ftrace, kprobes: Fix a deadlock on ftrace_regex_lock

Fix a deadlock on ftrace_regex_lock which happens when setting
an enable_event trigger on dynamic kprobe event as below.

----
sh-2.05b# echo p vfs_symlink > kprobe_events
sh-2.05b# echo vfs_symlink:enable_event:kprobes:p_vfs_symlink_0 > set_ftrace_filter

=============================================
[ INFO: possible recursive locking detected ]
3.9.0+ #35 Not tainted
---------------------------------------------
sh/72 is trying to acquire lock:
 (ftrace_regex_lock){+.+.+.}, at: [<ffffffff810ba6c1>] ftrace_set_hash+0x81/0x1f0

but task is already holding lock:
 (ftrace_regex_lock){+.+.+.}, at: [<ffffffff810b7cbd>] ftrace_regex_write.isra.29.part.30+0x3d/0x220

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(ftrace_regex_lock);
  lock(ftrace_regex_lock);

 *** DEADLOCK ***
----

To fix that, this introduces a finer regex_lock for each ftrace_ops.
ftrace_regex_lock is too big of a lock which protects all
filter/notrace_hash operations, but it doesn't need to be a global
lock after supporting multiple ftrace_ops because each ftrace_ops
has its own filter/notrace_hash.

Link: http://lkml.kernel.org/r/20130509054417.30398.84254.stgit@mhiramat-M0-7522

Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Tom Zanussi <tom.zanussi@intel.com>
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
[ Added initialization flag and automate mutex initialization for
  non ftrace.c ftrace_probes. ]
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

2 files changed, 56 insertions, 21 deletions

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index f83e17a40e8b..99d0fbcbaf79 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -90,6 +90,8 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
  *            not set this, then the ftrace infrastructure will add recursion
  *            protection for the caller.
  * STUB   - The ftrace_ops is just a place holder.
+ * INITIALIZED - The ftrace_ops has already been initialized (first use time
+ *            register_ftrace_function() is called, it will initialized the ops)
  */
 enum {
         FTRACE_OPS_FL_ENABLED                   = 1 << 0,
@@ -100,6 +102,7 @@ enum {
         FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED    = 1 << 5,
         FTRACE_OPS_FL_RECURSION_SAFE            = 1 << 6,
         FTRACE_OPS_FL_STUB                      = 1 << 7,
+        FTRACE_OPS_FL_INITIALIZED               = 1 << 8,
 };
 
 struct ftrace_ops {
@@ -110,6 +113,7 @@ struct ftrace_ops {
 #ifdef CONFIG_DYNAMIC_FTRACE
         struct ftrace_hash              *notrace_hash;
         struct ftrace_hash              *filter_hash;
+        struct mutex                    regex_lock;
 #endif
 };
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index d85a0ad81a67..827f2fe7bc3f 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -64,6 +64,13 @@
 
 #define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_CONTROL)
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+#define INIT_REGEX_LOCK(opsname)        \
+        .regex_lock     = __MUTEX_INITIALIZER(opsname.regex_lock),
+#else
+#define INIT_REGEX_LOCK(opsname)
+#endif
+
 static struct ftrace_ops ftrace_list_end __read_mostly = {
         .func           = ftrace_stub,
         .flags          = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_STUB,
@@ -131,6 +138,16 @@ static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip);
         while (likely(op = rcu_dereference_raw((op)->next)) &&  \
                unlikely((op) != &ftrace_list_end))
 
+static inline void ftrace_ops_init(struct ftrace_ops *ops)
+{
+#ifdef CONFIG_DYNAMIC_FTRACE
+        if (!(ops->flags & FTRACE_OPS_FL_INITIALIZED)) {
+                mutex_init(&ops->regex_lock);
+                ops->flags |= FTRACE_OPS_FL_INITIALIZED;
+        }
+#endif
+}
+
 /**
  * ftrace_nr_registered_ops - return number of ops registered
  *
@@ -907,7 +924,8 @@ static void unregister_ftrace_profiler(void)
 #else
 static struct ftrace_ops ftrace_profile_ops __read_mostly = {
         .func           = function_profile_call,
-        .flags          = FTRACE_OPS_FL_RECURSION_SAFE,
+        .flags          = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED,
+        INIT_REGEX_LOCK(ftrace_profile_ops)
 };
 
 static int register_ftrace_profiler(void)
@@ -1103,11 +1121,10 @@ static struct ftrace_ops global_ops = {
         .func                   = ftrace_stub,
         .notrace_hash           = EMPTY_HASH,
         .filter_hash            = EMPTY_HASH,
-        .flags                  = FTRACE_OPS_FL_RECURSION_SAFE,
+        .flags                  = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED,
+        INIT_REGEX_LOCK(global_ops)
 };
 
-static DEFINE_MUTEX(ftrace_regex_lock);
-
 struct ftrace_page {
         struct ftrace_page      *next;
         struct dyn_ftrace       *records;
@@ -1247,6 +1264,7 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash)
 
 void ftrace_free_filter(struct ftrace_ops *ops)
 {
+        ftrace_ops_init(ops);
         free_ftrace_hash(ops->filter_hash);
         free_ftrace_hash(ops->notrace_hash);
 }
@@ -2624,6 +2642,8 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
         struct ftrace_hash *hash;
         int ret = 0;
 
+        ftrace_ops_init(ops);
+
         if (unlikely(ftrace_disabled))
                 return -ENODEV;
 
@@ -2656,7 +2676,7 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
                 }
         }
 
-        mutex_lock(&ftrace_regex_lock);
+        mutex_lock(&ops->regex_lock);
 
         if ((file->f_mode & FMODE_WRITE) &&
             (file->f_flags & O_TRUNC))
@@ -2677,7 +2697,7 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
                 }
         } else
                 file->private_data = iter;
-        mutex_unlock(&ftrace_regex_lock);
+        mutex_unlock(&ops->regex_lock);
 
         return ret;
 }
@@ -2910,6 +2930,8 @@ static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip,
 static struct ftrace_ops trace_probe_ops __read_mostly =
 {
         .func           = function_trace_probe_call,
+        .flags          = FTRACE_OPS_FL_INITIALIZED,
+        INIT_REGEX_LOCK(trace_probe_ops)
 };
 
 static int ftrace_probe_registered;
@@ -3256,18 +3278,18 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
         if (!cnt)
                 return 0;
 
-        mutex_lock(&ftrace_regex_lock);
-
-        ret = -ENODEV;
-        if (unlikely(ftrace_disabled))
-                goto out_unlock;
-
         if (file->f_mode & FMODE_READ) {
                 struct seq_file *m = file->private_data;
                 iter = m->private;
         } else
                 iter = file->private_data;
 
+        mutex_lock(&iter->ops->regex_lock);
+
+        ret = -ENODEV;
+        if (unlikely(ftrace_disabled))
+                goto out_unlock;
+
         parser = &iter->parser;
         read = trace_get_user(parser, ubuf, cnt, ppos);
 
@@ -3282,7 +3304,7 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
 
         ret = read;