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
|
/* arch/sparc64/mm/tlb.c
*
* Copyright (C) 2004 David S. Miller <davem@redhat.com>
*/
#include <linux/kernel.h>
#include <linux/percpu.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/preempt.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/cacheflush.h>
#include <asm/mmu_context.h>
#include <asm/tlb.h>
/* Heavily inspired by the ppc64 code. */
static DEFINE_PER_CPU(struct tlb_batch, tlb_batch);
void flush_tlb_pending(void)
{
struct tlb_batch *tb = &get_cpu_var(tlb_batch);
struct mm_struct *mm = tb->mm;
if (!tb->tlb_nr)
goto out;
flush_tsb_user(tb);
if (CTX_VALID(mm->context)) {
if (tb->tlb_nr == 1) {
global_flush_tlb_page(mm, tb->vaddrs[0]);
} else {
#ifdef CONFIG_SMP
smp_flush_tlb_pending(tb->mm, tb->tlb_nr,
&tb->vaddrs[0]);
#else
__flush_tlb_pending(CTX_HWBITS(tb->mm->context),
tb->tlb_nr, &tb->vaddrs[0]);
#endif
}
}
tb->tlb_nr = 0;
out:
put_cpu_var(tlb_batch);
}
void arch_enter_lazy_mmu_mode(void)
{
struct tlb_batch *tb = this_cpu_ptr(&tlb_batch);
tb->active = 1;
}
void arch_leave_lazy_mmu_mode(void)
{
struct tlb_batch *tb = this_cpu_ptr(&tlb_batch);
if (tb->tlb_nr)
flush_tlb_pending();
tb->active = 0;
}
static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
bool exec, bool huge)
{
struct tlb_batch *tb = &get_cpu_var(tlb_batch);
unsigned long nr;
vaddr &= PAGE_MASK;
if (exec)
vaddr |= 0x1UL;
nr = tb->tlb_nr;
if (unlikely(nr != 0 && mm != tb->mm)) {
flush_tlb_pending();
nr = 0;
}
if (!tb->active) {
flush_tsb_user_page(mm, vaddr, huge);
global_flush_tlb_page(mm, vaddr);
goto out;
}
if (nr == 0) {
tb->mm = mm;
tb->huge = huge;
}
if (tb->huge != huge) {
flush_tlb_pending();
tb->huge = huge;
nr = 0;
}
tb->vaddrs[nr] = vaddr;
tb->tlb_nr = ++nr;
if (nr >= TLB_BATCH_NR)
flush_tlb_pending();
out:
put_cpu_var(tlb_batch);
}
void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
pte_t *ptep, pte_t orig, int fullmm)
{
bool huge = is_hugetlb_pte(orig);
if (tlb_type != hypervisor &&
pte_dirty(orig)) {
unsigned long paddr, pfn = pte_pfn(orig);
struct address_space *mapping;
struct page *page;
if (!pfn_valid(pfn))
goto no_cache_flush;
page = pfn_to_page(pfn);
if (PageReserved(page))
goto no_cache_flush;
/* A real file page? */
mapping = page_mapping(page);
if (!mapping)
goto no_cache_flush;
paddr = (unsigned long) page_address(page);
if ((paddr ^ vaddr) & (1 << 13))
flush_dcache_page_all(mm, page);
}
no_cache_flush:
if (!fullmm)
tlb_batch_add_one(mm, vaddr, pte_exec(orig), huge);
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr,
pmd_t pmd)
{
unsigned long end;
pte_t *pte;
pte = pte_offset_map(&pmd, vaddr);
end = vaddr + HPAGE_SIZE;
while (vaddr < end) {
if (pte_val(*pte) & _PAGE_VALID) {
bool exec = pte_exec(*pte);
tlb_batch_add_one(mm, vaddr, exec, false);
}
pte++;
vaddr += PAGE_SIZE;
}
pte_unmap(pte);
}
void set_pmd_at(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp, pmd_t pmd)
{
pmd_t orig = *pmdp;
*pmdp = pmd;
if (mm == &init_mm)
return;
if ((pmd_val(pmd) ^ pmd_val(orig)) & _PAGE_PMD_HUGE) {
if (pmd_val(pmd) & _PAGE_PMD_HUGE)
mm->context.thp_pte_count++;
else
mm->context.thp_pte_count--;
/* Do not try to allocate the TSB hash table if we
* don't have one already. We have various locks held
* and thus we'll end up doing a GFP_KERNEL allocation
* in an atomic context.
*
* Instead, we let the first TLB miss on a hugepage
* take care of this.
*/
}
if (!pmd_none(orig)) {
addr &= HPAGE_MASK;
if (pmd_trans_huge(orig)) {
pte_t orig_pte = __pte(pmd_val(orig));
bool exec = pte_exec(orig_pte);
tlb_batch_add_one(mm, addr, exec, true);
tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec,
true);
} else {
tlb_batch_pmd_scan(mm, addr, orig);
}
}
}
void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
pmd_t entry = *pmdp;
pmd_val(entry) &= ~_PAGE_VALID;
set_pmd_at(vma->vm_mm, address, pmdp, entry);
flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
}
void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
pgtable_t pgtable)
{
struct list_head *lh = (struct list_head *) pgtable;
assert_spin_locked(&mm->page_table_lock);
/* FIFO */
if (!pmd_huge_pte(mm, pmdp))
INIT_LIST_HEAD(lh);
else
list_add(lh, (struct list_head *) pmd_huge_pte(mm, pmdp));
pmd_huge_pte(mm, pmdp) = pgtable;
}
pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
{
struct list_head *lh;
pgtable_t pgtable;
assert_spin_locked(&mm->page_table_lock);
/* FIFO */
pgtable = pmd_huge_pte(mm, pmdp);
lh = (struct list_head *) pgtable;
if (list_empty(lh))
pmd_huge_pte(mm, pmdp) = NULL;
else {
pmd_huge_pte(mm, pmdp) = (pgtable_t) lh->next;
list_del(lh);
}
pte_val(pgtable[0]) = 0;
pte_val(pgtable[1]) = 0;
return pgtable;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
|
