tracing: Change event_filter_read/write to verify i_private != NULL
event_filter_read/write() are racy, ftrace_event_call can be already
freed by trace_remove_event_call() callers.
1. Shift mutex_lock(event_mutex) from print/apply_event_filter to
the callers.
2. Change the callers, event_filter_read() and event_filter_write()
to read i_private under this mutex and abort if it is NULL.
This fixes nothing, but now we can change debugfs_remove("filter")
callers to nullify ->i_private and fix the the problem.
Link: http://lkml.kernel.org/r/20130726172540.GA3619@redhat.com
Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 3dfa841..1d7b6d0 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -980,21 +980,28 @@
event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
loff_t *ppos)
{
- struct ftrace_event_call *call = filp->private_data;
+ struct ftrace_event_call *call;
struct trace_seq *s;
- int r;
+ int r = -ENODEV;
if (*ppos)
return 0;
s = kmalloc(sizeof(*s), GFP_KERNEL);
+
if (!s)
return -ENOMEM;
trace_seq_init(s);
- print_event_filter(call, s);
- r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+ mutex_lock(&event_mutex);
+ call = event_file_data(filp);
+ if (call)
+ print_event_filter(call, s);
+ mutex_unlock(&event_mutex);
+
+ if (call)
+ r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
kfree(s);
@@ -1005,9 +1012,9 @@
event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
loff_t *ppos)
{
- struct ftrace_event_call *call = filp->private_data;
+ struct ftrace_event_call *call;
char *buf;
- int err;
+ int err = -ENODEV;
if (cnt >= PAGE_SIZE)
return -EINVAL;
@@ -1022,7 +1029,12 @@
}
buf[cnt] = '\0';
- err = apply_event_filter(call, buf);
+ mutex_lock(&event_mutex);
+ call = event_file_data(filp);
+ if (call)
+ err = apply_event_filter(call, buf);
+ mutex_unlock(&event_mutex);
+
free_page((unsigned long) buf);
if (err < 0)
return err;
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 0c7b75a..97daa8c 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -637,17 +637,15 @@
free_page((unsigned long) buf);
}
+/* caller must hold event_mutex */
void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
{
- struct event_filter *filter;
+ struct event_filter *filter = call->filter;
- mutex_lock(&event_mutex);
- filter = call->filter;
if (filter && filter->filter_string)
trace_seq_printf(s, "%s\n", filter->filter_string);
else
trace_seq_puts(s, "none\n");
- mutex_unlock(&event_mutex);
}
void print_subsystem_event_filter(struct event_subsystem *system,
@@ -1841,23 +1839,22 @@
return err;
}
+/* caller must hold event_mutex */
int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
{
struct event_filter *filter;
- int err = 0;
-
- mutex_lock(&event_mutex);
+ int err;
if (!strcmp(strstrip(filter_string), "0")) {
filter_disable(call);
filter = call->filter;
if (!filter)
- goto out_unlock;
+ return 0;
RCU_INIT_POINTER(call->filter, NULL);
/* Make sure the filter is not being used */
synchronize_sched();
__free_filter(filter);
- goto out_unlock;
+ return 0;
}
err = create_filter(call, filter_string, true, &filter);
@@ -1884,8 +1881,6 @@
__free_filter(tmp);
}
}
-out_unlock:
- mutex_unlock(&event_mutex);
return err;
}
