UL
+#endif
+
+#ifdef CONFIG_STACKTRACE
+# define STACK_FLAGS				\
+		C(STACKTRACE,		"stacktrace"),
+#else
+# define STACK_FLAGS
+#endif
+
 /*
  * trace_iterator_flags is an enumeration that defines bit
  * positions into trace_flags that controls the output.
  *
  * NOTE: These bits must match the trace_options array in
- *       trace.c.
+ *       trace.c (this macro guarantees it).
+ */
+#define TRACE_FLAGS						\
+		C(PRINT_PARENT,		"print-parent"),	\
+		C(SYM_OFFSET,		"sym-offset"),		\
+		C(SYM_ADDR,		"sym-addr"),		\
+		C(VERBOSE,		"verbose"),		\
+		C(RAW,			"raw"),			\
+		C(HEX,			"hex"),			\
+		C(BIN,			"bin"),			\
+		C(BLOCK,		"block"),		\
+		C(PRINTK,		"trace_printk"),	\
+		C(ANNOTATE,		"annotate"),		\
+		C(USERSTACKTRACE,	"userstacktrace"),	\
+		C(SYM_USEROBJ,		"sym-userobj"),		\
+		C(PRINTK_MSGONLY,	"printk-msg-only"),	\
+		C(CONTEXT_INFO,		"context-info"),   /* Print pid/cpu/time */ \
+		C(LATENCY_FMT,		"latency-format"),	\
+		C(RECORD_CMD,		"record-cmd"),		\
+		C(OVERWRITE,		"overwrite"),		\
+		C(STOP_ON_FREE,		"disable_on_free"),	\
+		C(IRQ_INFO,		"irq-info"),		\
+		C(MARKERS,		"markers"),		\
+		FUNCTION_FLAGS					\
+		FGRAPH_FLAGS					\
+		STACK_FLAGS					\
+		BRANCH_FLAGS
+
+/*
+ * By defining C, we can make TRACE_FLAGS a list of bit names
+ * that will define the bits for the flag masks.
  */
-enum trace_iterator_flags {
-	TRACE_ITER_PRINT_PARENT		= 0x01,
-	TRACE_ITER_SYM_OFFSET		= 0x02,
-	TRACE_ITER_SYM_ADDR		= 0x04,
-	TRACE_ITER_VERBOSE		= 0x08,
-	TRACE_ITER_RAW			= 0x10,
-	TRACE_ITER_HEX			= 0x20,
-	TRACE_ITER_BIN			= 0x40,
-	TRACE_ITER_BLOCK		= 0x80,
-	TRACE_ITER_STACKTRACE		= 0x100,
-	TRACE_ITER_PRINTK		= 0x200,
-	TRACE_ITER_PREEMPTONLY		= 0x400,
-	TRACE_ITER_BRANCH		= 0x800,
-	TRACE_ITER_ANNOTATE		= 0x1000,
-	TRACE_ITER_USERSTACKTRACE       = 0x2000,
-	TRACE_ITER_SYM_USEROBJ          = 0x4000,
-	TRACE_ITER_PRINTK_MSGONLY	= 0x8000,
-	TRACE_ITER_CONTEXT_INFO		= 0x10000, /* Print pid/cpu/time */
-	TRACE_ITER_LATENCY_FMT		= 0x20000,
-	TRACE_ITER_SLEEP_TIME		= 0x40000,
-	TRACE_ITER_GRAPH_TIME		= 0x80000,
-	TRACE_ITER_RECORD_CMD		= 0x100000,
-	TRACE_ITER_OVERWRITE		= 0x200000,
-	TRACE_ITER_STOP_ON_FREE		= 0x400000,
-	TRACE_ITER_IRQ_INFO		= 0x800000,
-	TRACE_ITER_MARKERS		= 0x1000000,
-	TRACE_ITER_FUNCTION		= 0x2000000,
+#undef C
+#define C(a, b) TRACE_ITER_##a##_BIT
+
+enum trace_iterator_bits {
+	TRACE_FLAGS
+	/* Make sure we don't go more than we have bits for */
+	TRACE_ITER_LAST_BIT
 };
 
+/*
+ * By redefining C, we can make TRACE_FLAGS a list of masks that
+ * use the bits as defined above.
+ */
+#undef C
+#define C(a, b) TRACE_ITER_##a = (1 << TRACE_ITER_##a##_BIT)
+
+enum trace_iterator_flags { TRACE_FLAGS };
+
 /*
  * TRACE_ITER_SYM_MASK masks the options in trace_flags that
  * control the output of kernel symbols.
@@ -946,7 +1009,7 @@ extern int enable_branch_tracing(struct trace_array *tr);
 extern void disable_branch_tracing(void);
 static inline int trace_branch_enable(struct trace_array *tr)
 {
-	if (trace_flags & TRACE_ITER_BRANCH)
+	if (tr->trace_flags & TRACE_ITER_BRANCH)
 		return enable_branch_tracing(tr);
 	return 0;
 }
@@ -1269,6 +1332,7 @@ extern const char *__stop___trace_bprintk_fmt[];
 extern const char *__start___tracepoint_str[];
 extern const char *__stop___tracepoint_str[];
 
+void trace_printk_control(bool enabled);
 void trace_printk_init_buffers(void);
 void trace_printk_start_comm(void);
 int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set);

kernel/trace/trace_benchmark.c

@@ -43,7 +43,7 @@ static void trace_do_benchmark(void)
 	unsigned int std = 0;
 
 	/* Only run if the tracepoint is actually active */
-	if (!trace_benchmark_event_enabled())
+	if (!trace_benchmark_event_enabled() || !tracing_is_on())
 		return;
 
 	local_irq_disable();

kernel/trace/trace_branch.c

@@ -125,25 +125,14 @@ void disable_branch_tracing(void)
 	mutex_unlock(&branch_tracing_mutex);
 }
 
-static void start_branch_trace(struct trace_array *tr)
-{
-	enable_branch_tracing(tr);
-}
-
-static void stop_branch_trace(struct trace_array *tr)
-{
-	disable_branch_tracing();
-}
-
 static int branch_trace_init(struct trace_array *tr)
 {
-	start_branch_trace(tr);
-	return 0;
+	return enable_branch_tracing(tr);
 }
 
 static void branch_trace_reset(struct trace_array *tr)
 {
-	stop_branch_trace(tr);
+	disable_branch_tracing();
 }
 
 static enum print_line_t trace_branch_print(struct trace_iterator *iter,

kernel/trace/trace_events.c

@@ -15,11 +15,15 @@
 #include <linux/kthread.h>
 #include <linux/tracefs.h>
 #include <linux/uaccess.h>
+#include <linux/bsearch.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
+#include <linux/sort.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
 
+#include <trace/events/sched.h>
+
 #include <asm/setup.h>
 
 #include "trace_output.h"
@@ -38,21 +42,19 @@ static LIST_HEAD(ftrace_common_fields);
 static struct kmem_cache *field_cachep;
 static struct kmem_cache *file_cachep;
 
-#define SYSTEM_FL_FREE_NAME		(1 << 31)
-
 static inline int system_refcount(struct event_subsystem *system)
 {
-	return system->ref_count & ~SYSTEM_FL_FREE_NAME;
+	return system->ref_count;
 }
 
 static int system_refcount_inc(struct event_subsystem *system)
 {
-	return (system->ref_count++) & ~SYSTEM_FL_FREE_NAME;
+	return system->ref_count++;
 }
 
 static int system_refcount_dec(struct event_subsystem *system)
 {
-	return (--system->ref_count) & ~SYSTEM_FL_FREE_NAME;
+	return --system->ref_count;
 }
 
 /* Double loops, do not use break, only goto's work */
@@ -212,12 +214,32 @@ int trace_event_raw_init(struct trace_event_call *call)
 }
 EXPORT_SYMBOL_GPL(trace_event_raw_init);
 
+bool trace_event_ignore_this_pid(struct trace_event_file *trace_file)
+{
+	struct trace_array *tr = trace_file->tr;
+	struct trace_array_cpu *data;
+	struct trace_pid_list *pid_list;
+
+	pid_list = rcu_dereference_sched(tr->filtered_pids);
+	if (!pid_list)
+		return false;
+
+	data = this_cpu_ptr(tr->trace_buffer.data);
+
+	return data->ignore_pid;
+}
+EXPORT_SYMBOL_GPL(trace_event_ignore_this_pid);
+
 void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer,
 				 struct trace_event_file *trace_file,
 				 unsigned long len)
 {
 	struct trace_event_call *event_call = trace_file->event_call;
 
+	if ((trace_file->flags & EVENT_FILE_FL_PID_FILTER) &&
+	    trace_event_ignore_this_pid(trace_file))
+		return NULL;
+
 	local_save_flags(fbuffer->flags);
 	fbuffer->pc = preempt_count();
 	fbuffer->trace_file = trace_file;
@@ -338,6 +360,7 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 					 int enable, int soft_disable)
 {
 	struct trace_event_call *call = file->event_call;
+	struct trace_array *tr = file->tr;
 	int ret = 0;
 	int disable;
 
@@ -401,7 +424,7 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 			if (soft_disable)
 				set_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags);
 
-			if (trace_flags & TRACE_ITER_RECORD_CMD) {
+			if (tr->trace_flags & TRACE_ITER_RECORD_CMD) {
 				tracing_start_cmdline_record();
 				set_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags);
 			}
@@ -446,6 +469,142 @@ static void ftrace_clear_events(struct trace_array *tr)
 	mutex_unlock(&event_mutex);
 }
 
+static int cmp_pid(const void *key, const void *elt)
+{
+	const pid_t *search_pid = key;
+	const pid_t *pid = elt;
+
+	if (*search_pid == *pid)
+		return 0;
+	if (*search_pid < *pid)
+		return -1;
+	return 1;
+}
+
+static bool
+check_ignore_pid(struct trace_pid_list *filtered_pids, struct task_struct *task)
+{
+	pid_t search_pid;
+	pid_t *pid;
+
+	/*
+	 * Return false, because if filtered_pids does not exist,
+	 * all pids are good to trace.
+	 */
+	if (!filtered_pids)
+		return false;
+
+	search_pid = task->pid;
+
+	pid = bsearch(&search_pid, filtered_pids->pids,
+		      filtered_pids->nr_pids, sizeof(pid_t),
+		      cmp_pid);
+	if (!pid)
+		return true;
+
+	return false;
+}
+
+static void
+event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
+		    struct task_struct *prev, struct task_struct *next)
+{
+	struct trace_array *tr = data;
+	struct trace_pid_list *pid_list;
+
+	pid_list = rcu_dereference_sched(tr->filtered_pids);
+
+	this_cpu_write(tr->trace_buffer.data->ignore_pid,
+		       check_ignore_pid(pid_list, prev) &&
+		       check_ignore_pid(pid_list, next));
+}
+
+static void
+event_filter_pid_sched_switch_probe_post(void *data, bool preempt,
+		    struct task_struct *prev, struct task_struct *next)
+{
+	struct trace_array *tr = data;
+	struct trace_pid_list *pid_list;
+
+	pid_list = rcu_dereference_sched(tr->filtered_pids);
+
+	this_cpu_write(tr->trace_buffer.data->ignore_pid,
+		       check_ignore_pid(pid_list, next));
+}
+
+static void
+event_filter_pid_sched_wakeup_probe_pre(void *data, struct task_struct *task)
+{
+	struct trace_array *tr = data;
+	struct trace_pid_list *pid_list;
+
+	/* Nothing to do if we are already tracing */
+	if (!this_cpu_read(tr->trace_buffer.data->ignore_pid))
+		return;
+
+	pid_list = rcu_dereference_sched(tr->filtered_pids);
+
+	this_cpu_write(tr->trace_buffer.data->ignore_pid,
+		       check_ignore_pid(pid_list, task));
+}
+
+static void
+event_filter_pid_sched_wakeup_probe_post(void *data, struct task_struct *task)
+{
+	struct trace_array *tr = data;
+	struct trace_pid_list *pid_list;
+
+	/* Nothing to do if we are not tracing */
+	if (this_cpu_read(tr->trace_buffer.data->ignore_pid))
+		return;
+
+	pid_list = rcu_dereference_sched(tr->filtered_pids);
+
+	/* Set tracing if current is enabled */
+	this_cpu_write(tr->trace_buffer.data->ignore_pid,
+		       check_ignore_pid(pid_list, current));
+}
+
+static void __ftrace_clear_event_pids(struct trace_array *tr)
+{
+	struct trace_pid_list *pid_list;
+	struct trace_event_file *file;
+	int cpu;
+
+	pid_list = rcu_dereference_protected(tr->filtered_pids,
+					     lockdep_is_held(&event_mutex));
+	if (!pid_list)
+		return;
+
+	unregister_trace_sched_switch(event_filter_pid_sched_switch_probe_pre, tr);
+	unregister_trace_sched_switch(event_filter_pid_sched_switch_probe_post, tr);
+
+	unregister_trace_sched_wakeup(event_filter_pid_sched_wakeup_probe_pre, tr);
+	unregister_trace_sched_wakeup(event_filter_pid_sched_wakeup_probe_post, tr);
+
+	list_for_each_entry(file, &tr->events, list) {
+		clear_bit(EVENT_FILE_FL_PID_FILTER_BIT, &file->flags);
+	}
+
+	for_each_possible_cpu(cpu)
+		per_cpu_ptr(tr->trace_buffer.data, cpu)->ignore_pid = false;
+
+	rcu_assign_pointer(tr->filtered_pids, NULL);
+
+	/* Wait till all users are no longer using pid filtering */
+	synchronize_sched();
+
+	free_pages((unsigned long)pid_list->pids, pid_list->order);
+	kfree(pid_list);
+}
+
+static void ftrace_clear_event_pids(struct trace_array *tr)
+{
+	mutex_lock(&event_mutex);
+	__ftrace_clear_event_pids(tr);
+	mutex_unlock(&event_mutex);
+}
+
 static void __put_system(struct event_subsystem *system)
 {
 	struct event_filter *filter = system->filter;
@@ -460,8 +619,7 @@ static void __put_system(struct event_subsystem *system)
 		kfree(filter->filter_string);
 		kfree(filter);
 	}
-	if (system->ref_count & SYSTEM_FL_FREE_NAME)
-		kfree(system->name);
+	kfree_const(system->name);
 	kfree(system);
 }
 
@@ -779,6 +937,58 @@ static void t_stop(struct seq_file *m, void *p)
 	mutex_unlock(&event_mutex);
 }
 
+static void *p_start(struct seq_file *m, loff_t *pos)
+	__acquires(RCU)
+{
+	struct trace_pid_list *pid_list;
+	struct trace_array *tr = m->private;
+
+	/*
+	 * Grab the mutex, to keep calls to p_next() having the same
+	 * tr->filtered_pids as p_start() has.
+	 * If we just passed the tr->filtered_pids around, then RCU would
+	 * have been enough, but doing that makes things more complex.
+	 */
+	mutex_lock(&event_mutex);
+	rcu_read_lock_sched();
+
+	pid_list = rcu_dereference_sched(tr->filtered_pids);
+
+	if (!pid_list || *pos >= pid_list->nr_pids)
+		return NULL;
+
+	return (void *)&pid_list->pids[*pos];
+}
+
+static void p_stop(struct seq_file *m, void *p)
+	__releases(RCU)
+{
+	rcu_read_unlock_sched();
+	mutex_unlock(&event_mutex);
+}
+
+static void *
+p_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct trace_array *tr = m->private;
+	struct trace_pid_list *pid_list = rcu_dereference_sched(tr->filtered_pids);
+
+	(*pos)++;
+
+	if (*pos >= pid_list->nr_pids)
+		return NULL;
+
+	return (void *)&pid_list->pids[*pos];
+}
+
+static int p_show(struct seq_file *m, void *v)
+{
+	pid_t *pid = v;
+
+	seq_printf(m, "%d\n", *pid);
+	return 0;
+}
+
 static ssize_t
 event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
 		  loff_t *ppos)
@@ -1336,8 +1546,209 @@ show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
 	return r;
 }
 
+static int max_pids(struct trace_pid_list *pid_list)
+{
+	return (PAGE_SIZE << pid_list->order) / sizeof(pid_t);
+}
+
+static void ignore_task_cpu(void *data)
+{
+	struct trace_array *tr = data;
+	struct trace_pid_list *pid_list;
+
+	/*
+	 * This function is called by on_each_cpu() while the
+	 * event_mutex is held.
+	 */
+	pid_list = rcu_dereference_protected(tr->filtered_pids,
+					     mutex_is_locked(&event_mutex));
+
+	this_cpu_write(tr->trace_buffer.data->ignore_pid,
+		       check_ignore_pid(pid_list, current));
+}
+
+static ssize_t
+ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
+		       size_t cnt, loff_t *ppos)
+{
+	struct seq_file *m = filp->private_data;
+	struct trace_array *tr = m->private;
+	struct trace_pid_list *filtered_pids = NULL;
+	struct trace_pid_list *pid_list = NULL;
+	struct trace_event_file *file;
+	struct trace_parser parser;
+	unsigned long val;
+	loff_t this_pos;
+	ssize_t read = 0;
+	ssize_t ret = 0;
+	pid_t pid;
+	int i;
+
+	if (!cnt)
+		return 0;
+
+	ret = tracing_update_buffers();
+	if (ret < 0)
+		return ret;
+
+	if (trace_parser_get_init(&parser, EVENT_BUF_SIZE + 1))
+		return -ENOMEM;
+
+	mutex_lock(&event_mutex);
+	/*
+	 * Load as many pids into the array before doing a
+	 * swap from the tr->filtered_pids to the new list.
+	 */
+	while (cnt > 0) {
+
+		this_pos = 0;
+
+		ret = trace_get_user(&parser, ubuf, cnt, &this_pos);
+		if (ret < 0 || !trace_parser_loaded(&parser))
+			break;
+
+		read += ret;
+		ubuf += ret;
+		cnt -= ret;
+
+		parser.buffer[parser.idx] = 0;
+
+		ret = -EINVAL;
+		if (kstrtoul(parser.buffer, 0, &val))
+			break;
+		if (val > INT_MAX)
+			break;
+
+		pid = (pid_t)val;
+
+		ret = -ENOMEM;
+		if (!pid_list) {
+			pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL);
+			if (!pid_list)
+				break;
+
+			filtered_pids = rcu_dereference_protected(tr->filtered_pids,
+							lockdep_is_held(&event_mutex));
+			if (filtered_pids)
+				pid_list->order = filtered_pids->order;
+			else
+				pid_list->order = 0;
+
+			pid_list->pids = (void *)__get_free_pages(GFP_KERNEL,
+								  pid_list->order);
+			if (!pid_list->pids)
+				break;
+
+			if (filtered_pids) {
+				pid_list->nr_pids = filtered_pids->nr_pids;
+				memcpy(pid_list->pids, filtered_pids->pids,
+				       pid_list->nr_pids * sizeof(pid_t));
+			} else
+				pid_list->nr_pids = 0;
+		}
+
+		if (pid_list->nr_pids >= max_pids(pid_list)) {
+			pid_t *pid_page;
+
+			pid_page = (void *)__get_free_pages(GFP_KERNEL,
+							    pid_list->order + 1);
+			if (!pid_page)
+				break;
+			memcpy(pid_page, pid_list->pids,
+			       pid_list->nr_pids * sizeof(pid_t));
+			free_pages((unsigned long)pid_list->pids, pid_list->order);
+
+			pid_list->order++;
+			pid_list->pids = pid_page;
+		}
+
+		pid_list->pids[pid_list->nr_pids++] = pid;
+		trace_parser_clear(&parser);
+		ret = 0;
+	}
+	trace_parser_put(&parser);
+
+	if (ret < 0) {
+		if (pid_list)
+			free_pages((unsigned long)pid_list->pids, pid_list->order);
+		kfree(pid_list);
+		mutex_unlock(&event_mutex);
+		return ret;
+	}
+
+	if (!pid_list) {
+		mutex_unlock(&event_mutex);
+		return ret;
+	}
+
+	sort(pid_list->pids, pid_list->nr_pids, sizeof(pid_t), cmp_pid, NULL);
+
+	/* Remove duplicates */
+	for (i = 1; i < pid_list->nr_pids; i++) {
+		int start = i;
+
+		while (i < pid_list->nr_pids &&
+		       pid_list->pids[i - 1] == pid_list->pids[i])
+			i++;
+
+		if (start != i) {
+			if (i < pid_list->nr_pids) {
+				memmove(&pid_list->pids[start], &pid_list->pids[i],
+					(pid_list->nr_pids - i) * sizeof(pid_t));
+				pid_list->nr_pids -= i - start;
+				i = start;
+			} else
+				pid_list->nr_pids = start;
+		}
+	}
+
+	rcu_assign_pointer(tr->filtered_pids, pid_list);
+
+	list_for_each_entry(file, &tr->events, list) {
+		set_bit(EVENT_FILE_FL_PID_FILTER_BIT, &file->flags);
+	}
+
+	if (filtered_pids) {
+		synchronize_sched();
+
+		free_pages((unsigned long)filtered_pids->pids, filtered_pids->order);
+		kfree(filtered_pids);
+	} else {
+		/*
+		 * Register a probe that is called before all other probes
+		 * to set ignore_pid if next or prev do not match.
+		 * Register a probe this is called after all other probes
+		 * to only keep ignore_pid set if next pid matches.
+		 */
+		register_trace_prio_sched_switch(event_filter_pid_sched_switch_probe_pre,
+						 tr, INT_MAX);
+		register_trace_prio_sched_switch(event_filter_pid_sched_switch_probe_post,
+						 tr, 0);
+
+		register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_pre,
+						 tr, INT_MAX);
+		register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_post,
+						 tr, 0);
+	}
+
+	/*
+	 * Ignoring of pids is done at task switch. But we have to
+	 * check for those tasks that are currently running.
+	 * Always do this in case a pid was appended or removed.
+	 */
+	on_each_cpu(ignore_task_cpu, tr, 1);
+
+	mutex_unlock(&event_mutex);
+
+	ret = read;
+	*ppos += read;
+
+	return ret;
+}
+
 static int ftrace_event_avail_open(struct inode *inode, struct file *file);
 static int ftrace_event_set_open(struct inode *inode, struct file *file);
+static int ftrace_event_set_pid_open(struct inode *inode, struct file *file);
 static int ftrace_event_release(struct inode *inode, struct file *file);
 
 static const struct seq_operations show_event_seq_ops = {
@@ -1354,6 +1765,13 @@ static const struct seq_operations show_set_event_seq_ops = {
 	.stop = t_stop,
 };
 
+static const struct seq_operations show_set_pid_seq_ops = {
+	.start = p_start,
+	.next = p_next,
+	.show = p_show,
+	.stop = p_stop,
+};
+
 static const struct file_operations ftrace_avail_fops = {
 	.open = ftrace_event_avail_open,
 	.read = seq_read,
@@ -1369,6 +1787,14 @@ static const struct file_operations ftrace_set_event_fops = {
 	.release = ftrace_event_release,
 };
 
+static const struct file_operations ftrace_set_event_pid_fops = {
+	.open = ftrace_event_set_pid_open,
+	.read = seq_read,
+	.write = ftrace_event_pid_write,
+	.llseek = seq_lseek,
+	.release = ftrace_event_release,
+};
+
 static const struct file_operations ftrace_enable_fops = {
 	.open = tracing_open_generic,
 	.read = event_enable_read,
@@ -1479,6 +1905,26 @@ ftrace_event_set_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
+static int
+ftrace_event_set_pid_open(struct inode *inode, struct file *file)
+{
+	const struct seq_operations *seq_ops = &show_set_pid_seq_ops;
+	struct trace_array *tr = inode->i_private;
+	int ret;
+
+	if (trace_array_get(tr) < 0)
+		return -ENODEV;
+
+	if ((file->f_mode & FMODE_WRITE) &&
+	    (file->f_flags & O_TRUNC))
+		ftrace_clear_event_pids(tr);
+
+	ret = ftrace_event_open(inode, file, seq_ops);
+	if (ret < 0)
+		trace_array_put(tr);
+	return ret;
+}
+
 static struct event_subsystem *
 create_new_subsystem(const char *name)
 {
@@ -1492,13 +1938,9 @@ create_new_subsystem(const char *name)
 	system->ref_count = 1;
 
 	/* Only allocate if dynamic (kprobes and modules) */
-	if (!core_kernel_data((unsigned long)name)) {
-		system->ref_count |= SYSTEM_FL_FREE_NAME;
-		system->name = kstrdup(name, GFP_KERNEL);
-		if (!system->name)
-			goto out_free;
-	} else
-		system->name = name;
+	system->name = kstrdup_const(name, GFP_KERNEL);
+	if (!system->name)
+		goto out_free;
 
 	system->filter = NULL;
 
@@ -1511,8 +1953,7 @@ create_new_subsystem(const char *name)
 	return system;
 
  out_free:
-	if (system->ref_count & SYSTEM_FL_FREE_NAME)
-		kfree(system->name);
+	kfree_const(system->name);
 	kfree(system);
 	return NULL;
 }
@@ -2478,6 +2919,9 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
 		return -ENOMEM;
 	}
 
+	entry = tracefs_create_file("set_event_pid", 0644, parent,
+				    tr, &ftrace_set_event_pid_fops);
+
 	/* ring buffer internal formats */
 	trace_create_file("header_page", 0444, d_events,
 			  ring_buffer_print_page_header,
@@ -2558,6 +3002,9 @@ int event_trace_del_tracer(struct trace_array *tr)
 	/* Disable any event triggers and associated soft-disabled events */
 	clear_event_triggers(tr);
 
+	/* Clear the pid list */
+	__ftrace_clear_event_pids(tr);
+
 	/* Disable any running events */
 	__ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0);
 
@@ -2595,16 +3042,16 @@ early_enable_events(struct trace_array *tr, bool disable_first)
 
 		if (!token)
 			break;
-		if (!*token)
-			continue;
 
-		/* Restarting syscalls requires that we stop them first */
-		if (disable_first)
-			ftrace_set_clr_event(tr, token, 0);
+		if (*token) {
+			/* Restarting syscalls requires that we stop them first */
+			if (disable_first)
+				ftrace_set_clr_event(tr, token, 0);
 
-		ret = ftrace_set_clr_event(tr, token, 1);
-		if (ret)
-			pr_warn("Failed to enable trace event: %s\n", token);
+			ret = ftrace_set_clr_event(tr, token, 1);
+			if (ret)
+				pr_warn("Failed to enable trace event: %s\n", token);
+		}
 
 		/* Put back the comma to allow this to be called again */
 		if (buf)
@@ -2891,7 +3338,9 @@ static __init void event_trace_self_tests(void)
 
 static DEFINE_PER_CPU(atomic_t, ftrace_test_event_disable);
 
-static void
+static struct trace_array *event_tr;
+
+static void __init
 function_test_events_call(unsigned long ip, unsigned long parent_ip,
 			  struct ftrace_ops *op, struct pt_regs *pt_regs)
 {
@@ -2922,7 +3371,7 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip,
 	entry->ip			= ip;
 	entry->parent_ip		= parent_ip;
 
-	trace_buffer_unlock_commit(buffer, event, flags, pc);
+	trace_buffer_unlock_commit(event_tr, buffer, event, flags, pc);
 
  out:
 	atomic_dec(&per_cpu(ftrace_test_event_disable, cpu));
@@ -2938,6 +3387,9 @@ static struct ftrace_ops trace_ops __initdata  =
 static __init void event_trace_self_test_with_function(void)
 {
 	int ret;
+	event_tr = top_trace_array();
+	if (WARN_ON(!event_tr))
+		return;
 	ret = register_ftrace_function(&trace_ops);
 	if (WARN_ON(ret < 0)) {
 		pr_info("Failed to enable function tracer for event tests\n");

kernel/trace/trace_events_filter.c

@@ -973,15 +973,15 @@ static bool is_string_field(struct ftrace_event_field *field)
 	       field->filter_type == FILTER_PTR_STRING;
 }
 
-static int is_legal_op(struct ftrace_event_field *field, int op)
+static bool is_legal_op(struct ftrace_event_field *field, int op)
 {
 	if (is_string_field(field) &&
 	    (op != OP_EQ && op != OP_NE && op != OP_GLOB))
-		return 0;
+		return false;
 	if (!is_string_field(field) && op == OP_GLOB)
-		return 0;
+		return false;
 
-	return 1;
+	return true;
 }
 
 static filter_pred_fn_t select_comparison_fn(int op, int field_size,

kernel/trace/trace_export.c

@@ -187,7 +187,7 @@ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
 	FTRACE_ENTRY_REG(call, struct_name, etype,			\
 			 PARAMS(tstruct), PARAMS(print), filter, NULL)
 
-int ftrace_event_is_function(struct trace_event_call *call)
+bool ftrace_event_is_function(struct trace_event_call *call)
 {
 	return call == &event_function;
 }

kernel/trace/trace_functions_graph.c

@@ -83,13 +83,18 @@ static struct tracer_opt trace_opts[] = {
 	{ TRACER_OPT(funcgraph-irqs, TRACE_GRAPH_PRINT_IRQS) },
 	/* Display function name after trailing } */
 	{ TRACER_OPT(funcgraph-tail, TRACE_GRAPH_PRINT_TAIL) },
+	/* Include sleep time (scheduled out) between entry and return */
+	{ TRACER_OPT(sleep-time, TRACE_GRAPH_SLEEP_TIME) },
+	/* Include time within nested functions */
+	{ TRACER_OPT(graph-time, TRACE_GRAPH_GRAPH_TIME) },
 	{ } /* Empty entry */
 };
 
 static struct tracer_flags tracer_flags = {
 	/* Don't display overruns, proc, or tail by default */
 	.val = TRACE_GRAPH_PRINT_CPU | TRACE_GRAPH_PRINT_OVERHEAD |
-	       TRACE_GRAPH_PRINT_DURATION | TRACE_GRAPH_PRINT_IRQS,
+	       TRACE_GRAPH_PRINT_DURATION | TRACE_GRAPH_PRINT_IRQS |
+	       TRACE_GRAPH_SLEEP_TIME | TRACE_GRAPH_GRAPH_TIME,
 	.opts = trace_opts
 };
 
@@ -107,8 +112,8 @@ enum {
 };
 
 static void
-print_graph_duration(unsigned long long duration, struct trace_seq *s,
-		     u32 flags);
+print_graph_duration(struct trace_array *tr, unsigned long long duration,
+		     struct trace_seq *s, u32 flags);
 
 /* Add a function return address to the trace stack on thread info.*/
 int
@@ -653,6 +658,7 @@ static void
 print_graph_irq(struct trace_iterator *iter, unsigned long addr,
 		enum trace_type type, int cpu, pid_t pid, u32 flags)
 {
+	struct trace_array *tr = iter->tr;
 	struct trace_seq *s = &iter->seq;
 	struct trace_entry *ent = iter->ent;
 
@@ -660,7 +666,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
 		addr >= (unsigned long)__irqentry_text_end)
 		return;
 
-	if (trace_flags & TRACE_ITER_CONTEXT_INFO) {
+	if (tr->trace_flags & TRACE_ITER_CONTEXT_INFO) {
 		/* Absolute time */
 		if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
 			print_graph_abs_time(iter->ts, s);
@@ -676,19 +682,19 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
 		}
 
 		/* Latency format */
-		if (trace_flags & TRACE_ITER_LATENCY_FMT)
+		if (tr->trace_flags & TRACE_ITER_LATENCY_FMT)
 			print_graph_lat_fmt(s, ent);
 	}
 
 	/* No overhead */
-	print_graph_duration(0, s, flags | FLAGS_FILL_START);
+	print_graph_duration(tr, 0, s, flags | FLAGS_FILL_START);
 
 	if (type == TRACE_GRAPH_ENT)
 		trace_seq_puts(s, "==========>");
 	else
 		trace_seq_puts(s, "<==========");
 
-	print_graph_duration(0, s, flags | FLAGS_FILL_END);
+	print_graph_duration(tr, 0, s, flags | FLAGS_FILL_END);
 	trace_seq_putc(s, '\n');
 }
 
@@ -726,11 +732,11 @@ trace_print_graph_duration(unsigned long long duration, struct trace_seq *s)
 }
 
 static void
-print_graph_duration(unsigned long long duration, struct trace_seq *s,
-		     u32 flags)
+print_graph_duration(struct trace_array *tr, unsigned long long duration,
+		     struct trace_seq *s, u32 flags)
 {
 	if (!(flags & TRACE_GRAPH_PRINT_DURATION) ||
-	    !(trace_flags & TRACE_ITER_CONTEXT_INFO))
+	    !(tr->trace_flags & TRACE_ITER_CONTEXT_INFO))
 		return;
 
 	/* No real adata, just filling the column with spaces */
@@ -764,6 +770,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 		struct trace_seq *s, u32 flags)
 {
 	struct fgraph_data *data = iter->private;
+	struct trace_array *tr = iter->tr;
 	struct ftrace_graph_ret *graph_ret;
 	struct ftrace_graph_ent *call;
 	unsigned long long duration;
@@ -792,7 +799,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 	}
 
 	/* Overhead and duration */
-	print_graph_duration(duration, s, flags);
+	print_graph_duration(tr, duration, s, flags);
 
 	/* Function */
 	for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++)
@@ -810,6 +817,7 @@ print_graph_entry_nested(struct trace_iterator *iter,
 {
 	struct ftrace_graph_ent *call = &entry->graph_ent;
 	struct fgraph_data *data = iter->private;
+	struct trace_array *tr = iter->tr;
 	int i;
 
 	if (data) {
@@ -825,7 +833,7 @@ print_graph_entry_nested(struct trace_iterator *iter,
 	}
 
 	/* No time */
-	print_graph_duration(0, s, flags | FLAGS_FILL_FULL);
+	print_graph_duration(tr, 0, s, flags | FLAGS_FILL_FULL);
 
 	/* Function */
 	for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++)
@@ -849,6 +857,7 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
 {
 	struct fgraph_data *data = iter->private;
 	struct trace_entry *ent = iter->ent;
+	struct trace_array *tr = iter->tr;
 	int cpu = iter->cpu;
 
 	/* Pid */
@@ -858,7 +867,7 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
 		/* Interrupt */
 		print_graph_irq(iter, addr, type, cpu, ent->pid, flags);
 
-	if (!(trace_flags & TRACE_ITER_CONTEXT_INFO))
+	if (!(tr->trace_flags & TRACE_ITER_CONTEXT_INFO))
 		return;
 
 	/* Absolute time */
@@ -876,7 +885,7 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
 	}
 
 	/* Latency format */
-	if (trace_flags & TRACE_ITER_LATENCY_FMT)
+	if (tr->trace_flags & TRACE_ITER_LATENCY_FMT)
 		print_graph_lat_fmt(s, ent);
 
 	return;
@@ -1027,6 +1036,7 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 {
 	unsigned long long duration = trace->rettime - trace->calltime;
 	struct fgraph_data *data = iter->private;
+	struct trace_array *tr = iter->tr;
 	pid_t pid = ent->pid;
 	int cpu = iter->cpu;
 	int func_match = 1;
@@ -1058,7 +1068,7 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 	print_graph_prologue(iter, s, 0, 0, flags);
 
 	/* Overhead and duration */
-	print_graph_duration(duration, s, flags);
+	print_graph_duration(tr, duration, s, flags);
 
 	/* Closing brace */
 	for (i = 0; i < trace->depth * TRACE_GRAPH_INDENT; i++)
@@ -1091,7 +1101,8 @@ static enum print_line_t
 print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
 		    struct trace_iterator *iter, u32 flags)
 {
-	unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
+	struct trace_array *tr = iter->tr;
+	unsigned long sym_flags = (tr->trace_flags & TRACE_ITER_SYM_MASK);
 	struct fgraph_data *data = iter->private;
 	struct trace_event *event;
 	int depth = 0;
@@ -1104,7 +1115,7 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
 	print_graph_prologue(iter, s, 0, 0, flags);
 
 	/* No time */
-	print_graph_duration(0, s, flags | FLAGS_FILL_FULL);
+	print_graph_duration(tr, 0, s, flags | FLAGS_FILL_FULL);
 
 	/* Indentation */
 	if (depth > 0)
@@ -1245,9 +1256,10 @@ static void print_lat_header(struct seq_file *s, u32 flags)
 	seq_printf(s, "#%.*s||| /                      \n", size, spaces);
 }
 
-static void __print_graph_headers_flags(struct seq_file *s, u32 flags)
+static void __print_graph_headers_flags(struct trace_array *tr,
+					struct seq_file *s, u32 flags)
 {
-	int lat = trace_flags & TRACE_ITER_LATENCY_FMT;
+	int lat = tr->trace_flags & TRACE_ITER_LATENCY_FMT;
 
 	if (lat)
 		print_lat_header(s, flags);
@@ -1289,11 +1301,12 @@ static void print_graph_headers(struct seq_file *s)
 void print_graph_headers_flags(struct seq_file *s, u32 flags)
 {
 	struct trace_iterator *iter = s->private;
+	struct trace_array *tr = iter->tr;
 
-	if (!(trace_flags & TRACE_ITER_CONTEXT_INFO))
+	if (!(tr->trace_flags & TRACE_ITER_CONTEXT_INFO))
 		return;
 
-	if (trace_flags & TRACE_ITER_LATENCY_FMT) {
+	if (tr->trace_flags & TRACE_ITER_LATENCY_FMT) {
 		/* print nothing if the buffers are empty */
 		if (trace_empty(iter))
 			return;
@@ -1301,7 +1314,7 @@ void print_graph_headers_flags(struct seq_file *s, u32 flags)
 		print_trace_header(s, iter);
 	}
 
-	__print_graph_headers_flags(s, flags);
+	__print_graph_headers_flags(tr, s, flags);
 }
 
 void graph_trace_open(struct trace_iterator *iter)
@@ -1362,6 +1375,12 @@ func_graph_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 	if (bit == TRACE_GRAPH_PRINT_IRQS)
 		ftrace_graph_skip_irqs = !set;
 
+	if (bit == TRACE_GRAPH_SLEEP_TIME)
+		ftrace_graph_sleep_time_control(set);
+
+	if (bit == TRACE_GRAPH_GRAPH_TIME)
+		ftrace_graph_graph_time_control(set);
+
 	return 0;
 }
 

kernel/trace/trace_irqsoff.c

@@ -31,7 +31,6 @@ enum {
 static int trace_type __read_mostly;
 
 static int save_flags;
-static bool function_enabled;
 
 static void stop_irqsoff_tracer(struct trace_array *tr, int graph);
 static int start_irqsoff_tracer(struct trace_array *tr, int graph);
@@ -57,22 +56,16 @@ irq_trace(void)
 # define irq_trace() (0)
 #endif
 
-#define TRACE_DISPLAY_GRAPH	1
-
-static struct tracer_opt trace_opts[] = {
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	/* display latency trace as call graph */
-	{ TRACER_OPT(display-graph, TRACE_DISPLAY_GRAPH) },
+static int irqsoff_display_graph(struct trace_array *tr, int set);
+# define is_graph(tr) ((tr)->trace_flags & TRACE_ITER_DISPLAY_GRAPH)
+#else
+static inline int irqsoff_display_graph(struct trace_array *tr, int set)
+{
+	return -EINVAL;
+}
+# define is_graph(tr) false
 #endif
-	{ } /* Empty entry */
-};
-
-static struct tracer_flags tracer_flags = {
-	.val  = 0,
-	.opts = trace_opts,
-};
-
-#define is_graph() (tracer_flags.val & TRACE_DISPLAY_GRAPH)
 
 /*
  * Sequence count - we record it when starting a measurement and
@@ -152,15 +145,11 @@ irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip,
 #endif /* CONFIG_FUNCTION_TRACER */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static int
-irqsoff_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
+static int irqsoff_display_graph(struct trace_array *tr, int set)
 {
 	int cpu;
 
-	if (!(bit & TRACE_DISPLAY_GRAPH))
-		return -EINVAL;
-
-	if (!(is_graph() ^ set))
+	if (!(is_graph(tr) ^ set))
 		return 0;
 
 	stop_irqsoff_tracer(irqsoff_trace, !set);
@@ -209,7 +198,7 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace)
 
 static void irqsoff_trace_open(struct trace_iterator *iter)
 {
-	if (is_graph())
+	if (is_graph(iter->tr))
 		graph_trace_open(iter);
 
 }
@@ -231,7 +220,7 @@ static enum print_line_t irqsoff_print_line(struct trace_iterator *iter)
 	 * In graph mode call the graph tracer output function,
 	 * otherwise go with the TRACE_FN event handler
 	 */
-	if (is_graph())
+	if (is_graph(iter->tr))
 		return print_graph_function_flags(iter, GRAPH_TRACER_FLAGS);
 
 	return TRACE_TYPE_UNHANDLED;
@@ -239,7 +228,9 @@ static enum print_line_t irqsoff_print_line(struct trace_iterator *iter)
 
 static void irqsoff_print_header(struct seq_file *s)
 {
-	if (is_graph())
+	struct trace_array *tr = irqsoff_trace;
+
+	if (is_graph(tr))
 		print_graph_headers_flags(s, GRAPH_TRACER_FLAGS);
 	else
 		trace_default_header(s);
@@ -250,7 +241,7 @@ __trace_function(struct trace_array *tr,
 		 unsigned long ip, unsigned long parent_ip,
 		 unsigned long flags, int pc)
 {
-	if (is_graph())
+	if (is_graph(tr))
 		trace_graph_function(tr, ip, parent_ip, flags, pc);
 	else
 		trace_function(tr, ip, parent_ip, flags, pc);
@@ -259,27 +250,23 @@ __trace_function(struct trace_array *tr,
 #else
 #define __trace_function trace_function
 
-static int
-irqsoff_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
-{
-	return -EINVAL;
-}
-
+#ifdef CONFIG_FUNCTION_TRACER
 static int irqsoff_graph_entry(struct ftrace_graph_ent *trace)
 {
 	return -1;
 }
+#endif
 
 static enum print_line_t irqsoff_print_line(struct trace_iterator *iter)
 {
 	return TRACE_TYPE_UNHANDLED;
 }
 
-static void irqsoff_graph_return(struct ftrace_graph_ret *trace) { }
 static void irqsoff_trace_open(struct trace_iterator *iter) { }
 static void irqsoff_trace_close(struct trace_iterator *iter) { }
 
 #ifdef CONFIG_FUNCTION_TRACER
+static void irqsoff_graph_return(struct ftrace_graph_ret *trace) { }
 static void irqsoff_print_header(struct seq_file *s)
 {
 	trace_default_header(s);
@@ -295,16 +282,16 @@ static void irqsoff_print_header(struct seq_file *s)
 /*
  * Should this new latency be reported/recorded?
  */
-static int report_latency(struct trace_array *tr, cycle_t delta)
+static bool report_latency(struct trace_array *tr, cycle_t delta)
 {
 	if (tracing_thresh) {
 		if (delta < tracing_thresh)
-			return 0;
+			return false;
 	} else {
 		if (delta <= tr->max_latency)
-			return 0;
+			return false;
 	}
-	return 1;
+	return true;
 }
 
 static void
@@ -523,12 +510,15 @@ void trace_preempt_off(unsigned long a0, unsigned long a1)
 }
 #endif /* CONFIG_PREEMPT_TRACER */
 
+#ifdef CONFIG_FUNCTION_TRACER
+static bool function_enabled;
+
 static int register_irqsoff_function(struct trace_array *tr, int graph, int set)
 {
 	int ret;
 
 	/* 'set' is set if TRACE_ITER_FUNCTION is about to be set */
-	if (function_enabled || (!set && !(trace_flags & TRACE_ITER_FUNCTION)))
+	if (function_enabled || (!set && !(tr->trace_flags & TRACE_ITER_FUNCTION)))
 		return 0;
 
 	if (graph)
@@ -556,20 +546,40 @@ static void unregister_irqsoff_function(struct trace_array *tr, int graph)
 	function_enabled = false;
 }
 
-static void irqsoff_function_set(struct trace_array *tr, int set)
+static int irqsoff_function_set(struct trace_array *tr, u32 mask, int set)
 {
+	if (!(mask & TRACE_ITER_FUNCTION))
+		return 0;
+
 	if (set)
-		register_irqsoff_function(tr, is_graph(), 1);
+		register_irqsoff_function(tr, is_graph(tr), 1);
 	else
-		unregister_irqsoff_function(tr, is_graph());
+		unregister_irqsoff_function(tr, is_graph(tr));
+	return 1;
+}
+#else
+static int register_irqsoff_function(struct trace_array *tr, int graph, int set)
+{
+	return 0;
+}
+static void unregister_irqsoff_function(struct trace_array *tr, int graph) { }
+static inline int irqsoff_function_set(struct trace_array *tr, u32 mask, int set)
+{
+	return 0;
 }
+#endif /* CONFIG_FUNCTION_TRACER */
 
 static int irqsoff_flag_changed(struct trace_array *tr, u32 mask, int set)
 {
 	struct tracer *tracer = tr->current_trace;
 
-	if (mask & TRACE_ITER_FUNCTION)
-		irqsoff_function_set(tr, set);
+	if (irqsoff_function_set(tr, mask, set))
+		return 0;
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	if (mask & TRACE_ITER_DISPLAY_GRAPH)
+		return irqsoff_display_graph(tr, set);
+#endif
 
 	return trace_keep_overwrite(tracer, mask, set);
 }
@@ -602,7 +612,7 @@ static int __irqsoff_tracer_init(struct trace_array *tr)
 	if (irqsoff_busy)
 		return -EBUSY;
 
-	save_flags = trace_flags;
+	save_flags = tr->trace_flags;
 
 	/* non overwrite screws up the latency tracers */
 	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1);
@@ -618,7 +628,7 @@ static int __irqsoff_tracer_init(struct trace_array *tr)
 
 	/* Only toplevel instance supports graph tracing */
 	if (start_irqsoff_tracer(tr, (tr->flags & TRACE_ARRAY_FL_GLOBAL &&
-				      is_graph())))
+				      is_graph(tr))))
 		printk(KERN_ERR "failed to start irqsoff tracer\n");
 
 	irqsoff_busy = true;
@@ -630,7 +640,7 @@ static void irqsoff_tracer_reset(struct trace_array *tr)
 	int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
 	int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
 
-	stop_irqsoff_tracer(tr, is_graph());
+	stop_irqsoff_tracer(tr, is_graph(tr));
 
 	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, lat_flag);
 	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag);
@@ -666,8 +676,6 @@ static struct tracer irqsoff_tracer __read_mostly =
 	.print_max	= true,
 	.print_header   = irqsoff_print_header,
 	.print_line     = irqsoff_print_line,
-	.flags		= &tracer_flags,
-	.set_flag	= irqsoff_set_flag,
 	.flag_changed	= irqsoff_flag_changed,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_irqsoff,
@@ -700,8 +708,6 @@ static struct tracer preemptoff_tracer __read_mostly =
 	.print_max	= true,
 	.print_header   = irqsoff_print_header,
 	.print_line     = irqsoff_print_line,
-	.flags		= &tracer_flags,
-	.set_flag	= irqsoff_set_flag,
 	.flag_changed	= irqsoff_flag_changed,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_preemptoff,
@@ -736,8 +742,6 @@ static struct tracer preemptirqsoff_tracer __read_mostly =
 	.print_max	= true,
 	.print_header   = irqsoff_print_header,
 	.print_line     = irqsoff_print_line,
-	.flags		= &tracer_flags,
-	.set_flag	= irqsoff_set_flag,
 	.flag_changed	= irqsoff_flag_changed,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_preemptirqsoff,

kernel/trace/trace_kdb.c

@@ -21,20 +21,22 @@ static void ftrace_dump_buf(int skip_lines, long cpu_file)
 	/* use static because iter can be a bit big for the stack */
 	static struct trace_iterator iter;
 	static struct ring_buffer_iter *buffer_iter[CONFIG_NR_CPUS];
+	struct trace_array *tr;
 	unsigned int old_userobj;
 	int cnt = 0, cpu;
 
 	trace_init_global_iter(&iter);
 	iter.buffer_iter = buffer_iter;
+	tr = iter.tr;
 
 	for_each_tracing_cpu(cpu) {
 		atomic_inc(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled);
 	}
 
-	old_userobj = trace_flags;
+	old_userobj = tr->trace_flags;
 
 	/* don't look at user memory in panic mode */
-	trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
+	tr->trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
 
 	kdb_printf("Dumping ftrace buffer:\n");
 
@@ -82,7 +84,7 @@ static void ftrace_dump_buf(int skip_lines, long cpu_file)
 		kdb_printf("---------------------------------\n");
 
 out:
-	trace_flags = old_userobj;
+	tr->trace_flags = old_userobj;
 
 	for_each_tracing_cpu(cpu) {
 		atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled);

kernel/trace/trace_mmiotrace.c

@@ -314,7 +314,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
 	entry->rw			= *rw;
 
 	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit(buffer, event, 0, pc);
+		trace_buffer_unlock_commit(tr, buffer, event, 0, pc);
 }
 
 void mmio_trace_rw(struct mmiotrace_rw *rw)
@@ -344,7 +344,7 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
 	entry->map			= *map;
 
 	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit(buffer, event, 0, pc);
+		trace_buffer_unlock_commit(tr, buffer, event, 0, pc);
 }
 
 void mmio_trace_mapping(struct mmiotrace_map *map)

kernel/trace/trace_output.c

@@ -322,8 +322,8 @@ seq_print_sym_offset(struct trace_seq *s, const char *fmt,
 # define IP_FMT "%016lx"
 #endif
 
-int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
-		      unsigned long ip, unsigned long sym_flags)
+static int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
+			     unsigned long ip, unsigned long sym_flags)
 {
 	struct file *file = NULL;
 	unsigned long vmstart = 0;
@@ -354,50 +354,6 @@ int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
 	return !trace_seq_has_overflowed(s);
 }
 
-int
-seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s,
-		      unsigned long sym_flags)
-{
-	struct mm_struct *mm = NULL;
-	unsigned int i;
-
-	if (trace_flags & TRACE_ITER_SYM_USEROBJ) {
-		struct task_struct *task;
-		/*
-		 * we do the lookup on the thread group leader,
-		 * since individual threads might have already quit!
-		 */
-		rcu_read_lock();
-		task = find_task_by_vpid(entry->tgid);
-		if (task)
-			mm = get_task_mm(task);
-		rcu_read_unlock();
-	}
-
-	for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
-		unsigned long ip = entry->caller[i];
-
-		if (ip == ULONG_MAX || trace_seq_has_overflowed(s))
-			break;
-
-		trace_seq_puts(s, " => ");
-
-		if (!ip) {
-			trace_seq_puts(s, "??");
-			trace_seq_putc(s, '\n');
-			continue;
-		}
-
-		seq_print_user_ip(s, mm, ip, sym_flags);
-		trace_seq_putc(s, '\n');
-	}
-
-	if (mm)
-		mmput(mm);
-
-	return !trace_seq_has_overflowed(s);
-}
-
 int
 seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
 {
@@ -520,7 +476,8 @@ char trace_find_mark(unsigned long long d)
 static int
 lat_print_timestamp(struct trace_iterator *iter, u64 next_ts)
 {
-	unsigned long verbose = trace_flags & TRACE_ITER_VERBOSE;
+	struct trace_array *tr = iter->tr;
+	unsigned long verbose = tr->trace_flags & TRACE_ITER_VERBOSE;
 	unsigned long in_ns = iter->iter_flags & TRACE_FILE_TIME_IN_NS;
 	unsigned long long abs_ts = iter->ts - iter->trace_buffer->time_start;
 	unsigned long long rel_ts = next_ts - iter->ts;
@@ -563,6 +520,7 @@ lat_print_timestamp(struct trace_iterator *iter, u64 next_ts)
 
 int trace_print_context(struct trace_iterator *iter)
 {
+	struct trace_array *tr = iter->tr;
 	struct trace_seq *s = &iter->seq;
 	struct trace_entry *entry = iter->ent;
 	unsigned long long t;
@@ -574,7 +532,7 @@ int trace_print_context(struct trace_iterator *iter)
 	trace_seq_printf(s, "%16s-%-5d [%03d] ",
 			       comm, entry->pid, iter->cpu);
 
-	if (trace_flags & TRACE_ITER_IRQ_INFO)
+	if (tr->trace_flags & TRACE_ITER_IRQ_INFO)
 		trace_print_lat_fmt(s, entry);
 
 	if (iter->iter_flags & TRACE_FILE_TIME_IN_NS) {
@@ -590,14 +548,15 @@ int trace_print_context(struct trace_iterator *iter)
 
 int trace_print_lat_context(struct trace_iterator *iter)
 {
-	u64 next_ts;
+	struct trace_array *tr = iter->tr;
 	/* trace_find_next_entry will reset ent_size */
 	int ent_size = iter->ent_size;
 	struct trace_seq *s = &iter->seq;
+	u64 next_ts;
 	struct trace_entry *entry = iter->ent,
 			   *next_entry = trace_find_next_entry(iter, NULL,
 							       &next_ts);
-	unsigned long verbose = (trace_flags & TRACE_ITER_VERBOSE);
+	unsigned long verbose = (tr->trace_flags & TRACE_ITER_VERBOSE);
 
 	/* Restore the original ent_size */
 	iter->ent_size = ent_size;
@@ -1079,13 +1038,49 @@ static struct trace_event trace_stack_event = {
 static enum print_line_t trace_user_stack_print(struct trace_iterator *iter,
 						int flags, struct trace_event *event)
 {
+	struct trace_array *tr = iter->tr;
 	struct userstack_entry *field;
 	struct trace_seq *s = &iter->seq;
+	struct mm_struct *mm = NULL;
+	unsigned int i;
 
 	trace_assign_type(field, iter->ent);
 
 	trace_seq_puts(s, "<user stack trace>\n");
-	seq_print_userip_objs(field, s, flags);
+
+	if (tr->trace_flags & TRACE_ITER_SYM_USEROBJ) {
+		struct task_struct *task;
+		/*
+		 * we do the lookup on the thread group leader,
+		 * since individual threads might have already quit!
+		 */
+		rcu_read_lock();
+		task = find_task_by_vpid(field->tgid);
+		if (task)
+			mm = get_task_mm(task);
+		rcu_read_unlock();
+	}
+
+	for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
+		unsigned long ip = field->caller[i];
+
+		if (ip == ULONG_MAX || trace_seq_has_overflowed(s))
+			break;
+
+		trace_seq_puts(s, " => ");
+
+		if (!ip) {
+			trace_seq_puts(s, "??");
+			trace_seq_putc(s, '\n');
+			continue;
+		}
+
+		seq_print_user_ip(s, mm, ip, flags);
+		trace_seq_putc(s, '\n');
+	}
+
+	if (mm)
+		mmput(mm);
 
 	return trace_handle_return(s);
 }

kernel/trace/trace_output.h

@@ -14,10 +14,6 @@ trace_print_printk_msg_only(struct trace_iterator *iter);
 extern int
 seq_print_ip_sym(struct trace_seq *s, unsigned long ip,
 		unsigned long sym_flags);
-extern int seq_print_userip_objs(const struct userstack_entry *entry,
-				 struct trace_seq *s, unsigned long sym_flags);
-extern int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
-			     unsigned long ip, unsigned long sym_flags);
 
 extern int trace_print_context(struct trace_iterator *iter);
 extern int trace_print_lat_context(struct trace_iterator *iter);

kernel/trace/trace_printk.c

@@ -178,6 +178,12 @@ static inline void format_mod_start(void) { }
 static inline void format_mod_stop(void) { }
 #endif /* CONFIG_MODULES */
 
+static bool __read_mostly trace_printk_enabled = true;
+
+void trace_printk_control(bool enabled)
+{
+	trace_printk_enabled = enabled;
+}
 
 __initdata_or_module static
 struct notifier_block module_trace_bprintk_format_nb = {
@@ -192,7 +198,7 @@ int __trace_bprintk(unsigned long ip, const char *fmt, ...)
 	if (unlikely(!fmt))
 		return 0;
 
-	if (!(trace_flags & TRACE_ITER_PRINTK))
+	if (!trace_printk_enabled)
 		return 0;
 
 	va_start(ap, fmt);
@@ -207,7 +213,7 @@ int __ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap)
 	if (unlikely(!fmt))
 		return 0;
 
-	if (!(trace_flags & TRACE_ITER_PRINTK))
+	if (!trace_printk_enabled)
 		return 0;
 
 	return trace_vbprintk(ip, fmt, ap);
@@ -219,7 +225,7 @@ int __trace_printk(unsigned long ip, const char *fmt, ...)
 	int ret;
 	va_list ap;
 
-	if (!(trace_flags & TRACE_ITER_PRINTK))
+	if (!trace_printk_enabled)
 		return 0;
 
 	va_start(ap, fmt);
@@ -231,7 +237,7 @@ EXPORT_SYMBOL_GPL(__trace_printk);
 
 int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap)
 {
-	if (!(trace_flags & TRACE_ITER_PRINTK))
+	if (!trace_printk_enabled)
 		return 0;
 
 	return trace_vprintk(ip, fmt, ap);

kernel/trace/trace_probe.h

@@ -302,15 +302,15 @@ static nokprobe_inline void call_fetch(struct fetch_param *fprm,
 }
 
 /* Check the name is good for event/group/fields */
-static inline int is_good_name(const char *name)
+static inline bool is_good_name(const char *name)
 {
 	if (!isalpha(*name) && *name != '_')
-		return 0;
+		return false;
 	while (*++name != '\0') {
 		if (!isalpha(*name) && !isdigit(*name) && *name != '_')
-			return 0;
+			return false;
 	}
-	return 1;
+	return true;
 }
 
 static inline struct event_file_link *

kernel/trace/trace_sched_wakeup.c

@@ -34,31 +34,28 @@ static arch_spinlock_t wakeup_lock =
 
 static void wakeup_reset(struct trace_array *tr);
 static void __wakeup_reset(struct trace_array *tr);
-static int wakeup_graph_entry(struct ftrace_graph_ent *trace);
-static void wakeup_graph_return(struct ftrace_graph_ret *trace);
 
 static int save_flags;
-static bool function_enabled;
-
-#define TRACE_DISPLAY_GRAPH     1
 
-static struct tracer_opt trace_opts[] = {
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	/* display latency trace as call graph */
-	{ TRACER_OPT(display-graph, TRACE_DISPLAY_GRAPH) },
+static int wakeup_display_graph(struct trace_array *tr, int set);
+# define is_graph(tr) ((tr)->trace_flags & TRACE_ITER_DISPLAY_GRAPH)
+#else
+static inline int wakeup_display_graph(struct trace_array *tr, int set)
+{
+	return 0;
+}
+# define is_graph(tr) false
 #endif
-	{ } /* Empty entry */
-};
-
-static struct tracer_flags tracer_flags = {
-	.val  = 0,
-	.opts = trace_opts,
-};
 
-#define is_graph() (tracer_flags.val & TRACE_DISPLAY_GRAPH)
 
 #ifdef CONFIG_FUNCTION_TRACER
 
+static int wakeup_graph_entry(struct ftrace_graph_ent *trace);
+static void wakeup_graph_return(struct ftrace_graph_ret *trace);
+
+static bool function_enabled;
+
 /*
  * Prologue for the wakeup function tracers.
  *
@@ -128,14 +125,13 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip,
 	atomic_dec(&data->disabled);
 	preempt_enable_notrace();
 }
-#endif /* CONFIG_FUNCTION_TRACER */
 
 static int register_wakeup_function(struct trace_array *tr, int graph, int set)
 {
 	int ret;
 
 	/* 'set' is set if TRACE_ITER_FUNCTION is about to be set */
-	if (function_enabled || (!set && !(trace_flags & TRACE_ITER_FUNCTION)))
+	if (function_enabled || (!set && !(tr->trace_flags & TRACE_ITER_FUNCTION)))
 		return 0;
 
 	if (graph)
@@ -163,20 +159,40 @@ static void unregister_wakeup_function(struct trace_array *tr, int graph)
 	function_enabled = false;
 }
 
-static void wakeup_function_set(struct trace_array *tr, int set)
+static int wakeup_function_set(struct trace_array *tr, u32 mask, int set)
 {
+	if (!(mask & TRACE_ITER_FUNCTION))
+		return 0;
+
 	if (set)
-		register_wakeup_function(tr, is_graph(), 1);
+		register_wakeup_function(tr, is_graph(tr), 1);
 	else
-		unregister_wakeup_function(tr, is_graph());
+		unregister_wakeup_function(tr, is_graph(tr));
+	return 1;
+}
+#else
+static int register_wakeup_function(struct trace_array *tr, int graph, int set)
+{
+	return 0;
+}
+static void unregister_wakeup_function(struct trace_array *tr, int graph) { }
+static int wakeup_function_set(struct trace_array *tr, u32 mask, int set)
+{
+	return 0;
 }
+#endif /* CONFIG_FUNCTION_TRACER */
 
 static int wakeup_flag_changed(struct trace_array *tr, u32 mask, int set)
 {
 	struct tracer *tracer = tr->current_trace;
 
-	if (mask & TRACE_ITER_FUNCTION)
-		wakeup_function_set(tr, set);
+	if (wakeup_function_set(tr, mask, set))
+		return 0;
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	if (mask & TRACE_ITER_DISPLAY_GRAPH)
+		return wakeup_display_graph(tr, set);
+#endif
 
 	return trace_keep_overwrite(tracer, mask, set);
 }
@@ -203,14 +219,9 @@ static void stop_func_tracer(struct trace_array *tr, int graph)
 }
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static int
-wakeup_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
+static int wakeup_display_graph(struct trace_array *tr, int set)
 {
-
-	if (!(bit & TRACE_DISPLAY_GRAPH))
-		return -EINVAL;
-
-	if (!(is_graph() ^ set))
+	if (!(is_graph(tr) ^ set))
 		return 0;
 
 	stop_func_tracer(tr, !set);
@@ -259,7 +270,7 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace)
 
 static void wakeup_trace_open(struct trace_iterator *iter)
 {
-	if (is_graph())
+	if (is_graph(iter->tr))
 		graph_trace_open(iter);
 }
 
@@ -279,7 +290,7 @@ static enum print_line_t wakeup_print_line(struct trace_iterator *iter)
 	 * In graph mode call the graph tracer output function,
 	 * otherwise go with the TRACE_FN event handler
 	 */
-	if (is_graph())
+	if (is_graph(iter->tr))
 		return print_graph_function_flags(iter, GRAPH_TRACER_FLAGS);
 
 	return TRACE_TYPE_UNHANDLED;
@@ -287,7 +298,7 @@ static enum print_line_t wakeup_print_line(struct trace_iterator *iter)
 
 static void wakeup_print_header(struct seq_file *s)
 {
-	if (is_graph())
+	if (is_graph(wakeup_trace))
 		print_graph_headers_flags(s, GRAPH_TRACER_FLAGS);
 	else
 		trace_default_header(s);
@@ -298,7 +309,7 @@ __trace_function(struct trace_array *tr,
 		 unsigned long ip, unsigned long parent_ip,
 		 unsigned long flags, int pc)
 {
-	if (is_graph())
+	if (is_graph(tr))
 		trace_graph_function(tr, ip, parent_ip, flags, pc);
 	else
 		trace_function(tr, ip, parent_ip, flags, pc);
@@ -306,27 +317,20 @@ __trace_function(struct trace_array *tr,
 #else
 #define __trace_function trace_function
 
-static int
-wakeup_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
-{
-	return -EINVAL;
-}
-
-static int wakeup_graph_entry(struct ftrace_graph_ent *trace)
-{
-	return -1;
-}
-
 static enum print_line_t wakeup_print_line(struct trace_iterator *iter)
 {
 	return TRACE_TYPE_UNHANDLED;
 }
 
-static void wakeup_graph_return(struct ftrace_graph_ret *trace) { }
 static void wakeup_trace_open(struct trace_iterator *iter) { }
 static void wakeup_trace_close(struct trace_iterator *iter) { }
 
 #ifdef CONFIG_FUNCTION_TRACER
+static int wakeup_graph_entry(struct ftrace_graph_ent *trace)
+{
+	return -1;
+}
+static void wakeup_graph_return(struct ftrace_graph_ret *trace) { }
 static void wakeup_print_header(struct seq_file *s)
 {
 	trace_default_header(s);
@@ -342,16 +346,16 @@ static void wakeup_print_header(struct seq_file *s)
 /*
  * Should this new latency be reported/recorded?
  */
-static int report_latency(struct trace_array *tr, cycle_t delta)
+static bool report_latency(struct trace_array *tr, cycle_t delta)
 {
 	if (tracing_thresh) {
 		if (delta < tracing_thresh)
-			return 0;
+			return false;
 	} else {
 		if (delta <= tr->max_latency)
-			return 0;
+			return false;
 	}
-	return 1;
+	return true;
 }
 
 static void
@@ -388,7 +392,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
 	entry->next_cpu	= task_cpu(next);
 
 	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit(buffer, event, flags, pc);
+		trace_buffer_unlock_commit(tr, buffer, event, flags, pc);
 }
 
 static void
@@ -416,7 +420,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 	entry->next_cpu			= task_cpu(wakee);
 
 	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit(buffer, event, flags, pc);
+		trace_buffer_unlock_commit(tr, buffer, event, flags, pc);
 }
 
 static void notrace
@@ -635,7 +639,7 @@ static void start_wakeup_tracer(struct trace_array *tr)
 	 */
 	smp_wmb();
 
-	if (start_func_tracer(tr, is_graph()))
+	if (start_func_tracer(tr, is_graph(tr)))
 		printk(KERN_ERR "failed to start wakeup tracer\n");
 
 	return;
@@ -648,7 +652,7 @@ fail_deprobe:
 static void stop_wakeup_tracer(struct trace_array *tr)
 {
 	tracer_enabled = 0;
-	stop_func_tracer(tr, is_graph());
+	stop_func_tracer(tr, is_graph(tr));
 	unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL);
 	unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
 	unregister_trace_sched_wakeup(probe_wakeup, NULL);
@@ -659,7 +663,7 @@ static bool wakeup_busy;
 
 static int __wakeup_tracer_init(struct trace_array *tr)
 {
-	save_flags = trace_flags;
+	save_flags = tr->trace_flags;
 
 	/* non overwrite screws up the latency tracers */
 	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1);
@@ -740,8 +744,6 @@ static struct tracer wakeup_tracer __read_mostly =
 	.print_max	= true,
 	.print_header	= wakeup_print_header,
 	.print_line	= wakeup_print_line,
-	.flags		= &tracer_flags,
-	.set_flag	= wakeup_set_flag,
 	.flag_changed	= wakeup_flag_changed,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_wakeup,
@@ -762,8 +764,6 @@ static struct tracer wakeup_rt_tracer __read_mostly =
 	.print_max	= true,
 	.print_header	= wakeup_print_header,
 	.print_line	= wakeup_print_line,
-	.flags		= &tracer_flags,
-	.set_flag	= wakeup_set_flag,
 	.flag_changed	= wakeup_flag_changed,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_wakeup,
@@ -784,8 +784,6 @@ static struct tracer wakeup_dl_tracer __read_mostly =
 	.print_max	= true,
 	.print_header	= wakeup_print_header,
 	.print_line	= wakeup_print_line,
-	.flags		= &tracer_flags,
-	.set_flag	= wakeup_set_flag,
 	.flag_changed	= wakeup_flag_changed,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_wakeup,

kernel/trace/trace_stack.c

@@ -16,24 +16,22 @@
 
 #include "trace.h"
 
-#define STACK_TRACE_ENTRIES 500
-
 static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] =
 	 { [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX };
-static unsigned stack_dump_index[STACK_TRACE_ENTRIES];
+unsigned stack_trace_index[STACK_TRACE_ENTRIES];
 
 /*
  * Reserve one entry for the passed in ip. This will allow
  * us to remove most or all of the stack size overhead
  * added by the stack tracer itself.
  */
-static struct stack_trace max_stack_trace = {
+struct stack_trace stack_trace_max = {
 	.max_entries		= STACK_TRACE_ENTRIES - 1,
 	.entries		= &stack_dump_trace[0],
 };
 
-static unsigned long max_stack_size;
-static arch_spinlock_t max_stack_lock =
+unsigned long stack_trace_max_size;
+arch_spinlock_t stack_trace_max_lock =
 	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 
 static DEFINE_PER_CPU(int, trace_active);
@@ -42,30 +40,38 @@ static DEFINE_MUTEX(stack_sysctl_mutex);
 int stack_tracer_enabled;
 static int last_stack_tracer_enabled;
 
-static inline void print_max_stack(void)
+void stack_trace_print(void)
 {
 	long i;
 	int size;
 
 	pr_emerg("        Depth    Size   Location    (%d entries)\n"
 			   "        -----    ----   --------\n",
-			   max_stack_trace.nr_entries);
+			   stack_trace_max.nr_entries);
 
-	for (i = 0; i < max_stack_trace.nr_entries; i++) {
+	for (i = 0; i < stack_trace_max.nr_entries; i++) {
 		if (stack_dump_trace[i] == ULONG_MAX)
 			break;
-		if (i+1 == max_stack_trace.nr_entries ||
+		if (i+1 == stack_trace_max.nr_entries ||
 				stack_dump_trace[i+1] == ULONG_MAX)
-			size = stack_dump_index[i];
+			size = stack_trace_index[i];
 		else
-			size = stack_dump_index[i] - stack_dump_index[i+1];
+			size = stack_trace_index[i] - stack_trace_index[i+1];
 
-		pr_emerg("%3ld) %8d   %5d   %pS\n", i, stack_dump_index[i],
+		pr_emerg("%3ld) %8d   %5d   %pS\n", i, stack_trace_index[i],
 				size, (void *)stack_dump_trace[i]);
 	}
 }
 
-static inline void
+/*
+ * When arch-specific code overides this function, the following
+ * data should be filled up, assuming stack_trace_max_lock is held to
+ * prevent concurrent updates.
+ *     stack_trace_index[]
+ *     stack_trace_max
+ *     stack_trace_max_size
+ */
+void __weak
 check_stack(unsigned long ip, unsigned long *stack)
 {
 	unsigned long this_size, flags; unsigned long *p, *top, *start;
@@ -78,7 +84,7 @@ check_stack(unsigned long ip, unsigned long *stack)
 	/* Remove the frame of the tracer */
 	this_size -= frame_size;
 
-	if (this_size <= max_stack_size)
+	if (this_size <= stack_trace_max_size)
 		return;
 
 	/* we do not handle interrupt stacks yet */
@@ -90,7 +96,7 @@ check_stack(unsigned long ip, unsigned long *stack)
 		return;
 
 	local_irq_save(flags);
-	arch_spin_lock(&max_stack_lock);
+	arch_spin_lock(&stack_trace_max_lock);
 
 	/*
 	 * RCU may not be watching, make it see us.
@@ -103,18 +109,18 @@ check_stack(unsigned long ip, unsigned long *stack)
 		this_size -= tracer_frame;
 
 	/* a race could have already updated it */
-	if (this_size <= max_stack_size)
+	if (this_size <= stack_trace_max_size)
 		goto out;
 
-	max_stack_size = this_size;
+	stack_trace_max_size = this_size;
 
-	max_stack_trace.nr_entries = 0;
-	max_stack_trace.skip = 3;
+	stack_trace_max.nr_entries = 0;
+	stack_trace_max.skip = 3;
 
-	save_stack_trace(&max_stack_trace);
+	save_stack_trace(&stack_trace_max);
 
 	/* Skip over the overhead of the stack tracer itself */
-	for (i = 0; i < max_stack_trace.nr_entries; i++) {
+	for (i = 0; i < stack_trace_max.nr_entries; i++) {
 		if (stack_dump_trace[i] == ip)
 			break;
 	}
@@ -134,18 +140,18 @@ check_stack(unsigned long ip, unsigned long *stack)
 	 * loop will only happen once. This code only takes place
 	 * on a new max, so it is far from a fast path.
 	 */
-	while (i < max_stack_trace.nr_entries) {
+	while (i < stack_trace_max.nr_entries) {
 		int found = 0;
 
-		stack_dump_index[x] = this_size;
+		stack_trace_index[x] = this_size;
 		p = start;
 
-		for (; p < top && i < max_stack_trace.nr_entries; p++) {
+		for (; p < top && i < stack_trace_max.nr_entries; p++) {
 			if (stack_dump_trace[i] == ULONG_MAX)
 				break;
 			if (*p == stack_dump_trace[i]) {
 				stack_dump_trace[x] = stack_dump_trace[i++];
-				this_size = stack_dump_index[x++] =
+				this_size = stack_trace_index[x++] =
 					(top - p) * sizeof(unsigned long);
 				found = 1;
 				/* Start the search from here */
@@ -160,7 +166,7 @@ check_stack(unsigned long ip, unsigned long *stack)
 				if (unlikely(!tracer_frame)) {
 					tracer_frame = (p - stack) *
 						sizeof(unsigned long);
-					max_stack_size -= tracer_frame;
+					stack_trace_max_size -= tracer_frame;
 				}
 			}
 		}
@@ -169,18 +175,18 @@ check_stack(unsigned long ip, unsigned long *stack)
 			i++;
 	}
 
-	max_stack_trace.nr_entries = x;
+	stack_trace_max.nr_entries = x;
 	for (; x < i; x++)
 		stack_dump_trace[x] = ULONG_MAX;
 
 	if (task_stack_end_corrupted(current)) {
-		print_max_stack();
+		stack_trace_print();
 		BUG();
 	}
 
  out:
 	rcu_irq_exit();
-	arch_spin_unlock(&max_stack_lock);
+	arch_spin_unlock(&stack_trace_max_lock);
 	local_irq_restore(flags);
 }
 
@@ -251,9 +257,9 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
 	cpu = smp_processor_id();
 	per_cpu(trace_active, cpu)++;
 
-	arch_spin_lock(&max_stack_lock);
+	arch_spin_lock(&stack_trace_max_lock);
 	*ptr = val;
-	arch_spin_unlock(&max_stack_lock);
+	arch_spin_unlock(&stack_trace_max_lock);
 
 	per_cpu(trace_active, cpu)--;
 	local_irq_restore(flags);
@@ -273,7 +279,7 @@ __next(struct seq_file *m, loff_t *pos)
 {
 	long n = *pos - 1;
 
-	if (n > max_stack_trace.nr_entries || stack_dump_trace[n] == ULONG_MAX)
+	if (n > stack_trace_max.nr_entries || stack_dump_trace[n] == ULONG_MAX)
 		return NULL;
 
 	m->private = (void *)n;
@@ -296,7 +302,7 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 	cpu = smp_processor_id();
 	per_cpu(trace_active, cpu)++;
 
-	arch_spin_lock(&max_stack_lock);
+	arch_spin_lock(&stack_trace_max_lock);
 
 	if (*pos == 0)
 		return SEQ_START_TOKEN;
@@ -308,7 +314,7 @@ static void t_stop(struct seq_file *m, void *p)
 {
 	int cpu;
 
-	arch_spin_unlock(&max_stack_lock);
+	arch_spin_unlock(&stack_trace_max_lock);
 
 	cpu = smp_processor_id();
 	per_cpu(trace_active, cpu)--;
@@ -343,9 +349,9 @@ static int t_show(struct seq_file *m, void *v)
 		seq_printf(m, "        Depth    Size   Location"
 			   "    (%d entries)\n"
 			   "        -----    ----   --------\n",
-			   max_stack_trace.nr_entries);
+			   stack_trace_max.nr_entries);
 
-		if (!stack_tracer_enabled && !max_stack_size)
+		if (!stack_tracer_enabled && !stack_trace_max_size)
 			print_disabled(m);
 
 		return 0;
@@ -353,17 +359,17 @@ static int t_show(struct seq_file *m, void *v)
 
 	i = *(long *)v;
 
-	if (i >= max_stack_trace.nr_entries ||
+	if (i >= stack_trace_max.nr_entries ||
 	    stack_dump_trace[i] == ULONG_MAX)
 		return 0;
 
-	if (i+1 == max_stack_trace.nr_entries ||
+	if (i+1 == stack_trace_max.nr_entries ||
 	    stack_dump_trace[i+1] == ULONG_MAX)
-		size = stack_dump_index[i];
+		size = stack_trace_index[i];
 	else
-		size = stack_dump_index[i] - stack_dump_index[i+1];
+		size = stack_trace_index[i] - stack_trace_index[i+1];
 
-	seq_printf(m, "%3ld) %8d   %5d   ", i, stack_dump_index[i], size);
+	seq_printf(m, "%3ld) %8d   %5d   ", i, stack_trace_index[i], size);
 
 	trace_lookup_stack(m, i);
 
@@ -453,7 +459,7 @@ static __init int stack_trace_init(void)
 		return 0;
 
 	trace_create_file("stack_max_size", 0644, d_tracer,
-			&max_stack_size, &stack_max_size_fops);
+			&stack_trace_max_size, &stack_max_size_fops);
 
 	trace_create_file("stack_trace", 0444, d_tracer,
 			NULL, &stack_trace_fops);

kernel/trace/trace_syscalls.c

@@ -110,6 +110,7 @@ static enum print_line_t
 print_syscall_enter(struct trace_iterator *iter, int flags,
 		    struct trace_event *event)
 {
+	struct trace_array *tr = iter->tr;
 	struct trace_seq *s = &iter->seq;
 	struct trace_entry *ent = iter->ent;
 	struct syscall_trace_enter *trace;
@@ -136,7 +137,7 @@ print_syscall_enter(struct trace_iterator *iter, int flags,
 			goto end;
 
 		/* parameter types */
-		if (trace_flags & TRACE_ITER_VERBOSE)
+		if (tr->trace_flags & TRACE_ITER_VERBOSE)
 			trace_seq_printf(s, "%s ", entry->types[i]);
 
 		/* parameter values */

kernel/tracepoint.c

@@ -91,11 +91,13 @@ static void debug_print_probes(struct tracepoint_func *funcs)
 		printk(KERN_DEBUG "Probe %d : %p\n", i, funcs[i].func);
 }
 
-static struct tracepoint_func *func_add(struct tracepoint_func **funcs,
-		struct tracepoint_func *tp_func)
+static struct tracepoint_func *
+func_add(struct tracepoint_func **funcs, struct tracepoint_func *tp_func,
+	 int prio)
 {
-	int nr_probes = 0;
 	struct tracepoint_func *old, *new;
+	int nr_probes = 0;
+	int pos = -1;
 
 	if (WARN_ON(!tp_func->func))
 		return ERR_PTR(-EINVAL);
@@ -104,18 +106,33 @@ static struct tracepoint_func *func_add(struct tracepoint_func **funcs,
 	old = *funcs;
 	if (old) {
 		/* (N -> N+1), (N != 0, 1) probes */
-		for (nr_probes = 0; old[nr_probes].func; nr_probes++)
+		for (nr_probes = 0; old[nr_probes].func; nr_probes++) {
+			/* Insert before probes of lower priority */
+			if (pos < 0 && old[nr_probes].prio < prio)
+				pos = nr_probes;
 			if (old[nr_probes].func == tp_func->func &&
 			    old[nr_probes].data == tp_func->data)
 				return ERR_PTR(-EEXIST);
+		}
 	}
 	/* + 2 : one for new probe, one for NULL func */
 	new = allocate_probes(nr_probes + 2);
 	if (new == NULL)
 		return ERR_PTR(-ENOMEM);
-	if (old)
-		memcpy(new, old, nr_probes * sizeof(struct tracepoint_func));
-	new[nr_probes] = *tp_func;
+	if (old) {
+		if (pos < 0) {
+			pos = nr_probes;
+			memcpy(new, old, nr_probes * sizeof(struct tracepoint_func));
+		} else {
+			/* Copy higher priority probes ahead of the new probe */
+			memcpy(new, old, pos * sizeof(struct tracepoint_func));
+			/* Copy the rest after it. */
+			memcpy(new + pos + 1, old + pos,
+			       (nr_probes - pos) * sizeof(struct tracepoint_func));
+		}
+	} else
+		pos = 0;
+	new[pos] = *tp_func;
 	new[nr_probes + 1].func = NULL;
 	*funcs = new;
 	debug_print_probes(*funcs);
@@ -174,7 +191,7 @@ static void *func_remove(struct tracepoint_func **funcs,
  * Add the probe function to a tracepoint.
  */
 static int tracepoint_add_func(struct tracepoint *tp,
-		struct tracepoint_func *func)
+			       struct tracepoint_func *func, int prio)
 {
 	struct tracepoint_func *old, *tp_funcs;
 
@@ -183,7 +200,7 @@ static int tracepoint_add_func(struct tracepoint *tp,
 
 	tp_funcs = rcu_dereference_protected(tp->funcs,
 			lockdep_is_held(&tracepoints_mutex));
-	old = func_add(&tp_funcs, func);
+	old = func_add(&tp_funcs, func, prio);
 	if (IS_ERR(old)) {
 		WARN_ON_ONCE(1);
 		return PTR_ERR(old);
@@ -240,6 +257,7 @@ static int tracepoint_remove_func(struct tracepoint *tp,
  * @tp: tracepoint
  * @probe: probe handler
  * @data: tracepoint data
+ * @prio: priority of this function over other registered functions
  *
  * Returns 0 if ok, error value on error.
  * Note: if @tp is within a module, the caller is responsible for
@@ -247,7 +265,8 @@ static int tracepoint_remove_func(struct tracepoint *tp,
  * performed either with a tracepoint module going notifier, or from
  * within module exit functions.
  */
-int tracepoint_probe_register(struct tracepoint *tp, void *probe, void *data)
+int tracepoint_probe_register_prio(struct tracepoint *tp, void *probe,
+				   void *data, int prio)
 {
 	struct tracepoint_func tp_func;
 	int ret;
@@ -255,10 +274,30 @@ int tracepoint_probe_register(struct tracepoint *tp, void *probe, void *data)
 	mutex_lock(&tracepoints_mutex);
 	tp_func.func = probe;
 	tp_func.data = data;
-	ret = tracepoint_add_func(tp, &tp_func);
+	tp_func.prio = prio;
+	ret = tracepoint_add_func(tp, &tp_func, prio);
 	mutex_unlock(&tracepoints_mutex);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(tracepoint_probe_register_prio);
+
+/**
+ * tracepoint_probe_register -  Connect a probe to a tracepoint
+ * @tp: tracepoint
+ * @probe: probe handler
+ * @data: tracepoint data
+ * @prio: priority of this function over other registered functions
+ *
+ * Returns 0 if ok, error value on error.
+ * Note: if @tp is within a module, the caller is responsible for
+ * unregistering the probe before the module is gone. This can be
+ * performed either with a tracepoint module going notifier, or from
+ * within module exit functions.
+ */
+int tracepoint_probe_register(struct tracepoint *tp, void *probe, void *data)
+{
+	return tracepoint_probe_register_prio(tp, probe, data, TRACEPOINT_DEFAULT_PRIO);
+}
 EXPORT_SYMBOL_GPL(tracepoint_probe_register);
 
 /**

samples/trace_events/trace-events-sample.h

@@ -4,14 +4,14 @@
  *
  * The define_trace.h below will also look for a file name of
  * TRACE_SYSTEM.h where TRACE_SYSTEM is what is defined here.
- * In this case, it would look for sample.h
+ * In this case, it would look for sample-trace.h
  *
  * If the header name will be different than the system name
  * (as in this case), then you can override the header name that
  * define_trace.h will look up by defining TRACE_INCLUDE_FILE
  *
  * This file is called trace-events-sample.h but we want the system
- * to be called "sample". Therefore we must define the name of this
+ * to be called "sample-trace". Therefore we must define the name of this
  * file:
  *
  * #define TRACE_INCLUDE_FILE trace-events-sample
@@ -106,7 +106,7 @@
  *
  *         memcpy(__entry->foo, bar, 10);
  *
- *   __dynamic_array: This is similar to array, but can vary is size from
+ *   __dynamic_array: This is similar to array, but can vary its size from
  *         instance to instance of the tracepoint being called.
  *         Like __array, this too has three elements (type, name, size);
  *         type is the type of the element, name is the name of the array.

scripts/recordmcount.c

@@ -42,6 +42,7 @@
 
 #ifndef EM_AARCH64
 #define EM_AARCH64	183
+#define R_AARCH64_NONE		0
 #define R_AARCH64_ABS64	257
 #endif
 
@@ -160,6 +161,22 @@ static int make_nop_x86(void *map, size_t const offset)
 	return 0;
 }
 
+static unsigned char ideal_nop4_arm64[4] = {0x1f, 0x20, 0x03, 0xd5};
+static int make_nop_arm64(void *map, size_t const offset)
+{
+	uint32_t *ptr;
+
+	ptr = map + offset;
+	/* bl <_mcount> is 0x94000000 before relocation */
+	if (*ptr != 0x94000000)
+		return -1;
+
+	/* Convert to nop */
+	ulseek(fd_map, offset, SEEK_SET);
+	uwrite(fd_map, ideal_nop, 4);
+	return 0;
+}
+
 /*
  * Get the whole file as a programming convenience in order to avoid
  * malloc+lseek+read+free of many pieces.  If successful, then mmap
@@ -345,6 +362,7 @@ do_file(char const *const fname)
 		break;
 	case EM_386:
 		reltype = R_386_32;
+		rel_type_nop = R_386_NONE;
 		make_nop = make_nop_x86;
 		ideal_nop = ideal_nop5_x86_32;
 		mcount_adjust_32 = -1;
@@ -353,7 +371,12 @@ do_file(char const *const fname)
 			 altmcount = "__gnu_mcount_nc";
 			 break;
 	case EM_AARCH64:
-			 reltype = R_AARCH64_ABS64; gpfx = '_'; break;
+			reltype = R_AARCH64_ABS64;
+			make_nop = make_nop_arm64;
+			rel_type_nop = R_AARCH64_NONE;
+			ideal_nop = ideal_nop4_arm64;
+			gpfx = '_';
+			break;
 	case EM_IA_64:	 reltype = R_IA64_IMM64;   gpfx = '_'; break;
 	case EM_METAG:	 reltype = R_METAG_ADDR32;
 			 altmcount = "_mcount_wrapper";
@@ -371,6 +394,7 @@ do_file(char const *const fname)
 		make_nop = make_nop_x86;
 		ideal_nop = ideal_nop5_x86_64;
 		reltype = R_X86_64_64;
+		rel_type_nop = R_X86_64_NONE;
 		mcount_adjust_64 = -1;
 		break;
 	}  /* end switch */

scripts/recordmcount.h

@@ -377,7 +377,7 @@ static void nop_mcount(Elf_Shdr const *const relhdr,
 
 		if (mcountsym == Elf_r_sym(relp) && !is_fake_mcount(relp)) {
 			if (make_nop)
-				ret = make_nop((void *)ehdr, shdr->sh_offset + relp->r_offset);
+				ret = make_nop((void *)ehdr, _w(shdr->sh_offset) + _w(relp->r_offset));
 			if (warn_on_notrace_sect && !once) {
 				printf("Section %s has mcount callers being ignored\n",
 				       txtname);