87 lines
3.3 KiB
Diff
87 lines
3.3 KiB
Diff
|
From 135bcffd6e7db60297ba46d7fdb099ea81081bec Mon Sep 17 00:00:00 2001
|
||
|
|
From: Peter Zijlstra <peterz@infradead.org>
|
||
|
|
Date: Wed, 22 Mar 2017 11:35:59 +0100
|
||
|
|
Subject: [PATCH 016/365] futex: Futex_unlock_pi() determinism
|
||
|
|
|
||
|
|
Upstream commit bebe5b514345f09be2c15e414d076b02ecb9cce8
|
||
|
|
|
||
|
|
The problem with returning -EAGAIN when the waiter state mismatches is that
|
||
|
|
it becomes very hard to proof a bounded execution time on the
|
||
|
|
operation. And seeing that this is a RT operation, this is somewhat
|
||
|
|
important.
|
||
|
|
|
||
|
|
While in practise; given the previous patch; it will be very unlikely to
|
||
|
|
ever really take more than one or two rounds, proving so becomes rather
|
||
|
|
hard.
|
||
|
|
|
||
|
|
However, now that modifying wait_list is done while holding both hb->lock
|
||
|
|
and wait_lock, the scenario can be avoided entirely by acquiring wait_lock
|
||
|
|
while still holding hb-lock. Doing a hand-over, without leaving a hole.
|
||
|
|
|
||
|
|
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
|
||
|
|
Cc: juri.lelli@arm.com
|
||
|
|
Cc: bigeasy@linutronix.de
|
||
|
|
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/20170322104152.112378812@infradead.org
|
||
|
|
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
|
||
|
|
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
|
||
|
|
---
|
||
|
|
kernel/futex.c | 24 +++++++++++-------------
|
||
|
|
1 file changed, 11 insertions(+), 13 deletions(-)
|
||
|
|
|
||
|
|
diff --git a/kernel/futex.c b/kernel/futex.c
|
||
|
|
index 7e89ec3ca138..079f34048e90 100644
|
||
|
|
--- a/kernel/futex.c
|
||
|
|
+++ b/kernel/futex.c
|
||
|
|
@@ -1414,15 +1414,10 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_
|
||
|
|
WAKE_Q(wake_q);
|
||
|
|
int ret = 0;
|
||
|
|
|
||
|
|
- raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
|
||
|
|
new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
|
||
|
|
- if (!new_owner) {
|
||
|
|
+ if (WARN_ON_ONCE(!new_owner)) {
|
||
|
|
/*
|
||
|
|
- * Since we held neither hb->lock nor wait_lock when coming
|
||
|
|
- * into this function, we could have raced with futex_lock_pi()
|
||
|
|
- * such that we might observe @this futex_q waiter, but the
|
||
|
|
- * rt_mutex's wait_list can be empty (either still, or again,
|
||
|
|
- * depending on which side we land).
|
||
|
|
+ * As per the comment in futex_unlock_pi() this should not happen.
|
||
|
|
*
|
||
|
|
* When this happens, give up our locks and try again, giving
|
||
|
|
* the futex_lock_pi() instance time to complete, either by
|
||
|
|
@@ -2860,15 +2855,18 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
|
||
|
|
if (pi_state->owner != current)
|
||
|
|
goto out_unlock;
|
||
|
|
|
||
|
|
+ get_pi_state(pi_state);
|
||
|
|
/*
|
||
|
|
- * Grab a reference on the pi_state and drop hb->lock.
|
||
|
|
+ * Since modifying the wait_list is done while holding both
|
||
|
|
+ * hb->lock and wait_lock, holding either is sufficient to
|
||
|
|
+ * observe it.
|
||
|
|
*
|
||
|
|
- * 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.
|
||
|
|
+ * 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
|
||
|
|
+ * observed.
|
||
|
|
*/
|
||
|
|
- get_pi_state(pi_state);
|
||
|
|
+ raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
|
||
|
|
spin_unlock(&hb->lock);
|
||
|
|
|
||
|
|
ret = wake_futex_pi(uaddr, uval, pi_state);
|
||
|
|
--
|
||
|
|
2.28.0
|
||
|
|
|