Merge tag 'trace-3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "Along with the usual minor fixes and clean ups there are a few major
  changes with this pull request.

   1) Multiple buffers for the ftrace facility

  This feature has been requested by many people over the last few
  years.  I even heard that Google was about to implement it themselves.
  I finally had time and cleaned up the code such that you can now
  create multiple instances of the ftrace buffer and have different
  events go to different buffers.  This way, a low frequency event will
  not be lost in the noise of a high frequency event.

  Note, currently only events can go to different buffers, the tracers
  (ie function, function_graph and the latency tracers) still can only
  be written to the main buffer.

   2) The function tracer triggers have now been extended.

  The function tracer had two triggers.  One to enable tracing when a
  function is hit, and one to disable tracing.  Now you can record a
  stack trace on a single (or many) function(s), take a snapshot of the
  buffer (copy it to the snapshot buffer), and you can enable or disable
  an event to be traced when a function is hit.

   3) A perf clock has been added.

  A "perf" clock can be chosen to be used when tracing.  This will cause
  ftrace to use the same clock as perf uses, and hopefully this will
  make it easier to interleave the perf and ftrace data for analysis."

* tag 'trace-3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (82 commits)
  tracepoints: Prevent null probe from being added
  tracing: Compare to 1 instead of zero for is_signed_type()
  tracing: Remove obsolete macro guard _TRACE_PROFILE_INIT
  ftrace: Get rid of ftrace_profile_bits
  tracing: Check return value of tracing_init_dentry()
  tracing: Get rid of unneeded key calculation in ftrace_hash_move()
  tracing: Reset ftrace_graph_filter_enabled if count is zero
  tracing: Fix off-by-one on allocating stat->pages
  kernel: tracing: Use strlcpy instead of strncpy
  tracing: Update debugfs README file
  tracing: Fix ftrace_dump()
  tracing: Rename trace_event_mutex to trace_event_sem
  tracing: Fix comment about prefix in arch_syscall_match_sym_name()
  tracing: Convert trace_destroy_fields() to static
  tracing: Move find_event_field() into trace_events.c
  tracing: Use TRACE_MAX_PRINT instead of constant
  tracing: Use pr_warn_once instead of open coded implementation
  ring-buffer: Add ring buffer startup selftest
  tracing: Bring Documentation/trace/ftrace.txt up to date
  tracing: Add "perf" trace_clock
  ...

Conflicts:
	kernel/trace/ftrace.c
	kernel/trace/trace.c

6 files changed, 186 insertions, 57 deletions

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 52da2a250795..f83e17a40e8b 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -261,8 +261,10 @@ struct ftrace_probe_ops {
 	void			(*func)(unsigned long ip,
 					unsigned long parent_ip,
 					void **data);
-	int			(*callback)(unsigned long ip, void **data);
-	void			(*free)(void **data);
+	int			(*init)(struct ftrace_probe_ops *ops,
+					unsigned long ip, void **data);
+	void			(*free)(struct ftrace_probe_ops *ops,
+					unsigned long ip, void **data);
 	int			(*print)(struct seq_file *m,
 					 unsigned long ip,
 					 struct ftrace_probe_ops *ops,
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 13a54d0bdfa8..34e00fb49bec 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -8,6 +8,7 @@
 #include <linux/perf_event.h>
 
 struct trace_array;
+struct trace_buffer;
 struct tracer;
 struct dentry;
 
@@ -38,6 +39,12 @@ const char *ftrace_print_symbols_seq_u64(struct trace_seq *p,
 const char *ftrace_print_hex_seq(struct trace_seq *p,
 				 const unsigned char *buf, int len);
 
+struct trace_iterator;
+struct trace_event;
+
+int ftrace_raw_output_prep(struct trace_iterator *iter,
+			   struct trace_event *event);
+
 /*
  * The trace entry - the most basic unit of tracing. This is what
  * is printed in the end as a single line in the trace output, such as:
@@ -61,6 +68,7 @@ struct trace_entry {
 struct trace_iterator {
 	struct trace_array	*tr;
 	struct tracer		*trace;
+	struct trace_buffer	*trace_buffer;
 	void			*private;
 	int			cpu_file;
 	struct mutex		mutex;
@@ -95,8 +103,6 @@ enum trace_iter_flags {
 };
 
 
-struct trace_event;
-
 typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter,
 				      int flags, struct trace_event *event);
 
@@ -128,6 +134,13 @@ enum print_line_t {
 void tracing_generic_entry_update(struct trace_entry *entry,
 				  unsigned long flags,
 				  int pc);
+struct ftrace_event_file;
+
+struct ring_buffer_event *
+trace_event_buffer_lock_reserve(struct ring_buffer **current_buffer,
+				struct ftrace_event_file *ftrace_file,
+				int type, unsigned long len,
+				unsigned long flags, int pc);
 struct ring_buffer_event *
 trace_current_buffer_lock_reserve(struct ring_buffer **current_buffer,
 				  int type, unsigned long len,
@@ -182,53 +195,49 @@ extern int ftrace_event_reg(struct ftrace_event_call *event,
 			    enum trace_reg type, void *data);
 
 enum {
-	TRACE_EVENT_FL_ENABLED_BIT,
 	TRACE_EVENT_FL_FILTERED_BIT,
-	TRACE_EVENT_FL_RECORDED_CMD_BIT,
 	TRACE_EVENT_FL_CAP_ANY_BIT,
 	TRACE_EVENT_FL_NO_SET_FILTER_BIT,
 	TRACE_EVENT_FL_IGNORE_ENABLE_BIT,
+	TRACE_EVENT_FL_WAS_ENABLED_BIT,
 };
 
+/*
+ * Event flags:
+ *  FILTERED	  - The event has a filter attached
+ *  CAP_ANY	  - Any user can enable for perf
+ *  NO_SET_FILTER - Set when filter has error and is to be ignored
+ *  IGNORE_ENABLE - For ftrace internal events, do not enable with debugfs file
+ *  WAS_ENABLED   - Set and stays set when an event was ever enabled
+ *                    (used for module unloading, if a module event is enabled,
+ *                     it is best to clear the buffers that used it).
+ */
 enum {
-	TRACE_EVENT_FL_ENABLED		= (1 << TRACE_EVENT_FL_ENABLED_BIT),
 	TRACE_EVENT_FL_FILTERED		= (1 << TRACE_EVENT_FL_FILTERED_BIT),
-	TRACE_EVENT_FL_RECORDED_CMD	= (1 << TRACE_EVENT_FL_RECORDED_CMD_BIT),
 	TRACE_EVENT_FL_CAP_ANY		= (1 << TRACE_EVENT_FL_CAP_ANY_BIT),
 	TRACE_EVENT_FL_NO_SET_FILTER	= (1 << TRACE_EVENT_FL_NO_SET_FILTER_BIT),
 	TRACE_EVENT_FL_IGNORE_ENABLE	= (1 << TRACE_EVENT_FL_IGNORE_ENABLE_BIT),
+	TRACE_EVENT_FL_WAS_ENABLED	= (1 << TRACE_EVENT_FL_WAS_ENABLED_BIT),
 };
 
 struct ftrace_event_call {
 	struct list_head	list;
 	struct ftrace_event_class *class;
 	char			*name;
-	struct dentry		*dir;
 	struct trace_event	event;
 	const char		*print_fmt;
 	struct event_filter	*filter;
+	struct list_head	*files;
 	void			*mod;
 	void			*data;
-
 	/*
-	 * 32 bit flags:
-	 *   bit 1:		enabled
-	 *   bit 2:		filter_active
-	 *   bit 3:		enabled cmd record
-	 *   bit 4:		allow trace by non root (cap any)
-	 *   bit 5:		failed to apply filter
-	 *   bit 6:		ftrace internal event (do not enable)
-	 *
-	 * Changes to flags must hold the event_mutex.
-	 *
-	 * Note: Reads of flags do not hold the event_mutex since
-	 * they occur in critical sections. But the way flags
-	 * is currently used, these changes do no affect the code
-	 * except that when a change is made, it may have a slight
-	 * delay in propagating the changes to other CPUs due to
-	 * caching and such.
+	 *   bit 0:		filter_active
+	 *   bit 1:		allow trace by non root (cap any)
+	 *   bit 2:		failed to apply filter
+	 *   bit 3:		ftrace internal event (do not enable)
+	 *   bit 4:		Event was enabled by module
 	 */
-	unsigned int		flags;
+	int			flags; /* static flags of different events */
 
 #ifdef CONFIG_PERF_EVENTS
 	int				perf_refcount;
@@ -236,6 +245,56 @@ struct ftrace_event_call {
 #endif
 };
 
+struct trace_array;
+struct ftrace_subsystem_dir;
+
+enum {
+	FTRACE_EVENT_FL_ENABLED_BIT,
+	FTRACE_EVENT_FL_RECORDED_CMD_BIT,
+	FTRACE_EVENT_FL_SOFT_MODE_BIT,
+	FTRACE_EVENT_FL_SOFT_DISABLED_BIT,
+};
+
+/*
+ * Ftrace event file flags:
+ *  ENABLED	  - The event is enabled
+ *  RECORDED_CMD  - The comms should be recorded at sched_switch
+ *  SOFT_MODE     - The event is enabled/disabled by SOFT_DISABLED
+ *  SOFT_DISABLED - When set, do not trace the event (even though its
+ *                   tracepoint may be enabled)
+ */
+enum {
+	FTRACE_EVENT_FL_ENABLED		= (1 << FTRACE_EVENT_FL_ENABLED_BIT),
+	FTRACE_EVENT_FL_RECORDED_CMD	= (1 << FTRACE_EVENT_FL_RECORDED_CMD_BIT),
+	FTRACE_EVENT_FL_SOFT_MODE	= (1 << FTRACE_EVENT_FL_SOFT_MODE_BIT),
+	FTRACE_EVENT_FL_SOFT_DISABLED	= (1 << FTRACE_EVENT_FL_SOFT_DISABLED_BIT),
+};
+
+struct ftrace_event_file {
+	struct list_head		list;
+	struct ftrace_event_call	*event_call;
+	struct dentry			*dir;
+	struct trace_array		*tr;
+	struct ftrace_subsystem_dir	*system;
+
+	/*
+	 * 32 bit flags:
+	 *   bit 0:		enabled
+	 *   bit 1:		enabled cmd record
+	 *   bit 2:		enable/disable with the soft disable bit
+	 *   bit 3:		soft disabled
+	 *
+	 * Note: The bits must be set atomically to prevent races
+	 * from other writers. Reads of flags do not need to be in
+	 * sync as they occur in critical sections. But the way flags
+	 * is currently used, these changes do not affect the code
+	 * except that when a change is made, it may have a slight
+	 * delay in propagating the changes to other CPUs due to
+	 * caching and such. Which is mostly OK ;-)
+	 */
+	unsigned long		flags;
+};
+
 #define __TRACE_EVENT_FLAGS(name, value)				\
 	static int __init trace_init_flags_##name(void)			\
 	{								\
@@ -274,7 +333,7 @@ extern int trace_define_field(struct ftrace_event_call *call, const char *type,
 extern int trace_add_event_call(struct ftrace_event_call *call);
 extern void trace_remove_event_call(struct ftrace_event_call *call);
 
-#define is_signed_type(type)	(((type)(-1)) < (type)0)
+#define is_signed_type(type)	(((type)(-1)) < (type)1)
 
 int trace_set_clr_event(const char *system, const char *event, int set);
 
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 79fdd80a42d4..2dac79c39199 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -486,6 +486,8 @@ enum ftrace_dump_mode {
 void tracing_on(void);
 void tracing_off(void);
 int tracing_is_on(void);
+void tracing_snapshot(void);
+void tracing_snapshot_alloc(void);
 
 extern void tracing_start(void);
 extern void tracing_stop(void);
@@ -515,10 +517,32 @@ do {									\
  *
  * This is intended as a debugging tool for the developer only.
  * Please refrain from leaving trace_printks scattered around in
- * your code.
+ * your code. (Extra memory is used for special buffers that are
+ * allocated when trace_printk() is used)
+ *
+ * A little optization trick is done here. If there's only one
+ * argument, there's no need to scan the string for printf formats.
+ * The trace_puts() will suffice. But how can we take advantage of
+ * using trace_puts() when trace_printk() has only one argument?
+ * By stringifying the args and checking the size we can tell
+ * whether or not there are args. __stringify((__VA_ARGS__)) will
+ * turn into "()\0" with a size of 3 when there are no args, anything
+ * else will be bigger. All we need to do is define a string to this,
+ * and then take its size and compare to 3. If it's bigger, use
+ * do_trace_printk() otherwise, optimize it to trace_puts(). Then just
+ * let gcc optimize the rest.
  */
 
-#define trace_printk(fmt, args...)					\
+#define trace_printk(fmt, ...)				\
+do {							\
+	char _______STR[] = __stringify((__VA_ARGS__));	\
+	if (sizeof(_______STR) > 3)			\
+		do_trace_printk(fmt, ##__VA_ARGS__);	\
+	else						\
+		trace_puts(fmt);			\
+} while (0)
+
+#define do_trace_printk(fmt, args...)					\
 do {									\
 	static const char *trace_printk_fmt				\
 		__attribute__((section("__trace_printk_fmt"))) =	\
@@ -538,7 +562,45 @@ int __trace_bprintk(unsigned long ip, const char *fmt, ...);
 extern __printf(2, 3)
 int __trace_printk(unsigned long ip, const char *fmt, ...);
 
-extern void trace_dump_stack(void);
+/**
+ * trace_puts - write a string into the ftrace buffer
+ * @str: the string to record
+ *
+ * Note: __trace_bputs is an internal function for trace_puts and
+ *       the @ip is passed in via the trace_puts macro.
+ *
+ * This is similar to trace_printk() but is made for those really fast
+ * paths that a developer wants the least amount of "Heisenbug" affects,
+ * where the processing of the print format is still too much.
+ *
+ * This function allows a kernel developer to debug fast path sections
+ * that printk is not appropriate for. By scattering in various
+ * printk like tracing in the code, a developer can quickly see
+ * where problems are occurring.
+ *
+ * This is intended as a debugging tool for the developer only.
+ * Please refrain from leaving trace_puts scattered around in
+ * your code. (Extra memory is used for special buffers that are
+ * allocated when trace_puts() is used)
+ *
+ * Returns: 0 if nothing was written, positive # if string was.
+ *  (1 when __trace_bputs is used, strlen(str) when __trace_puts is used)
+ */
+
+extern int __trace_bputs(unsigned long ip, const char *str);
+extern int __trace_puts(unsigned long ip, const char *str, int size);
+#define trace_puts(str) ({						\
+	static const char *trace_printk_fmt				\
+		__attribute__((section("__trace_printk_fmt"))) =	\
+		__builtin_constant_p(str) ? str : NULL;			\
+									\
+	if (__builtin_constant_p(str))					\
+		__trace_bputs(_THIS_IP_, trace_printk_fmt);		\
+	else								\
+		__trace_puts(_THIS_IP_, str, strlen(str));		\
+})
+
+extern void trace_dump_stack(int skip);
 
 /*
  * The double __builtin_constant_p is because gcc will give us an error
@@ -573,6 +635,8 @@ static inline void trace_dump_stack(void) { }
 static inline void tracing_on(void) { }
 static inline void tracing_off(void) { }
 static inline int tracing_is_on(void) { return 0; }
+static inline void tracing_snapshot(void) { }
+static inline void tracing_snapshot_alloc(void) { }
 
 static inline __printf(1, 2)
 int trace_printk(const char *fmt, ...)
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 1342e69542f3..d69cf637a15a 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -4,6 +4,7 @@
 #include <linux/kmemcheck.h>
 #include <linux/mm.h>
 #include <linux/seq_file.h>
+#include <linux/poll.h>
 
 struct ring_buffer;
 struct ring_buffer_iter;
@@ -96,6 +97,11 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k
 	__ring_buffer_alloc((size), (flags), &__key);	\
 })
 
+void ring_buffer_wait(struct ring_buffer *buffer, int cpu);
+int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
+			  struct file *filp, poll_table *poll_table);
+
+
 #define RING_BUFFER_ALL_CPUS -1
 
 void ring_buffer_free(struct ring_buffer *buffer);
diff --git a/include/linux/trace_clock.h b/include/linux/trace_clock.h
index d563f37e1a1d..1d7ca2739272 100644
--- a/include/linux/trace_clock.h
+++ b/include/linux/trace_clock.h
@@ -16,6 +16,7 @@
 
 extern u64 notrace trace_clock_local(void);
 extern u64 notrace trace_clock(void);
+extern u64 notrace trace_clock_jiffies(void);
 extern u64 notrace trace_clock_global(void);
 extern u64 notrace trace_clock_counter(void);
 
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 40dc5e8fe340..19edd7facaa1 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -227,29 +227,18 @@ static notrace enum print_line_t					\
 ftrace_raw_output_##call(struct trace_iterator *iter, int flags,	\
 			 struct trace_event *trace_event)		\
 {									\
-	struct ftrace_event_call *event;				\
 	struct trace_seq *s = &iter->seq;				\
+	struct trace_seq __maybe_unused *p = &iter->tmp_seq;		\
 	struct ftrace_raw_##call *field;				\
-	struct trace_entry *entry;					\
-	struct trace_seq *p = &iter->tmp_seq;				\
 	int ret;							\
 									\
-	event = container_of(trace_event, struct ftrace_event_call,	\
-			     event);					\
-									\
-	entry = iter->ent;						\
-									\
-	if (entry->type != event->event.type) {				\
-		WARN_ON_ONCE(1);					\
-		return TRACE_TYPE_UNHANDLED;				\
-	}								\
-									\
-	field = (typeof(field))entry;					\
+	field = (typeof(field))iter->ent;				\
 									\
-	trace_seq_init(p);						\
-	ret = trace_seq_printf(s, "%s: ", event->name);			\
+	ret = ftrace_raw_output_prep(iter, trace_event);		\
 	if (ret)							\
-		ret = trace_seq_printf(s, print);			\
+		return ret;						\
+									\
+	ret = trace_seq_printf(s, print);				\
 	if (!ret)							\
 		return TRACE_TYPE_PARTIAL_LINE;				\
 									\
@@ -335,7 +324,7 @@ static struct trace_event_functions ftrace_event_type_funcs_##call = {	\
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print)	\
-static int notrace							\
+static int notrace __init						\
 ftrace_define_fields_##call(struct ftrace_event_call *event_call)	\
 {									\
 	struct ftrace_raw_##call field;					\
@@ -414,7 +403,8 @@ static inline notrace int ftrace_get_offsets_##call(			\
  *
  * static void ftrace_raw_event_<call>(void *__data, proto)
  * {
- *	struct ftrace_event_call *event_call = __data;
+ *	struct ftrace_event_file *ftrace_file = __data;
+ *	struct ftrace_event_call *event_call = ftrace_file->event_call;
  *	struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
  *	struct ring_buffer_event *event;
  *	struct ftrace_raw_<call> *entry; <-- defined in stage 1
@@ -423,12 +413,16 @@ static inline notrace int ftrace_get_offsets_##call(			\
  *	int __data_size;
  *	int pc;
  *
+ *	if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT,
+ *		     &ftrace_file->flags))
+ *		return;
+ *
  *	local_save_flags(irq_flags);
  *	pc = preempt_count();
  *
  *	__data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
  *
- *	event = trace_current_buffer_lock_reserve(&buffer,
+ *	event = trace_event_buffer_lock_reserve(&buffer, ftrace_file,
  *				  event_<call>->event.type,
  *				  sizeof(*entry) + __data_size,
  *				  irq_flags, pc);
@@ -440,7 +434,7 @@ static inline notrace int ftrace_get_offsets_##call(			\
  *			   __array macros.
  *
  *	if (!filter_current_check_discard(buffer, event_call, entry, event))
- *		trace_current_buffer_unlock_commit(buffer,
+ *		trace_nowake_buffer_unlock_commit(buffer,
  *						   event, irq_flags, pc);
  * }
  *
@@ -518,7 +512,8 @@ static inline notrace int ftrace_get_offsets_##call(			\
 static notrace void							\
 ftrace_raw_event_##call(void *__data, proto)				\
 {									\
-	struct ftrace_event_call *event_call = __data;			\
+	struct ftrace_event_file *ftrace_file = __data;			\
+	struct ftrace_event_call *event_call = ftrace_file->event_call;	\
 	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
 	struct ring_buffer_event *event;				\
 	struct ftrace_raw_##call *entry;				\
@@ -527,12 +522,16 @@ ftrace_raw_event_##call(void *__data, proto)				\
 	int __data_size;						\
 	int pc;								\
 									\
+	if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT,			\
+		     &ftrace_file->flags))				\
+		return;							\
+									\
 	local_save_flags(irq_flags);					\
 	pc = preempt_count();						\
 									\
 	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
 									\
-	event = trace_current_buffer_lock_reserve(&buffer,		\
+	event = trace_event_buffer_lock_reserve(&buffer, ftrace_file,	\
 				 event_call->event.type,		\
 				 sizeof(*entry) + __data_size,		\
 				 irq_flags, pc);			\
@@ -581,7 +580,7 @@ static inline void ftrace_test_probe_##call(void)			\
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
 _TRACE_PERF_PROTO(call, PARAMS(proto));					\
 static const char print_fmt_##call[] = print;				\
-static struct ftrace_event_class __used event_class_##call = {		\
+static struct ftrace_event_class __used __refdata event_class_##call = { \
 	.system			= __stringify(TRACE_SYSTEM),		\
 	.define_fields		= ftrace_define_fields_##call,		\
 	.fields			= LIST_HEAD_INIT(event_class_##call.fields),\
@@ -705,5 +704,3 @@ static inline void perf_test_probe_##call(void)				\
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 #endif /* CONFIG_PERF_EVENTS */
 
-#undef _TRACE_PROFILE_INIT
-