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
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
|
/*
* Copyright IBM Corporation, 2015
* Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of version 2 of the GNU Lesser General Public License
* as published by the Free Software Foundation.
*
* This program is distributed in the hope that it would be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
*
*/
#include <linux/mm.h>
#include <asm/machdep.h>
#include <asm/mmu.h>
/*
* index from 0 - 15
*/
bool __rpte_sub_valid(real_pte_t rpte, unsigned long index)
{
unsigned long g_idx;
unsigned long ptev = pte_val(rpte.pte);
g_idx = (ptev & H_PAGE_COMBO_VALID) >> H_PAGE_F_GIX_SHIFT;
index = index >> 2;
if (g_idx & (0x1 << index))
return true;
else
return false;
}
/*
* index from 0 - 15
*/
static unsigned long mark_subptegroup_valid(unsigned long ptev, unsigned long index)
{
unsigned long g_idx;
if (!(ptev & H_PAGE_COMBO))
return ptev;
index = index >> 2;
g_idx = 0x1 << index;
return ptev | (g_idx << H_PAGE_F_GIX_SHIFT);
}
int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
pte_t *ptep, unsigned long trap, unsigned long flags,
int ssize, int subpg_prot)
{
real_pte_t rpte;
unsigned long *hidxp;
unsigned long hpte_group;
unsigned int subpg_index;
unsigned long rflags, pa, hidx;
unsigned long old_pte, new_pte, subpg_pte;
unsigned long vpn, hash, slot;
unsigned long shift = mmu_psize_defs[MMU_PAGE_4K].shift;
/*
* atomically mark the linux large page PTE busy and dirty
*/
do {
pte_t pte = READ_ONCE(*ptep);
old_pte = pte_val(pte);
/* If PTE busy, retry the access */
if (unlikely(old_pte & H_PAGE_BUSY))
return 0;
/* If PTE permissions don't match, take page fault */
if (unlikely(!check_pte_access(access, old_pte)))
return 1;
/*
* Try to lock the PTE, add ACCESSED and DIRTY if it was
* a write access. Since this is 4K insert of 64K page size
* also add H_PAGE_COMBO
*/
new_pte = old_pte | H_PAGE_BUSY | _PAGE_ACCESSED | H_PAGE_COMBO;
if (access & _PAGE_WRITE)
new_pte |= _PAGE_DIRTY;
} while (!pte_xchg(ptep, __pte(old_pte), __pte(new_pte)));
/*
* Handle the subpage protection bits
*/
subpg_pte = new_pte & ~subpg_prot;
rflags = htab_convert_pte_flags(subpg_pte);
if (!cpu_has_feature(CPU_FTR_NOEXECUTE) &&
!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) {
/*
* No CPU has hugepages but lacks no execute, so we
* don't need to worry about that case
*/
rflags = hash_page_do_lazy_icache(rflags, __pte(old_pte), trap);
}
subpg_index = (ea & (PAGE_SIZE - 1)) >> shift;
vpn = hpt_vpn(ea, vsid, ssize);
rpte = __real_pte(__pte(old_pte), ptep);
/*
*None of the sub 4k page is hashed
*/
if (!(old_pte & H_PAGE_HASHPTE))
goto htab_insert_hpte;
/*
* Check if the pte was already inserted into the hash table
* as a 64k HW page, and invalidate the 64k HPTE if so.
*/
if (!(old_pte & H_PAGE_COMBO)) {
flush_hash_page(vpn, rpte, MMU_PAGE_64K, ssize, flags);
/*
* clear the old slot details from the old and new pte.
* On hash insert failure we use old pte value and we don't
* want slot information there if we have a insert failure.
*/
old_pte &= ~(H_PAGE_HASHPTE | H_PAGE_F_GIX | H_PAGE_F_SECOND);
new_pte &= ~(H_PAGE_HASHPTE | H_PAGE_F_GIX | H_PAGE_F_SECOND);
goto htab_insert_hpte;
}
/*
* Check for sub page valid and update
*/
if (__rpte_sub_valid(rpte, subpg_index)) {
int ret;
hash = hpt_hash(vpn, shift, ssize);
hidx = __rpte_to_hidx(rpte, subpg_index);
if (hidx & _PTEIDX_SECONDARY)
hash = ~hash;
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
slot += hidx & _PTEIDX_GROUP_IX;
ret = mmu_hash_ops.hpte_updatepp(slot, rflags, vpn,
MMU_PAGE_4K, MMU_PAGE_4K,
ssize, flags);
/*
*if we failed because typically the HPTE wasn't really here
* we try an insertion.
*/
if (ret == -1)
goto htab_insert_hpte;
*ptep = __pte(new_pte & ~H_PAGE_BUSY);
return 0;
}
htab_insert_hpte:
/*
* handle H_PAGE_4K_PFN case
*/
if (old_pte & H_PAGE_4K_PFN) {
/*
* All the sub 4k page have the same
* physical address.
*/
pa = pte_pfn(__pte(old_pte)) << HW_PAGE_SHIFT;
} else {
pa = pte_pfn(__pte(old_pte)) << PAGE_SHIFT;
pa += (subpg_index << shift);
}
hash = hpt_hash(vpn, shift, ssize);
repeat:
hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
/* Insert into the hash table, primary slot */
slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, 0,
MMU_PAGE_4K, MMU_PAGE_4K, ssize);
/*
* Primary is full, try the secondary
*/
if (unlikely(slot == -1)) {
hpte_group = ((~hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa,
rflags, HPTE_V_SECONDARY,
MMU_PAGE_4K, MMU_PAGE_4K,
ssize);
if (slot == -1) {
if (mftb() & 0x1)
hpte_group = ((hash & htab_hash_mask) *
HPTES_PER_GROUP) & ~0x7UL;
mmu_hash_ops.hpte_remove(hpte_group);
/*
* FIXME!! Should be try the group from which we removed ?
*/
goto repeat;
}
}
/*
* Hypervisor failure. Restore old pte and return -1
* similar to __hash_page_*
*/
if (unlikely(slot == -2)) {
*ptep = __pte(old_pte);
hash_failure_debug(ea, access, vsid, trap, ssize,
MMU_PAGE_4K, MMU_PAGE_4K, old_pte);
return -1;
}
/*
* Insert slot number & secondary bit in PTE second half,
* clear H_PAGE_BUSY and set appropriate HPTE slot bit
* Since we have H_PAGE_BUSY set on ptep, we can be sure
* nobody is undating hidx.
*/
hidxp = (unsigned long *)(ptep + PTRS_PER_PTE);
rpte.hidx &= ~(0xfUL << (subpg_index << 2));
*hidxp = rpte.hidx | (slot << (subpg_index << 2));
new_pte = mark_subptegroup_valid(new_pte, subpg_index);
new_pte |= H_PAGE_HASHPTE;
/*
* check __real_pte for details on matching smp_rmb()
*/
smp_wmb();
*ptep = __pte(new_pte & ~H_PAGE_BUSY);
return 0;
}
int __hash_page_64K(unsigned long ea, unsigned long access,
unsigned long vsid, pte_t *ptep, unsigned long trap,
unsigned long flags, int ssize)
{
unsigned long hpte_group;
unsigned long rflags, pa;
unsigned long old_pte, new_pte;
unsigned long vpn, hash, slot;
unsigned long shift = mmu_psize_defs[MMU_PAGE_64K].shift;
/*
* atomically mark the linux large page PTE busy and dirty
*/
do {
pte_t pte = READ_ONCE(*ptep);
old_pte = pte_val(pte);
/* If PTE busy, retry the access */
if (unlikely(old_pte & H_PAGE_BUSY))
return 0;
/* If PTE permissions don't match, take page fault */
if (unlikely(!check_pte_access(access, old_pte)))
return 1;
/*
* Check if PTE has the cache-inhibit bit set
* If so, bail out and refault as a 4k page
*/
if (!mmu_has_feature(MMU_FTR_CI_LARGE_PAGE) &&
unlikely(pte_ci(pte)))
return 0;
/*
* Try to lock the PTE, add ACCESSED and DIRTY if it was
* a write access.
*/
new_pte = old_pte | H_PAGE_BUSY | _PAGE_ACCESSED;
if (access & _PAGE_WRITE)
new_pte |= _PAGE_DIRTY;
} while (!pte_xchg(ptep, __pte(old_pte), __pte(new_pte)));
rflags = htab_convert_pte_flags(new_pte);
if (!cpu_has_feature(CPU_FTR_NOEXECUTE) &&
!cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
rflags = hash_page_do_lazy_icache(rflags, __pte(old_pte), trap);
vpn = hpt_vpn(ea, vsid, ssize);
if (unlikely(old_pte & H_PAGE_HASHPTE)) {
/*
* There MIGHT be an HPTE for this pte
*/
hash = hpt_hash(vpn, shift, ssize);
if (old_pte & H_PAGE_F_SECOND)
hash = ~hash;
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
slot += (old_pte & H_PAGE_F_GIX) >> H_PAGE_F_GIX_SHIFT;
if (mmu_hash_ops.hpte_updatepp(slot, rflags, vpn, MMU_PAGE_64K,
MMU_PAGE_64K, ssize,
flags) == -1)
old_pte &= ~_PAGE_HPTEFLAGS;
}
if (likely(!(old_pte & H_PAGE_HASHPTE))) {
pa = pte_pfn(__pte(old_pte)) << PAGE_SHIFT;
hash = hpt_hash(vpn, shift, ssize);
repeat:
hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
/* Insert into the hash table, primary slot */
slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, 0,
MMU_PAGE_64K, MMU_PAGE_64K,
ssize);
/*
* Primary is full, try the secondary
*/
if (unlikely(slot == -1)) {
hpte_group = ((~hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa,
rflags,
HPTE_V_SECONDARY,
MMU_PAGE_64K,
MMU_PAGE_64K, ssize);
if (slot == -1) {
if (mftb() & 0x1)
hpte_group = ((hash & htab_hash_mask) *
HPTES_PER_GROUP) & ~0x7UL;
mmu_hash_ops.hpte_remove(hpte_group);
/*
* FIXME!! Should be try the group from which we removed ?
*/
goto repeat;
}
}
/*
* Hypervisor failure. Restore old pte and return -1
* similar to __hash_page_*
*/
if (unlikely(slot == -2)) {
*ptep = __pte(old_pte);
hash_failure_debug(ea, access, vsid, trap, ssize,
MMU_PAGE_64K, MMU_PAGE_64K, old_pte);
return -1;
}
new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE;
new_pte |= (slot << H_PAGE_F_GIX_SHIFT) &
(H_PAGE_F_SECOND | H_PAGE_F_GIX);
}
*ptep = __pte(new_pte & ~H_PAGE_BUSY);
return 0;
}
|
