init, sched: Fix race between init and kthreadd

Ilya reported that on a very slow machine he could reliably
reproduce a race between forking init and kthreadd. We first
fork init so that it  obtains pid-1, however since the scheduler
is already fully running at this point it can preempt and run
the init thread before we spawn and set kthreadd_task.

The init thread can then attempt spawning kthreads without
kthreadd being present which results in an OOPS.

Reported-by: Ilya Loginov <isloginov@gmail.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
LKML-Reference: <1277736661.3561.110.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/init/main.c b/init/main.c
index 3bdb152f412f32b8edeeb1036a24f934988b5be2..633442f79e9020c1e057858420d212d7f7e3ae08 100644 (file)
--- a/init/main.c
+++ b/init/main.c
@@ -422,18 +422,26 @@ static void __init setup_command_line(char *command_line)
  * gcc-3.4 accidentally inlines this function, so use noinline.
  */
 
+static __initdata DECLARE_COMPLETION(kthreadd_done);
+
 static noinline void __init_refok rest_init(void)
        __releases(kernel_lock)
 {
        int pid;
 
        rcu_scheduler_starting();
+       /*
+        * We need to spawn init first so that it obtains pid-1, however
+        * the init task will end up wanting to create kthreads, which, if
+        * we schedule it before we create kthreadd, will OOPS.
+        */
        kernel_thread(kernel_init, NULL, CLONE_FS | CLONE_SIGHAND);
        numa_default_policy();
        pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
        rcu_read_lock();
        kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns);
        rcu_read_unlock();
+       complete(&kthreadd_done);
        unlock_kernel();
 
        /*
@@ -855,6 +863,10 @@ static noinline int init_post(void)
 
 static int __init kernel_init(void * unused)
 {
+       /*
+        * Wait until kthreadd is all set-up.
+        */
+       wait_for_completion(&kthreadd_done);
        lock_kernel();
 
        /*