kmod: avoid deadlock from recursive kmod call

The system deadlocks (at least since 2.6.10) when
call_usermodehelper(UMH_WAIT_EXEC) request triggers
call_usermodehelper(UMH_WAIT_PROC) request.

This is because "khelper thread is waiting for the worker thread at
wait_for_completion() in do_fork() since the worker thread was created
with CLONE_VFORK flag" and "the worker thread cannot call complete()
because do_execve() is blocked at UMH_WAIT_PROC request" and "the khelper
thread cannot start processing UMH_WAIT_PROC request because the khelper
thread is waiting for the worker thread at wait_for_completion() in
do_fork()".

The easiest example to observe this deadlock is to use a corrupted
/sbin/hotplug binary (like shown below).

  # : > /tmp/dummy
  # chmod 755 /tmp/dummy
  # echo /tmp/dummy > /proc/sys/kernel/hotplug
  # modprobe whatever

call_usermodehelper("/tmp/dummy", UMH_WAIT_EXEC) is called from
kobject_uevent_env() in lib/kobject_uevent.c upon loading/unloading a
module.  do_execve("/tmp/dummy") triggers a call to
request_module("binfmt-0000") from search_binary_handler() which in turn
calls call_usermodehelper(UMH_WAIT_PROC).

In order to avoid deadlock, as a for-now and easy-to-backport solution, do
not try to call wait_for_completion() in call_usermodehelper_exec() if the
worker thread was created by khelper thread with CLONE_VFORK flag.  Future
and fundamental solution might be replacing singleton khelper thread with
some workqueue so that recursive calls up to max_active dependency loop
can be handled without deadlock.

[akpm@linux-foundation.org: add comment to kmod_thread_locker]
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Tejun Heo <tj@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 29 insertions, 2 deletions

diff --git a/kernel/kmod.c b/kernel/kmod.c
index 2a8351516a0e..6f99aead66c6 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -45,6 +45,13 @@ extern int max_threads;
 
 static struct workqueue_struct *khelper_wq;
 
+/*
+ * kmod_thread_locker is used for deadlock avoidance.  There is no explicit
+ * locking to protect this global - it is private to the singleton khelper
+ * thread and should only ever be modified by that thread.
+ */
+static const struct task_struct *kmod_thread_locker;
+
 #define CAP_BSET        (void *)1
 #define CAP_PI          (void *)2
 
@@ -221,6 +228,13 @@ fail:
         return 0;
 }
 
+static int call_helper(void *data)
+{
+        /* Worker thread started blocking khelper thread. */
+        kmod_thread_locker = current;
+        return ____call_usermodehelper(data);
+}
+
 static void call_usermodehelper_freeinfo(struct subprocess_info *info)
 {
         if (info->cleanup)
@@ -295,9 +309,12 @@ static void __call_usermodehelper(struct work_struct *work)
         if (wait == UMH_WAIT_PROC)
                 pid = kernel_thread(wait_for_helper, sub_info,
                                     CLONE_FS | CLONE_FILES | SIGCHLD);
-        else
-                pid = kernel_thread(____call_usermodehelper, sub_info,
+        else {
+                pid = kernel_thread(call_helper, sub_info,
                                     CLONE_VFORK | SIGCHLD);
+                /* Worker thread stopped blocking khelper thread. */
+                kmod_thread_locker = NULL;
+        }
 
         switch (wait) {
         case UMH_NO_WAIT:
@@ -548,6 +565,16 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
                 retval = -EBUSY;
                 goto out;
         }
+        /*
+         * Worker thread must not wait for khelper thread at below
+         * wait_for_completion() if the thread was created with CLONE_VFORK
+         * flag, for khelper thread is already waiting for the thread at
+         * wait_for_completion() in do_fork().
+         */
+        if (wait != UMH_NO_WAIT && current == kmod_thread_locker) {
+                retval = -EBUSY;
+                goto out;
+        }
 
         sub_info->complete = &done;
         sub_info->wait = wait;