Merge tag 'trace-v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:

 - Update to the way irqs and preemption is tracked via the trace event
   PC field

 - Fix handling of unregistering event failing due to allocate memory.
   This is only triggered by failure injection, as it is pretty much
   guaranteed to have less than a page allocation succeed.

 - Do not show the useless "filter" or "enable" files for the "ftrace"
   trace system, as they have no effect on doing anything.

 - Add a warning if kprobes are registered more than once.

 - Synthetic events now have their fields parsed by semicolons. Old
   formats without semicolons will still work, but new features will
   require them.

 - New option to allow trace events to show %p without hashing in trace
   file. The trace file can only be read by root, and reading the raw
   event buffer did not have any pointers hashed, so this does not
   expose anything new.

 - New directory in tools called tools/tracing, where a new tool that
   reads sequential latency reports from the ftrace latency tracers.

 - Other minor fixes and cleanups.

* tag 'trace-v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (33 commits)
  kprobes: Fix to delay the kprobes jump optimization
  tracing/tools: Add the latency-collector to tools directory
  tracing: Make hash-ptr option default
  tracing: Add ptr-hash option to show the hashed pointer value
  tracing: Update the stage 3 of trace event macro comment
  tracing: Show real address for trace event arguments
  selftests/ftrace: Add '!event' synthetic event syntax check
  selftests/ftrace: Update synthetic event syntax errors
  tracing: Add a backward-compatibility check for synthetic event creation
  tracing: Update synth command errors
  tracing: Rework synthetic event command parsing
  tracing/dynevent: Delegate parsing to create function
  kprobes: Warn if the kprobe is reregistered
  ftrace: Remove unused ftrace_force_update()
  tracepoints: Code clean up
  tracepoints: Do not punish non static call users
  tracepoints: Remove unnecessary "data_args" macro parameter
  tracing: Do not create "enable" or "filter" files for ftrace event subsystem
  kernel: trace: preemptirq_delay_test: add cpu affinity
  tracepoint: Do not fail unregistering a probe due to memory failure
  ...

1 files changed, 21 insertions, 10 deletions

diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
index 7785961d82ba..8268bf747d6f 100644
--- a/include/trace/trace_events.h
+++ b/include/trace/trace_events.h
@@ -231,9 +231,11 @@ TRACE_MAKE_SYSTEM_STR();
  * {
  *	struct trace_seq *s = &iter->seq;
  *	struct trace_event_raw_<call> *field; <-- defined in stage 1
- *	struct trace_entry *entry;
  *	struct trace_seq *p = &iter->tmp_seq;
- *	int ret;
+ *
+ * -------(for event)-------
+ *
+ *	struct trace_entry *entry;
  *
  *	entry = iter->ent;
  *
@@ -245,14 +247,23 @@ TRACE_MAKE_SYSTEM_STR();
  *	field = (typeof(field))entry;
  *
  *	trace_seq_init(p);
- *	ret = trace_seq_printf(s, "%s: ", <call>);
- *	if (ret)
- *		ret = trace_seq_printf(s, <TP_printk> "\n");
- *	if (!ret)
- *		return TRACE_TYPE_PARTIAL_LINE;
+ *	return trace_output_call(iter, <call>, <TP_printk> "\n");
  *
- *	return TRACE_TYPE_HANDLED;
- * }
+ * ------(or, for event class)------
+ *
+ *	int ret;
+ *
+ *	field = (typeof(field))iter->ent;
+ *
+ *	ret = trace_raw_output_prep(iter, trace_event);
+ *	if (ret != TRACE_TYPE_HANDLED)
+ *		return ret;
+ *
+ *	trace_event_printf(iter, <TP_printk> "\n");
+ *
+ *	return trace_handle_return(s);
+ * -------
+ *  }
  *
  * This is the method used to print the raw event to the trace
  * output format. Note, this is not needed if the data is read
@@ -364,7 +375,7 @@ trace_raw_output_##call(struct trace_iterator *iter, int flags,		\
 	if (ret != TRACE_TYPE_HANDLED)					\
 		return ret;						\
 									\
-	trace_seq_printf(s, print);					\
+	trace_event_printf(iter, print);				\
 									\
 	return trace_handle_return(s);					\
 }									\