X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Ftrace%2Ftrace_events.c;h=53cffc0b08014db76d9e87da0d8bbc3c9768bd49;hb=9b8eb4d14767209c83087063352cd04266ecdfd1;hp=bbbea7479371fa9ae413158426d6f62976996992;hpb=a118e4d1402f1349fe3d953493e4168a300a752d;p=safe%2Fjmp%2Flinux-2.6

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index bbbea74..53cffc0 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -15,20 +15,37 @@
 #include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
+#include <linux/slab.h>
 #include <linux/delay.h>
 
+#include <asm/setup.h>
+
 #include "trace_output.h"
 
+#undef TRACE_SYSTEM
 #define TRACE_SYSTEM "TRACE_SYSTEM"
 
-static DEFINE_MUTEX(event_mutex);
+DEFINE_MUTEX(event_mutex);
 
 LIST_HEAD(ftrace_events);
 
-int trace_define_field(struct ftrace_event_call *call, char *type,
-		       char *name, int offset, int size, int is_signed)
+struct list_head *
+trace_get_fields(struct ftrace_event_call *event_call)
+{
+	if (!event_call->class->get_fields)
+		return &event_call->class->fields;
+	return event_call->class->get_fields(event_call);
+}
+
+int trace_define_field(struct ftrace_event_call *call, const char *type,
+		       const char *name, int offset, int size, int is_signed,
+		       int filter_type)
 {
 	struct ftrace_event_field *field;
+	struct list_head *head;
+
+	if (WARN_ON(!call->class))
+		return 0;
 
 	field = kzalloc(sizeof(*field), GFP_KERNEL);
 	if (!field)
@@ -42,63 +59,169 @@ int trace_define_field(struct ftrace_event_call *call, char *type,
 	if (!field->type)
 		goto err;
 
+	if (filter_type == FILTER_OTHER)
+		field->filter_type = filter_assign_type(type);
+	else
+		field->filter_type = filter_type;
+
 	field->offset = offset;
 	field->size = size;
 	field->is_signed = is_signed;
-	list_add(&field->link, &call->fields);
+
+	head = trace_get_fields(call);
+	list_add(&field->link, head);
 
 	return 0;
 
 err:
-	if (field) {
+	if (field)
 		kfree(field->name);
-		kfree(field->type);
-	}
 	kfree(field);
 
 	return -ENOMEM;
 }
 EXPORT_SYMBOL_GPL(trace_define_field);
 
-static void ftrace_clear_events(void)
+#define __common_field(type, item)					\
+	ret = trace_define_field(call, #type, "common_" #item,		\
+				 offsetof(typeof(ent), item),		\
+				 sizeof(ent.item),			\
+				 is_signed_type(type), FILTER_OTHER);	\
+	if (ret)							\
+		return ret;
+
+static int trace_define_common_fields(struct ftrace_event_call *call)
 {
-	struct ftrace_event_call *call;
+	int ret;
+	struct trace_entry ent;
 
-	list_for_each_entry(call, &ftrace_events, list) {
+	__common_field(unsigned short, type);
+	__common_field(unsigned char, flags);
+	__common_field(unsigned char, preempt_count);
+	__common_field(int, pid);
+	__common_field(int, lock_depth);
 
-		if (call->enabled) {
-			call->enabled = 0;
-			call->unregfunc();
-		}
+	return ret;
+}
+
+void trace_destroy_fields(struct ftrace_event_call *call)
+{
+	struct ftrace_event_field *field, *next;
+	struct list_head *head;
+
+	head = trace_get_fields(call);
+	list_for_each_entry_safe(field, next, head, link) {
+		list_del(&field->link);
+		kfree(field->type);
+		kfree(field->name);
+		kfree(field);
 	}
 }
 
-static void ftrace_event_enable_disable(struct ftrace_event_call *call,
+int trace_event_raw_init(struct ftrace_event_call *call)
+{
+	int id;
+
+	id = register_ftrace_event(&call->event);
+	if (!id)
+		return -ENODEV;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(trace_event_raw_init);
+
+static int ftrace_event_enable_disable(struct ftrace_event_call *call,
 					int enable)
 {
+	int ret = 0;
 
 	switch (enable) {
 	case 0:
-		if (call->enabled) {
-			call->enabled = 0;
-			call->unregfunc();
+		if (call->flags & TRACE_EVENT_FL_ENABLED) {
+			call->flags &= ~TRACE_EVENT_FL_ENABLED;
+			tracing_stop_cmdline_record();
+			if (call->class->reg)
+				call->class->reg(call, TRACE_REG_UNREGISTER);
+			else
+				tracepoint_probe_unregister(call->name,
+							    call->class->probe,
+							    call);
 		}
 		break;
 	case 1:
-		if (!call->enabled) {
-			call->enabled = 1;
-			call->regfunc();
+		if (!(call->flags & TRACE_EVENT_FL_ENABLED)) {
+			tracing_start_cmdline_record();
+			if (call->class->reg)
+				ret = call->class->reg(call, TRACE_REG_REGISTER);
+			else
+				ret = tracepoint_probe_register(call->name,
+								call->class->probe,
+								call);
+			if (ret) {
+				tracing_stop_cmdline_record();
+				pr_info("event trace: Could not enable event "
+					"%s\n", call->name);
+				break;
+			}
+			call->flags |= TRACE_EVENT_FL_ENABLED;
 		}
 		break;
 	}
+
+	return ret;
 }
 
-static int ftrace_set_clr_event(char *buf, int set)
+static void ftrace_clear_events(void)
+{
+	struct ftrace_event_call *call;
+
+	mutex_lock(&event_mutex);
+	list_for_each_entry(call, &ftrace_events, list) {
+		ftrace_event_enable_disable(call, 0);
+	}
+	mutex_unlock(&event_mutex);
+}
+
+/*
+ * __ftrace_set_clr_event(NULL, NULL, NULL, set) will set/unset all events.
+ */
+static int __ftrace_set_clr_event(const char *match, const char *sub,
+				  const char *event, int set)
 {
 	struct ftrace_event_call *call;
-	char *event = NULL, *sub = NULL, *match;
 	int ret = -EINVAL;
 
+	mutex_lock(&event_mutex);
+	list_for_each_entry(call, &ftrace_events, list) {
+
+		if (!call->name || !call->class ||
+		    (!call->class->probe && !call->class->reg))
+			continue;
+
+		if (match &&
+		    strcmp(match, call->name) != 0 &&
+		    strcmp(match, call->class->system) != 0)
+			continue;
+
+		if (sub && strcmp(sub, call->class->system) != 0)
+			continue;
+
+		if (event && strcmp(event, call->name) != 0)
+			continue;
+
+		ftrace_event_enable_disable(call, set);
+
+		ret = 0;
+	}
+	mutex_unlock(&event_mutex);
+
+	return ret;
+}
+
+static int ftrace_set_clr_event(char *buf, int set)
+{
+	char *event = NULL, *sub = NULL, *match;
+
 	/*
 	 * The buf format can be <subsystem>:<event-name>
 	 *  *:<event-name> means any event by that name.
@@ -123,30 +246,24 @@ static int ftrace_set_clr_event(char *buf, int set)
 			event = NULL;
 	}
 
-	mutex_lock(&event_mutex);
-	list_for_each_entry(call, &ftrace_events, list) {
-
-		if (!call->name || !call->regfunc)
-			continue;
-
-		if (match &&
-		    strcmp(match, call->name) != 0 &&
-		    strcmp(match, call->system) != 0)
-			continue;
-
-		if (sub && strcmp(sub, call->system) != 0)
-			continue;
-
-		if (event && strcmp(event, call->name) != 0)
-			continue;
-
-		ftrace_event_enable_disable(call, set);
-
-		ret = 0;
-	}
-	mutex_unlock(&event_mutex);
+	return __ftrace_set_clr_event(match, sub, event, set);
+}
 
-	return ret;
+/**
+ * trace_set_clr_event - enable or disable an event
+ * @system: system name to match (NULL for any system)
+ * @event: event name to match (NULL for all events, within system)
+ * @set: 1 to enable, 0 to disable
+ *
+ * This is a way for other parts of the kernel to enable or disable
+ * event recording.
+ *
+ * Returns 0 on success, -EINVAL if the parameters do not match any
+ * registered events.
+ */
+int trace_set_clr_event(const char *system, const char *event, int set)
+{
+	return __ftrace_set_clr_event(NULL, system, event, set);
 }
 
 /* 128 should be much more than enough */
@@ -156,73 +273,38 @@ static ssize_t
 ftrace_event_write(struct file *file, const char __user *ubuf,
 		   size_t cnt, loff_t *ppos)
 {
-	size_t read = 0;
-	int i, set = 1;
-	ssize_t ret;
-	char *buf;
-	char ch;
+	struct trace_parser parser;
+	ssize_t read, ret;
 
-	if (!cnt || cnt < 0)
+	if (!cnt)
 		return 0;
 
 	ret = tracing_update_buffers();
 	if (ret < 0)
 		return ret;
 
-	ret = get_user(ch, ubuf++);
-	if (ret)
-		return ret;
-	read++;
-	cnt--;
-
-	/* skip white space */
-	while (cnt && isspace(ch)) {
-		ret = get_user(ch, ubuf++);
-		if (ret)
-			return ret;
-		read++;
-		cnt--;
-	}
-
-	/* Only white space found? */
-	if (isspace(ch)) {
-		file->f_pos += read;
-		ret = read;
-		return ret;
-	}
-
-	buf = kmalloc(EVENT_BUF_SIZE+1, GFP_KERNEL);
-	if (!buf)
+	if (trace_parser_get_init(&parser, EVENT_BUF_SIZE + 1))
 		return -ENOMEM;
 
-	if (cnt > EVENT_BUF_SIZE)
-		cnt = EVENT_BUF_SIZE;
+	read = trace_get_user(&parser, ubuf, cnt, ppos);
 
-	i = 0;
-	while (cnt && !isspace(ch)) {
-		if (!i && ch == '!')
+	if (read >= 0 && trace_parser_loaded((&parser))) {
+		int set = 1;
+
+		if (*parser.buffer == '!')
 			set = 0;
-		else
-			buf[i++] = ch;
 
-		ret = get_user(ch, ubuf++);
+		parser.buffer[parser.idx] = 0;
+
+		ret = ftrace_set_clr_event(parser.buffer + !set, set);
 		if (ret)
-			goto out_free;
-		read++;
-		cnt--;
+			goto out_put;
 	}
-	buf[i] = 0;
-
-	file->f_pos += read;
-
-	ret = ftrace_set_clr_event(buf, set);
-	if (ret)
-		goto out_free;
 
 	ret = read;
 
- out_free:
-	kfree(buf);
+ out_put:
+	trace_parser_put(&parser);
 
 	return ret;
 }
@@ -230,72 +312,75 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
 static void *
 t_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct list_head *list = m->private;
-	struct ftrace_event_call *call;
+	struct ftrace_event_call *call = v;
 
 	(*pos)++;
 
-	for (;;) {
-		if (list == &ftrace_events)
-			return NULL;
-
-		call = list_entry(list, struct ftrace_event_call, list);
-
+	list_for_each_entry_continue(call, &ftrace_events, list) {
 		/*
 		 * The ftrace subsystem is for showing formats only.
 		 * They can not be enabled or disabled via the event files.
 		 */
-		if (call->regfunc)
-			break;
-
-		list = list->next;
+		if (call->class && (call->class->probe || call->class->reg))
+			return call;
 	}
 
-	m->private = list->next;
-
-	return call;
+	return NULL;
 }
 
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
-	return t_next(m, NULL, pos);
+	struct ftrace_event_call *call;
+	loff_t l;
+
+	mutex_lock(&event_mutex);
+
+	call = list_entry(&ftrace_events, struct ftrace_event_call, list);
+	for (l = 0; l <= *pos; ) {
+		call = t_next(m, call, &l);
+		if (!call)
+			break;
+	}
+	return call;
 }
 
 static void *
 s_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct list_head *list = m->private;
-	struct ftrace_event_call *call;
+	struct ftrace_event_call *call = v;
 
 	(*pos)++;
 
- retry:
-	if (list == &ftrace_events)
-		return NULL;
-
-	call = list_entry(list, struct ftrace_event_call, list);
-
-	if (!call->enabled) {
-		list = list->next;
-		goto retry;
+	list_for_each_entry_continue(call, &ftrace_events, list) {
+		if (call->flags & TRACE_EVENT_FL_ENABLED)
+			return call;
 	}
 
-	m->private = list->next;
-
-	return call;
+	return NULL;
 }
 
 static void *s_start(struct seq_file *m, loff_t *pos)
 {
-	return s_next(m, NULL, pos);
+	struct ftrace_event_call *call;
+	loff_t l;
+
+	mutex_lock(&event_mutex);
+
+	call = list_entry(&ftrace_events, struct ftrace_event_call, list);
+	for (l = 0; l <= *pos; ) {
+		call = s_next(m, call, &l);
+		if (!call)
+			break;
+	}
+	return call;
 }
 
 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);
+	if (strcmp(call->class->system, TRACE_SYSTEM) != 0)
+		seq_printf(m, "%s:", call->class->system);
 	seq_printf(m, "%s\n", call->name);
 
 	return 0;
@@ -303,26 +388,20 @@ static int t_show(struct seq_file *m, void *v)
 
 static void t_stop(struct seq_file *m, void *p)
 {
+	mutex_unlock(&event_mutex);
 }
 
 static int
 ftrace_event_seq_open(struct inode *inode, struct file *file)
 {
-	int ret;
 	const struct seq_operations *seq_ops;
 
 	if ((file->f_mode & FMODE_WRITE) &&
-	    !(file->f_flags & O_APPEND))
+	    (file->f_flags & O_TRUNC))
 		ftrace_clear_events();
 
 	seq_ops = inode->i_private;
-	ret = seq_open(file, seq_ops);
-	if (!ret) {
-		struct seq_file *m = file->private_data;
-
-		m->private = ftrace_events.next;
-	}
-	return ret;
+	return seq_open(file, seq_ops);
 }
 
 static ssize_t
@@ -332,7 +411,7 @@ 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->flags & TRACE_EVENT_FL_ENABLED)
 		buf = "1\n";
 	else
 		buf = "0\n";
@@ -369,7 +448,7 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	case 0:
 	case 1:
 		mutex_lock(&event_mutex);
-		ftrace_event_enable_disable(call, val);
+		ret = ftrace_event_enable_disable(call, val);
 		mutex_unlock(&event_mutex);
 		break;
 
@@ -379,34 +458,90 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
 	*ppos += cnt;
 
-	return cnt;
+	return ret ? ret : cnt;
 }
 
-extern char *__bad_type_size(void);
+static ssize_t
+system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
+		   loff_t *ppos)
+{
+	const char set_to_char[4] = { '?', '0', '1', 'X' };
+	const char *system = filp->private_data;
+	struct ftrace_event_call *call;
+	char buf[2];
+	int set = 0;
+	int ret;
+
+	mutex_lock(&event_mutex);
+	list_for_each_entry(call, &ftrace_events, list) {
+		if (!call->name || !call->class ||
+		    (!call->class->probe && !call->class->reg))
+			continue;
+
+		if (system && strcmp(call->class->system, system) != 0)
+			continue;
+
+		/*
+		 * We need to find out if all the events are set
+		 * or if all events or cleared, or if we have
+		 * a mixture.
+		 */
+		set |= (1 << !!(call->flags & TRACE_EVENT_FL_ENABLED));
+
+		/*
+		 * If we have a mixture, no need to look further.
+		 */
+		if (set == 3)
+			break;
+	}
+	mutex_unlock(&event_mutex);
+
+	buf[0] = set_to_char[set];
+	buf[1] = '\n';
 
-#undef FIELD
-#define FIELD(type, name)						\
-	sizeof(type) != sizeof(field.name) ? __bad_type_size() :	\
-	#type, "common_" #name, offsetof(typeof(field), name),		\
-		sizeof(field.name)
+	ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, 2);
 
-static int trace_write_header(struct trace_seq *s)
+	return ret;
+}
+
+static ssize_t
+system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
+		    loff_t *ppos)
 {
-	struct trace_entry field;
-
-	/* struct trace_entry */
-	return trace_seq_printf(s,
-				"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-				"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-				"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-				"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-				"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-				"\n",
-				FIELD(unsigned short, type),
-				FIELD(unsigned char, flags),
-				FIELD(unsigned char, preempt_count),
-				FIELD(int, pid),
-				FIELD(int, tgid));
+	const char *system = filp->private_data;
+	unsigned long val;
+	char buf[64];
+	ssize_t ret;
+
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+
+	ret = strict_strtoul(buf, 10, &val);
+	if (ret < 0)
+		return ret;
+
+	ret = tracing_update_buffers();
+	if (ret < 0)
+		return ret;
+
+	if (val != 0 && val != 1)
+		return -EINVAL;
+
+	ret = __ftrace_set_clr_event(NULL, system, NULL, val);
+	if (ret)
+		goto out;
+
+	ret = cnt;
+
+out:
+	*ppos += cnt;
+
+	return ret;
 }
 
 static ssize_t
@@ -414,9 +549,12 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
 		  loff_t *ppos)
 {
 	struct ftrace_event_call *call = filp->private_data;
+	struct ftrace_event_field *field;
+	struct list_head *head;
 	struct trace_seq *s;
+	int common_field_count = 5;
 	char *buf;
-	int r;
+	int r = 0;
 
 	if (*ppos)
 		return 0;
@@ -427,14 +565,49 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
 
 	trace_seq_init(s);
 
-	/* If any of the first writes fail, so will the show_format. */
-
 	trace_seq_printf(s, "name: %s\n", call->name);
-	trace_seq_printf(s, "ID: %d\n", call->id);
+	trace_seq_printf(s, "ID: %d\n", call->event.type);
 	trace_seq_printf(s, "format:\n");
-	trace_write_header(s);
 
-	r = call->show_format(s);
+	head = trace_get_fields(call);
+	list_for_each_entry_reverse(field, head, link) {
+		/*
+		 * Smartly shows the array type(except dynamic array).
+		 * Normal:
+		 *	field:TYPE VAR
+		 * If TYPE := TYPE[LEN], it is shown:
+		 *	field:TYPE VAR[LEN]
+		 */
+		const char *array_descriptor = strchr(field->type, '[');
+
+		if (!strncmp(field->type, "__data_loc", 10))
+			array_descriptor = NULL;
+
+		if (!array_descriptor) {
+			r = trace_seq_printf(s, "\tfield:%s %s;\toffset:%u;"
+					"\tsize:%u;\tsigned:%d;\n",
+					field->type, field->name, field->offset,
+					field->size, !!field->is_signed);
+		} else {
+			r = trace_seq_printf(s, "\tfield:%.*s %s%s;\toffset:%u;"
+					"\tsize:%u;\tsigned:%d;\n",
+					(int)(array_descriptor - field->type),
+					field->type, field->name,
+					array_descriptor, field->offset,
+					field->size, !!field->is_signed);
+		}
+
+		if (--common_field_count == 0)
+			r = trace_seq_printf(s, "\n");
+
+		if (!r)
+			break;
+	}
+
+	if (r)
+		r = trace_seq_printf(s, "\nprint fmt: %s\n",
+				call->print_fmt);
+
 	if (!r) {
 		/*
 		 * ug!  The format output is bigger than a PAGE!!
@@ -467,7 +640,7 @@ event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
 		return -ENOMEM;
 
 	trace_seq_init(s);
-	trace_seq_printf(s, "%d\n", call->id);
+	trace_seq_printf(s, "%d\n", call->event.type);
 
 	r = simple_read_from_buffer(ubuf, cnt, ppos,
 				    s->buffer, s->len);
@@ -492,7 +665,7 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
 
 	trace_seq_init(s);
 
-	filter_print_preds(call, s);
+	print_event_filter(call, s);
 	r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
 
 	kfree(s);
@@ -505,40 +678,26 @@ event_filter_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], *pbuf = buf;
-	struct filter_pred *pred;
+	char *buf;
 	int err;
 
-	if (cnt >= sizeof(buf))
+	if (cnt >= PAGE_SIZE)
 		return -EINVAL;
 
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-	buf[cnt] = '\0';
-
-	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
-	if (!pred)
+	buf = (char *)__get_free_page(GFP_TEMPORARY);
+	if (!buf)
 		return -ENOMEM;
 
-	err = filter_parse(&pbuf, pred);
-	if (err < 0) {
-		filter_free_pred(pred);
-		return err;
-	}
-
-	if (pred->clear) {
-		filter_disable_preds(call);
-		filter_free_pred(pred);
-		return cnt;
+	if (copy_from_user(buf, ubuf, cnt)) {
+		free_page((unsigned long) buf);
+		return -EFAULT;
 	}
+	buf[cnt] = '\0';
 
-	err = filter_add_pred(call, pred);
-	if (err < 0) {
-		filter_free_pred(pred);
+	err = apply_event_filter(call, buf);
+	free_page((unsigned long) buf);
+	if (err < 0)
 		return err;
-	}
-
-	filter_free_pred(pred);
 
 	*ppos += cnt;
 
@@ -562,7 +721,7 @@ subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
 
 	trace_seq_init(s);
 
-	filter_print_subsystem_preds(system, s);
+	print_subsystem_event_filter(system, s);
 	r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
 
 	kfree(s);
@@ -575,38 +734,26 @@ subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		       loff_t *ppos)
 {
 	struct event_subsystem *system = filp->private_data;
-	char buf[64], *pbuf = buf;
-	struct filter_pred *pred;
+	char *buf;
 	int err;
 
-	if (cnt >= sizeof(buf))
+	if (cnt >= PAGE_SIZE)
 		return -EINVAL;
 
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-	buf[cnt] = '\0';
-
-	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
-	if (!pred)
+	buf = (char *)__get_free_page(GFP_TEMPORARY);
+	if (!buf)
 		return -ENOMEM;
 
-	err = filter_parse(&pbuf, pred);
-	if (err < 0) {
-		filter_free_pred(pred);
-		return err;
-	}
-
-	if (pred->clear) {
-		filter_free_subsystem_preds(system);
-		filter_free_pred(pred);
-		return cnt;
+	if (copy_from_user(buf, ubuf, cnt)) {
+		free_page((unsigned long) buf);
+		return -EFAULT;
 	}
+	buf[cnt] = '\0';
 
-	err = filter_add_subsystem_pred(system, pred);
-	if (err < 0) {
-		filter_free_pred(pred);
+	err = apply_subsystem_event_filter(system, buf);
+	free_page((unsigned long) buf);
+	if (err < 0)
 		return err;
-	}
 
 	*ppos += cnt;
 
@@ -694,6 +841,12 @@ static const struct file_operations ftrace_subsystem_filter_fops = {
 	.write = subsystem_filter_write,
 };
 
+static const struct file_operations ftrace_system_enable_fops = {
+	.open = tracing_open_generic,
+	.read = system_enable_read,
+	.write = system_enable_write,
+};
+
 static const struct file_operations ftrace_show_header_fops = {
 	.open = tracing_open_generic,
 	.read = show_header,
@@ -729,8 +882,10 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 
 	/* First see if we did not already create this dir */
 	list_for_each_entry(system, &event_subsystems, list) {
-		if (strcmp(system->name, name) == 0)
+		if (strcmp(system->name, name) == 0) {
+			system->nr_events++;
 			return system->entry;
+		}
 	}
 
 	/* need to create new entry */
@@ -749,6 +904,7 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 		return d_events;
 	}
 
+	system->nr_events = 1;
 	system->name = kstrdup(name, GFP_KERNEL);
 	if (!system->name) {
 		debugfs_remove(system->entry);
@@ -760,11 +916,25 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 
 	system->filter = NULL;
 
+	system->filter = kzalloc(sizeof(struct event_filter), GFP_KERNEL);
+	if (!system->filter) {
+		pr_warning("Could not allocate filter for subsystem "
+			   "'%s'\n", name);
+		return system->entry;
+	}
+
 	entry = debugfs_create_file("filter", 0644, system->entry, system,
 				    &ftrace_subsystem_filter_fops);
-	if (!entry)
+	if (!entry) {
+		kfree(system->filter);
+		system->filter = NULL;
 		pr_warning("Could not create debugfs "
 			   "'%s/filter' entry\n", name);
+	}
+
+	trace_create_file("enable", 0644, system->entry,
+			  (void *)system->name,
+			  &ftrace_system_enable_fops);
 
 	return system->entry;
 }
@@ -776,24 +946,15 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 		 const struct file_operations *filter,
 		 const struct file_operations *format)
 {
-	struct dentry *entry;
+	struct list_head *head;
 	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;
-		}
-	}
+	if (strcmp(call->class->system, TRACE_SYSTEM) != 0)
+		d_events = event_subsystem_dir(call->class->system, d_events);
 
 	call->dir = debugfs_create_dir(call->name, d_events);
 	if (!call->dir) {
@@ -802,33 +963,132 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 		return -1;
 	}
 
-	if (call->regfunc)
-		entry = trace_create_file("enable", 0644, call->dir, call,
-					  enable);
+	if (call->class->probe || call->class->reg)
+		trace_create_file("enable", 0644, call->dir, call,
+				  enable);
+
+#ifdef CONFIG_PERF_EVENTS
+	if (call->event.type && (call->class->perf_probe || call->class->reg))
+		trace_create_file("id", 0444, call->dir, call,
+		 		  id);
+#endif
+
+	if (call->class->define_fields) {
+		/*
+		 * Other events may have the same class. Only update
+		 * the fields if they are not already defined.
+		 */
+		head = trace_get_fields(call);
+		if (list_empty(head)) {
+			ret = trace_define_common_fields(call);
+			if (!ret)
+				ret = call->class->define_fields(call);
+			if (ret < 0) {
+				pr_warning("Could not initialize trace point"
+					   " events/%s\n", call->name);
+				return ret;
+			}
+		}
+		trace_create_file("filter", 0644, call->dir, call,
+				  filter);
+	}
 
-	if (call->id)
-		entry = trace_create_file("id", 0444, call->dir, call,
-					  id);
+	trace_create_file("format", 0444, call->dir, call,
+			  format);
 
-	if (call->define_fields) {
-		ret = call->define_fields();
+	return 0;
+}
+
+static int __trace_add_event_call(struct ftrace_event_call *call)
+{
+	struct dentry *d_events;
+	int ret;
+
+	if (!call->name)
+		return -EINVAL;
+
+	if (call->class->raw_init) {
+		ret = call->class->raw_init(call);
 		if (ret < 0) {
-			pr_warning("Could not initialize trace point"
-				   " events/%s\n", call->name);
+			if (ret != -ENOSYS)
+				pr_warning("Could not initialize trace "
+				"events/%s\n", call->name);
 			return ret;
 		}
-		entry = trace_create_file("filter", 0644, call->dir, call,
-					  filter);
 	}
 
-	/* A trace may not want to export its format */
-	if (!call->show_format)
-		return 0;
+	d_events = event_trace_events_dir();
+	if (!d_events)
+		return -ENOENT;
 
-	entry = trace_create_file("format", 0444, call->dir, call,
-				  format);
+	ret = event_create_dir(call, d_events, &ftrace_event_id_fops,
+				&ftrace_enable_fops, &ftrace_event_filter_fops,
+				&ftrace_event_format_fops);
+	if (!ret)
+		list_add(&call->list, &ftrace_events);
 
-	return 0;
+	return ret;
+}
+
+/* Add an additional event_call dynamically */
+int trace_add_event_call(struct ftrace_event_call *call)
+{
+	int ret;
+	mutex_lock(&event_mutex);
+	ret = __trace_add_event_call(call);
+	mutex_unlock(&event_mutex);
+	return ret;
+}
+
+static void remove_subsystem_dir(const char *name)
+{
+	struct event_subsystem *system;
+
+	if (strcmp(name, TRACE_SYSTEM) == 0)
+		return;
+
+	list_for_each_entry(system, &event_subsystems, list) {
+		if (strcmp(system->name, name) == 0) {
+			if (!--system->nr_events) {
+				struct event_filter *filter = system->filter;
+
+				debugfs_remove_recursive(system->entry);
+				list_del(&system->list);
+				if (filter) {
+					kfree(filter->filter_string);
+					kfree(filter);
+				}
+				kfree(system->name);
+				kfree(system);
+			}
+			break;
+		}
+	}
+}
+
+/*
+ * Must be called under locking both of event_mutex and trace_event_mutex.
+ */
+static void __trace_remove_event_call(struct ftrace_event_call *call)
+{
+	ftrace_event_enable_disable(call, 0);
+	if (call->event.funcs)
+		__unregister_ftrace_event(&call->event);
+	debugfs_remove_recursive(call->dir);
+	list_del(&call->list);
+	trace_destroy_fields(call);
+	destroy_preds(call);
+	remove_subsystem_dir(call->class->system);
+}
+
+/* Remove an event_call */
+void trace_remove_event_call(struct ftrace_event_call *call)
+{
+	mutex_lock(&event_mutex);
+	down_write(&trace_event_mutex);
+	__trace_remove_event_call(call);
+	up_write(&trace_event_mutex);
+	mutex_unlock(&event_mutex);
 }
 
 #define for_each_event(event, start, end)			\
@@ -893,6 +1153,7 @@ static void trace_module_add_events(struct module *mod)
 	struct ftrace_module_file_ops *file_ops = NULL;
 	struct ftrace_event_call *call, *start, *end;
 	struct dentry *d_events;
+	int ret;
 
 	start = mod->trace_events;
 	end = mod->trace_events + mod->num_trace_events;
@@ -908,7 +1169,15 @@ static void trace_module_add_events(struct module *mod)
 		/* The linker may leave blanks */
 		if (!call->name)
 			continue;
-
+		if (call->class->raw_init) {
+			ret = call->class->raw_init(call);
+			if (ret < 0) {
+				if (ret != -ENOSYS)
+					pr_warning("Could not initialize trace "
+					"point events/%s\n", call->name);
+				continue;
+			}
+		}
 		/*
 		 * This module has events, create file ops for this module
 		 * if not already done.
@@ -919,10 +1188,11 @@ static void trace_module_add_events(struct module *mod)
 				return;
 		}
 		call->mod = mod;
-		list_add(&call->list, &ftrace_events);
-		event_create_dir(call, d_events,
-				 &file_ops->id, &file_ops->enable,
-				 &file_ops->filter, &file_ops->format);
+		ret = event_create_dir(call, d_events,
+				       &file_ops->id, &file_ops->enable,
+				       &file_ops->filter, &file_ops->format);
+		if (!ret)
+			list_add(&call->list, &ftrace_events);
 	}
 }
 
@@ -930,17 +1200,13 @@ static void trace_module_remove_events(struct module *mod)
 {
 	struct ftrace_module_file_ops *file_ops;
 	struct ftrace_event_call *call, *p;
+	bool found = false;
 
+	down_write(&trace_event_mutex);
 	list_for_each_entry_safe(call, p, &ftrace_events, list) {
 		if (call->mod == mod) {
-			if (call->enabled) {
-				call->enabled = 0;
-				call->unregfunc();
-			}
-			if (call->event)
-				unregister_ftrace_event(call->event);
-			debugfs_remove_recursive(call->dir);
-			list_del(&call->list);
+			found = true;
+			__trace_remove_event_call(call);
 		}
 	}
 
@@ -953,6 +1219,14 @@ static void trace_module_remove_events(struct module *mod)
 		list_del(&file_ops->list);
 		kfree(file_ops);
 	}
+
+	/*
+	 * It is safest to reset the ring buffer if the module being unloaded
+	 * registered any events.
+	 */
+	if (found)
+		tracing_reset_current_online_cpus();
+	up_write(&trace_event_mutex);
 }
 
 static int trace_module_notify(struct notifier_block *self,
@@ -981,7 +1255,7 @@ static int trace_module_notify(struct notifier_block *self,
 }
 #endif /* CONFIG_MODULES */
 
-struct notifier_block trace_module_nb = {
+static struct notifier_block trace_module_nb = {
 	.notifier_call = trace_module_notify,
 	.priority = 0,
 };
@@ -989,6 +1263,18 @@ struct notifier_block trace_module_nb = {
 extern struct ftrace_event_call __start_ftrace_events[];
 extern struct ftrace_event_call __stop_ftrace_events[];
 
+static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata;
+
+static __init int setup_trace_event(char *str)
+{
+	strlcpy(bootup_event_buf, str, COMMAND_LINE_SIZE);
+	ring_buffer_expanded = 1;
+	tracing_selftest_disabled = 1;
+
+	return 1;
+}
+__setup("trace_event=", setup_trace_event);
+
 static __init int event_trace_init(void)
 {
 	struct ftrace_event_call *call;
@@ -996,6 +1282,8 @@ static __init int event_trace_init(void)
 	struct dentry *entry;
 	struct dentry *d_events;
 	int ret;
+	char *buf = bootup_event_buf;
+	char *token;
 
 	d_tracer = tracing_init_dentry();
 	if (!d_tracer)
@@ -1028,18 +1316,45 @@ static __init int event_trace_init(void)
 			  ring_buffer_print_entry_header,
 			  &ftrace_show_header_fops);
 
+	trace_create_file("enable", 0644, d_events,
+			  NULL, &ftrace_system_enable_fops);
+
 	for_each_event(call, __start_ftrace_events, __stop_ftrace_events) {
 		/* The linker may leave blanks */
 		if (!call->name)
 			continue;
-		list_add(&call->list, &ftrace_events);
-		event_create_dir(call, d_events, &ftrace_event_id_fops,
-				 &ftrace_enable_fops, &ftrace_event_filter_fops,
-				 &ftrace_event_format_fops);
+		if (call->class->raw_init) {
+			ret = call->class->raw_init(call);
+			if (ret < 0) {
+				if (ret != -ENOSYS)
+					pr_warning("Could not initialize trace "
+					"point events/%s\n", call->name);
+				continue;
+			}
+		}
+		ret = event_create_dir(call, d_events, &ftrace_event_id_fops,
+				       &ftrace_enable_fops,
+				       &ftrace_event_filter_fops,
+				       &ftrace_event_format_fops);
+		if (!ret)
+			list_add(&call->list, &ftrace_events);
+	}
+
+	while (true) {
+		token = strsep(&buf, ",");
+
+		if (!token)
+			break;
+		if (!*token)
+			continue;
+
+		ret = ftrace_set_clr_event(token, 1);
+		if (ret)
+			pr_warning("Failed to enable trace event: %s\n", token);
 	}
 
 	ret = register_module_notifier(&trace_module_nb);
-	if (!ret)
+	if (ret)
 		pr_warning("Failed to register trace events module notifier\n");
 
 	return 0;
@@ -1104,36 +1419,43 @@ static __init void event_trace_self_tests(void)
 {
 	struct ftrace_event_call *call;
 	struct event_subsystem *system;
-	char *sysname;
 	int ret;
 
 	pr_info("Running tests on trace events:\n");
 
 	list_for_each_entry(call, &ftrace_events, list) {
 
-		/* Only test those that have a regfunc */
-		if (!call->regfunc)
+		/* Only test those that have a probe */
+		if (!call->class || !call->class->probe)
 			continue;
 
+/*
+ * Testing syscall events here is pretty useless, but
+ * we still do it if configured. But this is time consuming.
+ * What we really need is a user thread to perform the
+ * syscalls as we test.
+ */
+#ifndef CONFIG_EVENT_TRACE_TEST_SYSCALLS
+		if (call->class->system &&
+		    strcmp(call->class->system, "syscalls") == 0)
+			continue;
+#endif
+
 		pr_info("Testing event %s: ", call->name);
 
 		/*
 		 * If an event is already enabled, someone is using
 		 * it and the self test should not be on.
 		 */
-		if (call->enabled) {
+		if (call->flags & TRACE_EVENT_FL_ENABLED) {
 			pr_warning("Enabled event during self test!\n");
 			WARN_ON_ONCE(1);
 			continue;
 		}
 
-		call->enabled = 1;
-		call->regfunc();
-
+		ftrace_event_enable_disable(call, 1);
 		event_test_stuff();
-
-		call->unregfunc();
-		call->enabled = 0;
+		ftrace_event_enable_disable(call, 0);
 
 		pr_cont("OK\n");
 	}
@@ -1150,14 +1472,7 @@ static __init void event_trace_self_tests(void)
 
 		pr_info("Testing event system %s: ", system->name);
 
-		/* ftrace_set_clr_event can modify the name passed in. */
-		sysname = kstrdup(system->name, GFP_KERNEL);
-		if (WARN_ON(!sysname)) {
-			pr_warning("Can't allocate memory, giving up!\n");
-			return;
-		}
-		ret = ftrace_set_clr_event(sysname, 1);
-		kfree(sysname);
+		ret = __ftrace_set_clr_event(NULL, system->name, NULL, 1);
 		if (WARN_ON_ONCE(ret)) {
 			pr_warning("error enabling system %s\n",
 				   system->name);
@@ -1166,14 +1481,7 @@ static __init void event_trace_self_tests(void)
 
 		event_test_stuff();
 
-		sysname = kstrdup(system->name, GFP_KERNEL);
-		if (WARN_ON(!sysname)) {
-			pr_warning("Can't allocate memory, giving up!\n");
-			return;
-		}
-		ret = ftrace_set_clr_event(sysname, 0);
-		kfree(sysname);
-
+		ret = __ftrace_set_clr_event(NULL, system->name, NULL, 0);
 		if (WARN_ON_ONCE(ret))
 			pr_warning("error disabling system %s\n",
 				   system->name);
@@ -1186,15 +1494,8 @@ static __init void event_trace_self_tests(void)
 	pr_info("Running tests on all trace events:\n");
 	pr_info("Testing all events: ");
 
-	sysname = kmalloc(4, GFP_KERNEL);
-	if (WARN_ON(!sysname)) {
-		pr_warning("Can't allocate memory, giving up!\n");
-		return;
-	}
-	memcpy(sysname, "*:*", 4);
-	ret = ftrace_set_clr_event(sysname, 1);
+	ret = __ftrace_set_clr_event(NULL, NULL, NULL, 1);
 	if (WARN_ON_ONCE(ret)) {
-		kfree(sysname);
 		pr_warning("error enabling all events\n");
 		return;
 	}
@@ -1202,10 +1503,7 @@ static __init void event_trace_self_tests(void)
 	event_test_stuff();
 
 	/* reset sysname */
-	memcpy(sysname, "*:*", 4);
-	ret = ftrace_set_clr_event(sysname, 0);
-	kfree(sysname);
-
+	ret = __ftrace_set_clr_event(NULL, NULL, NULL, 0);
 	if (WARN_ON_ONCE(ret)) {
 		pr_warning("error disabling all events\n");
 		return;
@@ -1216,12 +1514,13 @@ static __init void event_trace_self_tests(void)
 
 #ifdef CONFIG_FUNCTION_TRACER
 
-static DEFINE_PER_CPU(atomic_t, test_event_disable);
+static DEFINE_PER_CPU(atomic_t, ftrace_test_event_disable);
 
 static void
 function_test_events_call(unsigned long ip, unsigned long parent_ip)
 {
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	struct ftrace_entry *entry;
 	unsigned long flags;
 	long disabled;
@@ -1232,14 +1531,15 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip)
 	pc = preempt_count();
 	resched = ftrace_preempt_disable();
 	cpu = raw_smp_processor_id();
-	disabled = atomic_inc_return(&per_cpu(test_event_disable, cpu));
+	disabled = atomic_inc_return(&per_cpu(ftrace_test_event_disable, cpu));
 
 	if (disabled != 1)
 		goto out;
 
 	local_save_flags(flags);
 
-	event = trace_current_buffer_lock_reserve(TRACE_FN, sizeof(*entry),
+	event = trace_current_buffer_lock_reserve(&buffer,
+						  TRACE_FN, sizeof(*entry),
 						  flags, pc);
 	if (!event)
 		goto out;
@@ -1247,10 +1547,10 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip)
 	entry->ip			= ip;
 	entry->parent_ip		= parent_ip;
 
-	trace_nowake_buffer_unlock_commit(event, flags, pc);
+	trace_nowake_buffer_unlock_commit(buffer, event, flags, pc);
 
  out:
-	atomic_dec(&per_cpu(test_event_disable, cpu));
+	atomic_dec(&per_cpu(ftrace_test_event_disable, cpu));
 	ftrace_preempt_enable(resched);
 }
 
@@ -1274,10 +1574,10 @@ static __init void event_trace_self_test_with_function(void)
 
 static __init int event_trace_self_tests_init(void)
 {
-
-	event_trace_self_tests();
-
-	event_trace_self_test_with_function();
+	if (!tracing_selftest_disabled) {
+		event_trace_self_tests();
+		event_trace_self_test_with_function();
+	}
 
 	return 0;
 }