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
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
|
From f02e82a420b85d84d71af75e0079f12ce87511d6 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 10 Nov 2016 18:44:46 +0100
Subject: [PATCH 048/154] x86/mcheck: Move CPU_ONLINE and CPU_DOWN_PREPARE to
hotplug state machine
The CPU_ONLINE and CPU_DOWN_PREPARE look fully symmetrical and could be move
to the hotplug state machine.
On a failure during registration we have the tear down callback invoked
(mce_cpu_pre_down()) so there should be no timer around and so no need to need
keep notifier installed (this was the reason according to the comment why the
notifier was registered despite of errors).
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: rt@linutronix.de
Cc: linux-edac@vger.kernel.org
Link: http://lkml.kernel.org/r/20161110174447.11848-7-bigeasy@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sudheesh Mavila <sudheesh.mavila@amd.com>
---
arch/x86/kernel/cpu/mcheck/mce.c | 78 +++++++++++++++++++---------------------
1 file changed, 36 insertions(+), 42 deletions(-)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index d09f4bd..67a2dcd 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -2555,21 +2555,8 @@ static int
mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
{
unsigned int cpu = (unsigned long)hcpu;
- struct timer_list *t = &per_cpu(mce_timer, cpu);
switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_ONLINE:
- case CPU_DOWN_FAILED:
-
- mce_device_create(cpu);
-
- if (mce_threshold_create_device(cpu)) {
- mce_device_remove(cpu);
- return NOTIFY_BAD;
- }
- mce_reenable_cpu();
- mce_start_timer(cpu, t);
- break;
case CPU_DEAD:
mce_intel_hcpu_update(cpu);
@@ -2578,17 +2565,41 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
cmci_rediscover();
break;
case CPU_DOWN_PREPARE:
- mce_disable_cpu();
- del_timer_sync(t);
- mce_threshold_remove_device(cpu);
- mce_device_remove(cpu);
break;
}
return NOTIFY_OK;
}
+static int mce_cpu_online(unsigned int cpu)
+{
+ struct timer_list *t = &per_cpu(mce_timer, cpu);
+ int ret;
+
+ mce_device_create(cpu);
+
+ ret = mce_threshold_create_device(cpu);
+ if (ret) {
+ mce_device_remove(cpu);
+ return ret;
+ }
+ mce_reenable_cpu();
+ mce_start_timer(cpu, t);
+ return 0;
+}
+
+static int mce_cpu_pre_down(unsigned int cpu)
+{
+ struct timer_list *t = &per_cpu(mce_timer, cpu);
+
+ mce_disable_cpu();
+ del_timer_sync(t);
+ mce_threshold_remove_device(cpu);
+ mce_device_remove(cpu);
+ return 0;
+}
+
static struct notifier_block mce_cpu_notifier = {
.notifier_call = mce_cpu_callback,
};
@@ -2613,8 +2624,8 @@ static __init void mce_init_banks(void)
static __init int mcheck_init_device(void)
{
+ enum cpuhp_state hp_online;
int err;
- int i = 0;
if (!mce_available(&boot_cpu_data)) {
err = -EIO;
@@ -2632,21 +2643,13 @@ static __init int mcheck_init_device(void)
if (err)
goto err_out_mem;
- cpu_notifier_register_begin();
- for_each_online_cpu(i) {
- err = mce_device_create(i);
- if (err) {
- /*
- * Register notifier anyway (and do not unreg it) so
- * that we don't leave undeleted timers, see notifier
- * callback above.
- */
- __register_hotcpu_notifier(&mce_cpu_notifier);
- cpu_notifier_register_done();
- goto err_device_create;
- }
- }
+ err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/mce:online",
+ mce_cpu_online, mce_cpu_pre_down);
+ if (err < 0)
+ goto err_out_mem;
+ hp_online = err;
+ cpu_notifier_register_begin();
__register_hotcpu_notifier(&mce_cpu_notifier);
cpu_notifier_register_done();
@@ -2661,16 +2664,7 @@ static __init int mcheck_init_device(void)
err_register:
unregister_syscore_ops(&mce_syscore_ops);
-
-err_device_create:
- /*
- * We didn't keep track of which devices were created above, but
- * even if we had, the set of online cpus might have changed.
- * Play safe and remove for every possible cpu, since
- * mce_device_remove() will do the right thing.
- */
- for_each_possible_cpu(i)
- mce_device_remove(i);
+ cpuhp_remove_state(hp_online);
err_out_mem:
free_cpumask_var(mce_device_initialized);
--
2.7.4
|
