tracing: append ":*" to internal setting of system events

The system enabling of events uses the same code as the set_event file.
It passes in the name of the system to the parser and that will enable
all the events that has that system as a name.

The problem is that it will also enable events with the same name as the
system.

If you have system name foo, and system name bar, but within the system
bar, there exists an event called foo. By setting the system name foo,
you will also be enabling the event foo in the system bar. This is not
an expected result.

The solution is to pass in "foo:*", which will only enable the system
foo and not events called foo.

[ Impact: prevent accidental enabling of events with same name as a system ]

Reported-by: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 87feb0117ce28a5c1a51b75e6857e21281e0ed7e..8d0fae3af5954599cde32153e93c9ce0e7e5e031 100644 (file)
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -509,9 +509,11 @@ system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
                return -EINVAL;
        }
 
-       command = kstrdup(system, GFP_KERNEL);
+       /* +3 for the ":*\0" */
+       command = kmalloc(strlen(system)+3, GFP_KERNEL);
        if (!command)
                return -ENOMEM;
+       sprintf(command, "%s:*", system);
 
        ret = ftrace_set_clr_event(command, val);
        if (ret)
@@ -1179,7 +1181,7 @@ static __init int event_trace_init(void)
                          &ftrace_show_header_fops);
 
        trace_create_file("enable", 0644, d_events,
-                         "*:*", &ftrace_system_enable_fops);
+                         "*", &ftrace_system_enable_fops);
 
        for_each_event(call, __start_ftrace_events, __stop_ftrace_events) {
                /* The linker may leave blanks */