summaryrefslogtreecommitdiffstats
path: root/mm/hugetlb_vmemmap.c
blob: 1089ea8a9c985206bbf5b98334368be1a391d5da (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Optimize vmemmap pages associated with HugeTLB
 *
 * Copyright (c) 2020, Bytedance. All rights reserved.
 *
 *     Author: Muchun Song <songmuchun@bytedance.com>
 *
 * See Documentation/vm/vmemmap_dedup.rst
 */
#define pr_fmt(fmt)	"HugeTLB: " fmt

#include <linux/memory_hotplug.h>
#include "hugetlb_vmemmap.h"

/*
 * There are a lot of struct page structures associated with each HugeTLB page.
 * For tail pages, the value of compound_head is the same. So we can reuse first
 * page of head page structures. We map the virtual addresses of all the pages
 * of tail page structures to the head page struct, and then free these page
 * frames. Therefore, we need to reserve one pages as vmemmap areas.
 */
#define RESERVE_VMEMMAP_NR		1U
#define RESERVE_VMEMMAP_SIZE		(RESERVE_VMEMMAP_NR << PAGE_SHIFT)

enum vmemmap_optimize_mode {
	VMEMMAP_OPTIMIZE_OFF,
	VMEMMAP_OPTIMIZE_ON,
};

DEFINE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON,
			hugetlb_optimize_vmemmap_key);
EXPORT_SYMBOL(hugetlb_optimize_vmemmap_key);

static enum vmemmap_optimize_mode vmemmap_optimize_mode =
	IS_ENABLED(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON);

static void vmemmap_optimize_mode_switch(enum vmemmap_optimize_mode to)
{
	if (vmemmap_optimize_mode == to)
		return;

	if (to == VMEMMAP_OPTIMIZE_OFF)
		static_branch_dec(&hugetlb_optimize_vmemmap_key);
	else
		static_branch_inc(&hugetlb_optimize_vmemmap_key);
	WRITE_ONCE(vmemmap_optimize_mode, to);
}

static int __init hugetlb_vmemmap_early_param(char *buf)
{
	bool enable;
	enum vmemmap_optimize_mode mode;

	if (kstrtobool(buf, &enable))
		return -EINVAL;

	mode = enable ? VMEMMAP_OPTIMIZE_ON : VMEMMAP_OPTIMIZE_OFF;
	vmemmap_optimize_mode_switch(mode);

	return 0;
}
early_param("hugetlb_free_vmemmap", hugetlb_vmemmap_early_param);

/*
 * Previously discarded vmemmap pages will be allocated and remapping
 * after this function returns zero.
 */
int hugetlb_vmemmap_alloc(struct hstate *h, struct page *head)
{
	int ret;
	unsigned long vmemmap_addr = (unsigned long)head;
	unsigned long vmemmap_end, vmemmap_reuse, vmemmap_pages;

	if (!HPageVmemmapOptimized(head))
		return 0;

	vmemmap_addr	+= RESERVE_VMEMMAP_SIZE;
	vmemmap_pages	= hugetlb_optimize_vmemmap_pages(h);
	vmemmap_end	= vmemmap_addr + (vmemmap_pages << PAGE_SHIFT);
	vmemmap_reuse	= vmemmap_addr - PAGE_SIZE;

	/*
	 * The pages which the vmemmap virtual address range [@vmemmap_addr,
	 * @vmemmap_end) are mapped to are freed to the buddy allocator, and
	 * the range is mapped to the page which @vmemmap_reuse is mapped to.
	 * When a HugeTLB page is freed to the buddy allocator, previously
	 * discarded vmemmap pages must be allocated and remapping.
	 */
	ret = vmemmap_remap_alloc(vmemmap_addr, vmemmap_end, vmemmap_reuse,
				  GFP_KERNEL | __GFP_NORETRY | __GFP_THISNODE);
	if (!ret) {
		ClearHPageVmemmapOptimized(head);
		static_branch_dec(&hugetlb_optimize_vmemmap_key);
	}

	return ret;
}

void hugetlb_vmemmap_free(struct hstate *h, struct page *head)
{
	unsigned long vmemmap_addr = (unsigned long)head;
	unsigned long vmemmap_end, vmemmap_reuse, vmemmap_pages;

	vmemmap_pages = hugetlb_optimize_vmemmap_pages(h);
	if (!vmemmap_pages)
		return;

	if (READ_ONCE(vmemmap_optimize_mode) == VMEMMAP_OPTIMIZE_OFF)
		return;

	static_branch_inc(&hugetlb_optimize_vmemmap_key);

	vmemmap_addr	+= RESERVE_VMEMMAP_SIZE;
	vmemmap_end	= vmemmap_addr + (vmemmap_pages << PAGE_SHIFT);
	vmemmap_reuse	= vmemmap_addr - PAGE_SIZE;

	/*
	 * Remap the vmemmap virtual address range [@vmemmap_addr, @vmemmap_end)
	 * to the page which @vmemmap_reuse is mapped to, then free the pages
	 * which the range [@vmemmap_addr, @vmemmap_end] is mapped to.
	 */
	if (vmemmap_remap_free(vmemmap_addr, vmemmap_end, vmemmap_reuse))
		static_branch_dec(&hugetlb_optimize_vmemmap_key);
	else
		SetHPageVmemmapOptimized(head);
}

void __init hugetlb_vmemmap_init(struct hstate *h)
{
	unsigned int nr_pages = pages_per_huge_page(h);
	unsigned int vmemmap_pages;

	/*
	 * There are only (RESERVE_VMEMMAP_SIZE / sizeof(struct page)) struct
	 * page structs that can be used when CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP,
	 * so add a BUILD_BUG_ON to catch invalid usage of the tail struct page.
	 */
	BUILD_BUG_ON(__NR_USED_SUBPAGE >=
		     RESERVE_VMEMMAP_SIZE / sizeof(struct page));

	if (!is_power_of_2(sizeof(struct page))) {
		pr_warn_once("cannot optimize vmemmap pages because \"struct page\" crosses page boundaries\n");
		static_branch_disable(&hugetlb_optimize_vmemmap_key);
		return;
	}

	vmemmap_pages = (nr_pages * sizeof(struct page)) >> PAGE_SHIFT;
	/*
	 * The head page is not to be freed to buddy allocator, the other tail
	 * pages will map to the head page, so they can be freed.
	 *
	 * Could RESERVE_VMEMMAP_NR be greater than @vmemmap_pages? It is true
	 * on some architectures (e.g. aarch64). See Documentation/arm64/
	 * hugetlbpage.rst for more details.
	 */
	if (likely(vmemmap_pages > RESERVE_VMEMMAP_NR))
		h->optimize_vmemmap_pages = vmemmap_pages - RESERVE_VMEMMAP_NR;

	pr_info("can optimize %d vmemmap pages for %s\n",
		h->optimize_vmemmap_pages, h->name);
}

#ifdef CONFIG_PROC_SYSCTL
static int hugetlb_optimize_vmemmap_handler(struct ctl_table *table, int write,
					    void *buffer, size_t *length,
					    loff_t *ppos)
{
	int ret;
	enum vmemmap_optimize_mode mode;
	static DEFINE_MUTEX(sysctl_mutex);

	if (write && !capable(CAP_SYS_ADMIN))
		return -EPERM;

	mutex_lock(&sysctl_mutex);
	mode = vmemmap_optimize_mode;
	table->data = &mode;
	ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
	if (write && !ret)
		vmemmap_optimize_mode_switch(mode);
	mutex_unlock(&sysctl_mutex);

	return ret;
}

static struct ctl_table hugetlb_vmemmap_sysctls[] = {
	{
		.procname	= "hugetlb_optimize_vmemmap",
		.maxlen		= sizeof(enum vmemmap_optimize_mode),
		.mode		= 0644,
		.proc_handler	= hugetlb_optimize_vmemmap_handler,
		.extra1		= SYSCTL_ZERO,
		.extra2		= SYSCTL_ONE,
	},
	{ }
};

static __init int hugetlb_vmemmap_sysctls_init(void)
{
	/*
	 * If "memory_hotplug.memmap_on_memory" is enabled or "struct page"
	 * crosses page boundaries, the vmemmap pages cannot be optimized.
	 */
	if (!mhp_memmap_on_memory() && is_power_of_2(sizeof(struct page)))
		register_sysctl_init("vm", hugetlb_vmemmap_sysctls);

	return 0;
}
late_initcall(hugetlb_vmemmap_sysctls_init);
#endif /* CONFIG_PROC_SYSCTL */