aboutsummaryrefslogtreecommitdiff
path: root/kernel/irq/cpuhotplug.c
blob: 02236b13b359974e95a2e3ca4ec3f0cadfd0962a (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
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
// SPDX-License-Identifier: GPL-2.0
/*
 * Generic cpu hotunplug interrupt migration code copied from the
 * arch/arm implementation
 *
 * Copyright (C) Russell King
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */
#include <linux/interrupt.h>
#include <linux/ratelimit.h>
#include <linux/irq.h>
#include <linux/sched/isolation.h>

#include "internals.h"

/* For !GENERIC_IRQ_EFFECTIVE_AFF_MASK this looks at general affinity mask */
static inline bool irq_needs_fixup(struct irq_data *d)
{
	const struct cpumask *m = irq_data_get_effective_affinity_mask(d);
	unsigned int cpu = smp_processor_id();

#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
	/*
	 * The cpumask_empty() check is a workaround for interrupt chips,
	 * which do not implement effective affinity, but the architecture has
	 * enabled the config switch. Use the general affinity mask instead.
	 */
	if (cpumask_empty(m))
		m = irq_data_get_affinity_mask(d);

	/*
	 * Sanity check. If the mask is not empty when excluding the outgoing
	 * CPU then it must contain at least one online CPU. The outgoing CPU
	 * has been removed from the online mask already.
	 */
	if (cpumask_any_but(m, cpu) < nr_cpu_ids &&
	    cpumask_any_and(m, cpu_online_mask) >= nr_cpu_ids) {
		/*
		 * If this happens then there was a missed IRQ fixup at some
		 * point. Warn about it and enforce fixup.
		 */
		pr_warn("Eff. affinity %*pbl of IRQ %u contains only offline CPUs after offlining CPU %u\n",
			cpumask_pr_args(m), d->irq, cpu);
		return true;
	}
#endif
	return cpumask_test_cpu(cpu, m);
}

static bool migrate_one_irq(struct irq_desc *desc)
{
	struct irq_data *d = irq_desc_get_irq_data(desc);
	struct irq_chip *chip = irq_data_get_irq_chip(d);
	bool maskchip = !irq_can_move_pcntxt(d) && !irqd_irq_masked(d);
	const struct cpumask *affinity;
	bool brokeaff = false;
	int err;

	/*
	 * IRQ chip might be already torn down, but the irq descriptor is
	 * still in the radix tree. Also if the chip has no affinity setter,
	 * nothing can be done here.
	 */
	if (!chip || !chip->irq_set_affinity) {
		pr_debug("IRQ %u: Unable to migrate away\n", d->irq);
		return false;
	}

	/*
	 * No move required, if:
	 * - Interrupt is per cpu
	 * - Interrupt is not started
	 * - Affinity mask does not include this CPU.
	 *
	 * Note: Do not check desc->action as this might be a chained
	 * interrupt.
	 */
	if (irqd_is_per_cpu(d) || !irqd_is_started(d) || !irq_needs_fixup(d)) {
		/*
		 * If an irq move is pending, abort it if the dying CPU is
		 * the sole target.
		 */
		irq_fixup_move_pending(desc, false);
		return false;
	}

	/*
	 * Complete an eventually pending irq move cleanup. If this
	 * interrupt was moved in hard irq context, then the vectors need
	 * to be cleaned up. It can't wait until this interrupt actually
	 * happens and this CPU was involved.
	 */
	irq_force_complete_move(desc);

	/*
	 * If there is a setaffinity pending, then try to reuse the pending
	 * mask, so the last change of the affinity does not get lost. If
	 * there is no move pending or the pending mask does not contain
	 * any online CPU, use the current affinity mask.
	 */
	if (irq_fixup_move_pending(desc, true))
		affinity = irq_desc_get_pending_mask(desc);
	else
		affinity = irq_data_get_affinity_mask(d);

	/* Mask the chip for interrupts which cannot move in process context */
	if (maskchip && chip->irq_mask)
		chip->irq_mask(d);

	if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
		/*
		 * If the interrupt is managed, then shut it down and leave
		 * the affinity untouched.
		 */
		if (irqd_affinity_is_managed(d)) {
			irqd_set_managed_shutdown(d);
			irq_shutdown_and_deactivate(desc);
			return false;
		}
		affinity = cpu_online_mask;
		brokeaff = true;
	}
	/*
	 * Do not set the force argument of irq_do_set_affinity() as this
	 * disables the masking of offline CPUs from the supplied affinity
	 * mask and therefore might keep/reassign the irq to the outgoing
	 * CPU.
	 */
	err = irq_do_set_affinity(d, affinity, false);
	if (err) {
		pr_warn_ratelimited("IRQ%u: set affinity failed(%d).\n",
				    d->irq, err);
		brokeaff = false;
	}

	if (maskchip && chip->irq_unmask)
		chip->irq_unmask(d);

	return brokeaff;
}

/**
 * irq_migrate_all_off_this_cpu - Migrate irqs away from offline cpu
 *
 * The current CPU has been marked offline.  Migrate IRQs off this CPU.
 * If the affinity settings do not allow other CPUs, force them onto any
 * available CPU.
 *
 * Note: we must iterate over all IRQs, whether they have an attached
 * action structure or not, as we need to get chained interrupts too.
 */
void irq_migrate_all_off_this_cpu(void)
{
	struct irq_desc *desc;
	unsigned int irq;

	for_each_active_irq(irq) {
		bool affinity_broken;

		desc = irq_to_desc(irq);
		raw_spin_lock(&desc->lock);
		affinity_broken = migrate_one_irq(desc);
		raw_spin_unlock(&desc->lock);

		if (affinity_broken) {
			pr_warn_ratelimited("IRQ %u: no longer affine to CPU%u\n",
					    irq, smp_processor_id());
		}
	}
}

static bool hk_should_isolate(struct irq_data *data, unsigned int cpu)
{
	const struct cpumask *hk_mask;

	if (!housekeeping_enabled(HK_FLAG_MANAGED_IRQ))
		return false;

	hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ);
	if (cpumask_subset(irq_data_get_effective_affinity_mask(data), hk_mask))
		return false;

	return cpumask_test_cpu(cpu, hk_mask);
}

static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu)
{
	struct irq_data *data = irq_desc_get_irq_data(desc);
	const struct cpumask *affinity = irq_data_get_affinity_mask(data);

	if (!irqd_affinity_is_managed(data) || !desc->action ||
	    !irq_data_get_irq_chip(data) || !cpumask_test_cpu(cpu, affinity))
		return;

	if (irqd_is_managed_and_shutdown(data)) {
		irq_startup(desc, IRQ_RESEND, IRQ_START_COND);
		return;
	}

	/*
	 * If the interrupt can only be directed to a single target
	 * CPU then it is already assigned to a CPU in the affinity
	 * mask. No point in trying to move it around unless the
	 * isolation mechanism requests to move it to an upcoming
	 * housekeeping CPU.
	 */
	if (!irqd_is_single_target(data) || hk_should_isolate(data, cpu))
		irq_set_affinity_locked(data, affinity, false);
}

/**
 * irq_affinity_online_cpu - Restore affinity for managed interrupts
 * @cpu:	Upcoming CPU for which interrupts should be restored
 */
int irq_affinity_online_cpu(unsigned int cpu)
{
	struct irq_desc *desc;
	unsigned int irq;

	irq_lock_sparse();
	for_each_active_irq(irq) {
		desc = irq_to_desc(irq);
		raw_spin_lock_irq(&desc->lock);
		irq_restore_affinity_of_irq(desc, cpu);
		raw_spin_unlock_irq(&desc->lock);
	}
	irq_unlock_sparse();

	return 0;
}