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
234
235
236
237
238
239
240
|
// SPDX-License-Identifier: GPL-2.0
/*
* Free some vmemmap pages of HugeTLB
*
* Copyright (c) 2020, Bytedance. All rights reserved.
*
* Author: Muchun Song <songmuchun@bytedance.com>
*
* The struct page structures (page structs) are used to describe a physical
* page frame. By default, there is a one-to-one mapping from a page frame to
* it's corresponding page struct.
*
* HugeTLB pages consist of multiple base page size pages and is supported by
* many architectures. See hugetlbpage.rst in the Documentation directory for
* more details. On the x86-64 architecture, HugeTLB pages of size 2MB and 1GB
* are currently supported. Since the base page size on x86 is 4KB, a 2MB
* HugeTLB page consists of 512 base pages and a 1GB HugeTLB page consists of
* 4096 base pages. For each base page, there is a corresponding page struct.
*
* Within the HugeTLB subsystem, only the first 4 page structs are used to
* contain unique information about a HugeTLB page. __NR_USED_SUBPAGE provides
* this upper limit. The only 'useful' information in the remaining page structs
* is the compound_head field, and this field is the same for all tail pages.
*
* By removing redundant page structs for HugeTLB pages, memory can be returned
* to the buddy allocator for other uses.
*
* Different architectures support different HugeTLB pages. For example, the
* following table is the HugeTLB page size supported by x86 and arm64
* architectures. Because arm64 supports 4k, 16k, and 64k base pages and
* supports contiguous entries, so it supports many kinds of sizes of HugeTLB
* page.
*
* +--------------+-----------+-----------------------------------------------+
* | Architecture | Page Size | HugeTLB Page Size |
* +--------------+-----------+-----------+-----------+-----------+-----------+
* | x86-64 | 4KB | 2MB | 1GB | | |
* +--------------+-----------+-----------+-----------+-----------+-----------+
* | | 4KB | 64KB | 2MB | 32MB | 1GB |
* | +-----------+-----------+-----------+-----------+-----------+
* | arm64 | 16KB | 2MB | 32MB | 1GB | |
* | +-----------+-----------+-----------+-----------+-----------+
* | | 64KB | 2MB | 512MB | 16GB | |
* +--------------+-----------+-----------+-----------+-----------+-----------+
*
* When the system boot up, every HugeTLB page has more than one struct page
* structs which size is (unit: pages):
*
* struct_size = HugeTLB_Size / PAGE_SIZE * sizeof(struct page) / PAGE_SIZE
*
* Where HugeTLB_Size is the size of the HugeTLB page. We know that the size
* of the HugeTLB page is always n times PAGE_SIZE. So we can get the following
* relationship.
*
* HugeTLB_Size = n * PAGE_SIZE
*
* Then,
*
* struct_size = n * PAGE_SIZE / PAGE_SIZE * sizeof(struct page) / PAGE_SIZE
* = n * sizeof(struct page) / PAGE_SIZE
*
* We can use huge mapping at the pud/pmd level for the HugeTLB page.
*
* For the HugeTLB page of the pmd level mapping, then
*
* struct_size = n * sizeof(struct page) / PAGE_SIZE
* = PAGE_SIZE / sizeof(pte_t) * sizeof(struct page) / PAGE_SIZE
* = sizeof(struct page) / sizeof(pte_t)
* = 64 / 8
* = 8 (pages)
*
* Where n is how many pte entries which one page can contains. So the value of
* n is (PAGE_SIZE / sizeof(pte_t)).
*
* This optimization only supports 64-bit system, so the value of sizeof(pte_t)
* is 8. And this optimization also applicable only when the size of struct page
* is a power of two. In most cases, the size of struct page is 64 bytes (e.g.
* x86-64 and arm64). So if we use pmd level mapping for a HugeTLB page, the
* size of struct page structs of it is 8 page frames which size depends on the
* size of the base page.
*
* For the HugeTLB page of the pud level mapping, then
*
* struct_size = PAGE_SIZE / sizeof(pmd_t) * struct_size(pmd)
* = PAGE_SIZE / 8 * 8 (pages)
* = PAGE_SIZE (pages)
*
* Where the struct_size(pmd) is the size of the struct page structs of a
* HugeTLB page of the pmd level mapping.
*
* E.g.: A 2MB HugeTLB page on x86_64 consists in 8 page frames while 1GB
* HugeTLB page consists in 4096.
*
* Next, we take the pmd level mapping of the HugeTLB page as an example to
* show the internal implementation of this optimization. There are 8 pages
* struct page structs associated with a HugeTLB page which is pmd mapped.
*
* Here is how things look before optimization.
*
* HugeTLB struct pages(8 pages) page frame(8 pages)
* +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+
* | | | 0 | -------------> | 0 |
* | | +-----------+ +-----------+
* | | | 1 | -------------> | 1 |
* | | +-----------+ +-----------+
* | | | 2 | -------------> | 2 |
* | | +-----------+ +-----------+
* | | | 3 | -------------> | 3 |
* | | +-----------+ +-----------+
* | | | 4 | -------------> | 4 |
* | PMD | +-----------+ +-----------+
* | level | | 5 | -------------> | 5 |
* | mapping | +-----------+ +-----------+
* | | | 6 | -------------> | 6 |
* | | +-----------+ +-----------+
* | | | 7 | -------------> | 7 |
* | | +-----------+ +-----------+
* | |
* | |
* | |
* +-----------+
*
* The value of page->compound_head is the same for all tail pages. The first
* page of page structs (page 0) associated with the HugeTLB page contains the 4
* page structs necessary to describe the HugeTLB. The only use of the remaining
* pages of page structs (page 1 to page 7) is to point to page->compound_head.
* Therefore, we can remap pages 2 to 7 to page 1. Only 2 pages of page structs
* will be used for each HugeTLB page. This will allow us to free the remaining
* 6 pages to the buddy allocator.
*
* Here is how things look after remapping.
*
* HugeTLB struct pages(8 pages) page frame(8 pages)
* +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+
* | | | 0 | -------------> | 0 |
* | | +-----------+ +-----------+
* | | | 1 | -------------> | 1 |
* | | +-----------+ +-----------+
* | | | 2 | ----------------^ ^ ^ ^ ^ ^
* | | +-----------+ | | | | |
* | | | 3 | ------------------+ | | | |
* | | +-----------+ | | | |
* | | | 4 | --------------------+ | | |
* | PMD | +-----------+ | | |
* | level | | 5 | ----------------------+ | |
* | mapping | +-----------+ | |
* | | | 6 | ------------------------+ |
* | | +-----------+ |
* | | | 7 | --------------------------+
* | | +-----------+
* | |
* | |
* | |
* +-----------+
*
* When a HugeTLB is freed to the buddy system, we should allocate 6 pages for
* vmemmap pages and restore the previous mapping relationship.
*
* For the HugeTLB page of the pud level mapping. It is similar to the former.
* We also can use this approach to free (PAGE_SIZE - 2) vmemmap pages.
*
* Apart from the HugeTLB page of the pmd/pud level mapping, some architectures
* (e.g. aarch64) provides a contiguous bit in the translation table entries
* that hints to the MMU to indicate that it is one of a contiguous set of
* entries that can be cached in a single TLB entry.
*
* The contiguous bit is used to increase the mapping size at the pmd and pte
* (last) level. So this type of HugeTLB page can be optimized only when its
* size of the struct page structs is greater than 2 pages.
*/
#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 tail page structures. We map the virtual addresses of the remaining
* pages of tail page structures to the first tail page struct, and then free
* these page frames. Therefore, we need to reserve two pages as vmemmap areas.
*/
#define RESERVE_VMEMMAP_NR 2U
#define RESERVE_VMEMMAP_SIZE (RESERVE_VMEMMAP_NR << PAGE_SHIFT)
static inline unsigned long free_vmemmap_pages_size_per_hpage(struct hstate *h)
{
return (unsigned long)free_vmemmap_pages_per_hpage(h) << PAGE_SHIFT;
}
/*
* Previously discarded vmemmap pages will be allocated and remapping
* after this function returns zero.
*/
int alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
{
int ret;
unsigned long vmemmap_addr = (unsigned long)head;
unsigned long vmemmap_end, vmemmap_reuse;
if (!HPageVmemmapOptimized(head))
return 0;
vmemmap_addr += RESERVE_VMEMMAP_SIZE;
vmemmap_end = vmemmap_addr + free_vmemmap_pages_size_per_hpage(h);
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);
return ret;
}
void free_huge_page_vmemmap(struct hstate *h, struct page *head)
{
unsigned long vmemmap_addr = (unsigned long)head;
unsigned long vmemmap_end, vmemmap_reuse;
if (!free_vmemmap_pages_per_hpage(h))
return;
vmemmap_addr += RESERVE_VMEMMAP_SIZE;
vmemmap_end = vmemmap_addr + free_vmemmap_pages_size_per_hpage(h);
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.
*/
vmemmap_remap_free(vmemmap_addr, vmemmap_end, vmemmap_reuse);
SetHPageVmemmapOptimized(head);
}
|
