context_tracking.c 5.71 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
/*
 * 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.
 *
 */

17 18 19 20
#include <linux/context_tracking.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/hardirq.h>
21
#include <linux/export.h>
22
#include <linux/kprobes.h>
23

24 25 26
#define CREATE_TRACE_POINTS
#include <trace/events/context_tracking.h>

27
struct static_key context_tracking_enabled = STATIC_KEY_INIT_FALSE;
28
EXPORT_SYMBOL_GPL(context_tracking_enabled);
29 30

DEFINE_PER_CPU(struct context_tracking, context_tracking);
31
EXPORT_SYMBOL_GPL(context_tracking);
32

33 34
void context_tracking_cpu_set(int cpu)
{
35 36 37 38
	if (!per_cpu(context_tracking.active, cpu)) {
		per_cpu(context_tracking.active, cpu) = true;
		static_key_slow_inc(&context_tracking_enabled);
	}
39 40
}

41
/**
42 43
 * context_tracking_user_enter - Inform the context tracking that the CPU is going to
 *                               enter userspace mode.
44 45 46 47 48 49
 *
 * 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.
 */
50
void context_tracking_user_enter(void)
51 52 53
{
	unsigned long flags;

54 55 56
	/*
	 * Repeat the user_enter() check here because some archs may be calling
	 * this from asm and if no CPU needs context tracking, they shouldn't
57 58
	 * go further. Repeat the check here until they support the inline static
	 * key check.
59
	 */
60
	if (!context_tracking_is_enabled())
61 62
		return;

63 64 65 66 67 68 69 70 71 72 73
	/*
	 * 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;

74
	/* Kernel threads aren't supposed to go to userspace */
75 76 77
	WARN_ON_ONCE(!current->mm);

	local_irq_save(flags);
78 79
	if ( __this_cpu_read(context_tracking.state) != IN_USER) {
		if (__this_cpu_read(context_tracking.active)) {
80
			trace_user_enter(0);
81 82 83 84 85 86 87 88 89 90
			/*
			 * 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();
		}
91
		/*
92 93 94 95 96 97 98 99 100 101 102
		 * 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.
103
		 */
104
		__this_cpu_write(context_tracking.state, IN_USER);
105 106 107
	}
	local_irq_restore(flags);
}
108
NOKPROBE_SYMBOL(context_tracking_user_enter);
109

110
/**
111 112
 * context_tracking_user_exit - Inform the context tracking that the CPU is
 *                              exiting userspace mode and entering the kernel.
113 114 115 116 117 118 119 120
 *
 * 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.
 */
121
void context_tracking_user_exit(void)
122 123 124
{
	unsigned long flags;

125
	if (!context_tracking_is_enabled())
126 127
		return;

128 129 130 131 132
	if (in_interrupt())
		return;

	local_irq_save(flags);
	if (__this_cpu_read(context_tracking.state) == IN_USER) {
133 134 135 136 137 138 139
		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);
140
			trace_user_exit(0);
141
		}
142
		__this_cpu_write(context_tracking.state, IN_KERNEL);
143 144 145
	}
	local_irq_restore(flags);
}
146
NOKPROBE_SYMBOL(context_tracking_user_exit);
147

148
/**
149
 * __context_tracking_task_switch - context switch the syscall callbacks
150 151 152 153 154 155 156 157 158 159 160
 * @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.
 */
161 162
void __context_tracking_task_switch(struct task_struct *prev,
				    struct task_struct *next)
163
{
164 165
	clear_tsk_thread_flag(prev, TIF_NOHZ);
	set_tsk_thread_flag(next, TIF_NOHZ);
166
}
167 168 169 170 171 172 173 174 175 176

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

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