futex: Handle unlock_pi race gracefully

[ Upstream commit 89e9e66ba1b3bde9d8ea90566c2aee20697ad681 ]

If userspace calls UNLOCK_PI unconditionally without trying the TID -> 0
transition in user space first then the user space value might not have the
waiters bit set. This opens the following race:

CPU0	    	      	    CPU1
uval = get_user(futex)
			    lock(hb)
lock(hb)
			    futex |= FUTEX_WAITERS
			    ....
			    unlock(hb)

cmpxchg(futex, uval, newval)

So the cmpxchg fails and returns -EINVAL to user space, which is wrong because
the futex value is valid.

To handle this (yes, yet another) corner case gracefully, check for a flag
change and retry.

[ tglx: Massaged changelog and slightly reworked implementation ]

Fixes: ccf9e6a80d9e ("futex: Make unlock_pi more robust")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: stable@vger.kernel.org
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Darren Hart <dvhart@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1460723739-5195-1-git-send-email-bigeasy@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>

1 files changed, 22 insertions, 3 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index b75fbddacf0e..46b168e19c98 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1157,10 +1157,20 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
 	 */
 	newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
 
-	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
+	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) {
 		ret = -EFAULT;
-	else if (curval != uval)
-		ret = -EINVAL;
+	} else if (curval != uval) {
+		/*
+		 * If a unconditional UNLOCK_PI operation (user space did not
+		 * try the TID->0 transition) raced with a waiter setting the
+		 * FUTEX_WAITERS flag between get_user() and locking the hash
+		 * bucket lock, retry the operation.
+		 */
+		if ((FUTEX_TID_MASK & curval) == uval)
+			ret = -EAGAIN;
+		else
+			ret = -EINVAL;
+	}
 	if (ret) {
 		raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
 		return ret;
@@ -2419,6 +2429,15 @@ retry:
 		 */
 		if (ret == -EFAULT)
 			goto pi_faulted;
+		/*
+		 * A unconditional UNLOCK_PI op raced against a waiter
+		 * setting the FUTEX_WAITERS bit. Try again.
+		 */
+		if (ret == -EAGAIN) {
+			spin_unlock(&hb->lock);
+			put_futex_key(&key);
+			goto retry;
+		}
 		goto out_unlock;
 	}