tracing: add trace_event_read_lock()

I found that there is nothing to protect event_hash in
ftrace_find_event(). Rcu protects the event hashlist
but not the event itself while we use it after its extraction
through ftrace_find_event().

This lack of a proper locking in this spot opens a race
window between any event dereferencing and module removal.

Eg:

--Task A--

print_trace_line(trace) {
  event = find_ftrace_event(trace)

--Task B--

trace_module_remove_events(mod) {
  list_trace_events_module(ev, mod) {
    unregister_ftrace_event(ev->event) {
      hlist_del(ev->event->node)
        list_del(....)
    }
  }
}
|--> module removed, the event has been dropped

--Task A--

  event->print(trace); // Dereferencing freed memory

If the event retrieved belongs to a module and this module
is concurrently removed, we may end up dereferencing a data
from a freed module.

RCU could solve this, but it would add latency to the kernel and
forbid tracers output callbacks to call any sleepable code.
So this fix converts 'trace_event_mutex' to a read/write semaphore,
and adds trace_event_read_lock() to protect ftrace_find_event().

[ Impact: fix possible freed memory dereference in ftrace ]

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <4A114806.7090302@cn.fujitsu.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>

1 files changed, 8 insertions, 0 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index dd40d2320346..02d32baa23ac 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1569,12 +1569,14 @@ static void *s_start(struct seq_file *m, loff_t *pos)
                 p = s_next(m, p, &l);
         }
 
+        trace_event_read_lock();
         return p;
 }
 
 static void s_stop(struct seq_file *m, void *p)
 {
         atomic_dec(&trace_record_cmdline_disabled);
+        trace_event_read_unlock();
 }
 
 static void print_lat_help_header(struct seq_file *m)
@@ -1817,6 +1819,7 @@ static int trace_empty(struct trace_iterator *iter)
         return 1;
 }
 
+/*  Called with trace_event_read_lock() held. */
 static enum print_line_t print_trace_line(struct trace_iterator *iter)
 {
         enum print_line_t ret;
@@ -3008,6 +3011,7 @@ waitagain:
                offsetof(struct trace_iterator, seq));
         iter->pos = -1;
 
+        trace_event_read_lock();
         while (find_next_entry_inc(iter) != NULL) {
                 enum print_line_t ret;
                 int len = iter->seq.len;
@@ -3024,6 +3028,7 @@ waitagain:
                 if (iter->seq.len >= cnt)
                         break;
         }
+        trace_event_read_unlock();
 
         /* Now copy what we have to the user */
         sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
@@ -3146,6 +3151,8 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
                 goto out_err;
         }
 
+        trace_event_read_lock();
+
         /* Fill as many pages as possible. */
         for (i = 0, rem = len; i < PIPE_BUFFERS && rem; i++) {
                 pages[i] = alloc_page(GFP_KERNEL);
@@ -3168,6 +3175,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
                 trace_seq_init(&iter->seq);
         }
 
+        trace_event_read_unlock();
         mutex_unlock(&iter->mutex);
 
         spd.nr_pages = i;