tracing: Add a way to soft disable trace events

In order to let triggers enable or disable events, we need a 'soft'
method for doing so. For example, if a function probe is added that
lets a user enable or disable events when a function is called, that
change must be done without taking locks or a mutex, and definitely
it can't sleep. But the full enabling of a tracepoint is expensive.

By adding a 'SOFT_DISABLE' flag, and converting the flags to be updated
without the protection of a mutex (using set/clear_bit()), this soft
disable flag can be used to allow critical sections to enable or disable
events from being traced (after the event has been placed into "SOFT_MODE").

Some caveats though: The comm recorder (to map pids with a comm) can not
be soft disabled (yet). If you disable an event with with a "soft"
disable and wait a while before reading the trace, the comm cache may be
replaced and you'll get a bunch of <...> for comms in the trace.

Reading the "enable" file for an event that is disabled will now give
you "0*" where the '*' denotes that the tracepoint is still active but
the event itself is "disabled".

[ fixed _BIT used in & operation : thanks to Dan Carpenter and smatch ]

Cc: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

2 files changed, 22 insertions, 6 deletions

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 4cb6cd8338a..4e28b011e63 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -251,16 +251,23 @@ 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 {
@@ -274,17 +281,18 @@ struct ftrace_event_file {
 	 * 32 bit flags:
 	 *   bit 0:		enabled
 	 *   bit 1:		enabled cmd record
+	 *   bit 2:		enable/disable with the soft disable bit
+	 *   bit 3:		soft disabled
 	 *
-	 * 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
+	 * 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.
+	 * caching and such. Which is mostly OK ;-)
 	 */
-	unsigned int		flags;
+	unsigned long		flags;
 };
 
 #define __TRACE_EVENT_FLAGS(name, value)				\
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index bbf09c2021b..4bda044e6c7 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -413,6 +413,10 @@ 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();
  *
@@ -518,6 +522,10 @@ 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();						\
 									\