summaryrefslogtreecommitdiff
path: root/kernel/irq_work.c
blob: 828cc30774bc4d76f498503b083dad428dbf0baa (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra
 *
 * Provides a framework for enqueueing and running callbacks from hardirq
 * context. The enqueueing is NMI-safe.
 */

#include <linux/bug.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/irq_work.h>
#include <linux/percpu.h>
#include <linux/hardirq.h>
#include <linux/irqflags.h>
#include <linux/sched.h>
#include <linux/tick.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/smp.h>
#include <asm/processor.h>


static DEFINE_PER_CPU(struct llist_head, raised_list);
static DEFINE_PER_CPU(struct llist_head, lazy_list);

/*
 * Claim the entry so that no one else will poke at it.
 */
static bool irq_work_claim(struct irq_work *work)
{
	int oflags;

	oflags = atomic_fetch_or(IRQ_WORK_CLAIMED, &work->flags);
	/*
	 * If the work is already pending, no need to raise the IPI.
	 * The pairing atomic_fetch_andnot() in irq_work_run() makes sure
	 * everything we did before is visible.
	 */
	if (oflags & IRQ_WORK_PENDING)
		return false;
	return true;
}

void __weak arch_irq_work_raise(void)
{
	/*
	 * Lame architectures will get the timer tick callback
	 */
}

/* Enqueue on current CPU, work must already be claimed and preempt disabled */
static void __irq_work_queue_local(struct irq_work *work)
{
	/* If the work is "lazy", handle it from next tick if any */
	if (atomic_read(&work->flags) & IRQ_WORK_LAZY) {
		if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) &&
		    tick_nohz_tick_stopped())
			arch_irq_work_raise();
	} else {
		if (llist_add(&work->llnode, this_cpu_ptr(&raised_list)))
			arch_irq_work_raise();
	}
}

/* Enqueue the irq work @work on the current CPU */
bool irq_work_queue(struct irq_work *work)
{
	/* Only queue if not already pending */
	if (!irq_work_claim(work))
		return false;

	/* Queue the entry and raise the IPI if needed. */
	preempt_disable();
	__irq_work_queue_local(work);
	preempt_enable();

	return true;
}
EXPORT_SYMBOL_GPL(irq_work_queue);

/*
 * Enqueue the irq_work @work on @cpu unless it's already pending
 * somewhere.
 *
 * Can be re-enqueued while the callback is still in progress.
 */
bool irq_work_queue_on(struct irq_work *work, int cpu)
{
#ifndef CONFIG_SMP
	return irq_work_queue(work);

#else /* CONFIG_SMP: */
	/* All work should have been flushed before going offline */
	WARN_ON_ONCE(cpu_is_offline(cpu));

	/* Only queue if not already pending */
	if (!irq_work_claim(work))
		return false;

	preempt_disable();
	if (cpu != smp_processor_id()) {
		/* Arch remote IPI send/receive backend aren't NMI safe */
		WARN_ON_ONCE(in_nmi());
		if (llist_add(&work->llnode, &per_cpu(raised_list, cpu)))
			arch_send_call_function_single_ipi(cpu);
	} else {
		__irq_work_queue_local(work);
	}
	preempt_enable();

	return true;
#endif /* CONFIG_SMP */
}


bool irq_work_needs_cpu(void)
{
	struct llist_head *raised, *lazy;

	raised = this_cpu_ptr(&raised_list);
	lazy = this_cpu_ptr(&lazy_list);

	if (llist_empty(raised) || arch_irq_work_has_interrupt())
		if (llist_empty(lazy))
			return false;

	/* All work should have been flushed before going offline */
	WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));

	return true;
}

static void irq_work_run_list(struct llist_head *list)
{
	struct irq_work *work, *tmp;
	struct llist_node *llnode;

	BUG_ON(!irqs_disabled());

	if (llist_empty(list))
		return;

	llnode = llist_del_all(list);
	llist_for_each_entry_safe(work, tmp, llnode, llnode) {
		int flags;
		/*
		 * Clear the PENDING bit, after this point the @work
		 * can be re-used.
		 * Make it immediately visible so that other CPUs trying
		 * to claim that work don't rely on us to handle their data
		 * while we are in the middle of the func.
		 */
		flags = atomic_fetch_andnot(IRQ_WORK_PENDING, &work->flags);

		work->func(work);
		/*
		 * Clear the BUSY bit and return to the free state if
		 * no-one else claimed it meanwhile.
		 */
		flags &= ~IRQ_WORK_PENDING;
		(void)atomic_cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY);
	}
}

/*
 * hotplug calls this through:
 *  hotplug_cfd() -> flush_smp_call_function_queue()
 */
void irq_work_run(void)
{
	irq_work_run_list(this_cpu_ptr(&raised_list));
	irq_work_run_list(this_cpu_ptr(&lazy_list));
}
EXPORT_SYMBOL_GPL(irq_work_run);

void irq_work_tick(void)
{
	struct llist_head *raised = this_cpu_ptr(&raised_list);

	if (!llist_empty(raised) && !arch_irq_work_has_interrupt())
		irq_work_run_list(raised);
	irq_work_run_list(this_cpu_ptr(&lazy_list));
}

/*
 * Synchronize against the irq_work @entry, ensures the entry is not
 * currently in use.
 */
void irq_work_sync(struct irq_work *work)
{
	lockdep_assert_irqs_enabled();

	while (atomic_read(&work->flags) & IRQ_WORK_BUSY)
		cpu_relax();
}
EXPORT_SYMBOL_GPL(irq_work_sync);