sched: Fix a race between __kthread_bind() and sched_setaffinity()

Because sched_setscheduler() checks p->flags & PF_NO_SETAFFINITY
without locks, a caller might observe an old value and race with the
set_cpus_allowed_ptr() call from __kthread_bind() and effectively undo
it:

	__kthread_bind()
	  do_set_cpus_allowed()
						<SYSCALL>
						  sched_setaffinity()
						    if (p->flags & PF_NO_SETAFFINITIY)
						    set_cpus_allowed_ptr()
	  p->flags |= PF_NO_SETAFFINITY

Fix the bug by putting everything under the regular scheduler locks.

This also closes a hole in the serialization of task_struct::{nr_,}cpus_allowed.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: dedekind1@gmail.com
Cc: juri.lelli@arm.com
Cc: mgorman@suse.de
Cc: riel@redhat.com
Cc: rostedt@goodmis.org
Link: http://lkml.kernel.org/r/20150515154833.545640346@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 10e489c..7c40a18 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -325,16 +325,30 @@
 }
 EXPORT_SYMBOL(kthread_create_on_node);
 
-static void __kthread_bind(struct task_struct *p, unsigned int cpu, long state)
+static void __kthread_bind_mask(struct task_struct *p, const struct cpumask *mask, long state)
 {
-	/* Must have done schedule() in kthread() before we set_task_cpu */
+	unsigned long flags;
+
 	if (!wait_task_inactive(p, state)) {
 		WARN_ON(1);
 		return;
 	}
+
 	/* It's safe because the task is inactive. */
-	do_set_cpus_allowed(p, cpumask_of(cpu));
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	do_set_cpus_allowed(p, mask);
 	p->flags |= PF_NO_SETAFFINITY;
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+}
+
+static void __kthread_bind(struct task_struct *p, unsigned int cpu, long state)
+{
+	__kthread_bind_mask(p, cpumask_of(cpu), state);
+}
+
+void kthread_bind_mask(struct task_struct *p, const struct cpumask *mask)
+{
+	__kthread_bind_mask(p, mask, TASK_UNINTERRUPTIBLE);
 }
 
 /**