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

…/linux/kernel/git/tip/linux-2.6-tip

* 'tracing-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  tracing: Fix "integer as NULL pointer" warning.
  tracing: Fix tracepoint.h DECLARE_TRACE() to allow more than one header
  tracing: Make the documentation clear on trace_event boot option
  ring-buffer: Wrap open-coded WARN_ONCE
  tracing: Convert nop macros to static inlines
  tracing: Fix sleep time function profiling
  tracing: Show sample std dev in function profiling
  tracing: Add documentation for trace commands mod, traceon/traceoff
  ring-buffer: Make benchmark handle missed events
  ring-buffer: Make non-consuming read less expensive with lots of cpus.
  tracing: Add graph output support for irqsoff tracer
  tracing: Have graph flags passed in to ouput functions
  tracing: Add ftrace events for graph tracer
  tracing: Dump either the oops's cpu source or all cpus buffers
  tracing: Fix uninitialized variable of tracing/trace output

Documentation/kernel-parameters.txt

@@ -786,8 +786,12 @@ and is between 256 and 4096 characters. It is defined in the file
 			as early as possible in order to facilitate early
 			boot debugging.
 
-	ftrace_dump_on_oops
+	ftrace_dump_on_oops[=orig_cpu]
 			[FTRACE] will dump the trace buffers on oops.
+			If no parameter is passed, ftrace will dump
+			buffers of all CPUs, but if you pass orig_cpu, it will
+			dump only the buffer of the CPU that triggered the
+			oops.
 
 	ftrace_filter=[function-list]
 			[FTRACE] Limit the functions traced by the function

Documentation/trace/events.txt

@@ -90,7 +90,8 @@ In order to facilitate early boot debugging, use boot option:
 
 	trace_event=[event-list]
 
-The format of this boot option is the same as described in section 2.1.
+event-list is a comma separated list of events. See section 2.1 for event
+format.
 
 3. Defining an event-enabled tracepoint
 =======================================

Documentation/trace/ftrace.txt

@@ -155,6 +155,9 @@ of ftrace. Here is a list of some of the key files:
 	to be traced. Echoing names of functions into this file
 	will limit the trace to only those functions.
 
+	This interface also allows for commands to be used. See the
+	"Filter commands" section for more details.
+
   set_ftrace_notrace:
 
 	This has an effect opposite to that of
@@ -1337,12 +1340,14 @@ ftrace_dump_on_oops must be set. To set ftrace_dump_on_oops, one
 can either use the sysctl function or set it via the proc system
 interface.
 
-  sysctl kernel.ftrace_dump_on_oops=1
+  sysctl kernel.ftrace_dump_on_oops=n
 
 or
 
-  echo 1 > /proc/sys/kernel/ftrace_dump_on_oops
+  echo n > /proc/sys/kernel/ftrace_dump_on_oops
 
+If n = 1, ftrace will dump buffers of all CPUs, if n = 2 ftrace will
+only dump the buffer of the CPU that triggered the oops.
 
 Here's an example of such a dump after a null pointer
 dereference in a kernel module:
@@ -1822,6 +1827,47 @@ this special filter via:
  echo > set_graph_function
 
 
+Filter commands
+---------------
+
+A few commands are supported by the set_ftrace_filter interface.
+Trace commands have the following format:
+
+<function>:<command>:<parameter>
+
+The following commands are supported:
+
+- mod
+  This command enables function filtering per module. The
+  parameter defines the module. For example, if only the write*
+  functions in the ext3 module are desired, run:
+
+   echo 'write*:mod:ext3' > set_ftrace_filter
+
+  This command interacts with the filter in the same way as
+  filtering based on function names. Thus, adding more functions
+  in a different module is accomplished by appending (>>) to the
+  filter file. Remove specific module functions by prepending
+  '!':
+
+   echo '!writeback*:mod:ext3' >> 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
+  tracing system is turned on and off. If unspecified, there is
+  no limit. For example, to disable tracing when a schedule bug
+  is hit the first 5 times, run:
+
+   echo '__schedule_bug:traceoff:5' > set_ftrace_filter
+
+  These commands are cumulative whether or not they are appended
+  to set_ftrace_filter. To remove a command, prepend it by '!'
+  and drop the parameter:
+
+   echo '!__schedule_bug:traceoff' > set_ftrace_filter
+
+
 trace_pipe
 ----------
 

drivers/char/sysrq.c

@@ -289,7 +289,7 @@ static struct sysrq_key_op sysrq_showstate_blocked_op = {
 
 static void sysrq_ftrace_dump(int key, struct tty_struct *tty)
 {
-	ftrace_dump();
+	ftrace_dump(DUMP_ALL);
 }
 static struct sysrq_key_op sysrq_ftrace_dump_op = {
 	.handler	= sysrq_ftrace_dump,

include/linux/ftrace.h

@@ -82,9 +82,13 @@ void clear_ftrace_function(void);
 extern void ftrace_stub(unsigned long a0, unsigned long a1);
 
 #else /* !CONFIG_FUNCTION_TRACER */
-# define register_ftrace_function(ops) do { } while (0)
-# define unregister_ftrace_function(ops) do { } while (0)
-# define clear_ftrace_function(ops) do { } while (0)
+/*
+ * (un)register_ftrace_function must be a macro since the ops parameter
+ * must not be evaluated.
+ */
+#define register_ftrace_function(ops) ({ 0; })
+#define unregister_ftrace_function(ops) ({ 0; })
+static inline void clear_ftrace_function(void) { }
 static inline void ftrace_kill(void) { }
 static inline void ftrace_stop(void) { }
 static inline void ftrace_start(void) { }
@@ -237,11 +241,13 @@ extern int skip_trace(unsigned long ip);
 extern void ftrace_disable_daemon(void);
 extern void ftrace_enable_daemon(void);
 #else
-# define skip_trace(ip)				({ 0; })
-# define ftrace_force_update()			({ 0; })
-# define ftrace_set_filter(buf, len, reset)	do { } while (0)
-# define ftrace_disable_daemon()		do { } while (0)
-# define ftrace_enable_daemon()			do { } while (0)
+static inline int skip_trace(unsigned long ip) { return 0; }
+static inline int ftrace_force_update(void) { return 0; }
+static inline void ftrace_set_filter(unsigned char *buf, int len, int reset)
+{
+}
+static inline void ftrace_disable_daemon(void) { }
+static inline void ftrace_enable_daemon(void) { }
 static inline void ftrace_release_mod(struct module *mod) {}
 static inline int register_ftrace_command(struct ftrace_func_command *cmd)
 {
@@ -314,16 +320,16 @@ static inline void __ftrace_enabled_restore(int enabled)
   extern void time_hardirqs_on(unsigned long a0, unsigned long a1);
   extern void time_hardirqs_off(unsigned long a0, unsigned long a1);
 #else
-# define time_hardirqs_on(a0, a1)		do { } while (0)
-# define time_hardirqs_off(a0, a1)		do { } while (0)
+  static inline void time_hardirqs_on(unsigned long a0, unsigned long a1) { }
+  static inline void time_hardirqs_off(unsigned long a0, unsigned long a1) { }
 #endif
 
 #ifdef CONFIG_PREEMPT_TRACER
   extern void trace_preempt_on(unsigned long a0, unsigned long a1);
   extern void trace_preempt_off(unsigned long a0, unsigned long a1);
 #else
-# define trace_preempt_on(a0, a1)		do { } while (0)
-# define trace_preempt_off(a0, a1)		do { } while (0)
+  static inline void trace_preempt_on(unsigned long a0, unsigned long a1) { }
+  static inline void trace_preempt_off(unsigned long a0, unsigned long a1) { }
 #endif
 
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
@@ -352,6 +358,10 @@ struct ftrace_graph_ret {
 	int depth;
 };
 
+/* Type of the callback handlers for tracing function graph*/
+typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *); /* return */
+typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *); /* entry */
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 /* for init task */
@@ -400,10 +410,6 @@ extern char __irqentry_text_end[];
 
 #define FTRACE_RETFUNC_DEPTH 50
 #define FTRACE_RETSTACK_ALLOC_SIZE 32
-/* Type of the callback handlers for tracing function graph*/
-typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *); /* return */
-typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *); /* entry */
-
 extern int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 				trace_func_graph_ent_t entryfunc);
 
@@ -441,6 +447,13 @@ static inline void unpause_graph_tracing(void)
 static inline void ftrace_graph_init_task(struct task_struct *t) { }
 static inline void ftrace_graph_exit_task(struct task_struct *t) { }
 
+static inline int register_ftrace_graph(trace_func_graph_ret_t retfunc,
+			  trace_func_graph_ent_t entryfunc)
+{
+	return -1;
+}
+static inline void unregister_ftrace_graph(void) { }
+
 static inline int task_curr_ret_stack(struct task_struct *tsk)
 {
 	return -1;
@@ -492,7 +505,9 @@ static inline int test_tsk_trace_graph(struct task_struct *tsk)
 	return tsk->trace & TSK_TRACE_FL_GRAPH;
 }
 
-extern int ftrace_dump_on_oops;
+enum ftrace_dump_mode;
+
+extern enum ftrace_dump_mode ftrace_dump_on_oops;
 
 #ifdef CONFIG_PREEMPT
 #define INIT_TRACE_RECURSION		.trace_recursion = 0,

include/linux/kernel.h

@@ -490,6 +490,13 @@ static inline void tracing_off(void) { }
 static inline void tracing_off_permanent(void) { }
 static inline int tracing_is_on(void) { return 0; }
 #endif
+
+enum ftrace_dump_mode {
+	DUMP_NONE,
+	DUMP_ALL,
+	DUMP_ORIG,
+};
+
 #ifdef CONFIG_TRACING
 extern void tracing_start(void);
 extern void tracing_stop(void);
@@ -571,7 +578,7 @@ __ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap);
 extern int
 __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap);
 
-extern void ftrace_dump(void);
+extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode);
 #else
 static inline void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
@@ -592,7 +599,7 @@ ftrace_vprintk(const char *fmt, va_list ap)
 {
 	return 0;
 }
-static inline void ftrace_dump(void) { }
+static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 #endif /* CONFIG_TRACING */
 
 /*

include/linux/ring_buffer.h

@@ -127,7 +127,9 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts,
 		    unsigned long *lost_events);
 
 struct ring_buffer_iter *
-ring_buffer_read_start(struct ring_buffer *buffer, int cpu);
+ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu);
+void ring_buffer_read_prepare_sync(void);
+void ring_buffer_read_start(struct ring_buffer_iter *iter);
 void ring_buffer_read_finish(struct ring_buffer_iter *iter);
 
 struct ring_buffer_event *

include/linux/tracepoint.h

@@ -33,6 +33,65 @@ struct tracepoint {
 					 * Keep in sync with vmlinux.lds.h.
 					 */
 
+/*
+ * Connect a probe to a tracepoint.
+ * Internal API, should not be used directly.
+ */
+extern int tracepoint_probe_register(const char *name, void *probe);
+
+/*
+ * Disconnect a probe from a tracepoint.
+ * Internal API, should not be used directly.
+ */
+extern int tracepoint_probe_unregister(const char *name, void *probe);
+
+extern int tracepoint_probe_register_noupdate(const char *name, void *probe);
+extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe);
+extern void tracepoint_probe_update_all(void);
+
+struct tracepoint_iter {
+	struct module *module;
+	struct tracepoint *tracepoint;
+};
+
+extern void tracepoint_iter_start(struct tracepoint_iter *iter);
+extern void tracepoint_iter_next(struct tracepoint_iter *iter);
+extern void tracepoint_iter_stop(struct tracepoint_iter *iter);
+extern void tracepoint_iter_reset(struct tracepoint_iter *iter);
+extern int tracepoint_get_iter_range(struct tracepoint **tracepoint,
+	struct tracepoint *begin, struct tracepoint *end);
+
+/*
+ * tracepoint_synchronize_unregister must be called between the last tracepoint
+ * probe unregistration and the end of module exit to make sure there is no
+ * caller executing a probe when it is freed.
+ */
+static inline void tracepoint_synchronize_unregister(void)
+{
+	synchronize_sched();
+}
+
+#define PARAMS(args...) args
+
+#ifdef CONFIG_TRACEPOINTS
+extern void tracepoint_update_probe_range(struct tracepoint *begin,
+	struct tracepoint *end);
+#else
+static inline void tracepoint_update_probe_range(struct tracepoint *begin,
+	struct tracepoint *end)
+{ }
+#endif /* CONFIG_TRACEPOINTS */
+
+#endif /* _LINUX_TRACEPOINT_H */
+
+/*
+ * Note: we keep the TRACE_EVENT and DECLARE_TRACE outside the include
+ *  file ifdef protection.
+ *  This is due to the way trace events work. If a file includes two
+ *  trace event headers under one "CREATE_TRACE_POINTS" the first include
+ *  will override the TRACE_EVENT and break the second include.
+ */
+
 #ifndef DECLARE_TRACE
 
 #define TP_PROTO(args...)	args
@@ -96,9 +155,6 @@ struct tracepoint {
 #define EXPORT_TRACEPOINT_SYMBOL(name)					\
 	EXPORT_SYMBOL(__tracepoint_##name)
 
-extern void tracepoint_update_probe_range(struct tracepoint *begin,
-	struct tracepoint *end);
-
 #else /* !CONFIG_TRACEPOINTS */
 #define DECLARE_TRACE(name, proto, args)				\
 	static inline void _do_trace_##name(struct tracepoint *tp, proto) \
@@ -119,61 +175,9 @@ extern void tracepoint_update_probe_range(struct tracepoint *begin,
 #define EXPORT_TRACEPOINT_SYMBOL_GPL(name)
 #define EXPORT_TRACEPOINT_SYMBOL(name)
 
-static inline void tracepoint_update_probe_range(struct tracepoint *begin,
-	struct tracepoint *end)
-{ }
 #endif /* CONFIG_TRACEPOINTS */
 #endif /* DECLARE_TRACE */
 
-/*
- * Connect a probe to a tracepoint.
- * Internal API, should not be used directly.
- */
-extern int tracepoint_probe_register(const char *name, void *probe);
-
-/*
- * Disconnect a probe from a tracepoint.
- * Internal API, should not be used directly.
- */
-extern int tracepoint_probe_unregister(const char *name, void *probe);
-
-extern int tracepoint_probe_register_noupdate(const char *name, void *probe);
-extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe);
-extern void tracepoint_probe_update_all(void);
-
-struct tracepoint_iter {
-	struct module *module;
-	struct tracepoint *tracepoint;
-};
-
-extern void tracepoint_iter_start(struct tracepoint_iter *iter);
-extern void tracepoint_iter_next(struct tracepoint_iter *iter);
-extern void tracepoint_iter_stop(struct tracepoint_iter *iter);
-extern void tracepoint_iter_reset(struct tracepoint_iter *iter);
-extern int tracepoint_get_iter_range(struct tracepoint **tracepoint,
-	struct tracepoint *begin, struct tracepoint *end);
-
-/*
- * tracepoint_synchronize_unregister must be called between the last tracepoint
- * probe unregistration and the end of module exit to make sure there is no
- * caller executing a probe when it is freed.
- */
-static inline void tracepoint_synchronize_unregister(void)
-{
-	synchronize_sched();
-}
-
-#define PARAMS(args...) args
-
-#endif /* _LINUX_TRACEPOINT_H */
-
-/*
- * Note: we keep the TRACE_EVENT outside the include file ifdef protection.
- *  This is due to the way trace events work. If a file includes two
- *  trace event headers under one "CREATE_TRACE_POINTS" the first include
- *  will override the TRACE_EVENT and break the second include.
- */
-
 #ifndef TRACE_EVENT
 /*
  * For use with the TRACE_EVENT macro: