aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/cpu/mcheck/therm_throt.c
blob: d5ae2243f0b959bf26839c476850faec8a6a4476 (plain) (blame)
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
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
/*
 *
 * Thermal throttle event support code (such as syslog messaging and rate
 * limiting) that was factored out from x86_64 (mce_intel.c) and i386 (p4.c).
 * This allows consistent reporting of CPU thermal throttle events.
 *
 * Maintains a counter in /sys that keeps track of the number of thermal
 * events, such that the user knows how bad the thermal problem might be
 * (since the logging to syslog and mcelog is rate limited).
 *
 * Author: Dmitriy Zavin (dmitriyz@google.com)
 *
 * Credits: Adapted from Zwane Mwaikambo's original code in mce_intel.c.
 *          Inspired by Ross Biro's and Al Borchers' counter code.
 */

#include <linux/percpu.h>
#include <linux/sysdev.h>
#include <linux/cpu.h>
#include <asm/cpu.h>
#include <linux/notifier.h>
#include <linux/jiffies.h>
#include <asm/therm_throt.h>

/* How long to wait between reporting thermal events */
#define CHECK_INTERVAL              (300 * HZ)

static DEFINE_PER_CPU(__u64, next_check) = INITIAL_JIFFIES;
static DEFINE_PER_CPU(unsigned long, thermal_throttle_count);
atomic_t therm_throt_en = ATOMIC_INIT(0);

#ifdef CONFIG_SYSFS
#define define_therm_throt_sysdev_one_ro(_name)                              \
        static SYSDEV_ATTR(_name, 0444, therm_throt_sysdev_show_##_name, NULL)

#define define_therm_throt_sysdev_show_func(name)                            \
static ssize_t therm_throt_sysdev_show_##name(struct sys_device *dev,        \
					struct sysdev_attribute *attr,	     \
                                              char *buf)                     \
{                                                                            \
	unsigned int cpu = dev->id;                                          \
	ssize_t ret;                                                         \
                                                                             \
	preempt_disable();              /* CPU hotplug */                    \
	if (cpu_online(cpu))                                                 \
		ret = sprintf(buf, "%lu\n",                                  \
			      per_cpu(thermal_throttle_##name, cpu));        \
	else                                                                 \
		ret = 0;                                                     \
	preempt_enable();                                                    \
                                                                             \
	return ret;                                                          \
}

define_therm_throt_sysdev_show_func(count);
define_therm_throt_sysdev_one_ro(count);

static struct attribute *thermal_throttle_attrs[] = {
	&attr_count.attr,
	NULL
};

static struct attribute_group thermal_throttle_attr_group = {
	.attrs = thermal_throttle_attrs,
	.name = "thermal_throttle"
};
#endif /* CONFIG_SYSFS */

/***
 * therm_throt_process - Process thermal throttling event from interrupt
 * @curr: Whether the condition is current or not (boolean), since the
 *        thermal interrupt normally gets called both when the thermal
 *        event begins and once the event has ended.
 *
 * This function is called by the thermal interrupt after the
 * IRQ has been acknowledged.
 *
 * It will take care of rate limiting and printing messages to the syslog.
 *
 * Returns: 0 : Event should NOT be further logged, i.e. still in
 *              "timeout" from previous log message.
 *          1 : Event should be logged further, and a message has been
 *              printed to the syslog.
 */
int therm_throt_process(int curr)
{
	unsigned int cpu = smp_processor_id();
	__u64 tmp_jiffs = get_jiffies_64();

	if (curr)
		__get_cpu_var(thermal_throttle_count)++;

	if (time_before64(tmp_jiffs, __get_cpu_var(next_check)))
		return 0;

	__get_cpu_var(next_check) = tmp_jiffs + CHECK_INTERVAL;

	/* if we just entered the thermal event */
	if (curr) {
		printk(KERN_CRIT "CPU%d: Temperature above threshold, "
		       "cpu clock throttled (total events = %lu)\n", cpu,
		       __get_cpu_var(thermal_throttle_count));

		add_taint(TAINT_MACHINE_CHECK);
	} else {
		printk(KERN_CRIT "CPU%d: Temperature/speed normal\n", cpu);
	}

	return 1;
}

#ifdef CONFIG_SYSFS
/* Add/Remove thermal_throttle interface for CPU device */
static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev)
{
	return sysfs_create_group(&sys_dev->kobj, &thermal_throttle_attr_group);
}

static __cpuinit void thermal_throttle_remove_dev(struct sys_device *sys_dev)
{
	sysfs_remove_group(&sys_dev->kobj, &thermal_throttle_attr_group);
}

/* Mutex protecting device creation against CPU hotplug */
static DEFINE_MUTEX(therm_cpu_lock);

/* Get notified when a cpu comes on/off. Be hotplug friendly. */
static __cpuinit int thermal_throttle_cpu_callback(struct notifier_block *nfb,
						   unsigned long action,
						   void *hcpu)
{
	unsigned int cpu = (unsigned long)hcpu;
	struct sys_device *sys_dev;
	int err = 0;

	sys_dev = get_cpu_sysdev(cpu);
	switch (action) {
	case CPU_UP_PREPARE:
	case CPU_UP_PREPARE_FROZEN:
		mutex_lock(&therm_cpu_lock);
		err = thermal_throttle_add_dev(sys_dev);
		mutex_unlock(&therm_cpu_lock);
		WARN_ON(err);
		break;
	case CPU_UP_CANCELED:
	case CPU_UP_CANCELED_FROZEN:
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		mutex_lock(&therm_cpu_lock);
		thermal_throttle_remove_dev(sys_dev);
		mutex_unlock(&therm_cpu_lock);
		break;
	}
	return err ? NOTIFY_BAD : NOTIFY_OK;
}

static struct notifier_block thermal_throttle_cpu_notifier __cpuinitdata =
{
	.notifier_call = thermal_throttle_cpu_callback,
};

static __init int thermal_throttle_init_device(void)
{
	unsigned int cpu = 0;
	int err;

	if (!atomic_read(&therm_throt_en))
		return 0;

	register_hotcpu_notifier(&thermal_throttle_cpu_notifier);

#ifdef CONFIG_HOTPLUG_CPU
	mutex_lock(&therm_cpu_lock);
#endif
	/* connect live CPUs to sysfs */
	for_each_online_cpu(cpu) {
		err = thermal_throttle_add_dev(get_cpu_sysdev(cpu));
		WARN_ON(err);
	}
#ifdef CONFIG_HOTPLUG_CPU
	mutex_unlock(&therm_cpu_lock);
#endif

	return 0;
}

device_initcall(thermal_throttle_init_device);
#endif /* CONFIG_SYSFS */