[PATCH -v4 01/10] futex: Fix potential use-after-free in FUTEX_REQUEUE_PI

[Peter Zijlstra]

While working on the futex code, I stumbled over this potential
use-after-free scenario.

pi_mutex is a pointer into pi_state, which we drop the reference on in
unqueue_me_pi(). So any access to that pointer after that is bad.

Since other sites already do rt_mutex_unlock() with hb->lock held, see
for example futex_lock_pi(), simply move the unlock before
unqueue_me_pi().

Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: dvhart@xxxxxxxxxxxxx
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
 kernel/futex.c |   20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2813,7 +2813,6 @@ static int futex_wait_requeue_pi(u32 __u
 {
 	struct hrtimer_sleeper timeout, *to = NULL;
 	struct rt_mutex_waiter rt_waiter;
-	struct rt_mutex *pi_mutex = NULL;
 	struct futex_hash_bucket *hb;
 	union futex_key key2 = FUTEX_KEY_INIT;
 	struct futex_q q = futex_q_init;
@@ -2905,6 +2904,8 @@ static int futex_wait_requeue_pi(u32 __u
 			spin_unlock(q.lock_ptr);
 		}
 	} else {
+		struct rt_mutex *pi_mutex;
+
 		/*
 		 * We have been woken up by futex_unlock_pi(), a timeout, or a
 		 * signal.  futex_unlock_pi() will not destroy the lock_ptr nor
@@ -2928,18 +2929,19 @@ static int futex_wait_requeue_pi(u32 __u
 		if (res)
 			ret = (res < 0) ? res : 0;
 
+		/*
+		 * If fixup_pi_state_owner() faulted and was unable to handle
+		 * the fault, unlock the rt_mutex and return the fault to
+		 * userspace.
+		 */
+		if (ret && rt_mutex_owner(pi_mutex) == current)
+			rt_mutex_unlock(pi_mutex);
+
 		/* Unqueue and drop the lock. */
 		unqueue_me_pi(&q);
 	}
 
-	/*
-	 * If fixup_pi_state_owner() faulted and was unable to handle the
-	 * fault, unlock the rt_mutex and return the fault to userspace.
-	 */
-	if (ret == -EFAULT) {
-		if (pi_mutex && rt_mutex_owner(pi_mutex) == current)
-			rt_mutex_unlock(pi_mutex);
-	} else if (ret == -EINTR) {
+	if (ret == -EINTR) {
 		/*
 		 * We've already been requeued, but cannot restart by calling
 		 * futex_lock_pi() directly. We could restart this syscall, but