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
|
From d85ab7a0baf704638606240769ae82028b39d4e4 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 10 Nov 2016 18:44:45 +0100
Subject: [PATCH 047/154] x86/mcheck: Reorganize the hotplug callbacks
Initially I wanted to remove mcheck_cpu_init() from identify_cpu() and let it
become an independent early hotplug callback. The main problem here was that
the init on the boot CPU may happen too late
(device_initcall_sync(mcheck_init_device)) and nobody wanted to risk receiving
and MCE event at boot time leading to a shutdown (if the MCE feature is not yet
enabled).
Here is attempt two: the timming stays as-is but the ordering of the functions
is changed:
- mcheck_cpu_init() (which is run from identify_cpu()) will setup the timer
struct but won't fire the timer. This is moved to CPU_ONLINE since its
cleanup part is in CPU_DOWN_PREPARE. So if it is okay to stop the timer early
in the shutdown phase, it should be okay to start it late in the bring up phase.
- CPU_DOWN_PREPARE disables the MCE feature flags for !INTEL CPUs in
mce_disable_cpu(). If a failure occures it would be re-enabled on all vendor
CPUs (including Intel where it was not disabled during shutdown). To keep this
working I am moving it to CPU_ONLINE. smp_call_function_single() is dropped
beause the notifier runs nowdays on the target CPU.
- CPU_ONLINE is invoking mce_device_create() + mce_threshold_create_device()
but its cleanup part is in CPU_DEAD (mce_threshold_remove_device() and
mce_device_remove()). In order to keep this symmetrical I am moving the clean
up from CPU_DEAD to CPU_DOWN_PREPARE.
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/20161110174447.11848-6-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 | 36 ++++++++++++++++++++----------------
1 file changed, 20 insertions(+), 16 deletions(-)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index ef00b27..d09f4bd 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1788,6 +1788,14 @@ static void mce_start_timer(unsigned int cpu, struct timer_list *t)
add_timer_on(t, cpu);
}
+static void __mcheck_cpu_setup_timer(void)
+{
+ struct timer_list *t = this_cpu_ptr(&mce_timer);
+ unsigned int cpu = smp_processor_id();
+
+ setup_pinned_timer(t, mce_timer_fn, cpu);
+}
+
static void __mcheck_cpu_init_timer(void)
{
struct timer_list *t = this_cpu_ptr(&mce_timer);
@@ -1839,7 +1847,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
__mcheck_cpu_init_generic();
__mcheck_cpu_init_vendor(c);
__mcheck_cpu_init_clear_banks();
- __mcheck_cpu_init_timer();
+ __mcheck_cpu_setup_timer();
}
/*
@@ -2514,28 +2522,25 @@ static void mce_device_remove(unsigned int cpu)
}
/* Make sure there are no machine checks on offlined CPUs. */
-static void mce_disable_cpu(void *h)
+static void mce_disable_cpu(void)
{
- unsigned long action = *(unsigned long *)h;
-
if (!mce_available(raw_cpu_ptr(&cpu_info)))
return;
- if (!(action & CPU_TASKS_FROZEN))
+ if (!cpuhp_tasks_frozen)
cmci_clear();
vendor_disable_error_reporting();
}
-static void mce_reenable_cpu(void *h)
+static void mce_reenable_cpu(void)
{
- unsigned long action = *(unsigned long *)h;
int i;
if (!mce_available(raw_cpu_ptr(&cpu_info)))
return;
- if (!(action & CPU_TASKS_FROZEN))
+ if (!cpuhp_tasks_frozen)
cmci_reenable();
for (i = 0; i < mca_cfg.banks; i++) {
struct mce_bank *b = &mce_banks[i];
@@ -2554,6 +2559,7 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_ONLINE:
+ case CPU_DOWN_FAILED:
mce_device_create(cpu);
@@ -2561,11 +2567,10 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
mce_device_remove(cpu);
return NOTIFY_BAD;
}
-
+ mce_reenable_cpu();
+ mce_start_timer(cpu, t);
break;
case CPU_DEAD:
- mce_threshold_remove_device(cpu);
- mce_device_remove(cpu);
mce_intel_hcpu_update(cpu);
/* intentionally ignoring frozen here */
@@ -2573,12 +2578,11 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
cmci_rediscover();
break;
case CPU_DOWN_PREPARE:
- smp_call_function_single(cpu, mce_disable_cpu, &action, 1);
+ mce_disable_cpu();
del_timer_sync(t);
- break;
- case CPU_DOWN_FAILED:
- smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
- mce_start_timer(cpu, t);
+
+ mce_threshold_remove_device(cpu);
+ mce_device_remove(cpu);
break;
}
--
2.7.4
|
