Skip to contentSkip to conversation

Patch "futex: Handle unlock_pi race gracefully" has been added to the 4.5-stable tree

PATCH [email protected] 1 participant 1 message May 1, 2016 Stable branch

lore
Share & tools
lore

[email protected]

author maintainer Applied
#0 lore raw

This is a note to let you know that I've just added the patch titled

futex: Handle unlock_pi race gracefully

to the 4.5-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
futex-handle-unlock_pi-race-gracefully.patch
and it can be found in the queue-4.5 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree, please let <[email protected]> know about it.

Quoted 1 line

From 89e9e66ba1b3bde9d8ea90566c2aee20697ad681 Mon Sep 17 00:00:00 2001

From: Sebastian Andrzej Siewior <[email protected]>
Date: Fri, 15 Apr 2016 14:35:39 +0200
Subject: futex: Handle unlock_pi race gracefully

From: Sebastian Andrzej Siewior <[email protected]>

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")
Cc Davidlohr Bueso <[email protected]>
Cc Darren Hart <[email protected]>
Cc Peter Zijlstra <[email protected]>
---
 kernel/futex.c |   25 ++++++++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)
kernel/futex.c +22 -3
@@ -1212,10 +1212,20 @@ static int wake_futex_pi(u32 __user *uad
 	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_irq(&pi_state->pi_mutex.wait_lock);
 		return ret;
@@ -2536,6 +2546,15 @@ 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.
 		 */

Patches currently in stable-queue which might be from [email protected] are

queue-4.5/futex-handle-unlock_pi-race-gracefully.patch queue-4.5/futex-acknowledge-a-new-waiter-in-counter-before-plist.patch