tracing/events: fix concurrent access to ftrace_events list

A module will add/remove its trace events when it gets loaded/unloaded, so
the ftrace_events list is not "const", and concurrent access needs to be
protected.

This patch thus fixes races between loading/unloding modules and read
'available_events' or read/write 'set_event', etc.

Below shows how to reproduce the race:

 # for ((; ;)) { cat /mnt/tracing/available_events; } > /dev/null &
 # for ((; ;)) { insmod trace-events-sample.ko; rmmod sample; } &

After a while:

BUG: unable to handle kernel paging request at 0010011c
IP: [<c1080f27>] t_next+0x1b/0x2d
...
Call Trace:
 [<c10c90e6>] ? seq_read+0x217/0x30d
 [<c10c8ecf>] ? seq_read+0x0/0x30d
 [<c10b4c19>] ? vfs_read+0x8f/0x136
 [<c10b4fc3>] ? sys_read+0x40/0x65
 [<c1002a68>] ? sysenter_do_call+0x12/0x36

[ Impact: fix races when concurrent accessing ftrace_events list ]

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4A00F709.3080800@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 7 insertions, 3 deletions

diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index ce07b818671..7ac69108527 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -408,6 +408,7 @@ static void filter_free_subsystem_preds(struct event_subsystem *system)
                 filter->n_preds = 0;
         }
 
+        mutex_lock(&event_mutex);
         list_for_each_entry(call, &ftrace_events, list) {
                 if (!call->define_fields)
                         continue;
@@ -417,6 +418,7 @@ static void filter_free_subsystem_preds(struct event_subsystem *system)
                         remove_filter_string(call->filter);
                 }
         }
+        mutex_unlock(&event_mutex);
 }
 
 static int filter_add_pred_fn(struct filter_parse_state *ps,
@@ -567,6 +569,7 @@ static int filter_add_subsystem_pred(struct filter_parse_state *ps,
 {
         struct event_filter *filter = system->filter;
         struct ftrace_event_call *call;
+        int err = 0;
 
         if (!filter->preds) {
                 filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
@@ -584,8 +587,8 @@ static int filter_add_subsystem_pred(struct filter_parse_state *ps,
         filter->preds[filter->n_preds] = pred;
         filter->n_preds++;
 
+        mutex_lock(&event_mutex);
         list_for_each_entry(call, &ftrace_events, list) {
-                int err;
 
                 if (!call->define_fields)
                         continue;
@@ -597,12 +600,13 @@ static int filter_add_subsystem_pred(struct filter_parse_state *ps,
                 if (err) {
                         filter_free_subsystem_preds(system);
                         parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
-                        return err;
+                        break;
                 }
                 replace_filter_string(call->filter, filter_string);
         }
+        mutex_unlock(&event_mutex);
 
-        return 0;
+        return err;
 }
 
 static void parse_init(struct filter_parse_state *ps,