tracing: Add trace_array_get/put() to event handling

Commit a695cb58162 "tracing: Prevent deleting instances when they are being read"
tried to fix a race between deleting a trace instance and reading contents
of a trace file. But it wasn't good enough. The following could crash the kernel:

 # cd /sys/kernel/debug/tracing/instances
 # ( while :; do mkdir foo; rmdir foo; done ) &
 # ( while :; do echo 1 > foo/events/sched/sched_switch 2> /dev/null; done ) &

Luckily this can only be done by root user, but it should be fixed regardless.

The problem is that a delete of the file can happen after the write to the event
is opened, but before the enabling happens.

The solution is to make sure the trace_array is available before succeeding in
opening for write, and incerment the ref counter while opened.

Now the instance can be deleted when the events are writing to the buffer,
but the deletion of the instance will disable all events before the instance
is actually deleted.

Cc: stable@vger.kernel.org # 3.10
Reported-by: Alexander Lam <azl@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 2c3cba59552d805e170641231d97f3c6e082d111..c7fbf93f1b7c472017584c42c4370f1b8474074d 100644 (file)
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -226,6 +226,9 @@ extern struct list_head ftrace_trace_arrays;
 
 extern struct mutex trace_types_lock;
 
+extern int trace_array_get(struct trace_array *tr);
+extern void trace_array_put(struct trace_array *tr);
+
 /*
  * The global tracer (top) should be the first trace array added,
  * but we check the flag anyway.

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 35c6f23c71b2ea9fb727e9df5744af0b8f8f99a2..920e08fb53b31748f926f106834ed5386da42bce 100644 (file)
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -409,6 +409,35 @@ static void put_system(struct ftrace_subsystem_dir *dir)
        mutex_unlock(&event_mutex);
 }
 
+/*
+ * Open and update trace_array ref count.
+ * Must have the current trace_array passed to it.
+ */
+static int tracing_open_generic_file(struct inode *inode, struct file *filp)
+{
+       struct ftrace_event_file *file = inode->i_private;
+       struct trace_array *tr = file->tr;
+       int ret;
+
+       if (trace_array_get(tr) < 0)
+               return -ENODEV;
+
+       ret = tracing_open_generic(inode, filp);
+       if (ret < 0)
+               trace_array_put(tr);
+       return ret;
+}
+
+static int tracing_release_generic_file(struct inode *inode, struct file *filp)
+{
+       struct ftrace_event_file *file = inode->i_private;
+       struct trace_array *tr = file->tr;
+
+       trace_array_put(tr);
+
+       return 0;
+}
+
 /*
  * __ftrace_set_clr_event(NULL, NULL, NULL, set) will set/unset all events.
  */
@@ -1032,9 +1061,17 @@ static int subsystem_open(struct inode *inode, struct file *filp)
        /* Some versions of gcc think dir can be uninitialized here */
        WARN_ON(!dir);
 
+       /* Still need to increment the ref count of the system */
+       if (trace_array_get(tr) < 0) {
+               put_system(dir);
+               return -ENODEV;
+       }
+
        ret = tracing_open_generic(inode, filp);
-       if (ret < 0)
+       if (ret < 0) {
+               trace_array_put(tr);
                put_system(dir);
+       }
 
        return ret;
 }
@@ -1045,16 +1082,23 @@ static int system_tr_open(struct inode *inode, struct file *filp)
        struct trace_array *tr = inode->i_private;
        int ret;
 
+       if (trace_array_get(tr) < 0)
+               return -ENODEV;
+
        /* Make a temporary dir that has no system but points to tr */
        dir = kzalloc(sizeof(*dir), GFP_KERNEL);
-       if (!dir)
+       if (!dir) {
+               trace_array_put(tr);
                return -ENOMEM;
+       }
 
        dir->tr = tr;
 
        ret = tracing_open_generic(inode, filp);
-       if (ret < 0)
+       if (ret < 0) {
+               trace_array_put(tr);
                kfree(dir);
+       }
 
        filp->private_data = dir;
 
@@ -1065,6 +1109,8 @@ static int subsystem_release(struct inode *inode, struct file *file)
 {
        struct ftrace_subsystem_dir *dir = file->private_data;
 
+       trace_array_put(dir->tr);
+
        /*
         * If dir->subsystem is NULL, then this is a temporary
         * descriptor that was made for a trace_array to enable
@@ -1192,9 +1238,10 @@ static const struct file_operations ftrace_set_event_fops = {
 };
 
 static const struct file_operations ftrace_enable_fops = {
-       .open = tracing_open_generic,
+       .open = tracing_open_generic_file,
        .read = event_enable_read,
        .write = event_enable_write,
+       .release = tracing_release_generic_file,
        .llseek = default_llseek,
 };