Home Home > GIT Browse
summaryrefslogtreecommitdiff
blob: df34ceae0c678569446930eaf5ceb982a496f8b9 (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
/*
 * linux/mm/allocpercpu.c
 *
 * Separated from slab.c August 11, 2006 Christoph Lameter
 */
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/bootmem.h>
#include <asm/sections.h>

#ifndef cache_line_size
#define cache_line_size()	L1_CACHE_BYTES
#endif

/**
 * percpu_depopulate - depopulate per-cpu data for given cpu
 * @__pdata: per-cpu data to depopulate
 * @cpu: depopulate per-cpu data for this cpu
 *
 * Depopulating per-cpu data for a cpu going offline would be a typical
 * use case. You need to register a cpu hotplug handler for that purpose.
 */
static void percpu_depopulate(void *__pdata, int cpu)
{
	struct percpu_data *pdata = __percpu_disguise(__pdata);

	kfree(pdata->ptrs[cpu]);
	pdata->ptrs[cpu] = NULL;
}

/**
 * percpu_depopulate_mask - depopulate per-cpu data for some cpu's
 * @__pdata: per-cpu data to depopulate
 * @mask: depopulate per-cpu data for cpu's selected through mask bits
 */
static void __percpu_depopulate_mask(void *__pdata, const cpumask_t *mask)
{
	int cpu;
	for_each_cpu_mask_nr(cpu, *mask)
		percpu_depopulate(__pdata, cpu);
}

#define percpu_depopulate_mask(__pdata, mask) \
	__percpu_depopulate_mask((__pdata), &(mask))

/**
 * percpu_populate - populate per-cpu data for given cpu
 * @__pdata: per-cpu data to populate further
 * @size: size of per-cpu object
 * @gfp: may sleep or not etc.
 * @cpu: populate per-data for this cpu
 *
 * Populating per-cpu data for a cpu coming online would be a typical
 * use case. You need to register a cpu hotplug handler for that purpose.
 * Per-cpu object is populated with zeroed buffer.
 */
static void *percpu_populate(void *__pdata, size_t size, gfp_t gfp, int cpu)
{
	struct percpu_data *pdata = __percpu_disguise(__pdata);
	int node = cpu_to_node(cpu);

	/*
	 * We should make sure each CPU gets private memory.
	 */
	size = roundup(size, cache_line_size());

	BUG_ON(pdata->ptrs[cpu]);
	if (node_online(node))
		pdata->ptrs[cpu] = kmalloc_node(size, gfp|__GFP_ZERO, node);
	else
		pdata->ptrs[cpu] = kzalloc(size, gfp);
	return pdata->ptrs[cpu];
}

/**
 * percpu_populate_mask - populate per-cpu data for more cpu's
 * @__pdata: per-cpu data to populate further
 * @size: size of per-cpu object
 * @gfp: may sleep or not etc.
 * @mask: populate per-cpu data for cpu's selected through mask bits
 *
 * Per-cpu objects are populated with zeroed buffers.
 */
static int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp,
				  cpumask_t *mask)
{
	cpumask_t populated;
	int cpu;

	cpus_clear(populated);
	for_each_cpu_mask_nr(cpu, *mask)
		if (unlikely(!percpu_populate(__pdata, size, gfp, cpu))) {
			__percpu_depopulate_mask(__pdata, &populated);
			return -ENOMEM;
		} else
			cpu_set(cpu, populated);
	return 0;
}

#define percpu_populate_mask(__pdata, size, gfp, mask) \
	__percpu_populate_mask((__pdata), (size), (gfp), &(mask))

/**
 * alloc_percpu - initial setup of per-cpu data
 * @size: size of per-cpu object
 * @align: alignment
 *
 * Allocate dynamic percpu area.  Percpu objects are populated with
 * zeroed buffers.
 */
void *__alloc_percpu(size_t size, size_t align)
{
	/*
	 * We allocate whole cache lines to avoid false sharing
	 */
	size_t sz = roundup(nr_cpu_ids * sizeof(void *), cache_line_size());
	void *pdata = kzalloc(sz, GFP_KERNEL);
	void *__pdata = __percpu_disguise(pdata);

	/*
	 * Can't easily make larger alignment work with kmalloc.  WARN
	 * on it.  Larger alignment should only be used for module
	 * percpu sections on SMP for which this path isn't used.
	 */
	WARN_ON_ONCE(align > SMP_CACHE_BYTES);

	if (unlikely(!pdata))
		return NULL;
	if (likely(!__percpu_populate_mask(__pdata, size, GFP_KERNEL,
					   &cpu_possible_map)))
		return __pdata;
	kfree(pdata);
	return NULL;
}
EXPORT_SYMBOL_GPL(__alloc_percpu);

/**
 * free_percpu - final cleanup of per-cpu data
 * @__pdata: object to clean up
 *
 * We simply clean up any per-cpu object left. No need for the client to
 * track and specify through a bis mask which per-cpu objects are to free.
 */
void free_percpu(void *__pdata)
{
	if (unlikely(!__pdata))
		return;
	__percpu_depopulate_mask(__pdata, cpu_possible_mask);
	kfree(__percpu_disguise(__pdata));
}
EXPORT_SYMBOL_GPL(free_percpu);

/*
 * Generic percpu area setup.
 */
#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;

EXPORT_SYMBOL(__per_cpu_offset);

void __init setup_per_cpu_areas(void)
{
	unsigned long size, i;
	char *ptr;
	unsigned long nr_possible_cpus = num_possible_cpus();

	/* Copy section for each CPU (we discard the original) */
	size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
	ptr = alloc_bootmem_pages(size * nr_possible_cpus);

	for_each_possible_cpu(i) {
		__per_cpu_offset[i] = ptr - __per_cpu_start;
		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
		ptr += size;
	}
}
#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */