summaryrefslogtreecommitdiffstats
path: root/kernel/sched/idle.c
blob: d5aaf5eb45319a66412aea8e9cbbd43b2805cada (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
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
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
/*
 * Generic entry point for the idle threads
 */
#include <linux/sched.h>
#include <linux/cpu.h>
#include <linux/cpuidle.h>
#include <linux/tick.h>
#include <linux/mm.h>
#include <linux/stackprotector.h>

#include <asm/tlb.h>

#include <trace/events/power.h>

static int __read_mostly cpu_idle_force_poll;

void cpu_idle_poll_ctrl(bool enable)
{
	if (enable) {
		cpu_idle_force_poll++;
	} else {
		cpu_idle_force_poll--;
		WARN_ON_ONCE(cpu_idle_force_poll < 0);
	}
}

#ifdef CONFIG_GENERIC_IDLE_POLL_SETUP
static int __init cpu_idle_poll_setup(char *__unused)
{
	cpu_idle_force_poll = 1;
	return 1;
}
__setup("nohlt", cpu_idle_poll_setup);

static int __init cpu_idle_nopoll_setup(char *__unused)
{
	cpu_idle_force_poll = 0;
	return 1;
}
__setup("hlt", cpu_idle_nopoll_setup);
#endif

static inline int cpu_idle_poll(void)
{
	rcu_idle_enter();
	trace_cpu_idle_rcuidle(0, smp_processor_id());
	local_irq_enable();
	while (!tif_need_resched())
		cpu_relax();
	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
	rcu_idle_exit();
	return 1;
}

/* Weak implementations for optional arch specific functions */
void __weak arch_cpu_idle_prepare(void) { }
void __weak arch_cpu_idle_enter(void) { }
void __weak arch_cpu_idle_exit(void) { }
void __weak arch_cpu_idle_dead(void) { }
void __weak arch_cpu_idle(void)
{
	cpu_idle_force_poll = 1;
	local_irq_enable();
}

#ifdef CONFIG_CPU_IDLE
/**
 * cpuidle_idle_call - the main idle function
 *
 * NOTE: no locks or semaphores should be used here
 * return non-zero on failure
 */
static int cpuidle_idle_call(void)
{
	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
	int next_state, entered_state, ret;
	bool broadcast;

	ret = cpuidle_enabled(drv, dev);
	if (ret < 0)
		return ret;

	/* ask the governor for the next state */
	next_state = cpuidle_select(drv, dev);

	if (need_resched()) {
		dev->last_residency = 0;
		/* give the governor an opportunity to reflect on the outcome */
		cpuidle_reflect(dev, next_state);
		local_irq_enable();
		return 0;
	}

	broadcast = !!(drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP);

	if (broadcast &&
	    clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu))
		return -EBUSY;

	trace_cpu_idle_rcuidle(next_state, dev->cpu);

	entered_state = cpuidle_enter(drv, dev, next_state);

	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);

	if (broadcast)
		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);

	/* give the governor an opportunity to reflect on the outcome */
	cpuidle_reflect(dev, entered_state);

	return 0;
}
#else
static inline int cpuidle_idle_call(void)
{
	return -ENODEV;
}
#endif

/*
 * Generic idle loop implementation
 */
static void cpu_idle_loop(void)
{
	while (1) {
		tick_nohz_idle_enter();

		while (!need_resched()) {
			check_pgt_cache();
			rmb();

			if (cpu_is_offline(smp_processor_id()))
				arch_cpu_idle_dead();

			local_irq_disable();
			arch_cpu_idle_enter();

			/*
			 * In poll mode we reenable interrupts and spin.
			 *
			 * Also if we detected in the wakeup from idle
			 * path that the tick broadcast device expired
			 * for us, we don't want to go deep idle as we
			 * know that the IPI is going to arrive right
			 * away
			 */
			if (cpu_idle_force_poll || tick_check_broadcast_expired()) {
				cpu_idle_poll();
			} else {
				if (!current_clr_polling_and_test()) {
					stop_critical_timings();
					rcu_idle_enter();
					if (cpuidle_idle_call())
						arch_cpu_idle();
					if (WARN_ON_ONCE(irqs_disabled()))
						local_irq_enable();
					rcu_idle_exit();
					start_critical_timings();
				} else {
					local_irq_enable();
				}
				__current_set_polling();
			}
			arch_cpu_idle_exit();
		}

		/*
		 * Since we fell out of the loop above, we know
		 * TIF_NEED_RESCHED must be set, propagate it into
		 * PREEMPT_NEED_RESCHED.
		 *
		 * This is required because for polling idle loops we will
		 * not have had an IPI to fold the state for us.
		 */
		preempt_set_need_resched();
		tick_nohz_idle_exit();
		schedule_preempt_disabled();
	}
}

void cpu_startup_entry(enum cpuhp_state state)
{
	/*
	 * This #ifdef needs to die, but it's too late in the cycle to
	 * make this generic (arm and sh have never invoked the canary
	 * init for the non boot cpus!). Will be fixed in 3.11
	 */
#ifdef CONFIG_X86
	/*
	 * If we're the non-boot CPU, nothing set the stack canary up
	 * for us. The boot CPU already has it initialized but no harm
	 * in doing it again. This is a good place for updating it, as
	 * we wont ever return from this function (so the invalid
	 * canaries already on the stack wont ever trigger).
	 */
	boot_init_stack_canary();
#endif
	__current_set_polling();
	arch_cpu_idle_prepare();
	cpu_idle_loop();
}