Commit 4f535968 authored by Lai Jiangshan's avatar Lai Jiangshan Committed by Frederic Weisbecker
Browse files

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: default avatarLai Jiangshan <laijs@cn.fujitsu.com>
Acked-by: default avatarSteven Rostedt <rostedt@goodmis.org>
LKML-Reference: <4A114806.7090302@cn.fujitsu.com>
Signed-off-by: default avatarFrederic Weisbecker <fweisbec@gmail.com>
parent 55379376
......@@ -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 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
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 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
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;
......
......@@ -14,7 +14,7 @@
/* must be a power of 2 */
#define EVENT_HASHSIZE 128
static DEFINE_MUTEX(trace_event_mutex);
static DECLARE_RWSEM(trace_event_mutex);
static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
static int next_event_type = __TRACE_LAST_TYPE + 1;
......@@ -466,6 +466,7 @@ static int task_state_char(unsigned long state)
* @type: the type of event to look for
*
* Returns an event of type @type otherwise NULL
* Called with trace_event_read_lock() held.
*/
struct trace_event *ftrace_find_event(int type)
{
......@@ -475,7 +476,7 @@ struct trace_event *ftrace_find_event(int type)
key = type & (EVENT_HASHSIZE - 1);
hlist_for_each_entry_rcu(event, n, &event_hash[key], node) {
hlist_for_each_entry(event, n, &event_hash[key], node) {
if (event->type == type)
return event;
}
......@@ -513,6 +514,16 @@ static int trace_search_list(struct list_head **list)
return last + 1;
}
void trace_event_read_lock(void)
{
down_read(&trace_event_mutex);
}
void trace_event_read_unlock(void)
{
up_read(&trace_event_mutex);
}
/**
* register_ftrace_event - register output for an event type
* @event: the event type to register
......@@ -533,7 +544,7 @@ int register_ftrace_event(struct trace_event *event)
unsigned key;
int ret = 0;
mutex_lock(&trace_event_mutex);
down_write(&trace_event_mutex);
if (WARN_ON(!event))
goto out;
......@@ -581,11 +592,11 @@ int register_ftrace_event(struct trace_event *event)
key = event->type & (EVENT_HASHSIZE - 1);
hlist_add_head_rcu(&event->node, &event_hash[key]);
hlist_add_head(&event->node, &event_hash[key]);
ret = event->type;
out:
mutex_unlock(&trace_event_mutex);
up_write(&trace_event_mutex);
return ret;
}
......@@ -597,10 +608,10 @@ EXPORT_SYMBOL_GPL(register_ftrace_event);
*/
int unregister_ftrace_event(struct trace_event *event)
{
mutex_lock(&trace_event_mutex);
down_write(&trace_event_mutex);
hlist_del(&event->node);
list_del(&event->list);
mutex_unlock(&trace_event_mutex);
up_write(&trace_event_mutex);
return 0;
}
......
......@@ -20,6 +20,8 @@ extern int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
extern int trace_print_context(struct trace_iterator *iter);
extern int trace_print_lat_context(struct trace_iterator *iter);
extern void trace_event_read_lock(void);
extern void trace_event_read_unlock(void);
extern struct trace_event *ftrace_find_event(int type);
extern enum print_line_t trace_nop_print(struct trace_iterator *iter,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment