context_tracking.c 6.79 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 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59
static bool context_tracking_recursion_enter(void)
{
	int recursion;

	recursion = __this_cpu_inc_return(context_tracking.recursion);
	if (recursion == 1)
		return true;

	WARN_ONCE((recursion < 1), "Invalid context tracking recursion value %d\n", recursion);
	__this_cpu_dec(context_tracking.recursion);

	return false;
}

static void context_tracking_recursion_exit(void)
{
	__this_cpu_dec(context_tracking.recursion);
}

60
/**
61 62
 * context_tracking_enter - Inform the context tracking that the CPU is going
 *                          enter user or guest space mode.
63 64
 *
 * This function must be called right before we switch from the kernel
65 66 67
 * to user or guest space, 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.
68
 */
69
void context_tracking_enter(enum ctx_state state)
70 71 72
{
	unsigned long flags;

73 74 75
	/*
	 * 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
76 77
	 * go further. Repeat the check here until they support the inline static
	 * key check.
78
	 */
79
	if (!context_tracking_is_enabled())
80 81
		return;

82 83 84 85 86 87 88 89 90 91 92
	/*
	 * 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;

93
	/* Kernel threads aren't supposed to go to userspace */
94 95 96
	WARN_ON_ONCE(!current->mm);

	local_irq_save(flags);
97 98 99
	if (!context_tracking_recursion_enter())
		goto out_irq_restore;

100
	if ( __this_cpu_read(context_tracking.state) != state) {
101 102 103 104 105 106 107 108
		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.
			 */
109 110 111 112
			if (state == CONTEXT_USER) {
				trace_user_enter(0);
				vtime_user_enter(current);
			}
113 114
			rcu_user_enter();
		}
115
		/*
116 117 118 119 120 121 122 123 124 125 126
		 * 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.
127
		 */
128
		__this_cpu_write(context_tracking.state, state);
129
	}
130 131
	context_tracking_recursion_exit();
out_irq_restore:
132 133
	local_irq_restore(flags);
}
134
NOKPROBE_SYMBOL(context_tracking_enter);
135
EXPORT_SYMBOL_GPL(context_tracking_enter);
136 137 138 139 140

void context_tracking_user_enter(void)
{
	context_tracking_enter(CONTEXT_USER);
}
141
NOKPROBE_SYMBOL(context_tracking_user_enter);
142

143
/**
144 145
 * context_tracking_exit - Inform the context tracking that the CPU is
 *                         exiting user or guest mode and entering the kernel.
146
 *
147 148 149 150
 * This function must be called after we entered the kernel from user or
 * guest space before any use of RCU read side critical section. This
 * potentially include any high level kernel code like syscalls, exceptions,
 * signal handling, etc...
151 152 153 154
 *
 * 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.
 */
155
void context_tracking_exit(enum ctx_state state)
156 157 158
{
	unsigned long flags;

159
	if (!context_tracking_is_enabled())
160 161
		return;

162 163 164 165
	if (in_interrupt())
		return;

	local_irq_save(flags);
166 167 168
	if (!context_tracking_recursion_enter())
		goto out_irq_restore;

169
	if (__this_cpu_read(context_tracking.state) == state) {
170 171 172 173 174 175
		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();
176 177 178 179
			if (state == CONTEXT_USER) {
				vtime_user_exit(current);
				trace_user_exit(0);
			}
180
		}
181
		__this_cpu_write(context_tracking.state, CONTEXT_KERNEL);
182
	}
183 184
	context_tracking_recursion_exit();
out_irq_restore:
185 186
	local_irq_restore(flags);
}
187
NOKPROBE_SYMBOL(context_tracking_exit);
188
EXPORT_SYMBOL_GPL(context_tracking_exit);
189 190 191 192 193

void context_tracking_user_exit(void)
{
	context_tracking_exit(CONTEXT_USER);
}
194
NOKPROBE_SYMBOL(context_tracking_user_exit);
195

196
/**
197
 * __context_tracking_task_switch - context switch the syscall callbacks
198 199 200 201 202 203 204 205 206 207 208
 * @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.
 */
209 210
void __context_tracking_task_switch(struct task_struct *prev,
				    struct task_struct *next)
211
{
212 213
	clear_tsk_thread_flag(prev, TIF_NOHZ);
	set_tsk_thread_flag(next, TIF_NOHZ);
214
}
215 216 217 218 219 220 221 222 223 224

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

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