[PATCH 0/4 v2] tracing: Add a way to have custom events in the tracefs directory

[PATCH 0/4 v2] tracing: Add a way to have custom events in the tracefs directory

[Steven Rostedt]

We would like to have in production a way to record sched wakeups and
sched switch, and be able to save the information in a small file
with as much available as possible. Currently the wake up and sched switch
events are 36 and 64 bytes each (plus a 4 byte ring buffer event header).

By having a custom module tap into the sched switch and waking trace points
we can bring those events down to 16 and 14 bytes respectively.

This version adds the new TRACE_CUSTOM_EVENT() which makes creating
a custom event as easy as creating a TRACE_EVENT()!

The TRACE_CUSTOM_EVENT() macro does all the work to create the
event, and has the same format as the TRACE_EVENT() does.

Note, currently perf and bpf do not hook to this, but we can add
that later.

I kept patch 2 that has the complex way of hand coding the custom
event just to keep the histor of it.

But now, to add a custom event for sched_switch, all that needs to be
done is:

trace_custom_sched.c:
-------------------------%<-------------------------
#include <linux/trace_events.h>
#include <linux/version.h>
#include <linux/module.h>
#include <linux/sched.h>

#include <trace/events/sched.h>

#define CREATE_CUSTOM_TRACE_EVENTS

#include "trace_custom_sched.h"

static void fct(struct tracepoint *tp, void *priv)
{
	trace_custom_event_sched_switch_update(tp);
}

static int __init trace_sched_init(void)
{
	for_each_kernel_tracepoint(fct, NULL);
	return 0;
}

static void __exit trace_sched_exit(void)
{
}

module_init(trace_sched_init);
module_exit(trace_sched_exit);
------------------------->%-------------------------


-------------------------%<-------------------------
#if !defined(_TRACE_CUSTOM_SCHED_H) || defined(TRACE_CUSTOM_MULTI_READ)
#define _TRACE_CUSTOM_SCHED_H

#include <linux/trace_events.h>

TRACE_CUSTOM_EVENT(sched_switch,

	/* The below must be the same as the original sched_switch */
	TP_PROTO(bool preempt,
		 struct task_struct *prev,
		 struct task_struct *next),

	TP_ARGS(preempt, prev, next),

	/* The below is the customization */
	TP_STRUCT__entry(
		__field(	unsigned short,		prev_prio	)
		__field(	unsigned short,		next_prio	)
		__field(	pid_t,	next_pid			)
	),

	TP_fast_assign(
		__entry->prev_prio	= prev->prio;
		__entry->next_pid	= next->pid;
		__entry->next_prio	= next->prio;
	),

	TP_printk("prev_prio=%d next_pid=%d next_prio=%d",
		  __entry->prev_prio, __entry->next_pid, __entry->next_prio)
)
#endif
#undef TRACE_INCLUDE_PATH
#undef TRACE_INCLUDE_FILE
#define TRACE_INCLUDE_PATH .

#define TRACE_INCLUDE_FILE trace_custom_sched
#include <trace/define_custom_trace.h>
------------------------->%-------------------------

And update the Makefile to have:

  CFLAGS_trace_custom_sched.o := -I$(src)

Steven Rostedt (Google) (4):
      tracing: Allow custom events to be added to the tracefs directory
      tracing: Add sample code for custom trace events
      tracing: Move the defines to create TRACE_EVENTS into their own files
      tracing: Add TRACE_CUSTOM_EVENT() macro

----
 arch/x86/kernel/kprobes/core.c            |   4 +-
 include/linux/trace_events.h              |  24 +-
 include/trace/stages/init.h               |  37 +++
 include/trace/stages/stage1_defines.h     |  46 +++
 include/trace/stages/stage2_defines.h     |  48 +++
 include/trace/stages/stage3_defines.h     | 129 ++++++++
 include/trace/stages/stage4_defines.h     |  57 ++++
 include/trace/stages/stage5_defines.h     |  83 +++++
 include/trace/stages/stage6_defines.h     |  86 +++++
 include/trace/stages/stage7_defines.h     |  34 ++
 include/trace/trace_events.h              | 499 +-----------------------------
 kernel/trace/ftrace.c                     |  33 +-
 kernel/trace/trace_events.c               |   2 +
 samples/Kconfig                           |   8 +-
 samples/Makefile                          |   1 +
 samples/trace_events/Makefile             |   2 +
 samples/trace_events/trace_custom_sched.c |  60 ++++
 samples/trace_events/trace_custom_sched.h |  95 ++++++
 18 files changed, 751 insertions(+), 497 deletions(-)
 create mode 100644 include/trace/stages/init.h
 create mode 100644 include/trace/stages/stage1_defines.h
 create mode 100644 include/trace/stages/stage2_defines.h
 create mode 100644 include/trace/stages/stage3_defines.h
 create mode 100644 include/trace/stages/stage4_defines.h
 create mode 100644 include/trace/stages/stage5_defines.h
 create mode 100644 include/trace/stages/stage6_defines.h
 create mode 100644 include/trace/stages/stage7_defines.h
 create mode 100644 samples/trace_events/trace_custom_sched.c
 create mode 100644 samples/trace_events/trace_custom_sched.h

[PATCH 1/4 v2] tracing: Allow custom events to be added to the tracefs directory

[Steven Rostedt]

From: "Steven Rostedt (Google)" <rostedt@goodmis.org>

Allow custom events to be added to the events directory in the tracefs
file system. For example, a module could be installed that attaches to an
event and wants to be enabled and disabled via the tracefs file system. It
would use trace_add_event_call() to add the event to the tracefs
directory, and trace_remove_event_call() to remove it.

Make both those functions EXPORT_SYMBOL_GPL().

Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 3147614c1812..38afd66d80e3 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2758,6 +2758,7 @@ int trace_add_event_call(struct trace_event_call *call)
 	mutex_unlock(&trace_types_lock);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(trace_add_event_call);
 
 /*
  * Must be called under locking of trace_types_lock, event_mutex and
@@ -2819,6 +2820,7 @@ int trace_remove_event_call(struct trace_event_call *call)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(trace_remove_event_call);
 
 #define for_each_event(event, start, end)			\
 	for (event = start;					\
-- 
2.34.1

[PATCH 2/4 v2] tracing: Add sample code for custom trace events

[Steven Rostedt]

From: "Steven Rostedt (Google)" <rostedt@goodmis.org>

Add sample code to show how to create custom trace events in the tracefs
directory that can be enabled and modified like any event in tracefs
(including triggers, histograms, synthetic events and event probes).

The example is creating a custom sched_switch and a sched_waking to limit
what is recorded:

If the custom sched switch only records the prev_prio, next_prio and
next_pid, it can bring the size from 64 bytes per event, down to just 16
bytes!

If sched_waking only records the prio and pid of the woken event, it will
bring the size down from 36 bytes to 12 bytes per event.

This will allow for a much smaller footprint into the ring buffer and keep
more events from dropping.

Suggested-by: Joel Fernandes <joel@joelfernandes.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 arch/x86/kernel/kprobes/core.c            |   4 +-
 kernel/trace/ftrace.c                     |  33 ++-
 samples/Kconfig                           |   8 +-
 samples/Makefile                          |   1 +
 samples/trace_events/Makefile             |   2 +
 samples/trace_events/trace_custom_sched.c | 271 ++++++++++++++++++++++
 6 files changed, 314 insertions(+), 5 deletions(-)
 create mode 100644 samples/trace_events/trace_custom_sched.c

diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 6290712cb36d..2ea1ecd6f60b 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -202,8 +202,10 @@ __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
 	 * arch_check_ftrace_location(). Something went terribly wrong
 	 * if such an address is checked here.
 	 */
-	if (WARN_ON(faddr && faddr != addr))
+	if (WARN_ON(faddr && faddr != addr)) {
+		printk("faddr=%pS (%lx) addr=%pS (%lx)\n", (void*)faddr, faddr, (void*)addr, addr);
 		return 0UL;
+	}
 	/*
 	 * Use the current code if it is not modified by Kprobe
 	 * and it cannot be modified by ftrace.
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index a4b462b6f944..cb67527e1203 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1578,7 +1578,24 @@ unsigned long ftrace_location_range(unsigned long start, unsigned long end)
  */
 unsigned long ftrace_location(unsigned long ip)
 {
-	return ftrace_location_range(ip, ip);
+	struct dyn_ftrace *rec;
+	unsigned long offset;
+	unsigned long size;
+
+	rec = lookup_rec(ip, ip);
+	if (!rec) {
+		if (!kallsyms_lookup_size_offset(ip, &size, &offset))
+			goto out;
+
+		if (!offset)
+			rec = lookup_rec(ip - offset, (ip - offset) + size - 1);
+	}
+
+	if (rec)
+		return rec->ip;
+
+out:
+	return 0;
 }
 
 /**
@@ -4962,7 +4979,8 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
 {
 	struct ftrace_func_entry *entry;
 
-	if (!ftrace_location(ip))
+	ip = ftrace_location(ip);
+	if (!ip)
 		return -EINVAL;
 
 	if (remove) {
@@ -5110,11 +5128,16 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr)
 	struct ftrace_func_entry *entry;
 	struct ftrace_hash *free_hash = NULL;
 	struct dyn_ftrace *rec;
-	int ret = -EBUSY;
+	int ret = -ENODEV;
 
 	mutex_lock(&direct_mutex);
 
+	ip = ftrace_location(ip);
+	if (!ip)
+		goto out_unlock;
+
 	/* See if there's a direct function at @ip already */
+	ret = -EBUSY;
 	if (ftrace_find_rec_direct(ip))
 		goto out_unlock;
 
@@ -5222,6 +5245,10 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr)
 
 	mutex_lock(&direct_mutex);
 
+	ip = ftrace_location(ip);
+	if (!ip)
+		goto out_unlock;
+
 	entry = find_direct_entry(&ip, NULL);
 	if (!entry)
 		goto out_unlock;
diff --git a/samples/Kconfig b/samples/Kconfig
index 22cc921ae291..10e021c72282 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -14,7 +14,13 @@ config SAMPLE_TRACE_EVENTS
 	tristate "Build trace_events examples -- loadable modules only"
 	depends on EVENT_TRACING && m
 	help
-	  This build trace event example modules.
+	  This builds the trace event example module.
+
+config SAMPLE_TRACE_CUSTOM_EVENTS
+	tristate "Build custom trace event example -- loadable modules only"
+	depends on EVENT_TRACING && m
+	help
+	  This builds the custom trace event example module.
 
 config SAMPLE_TRACE_PRINTK
         tristate "Build trace_printk module - tests various trace_printk formats"
diff --git a/samples/Makefile b/samples/Makefile
index 1ae4de99c983..448343e8faeb 100644
--- a/samples/Makefile
+++ b/samples/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_SAMPLE_RPMSG_CLIENT)	+= rpmsg/
 subdir-$(CONFIG_SAMPLE_SECCOMP)		+= seccomp
 subdir-$(CONFIG_SAMPLE_TIMER)		+= timers
 obj-$(CONFIG_SAMPLE_TRACE_EVENTS)	+= trace_events/
+obj-$(CONFIG_SAMPLE_TRACE_CUSTOM_EVENTS) += trace_events/
 obj-$(CONFIG_SAMPLE_TRACE_PRINTK)	+= trace_printk/
 obj-$(CONFIG_SAMPLE_FTRACE_DIRECT)	+= ftrace/
 obj-$(CONFIG_SAMPLE_FTRACE_DIRECT_MULTI) += ftrace/
diff --git a/samples/trace_events/Makefile b/samples/trace_events/Makefile
index b78344e7bbed..e98afc447fe1 100644
--- a/samples/trace_events/Makefile
+++ b/samples/trace_events/Makefile
@@ -13,3 +13,5 @@
 CFLAGS_trace-events-sample.o := -I$(src)
 
 obj-$(CONFIG_SAMPLE_TRACE_EVENTS) += trace-events-sample.o
+
+obj-$(CONFIG_SAMPLE_TRACE_CUSTOM_EVENTS) += trace_custom_sched.o
diff --git a/samples/trace_events/trace_custom_sched.c b/samples/trace_events/trace_custom_sched.c
new file mode 100644
index 000000000000..70a12c32ff99
--- /dev/null
+++ b/samples/trace_events/trace_custom_sched.c
@@ -0,0 +1,271 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * event tracer
+ *
+ * Copyright (C) 2022 Google Inc, Steven Rostedt <rostedt@goodmis.org>
+ */
+
+#define pr_fmt(fmt) fmt
+
+#include <linux/trace_events.h>
+#include <linux/version.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <trace/events/sched.h>
+
+#define THIS_SYSTEM "custom_sched"
+
+#define SCHED_PRINT_FMT							\
+	C("prev_prio=%d next_pid=%d next_prio=%d", REC->prev_prio, REC->next_pid, \
+	  REC->next_prio)
+
+#define SCHED_WAKING_FMT				\
+	C("pid=%d prio=%d", REC->pid, REC->prio)
+
+#undef C
+#define C(a, b...) a, b
+
+static struct trace_event_fields sched_switch_fields[] = {
+	{
+		.type = "unsigned short",
+		.name = "prev_prio",
+		.size = sizeof(short),
+		.align = __alignof__(short),
+		.is_signed = 0,
+		.filter_type = FILTER_OTHER,
+	},
+	{
+		.type = "unsigned short",
+		.name = "next_prio",
+		.size = sizeof(short),
+		.align = __alignof__(short),
+		.is_signed = 0,
+		.filter_type = FILTER_OTHER,
+	},
+	{
+		.type = "unsigned int",
+		.name = "next_prio",
+		.size = sizeof(int),
+		.align = __alignof__(int),
+		.is_signed = 0,
+		.filter_type = FILTER_OTHER,
+	},
+	{}
+};
+
+struct sched_event {
+	struct trace_entry	ent;
+	unsigned short		prev_prio;
+	unsigned short		next_prio;
+	unsigned int		next_pid;
+};
+
+static struct trace_event_fields sched_waking_fields[] = {
+	{
+		.type = "unsigned int",
+		.name = "pid",
+		.size = sizeof(int),
+		.align = __alignof__(int),
+		.is_signed = 0,
+		.filter_type = FILTER_OTHER,
+	},
+	{
+		.type = "unsigned short",
+		.name = "prio",
+		.size = sizeof(short),
+		.align = __alignof__(short),
+		.is_signed = 0,
+		.filter_type = FILTER_OTHER,
+	},
+	{}
+};
+
+struct wake_event {
+	struct trace_entry	ent;
+	unsigned int		pid;
+	unsigned short		prio;
+};
+
+static void sched_switch_probe(void *data, bool preempt, struct task_struct *prev,
+			       struct task_struct *next)
+{
+	struct trace_event_file *trace_file = data;
+	struct trace_event_buffer fbuffer;
+	struct sched_event *entry;
+
+	if (trace_trigger_soft_disabled(trace_file))
+		return;
+
+	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
+					   sizeof(*entry));
+
+	if (!entry)
+		return;
+
+	entry->prev_prio = prev->prio;
+	entry->next_prio = next->prio;
+	entry->next_pid = next->pid;
+
+	trace_event_buffer_commit(&fbuffer);
+}
+
+static struct trace_event_class sched_switch_class = {
+	.system			= THIS_SYSTEM,
+	.reg			= trace_event_reg,
+	.fields_array		= sched_switch_fields,
+	.fields			= LIST_HEAD_INIT(sched_switch_class.fields),
+	.probe			= sched_switch_probe,
+};
+
+static void sched_waking_probe(void *data, struct task_struct *t)
+{
+	struct trace_event_file *trace_file = data;
+	struct trace_event_buffer fbuffer;
+	struct wake_event *entry;
+
+	if (trace_trigger_soft_disabled(trace_file))
+		return;
+
+	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
+					   sizeof(*entry));
+
+	if (!entry)
+		return;
+
+	entry->prio = t->prio;
+	entry->pid = t->pid;
+
+	trace_event_buffer_commit(&fbuffer);
+}
+
+static struct trace_event_class sched_waking_class = {
+	.system			= THIS_SYSTEM,
+	.reg			= trace_event_reg,
+	.fields_array		= sched_waking_fields,
+	.fields			= LIST_HEAD_INIT(sched_waking_class.fields),
+	.probe			= sched_waking_probe,
+};
+
+static enum print_line_t sched_switch_output(struct trace_iterator *iter, int flags,
+					     struct trace_event *trace_event)
+{
+	struct trace_seq *s = &iter->seq;
+	struct sched_event *REC = (struct sched_event *)iter->ent;
+	int ret;
+
+	ret = trace_raw_output_prep(iter, trace_event);
+	if (ret != TRACE_TYPE_HANDLED)
+		return ret;
+
+	trace_seq_printf(s, SCHED_PRINT_FMT);
+	trace_seq_putc(s, '\n');
+
+	return trace_handle_return(s);
+}
+
+static struct trace_event_functions sched_switch_funcs = {
+	.trace			= sched_switch_output,
+};
+
+static enum print_line_t sched_waking_output(struct trace_iterator *iter, int flags,
+					     struct trace_event *trace_event)
+{
+	struct trace_seq *s = &iter->seq;
+	struct wake_event *REC = (struct wake_event *)iter->ent;
+	int ret;
+
+	ret = trace_raw_output_prep(iter, trace_event);
+	if (ret != TRACE_TYPE_HANDLED)
+		return ret;
+
+	trace_seq_printf(s, SCHED_WAKING_FMT);
+	trace_seq_putc(s, '\n');
+
+	return trace_handle_return(s);
+}
+
+static struct trace_event_functions sched_waking_funcs = {
+	.trace			= sched_waking_output,
+};
+
+#undef C
+#define C(a, b...) #a "," __stringify(b)
+
+static struct trace_event_call sched_switch_call = {
+	.class			= &sched_switch_class,
+	.event			= {
+		.funcs			= &sched_switch_funcs,
+	},
+	.print_fmt		= SCHED_PRINT_FMT,
+	.module			= THIS_MODULE,
+	.flags			= TRACE_EVENT_FL_TRACEPOINT,
+};
+
+static struct trace_event_call sched_waking_call = {
+	.class			= &sched_waking_class,
+	.event			= {
+		.funcs			= &sched_waking_funcs,
+	},
+	.print_fmt		= SCHED_WAKING_FMT,
+	.module			= THIS_MODULE,
+	.flags			= TRACE_EVENT_FL_TRACEPOINT,
+};
+
+static void fct(struct tracepoint *tp, void *priv)
+{
+	if (tp->name && strcmp(tp->name, "sched_switch") == 0)
+		sched_switch_call.tp = tp;
+	else if (tp->name && strcmp(tp->name, "sched_waking") == 0)
+		sched_waking_call.tp = tp;
+}
+
+static int add_event(struct trace_event_call *call)
+{
+	int ret;
+
+	ret = register_trace_event(&call->event);
+	if (WARN_ON(!ret))
+		return -ENODEV;
+
+	ret = trace_add_event_call(call);
+	if (WARN_ON(ret))
+		unregister_trace_event(&call->event);
+
+	return ret;
+}
+
+static int __init trace_sched_init(void)
+{
+	int ret;
+
+	check_trace_callback_type_sched_switch(sched_switch_probe);
+	check_trace_callback_type_sched_waking(sched_waking_probe);
+
+	for_each_kernel_tracepoint(fct, NULL);
+
+	ret = add_event(&sched_switch_call);
+	if (ret)
+		return ret;
+
+	ret = add_event(&sched_waking_call);
+	if (ret)
+		trace_remove_event_call(&sched_switch_call);
+
+	return ret;
+}
+
+static void __exit trace_sched_exit(void)
+{
+	trace_set_clr_event(THIS_SYSTEM, "sched_switch", 0);
+	trace_set_clr_event(THIS_SYSTEM, "sched_waking", 0);
+
+	trace_remove_event_call(&sched_switch_call);
+	trace_remove_event_call(&sched_waking_call);
+}
+
+module_init(trace_sched_init);
+module_exit(trace_sched_exit);
+
+MODULE_AUTHOR("Steven Rostedt");
+MODULE_DESCRIPTION("Custom scheduling events");
+MODULE_LICENSE("GPL");
-- 
2.34.1

[PATCH 3/4 v2] tracing: Move the defines to create TRACE_EVENTS into their own files

[Steven Rostedt]

From: "Steven Rostedt (Google)" <rostedt@goodmis.org>

In an effort to add custom event macros that can be used to create your
own custom events based on existing tracepoints, move the defines of the
special macros used in TRACE_EVENT() into their own files such that they
can be reused for TRACE_CUSTOM_EVENT().

Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/trace/stages/init.h           |  37 ++
 include/trace/stages/stage1_defines.h |  46 +++
 include/trace/stages/stage2_defines.h |  48 +++
 include/trace/stages/stage3_defines.h | 129 +++++++
 include/trace/stages/stage4_defines.h |  57 +++
 include/trace/stages/stage5_defines.h |  83 +++++
 include/trace/stages/stage6_defines.h |  86 +++++
 include/trace/stages/stage7_defines.h |  34 ++
 include/trace/trace_events.h          | 499 +-------------------------
 9 files changed, 528 insertions(+), 491 deletions(-)
 create mode 100644 include/trace/stages/init.h
 create mode 100644 include/trace/stages/stage1_defines.h
 create mode 100644 include/trace/stages/stage2_defines.h
 create mode 100644 include/trace/stages/stage3_defines.h
 create mode 100644 include/trace/stages/stage4_defines.h
 create mode 100644 include/trace/stages/stage5_defines.h
 create mode 100644 include/trace/stages/stage6_defines.h
 create mode 100644 include/trace/stages/stage7_defines.h

diff --git a/include/trace/stages/init.h b/include/trace/stages/init.h
new file mode 100644
index 000000000000..000bcfc8dd2e
--- /dev/null
+++ b/include/trace/stages/init.h
@@ -0,0 +1,37 @@
+
+#define __app__(x, y) str__##x##y
+#define __app(x, y) __app__(x, y)
+
+#define TRACE_SYSTEM_STRING __app(TRACE_SYSTEM_VAR,__trace_system_name)
+
+#define TRACE_MAKE_SYSTEM_STR()				\
+	static const char TRACE_SYSTEM_STRING[] =	\
+		__stringify(TRACE_SYSTEM)
+
+TRACE_MAKE_SYSTEM_STR();
+
+#undef TRACE_DEFINE_ENUM
+#define TRACE_DEFINE_ENUM(a)				\
+	static struct trace_eval_map __used __initdata	\
+	__##TRACE_SYSTEM##_##a =			\
+	{						\
+		.system = TRACE_SYSTEM_STRING,		\
+		.eval_string = #a,			\
+		.eval_value = a				\
+	};						\
+	static struct trace_eval_map __used		\
+	__section("_ftrace_eval_map")			\
+	*TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a
+
+#undef TRACE_DEFINE_SIZEOF
+#define TRACE_DEFINE_SIZEOF(a)				\
+	static struct trace_eval_map __used __initdata	\
+	__##TRACE_SYSTEM##_##a =			\
+	{						\
+		.system = TRACE_SYSTEM_STRING,		\
+		.eval_string = "sizeof(" #a ")",	\
+		.eval_value = sizeof(a)			\
+	};						\
+	static struct trace_eval_map __used		\
+	__section("_ftrace_eval_map")			\
+	*TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a
diff --git a/include/trace/stages/stage1_defines.h b/include/trace/stages/stage1_defines.h
new file mode 100644
index 000000000000..2efabb6f09a9
--- /dev/null
+++ b/include/trace/stages/stage1_defines.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/* Stage 1 definitions for creating trace events */
+
+#undef __field
+#define __field(type, item)		type	item;
+
+#undef __field_ext
+#define __field_ext(type, item, filter_type)	type	item;
+
+#undef __field_struct
+#define __field_struct(type, item)	type	item;
+
+#undef __field_struct_ext
+#define __field_struct_ext(type, item, filter_type)	type	item;
+
+#undef __array
+#define __array(type, item, len)	type	item[len];
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len) u32 __data_loc_##item;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef __string_len
+#define __string_len(item, src, len) __dynamic_array(char, item, -1)
+
+#undef __bitmask
+#define __bitmask(item, nr_bits) __dynamic_array(char, item, -1)
+
+#undef __rel_dynamic_array
+#define __rel_dynamic_array(type, item, len) u32 __rel_loc_##item;
+
+#undef __rel_string
+#define __rel_string(item, src) __rel_dynamic_array(char, item, -1)
+
+#undef __rel_string_len
+#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1)
+
+#undef __rel_bitmask
+#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(char, item, -1)
+
+#undef TP_STRUCT__entry
+#define TP_STRUCT__entry(args...) args
+
diff --git a/include/trace/stages/stage2_defines.h b/include/trace/stages/stage2_defines.h
new file mode 100644
index 000000000000..9f2341df40da
--- /dev/null
+++ b/include/trace/stages/stage2_defines.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/* Stage 2 definitions for creating trace events */
+
+#undef TRACE_DEFINE_ENUM
+#define TRACE_DEFINE_ENUM(a)
+
+#undef TRACE_DEFINE_SIZEOF
+#define TRACE_DEFINE_SIZEOF(a)
+
+#undef __field
+#define __field(type, item)
+
+#undef __field_ext
+#define __field_ext(type, item, filter_type)
+
+#undef __field_struct
+#define __field_struct(type, item)
+
+#undef __field_struct_ext
+#define __field_struct_ext(type, item, filter_type)
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)	u32 item;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef __bitmask
+#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1)
+
+#undef __string_len
+#define __string_len(item, src, len) __dynamic_array(char, item, -1)
+
+#undef __rel_dynamic_array
+#define __rel_dynamic_array(type, item, len)	u32 item;
+
+#undef __rel_string
+#define __rel_string(item, src) __rel_dynamic_array(char, item, -1)
+
+#undef __rel_string_len
+#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1)
+
+#undef __rel_bitmask
+#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1)
diff --git a/include/trace/stages/stage3_defines.h b/include/trace/stages/stage3_defines.h
new file mode 100644
index 000000000000..0bc131993b7a
--- /dev/null
+++ b/include/trace/stages/stage3_defines.h
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/* Stage 3 definitions for creating trace events */
+
+#undef __entry
+#define __entry field
+
+#undef TP_printk
+#define TP_printk(fmt, args...) fmt "\n", args
+
+#undef __get_dynamic_array
+#define __get_dynamic_array(field)	\
+		((void *)__entry + (__entry->__data_loc_##field & 0xffff))
+
+#undef __get_dynamic_array_len
+#define __get_dynamic_array_len(field)	\
+		((__entry->__data_loc_##field >> 16) & 0xffff)
+
+#undef __get_str
+#define __get_str(field) ((char *)__get_dynamic_array(field))
+
+#undef __get_rel_dynamic_array
+#define __get_rel_dynamic_array(field)					\
+		((void *)__entry + 					\
+		 offsetof(typeof(*__entry), __rel_loc_##field) +	\
+		 sizeof(__entry->__rel_loc_##field) +			\
+		 (__entry->__rel_loc_##field & 0xffff))
+
+#undef __get_rel_dynamic_array_len
+#define __get_rel_dynamic_array_len(field)	\
+		((__entry->__rel_loc_##field >> 16) & 0xffff)
+
+#undef __get_rel_str
+#define __get_rel_str(field) ((char *)__get_rel_dynamic_array(field))
+
+#undef __get_bitmask
+#define __get_bitmask(field)						\
+	({								\
+		void *__bitmask = __get_dynamic_array(field);		\
+		unsigned int __bitmask_size;				\
+		__bitmask_size = __get_dynamic_array_len(field);	\
+		trace_print_bitmask_seq(p, __bitmask, __bitmask_size);	\
+	})
+
+#undef __get_rel_bitmask
+#define __get_rel_bitmask(field)						\
+	({								\
+		void *__bitmask = __get_rel_dynamic_array(field);		\
+		unsigned int __bitmask_size;				\
+		__bitmask_size = __get_rel_dynamic_array_len(field);	\
+		trace_print_bitmask_seq(p, __bitmask, __bitmask_size);	\
+	})
+
+#undef __print_flags
+#define __print_flags(flag, delim, flag_array...)			\
+	({								\
+		static const struct trace_print_flags __flags[] =	\
+			{ flag_array, { -1, NULL }};			\
+		trace_print_flags_seq(p, delim, flag, __flags);	\
+	})
+
+#undef __print_symbolic
+#define __print_symbolic(value, symbol_array...)			\
+	({								\
+		static const struct trace_print_flags symbols[] =	\
+			{ symbol_array, { -1, NULL }};			\
+		trace_print_symbols_seq(p, value, symbols);		\
+	})
+
+#undef __print_flags_u64
+#undef __print_symbolic_u64
+#if BITS_PER_LONG == 32
+#define __print_flags_u64(flag, delim, flag_array...)			\
+	({								\
+		static const struct trace_print_flags_u64 __flags[] =	\
+			{ flag_array, { -1, NULL } };			\
+		trace_print_flags_seq_u64(p, delim, flag, __flags);	\
+	})
+
+#define __print_symbolic_u64(value, symbol_array...)			\
+	({								\
+		static const struct trace_print_flags_u64 symbols[] =	\
+			{ symbol_array, { -1, NULL } };			\
+		trace_print_symbols_seq_u64(p, value, symbols);	\
+	})
+#else
+#define __print_flags_u64(flag, delim, flag_array...)			\
+			__print_flags(flag, delim, flag_array)
+
+#define __print_symbolic_u64(value, symbol_array...)			\
+			__print_symbolic(value, symbol_array)
+#endif
+
+#undef __print_hex
+#define __print_hex(buf, buf_len)					\
+	trace_print_hex_seq(p, buf, buf_len, false)
+
+#undef __print_hex_str
+#define __print_hex_str(buf, buf_len)					\
+	trace_print_hex_seq(p, buf, buf_len, true)
+
+#undef __print_array
+#define __print_array(array, count, el_size)				\
+	({								\
+		BUILD_BUG_ON(el_size != 1 && el_size != 2 &&		\
+			     el_size != 4 && el_size != 8);		\
+		trace_print_array_seq(p, array, count, el_size);	\
+	})
+
+#undef __print_hex_dump
+#define __print_hex_dump(prefix_str, prefix_type,			\
+			 rowsize, groupsize, buf, len, ascii)		\
+	trace_print_hex_dump_seq(p, prefix_str, prefix_type,		\
+				 rowsize, groupsize, buf, len, ascii)
+
+#undef __print_ns_to_secs
+#define __print_ns_to_secs(value)			\
+	({						\
+		u64 ____val = (u64)(value);		\
+		do_div(____val, NSEC_PER_SEC);		\
+		____val;				\
+	})
+
+#undef __print_ns_without_secs
+#define __print_ns_without_secs(value)			\
+	({						\
+		u64 ____val = (u64)(value);		\
+		(u32) do_div(____val, NSEC_PER_SEC);	\
+	})
diff --git a/include/trace/stages/stage4_defines.h b/include/trace/stages/stage4_defines.h
new file mode 100644
index 000000000000..780a10fa5279
--- /dev/null
+++ b/include/trace/stages/stage4_defines.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/* Stage 4 definitions for creating trace events */
+
+#undef __field_ext
+#define __field_ext(_type, _item, _filter_type) {			\
+	.type = #_type, .name = #_item,					\
+	.size = sizeof(_type), .align = __alignof__(_type),		\
+	.is_signed = is_signed_type(_type), .filter_type = _filter_type },
+
+#undef __field_struct_ext
+#define __field_struct_ext(_type, _item, _filter_type) {		\
+	.type = #_type, .name = #_item,					\
+	.size = sizeof(_type), .align = __alignof__(_type),		\
+	0, .filter_type = _filter_type },
+
+#undef __field
+#define __field(type, item)	__field_ext(type, item, FILTER_OTHER)
+
+#undef __field_struct
+#define __field_struct(type, item) __field_struct_ext(type, item, FILTER_OTHER)
+
+#undef __array
+#define __array(_type, _item, _len) {					\
+	.type = #_type"["__stringify(_len)"]", .name = #_item,		\
+	.size = sizeof(_type[_len]), .align = __alignof__(_type),	\
+	.is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER },
+
+#undef __dynamic_array
+#define __dynamic_array(_type, _item, _len) {				\
+	.type = "__data_loc " #_type "[]", .name = #_item,		\
+	.size = 4, .align = 4,						\
+	.is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER },
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef __string_len
+#define __string_len(item, src, len) __dynamic_array(char, item, -1)
+
+#undef __bitmask
+#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1)
+
+#undef __rel_dynamic_array
+#define __rel_dynamic_array(_type, _item, _len) {			\
+	.type = "__rel_loc " #_type "[]", .name = #_item,		\
+	.size = 4, .align = 4,						\
+	.is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER },
+
+#undef __rel_string
+#define __rel_string(item, src) __rel_dynamic_array(char, item, -1)
+
+#undef __rel_string_len
+#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1)
+
+#undef __rel_bitmask
+#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1)
diff --git a/include/trace/stages/stage5_defines.h b/include/trace/stages/stage5_defines.h
new file mode 100644
index 000000000000..fb15394aae31
--- /dev/null
+++ b/include/trace/stages/stage5_defines.h
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/* Stage 5 definitions for creating trace events */
+
+/*
+ * remember the offset of each array from the beginning of the event.
+ */
+
+#undef __entry
+#define __entry entry
+
+#undef __field
+#define __field(type, item)
+
+#undef __field_ext
+#define __field_ext(type, item, filter_type)
+
+#undef __field_struct
+#define __field_struct(type, item)
+
+#undef __field_struct_ext
+#define __field_struct_ext(type, item, filter_type)
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)				\
+	__item_length = (len) * sizeof(type);				\
+	__data_offsets->item = __data_size +				\
+			       offsetof(typeof(*entry), __data);	\
+	__data_offsets->item |= __item_length << 16;			\
+	__data_size += __item_length;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item,			\
+		    strlen((src) ? (const char *)(src) : "(null)") + 1)
+
+#undef __string_len
+#define __string_len(item, src, len) __dynamic_array(char, item, (len) + 1)
+
+#undef __rel_dynamic_array
+#define __rel_dynamic_array(type, item, len)				\
+	__item_length = (len) * sizeof(type);				\
+	__data_offsets->item = __data_size +				\
+			       offsetof(typeof(*entry), __data) -	\
+			       offsetof(typeof(*entry), __rel_loc_##item) -	\
+			       sizeof(u32);				\
+	__data_offsets->item |= __item_length << 16;			\
+	__data_size += __item_length;
+
+#undef __rel_string
+#define __rel_string(item, src) __rel_dynamic_array(char, item,			\
+		    strlen((src) ? (const char *)(src) : "(null)") + 1)
+
+#undef __rel_string_len
+#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, (len) + 1)
+/*
+ * __bitmask_size_in_bytes_raw is the number of bytes needed to hold
+ * num_possible_cpus().
+ */
+#define __bitmask_size_in_bytes_raw(nr_bits)	\
+	(((nr_bits) + 7) / 8)
+
+#define __bitmask_size_in_longs(nr_bits)			\
+	((__bitmask_size_in_bytes_raw(nr_bits) +		\
+	  ((BITS_PER_LONG / 8) - 1)) / (BITS_PER_LONG / 8))
+
+/*
+ * __bitmask_size_in_bytes is the number of bytes needed to hold
+ * num_possible_cpus() padded out to the nearest long. This is what
+ * is saved in the buffer, just to be consistent.
+ */
+#define __bitmask_size_in_bytes(nr_bits)				\
+	(__bitmask_size_in_longs(nr_bits) * (BITS_PER_LONG / 8))
+
+#undef __bitmask
+#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item,	\
+					 __bitmask_size_in_longs(nr_bits))
+
+#undef __rel_bitmask
+#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item,	\
+					 __bitmask_size_in_longs(nr_bits))
diff --git a/include/trace/stages/stage6_defines.h b/include/trace/stages/stage6_defines.h
new file mode 100644
index 000000000000..b3a1f26026be
--- /dev/null
+++ b/include/trace/stages/stage6_defines.h
@@ -0,0 +1,86 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/* Stage 6 definitions for creating trace events */
+
+#undef __entry
+#define __entry entry
+
+#undef __field
+#define __field(type, item)
+
+#undef __field_struct
+#define __field_struct(type, item)
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)				\
+	__entry->__data_loc_##item = __data_offsets.item;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef __string_len
+#define __string_len(item, src, len) __dynamic_array(char, item, -1)
+
+#undef __assign_str
+#define __assign_str(dst, src)						\
+	strcpy(__get_str(dst), (src) ? (const char *)(src) : "(null)");
+
+#undef __assign_str_len
+#define __assign_str_len(dst, src, len)					\
+	do {								\
+		memcpy(__get_str(dst), (src), (len));			\
+		__get_str(dst)[len] = '\0';				\
+	} while(0)
+
+#undef __bitmask
+#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1)
+
+#undef __get_bitmask
+#define __get_bitmask(field) (char *)__get_dynamic_array(field)
+
+#undef __assign_bitmask
+#define __assign_bitmask(dst, src, nr_bits)					\
+	memcpy(__get_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits))
+
+#undef __rel_dynamic_array
+#define __rel_dynamic_array(type, item, len)				\
+	__entry->__rel_loc_##item = __data_offsets.item;
+
+#undef __rel_string
+#define __rel_string(item, src) __rel_dynamic_array(char, item, -1)
+
+#undef __rel_string_len
+#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1)
+
+#undef __assign_rel_str
+#define __assign_rel_str(dst, src)					\
+	strcpy(__get_rel_str(dst), (src) ? (const char *)(src) : "(null)");
+
+#undef __assign_rel_str_len
+#define __assign_rel_str_len(dst, src, len)				\
+	do {								\
+		memcpy(__get_rel_str(dst), (src), (len));		\
+		__get_rel_str(dst)[len] = '\0';				\
+	} while (0)
+
+#undef __rel_bitmask
+#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1)
+
+#undef __get_rel_bitmask
+#define __get_rel_bitmask(field) (char *)__get_rel_dynamic_array(field)
+
+#undef __assign_rel_bitmask
+#define __assign_rel_bitmask(dst, src, nr_bits)					\
+	memcpy(__get_rel_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits))
+
+#undef TP_fast_assign
+#define TP_fast_assign(args...) args
+
+#undef __perf_count
+#define __perf_count(c)	(c)
+
+#undef __perf_task
+#define __perf_task(t)	(t)
diff --git a/include/trace/stages/stage7_defines.h b/include/trace/stages/stage7_defines.h
new file mode 100644
index 000000000000..d65445328f18
--- /dev/null
+++ b/include/trace/stages/stage7_defines.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/* Stage 7 definitions for creating trace events */
+
+#undef __entry
+#define __entry REC
+
+#undef __print_flags
+#undef __print_symbolic
+#undef __print_hex
+#undef __print_hex_str
+#undef __get_dynamic_array
+#undef __get_dynamic_array_len
+#undef __get_str
+#undef __get_bitmask
+#undef __get_rel_dynamic_array
+#undef __get_rel_dynamic_array_len
+#undef __get_rel_str
+#undef __get_rel_bitmask
+#undef __print_array
+#undef __print_hex_dump
+
+/*
+ * The below is not executed in the kernel. It is only what is
+ * displayed in the print format for userspace to parse.
+ */
+#undef __print_ns_to_secs
+#define __print_ns_to_secs(val) (val) / 1000000000UL
+
+#undef __print_ns_without_secs
+#define __print_ns_without_secs(val) (val) % 1000000000UL
+
+#undef TP_printk
+#define TP_printk(fmt, args...) "\"" fmt "\", "  __stringify(args)
diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
index 3d29919045af..8a8cd66cc6d5 100644
--- a/include/trace/trace_events.h
+++ b/include/trace/trace_events.h
@@ -24,42 +24,7 @@
 #define TRACE_SYSTEM_VAR TRACE_SYSTEM
 #endif
 
-#define __app__(x, y) str__##x##y
-#define __app(x, y) __app__(x, y)
-
-#define TRACE_SYSTEM_STRING __app(TRACE_SYSTEM_VAR,__trace_system_name)
-
-#define TRACE_MAKE_SYSTEM_STR()				\
-	static const char TRACE_SYSTEM_STRING[] =	\
-		__stringify(TRACE_SYSTEM)
-
-TRACE_MAKE_SYSTEM_STR();
-
-#undef TRACE_DEFINE_ENUM
-#define TRACE_DEFINE_ENUM(a)				\
-	static struct trace_eval_map __used __initdata	\
-	__##TRACE_SYSTEM##_##a =			\
-	{						\
-		.system = TRACE_SYSTEM_STRING,		\
-		.eval_string = #a,			\
-		.eval_value = a				\
-	};						\
-	static struct trace_eval_map __used		\
-	__section("_ftrace_eval_map")			\
-	*TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a
-
-#undef TRACE_DEFINE_SIZEOF
-#define TRACE_DEFINE_SIZEOF(a)				\
-	static struct trace_eval_map __used __initdata	\
-	__##TRACE_SYSTEM##_##a =			\
-	{						\
-		.system = TRACE_SYSTEM_STRING,		\
-		.eval_string = "sizeof(" #a ")",	\
-		.eval_value = sizeof(a)			\
-	};						\
-	static struct trace_eval_map __used		\
-	__section("_ftrace_eval_map")			\
-	*TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a
+#include "stages/init.h"
 
 /*
  * DECLARE_EVENT_CLASS can be used to add a generic function
@@ -80,48 +45,7 @@ TRACE_MAKE_SYSTEM_STR();
 			     PARAMS(print));		       \
 	DEFINE_EVENT(name, name, PARAMS(proto), PARAMS(args));
 
-
-#undef __field
-#define __field(type, item)		type	item;
-
-#undef __field_ext
-#define __field_ext(type, item, filter_type)	type	item;
-
-#undef __field_struct
-#define __field_struct(type, item)	type	item;
-
-#undef __field_struct_ext
-#define __field_struct_ext(type, item, filter_type)	type	item;
-
-#undef __array
-#define __array(type, item, len)	type	item[len];
-
-#undef __dynamic_array
-#define __dynamic_array(type, item, len) u32 __data_loc_##item;
-
-#undef __string
-#define __string(item, src) __dynamic_array(char, item, -1)
-
-#undef __string_len
-#define __string_len(item, src, len) __dynamic_array(char, item, -1)
-
-#undef __bitmask
-#define __bitmask(item, nr_bits) __dynamic_array(char, item, -1)
-
-#undef __rel_dynamic_array
-#define __rel_dynamic_array(type, item, len) u32 __rel_loc_##item;
-
-#undef __rel_string
-#define __rel_string(item, src) __rel_dynamic_array(char, item, -1)
-
-#undef __rel_string_len
-#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1)
-
-#undef __rel_bitmask
-#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(char, item, -1)
-
-#undef TP_STRUCT__entry
-#define TP_STRUCT__entry(args...) args
+#include "stages/stage1_defines.h"
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(name, proto, args, tstruct, assign, print)	\
@@ -185,50 +109,7 @@ TRACE_MAKE_SYSTEM_STR();
  * The size of an array is also encoded, in the higher 16 bits of <item>.
  */
 
-#undef TRACE_DEFINE_ENUM
-#define TRACE_DEFINE_ENUM(a)
-
-#undef TRACE_DEFINE_SIZEOF
-#define TRACE_DEFINE_SIZEOF(a)
-
-#undef __field
-#define __field(type, item)
-
-#undef __field_ext
-#define __field_ext(type, item, filter_type)
-
-#undef __field_struct
-#define __field_struct(type, item)
-
-#undef __field_struct_ext
-#define __field_struct_ext(type, item, filter_type)
-
-#undef __array
-#define __array(type, item, len)
-
-#undef __dynamic_array
-#define __dynamic_array(type, item, len)	u32 item;
-
-#undef __string
-#define __string(item, src) __dynamic_array(char, item, -1)
-
-#undef __bitmask
-#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1)
-
-#undef __string_len
-#define __string_len(item, src, len) __dynamic_array(char, item, -1)
-
-#undef __rel_dynamic_array
-#define __rel_dynamic_array(type, item, len)	u32 item;
-
-#undef __rel_string
-#define __rel_string(item, src) __rel_dynamic_array(char, item, -1)
-
-#undef __rel_string_len
-#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1)
-
-#undef __rel_bitmask
-#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1)
+#include "stages/stage2_defines.h"
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
@@ -300,131 +181,7 @@ TRACE_MAKE_SYSTEM_STR();
  * in binary.
  */
 
-#undef __entry
-#define __entry field
-
-#undef TP_printk
-#define TP_printk(fmt, args...) fmt "\n", args
-
-#undef __get_dynamic_array
-#define __get_dynamic_array(field)	\
-		((void *)__entry + (__entry->__data_loc_##field & 0xffff))
-
-#undef __get_dynamic_array_len
-#define __get_dynamic_array_len(field)	\
-		((__entry->__data_loc_##field >> 16) & 0xffff)
-
-#undef __get_str
-#define __get_str(field) ((char *)__get_dynamic_array(field))
-
-#undef __get_rel_dynamic_array
-#define __get_rel_dynamic_array(field)					\
-		((void *)__entry + 					\
-		 offsetof(typeof(*__entry), __rel_loc_##field) +	\
-		 sizeof(__entry->__rel_loc_##field) +			\
-		 (__entry->__rel_loc_##field & 0xffff))
-
-#undef __get_rel_dynamic_array_len
-#define __get_rel_dynamic_array_len(field)	\
-		((__entry->__rel_loc_##field >> 16) & 0xffff)
-
-#undef __get_rel_str
-#define __get_rel_str(field) ((char *)__get_rel_dynamic_array(field))
-
-#undef __get_bitmask
-#define __get_bitmask(field)						\
-	({								\
-		void *__bitmask = __get_dynamic_array(field);		\
-		unsigned int __bitmask_size;				\
-		__bitmask_size = __get_dynamic_array_len(field);	\
-		trace_print_bitmask_seq(p, __bitmask, __bitmask_size);	\
-	})
-
-#undef __get_rel_bitmask
-#define __get_rel_bitmask(field)						\
-	({								\
-		void *__bitmask = __get_rel_dynamic_array(field);		\
-		unsigned int __bitmask_size;				\
-		__bitmask_size = __get_rel_dynamic_array_len(field);	\
-		trace_print_bitmask_seq(p, __bitmask, __bitmask_size);	\
-	})
-
-#undef __print_flags
-#define __print_flags(flag, delim, flag_array...)			\
-	({								\
-		static const struct trace_print_flags __flags[] =	\
-			{ flag_array, { -1, NULL }};			\
-		trace_print_flags_seq(p, delim, flag, __flags);	\
-	})
-
-#undef __print_symbolic
-#define __print_symbolic(value, symbol_array...)			\
-	({								\
-		static const struct trace_print_flags symbols[] =	\
-			{ symbol_array, { -1, NULL }};			\
-		trace_print_symbols_seq(p, value, symbols);		\
-	})
-
-#undef __print_flags_u64
-#undef __print_symbolic_u64
-#if BITS_PER_LONG == 32
-#define __print_flags_u64(flag, delim, flag_array...)			\
-	({								\
-		static const struct trace_print_flags_u64 __flags[] =	\
-			{ flag_array, { -1, NULL } };			\
-		trace_print_flags_seq_u64(p, delim, flag, __flags);	\
-	})
-
-#define __print_symbolic_u64(value, symbol_array...)			\
-	({								\
-		static const struct trace_print_flags_u64 symbols[] =	\
-			{ symbol_array, { -1, NULL } };			\
-		trace_print_symbols_seq_u64(p, value, symbols);	\
-	})
-#else
-#define __print_flags_u64(flag, delim, flag_array...)			\
-			__print_flags(flag, delim, flag_array)
-
-#define __print_symbolic_u64(value, symbol_array...)			\
-			__print_symbolic(value, symbol_array)
-#endif
-
-#undef __print_hex
-#define __print_hex(buf, buf_len)					\
-	trace_print_hex_seq(p, buf, buf_len, false)
-
-#undef __print_hex_str
-#define __print_hex_str(buf, buf_len)					\
-	trace_print_hex_seq(p, buf, buf_len, true)
-
-#undef __print_array
-#define __print_array(array, count, el_size)				\
-	({								\
-		BUILD_BUG_ON(el_size != 1 && el_size != 2 &&		\
-			     el_size != 4 && el_size != 8);		\
-		trace_print_array_seq(p, array, count, el_size);	\
-	})
-
-#undef __print_hex_dump
-#define __print_hex_dump(prefix_str, prefix_type,			\
-			 rowsize, groupsize, buf, len, ascii)		\
-	trace_print_hex_dump_seq(p, prefix_str, prefix_type,		\
-				 rowsize, groupsize, buf, len, ascii)
-
-#undef __print_ns_to_secs
-#define __print_ns_to_secs(value)			\
-	({						\
-		u64 ____val = (u64)(value);		\
-		do_div(____val, NSEC_PER_SEC);		\
-		____val;				\
-	})
-
-#undef __print_ns_without_secs
-#define __print_ns_without_secs(value)			\
-	({						\
-		u64 ____val = (u64)(value);		\
-		(u32) do_div(____val, NSEC_PER_SEC);	\
-	})
+#include "stages/stage3_defines.h"
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
@@ -479,59 +236,7 @@ static struct trace_event_functions trace_event_type_funcs_##call = {	\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
-#undef __field_ext
-#define __field_ext(_type, _item, _filter_type) {			\
-	.type = #_type, .name = #_item,					\
-	.size = sizeof(_type), .align = __alignof__(_type),		\
-	.is_signed = is_signed_type(_type), .filter_type = _filter_type },
-
-#undef __field_struct_ext
-#define __field_struct_ext(_type, _item, _filter_type) {		\
-	.type = #_type, .name = #_item,					\
-	.size = sizeof(_type), .align = __alignof__(_type),		\
-	0, .filter_type = _filter_type },
-
-#undef __field
-#define __field(type, item)	__field_ext(type, item, FILTER_OTHER)
-
-#undef __field_struct
-#define __field_struct(type, item) __field_struct_ext(type, item, FILTER_OTHER)
-
-#undef __array
-#define __array(_type, _item, _len) {					\
-	.type = #_type"["__stringify(_len)"]", .name = #_item,		\
-	.size = sizeof(_type[_len]), .align = __alignof__(_type),	\
-	.is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER },
-
-#undef __dynamic_array
-#define __dynamic_array(_type, _item, _len) {				\
-	.type = "__data_loc " #_type "[]", .name = #_item,		\
-	.size = 4, .align = 4,						\
-	.is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER },
-
-#undef __string
-#define __string(item, src) __dynamic_array(char, item, -1)
-
-#undef __string_len
-#define __string_len(item, src, len) __dynamic_array(char, item, -1)
-
-#undef __bitmask
-#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1)
-
-#undef __rel_dynamic_array
-#define __rel_dynamic_array(_type, _item, _len) {			\
-	.type = "__rel_loc " #_type "[]", .name = #_item,		\
-	.size = 4, .align = 4,						\
-	.is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER },
-
-#undef __rel_string
-#define __rel_string(item, src) __rel_dynamic_array(char, item, -1)
-
-#undef __rel_string_len
-#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1)
-
-#undef __rel_bitmask
-#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1)
+#include "stages/stage4_defines.h"
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print)	\
@@ -544,85 +249,7 @@ static struct trace_event_fields trace_event_fields_##call[] = {	\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
-/*
- * remember the offset of each array from the beginning of the event.
- */
-
-#undef __entry
-#define __entry entry
-
-#undef __field
-#define __field(type, item)
-
-#undef __field_ext
-#define __field_ext(type, item, filter_type)
-
-#undef __field_struct
-#define __field_struct(type, item)
-
-#undef __field_struct_ext
-#define __field_struct_ext(type, item, filter_type)
-
-#undef __array
-#define __array(type, item, len)
-
-#undef __dynamic_array
-#define __dynamic_array(type, item, len)				\
-	__item_length = (len) * sizeof(type);				\
-	__data_offsets->item = __data_size +				\
-			       offsetof(typeof(*entry), __data);	\
-	__data_offsets->item |= __item_length << 16;			\
-	__data_size += __item_length;
-
-#undef __string
-#define __string(item, src) __dynamic_array(char, item,			\
-		    strlen((src) ? (const char *)(src) : "(null)") + 1)
-
-#undef __string_len
-#define __string_len(item, src, len) __dynamic_array(char, item, (len) + 1)
-
-#undef __rel_dynamic_array
-#define __rel_dynamic_array(type, item, len)				\
-	__item_length = (len) * sizeof(type);				\
-	__data_offsets->item = __data_size +				\
-			       offsetof(typeof(*entry), __data) -	\
-			       offsetof(typeof(*entry), __rel_loc_##item) -	\
-			       sizeof(u32);				\
-	__data_offsets->item |= __item_length << 16;			\
-	__data_size += __item_length;
-
-#undef __rel_string
-#define __rel_string(item, src) __rel_dynamic_array(char, item,			\
-		    strlen((src) ? (const char *)(src) : "(null)") + 1)
-
-#undef __rel_string_len
-#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, (len) + 1)
-/*
- * __bitmask_size_in_bytes_raw is the number of bytes needed to hold
- * num_possible_cpus().
- */
-#define __bitmask_size_in_bytes_raw(nr_bits)	\
-	(((nr_bits) + 7) / 8)
-
-#define __bitmask_size_in_longs(nr_bits)			\
-	((__bitmask_size_in_bytes_raw(nr_bits) +		\
-	  ((BITS_PER_LONG / 8) - 1)) / (BITS_PER_LONG / 8))
-
-/*
- * __bitmask_size_in_bytes is the number of bytes needed to hold
- * num_possible_cpus() padded out to the nearest long. This is what
- * is saved in the buffer, just to be consistent.
- */
-#define __bitmask_size_in_bytes(nr_bits)				\
-	(__bitmask_size_in_longs(nr_bits) * (BITS_PER_LONG / 8))
-
-#undef __bitmask
-#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item,	\
-					 __bitmask_size_in_longs(nr_bits))
-
-#undef __rel_bitmask
-#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item,	\
-					 __bitmask_size_in_longs(nr_bits))
+#include "stages/stage5_defines.h"
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
@@ -745,88 +372,7 @@ static inline notrace int trace_event_get_offsets_##call(		\
 #define _TRACE_PERF_INIT(call)
 #endif /* CONFIG_PERF_EVENTS */
 
-#undef __entry
-#define __entry entry
-
-#undef __field
-#define __field(type, item)
-
-#undef __field_struct
-#define __field_struct(type, item)
-
-#undef __array
-#define __array(type, item, len)
-
-#undef __dynamic_array
-#define __dynamic_array(type, item, len)				\
-	__entry->__data_loc_##item = __data_offsets.item;
-
-#undef __string
-#define __string(item, src) __dynamic_array(char, item, -1)
-
-#undef __string_len
-#define __string_len(item, src, len) __dynamic_array(char, item, -1)
-
-#undef __assign_str
-#define __assign_str(dst, src)						\
-	strcpy(__get_str(dst), (src) ? (const char *)(src) : "(null)");
-
-#undef __assign_str_len
-#define __assign_str_len(dst, src, len)					\
-	do {								\
-		memcpy(__get_str(dst), (src), (len));			\
-		__get_str(dst)[len] = '\0';				\
-	} while(0)
-
-#undef __bitmask
-#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1)
-
-#undef __get_bitmask
-#define __get_bitmask(field) (char *)__get_dynamic_array(field)
-
-#undef __assign_bitmask
-#define __assign_bitmask(dst, src, nr_bits)					\
-	memcpy(__get_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits))
-
-#undef __rel_dynamic_array
-#define __rel_dynamic_array(type, item, len)				\
-	__entry->__rel_loc_##item = __data_offsets.item;
-
-#undef __rel_string
-#define __rel_string(item, src) __rel_dynamic_array(char, item, -1)
-
-#undef __rel_string_len
-#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1)
-
-#undef __assign_rel_str
-#define __assign_rel_str(dst, src)					\
-	strcpy(__get_rel_str(dst), (src) ? (const char *)(src) : "(null)");
-
-#undef __assign_rel_str_len
-#define __assign_rel_str_len(dst, src, len)				\
-	do {								\
-		memcpy(__get_rel_str(dst), (src), (len));		\
-		__get_rel_str(dst)[len] = '\0';				\
-	} while (0)
-
-#undef __rel_bitmask
-#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1)
-
-#undef __get_rel_bitmask
-#define __get_rel_bitmask(field) (char *)__get_rel_dynamic_array(field)
-
-#undef __assign_rel_bitmask
-#define __assign_rel_bitmask(dst, src, nr_bits)					\
-	memcpy(__get_rel_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits))
-
-#undef TP_fast_assign
-#define TP_fast_assign(args...) args
-
-#undef __perf_count
-#define __perf_count(c)	(c)
-
-#undef __perf_task
-#define __perf_task(t)	(t)
+#include "stages/stage6_defines.h"
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
@@ -872,36 +418,7 @@ static inline void ftrace_test_probe_##call(void)			\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
-#undef __entry
-#define __entry REC
-
-#undef __print_flags
-#undef __print_symbolic
-#undef __print_hex
-#undef __print_hex_str
-#undef __get_dynamic_array
-#undef __get_dynamic_array_len
-#undef __get_str
-#undef __get_bitmask
-#undef __get_rel_dynamic_array
-#undef __get_rel_dynamic_array_len
-#undef __get_rel_str
-#undef __get_rel_bitmask
-#undef __print_array
-#undef __print_hex_dump
-
-/*
- * The below is not executed in the kernel. It is only what is
- * displayed in the print format for userspace to parse.
- */
-#undef __print_ns_to_secs
-#define __print_ns_to_secs(val) (val) / 1000000000UL
-
-#undef __print_ns_without_secs
-#define __print_ns_without_secs(val) (val) % 1000000000UL
-
-#undef TP_printk
-#define TP_printk(fmt, args...) "\"" fmt "\", "  __stringify(args)
+#include "stages/stage7_defines.h"
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
-- 
2.34.1

[PATCH 4/4 v2] tracing: Add TRACE_CUSTOM_EVENT() macro

[Steven Rostedt]

From: "Steven Rostedt (Google)" <rostedt@goodmis.org>

To make it really easy to add custom events from modules, add a
TRACE_CUSTOM_EVENT() macro that acts just like the TRACE_EVENT() macro,
but creates a custom event to an already existing tracepoint.

The trace_custom_sched.[ch] has been updated to use this new macro to show
how simple it is.

Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/trace_events.h              |  24 +-
 samples/trace_events/Makefile             |   2 +-
 samples/trace_events/trace_custom_sched.c | 259 ++--------------------
 samples/trace_events/trace_custom_sched.h |  95 ++++++++
 4 files changed, 143 insertions(+), 237 deletions(-)
 create mode 100644 samples/trace_events/trace_custom_sched.h

diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index dcea51fb60e2..6c7ae3c2ba9b 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -315,6 +315,7 @@ enum {
 	TRACE_EVENT_FL_KPROBE_BIT,
 	TRACE_EVENT_FL_UPROBE_BIT,
 	TRACE_EVENT_FL_EPROBE_BIT,
+	TRACE_EVENT_FL_CUSTOM_BIT,
 };
 
 /*
@@ -328,6 +329,9 @@ enum {
  *  KPROBE        - Event is a kprobe
  *  UPROBE        - Event is a uprobe
  *  EPROBE        - Event is an event probe
+ *  CUSTOM        - Event is a custom event (to be attached to an exsiting tracepoint)
+ *                   This is set when the custom event has not been attached
+ *                   to a tracepoint yet, then it is cleared when it is.
  */
 enum {
 	TRACE_EVENT_FL_FILTERED		= (1 << TRACE_EVENT_FL_FILTERED_BIT),
@@ -339,6 +343,7 @@ enum {
 	TRACE_EVENT_FL_KPROBE		= (1 << TRACE_EVENT_FL_KPROBE_BIT),
 	TRACE_EVENT_FL_UPROBE		= (1 << TRACE_EVENT_FL_UPROBE_BIT),
 	TRACE_EVENT_FL_EPROBE		= (1 << TRACE_EVENT_FL_EPROBE_BIT),
+	TRACE_EVENT_FL_CUSTOM		= (1 << TRACE_EVENT_FL_CUSTOM_BIT),
 };
 
 #define TRACE_EVENT_FL_UKPROBE (TRACE_EVENT_FL_KPROBE | TRACE_EVENT_FL_UPROBE)
@@ -440,7 +445,9 @@ static inline bool bpf_prog_array_valid(struct trace_event_call *call)
 static inline const char *
 trace_event_name(struct trace_event_call *call)
 {
-	if (call->flags & TRACE_EVENT_FL_TRACEPOINT)
+	if (call->flags & TRACE_EVENT_FL_CUSTOM)
+		return call->name;
+	else if (call->flags & TRACE_EVENT_FL_TRACEPOINT)
 		return call->tp ? call->tp->name : NULL;
 	else
 		return call->name;
@@ -903,3 +910,18 @@ perf_trace_buf_submit(void *raw_data, int size, int rctx, u16 type,
 #endif
 
 #endif /* _LINUX_TRACE_EVENT_H */
+
+/*
+ * Note: we keep the TRACE_CUSTOM_EVENT outside the include file ifdef protection.
+ *  This is due to the way trace custom events work. If a file includes two
+ *  trace event headers under one "CREATE_CUSTOM_TRACE_EVENTS" the first include
+ *  will override the TRACE_CUSTOM_EVENT and break the second include.
+ */
+
+#ifndef TRACE_CUSTOM_EVENT
+
+#define DECLARE_CUSTOM_EVENT_CLASS(name, proto, args, tstruct, assign, print)
+#define DEFINE_CUSTOM_EVENT(template, name, proto, args)
+#define TRACE_CUSTOM_EVENT(name, proto, args, struct, assign, print)
+
+#endif /* ifdef TRACE_CUSTOM_EVENT (see note above) */
diff --git a/samples/trace_events/Makefile b/samples/trace_events/Makefile
index e98afc447fe1..b3808bb4cf8b 100644
--- a/samples/trace_events/Makefile
+++ b/samples/trace_events/Makefile
@@ -11,7 +11,7 @@
 # Here trace-events-sample.c does the CREATE_TRACE_POINTS.
 #
 CFLAGS_trace-events-sample.o := -I$(src)
+CFLAGS_trace_custom_sched.o := -I$(src)
 
 obj-$(CONFIG_SAMPLE_TRACE_EVENTS) += trace-events-sample.o
-
 obj-$(CONFIG_SAMPLE_TRACE_CUSTOM_EVENTS) += trace_custom_sched.o
diff --git a/samples/trace_events/trace_custom_sched.c b/samples/trace_events/trace_custom_sched.c
index 70a12c32ff99..b99d9ab7db85 100644
--- a/samples/trace_events/trace_custom_sched.c
+++ b/samples/trace_events/trace_custom_sched.c
@@ -11,256 +11,45 @@
 #include <linux/version.h>
 #include <linux/module.h>
 #include <linux/sched.h>
-#include <trace/events/sched.h>
-
-#define THIS_SYSTEM "custom_sched"
-
-#define SCHED_PRINT_FMT							\
-	C("prev_prio=%d next_pid=%d next_prio=%d", REC->prev_prio, REC->next_pid, \
-	  REC->next_prio)
-
-#define SCHED_WAKING_FMT				\
-	C("pid=%d prio=%d", REC->pid, REC->prio)
-
-#undef C
-#define C(a, b...) a, b
-
-static struct trace_event_fields sched_switch_fields[] = {
-	{
-		.type = "unsigned short",
-		.name = "prev_prio",
-		.size = sizeof(short),
-		.align = __alignof__(short),
-		.is_signed = 0,
-		.filter_type = FILTER_OTHER,
-	},
-	{
-		.type = "unsigned short",
-		.name = "next_prio",
-		.size = sizeof(short),
-		.align = __alignof__(short),
-		.is_signed = 0,
-		.filter_type = FILTER_OTHER,
-	},
-	{
-		.type = "unsigned int",
-		.name = "next_prio",
-		.size = sizeof(int),
-		.align = __alignof__(int),
-		.is_signed = 0,
-		.filter_type = FILTER_OTHER,
-	},
-	{}
-};
-
-struct sched_event {
-	struct trace_entry	ent;
-	unsigned short		prev_prio;
-	unsigned short		next_prio;
-	unsigned int		next_pid;
-};
-
-static struct trace_event_fields sched_waking_fields[] = {
-	{
-		.type = "unsigned int",
-		.name = "pid",
-		.size = sizeof(int),
-		.align = __alignof__(int),
-		.is_signed = 0,
-		.filter_type = FILTER_OTHER,
-	},
-	{
-		.type = "unsigned short",
-		.name = "prio",
-		.size = sizeof(short),
-		.align = __alignof__(short),
-		.is_signed = 0,
-		.filter_type = FILTER_OTHER,
-	},
-	{}
-};
-
-struct wake_event {
-	struct trace_entry	ent;
-	unsigned int		pid;
-	unsigned short		prio;
-};
-
-static void sched_switch_probe(void *data, bool preempt, struct task_struct *prev,
-			       struct task_struct *next)
-{
-	struct trace_event_file *trace_file = data;
-	struct trace_event_buffer fbuffer;
-	struct sched_event *entry;
-
-	if (trace_trigger_soft_disabled(trace_file))
-		return;
-
-	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
-					   sizeof(*entry));
-
-	if (!entry)
-		return;
-
-	entry->prev_prio = prev->prio;
-	entry->next_prio = next->prio;
-	entry->next_pid = next->pid;
-
-	trace_event_buffer_commit(&fbuffer);
-}
-
-static struct trace_event_class sched_switch_class = {
-	.system			= THIS_SYSTEM,
-	.reg			= trace_event_reg,
-	.fields_array		= sched_switch_fields,
-	.fields			= LIST_HEAD_INIT(sched_switch_class.fields),
-	.probe			= sched_switch_probe,
-};
-
-static void sched_waking_probe(void *data, struct task_struct *t)
-{
-	struct trace_event_file *trace_file = data;
-	struct trace_event_buffer fbuffer;
-	struct wake_event *entry;
-
-	if (trace_trigger_soft_disabled(trace_file))
-		return;
-
-	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
-					   sizeof(*entry));
-
-	if (!entry)
-		return;
-
-	entry->prio = t->prio;
-	entry->pid = t->pid;
-
-	trace_event_buffer_commit(&fbuffer);
-}
-
-static struct trace_event_class sched_waking_class = {
-	.system			= THIS_SYSTEM,
-	.reg			= trace_event_reg,
-	.fields_array		= sched_waking_fields,
-	.fields			= LIST_HEAD_INIT(sched_waking_class.fields),
-	.probe			= sched_waking_probe,
-};
-
-static enum print_line_t sched_switch_output(struct trace_iterator *iter, int flags,
-					     struct trace_event *trace_event)
-{
-	struct trace_seq *s = &iter->seq;
-	struct sched_event *REC = (struct sched_event *)iter->ent;
-	int ret;
-
-	ret = trace_raw_output_prep(iter, trace_event);
-	if (ret != TRACE_TYPE_HANDLED)
-		return ret;
-
-	trace_seq_printf(s, SCHED_PRINT_FMT);
-	trace_seq_putc(s, '\n');
 
-	return trace_handle_return(s);
-}
-
-static struct trace_event_functions sched_switch_funcs = {
-	.trace			= sched_switch_output,
-};
-
-static enum print_line_t sched_waking_output(struct trace_iterator *iter, int flags,
-					     struct trace_event *trace_event)
-{
-	struct trace_seq *s = &iter->seq;
-	struct wake_event *REC = (struct wake_event *)iter->ent;
-	int ret;
-
-	ret = trace_raw_output_prep(iter, trace_event);
-	if (ret != TRACE_TYPE_HANDLED)
-		return ret;
-
-	trace_seq_printf(s, SCHED_WAKING_FMT);
-	trace_seq_putc(s, '\n');
-
-	return trace_handle_return(s);
-}
-
-static struct trace_event_functions sched_waking_funcs = {
-	.trace			= sched_waking_output,
-};
-
-#undef C
-#define C(a, b...) #a "," __stringify(b)
+/*
+ * Must include the event header that the custom event will attach to,
+ * from the C file, and not in the custom header file.
+ */
+#include <trace/events/sched.h>
 
-static struct trace_event_call sched_switch_call = {
-	.class			= &sched_switch_class,
-	.event			= {
-		.funcs			= &sched_switch_funcs,
-	},
-	.print_fmt		= SCHED_PRINT_FMT,
-	.module			= THIS_MODULE,
-	.flags			= TRACE_EVENT_FL_TRACEPOINT,
-};
+/* Declare CREATE_CUSTOM_TRACE_EVENTS before including custom header */
+#define CREATE_CUSTOM_TRACE_EVENTS
 
-static struct trace_event_call sched_waking_call = {
-	.class			= &sched_waking_class,
-	.event			= {
-		.funcs			= &sched_waking_funcs,
-	},
-	.print_fmt		= SCHED_WAKING_FMT,
-	.module			= THIS_MODULE,
-	.flags			= TRACE_EVENT_FL_TRACEPOINT,
-};
+#include "trace_custom_sched.h"
 
+/*
+ * As the trace events are not exported to modules, the use of
+ * for_each_kernel_tracepoint() is needed to find the trace event
+ * to attach to. The fct() function below, is a callback that
+ * will be called for every event.
+ *
+ * Helper functions are created by the TRACE_CUSTOM_EVENT() macro
+ * update the event. Those are of the form:
+ *
+ *    trace_custom_event_<event>_update()
+ *
+ * Where <event> is the event to attach.
+ */
 static void fct(struct tracepoint *tp, void *priv)
 {
-	if (tp->name && strcmp(tp->name, "sched_switch") == 0)
-		sched_switch_call.tp = tp;
-	else if (tp->name && strcmp(tp->name, "sched_waking") == 0)
-		sched_waking_call.tp = tp;
-}
-
-static int add_event(struct trace_event_call *call)
-{
-	int ret;
-
-	ret = register_trace_event(&call->event);
-	if (WARN_ON(!ret))
-		return -ENODEV;
-
-	ret = trace_add_event_call(call);
-	if (WARN_ON(ret))
-		unregister_trace_event(&call->event);
-
-	return ret;
+	trace_custom_event_sched_switch_update(tp);
+	trace_custom_event_sched_waking_update(tp);
 }
 
 static int __init trace_sched_init(void)
 {
-	int ret;
-
-	check_trace_callback_type_sched_switch(sched_switch_probe);
-	check_trace_callback_type_sched_waking(sched_waking_probe);
-
 	for_each_kernel_tracepoint(fct, NULL);
-
-	ret = add_event(&sched_switch_call);
-	if (ret)
-		return ret;
-
-	ret = add_event(&sched_waking_call);
-	if (ret)
-		trace_remove_event_call(&sched_switch_call);
-
-	return ret;
+	return 0;
 }
 
 static void __exit trace_sched_exit(void)
 {
-	trace_set_clr_event(THIS_SYSTEM, "sched_switch", 0);
-	trace_set_clr_event(THIS_SYSTEM, "sched_waking", 0);
-
-	trace_remove_event_call(&sched_switch_call);
-	trace_remove_event_call(&sched_waking_call);
 }
 
 module_init(trace_sched_init);
diff --git a/samples/trace_events/trace_custom_sched.h b/samples/trace_events/trace_custom_sched.h
new file mode 100644
index 000000000000..a3d14de6a2e5
--- /dev/null
+++ b/samples/trace_events/trace_custom_sched.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Like the headers that use TRACE_EVENT(), the TRACE_CUSTOM_EVENT()
+ * needs a header that allows for multiple inclusions.
+ *
+ * Test for a unique name (here we have _TRACE_CUSTOM_SCHED_H),
+ * also allowing to continue if TRACE_CUSTOM_MULTI_READ is defined.
+ */
+#if !defined(_TRACE_CUSTOM_SCHED_H) || defined(TRACE_CUSTOM_MULTI_READ)
+#define _TRACE_CUSTOM_SCHED_H
+
+/* Include linux/trace_events.h for initial defines of TRACE_CUSTOM_EVENT() */
+#include <linux/trace_events.h>
+
+/*
+ * TRACE_CUSTOM_EVENT() is just like TRACE_EVENT(). The first parameter
+ * is the event name of an existing event where the TRACE_EVENT has been included
+ * in the C file before including this file.
+ */
+TRACE_CUSTOM_EVENT(sched_switch,
+
+	/*
+	 * The TP_PROTO() and TP_ARGS must match the trace event
+	 * that the custom event is using.
+	 */
+	TP_PROTO(bool preempt,
+		 struct task_struct *prev,
+		 struct task_struct *next),
+
+	TP_ARGS(preempt, prev, next),
+
+	/*
+	 * The next fields are where the customization happens.
+	 * The TP_STRUCT__entry() defines what will be recorded
+	 * in the ring buffer when the custom event triggers.
+	 *
+	 * The rest is just like the TRACE_EVENT() macro except that
+	 * it uses the custom entry.
+	 */
+	TP_STRUCT__entry(
+		__field(	unsigned short,		prev_prio	)
+		__field(	unsigned short,		next_prio	)
+		__field(	pid_t,	next_pid			)
+	),
+
+	TP_fast_assign(
+		__entry->prev_prio	= prev->prio;
+		__entry->next_pid	= next->pid;
+		__entry->next_prio	= next->prio;
+	),
+
+	TP_printk("prev_prio=%d next_pid=%d next_prio=%d",
+		  __entry->prev_prio, __entry->next_pid, __entry->next_prio)
+)
+
+
+TRACE_CUSTOM_EVENT(sched_waking,
+
+	TP_PROTO(struct task_struct *p),
+
+	TP_ARGS(p),
+
+	TP_STRUCT__entry(
+		__field(	pid_t,			pid	)
+		__field(	unsigned short,		prio	)
+	),
+
+	TP_fast_assign(
+		__entry->pid	= p->pid;
+		__entry->prio	= p->prio;
+	),
+
+	TP_printk("pid=%d prio=%d", __entry->pid, __entry->prio)
+)
+#endif
+/*
+ * Just like the headers that create TRACE_EVENTs, the below must
+ * be outside the protection of the above #if block.
+ */
+
+/*
+ * It is required that the Makefile includes:
+ *    CFLAGS_<c_file>.o := -I$(src)
+ */
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_PATH .
+
+/*
+ * It is requred that the TRACE_INCLUDE_FILE be the same
+ * as this file without the ".h".
+ */
+#define TRACE_INCLUDE_FILE trace_custom_sched
+#include <trace/define_custom_trace.h>
-- 
2.34.1

Re: [PATCH 0/4 v2] tracing: Add a way to have custom events in the tracefs directory

[Steven Rostedt]

On Thu, 03 Mar 2022 16:48:32 -0500
Steven Rostedt <rostedt@goodmis.org> wrote:

> #define TRACE_INCLUDE_FILE trace_custom_sched
> #include <trace/define_custom_trace.h>
> ------------------------->%-------------------------  

It appears that I forgot to do a:

  git add include/trace/trace_custom_events.h include/trace/define_custom_trace.h

and those two very important files are missing from the last patch.

Will send a v3.

-- Steve