summaryrefslogtreecommitdiffstats
path: root/debian/patches-rt/0161-futex-Fix-bug-on-when-a-requeued-RT-task-times-out.patch
blob: bab95baf23a5df2998173860265d58f77c61daed (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
From 787b0032cdfc388293dcde2c4bc3a2c40b6d9cf2 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Tue, 14 Jul 2015 14:26:34 +0200
Subject: [PATCH 161/323] futex: Fix bug on when a requeued RT task times out
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/5.10/older/patches-5.10.204-rt100.tar.xz

Requeue with timeout causes a bug with PREEMPT_RT.

The bug comes from a timed out condition.

	TASK 1				TASK 2
	------				------
    futex_wait_requeue_pi()
	futex_wait_queue_me()
	<timed out>

					double_lock_hb();

	raw_spin_lock(pi_lock);
	if (current->pi_blocked_on) {
	} else {
	    current->pi_blocked_on = PI_WAKE_INPROGRESS;
	    run_spin_unlock(pi_lock);
	    spin_lock(hb->lock); <-- blocked!

					plist_for_each_entry_safe(this) {
					    rt_mutex_start_proxy_lock();
						task_blocks_on_rt_mutex();
						BUG_ON(task->pi_blocked_on)!!!!

The BUG_ON() actually has a check for PI_WAKE_INPROGRESS, but the
problem is that, after TASK 1 sets PI_WAKE_INPROGRESS, it then tries to
grab the hb->lock, which it fails to do so. As the hb->lock is a mutex,
it will block and set the "pi_blocked_on" to the hb->lock.

When TASK 2 goes to requeue it, the check for PI_WAKE_INPROGESS fails
because the task1's pi_blocked_on is no longer set to that, but instead,
set to the hb->lock.

The fix:

When calling rt_mutex_start_proxy_lock() a check is made to see
if the proxy tasks pi_blocked_on is set. If so, exit out early.
Otherwise set it to a new flag PI_REQUEUE_INPROGRESS, which notifies
the proxy task that it is being requeued, and will handle things
appropriately.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 kernel/locking/rtmutex.c        | 31 ++++++++++++++++++++++++++++++-
 kernel/locking/rtmutex_common.h |  1 +
 2 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 2ef5a6eb95da..d8755d5ef227 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -138,7 +138,8 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock)
 
 static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter)
 {
-	return waiter && waiter != PI_WAKEUP_INPROGRESS;
+	return waiter && waiter != PI_WAKEUP_INPROGRESS &&
+		waiter != PI_REQUEUE_INPROGRESS;
 }
 
 /*
@@ -1720,6 +1721,34 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 	if (try_to_take_rt_mutex(lock, task, NULL))
 		return 1;
 
+#ifdef CONFIG_PREEMPT_RT
+	/*
+	 * In PREEMPT_RT there's an added race.
+	 * If the task, that we are about to requeue, times out,
+	 * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue
+	 * to skip this task. But right after the task sets
+	 * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then
+	 * block on the spin_lock(&hb->lock), which in RT is an rtmutex.
+	 * This will replace the PI_WAKEUP_INPROGRESS with the actual
+	 * lock that it blocks on. We *must not* place this task
+	 * on this proxy lock in that case.
+	 *
+	 * To prevent this race, we first take the task's pi_lock
+	 * and check if it has updated its pi_blocked_on. If it has,
+	 * we assume that it woke up and we return -EAGAIN.
+	 * Otherwise, we set the task's pi_blocked_on to
+	 * PI_REQUEUE_INPROGRESS, so that if the task is waking up
+	 * it will know that we are in the process of requeuing it.
+	 */
+	raw_spin_lock(&task->pi_lock);
+	if (task->pi_blocked_on) {
+		raw_spin_unlock(&task->pi_lock);
+		return -EAGAIN;
+	}
+	task->pi_blocked_on = PI_REQUEUE_INPROGRESS;
+	raw_spin_unlock(&task->pi_lock);
+#endif
+
 	/* We enforce deadlock detection for futexes */
 	ret = task_blocks_on_rt_mutex(lock, waiter, task,
 				      RT_MUTEX_FULL_CHAINWALK);
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 096b16cfb096..37cd6b3bf6f4 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -126,6 +126,7 @@ enum rtmutex_chainwalk {
  * PI-futex support (proxy locking functions, etc.):
  */
 #define PI_WAKEUP_INPROGRESS	((struct rt_mutex_waiter *) 1)
+#define PI_REQUEUE_INPROGRESS	((struct rt_mutex_waiter *) 2)
 
 extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock);
 extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
-- 
2.43.0