| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Tue, 13 Dec 2016 17:07:14 +0100
From: Peter Zijlstra <peterz@...radead.org>
To: tglx@...utronix.de
Cc: mingo@...nel.org, juri.lelli@....com, rostedt@...dmis.org,
xlpang@...hat.com, bigeasy@...utronix.de,
linux-kernel@...r.kernel.org, mathieu.desnoyers@...icios.com,
jdesfossez@...icios.com, bristot@...hat.com, dvhart@...radead.org
Subject: Re: [PATCH -v4 00/10] FUTEX_UNLOCK_PI wobbles
On Tue, Dec 13, 2016 at 09:36:38AM +0100, Peter Zijlstra wrote:
> The basic idea is to, like requeue PI, break the rt_mutex_lock() function into
> pieces, such that we can enqueue the waiter while holding hb->lock, wait for
> acquisition without hb->lock and can remove the waiter, on failure, while
> holding hb->lock again.
>
> That way, when we drop hb->lock to wait, futex and rt_mutex wait state is
> consistent.
And of course, there's a hole in...
There is a point in futex_unlock_pi() where we hold neither hb->lock nor
wait_lock, at that point a futex_lock_pi() that had failed its
rt_mutex_wait_proxy_lock() can sneak in and remove itself, even though
we saw its waiter, recreating a vraiant of the initial problem.
The below plugs the hole, but its rather fragile in that it relies on
overlapping critical sections and the specific detail that we call
rt_mutex_cleanup_proxy_lock() immediately after (re)acquiring hb->lock.
There is another solution, but that's more involved and uglier still.
I'll give it a bit more thought.
---
kernel/futex.c | 36 +++++++++++++++++++++++++-----------
kernel/locking/rtmutex.c | 21 ++++++++++++++++++---
kernel/locking/rtmutex_common.h | 2 +-
3 files changed, 44 insertions(+), 15 deletions(-)
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1384,6 +1384,7 @@ static void mark_wake_futex(struct wake_
}
static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_state)
+ __releases(&pi_state->pi_mutex.wait_lock)
{
u32 uninitialized_var(curval), newval;
struct task_struct *new_owner;
@@ -1391,7 +1392,8 @@ static int wake_futex_pi(u32 __user *uad
DEFINE_WAKE_Q(wake_q);
int ret = 0;
- raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+ lockdep_assert_held(&pi_state->pi_mutex.wait_lock);
+
new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
BUG_ON(!new_owner);
@@ -2655,8 +2657,8 @@ static int futex_lock_pi(u32 __user *uad
* rt_mutex waitqueue, such that we can keep the hb and rt_mutex
* wait lists consistent.
*/
- if (ret)
- rt_mutex_cleanup_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter);
+ if (ret && !rt_mutex_cleanup_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter))
+ ret = 0;
did_trylock:
/*
@@ -2763,15 +2765,26 @@ static int futex_unlock_pi(u32 __user *u
if (pi_state->owner != current)
goto out_unlock;
+ get_pi_state(pi_state);
+
/*
- * Grab a reference on the pi_state and drop hb->lock.
+ * We must grab wait_lock _before_ dropping hb->lock, such that
+ * the critical sections overlap. Without this there is a hole
+ * in which futex_lock_pi()'s rt_mutex_wait_proxy_lock() can
+ * fail, re-acquire the hb->lock and wait_lock and have our
+ * top_waiter dissapear.
+ */
+ raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+ /*
+ * Now that we have a reference on pi_state and hole wait_lock
+ * we can drop hb->lock without risk of a waiter dissapearing
+ * on us.
*
- * The reference ensures pi_state lives, dropping the hb->lock
- * is tricky.. wake_futex_pi() will take rt_mutex::wait_lock to
- * close the races against futex_lock_pi(), but in case of
- * _any_ fail we'll abort and retry the whole deal.
+ * Even if rt_mutex_wait_proxy_lock() fails, us holding
+ * wait_lock ensures it cannot be removed and the
+ * rt_mutex_cleanup_proxy_lock() call will find it owns the
+ * lock anyway.
*/
- get_pi_state(pi_state);
spin_unlock(&hb->lock);
ret = wake_futex_pi(uaddr, uval, pi_state);
@@ -3041,8 +3054,9 @@ static int futex_wait_requeue_pi(u32 __u
debug_rt_mutex_free_waiter(&rt_waiter);
spin_lock(q.lock_ptr);
- if (ret)
- rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter);
+ if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter))
+ ret = 0;
+
/*
* Fixup the pi_state owner and possibly acquire the lock if we
* haven't already.
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1779,16 +1779,31 @@ int rt_mutex_wait_proxy_lock(struct rt_m
*
* Clean up the failed lock acquisition as per rt_mutex_wait_proxy_lock().
*
+ * Returns:
+ * true - did cleanup, we done.
+ * false - we acquired the lock anyway, after rt_mutex_wait_proxy_lock(),
+ * caller should disregard its return value.
+ *
* Special API call for PI-futex support
*/
-void rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
+bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
struct rt_mutex_waiter *waiter)
{
+ bool cleanup = false;
+
raw_spin_lock_irq(&lock->wait_lock);
- remove_waiter(lock, waiter);
- fixup_rt_mutex_waiters(lock);
+ /*
+ * Check if we got the lock anyway...
+ */
+ if (rt_mutex_owner(lock) != current) {
+ remove_waiter(lock, waiter);
+ fixup_rt_mutex_waiters(lock);
+ cleanup = true;
+ }
raw_spin_unlock_irq(&lock->wait_lock);
+
+ return cleanup;
}
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -109,7 +109,7 @@ extern int rt_mutex_start_proxy_lock(str
extern int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
struct hrtimer_sleeper *to,
struct rt_mutex_waiter *waiter);
-extern void rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
+extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
struct rt_mutex_waiter *waiter);
extern int rt_mutex_futex_trylock(struct rt_mutex *l);
Powered by blists - more mailing lists