summaryrefslogtreecommitdiff
path: root/kernel/context_tracking.c
blob: 839d377d0da51768f14f0521a50b71bb3205116b (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
204
205
206
207
208
209
210
211
212
213
214
215
/*
 * Context tracking: Probe on high level context boundaries such as kernel
 * and userspace. This includes syscalls and exceptions entry/exit.
 *
 * This is used by RCU to remove its dependency on the timer tick while a CPU
 * runs in userspace.
 *
 *  Started by Frederic Weisbecker:
 *
 * Copyright (C) 2012 Red Hat, Inc., Frederic Weisbecker <fweisbec@redhat.com>
 *
 * Many thanks to Gilad Ben-Yossef, Paul McKenney, Ingo Molnar, Andrew Morton,
 * Steven Rostedt, Peter Zijlstra for suggestions and improvements.
 *
 */

#include <linux/context_tracking.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/hardirq.h>
#include <linux/export.h>

struct static_key context_tracking_enabled = STATIC_KEY_INIT_FALSE;

DEFINE_PER_CPU(struct context_tracking, context_tracking);

void context_tracking_cpu_set(int cpu)
{
	if (!per_cpu(context_tracking.active, cpu)) {
		per_cpu(context_tracking.active, cpu) = true;
		static_key_slow_inc(&context_tracking_enabled);
	}
}

/**
 * user_enter - Inform the context tracking that the CPU is going to
 *              enter userspace mode.
 *
 * This function must be called right before we switch from the kernel
 * to userspace, when it's guaranteed the remaining kernel instructions
 * to execute won't use any RCU read side critical section because this
 * function sets RCU in extended quiescent state.
 */
void user_enter(void)
{
	unsigned long flags;

	/*
	 * Some contexts may involve an exception occuring in an irq,
	 * leading to that nesting:
	 * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit()
	 * This would mess up the dyntick_nesting count though. And rcu_irq_*()
	 * helpers are enough to protect RCU uses inside the exception. So
	 * just return immediately if we detect we are in an IRQ.
	 */
	if (in_interrupt())
		return;

	/* Kernel threads aren't supposed to go to userspace */
	WARN_ON_ONCE(!current->mm);

	local_irq_save(flags);
	if ( __this_cpu_read(context_tracking.state) != IN_USER) {
		if (__this_cpu_read(context_tracking.active)) {
			/*
			 * At this stage, only low level arch entry code remains and
			 * then we'll run in userspace. We can assume there won't be
			 * any RCU read-side critical section until the next call to
			 * user_exit() or rcu_irq_enter(). Let's remove RCU's dependency
			 * on the tick.
			 */
			vtime_user_enter(current);
			rcu_user_enter();
		}
		/*
		 * Even if context tracking is disabled on this CPU, because it's outside
		 * the full dynticks mask for example, we still have to keep track of the
		 * context transitions and states to prevent inconsistency on those of
		 * other CPUs.
		 * If a task triggers an exception in userspace, sleep on the exception
		 * handler and then migrate to another CPU, that new CPU must know where
		 * the exception returns by the time we call exception_exit().
		 * This information can only be provided by the previous CPU when it called
		 * exception_enter().
		 * OTOH we can spare the calls to vtime and RCU when context_tracking.active
		 * is false because we know that CPU is not tickless.
		 */
		__this_cpu_write(context_tracking.state, IN_USER);
	}
	local_irq_restore(flags);
}

#ifdef CONFIG_PREEMPT
/**
 * preempt_schedule_context - preempt_schedule called by tracing
 *
 * The tracing infrastructure uses preempt_enable_notrace to prevent
 * recursion and tracing preempt enabling caused by the tracing
 * infrastructure itself. But as tracing can happen in areas coming
 * from userspace or just about to enter userspace, a preempt enable
 * can occur before user_exit() is called. This will cause the scheduler
 * to be called when the system is still in usermode.
 *
 * To prevent this, the preempt_enable_notrace will use this function
 * instead of preempt_schedule() to exit user context if needed before
 * calling the scheduler.
 */
void __sched notrace preempt_schedule_context(void)
{
	enum ctx_state prev_ctx;

	if (likely(!preemptible()))
		return;

	/*
	 * Need to disable preemption in case user_exit() is traced
	 * and the tracer calls preempt_enable_notrace() causing
	 * an infinite recursion.
	 */
	preempt_disable_notrace();
	prev_ctx = exception_enter();
	preempt_enable_no_resched_notrace();

	preempt_schedule();

	preempt_disable_notrace();
	exception_exit(prev_ctx);
	preempt_enable_notrace();
}
EXPORT_SYMBOL_GPL(preempt_schedule_context);
#endif /* CONFIG_PREEMPT */

/**
 * user_exit - Inform the context tracking that the CPU is
 *             exiting userspace mode and entering the kernel.
 *
 * This function must be called after we entered the kernel from userspace
 * before any use of RCU read side critical section. This potentially include
 * any high level kernel code like syscalls, exceptions, signal handling, etc...
 *
 * This call supports re-entrancy. This way it can be called from any exception
 * handler without needing to know if we came from userspace or not.
 */
void user_exit(void)
{
	unsigned long flags;

	if (in_interrupt())
		return;

	local_irq_save(flags);
	if (__this_cpu_read(context_tracking.state) == IN_USER) {
		if (__this_cpu_read(context_tracking.active)) {
			/*
			 * We are going to run code that may use RCU. Inform
			 * RCU core about that (ie: we may need the tick again).
			 */
			rcu_user_exit();
			vtime_user_exit(current);
		}
		__this_cpu_write(context_tracking.state, IN_KERNEL);
	}
	local_irq_restore(flags);
}

#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
void guest_enter(void)
{
	if (vtime_accounting_enabled())
		vtime_guest_enter(current);
	else
		current->flags |= PF_VCPU;
}
EXPORT_SYMBOL_GPL(guest_enter);

void guest_exit(void)
{
	if (vtime_accounting_enabled())
		vtime_guest_exit(current);
	else
		current->flags &= ~PF_VCPU;
}
EXPORT_SYMBOL_GPL(guest_exit);
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */


/**
 * context_tracking_task_switch - context switch the syscall callbacks
 * @prev: the task that is being switched out
 * @next: the task that is being switched in
 *
 * The context tracking uses the syscall slow path to implement its user-kernel
 * boundaries probes on syscalls. This way it doesn't impact the syscall fast
 * path on CPUs that don't do context tracking.
 *
 * But we need to clear the flag on the previous task because it may later
 * migrate to some CPU that doesn't do the context tracking. As such the TIF
 * flag may not be desired there.
 */
void context_tracking_task_switch(struct task_struct *prev,
			     struct task_struct *next)
{
	clear_tsk_thread_flag(prev, TIF_NOHZ);
	set_tsk_thread_flag(next, TIF_NOHZ);
}

#ifdef CONFIG_CONTEXT_TRACKING_FORCE
void __init context_tracking_init(void)
{
	int cpu;

	for_each_possible_cpu(cpu)
		context_tracking_cpu_set(cpu);
}
#endif