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
119
120
121
122
123
124
|
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Sun, 22 Nov 2020 20:19:04 +0000
Subject: [PATCH] notifier: Make atomic_notifiers use raw_spinlock
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/5.10/older/patches-5.10.8-rt24.tar.xz
Booting a recent PREEMPT_RT kernel (v5.10-rc3-rt7-rebase) on my arm64 Juno
leads to the idle task blocking on an RT sleeping spinlock down some
notifier path:
[ 1.809101] BUG: scheduling while atomic: swapper/5/0/0x00000002
[ 1.809116] Modules linked in:
[ 1.809123] Preemption disabled at:
[ 1.809125] secondary_start_kernel (arch/arm64/kernel/smp.c:227)
[ 1.809146] CPU: 5 PID: 0 Comm: swapper/5 Tainted: G W 5.10.0-rc3-rt7 #168
[ 1.809153] Hardware name: ARM Juno development board (r0) (DT)
[ 1.809158] Call trace:
[ 1.809160] dump_backtrace (arch/arm64/kernel/stacktrace.c:100 (discriminator 1))
[ 1.809170] show_stack (arch/arm64/kernel/stacktrace.c:198)
[ 1.809178] dump_stack (lib/dump_stack.c:122)
[ 1.809188] __schedule_bug (kernel/sched/core.c:4886)
[ 1.809197] __schedule (./arch/arm64/include/asm/preempt.h:18 kernel/sched/core.c:4913 kernel/sched/core.c:5040)
[ 1.809204] preempt_schedule_lock (kernel/sched/core.c:5365 (discriminator 1))
[ 1.809210] rt_spin_lock_slowlock_locked (kernel/locking/rtmutex.c:1072)
[ 1.809217] rt_spin_lock_slowlock (kernel/locking/rtmutex.c:1110)
[ 1.809224] rt_spin_lock (./include/linux/rcupdate.h:647 kernel/locking/rtmutex.c:1139)
[ 1.809231] atomic_notifier_call_chain_robust (kernel/notifier.c:71 kernel/notifier.c:118 kernel/notifier.c:186)
[ 1.809240] cpu_pm_enter (kernel/cpu_pm.c:39 kernel/cpu_pm.c:93)
[ 1.809249] psci_enter_idle_state (drivers/cpuidle/cpuidle-psci.c:52 drivers/cpuidle/cpuidle-psci.c:129)
[ 1.809258] cpuidle_enter_state (drivers/cpuidle/cpuidle.c:238)
[ 1.809267] cpuidle_enter (drivers/cpuidle/cpuidle.c:353)
[ 1.809275] do_idle (kernel/sched/idle.c:132 kernel/sched/idle.c:213 kernel/sched/idle.c:273)
[ 1.809282] cpu_startup_entry (kernel/sched/idle.c:368 (discriminator 1))
[ 1.809288] secondary_start_kernel (arch/arm64/kernel/smp.c:273)
Two points worth noting:
1) That this is conceptually the same issue as pointed out in:
313c8c16ee62 ("PM / CPU: replace raw_notifier with atomic_notifier")
2) Only the _robust() variant of atomic_notifier callchains suffer from
this
AFAICT only the cpu_pm_notifier_chain really needs to be changed, but
singling it out would mean introducing a new (truly) non-blocking API. At
the same time, callers that are fine with any blocking within the call
chain should use blocking notifiers, so patching up all atomic_notifier's
doesn't seem *too* crazy to me.
Fixes: 70d932985757 ("notifier: Fix broken error handling pattern")
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Link: https://lkml.kernel.org/r/20201122201904.30940-1-valentin.schneider@arm.com
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/linux/notifier.h | 6 +++---
kernel/notifier.c | 12 ++++++------
2 files changed, 9 insertions(+), 9 deletions(-)
--- a/include/linux/notifier.h
+++ b/include/linux/notifier.h
@@ -58,7 +58,7 @@ struct notifier_block {
};
struct atomic_notifier_head {
- spinlock_t lock;
+ raw_spinlock_t lock;
struct notifier_block __rcu *head;
};
@@ -78,7 +78,7 @@ struct srcu_notifier_head {
};
#define ATOMIC_INIT_NOTIFIER_HEAD(name) do { \
- spin_lock_init(&(name)->lock); \
+ raw_spin_lock_init(&(name)->lock); \
(name)->head = NULL; \
} while (0)
#define BLOCKING_INIT_NOTIFIER_HEAD(name) do { \
@@ -95,7 +95,7 @@ extern void srcu_init_notifier_head(stru
cleanup_srcu_struct(&(name)->srcu);
#define ATOMIC_NOTIFIER_INIT(name) { \
- .lock = __SPIN_LOCK_UNLOCKED(name.lock), \
+ .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \
.head = NULL }
#define BLOCKING_NOTIFIER_INIT(name) { \
.rwsem = __RWSEM_INITIALIZER((name).rwsem), \
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -142,9 +142,9 @@ int atomic_notifier_chain_register(struc
unsigned long flags;
int ret;
- spin_lock_irqsave(&nh->lock, flags);
+ raw_spin_lock_irqsave(&nh->lock, flags);
ret = notifier_chain_register(&nh->head, n);
- spin_unlock_irqrestore(&nh->lock, flags);
+ raw_spin_unlock_irqrestore(&nh->lock, flags);
return ret;
}
EXPORT_SYMBOL_GPL(atomic_notifier_chain_register);
@@ -164,9 +164,9 @@ int atomic_notifier_chain_unregister(str
unsigned long flags;
int ret;
- spin_lock_irqsave(&nh->lock, flags);
+ raw_spin_lock_irqsave(&nh->lock, flags);
ret = notifier_chain_unregister(&nh->head, n);
- spin_unlock_irqrestore(&nh->lock, flags);
+ raw_spin_unlock_irqrestore(&nh->lock, flags);
synchronize_rcu();
return ret;
}
@@ -182,9 +182,9 @@ int atomic_notifier_call_chain_robust(st
* Musn't use RCU; because then the notifier list can
* change between the up and down traversal.
*/
- spin_lock_irqsave(&nh->lock, flags);
+ raw_spin_lock_irqsave(&nh->lock, flags);
ret = notifier_call_chain_robust(&nh->head, val_up, val_down, v);
- spin_unlock_irqrestore(&nh->lock, flags);
+ raw_spin_unlock_irqrestore(&nh->lock, flags);
return ret;
}
|