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
|
/*
* Copyright 2007-2008 Paul Mackerras, IBM Corp.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/gfp.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/syscalls.h>
#include <asm/pgtable.h>
#include <linux/uaccess.h>
#include <asm/tlbflush.h>
/*
* Free all pages allocated for subpage protection maps and pointers.
* Also makes sure that the subpage_prot_table structure is
* reinitialized for the next user.
*/
void subpage_prot_free(struct mm_struct *mm)
{
struct subpage_prot_table *spt = &mm->context.spt;
unsigned long i, j, addr;
u32 **p;
for (i = 0; i < 4; ++i) {
if (spt->low_prot[i]) {
free_page((unsigned long)spt->low_prot[i]);
spt->low_prot[i] = NULL;
}
}
addr = 0;
for (i = 0; i < (TASK_SIZE_USER64 >> 43); ++i) {
p = spt->protptrs[i];
if (!p)
continue;
spt->protptrs[i] = NULL;
for (j = 0; j < SBP_L2_COUNT && addr < spt->maxaddr;
++j, addr += PAGE_SIZE)
if (p[j])
free_page((unsigned long)p[j]);
free_page((unsigned long)p);
}
spt->maxaddr = 0;
}
void subpage_prot_init_new_context(struct mm_struct *mm)
{
struct subpage_prot_table *spt = &mm->context.spt;
memset(spt, 0, sizeof(*spt));
}
static void hpte_flush_range(struct mm_struct *mm, unsigned long addr,
int npages)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
spinlock_t *ptl;
pgd = pgd_offset(mm, addr);
if (pgd_none(*pgd))
return;
pud = pud_offset(pgd, addr);
if (pud_none(*pud))
return;
pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd))
return;
pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
arch_enter_lazy_mmu_mode();
for (; npages > 0; --npages) {
pte_update(mm, addr, pte, 0, 0, 0);
addr += PAGE_SIZE;
++pte;
}
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(pte - 1, ptl);
}
/*
* Clear the subpage protection map for an address range, allowing
* all accesses that are allowed by the pte permissions.
*/
static void subpage_prot_clear(unsigned long addr, unsigned long len)
{
struct mm_struct *mm = current->mm;
struct subpage_prot_table *spt = &mm->context.spt;
u32 **spm, *spp;
unsigned long i;
size_t nw;
unsigned long next, limit;
down_write(&mm->mmap_sem);
limit = addr + len;
if (limit > spt->maxaddr)
limit = spt->maxaddr;
for (; addr < limit; addr = next) {
next = pmd_addr_end(addr, limit);
if (addr < 0x100000000UL) {
spm = spt->low_prot;
} else {
spm = spt->protptrs[addr >> SBP_L3_SHIFT];
if (!spm)
continue;
}
spp = spm[(addr >> SBP_L2_SHIFT) & (SBP_L2_COUNT - 1)];
if (!spp)
continue;
spp += (addr >> PAGE_SHIFT) & (SBP_L1_COUNT - 1);
i = (addr >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
nw = PTRS_PER_PTE - i;
if (addr + (nw << PAGE_SHIFT) > next)
nw = (next - addr) >> PAGE_SHIFT;
memset(spp, 0, nw * sizeof(u32));
/* now flush any existing HPTEs for the range */
hpte_flush_range(mm, addr, nw);
}
up_write(&mm->mmap_sem);
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static int subpage_walk_pmd_entry(pmd_t *pmd, unsigned long addr,
unsigned long end, struct mm_walk *walk)
{
struct vm_area_struct *vma = walk->vma;
split_huge_pmd(vma, pmd, addr);
return 0;
}
static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr,
unsigned long len)
{
struct vm_area_struct *vma;
struct mm_walk subpage_proto_walk = {
.mm = mm,
.pmd_entry = subpage_walk_pmd_entry,
};
/*
* We don't try too hard, we just mark all the vma in that range
* VM_NOHUGEPAGE and split them.
*/
vma = find_vma(mm, addr);
/*
* If the range is in unmapped range, just return
*/
if (vma && ((addr + len) <= vma->vm_start))
return;
while (vma) {
if (vma->vm_start >= (addr + len))
break;
vma->vm_flags |= VM_NOHUGEPAGE;
walk_page_vma(vma, &subpage_proto_walk);
vma = vma->vm_next;
}
}
#else
static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr,
unsigned long len)
{
return;
}
#endif
/*
* Copy in a subpage protection map for an address range.
* The map has 2 bits per 4k subpage, so 32 bits per 64k page.
* Each 2-bit field is 0 to allow any access, 1 to prevent writes,
* 2 or 3 to prevent all accesses.
* Note that the normal page protections also apply; the subpage
* protection mechanism is an additional constraint, so putting 0
* in a 2-bit field won't allow writes to a page that is otherwise
* write-protected.
*/
SYSCALL_DEFINE3(subpage_prot, unsigned long, addr,
unsigned long, len, u32 __user *, map)
{
struct mm_struct *mm = current->mm;
struct subpage_prot_table *spt = &mm->context.spt;
u32 **spm, *spp;
unsigned long i;
size_t nw;
unsigned long next, limit;
int err;
if (radix_enabled())
return -ENOENT;
/* Check parameters */
if ((addr & ~PAGE_MASK) || (len & ~PAGE_MASK) ||
addr >= mm->task_size || len >= mm->task_size ||
addr + len > mm->task_size)
return -EINVAL;
if (is_hugepage_only_range(mm, addr, len))
return -EINVAL;
if (!map) {
/* Clear out the protection map for the address range */
subpage_prot_clear(addr, len);
return 0;
}
if (!access_ok(VERIFY_READ, map, (len >> PAGE_SHIFT) * sizeof(u32)))
return -EFAULT;
down_write(&mm->mmap_sem);
subpage_mark_vma_nohuge(mm, addr, len);
for (limit = addr + len; addr < limit; addr = next) {
next = pmd_addr_end(addr, limit);
err = -ENOMEM;
if (addr < 0x100000000UL) {
spm = spt->low_prot;
} else {
spm = spt->protptrs[addr >> SBP_L3_SHIFT];
if (!spm) {
spm = (u32 **)get_zeroed_page(GFP_KERNEL);
if (!spm)
goto out;
spt->protptrs[addr >> SBP_L3_SHIFT] = spm;
}
}
spm += (addr >> SBP_L2_SHIFT) & (SBP_L2_COUNT - 1);
spp = *spm;
if (!spp) {
spp = (u32 *)get_zeroed_page(GFP_KERNEL);
if (!spp)
goto out;
*spm = spp;
}
spp += (addr >> PAGE_SHIFT) & (SBP_L1_COUNT - 1);
local_irq_disable();
demote_segment_4k(mm, addr);
local_irq_enable();
i = (addr >> PAGE_SHIFT) &
|