Merge branch 'tip/tracing/ftrace' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into tracing/ftrace

include/linux/tracepoint.h

@@ -157,4 +157,7 @@ static inline void tracepoint_synchronize_unregister(void)
 #define TRACE_FORMAT(name, proto, args, fmt)		\
 	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
 
+#define TRACE_EVENT_FORMAT(name, proto, args, fmt, struct, tpfmt)	\
+	TRACE_FORMAT(name, PARAMS(proto), PARAMS(args), PARAMS(fmt))
+
 #endif

include/trace/irq_event_types.h

@@ -5,13 +5,29 @@
 # error Unless you know what you are doing.
 #endif
 
-TRACE_FORMAT(irq_handler_entry,
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM irq
+
+TRACE_EVENT_FORMAT(irq_handler_entry,
 	TPPROTO(int irq, struct irqaction *action),
 	TPARGS(irq, action),
-	TPFMT("irq=%d handler=%s", irq, action->name));
+	TPFMT("irq=%d handler=%s", irq, action->name),
+	TRACE_STRUCT(
+		TRACE_FIELD(int, irq, irq)
+	),
+	TPRAWFMT("irq %d")
+	);
 
-TRACE_FORMAT(irq_handler_exit,
+TRACE_EVENT_FORMAT(irq_handler_exit,
 	TPPROTO(int irq, struct irqaction *action, int ret),
 	TPARGS(irq, action, ret),
 	TPFMT("irq=%d handler=%s return=%s",
-		irq, action->name, ret ? "handled" : "unhandled"));
+		irq, action->name, ret ? "handled" : "unhandled"),
+	TRACE_STRUCT(
+		TRACE_FIELD(int, irq, irq)
+		TRACE_FIELD(int, ret, ret)
+	),
+	TPRAWFMT("irq %d ret %d")
+	);
+
+#undef TRACE_SYSTEM

include/trace/sched_event_types.h

@@ -1,72 +1,146 @@
 
 /* use <trace/sched.h> instead */
-#ifndef TRACE_FORMAT
+#ifndef TRACE_EVENT_FORMAT
 # error Do not include this file directly.
 # error Unless you know what you are doing.
 #endif
 
-TRACE_FORMAT(sched_kthread_stop,
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM sched
+
+TRACE_EVENT_FORMAT(sched_kthread_stop,
 	TPPROTO(struct task_struct *t),
 	TPARGS(t),
-	TPFMT("task %s:%d", t->comm, t->pid));
+	TPFMT("task %s:%d", t->comm, t->pid),
+	TRACE_STRUCT(
+		TRACE_FIELD(pid_t, pid, t->pid)
+	),
+	TPRAWFMT("task %d")
+	);
 
-TRACE_FORMAT(sched_kthread_stop_ret,
+TRACE_EVENT_FORMAT(sched_kthread_stop_ret,
 	TPPROTO(int ret),
 	TPARGS(ret),
-	TPFMT("ret=%d", ret));
+	TPFMT("ret=%d", ret),
+	TRACE_STRUCT(
+		TRACE_FIELD(int, ret, ret)
+	),
+	TPRAWFMT("ret=%d")
+	);
 
-TRACE_FORMAT(sched_wait_task,
+TRACE_EVENT_FORMAT(sched_wait_task,
 	TPPROTO(struct rq *rq, struct task_struct *p),
 	TPARGS(rq, p),
-	TPFMT("task %s:%d", p->comm, p->pid));
+	TPFMT("task %s:%d", p->comm, p->pid),
+	TRACE_STRUCT(
+		TRACE_FIELD(pid_t, pid, p->pid)
+	),
+	TPRAWFMT("task %d")
+	);
 
-TRACE_FORMAT(sched_wakeup,
+TRACE_EVENT_FORMAT(sched_wakeup,
 	TPPROTO(struct rq *rq, struct task_struct *p, int success),
 	TPARGS(rq, p, success),
 	TPFMT("task %s:%d %s",
-	      p->comm, p->pid, success?"succeeded":"failed"));
+	      p->comm, p->pid, success ? "succeeded" : "failed"),
+	TRACE_STRUCT(
+		TRACE_FIELD(pid_t, pid, p->pid)
+		TRACE_FIELD(int, success, success)
+	),
+	TPRAWFMT("task %d success=%d")
+	);
 
-TRACE_FORMAT(sched_wakeup_new,
+TRACE_EVENT_FORMAT(sched_wakeup_new,
 	TPPROTO(struct rq *rq, struct task_struct *p, int success),
 	TPARGS(rq, p, success),
 	TPFMT("task %s:%d",
-	      p->comm, p->pid, success?"succeeded":"failed"));
+	      p->comm, p->pid, success ? "succeeded" : "failed"),
+	TRACE_STRUCT(
+		TRACE_FIELD(pid_t, pid, p->pid)
+		TRACE_FIELD(int, success, success)
+	),
+	TPRAWFMT("task %d success=%d")
+	);
 
-TRACE_FORMAT(sched_switch,
+TRACE_EVENT_FORMAT(sched_switch,
 	TPPROTO(struct rq *rq, struct task_struct *prev,
 		struct task_struct *next),
 	TPARGS(rq, prev, next),
 	TPFMT("task %s:%d ==> %s:%d",
-	      prev->comm, prev->pid, next->comm, next->pid));
+	      prev->comm, prev->pid, next->comm, next->pid),
+	TRACE_STRUCT(
+		TRACE_FIELD(pid_t, prev_pid, prev->pid)
+		TRACE_FIELD(int, prev_prio, prev->prio)
+		TRACE_FIELD(pid_t, next_pid, next->pid)
+		TRACE_FIELD(int, next_prio, next->prio)
+	),
+	TPRAWFMT("prev %d:%d ==> next %d:%d")
+	);
 
-TRACE_FORMAT(sched_migrate_task,
+TRACE_EVENT_FORMAT(sched_migrate_task,
 	TPPROTO(struct task_struct *p, int orig_cpu, int dest_cpu),
 	TPARGS(p, orig_cpu, dest_cpu),
 	TPFMT("task %s:%d from: %d  to: %d",
-	      p->comm, p->pid, orig_cpu, dest_cpu));
+	      p->comm, p->pid, orig_cpu, dest_cpu),
+	TRACE_STRUCT(
+		TRACE_FIELD(pid_t, pid, p->pid)
+		TRACE_FIELD(int, orig_cpu, orig_cpu)
+		TRACE_FIELD(int, dest_cpu, dest_cpu)
+	),
+	TPRAWFMT("task %d  from: %d to: %d")
+	);
 
-TRACE_FORMAT(sched_process_free,
+TRACE_EVENT_FORMAT(sched_process_free,
 	TPPROTO(struct task_struct *p),
 	TPARGS(p),
-	TPFMT("task %s:%d", p->comm, p->pid));
+	TPFMT("task %s:%d", p->comm, p->pid),
+	TRACE_STRUCT(
+		TRACE_FIELD(pid_t, pid, p->pid)
+	),
+	TPRAWFMT("task %d")
+	);
 
-TRACE_FORMAT(sched_process_exit,
+TRACE_EVENT_FORMAT(sched_process_exit,
 	TPPROTO(struct task_struct *p),
 	TPARGS(p),
-	TPFMT("task %s:%d", p->comm, p->pid));
+	TPFMT("task %s:%d", p->comm, p->pid),
+	TRACE_STRUCT(
+		TRACE_FIELD(pid_t, pid, p->pid)
+	),
+	TPRAWFMT("task %d")
+	);
 
-TRACE_FORMAT(sched_process_wait,
+TRACE_EVENT_FORMAT(sched_process_wait,
 	TPPROTO(struct pid *pid),
 	TPARGS(pid),
-	TPFMT("pid %d", pid));
+	TPFMT("pid %d", pid_nr(pid)),
+	TRACE_STRUCT(
+		TRACE_FIELD(pid_t, pid, pid_nr(pid))
+	),
+	TPRAWFMT("task %d")
+	);
 
-TRACE_FORMAT(sched_process_fork,
+TRACE_EVENT_FORMAT(sched_process_fork,
 	TPPROTO(struct task_struct *parent, struct task_struct *child),
 	TPARGS(parent, child),
 	TPFMT("parent %s:%d  child %s:%d",
-	      parent->comm, parent->pid, child->comm, child->pid));
+	      parent->comm, parent->pid, child->comm, child->pid),
+	TRACE_STRUCT(
+		TRACE_FIELD(pid_t, parent, parent->pid)
+		TRACE_FIELD(pid_t, child, child->pid)
+	),
+	TPRAWFMT("parent %d  child %d")
+	);
 
-TRACE_FORMAT(sched_signal_send,
+TRACE_EVENT_FORMAT(sched_signal_send,
 	TPPROTO(int sig, struct task_struct *p),
 	TPARGS(sig, p),
-	TPFMT("sig: %d   task %s:%d", sig, p->comm, p->pid));
+	TPFMT("sig: %d   task %s:%d", sig, p->comm, p->pid),
+	TRACE_STRUCT(
+		TRACE_FIELD(int, sig, sig)
+		TRACE_FIELD(pid_t, pid, p->pid)
+	),
+	TPRAWFMT("sig: %d  task %d")
+	);
+
+#undef TRACE_SYSTEM

include/trace/trace_event_types.h

@@ -0,0 +1,4 @@
+/* trace/<type>_event_types.h here */
+
+#include <trace/sched_event_types.h>
+#include <trace/irq_event_types.h>

include/trace/trace_events.h

@@ -0,0 +1,4 @@
+/* trace/<type>.h here */
+
+#include <trace/sched.h>
+#include <trace/irq.h>

kernel/trace/events.c

@@ -1,15 +1,17 @@
 /*
  * This is the place to register all trace points as events.
- * Include the trace/<type>.h at the top.
- * Include the trace/<type>_event_types.h at the bottom.
  */
 
-/* trace/<type>.h here */
-#include <trace/sched.h>
-#include <trace/irq.h>
+/* someday this needs to go in a generic header */
+#define __STR(x) #x
+#define STR(x) __STR(x)
 
-#include "trace_events.h"
+#include <trace/trace_events.h>
 
-/* trace/<type>_event_types.h here */
-#include <trace/sched_event_types.h>
-#include <trace/irq_event_types.h>
+#include "trace_output.h"
+
+#include "trace_events_stage_1.h"
+#include "trace_events_stage_2.h"
+#include "trace_events_stage_3.h"
+
+#include <trace/trace_event_types.h>

kernel/trace/trace.c

@@ -846,6 +846,20 @@ void trace_buffer_unlock_commit(struct trace_array *tr,
 	trace_wake_up();
 }
 
+struct ring_buffer_event *
+trace_current_buffer_lock_reserve(unsigned char type, unsigned long len,
+				  unsigned long flags, int pc)
+{
+	return trace_buffer_lock_reserve(&global_trace,
+					 type, len, flags, pc);
+}
+
+void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
+					unsigned long flags, int pc)
+{
+	return trace_buffer_unlock_commit(&global_trace, event, flags, pc);
+}
+
 void
 trace_function(struct trace_array *tr,
 	       unsigned long ip, unsigned long parent_ip, unsigned long flags,

kernel/trace/trace.h

@@ -442,6 +442,12 @@ void trace_buffer_unlock_commit(struct trace_array *tr,
 				struct ring_buffer_event *event,
 				unsigned long flags, int pc);
 
+struct ring_buffer_event *
+trace_current_buffer_lock_reserve(unsigned char type, unsigned long len,
+				  unsigned long flags, int pc);
+void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
+					unsigned long flags, int pc);
+
 struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
 						struct trace_array_cpu *data);
 
@@ -720,4 +726,30 @@ static inline void trace_branch_disable(void)
 }
 #endif /* CONFIG_BRANCH_TRACER */
 
+/* trace event type bit fields, not numeric */
+enum {
+	TRACE_EVENT_TYPE_PRINTF		= 1,
+	TRACE_EVENT_TYPE_RAW		= 2,
+};
+
+struct ftrace_event_call {
+	char		*name;
+	char		*system;
+	struct dentry	*dir;
+	int		enabled;
+	int		(*regfunc)(void);
+	void		(*unregfunc)(void);
+	int		id;
+	struct dentry	*raw_dir;
+	int		raw_enabled;
+	int		type;
+	int		(*raw_init)(void);
+	int		(*raw_reg)(void);
+	void		(*raw_unreg)(void);
+};
+
+void event_trace_printk(unsigned long ip, const char *fmt, ...);
+extern struct ftrace_event_call __start_ftrace_events[];
+extern struct ftrace_event_call __stop_ftrace_events[];
+
 #endif /* _LINUX_KERNEL_TRACE_H */

kernel/trace/trace_events.c

@@ -10,7 +10,9 @@
 #include <linux/module.h>
 #include <linux/ctype.h>
 
-#include "trace_events.h"
+#include "trace.h"
+
+#define TRACE_SYSTEM "TRACE_SYSTEM"
 
 #define events_for_each(event)						\
 	for (event = __start_ftrace_events;				\
@@ -42,35 +44,87 @@ static void ftrace_clear_events(void)
 	}
 }
 
+static void ftrace_event_enable_disable(struct ftrace_event_call *call,
+					int enable)
+{
+
+	switch (enable) {
+	case 0:
+		if (call->enabled) {
+			call->enabled = 0;
+			call->unregfunc();
+		}
+		if (call->raw_enabled) {
+			call->raw_enabled = 0;
+			call->raw_unreg();
+		}
+		break;
+	case 1:
+		if (!call->enabled &&
+		    (call->type & TRACE_EVENT_TYPE_PRINTF)) {
+			call->enabled = 1;
+			call->regfunc();
+		}
+		if (!call->raw_enabled &&
+		    (call->type & TRACE_EVENT_TYPE_RAW)) {
+			call->raw_enabled = 1;
+			call->raw_reg();
+		}
+		break;
+	}
+}
+
 static int ftrace_set_clr_event(char *buf, int set)
 {
 	struct ftrace_event_call *call = __start_ftrace_events;
-
+	char *event = NULL, *sub = NULL, *match;
+	int ret = -EINVAL;
+
+	/*
+	 * The buf format can be <subsystem>:<event-name>
+	 *  *:<event-name> means any event by that name.
+	 *  :<event-name> is the same.
+	 *
+	 *  <subsystem>:* means all events in that subsystem
+	 *  <subsystem>: means the same.
+	 *
+	 *  <name> (no ':') means all events in a subsystem with
+	 *  the name <name> or any event that matches <name>
+	 */
+
+	match = strsep(&buf, ":");
+	if (buf) {
+		sub = match;
+		event = buf;
+		match = NULL;
+
+		if (!strlen(sub) || strcmp(sub, "*") == 0)
+			sub = NULL;
+		if (!strlen(event) || strcmp(event, "*") == 0)
+			event = NULL;
+	}
 
 	events_for_each(call) {
 
 		if (!call->name)
 			continue;
 
-		if (strcmp(buf, call->name) != 0)
+		if (match &&
+		    strcmp(match, call->name) != 0 &&
+		    strcmp(match, call->system) != 0)
 			continue;
 
-		if (set) {
-			/* Already set? */
-			if (call->enabled)
-				return 0;
-			call->enabled = 1;
-			call->regfunc();
-		} else {
-			/* Already cleared? */
-			if (!call->enabled)
-				return 0;
-			call->enabled = 0;
-			call->unregfunc();
-		}
-		return 0;
+		if (sub && strcmp(sub, call->system) != 0)
+			continue;
+
+		if (event && strcmp(event, call->name) != 0)
+			continue;
+
+		ftrace_event_enable_disable(call, set);
+
+		ret = 0;
 	}
-	return -EINVAL;
+	return ret;
 }
 
 /* 128 should be much more than enough */
@@ -200,6 +254,8 @@ static int t_show(struct seq_file *m, void *v)
 {
 	struct ftrace_event_call *call = v;
 
+	if (strcmp(call->system, TRACE_SYSTEM) != 0)
+		seq_printf(m, "%s:", call->system);
 	seq_printf(m, "%s\n", call->name);
 
 	return 0;
@@ -236,7 +292,7 @@ event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
 	struct ftrace_event_call *call = filp->private_data;
 	char *buf;
 
-	if (call->enabled)
+	if (call->enabled || call->raw_enabled)
 		buf = "1\n";
 	else
 		buf = "0\n";
@@ -267,18 +323,8 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
 	switch (val) {
 	case 0:
-		if (!call->enabled)
-			break;
-
-		call->enabled = 0;
-		call->unregfunc();
-		break;
 	case 1:
-		if (call->enabled)
-			break;
-
-		call->enabled = 1;
-		call->regfunc();
+		ftrace_event_enable_disable(call, val);
 		break;
 
 	default:
@@ -290,6 +336,107 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	return cnt;
 }
 
+static ssize_t
+event_type_read(struct file *filp, char __user *ubuf, size_t cnt,
+		loff_t *ppos)
+{
+	struct ftrace_event_call *call = filp->private_data;
+	char buf[16];
+	int r = 0;
+
+	if (call->type & TRACE_EVENT_TYPE_PRINTF)
+		r += sprintf(buf, "printf\n");
+
+	if (call->type & TRACE_EVENT_TYPE_RAW)
+		r += sprintf(buf+r, "raw\n");
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+event_type_write(struct file *filp, const char __user *ubuf, size_t cnt,
+		 loff_t *ppos)
+{
+	struct ftrace_event_call *call = filp->private_data;
+	char buf[64];
+
+	/*
+	 * If there's only one type, we can't change it.
+	 * And currently we always have printf type, and we
+	 * may or may not have raw type.
+	 *
+	 * This is a redundant check, the file should be read
+	 * only if this is the case anyway.
+	 */
+
+	if (!call->raw_init)
+		return -EPERM;
+
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+
+	if (!strncmp(buf, "printf", 6) &&
+	    (!buf[6] || isspace(buf[6]))) {
+
+		call->type = TRACE_EVENT_TYPE_PRINTF;
+
+		/*
+		 * If raw enabled, the disable it and enable
+		 * printf type.
+		 */
+		if (call->raw_enabled) {
+			call->raw_enabled = 0;
+			call->raw_unreg();
+
+			call->enabled = 1;
+			call->regfunc();
+		}
+
+	} else if (!strncmp(buf, "raw", 3) &&
+	    (!buf[3] || isspace(buf[3]))) {
+
+		call->type = TRACE_EVENT_TYPE_RAW;
+
+		/*
+		 * If printf enabled, the disable it and enable
+		 * raw type.
+		 */
+		if (call->enabled) {
+			call->enabled = 0;
+			call->unregfunc();
+
+			call->raw_enabled = 1;
+			call->raw_reg();
+		}
+	} else
+		return -EINVAL;
+
+	*ppos += cnt;
+
+	return cnt;
+}
+
+static ssize_t
+event_available_types_read(struct file *filp, char __user *ubuf, size_t cnt,
+			   loff_t *ppos)
+{
+	struct ftrace_event_call *call = filp->private_data;
+	char buf[16];
+	int r = 0;
+
+	r += sprintf(buf, "printf\n");
+
+	if (call->raw_init)
+		r += sprintf(buf+r, "raw\n");
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
 static const struct seq_operations show_event_seq_ops = {
 	.start = t_start,
 	.next = t_next,
@@ -325,6 +472,17 @@ static const struct file_operations ftrace_enable_fops = {
 	.write = event_enable_write,
 };
 
+static const struct file_operations ftrace_type_fops = {
+	.open = tracing_open_generic,
+	.read = event_type_read,
+	.write = event_type_write,
+};
+
+static const struct file_operations ftrace_available_types_fops = {
+	.open = tracing_open_generic,
+	.read = event_available_types_read,
+};
+
 static struct dentry *event_trace_events_dir(void)
 {
 	static struct dentry *d_tracer;
@@ -345,10 +503,71 @@ static struct dentry *event_trace_events_dir(void)
 	return d_events;
 }
 
+struct event_subsystem {
+	struct list_head	list;
+	const char		*name;
+	struct dentry		*entry;
+};
+
+static LIST_HEAD(event_subsystems);
+
+static struct dentry *
+event_subsystem_dir(const char *name, struct dentry *d_events)
+{
+	struct event_subsystem *system;
+
+	/* First see if we did not already create this dir */
+	list_for_each_entry(system, &event_subsystems, list) {
+		if (strcmp(system->name, name) == 0)
+			return system->entry;
+	}
+
+	/* need to create new entry */
+	system = kmalloc(sizeof(*system), GFP_KERNEL);
+	if (!system) {
+		pr_warning("No memory to create event subsystem %s\n",
+			   name);
+		return d_events;
+	}
+
+	system->entry = debugfs_create_dir(name, d_events);
+	if (!system->entry) {
+		pr_warning("Could not create event subsystem %s\n",
+			   name);
+		kfree(system);
+		return d_events;
+	}
+
+	system->name = name;
+	list_add(&system->list, &event_subsystems);
+
+	return system->entry;
+}
+
 static int
 event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
 {
 	struct dentry *entry;
+	int ret;
+
+	/*
+	 * If the trace point header did not define TRACE_SYSTEM
+	 * then the system would be called "TRACE_SYSTEM".
+	 */
+	if (strcmp(call->system, "TRACE_SYSTEM") != 0)
+		d_events = event_subsystem_dir(call->system, d_events);
+
+	if (call->raw_init) {
+		ret = call->raw_init();
+		if (ret < 0) {
+			pr_warning("Could not initialize trace point"
+				   " events/%s\n", call->name);
+			return ret;
+		}
+	}
+
+	/* default the output to printf */
+	call->type = TRACE_EVENT_TYPE_PRINTF;
 
 	call->dir = debugfs_create_dir(call->name, d_events);
 	if (!call->dir) {
@@ -363,6 +582,21 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
 		pr_warning("Could not create debugfs "
 			   "'%s/enable' entry\n", call->name);
 
+	/* Only let type be writable, if we can change it */
+	entry = debugfs_create_file("type",
+				    call->raw_init ? 0644 : 0444,
+				    call->dir, call,
+				    &ftrace_type_fops);
+	if (!entry)
+		pr_warning("Could not create debugfs "
+			   "'%s/type' entry\n", call->name);
+
+	entry = debugfs_create_file("available_types", 0444, call->dir, call,
+				    &ftrace_available_types_fops);
+	if (!entry)
+		pr_warning("Could not create debugfs "
+			   "'%s/type' available_types\n", call->name);
+
 	return 0;
 }
 

kernel/trace/trace_events.h

@@ -1,55 +0,0 @@
-#ifndef _LINUX_KERNEL_TRACE_EVENTS_H
-#define _LINUX_KERNEL_TRACE_EVENTS_H
-
-#include <linux/debugfs.h>
-#include <linux/ftrace.h>
-#include "trace.h"
-
-struct ftrace_event_call {
-	char		*name;
-	struct dentry	*dir;
-	int		enabled;
-	int		(*regfunc)(void);
-	void		(*unregfunc)(void);
-};
-
-
-#undef TPFMT
-#define TPFMT(fmt, args...)	fmt "\n", ##args
-
-#undef TRACE_FORMAT
-#define TRACE_FORMAT(call, proto, args, fmt)				\
-static void ftrace_event_##call(proto)					\
-{									\
-	event_trace_printk(_RET_IP_, "(" #call ") " fmt);		\
-}									\
-									\
-static int ftrace_reg_event_##call(void)				\
-{									\
-	int ret;							\
-									\
-	ret = register_trace_##call(ftrace_event_##call);		\
-	if (!ret)							\
-		pr_info("event trace: Could not activate trace point "	\
-			"probe to " #call);				\
-	return ret;							\
-}									\
-									\
-static void ftrace_unreg_event_##call(void)				\
-{									\
-	unregister_trace_##call(ftrace_event_##call);			\
-}									\
-									\
-static struct ftrace_event_call __used					\
-__attribute__((__aligned__(4)))						\
-__attribute__((section("_ftrace_events"))) event_##call = {		\
-	.name 			= #call,				\
-	.regfunc		= ftrace_reg_event_##call,		\
-	.unregfunc		= ftrace_unreg_event_##call,		\
-}
-
-void event_trace_printk(unsigned long ip, const char *fmt, ...);
-extern struct ftrace_event_call __start_ftrace_events[];
-extern struct ftrace_event_call __stop_ftrace_events[];
-
-#endif /* _LINUX_KERNEL_TRACE_EVENTS_H */

kernel/trace/trace_events_stage_1.h

@@ -0,0 +1,34 @@
+/*
+ * Stage 1 of the trace events.
+ *
+ * Override the macros in <trace/trace_event_types.h> to include the following:
+ *
+ * struct ftrace_raw_<call> {
+ *	struct trace_entry		ent;
+ *	<type>				<item>;
+ *	[...]
+ * };
+ *
+ * The <type> <item> is created by the TRACE_FIELD(type, item, assign)
+ * macro. We simply do "type item;", and that will create the fields
+ * in the structure.
+ */
+
+#undef TRACE_FORMAT
+#define TRACE_FORMAT(call, proto, args, fmt)
+
+#undef TRACE_EVENT_FORMAT
+#define TRACE_EVENT_FORMAT(name, proto, args, fmt, tstruct, tpfmt)	\
+	struct ftrace_raw_##name {					\
+		struct trace_entry	ent;				\
+		tstruct							\
+	};								\
+	static struct ftrace_event_call event_##name
+
+#undef TRACE_STRUCT
+#define TRACE_STRUCT(args...) args
+
+#define TRACE_FIELD(type, item, assign) \
+	type item;
+
+#include <trace/trace_event_types.h>

kernel/trace/trace_events_stage_2.h

@@ -0,0 +1,72 @@
+/*
+ * Stage 2 of the trace events.
+ *
+ * Override the macros in <trace/trace_event_types.h> to include the following:
+ *
+ * enum print_line_t
+ * ftrace_raw_output_<call>(struct trace_iterator *iter, int flags)
+ * {
+ *	struct trace_seq *s = &iter->seq;
+ *	struct ftrace_raw_<call> *field; <-- defined in stage 1
+ *	struct trace_entry *entry;
+ *	int ret;
+ *
+ *	entry = iter->ent;
+ *
+ *	if (entry->type != event_<call>.id) {
+ *		WARN_ON_ONCE(1);
+ *		return TRACE_TYPE_UNHANDLED;
+ *	}
+ *
+ *	field = (typeof(field))entry;
+ *
+ *	ret = trace_seq_printf(s, <TPRAWFMT> "%s", <ARGS> "\n");
+ *	if (!ret)
+ *		return TRACE_TYPE_PARTIAL_LINE;
+ *
+ *	return TRACE_TYPE_HANDLED;
+ * }
+ *
+ * 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
+ * in binary.
+ */
+
+#undef TRACE_STRUCT
+#define TRACE_STRUCT(args...) args
+
+#undef TRACE_FIELD
+#define TRACE_FIELD(type, item, assign) \
+	field->item,
+
+
+#undef TPRAWFMT
+#define TPRAWFMT(args...)	args
+
+#undef TRACE_EVENT_FORMAT
+#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt)	\
+enum print_line_t							\
+ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
+{									\
+	struct trace_seq *s = &iter->seq;				\
+	struct ftrace_raw_##call *field;				\
+	struct trace_entry *entry;					\
+	int ret;							\
+									\
+	entry = iter->ent;						\
+									\
+	if (entry->type != event_##call.id) {				\
+		WARN_ON_ONCE(1);					\
+		return TRACE_TYPE_UNHANDLED;				\
+	}								\
+									\
+	field = (typeof(field))entry;					\
+									\
+	ret = trace_seq_printf(s, tpfmt "%s", tstruct "\n");		\
+	if (!ret)							\
+		return TRACE_TYPE_PARTIAL_LINE;				\
+									\
+	return TRACE_TYPE_HANDLED;					\
+}
+
+#include <trace/trace_event_types.h>

kernel/trace/trace_events_stage_3.h

@@ -0,0 +1,219 @@
+/*
+ * Stage 3 of the trace events.
+ *
+ * Override the macros in <trace/trace_event_types.h> to include the following:
+ *
+ * static void ftrace_event_<call>(proto)
+ * {
+ * 	event_trace_printk(_RET_IP_, "(<call>) " <fmt>);
+ * }
+ *
+ * static int ftrace_reg_event_<call>(void)
+ * {
+ * 	int ret;
+ *
+ * 	ret = register_trace_<call>(ftrace_event_<call>);
+ * 	if (!ret)
+ * 		pr_info("event trace: Could not activate trace point "
+ * 			"probe to  <call>");
+ * 	return ret;
+ * }
+ *
+ * static void ftrace_unreg_event_<call>(void)
+ * {
+ * 	unregister_trace_<call>(ftrace_event_<call>);
+ * }
+ *
+ * For those macros defined with TRACE_FORMAT:
+ *
+ * static struct ftrace_event_call __used
+ * __attribute__((__aligned__(4)))
+ * __attribute__((section("_ftrace_events"))) event_<call> = {
+ * 	.name 			= "<call>",
+ * 	.regfunc		= ftrace_reg_event_<call>,
+ * 	.unregfunc		= ftrace_unreg_event_<call>,
+ * }
+ *
+ *
+ * For those macros defined with TRACE_EVENT_FORMAT:
+ *
+ * static struct ftrace_event_call event_<call>;
+ *
+ * static void ftrace_raw_event_<call>(proto)
+ * {
+ * 	struct ring_buffer_event *event;
+ * 	struct ftrace_raw_<call> *entry; <-- defined in stage 1
+ * 	unsigned long irq_flags;
+ * 	int pc;
+ *
+ * 	local_save_flags(irq_flags);
+ * 	pc = preempt_count();
+ *
+ * 	event = trace_current_buffer_lock_reserve(event_<call>.id,
+ * 				  sizeof(struct ftrace_raw_<call>),
+ * 				  irq_flags, pc);
+ * 	if (!event)
+ * 		return;
+ * 	entry	= ring_buffer_event_data(event);
+ *
+ * 	<tstruct>;  <-- Here we assign the entries by the TRACE_FIELD.
+ *
+ * 	trace_current_buffer_unlock_commit(event, irq_flags, pc);
+ * }
+ *
+ * static int ftrace_raw_reg_event_<call>(void)
+ * {
+ * 	int ret;
+ *
+ * 	ret = register_trace_<call>(ftrace_raw_event_<call>);
+ * 	if (!ret)
+ * 		pr_info("event trace: Could not activate trace point "
+ * 			"probe to <call>");
+ * 	return ret;
+ * }
+ *
+ * static void ftrace_unreg_event_<call>(void)
+ * {
+ * 	unregister_trace_<call>(ftrace_raw_event_<call>);
+ * }
+ *
+ * static struct trace_event ftrace_event_type_<call> = {
+ * 	.trace			= ftrace_raw_output_<call>, <-- stage 2
+ * };
+ *
+ * static int ftrace_raw_init_event_<call>(void)
+ * {
+ * 	int id;
+ *
+ * 	id = register_ftrace_event(&ftrace_event_type_<call>);
+ * 	if (!id)
+ * 		return -ENODEV;
+ * 	event_<call>.id = id;
+ * 	return 0;
+ * }
+ *
+ * static struct ftrace_event_call __used
+ * __attribute__((__aligned__(4)))
+ * __attribute__((section("_ftrace_events"))) event_<call> = {
+ * 	.name 			= "<call>",
+ * 	.regfunc		= ftrace_reg_event_<call>,
+ * 	.unregfunc		= ftrace_unreg_event_<call>,
+ * 	.raw_init		= ftrace_raw_init_event_<call>,
+ * 	.raw_reg		= ftrace_raw_reg_event_<call>,
+ * 	.raw_unreg		= ftrace_raw_unreg_event_<call>,
+ * }
+ *
+ */
+
+#undef TPFMT
+#define TPFMT(fmt, args...)	fmt "\n", ##args
+
+#define _TRACE_FORMAT(call, proto, args, fmt)				\
+static void ftrace_event_##call(proto)					\
+{									\
+	event_trace_printk(_RET_IP_, "(" #call ") " fmt);		\
+}									\
+									\
+static int ftrace_reg_event_##call(void)				\
+{									\
+	int ret;							\
+									\
+	ret = register_trace_##call(ftrace_event_##call);		\
+	if (!ret)							\
+		pr_info("event trace: Could not activate trace point "	\
+			"probe to " #call);				\
+	return ret;							\
+}									\
+									\
+static void ftrace_unreg_event_##call(void)				\
+{									\
+	unregister_trace_##call(ftrace_event_##call);			\
+}									\
+
+
+#undef TRACE_FORMAT
+#define TRACE_FORMAT(call, proto, args, fmt)				\
+_TRACE_FORMAT(call, PARAMS(proto), PARAMS(args), PARAMS(fmt))		\
+static struct ftrace_event_call __used					\
+__attribute__((__aligned__(4)))						\
+__attribute__((section("_ftrace_events"))) event_##call = {		\
+	.name 			= #call,				\
+	.system			= STR(TRACE_SYSTEM),			\
+	.regfunc		= ftrace_reg_event_##call,		\
+	.unregfunc		= ftrace_unreg_event_##call,		\
+}
+
+#undef TRACE_FIELD
+#define TRACE_FIELD(type, item, assign)\
+	entry->item = assign;
+
+#undef TRACE_EVENT_FORMAT
+#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt)	\
+_TRACE_FORMAT(call, PARAMS(proto), PARAMS(args), PARAMS(fmt))		\
+									\
+static struct ftrace_event_call event_##call;				\
+									\
+static void ftrace_raw_event_##call(proto)				\
+{									\
+	struct ring_buffer_event *event;				\
+	struct ftrace_raw_##call *entry;				\
+	unsigned long irq_flags;					\
+	int pc;								\
+									\
+	local_save_flags(irq_flags);					\
+	pc = preempt_count();						\
+									\
+	event = trace_current_buffer_lock_reserve(event_##call.id,	\
+				  sizeof(struct ftrace_raw_##call), 	\
+				  irq_flags, pc);			\
+	if (!event)							\
+		return;							\
+	entry	= ring_buffer_event_data(event);			\
+									\
+	tstruct;							\
+									\
+	trace_current_buffer_unlock_commit(event, irq_flags, pc);	\
+}									\
+									\
+static int ftrace_raw_reg_event_##call(void)				\
+{									\
+	int ret;							\
+									\
+	ret = register_trace_##call(ftrace_raw_event_##call);		\
+	if (!ret)							\
+		pr_info("event trace: Could not activate trace point "	\
+			"probe to " #call);				\
+	return ret;							\
+}									\
+									\
+static void ftrace_raw_unreg_event_##call(void)				\
+{									\
+	unregister_trace_##call(ftrace_raw_event_##call);		\
+}									\
+									\
+static struct trace_event ftrace_event_type_##call = {			\
+	.trace			= ftrace_raw_output_##call,		\
+};									\
+									\
+static int ftrace_raw_init_event_##call(void)				\
+{									\
+	int id;								\
+									\
+	id = register_ftrace_event(&ftrace_event_type_##call);		\
+	if (!id)							\
+		return -ENODEV;						\
+	event_##call.id = id;						\
+	return 0;							\
+}									\
+									\
+static struct ftrace_event_call __used					\
+__attribute__((__aligned__(4)))						\
+__attribute__((section("_ftrace_events"))) event_##call = {		\
+	.name 			= #call,				\
+	.system			= STR(TRACE_SYSTEM),			\
+	.regfunc		= ftrace_reg_event_##call,		\
+	.unregfunc		= ftrace_unreg_event_##call,		\
+	.raw_init		= ftrace_raw_init_event_##call,		\
+	.raw_reg		= ftrace_raw_reg_event_##call,		\
+	.raw_unreg		= ftrace_raw_unreg_event_##call,	\
+}