tracing: add format file to describe event struct fields

This patch adds the "format" file to the trace point event directory.
This is based off of work by Tom Zanussi, in which a file is exported
to be tread from user land such that a user space app may read the
binary record stored in the ring buffer.

 # cat /debug/tracing/events/sched/sched_switch/format
        field:pid_t prev_pid;   offset:12;      size:4;
        field:int prev_prio;    offset:16;      size:4;
        field special:char next_comm[TASK_COMM_LEN];    offset:20;      size:16;
        field:pid_t next_pid;   offset:36;      size:4;
        field:int next_prio;    offset:40;      size:4;

Idea-from: Tom Zanussi <tzanussi@gmail.com>
Signed-off-by: Steven Rostedt <srostedt@redhat.com>

4 files changed, 110 insertions, 1 deletions

diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index cf6ba4181b14..e606633fb498 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -754,6 +754,7 @@ struct ftrace_event_call {
 	int		(*raw_init)(void);
 	int		(*raw_reg)(void);
 	void		(*raw_unreg)(void);
+	int		(*show_format)(struct trace_seq *s);
 };
 
 void event_trace_printk(unsigned long ip, const char *fmt, ...);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 26069fa6b3b0..d57a772981c1 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -3,6 +3,9 @@
  *
  * Copyright (C) 2008 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
  *
+ *  - Added format output of fields of the trace point.
+ *    This was based off of work by Tom Zanussi <tzanussi@gmail.com>.
+ *
  */
 
 #include <linux/debugfs.h>
@@ -444,6 +447,42 @@ event_available_types_read(struct file *filp, char __user *ubuf, size_t cnt,
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
 
+static ssize_t
+event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
+		  loff_t *ppos)
+{
+	struct ftrace_event_call *call = filp->private_data;
+	struct trace_seq *s;
+	char *buf;
+	int r;
+
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	trace_seq_init(s);
+
+	if (*ppos)
+		return 0;
+
+	r = call->show_format(s);
+	if (!r) {
+		/*
+		 * ug!  The format output is bigger than a PAGE!!
+		 */
+		buf = "FORMAT TOO BIG\n";
+		r = simple_read_from_buffer(ubuf, cnt, ppos,
+					      buf, strlen(buf));
+		goto out;
+	}
+
+	r = simple_read_from_buffer(ubuf, cnt, ppos,
+				    s->buffer, s->len);
+ out:
+	kfree(s);
+	return r;
+}
+
 static const struct seq_operations show_event_seq_ops = {
 	.start = t_start,
 	.next = t_next,
@@ -490,6 +529,11 @@ static const struct file_operations ftrace_available_types_fops = {
 	.read = event_available_types_read,
 };
 
+static const struct file_operations ftrace_event_format_fops = {
+	.open = tracing_open_generic,
+	.read = event_format_read,
+};
+
 static struct dentry *event_trace_events_dir(void)
 {
 	static struct dentry *d_tracer;
@@ -602,7 +646,17 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
 				    &ftrace_available_types_fops);
 	if (!entry)
 		pr_warning("Could not create debugfs "
-			   "'%s/type' available_types\n", call->name);
+			   "'%s/available_types' entry\n", call->name);
+
+	/* A trace may not want to export its format */
+	if (!call->show_format)
+		return 0;
+
+	entry = debugfs_create_file("format", 0444, call->dir, call,
+				    &ftrace_event_format_fops);
+	if (!entry)
+		pr_warning("Could not create debugfs "
+			   "'%s/format' entry\n", call->name);
 
 	return 0;
 }
diff --git a/kernel/trace/trace_events_stage_2.h b/kernel/trace/trace_events_stage_2.h
index dc79fe3a2ecb..3a80ea4e92cb 100644
--- a/kernel/trace/trace_events_stage_2.h
+++ b/kernel/trace/trace_events_stage_2.h
@@ -74,3 +74,55 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
 }
 
 #include <trace/trace_event_types.h>
+
+/*
+ * Setup the showing format of trace point.
+ *
+ * int
+ * ftrace_format_##call(struct trace_seq *s)
+ * {
+ * 	struct ftrace_raw_##call field;
+ * 	int ret;
+ *
+ * 	ret = trace_seq_printf(s, #type " " #item ";"
+ * 			       " size:%d; offset:%d;\n",
+ * 			       sizeof(field.type),
+ * 			       offsetof(struct ftrace_raw_##call,
+ * 					item));
+ *
+ * }
+ */
+
+#undef TRACE_FIELD
+#define TRACE_FIELD(type, item, assign)					\
+	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
+			       "offset:%lu;\tsize:%lu;\n",		\
+			       offsetof(typeof(field), item),		\
+			       sizeof(field.item));			\
+	if (!ret)							\
+		return 0;
+
+
+#undef TRACE_FIELD_SPECIAL
+#define TRACE_FIELD_SPECIAL(type_item, item, cmd)			\
+	ret = trace_seq_printf(s, "\tfield special:" #type_item ";\t"	\
+			       "offset:%lu;\tsize:%lu;\n",		\
+			       offsetof(typeof(field), item),		\
+			       sizeof(field.item));			\
+	if (!ret)							\
+		return 0;
+
+#undef TRACE_EVENT_FORMAT
+#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt)	\
+int									\
+ftrace_format_##call(struct trace_seq *s)				\
+{									\
+	struct ftrace_raw_##call field;					\
+	int ret;							\
+									\
+	tstruct;							\
+									\
+	return ret;							\
+}
+
+#include <trace/trace_event_types.h>
diff --git a/kernel/trace/trace_events_stage_3.h b/kernel/trace/trace_events_stage_3.h
index 2ab65e958223..c62a4d2a5283 100644
--- a/kernel/trace/trace_events_stage_3.h
+++ b/kernel/trace/trace_events_stage_3.h
@@ -101,6 +101,7 @@
  * 	.raw_init		= ftrace_raw_init_event_<call>,
  * 	.raw_reg		= ftrace_raw_reg_event_<call>,
  * 	.raw_unreg		= ftrace_raw_unreg_event_<call>,
+ *	.show_format		= ftrace_format_<call>,
  * }
  *
  */
@@ -230,4 +231,5 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.raw_init		= ftrace_raw_init_event_##call,		\
 	.raw_reg		= ftrace_raw_reg_event_##call,		\
 	.raw_unreg		= ftrace_raw_unreg_event_##call,	\
+	.show_format		= ftrace_format_##call,			\
 }