aboutsummaryrefslogtreecommitdiff
path: root/kernel/context_tracking.c
blob: 65349f07b8782a19f13014e66b8ff8ac0e7a5ecf (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
/*
 * 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/kvm_host.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/hardirq.h>
#include <linux/export.h>

DEFINE_PER_CPU(struct context_tracking, context_tracking) = {
#ifdef CONFIG_CONTEXT_TRACKING_FORCE
	.active = true,
#endif
};

/**
 * 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.active) &&
	    __this_cpu_read(context_tracking.state) != IN_USER) {
		/*
		 * 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();
		__this_cpu_write(context_tracking.state, IN_USER);
	}
	local_irq_restore(flags);
}


/**
 * 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) {
		/*
		 * 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);
}

void guest_enter(void)
{
	if (vtime_accounting_enabled())
		vtime_guest_enter(current);
	else
		__guest_enter();
}
EXPORT_SYMBOL_GPL(guest_enter);

void guest_exit(void)
{
	if (vtime_accounting_enabled())
		vtime_guest_exit(current);
	else
		__guest_exit();
}
EXPORT_SYMBOL_GPL(guest_exit);


/**
 * 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)
{
	if (__this_cpu_read(context_tracking.active)) {
		clear_tsk_thread_flag(prev, TIF_NOHZ);
		set_tsk_thread_flag(next, TIF_NOHZ);
	}
}