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
|
/*
* TLB flush routines for radix kernels.
*
* Copyright 2015-2016, Aneesh Kumar K.V, IBM Corporation.
*
* 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/mm.h>
#include <linux/hugetlb.h>
#include <linux/memblock.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
static DEFINE_RAW_SPINLOCK(native_tlbie_lock);
static inline void __tlbiel_pid(unsigned long pid, int set)
{
unsigned long rb,rs,ric,prs,r;
rb = PPC_BIT(53); /* IS = 1 */
rb |= set << PPC_BITLSHIFT(51);
rs = ((unsigned long)pid) << PPC_BITLSHIFT(31);
prs = 1; /* process scoped */
r = 1; /* raidx format */
ric = 2; /* invalidate all the caches */
asm volatile("ptesync": : :"memory");
asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |"
"(%2 << 17) | (%3 << 18) | (%4 << 21)"
: : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
asm volatile("ptesync": : :"memory");
}
/*
* We use 128 set in radix mode and 256 set in hpt mode.
*/
static inline void _tlbiel_pid(unsigned long pid)
{
int set;
for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) {
__tlbiel_pid(pid, set);
}
return;
}
static inline void _tlbie_pid(unsigned long pid)
{
unsigned long rb,rs,ric,prs,r;
rb = PPC_BIT(53); /* IS = 1 */
rs = pid << PPC_BITLSHIFT(31);
prs = 1; /* process scoped */
r = 1; /* raidx format */
ric = 2; /* invalidate all the caches */
asm volatile("ptesync": : :"memory");
asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |"
"(%2 << 17) | (%3 << 18) | (%4 << 21)"
: : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
asm volatile("eieio; tlbsync; ptesync": : :"memory");
}
static inline void _tlbiel_va(unsigned long va, unsigned long pid,
unsigned long ap)
{
unsigned long rb,rs,ric,prs,r;
rb = va & ~(PPC_BITMASK(52, 63));
rb |= ap << PPC_BITLSHIFT(58);
rs = pid << PPC_BITLSHIFT(31);
prs = 1; /* process scoped */
r = 1; /* raidx format */
ric = 0; /* no cluster flush yet */
asm volatile("ptesync": : :"memory");
asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |"
"(%2 << 17) | (%3 << 18) | (%4 << 21)"
: : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
asm volatile("ptesync": : :"memory");
}
static inline void _tlbie_va(unsigned long va, unsigned long pid,
unsigned long ap)
{
unsigned long rb,rs,ric,prs,r;
rb = va & ~(PPC_BITMASK(52, 63));
rb |= ap << PPC_BITLSHIFT(58);
rs = pid << PPC_BITLSHIFT(31);
prs = 1; /* process scoped */
r = 1; /* raidx format */
ric = 0; /* no cluster flush yet */
asm volatile("ptesync": : :"memory");
asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |"
"(%2 << 17) | (%3 << 18) | (%4 << 21)"
: : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
asm volatile("eieio; tlbsync; ptesync": : :"memory");
}
/*
* Base TLB flushing operations:
*
* - flush_tlb_mm(mm) flushes the specified mm context TLB's
* - flush_tlb_page(vma, vmaddr) flushes one page
* - flush_tlb_range(vma, start, end) flushes a range of pages
* - flush_tlb_kernel_range(start, end) flushes kernel pages
*
* - local_* variants of page and mm only apply to the current
* processor
*/
void radix__local_flush_tlb_mm(struct mm_struct *mm)
{
unsigned int pid;
preempt_disable();
pid = mm->context.id;
if (pid != MMU_NO_CONTEXT)
_tlbiel_pid(pid);
preempt_enable();
}
EXPORT_SYMBOL(radix__local_flush_tlb_mm);
void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
unsigned long ap, int nid)
{
unsigned int pid;
preempt_disable();
pid = mm ? mm->context.id : 0;
if (pid != MMU_NO_CONTEXT)
_tlbiel_va(vmaddr, pid, ap);
preempt_enable();
}
void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
{
#ifdef CONFIG_HUGETLB_PAGE
/* need the return fix for nohash.c */
if (vma && is_vm_hugetlb_page(vma))
return __local_flush_hugetlb_page(vma, vmaddr);
#endif
radix___local_flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr,
mmu_get_ap(mmu_virtual_psize), 0);
}
EXPORT_SYMBOL(radix__local_flush_tlb_page);
#ifdef CONFIG_SMP
static int mm_is_core_local(struct mm_struct *mm)
{
return cpumask_subset(mm_cpumask(mm),
topology_sibling_cpumask(smp_processor_id()));
}
void radix__flush_tlb_mm(struct mm_struct *mm)
{
unsigned int pid;
preempt_disable();
pid = mm->context.id;
if (unlikely(pid == MMU_NO_CONTEXT))
goto no_context;
if (!mm_is_core_local(mm)) {
int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
if (lock_tlbie)
raw_spin_lock(&native_tlbie_lock);
_tlbie_pid(pid);
if (lock_tlbie)
raw_spin_unlock(&native_tlbie_lock);
} else
_tlbiel_pid(pid);
no_context:
preempt_enable();
}
EXPORT_SYMBOL(radix__flush_tlb_mm);
void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
unsigned long ap, int nid)
{
unsigned int pid;
preempt_disable();
pid = mm ? mm->context.id : 0;
if (unlikely(pid == MMU_NO_CONTEXT))
goto bail;
if (!mm_is_core_local(mm)) {
int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
if (lock_tlbie)
raw_spin_lock(&native_tlbie_lock);
_tlbie_va(vmaddr, pid, ap);
if (lock_tlbie)
raw_spin_unlock(&native_tlbie_lock);
} else
_tlbiel_va(vmaddr, pid, ap);
bail:
preempt_enable();
}
void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
{
#ifdef CONFIG_HUGETLB_PAGE
if (vma && is_vm_hugetlb_page(vma))
return flush_hugetlb_page(vma, vmaddr);
#endif
radix___flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr,
mmu_get_ap(mmu_virtual_psize), 0);
}
EXPORT_SYMBOL(radix__flush_tlb_page);
#endif /* CONFIG_SMP */
void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
if (lock_tlbie)
raw_spin_lock(&native_tlbie_lock);
_tlbie_pid(0);
if (lock_tlbie)
raw_spin_unlock(&native_tlbie_lock);
}
EXPORT_SYMBOL(radix__flush_tlb_kernel_range);
/*
* Currently, for range flushing, we just do a full mm flush. Because
* we use this in code path where we don' track the page size.
*/
void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end)
{
struct mm_struct *mm = vma->vm_mm;
radix__flush_tlb_mm(mm);
}
EXPORT_SYMBOL(radix__flush_tlb_range);
void radix__tlb_flush(struct mmu_gather *tlb)
{
struct mm_struct *mm = tlb->mm;
radix__flush_tlb_mm(mm);
}
|
