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
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
|
/*
* arch/arm/include/asm/tlb.h
*
* Copyright (C) 2002 Russell King
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* Experimentation shows that on a StrongARM, it appears to be faster
* to use the "invalidate whole tlb" rather than "invalidate single
* tlb" for this.
*
* This appears true for both the process fork+exit case, as well as
* the munmap-large-area case.
*/
#ifndef __ASMARM_TLB_H
#define __ASMARM_TLB_H
#include <asm/cacheflush.h>
#ifndef CONFIG_MMU
#include <linux/pagemap.h>
#define tlb_flush(tlb) ((void) tlb)
#include <asm-generic/tlb.h>
#else /* !CONFIG_MMU */
#include <linux/swap.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#define MMU_GATHER_BUNDLE 8
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
static inline void __tlb_remove_table(void *_table)
{
free_page_and_swap_cache((struct page *)_table);
}
struct mmu_table_batch {
struct rcu_head rcu;
unsigned int nr;
void *tables[0];
};
#define MAX_TABLE_BATCH \
((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
extern void tlb_table_flush(struct mmu_gather *tlb);
extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
#define tlb_remove_entry(tlb, entry) tlb_remove_table(tlb, entry)
#else
#define tlb_remove_entry(tlb, entry) tlb_remove_page(tlb, entry)
#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
/*
* TLB handling. This allows us to remove pages from the page
* tables, and efficiently handle the TLB issues.
*/
struct mmu_gather {
struct mm_struct *mm;
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
struct mmu_table_batch *batch;
unsigned int need_flush;
#endif
unsigned int fullmm;
struct vm_area_struct *vma;
unsigned long start, end;
unsigned long range_start;
unsigned long range_end;
unsigned int nr;
unsigned int max;
struct page **pages;
struct page *local[MMU_GATHER_BUNDLE];
};
DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
/*
* This is unnecessarily complex. There's three ways the TLB shootdown
* code is used:
* 1. Unmapping a range of vmas. See zap_page_range(), unmap_region().
* tlb->fullmm = 0, and tlb_start_vma/tlb_end_vma will be called.
* tlb->vma will be non-NULL.
* 2. Unmapping all vmas. See exit_mmap().
* tlb->fullmm = 1, and tlb_start_vma/tlb_end_vma will be called.
* tlb->vma will be non-NULL. Additionally, page tables will be freed.
* 3. Unmapping argument pages. See shift_arg_pages().
* tlb->fullmm = 0, but tlb_start_vma/tlb_end_vma will not be called.
* tlb->vma will be NULL.
*/
static inline void tlb_flush(struct mmu_gather *tlb)
{
if (tlb->fullmm || !tlb->vma)
flush_tlb_mm(tlb->mm);
else if (tlb->range_end > 0) {
flush_tlb_range(tlb->vma, tlb->range_start, tlb->range_end);
tlb->range_start = TASK_SIZE;
tlb->range_end = 0;
}
}
static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr)
{
if (!tlb->fullmm) {
if (addr < tlb->range_start)
tlb->range_start = addr;
if (addr + PAGE_SIZE > tlb->range_end)
tlb->range_end = addr + PAGE_SIZE;
}
}
static inline void __tlb_alloc_page(struct mmu_gather *tlb)
{
unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
if (addr) {
tlb->pages = (void *)addr;
tlb->max = PAGE_SIZE / sizeof(struct page *);
}
}
static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
{
tlb_flush(tlb);
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
tlb_table_flush(tlb);
#endif
}
static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
{
free_pages_and_swap_cache(tlb->pages, tlb->nr);
tlb->nr = 0;
if (tlb->pages == tlb->local)
__tlb_alloc_page(tlb);
}
static inline void tlb_flush_mmu(struct mmu_gather *tlb)
{
tlb_flush_mmu_tlbonly(tlb);
tlb_flush_mmu_free(tlb);
}
static inline void
tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
tlb->mm = mm;
tlb->fullmm = !(start | (end+1));
tlb->start = start;
tlb->end = end;
tlb->vma = NULL;
tlb->max = ARRAY_SIZE(tlb->local);
tlb->pages = tlb->local;
tlb->nr = 0;
__tlb_alloc_page(tlb);
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
tlb->batch = NULL;
#endif
}
static inline void
tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
{
tlb_flush_mmu(tlb);
/* keep the page table cache within bounds */
check_pgt_cache();
if (tlb->pages != tlb->local)
free_pages((unsigned long)tlb->pages, 0);
}
/*
* Memorize the range for the TLB flush.
*/
static inline void
tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long addr)
{
tlb_add_flush(tlb, addr);
}
#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \
tlb_remove_tlb_entry(tlb, ptep, address)
/*
* In the case of tlb vma handling, we can optimise these away in the
* case where we're doing a full MM flush. When we're doing a munmap,
* the vmas are adjusted to only cover the region to be torn down.
*/
static inline void
tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
{
if (!tlb->fullmm) {
flush_cache_range(vma, vma->vm_start, vma->vm_end);
tlb->vma = vma;
tlb->range_start = TASK_SIZE;
tlb->range_end = 0;
}
}
static inline void
tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
{
if (!tlb->fullmm)
tlb_flush(tlb);
}
static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
{
if (tlb->nr == tlb->max)
return true;
tlb->pages[tlb->nr++] = page;
return false;
}
static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
{
if (__tlb_remove_page(tlb, page)) {
tlb_flush_mmu(tlb);
__tlb_remove_page(tlb, page);
}
}
static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
struct page *page, int page_size)
{
return __tlb_remove_page(tlb, page);
}
static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
struct page *page)
{
return __tlb_remove_page(tlb, page);
}
static inline void tlb_remove_page_size(struct mmu_gather *tlb,
struct page *page, int page_size)
{
return tlb_remove_page(tlb, page);
}
static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
unsigned long addr)
{
pgtable_page_dtor(pte);
#ifdef CONFIG_ARM_LPAE
tlb_add_flush(tlb, addr);
#else
/*
* With the classic ARM MMU, a pte page has two corresponding pmd
* entries, each covering 1MB.
*/
addr &= PMD_MASK;
tlb_add_flush(tlb, addr + SZ_1M - PAGE_SIZE);
tlb_add_flush(tlb, addr + SZ_1M);
#endif
tlb_remove_entry(tlb, pte);
}
static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
unsigned long addr)
{
#ifdef CONFIG_ARM_LPAE
tlb_add_flush(tlb, addr);
tlb_remove_entry(tlb, virt_to_page(pmdp));
#endif
}
static inline void
tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
{
tlb_add_flush(tlb, addr);
}
#define pte_free_tlb(tlb, ptep, addr) __pte_free_tlb(tlb, ptep, addr)
#define pmd_free_tlb(tlb, pmdp, addr) __pmd_free_tlb(tlb, pmdp, addr)
#define pud_free_tlb(tlb, pudp, addr) pud_free((tlb)->mm, pudp)
#define tlb_migrate_finish(mm) do { } while (0)
#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
unsigned int page_size)
{
}
#endif /* CONFIG_MMU */
#endif
|