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
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
|
/*
* arch/sh64/mm/hugetlbpage.c
*
* SuperH HugeTLB page support.
*
* Cloned from sparc64 by Paul Mundt.
*
* Copyright (C) 2002, 2003 David S. Miller (davem@redhat.com)
*/
#include <linux/config.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/pagemap.h>
#include <linux/smp_lock.h>
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <asm/mman.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/cacheflush.h>
pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
pmd_t *pmd;
pte_t *pte = NULL;
pgd = pgd_offset(mm, addr);
if (pgd) {
pmd = pmd_alloc(mm, pgd, addr);
if (pmd)
pte = pte_alloc_map(mm, pmd, addr);
}
return pte;
}
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
pmd_t *pmd;
pte_t *pte = NULL;
pgd = pgd_offset(mm, addr);
if (pgd) {
pmd = pmd_offset(pgd, addr);
if (pmd)
pte = pte_offset_map(pmd, addr);
}
return pte;
}
#define mk_pte_huge(entry) do { pte_val(entry) |= _PAGE_SZHUGE; } while (0)
static void set_huge_pte(struct mm_struct *mm, struct vm_area_struct *vma,
struct page *page, pte_t * page_table, int write_access)
{
unsigned long i;
pte_t entry;
add_mm_counter(mm, rss, HPAGE_SIZE / PAGE_SIZE);
if (write_access)
entry = pte_mkwrite(pte_mkdirty(mk_pte(page,
vma->vm_page_prot)));
else
entry = pte_wrprotect(mk_pte(page, vma->vm_page_prot));
entry = pte_mkyoung(entry);
mk_pte_huge(entry);
for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
set_pte(page_table, entry);
page_table++;
pte_val(entry) += PAGE_SIZE;
}
}
pte_t huge_ptep_get_and_clear(pte_t *ptep)
{
pte_t entry;
entry = *ptep;
for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
pte_clear(pte);
pte++;
}
return entry;
}
/*
* This function checks for proper alignment of input addr and len parameters.
*/
int is_aligned_hugepage_range(unsigned long addr, unsigned long len)
{
if (len & ~HPAGE_MASK)
return -EINVAL;
if (addr & ~HPAGE_MASK)
return -EINVAL;
return 0;
}
int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
struct vm_area_struct *vma)
{
pte_t *src_pte, *dst_pte, entry;
struct page *ptepage;
unsigned long addr = vma->vm_start;
unsigned long end = vma->vm_end;
int i;
while (addr < end) {
dst_pte = huge_pte_alloc(dst, addr);
if (!dst_pte)
goto nomem;
src_pte = huge_pte_offset(src, addr);
BUG_ON(!src_pte || pte_none(*src_pte));
entry = *src_pte;
ptepage = pte_page(entry);
get_page(ptepage);
for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
set_pte(dst_pte, entry);
pte_val(entry) += PAGE_SIZE;
dst_pte++;
}
add_mm_counter(dst, rss, HPAGE_SIZE / PAGE_SIZE);
addr += HPAGE_SIZE;
}
return 0;
nomem:
return -ENOMEM;
}
int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
struct page **pages, struct vm_area_struct **vmas,
unsigned long *position, int *length, int i)
{
unsigned long vaddr = *position;
int remainder = *length;
WARN_ON(!is_vm_hugetlb_page(vma));
while (vaddr < vma->vm_end && remainder) {
if (pages) {
pte_t *pte;
struct page *page;
pte = huge_pte_offset(mm, vaddr);
/* hugetlb should be locked, and hence, prefaulted */
BUG_ON(!pte || pte_none(*pte));
page = pte_page(*pte);
WARN_ON(!PageCompound(page));
get_page(page);
pages[i] = page;
}
if (vmas)
vmas[i] = vma;
vaddr += PAGE_SIZE;
--remainder;
++i;
}
*length = remainder;
*position = vaddr;
return i;
}
struct page *follow_huge_addr(struct mm_struct *mm,
unsigned long address, int write)
{
return ERR_PTR(-EINVAL);
}
int pmd_huge(pmd_t pmd)
{
return 0;
}
struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
pmd_t *pmd, int write)
{
return NULL;
}
void unmap_hugepage_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long address;
pte_t *pte;
struct page *page;
int i;
BUG_ON(start & (HPAGE_SIZE - 1));
BUG_ON(end & (HPAGE_SIZE - 1));
for (address = start; address < end; address += HPAGE_SIZE) {
pte = huge_pte_offset(mm, address);
BUG_ON(!pte);
if (pte_none(*pte))
continue;
page = pte_page(*pte);
put_page(page);
for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
pte_clear(mm, address+(i*PAGE_SIZE), pte);
pte++;
}
}
add_mm_counter(mm, rss, -((end - start) >> PAGE_SHIFT));
flush_tlb_range(vma, start, end);
}
int hugetlb_prefault(struct address_space *mapping, struct vm_area_struct *vma)
{
struct mm_struct *mm = current->mm;
unsigned long addr;
int ret = 0;
BUG_ON(vma->vm_start & ~HPAGE_MASK);
BUG_ON(vma->vm_end & ~HPAGE_MASK);
spin_lock(&mm->page_table_lock);
for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) {
unsigned long idx;
pte_t *pte = huge_pte_alloc(mm, addr);
struct page *page;
if (!pte) {
ret = -ENOMEM;
goto out;
}
if (!pte_none(*pte))
continue;
idx = ((addr - vma->vm_start) >> HPAGE_SHIFT)
+ (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
page = find_get_page(mapping, idx);
if (!page) {
/* charge the fs quota first */
if (hugetlb_get_quota(mapping)) {
ret = -ENOMEM;
goto out;
}
page = alloc_huge_page();
if (!page) {
hugetlb_put_quota(mapping);
ret = -ENOMEM;
goto out;
}
ret = add_to_page_cache(page, mapping, idx, GFP_ATOMIC);
if (! ret) {
unlock_page(page);
} else {
hugetlb_put_quota(mapping);
free_huge_page(page);
goto out;
}
}
set_huge_pte(mm, vma, page, pte, vma->vm_flags & VM_WRITE);
}
out:
spin_unlock(&mm->page_table_lock);
return ret;
}
|