futex: Drop hb->lock before enqueueing on the rtmutex
commit 56222b212e8edb1cf51f5dd73ff645809b082b40 upstream.
When PREEMPT_RT_FULL does the spinlock -> rt_mutex substitution the PI
chain code will (falsely) report a deadlock and BUG.
The problem is that it hold hb->lock (now an rt_mutex) while doing
task_blocks_on_rt_mutex on the futex's pi_state::rtmutex. This, when
interleaved just right with futex_unlock_pi() leads it to believe to see an
AB-BA deadlock.
Task1 (holds rt_mutex, Task2 (does FUTEX_LOCK_PI)
does FUTEX_UNLOCK_PI)
lock hb->lock
lock rt_mutex (as per start_proxy)
lock hb->lock
Which is a trivial AB-BA.
It is not an actual deadlock, because it won't be holding hb->lock by the
time it actually blocks on the rt_mutex, but the chainwalk code doesn't
know that and it would be a nightmare to handle this gracefully.
To avoid this problem, do the same as in futex_unlock_pi() and drop
hb->lock after acquiring wait_lock. This still fully serializes against
futex_unlock_pi(), since adding to the wait_list does the very same lock
dance, and removing it holds both locks.
Aside of solving the RT problem this makes the lock and unlock mechanism
symetric and reduces the hb->lock held time.
Reported-and-tested-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: juri.lelli@arm.com
Cc: xlpang@redhat.com
Cc: rostedt@goodmis.org
Cc: mathieu.desnoyers@efficios.com
Cc: jdesfossez@efficios.com
Cc: dvhart@infradead.org
Cc: bristot@redhat.com
Link: http://lkml.kernel.org/r/20170322104152.161341537@infradead.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
diff --git a/kernel/futex.c b/kernel/futex.c
index 0e72e51..491888a 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2948,20 +2948,33 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
goto no_block;
}
- /*
- * We must add ourselves to the rt_mutex waitlist while holding hb->lock
- * such that the hb and rt_mutex wait lists match.
- */
rt_mutex_init_waiter(&rt_waiter);
- ret = rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current);
+
+ /*
+ * On PREEMPT_RT_FULL, when hb->lock becomes an rt_mutex, we must not
+ * hold it while doing rt_mutex_start_proxy(), because then it will
+ * include hb->lock in the blocking chain, even through we'll not in
+ * fact hold it while blocking. This will lead it to report -EDEADLK
+ * and BUG when futex_unlock_pi() interleaves with this.
+ *
+ * Therefore acquire wait_lock while holding hb->lock, but drop the
+ * latter before calling rt_mutex_start_proxy_lock(). This still fully
+ * serializes against futex_unlock_pi() as that does the exact same
+ * lock handoff sequence.
+ */
+ raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock);
+ spin_unlock(q.lock_ptr);
+ ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current);
+ raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock);
+
if (ret) {
if (ret == 1)
ret = 0;
+ spin_lock(q.lock_ptr);
goto no_block;
}
- spin_unlock(q.lock_ptr);
if (unlikely(to))
hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS);
@@ -2974,6 +2987,9 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
* first acquire the hb->lock before removing the lock from the
* rt_mutex waitqueue, such that we can keep the hb and rt_mutex
* wait lists consistent.
+ *
+ * In particular; it is important that futex_unlock_pi() can not
+ * observe this inconsistency.
*/
if (ret && !rt_mutex_cleanup_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter))
ret = 0;
@@ -3071,10 +3087,6 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
get_pi_state(pi_state);
/*
- * Since modifying the wait_list is done while holding both
- * hb->lock and wait_lock, holding either is sufficient to
- * observe it.
- *
* By taking wait_lock while still holding hb->lock, we ensure
* there is no point where we hold neither; and therefore
* wake_futex_pi() must observe a state consistent with what we