summaryrefslogtreecommitdiff
path: root/kernel/irq/affinity.c
blob: d2747f9c5707a0686af739b088868de9018d7a18 (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
/*
 * Copyright (C) 2016 Thomas Gleixner.
 * Copyright (C) 2016-2017 Christoph Hellwig.
 */
#include <linux/interrupt.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/cpu.h>

static void irq_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
				int cpus_per_vec)
{
	const struct cpumask *siblmsk;
	int cpu, sibl;

	for ( ; cpus_per_vec > 0; ) {
		cpu = cpumask_first(nmsk);

		/* Should not happen, but I'm too lazy to think about it */
		if (cpu >= nr_cpu_ids)
			return;

		cpumask_clear_cpu(cpu, nmsk);
		cpumask_set_cpu(cpu, irqmsk);
		cpus_per_vec--;

		/* If the cpu has siblings, use them first */
		siblmsk = topology_sibling_cpumask(cpu);
		for (sibl = -1; cpus_per_vec > 0; ) {
			sibl = cpumask_next(sibl, siblmsk);
			if (sibl >= nr_cpu_ids)
				break;
			if (!cpumask_test_and_clear_cpu(sibl, nmsk))
				continue;
			cpumask_set_cpu(sibl, irqmsk);
			cpus_per_vec--;
		}
	}
}

static cpumask_var_t *alloc_node_to_present_cpumask(void)
{
	cpumask_var_t *masks;
	int node;

	masks = kcalloc(nr_node_ids, sizeof(cpumask_var_t), GFP_KERNEL);
	if (!masks)
		return NULL;

	for (node = 0; node < nr_node_ids; node++) {
		if (!zalloc_cpumask_var(&masks[node], GFP_KERNEL))
			goto out_unwind;
	}

	return masks;

out_unwind:
	while (--node >= 0)
		free_cpumask_var(masks[node]);
	kfree(masks);
	return NULL;
}

static void free_node_to_present_cpumask(cpumask_var_t *masks)
{
	int node;

	for (node = 0; node < nr_node_ids; node++)
		free_cpumask_var(masks[node]);
	kfree(masks);
}

static void build_node_to_present_cpumask(cpumask_var_t *masks)
{
	int cpu;

	for_each_present_cpu(cpu)
		cpumask_set_cpu(cpu, masks[cpu_to_node(cpu)]);
}

static int get_nodes_in_cpumask(cpumask_var_t *node_to_present_cpumask,
				const struct cpumask *mask, nodemask_t *nodemsk)
{
	int n, nodes = 0;

	/* Calculate the number of nodes in the supplied affinity mask */
	for_each_node(n) {
		if (cpumask_intersects(mask, node_to_present_cpumask[n])) {
			node_set(n, *nodemsk);
			nodes++;
		}
	}
	return nodes;
}

/**
 * irq_create_affinity_masks - Create affinity masks for multiqueue spreading
 * @nvecs:	The total number of vectors
 * @affd:	Description of the affinity requirements
 *
 * Returns the masks pointer or NULL if allocation failed.
 */
struct cpumask *
irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
{
	int n, nodes, cpus_per_vec, extra_vecs, curvec;
	int affv = nvecs - affd->pre_vectors - affd->post_vectors;
	int last_affv = affv + affd->pre_vectors;
	nodemask_t nodemsk = NODE_MASK_NONE;
	struct cpumask *masks;
	cpumask_var_t nmsk, *node_to_present_cpumask;

	if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL))
		return NULL;

	masks = kcalloc(nvecs, sizeof(*masks), GFP_KERNEL);
	if (!masks)
		goto out;

	node_to_present_cpumask = alloc_node_to_present_cpumask();
	if (!node_to_present_cpumask)
		goto out;

	/* Fill out vectors at the beginning that don't need affinity */
	for (curvec = 0; curvec < affd->pre_vectors; curvec++)
		cpumask_copy(masks + curvec, irq_default_affinity);

	/* Stabilize the cpumasks */
	get_online_cpus();
	build_node_to_present_cpumask(node_to_present_cpumask);
	nodes = get_nodes_in_cpumask(node_to_present_cpumask, cpu_present_mask,
				     &nodemsk);

	/*
	 * If the number of nodes in the mask is greater than or equal the
	 * number of vectors we just spread the vectors across the nodes.
	 */
	if (affv <= nodes) {
		for_each_node_mask(n, nodemsk) {
			cpumask_copy(masks + curvec,
				     node_to_present_cpumask[n]);
			if (++curvec == last_affv)
				break;
		}
		goto done;
	}

	for_each_node_mask(n, nodemsk) {
		int ncpus, v, vecs_to_assign, vecs_per_node;

		/* Spread the vectors per node */
		vecs_per_node = (affv - (curvec - affd->pre_vectors)) / nodes;

		/* Get the cpus on this node which are in the mask */
		cpumask_and(nmsk, cpu_present_mask, node_to_present_cpumask[n]);

		/* Calculate the number of cpus per vector */
		ncpus = cpumask_weight(nmsk);
		vecs_to_assign = min(vecs_per_node, ncpus);

		/* Account for rounding errors */
		extra_vecs = ncpus - vecs_to_assign * (ncpus / vecs_to_assign);

		for (v = 0; curvec < last_affv && v < vecs_to_assign;
		     curvec++, v++) {
			cpus_per_vec = ncpus / vecs_to_assign;

			/* Account for extra vectors to compensate rounding errors */
			if (extra_vecs) {
				cpus_per_vec++;
				--extra_vecs;
			}
			irq_spread_init_one(masks + curvec, nmsk, cpus_per_vec);
		}

		if (curvec >= last_affv)
			break;
		--nodes;
	}

done:
	put_online_cpus();

	/* Fill out vectors at the end that don't need affinity */
	for (; curvec < nvecs; curvec++)
		cpumask_copy(masks + curvec, irq_default_affinity);
	free_node_to_present_cpumask(node_to_present_cpumask);
out:
	free_cpumask_var(nmsk);
	return masks;
}

/**
 * irq_calc_affinity_vectors - Calculate the optimal number of vectors
 * @maxvec:	The maximum number of vectors available
 * @affd:	Description of the affinity requirements
 */
int irq_calc_affinity_vectors(int maxvec, const struct irq_affinity *affd)
{
	int resv = affd->pre_vectors + affd->post_vectors;
	int vecs = maxvec - resv;
	int ret;

	get_online_cpus();
	ret = min_t(int, cpumask_weight(cpu_present_mask), vecs) + resv;
	put_online_cpus();
	return ret;
}