futex: Handle unlock_pi race gracefully

commit 89e9e66ba1b3bde9d8ea90566c2aee20697ad681 upstream.

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: 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: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/kernel/futex.c b/kernel/futex.c
index 461c72b2dac2c4d316e66b38b5b7d73d980ab347..eaa3a8dfd34517adb0cf31a907735ce96115667e 100644 (file)
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1244,10 +1244,20 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
        if (unlikely(should_fail_futex(true)))
                ret = -EFAULT;
 
-       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;
@@ -2537,6 +2547,15 @@ 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;
+               }
                /*
                 * wake_futex_pi has detected invalid state. Tell user
                 * space.