rt_spin_unlock() releases the RCU protection before unlocking the
lock. That opens the door for the following UAF scenario:

 T1					T2
 spin_lock(&p->lock);		rcu_read_lock();
 invalidate(p);			p = rcu_dereference(ptr);
 rcu_assign_pointer(ptr, NULL);	if (!p) return;
 spin_unlock(&p->lock);		spin_lock(&p->lock)
 				   lock(&lock->lock);
				   rcu_read_lock();
 kfree_rcu(p);			rcu_read_unlock();
				....
				spin_unlock(&p->lock)
				  rcu_read_unlock(); // Ends grace period
 rcu_do_batch()
   kfree(p);
			    UAF ->	  rt_mutex_cmpxchg_release(&lock->lock...)

Regular spinlocks keep preemption disabled accross the unlock operation,
which provides full RCU protection, but the RT substitution fails to
resemble that. Same applies for the rwlock substitution.

Move the rcu_read_unlock() invocation past the unlock operations to match
the non-RT semantics. This makes it asymmetric vs. rt_xxx_lock(), but
that's harmless as the caller needs to hold RCU read lock across the lock
operation. The migrate_enable() call stays before the unlock operation
because there is no per CPU operation in the unlock path which would
require migration to be kept disabled.

Fixes: 0f383b6dc96e ("locking/spinlock: Provide RT variant")
Reported-by: syzbot+000c800a02097aaa10ed@syzkaller.appspotmail.com
Decoded-by: Jann Horn <jannh@google.com>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Cc: stable@vger.kernel.org
---
V2: Fold the corresponding rwlock changes - Sebastian
---
 kernel/locking/spinlock_rt.c |   27 ++++++++++++++++++++++++---
 1 file changed, 24 insertions(+), 3 deletions(-)

--- a/kernel/locking/spinlock_rt.c
+++ b/kernel/locking/spinlock_rt.c
@@ -79,10 +79,27 @@ void __sched rt_spin_unlock(spinlock_t *
 {
 	spin_release(&lock->dep_map, _RET_IP_);
 	migrate_enable();
-	rcu_read_unlock();
 
 	if (unlikely(!rt_mutex_cmpxchg_release(&lock->lock, current, NULL)))
 		rt_mutex_slowunlock(&lock->lock);
+
+	/*
+	 * This must be last to prevent the following UAF:
+	 *
+	 * T1					T2
+	 * spin_lock(&p->lock);			rcu_read_lock();
+	 * invalidate(p);			p = rcu_dereference(ptr);
+	 * rcu_assign_pointer(ptr, NULL);	if (!p) return;
+	 * spin_unlock(&p->lock);		spin_lock(&p->lock);
+	 * kfree_rcu(p);			rcu_read_unlock();
+	 *					....
+	 *					spin_unlock(&p->lock)
+	 *					  rcu_read_unlock(); // Ends grace period
+	 * rcu_do_batch()
+	 *   kfree(p);
+	 *			    UAF ->	  rt_mutex_cmpxchg_release(&p->lock.lock...)
+	 */
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL(rt_spin_unlock);
 
@@ -262,17 +279,21 @@ void __sched rt_read_unlock(rwlock_t *rw
 {
 	rwlock_release(&rwlock->dep_map, _RET_IP_);
 	migrate_enable();
-	rcu_read_unlock();
 	rwbase_read_unlock(&rwlock->rwbase, TASK_RTLOCK_WAIT);
+
+	/* This must be last. See comment in rt_spin_unlock() */
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL(rt_read_unlock);
 
 void __sched rt_write_unlock(rwlock_t *rwlock) __releases(RCU)
 {
 	rwlock_release(&rwlock->dep_map, _RET_IP_);
-	rcu_read_unlock();
 	migrate_enable();
 	rwbase_write_unlock(&rwlock->rwbase);
+
+	/* This must be last. See comment in rt_spin_unlock() */
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL(rt_write_unlock);