summaryrefslogtreecommitdiff
path: root/mm/mm_init.c
blob: 0d7b2bd2454a1f36b7d82976fda0ae10f4ab5dff (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * mm_init.c - Memory initialisation verification and debugging
 *
 * Copyright 2008 IBM Corporation, 2008
 * Author Mel Gorman <mel@csn.ul.ie>
 *
 */
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/kobject.h>
#include <linux/export.h>
#include <linux/memory.h>
#include <linux/notifier.h>
#include <linux/sched.h>
#include <linux/mman.h>
#include "internal.h"

#ifdef CONFIG_DEBUG_MEMORY_INIT
int __meminitdata mminit_loglevel;

/* The zonelists are simply reported, validation is manual. */
void __init mminit_verify_zonelist(void)
{
	int nid;

	if (mminit_loglevel < MMINIT_VERIFY)
		return;

	for_each_online_node(nid) {
		pg_data_t *pgdat = NODE_DATA(nid);
		struct zone *zone;
		struct zoneref *z;
		struct zonelist *zonelist;
		int i, listid, zoneid;

		BUILD_BUG_ON(MAX_ZONELISTS > 2);
		for (i = 0; i < MAX_ZONELISTS * MAX_NR_ZONES; i++) {

			/* Identify the zone and nodelist */
			zoneid = i % MAX_NR_ZONES;
			listid = i / MAX_NR_ZONES;
			zonelist = &pgdat->node_zonelists[listid];
			zone = &pgdat->node_zones[zoneid];
			if (!populated_zone(zone))
				continue;

			/* Print information about the zonelist */
			printk(KERN_DEBUG "mminit::zonelist %s %d:%s = ",
				listid > 0 ? "thisnode" : "general", nid,
				zone->name);

			/* Iterate the zonelist */
			for_each_zone_zonelist(zone, z, zonelist, zoneid)
				pr_cont("%d:%s ", zone_to_nid(zone), zone->name);
			pr_cont("\n");
		}
	}
}

void __init mminit_verify_pageflags_layout(void)
{
	int shift, width;
	unsigned long or_mask, add_mask;

	shift = 8 * sizeof(unsigned long);
	width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH
		- LAST_CPUPID_SHIFT - KASAN_TAG_WIDTH - LRU_GEN_WIDTH - LRU_REFS_WIDTH;
	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_widths",
		"Section %d Node %d Zone %d Lastcpupid %d Kasantag %d Gen %d Tier %d Flags %d\n",
		SECTIONS_WIDTH,
		NODES_WIDTH,
		ZONES_WIDTH,
		LAST_CPUPID_WIDTH,
		KASAN_TAG_WIDTH,
		LRU_GEN_WIDTH,
		LRU_REFS_WIDTH,
		NR_PAGEFLAGS);
	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_shifts",
		"Section %d Node %d Zone %d Lastcpupid %d Kasantag %d\n",
		SECTIONS_SHIFT,
		NODES_SHIFT,
		ZONES_SHIFT,
		LAST_CPUPID_SHIFT,
		KASAN_TAG_WIDTH);
	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_pgshifts",
		"Section %lu Node %lu Zone %lu Lastcpupid %lu Kasantag %lu\n",
		(unsigned long)SECTIONS_PGSHIFT,
		(unsigned long)NODES_PGSHIFT,
		(unsigned long)ZONES_PGSHIFT,
		(unsigned long)LAST_CPUPID_PGSHIFT,
		(unsigned long)KASAN_TAG_PGSHIFT);
	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodezoneid",
		"Node/Zone ID: %lu -> %lu\n",
		(unsigned long)(ZONEID_PGOFF + ZONEID_SHIFT),
		(unsigned long)ZONEID_PGOFF);
	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_usage",
		"location: %d -> %d layout %d -> %d unused %d -> %d page-flags\n",
		shift, width, width, NR_PAGEFLAGS, NR_PAGEFLAGS, 0);
#ifdef NODE_NOT_IN_PAGE_FLAGS
	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
		"Node not in page flags");
#endif
#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
		"Last cpupid not in page flags");
#endif

	if (SECTIONS_WIDTH) {
		shift -= SECTIONS_WIDTH;
		BUG_ON(shift != SECTIONS_PGSHIFT);
	}
	if (NODES_WIDTH) {
		shift -= NODES_WIDTH;
		BUG_ON(shift != NODES_PGSHIFT);
	}
	if (ZONES_WIDTH) {
		shift -= ZONES_WIDTH;
		BUG_ON(shift != ZONES_PGSHIFT);
	}

	/* Check for bitmask overlaps */
	or_mask = (ZONES_MASK << ZONES_PGSHIFT) |
			(NODES_MASK << NODES_PGSHIFT) |
			(SECTIONS_MASK << SECTIONS_PGSHIFT);
	add_mask = (ZONES_MASK << ZONES_PGSHIFT) +
			(NODES_MASK << NODES_PGSHIFT) +
			(SECTIONS_MASK << SECTIONS_PGSHIFT);
	BUG_ON(or_mask != add_mask);
}

static __init int set_mminit_loglevel(char *str)
{
	get_option(&str, &mminit_loglevel);
	return 0;
}
early_param("mminit_loglevel", set_mminit_loglevel);
#endif /* CONFIG_DEBUG_MEMORY_INIT */

struct kobject *mm_kobj;
EXPORT_SYMBOL_GPL(mm_kobj);

#ifdef CONFIG_SMP
s32 vm_committed_as_batch = 32;

void mm_compute_batch(int overcommit_policy)
{
	u64 memsized_batch;
	s32 nr = num_present_cpus();
	s32 batch = max_t(s32, nr*2, 32);
	unsigned long ram_pages = totalram_pages();

	/*
	 * For policy OVERCOMMIT_NEVER, set batch size to 0.4% of
	 * (total memory/#cpus), and lift it to 25% for other policies
	 * to easy the possible lock contention for percpu_counter
	 * vm_committed_as, while the max limit is INT_MAX
	 */
	if (overcommit_policy == OVERCOMMIT_NEVER)
		memsized_batch = min_t(u64, ram_pages/nr/256, INT_MAX);
	else
		memsized_batch = min_t(u64, ram_pages/nr/4, INT_MAX);

	vm_committed_as_batch = max_t(s32, memsized_batch, batch);
}

static int __meminit mm_compute_batch_notifier(struct notifier_block *self,
					unsigned long action, void *arg)
{
	switch (action) {
	case MEM_ONLINE:
	case MEM_OFFLINE:
		mm_compute_batch(sysctl_overcommit_memory);
		break;
	default:
		break;
	}
	return NOTIFY_OK;
}

static struct notifier_block compute_batch_nb __meminitdata = {
	.notifier_call = mm_compute_batch_notifier,
	.priority = IPC_CALLBACK_PRI, /* use lowest priority */
};

static int __init mm_compute_batch_init(void)
{
	mm_compute_batch(sysctl_overcommit_memory);
	register_hotmemory_notifier(&compute_batch_nb);

	return 0;
}

__initcall(mm_compute_batch_init);

#endif

static int __init mm_sysfs_init(void)
{
	mm_kobj = kobject_create_and_add("mm", kernel_kobj);
	if (!mm_kobj)
		return -ENOMEM;

	return 0;
}
postcore_initcall(mm_sysfs_init);