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
|
/*
* Copyright (C) 2009 SUSE Linux Products GmbH. All rights reserved.
*
* Authors:
* Alexander Graf <agraf@suse.de>
* Kevin Wolf <mail@kevin-wolf.de>
*
* 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.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*/
#include <linux/kvm_host.h>
#include <linux/hash.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
#include <asm/mmu-hash64.h>
#include <asm/machdep.h>
#include <asm/mmu_context.h>
#include <asm/hw_irq.h>
#define PTE_SIZE 12
#define VSID_ALL 0
/* #define DEBUG_MMU */
/* #define DEBUG_SLB */
#ifdef DEBUG_MMU
#define dprintk_mmu(a, ...) printk(KERN_INFO a, __VA_ARGS__)
#else
#define dprintk_mmu(a, ...) do { } while(0)
#endif
#ifdef DEBUG_SLB
#define dprintk_slb(a, ...) printk(KERN_INFO a, __VA_ARGS__)
#else
#define dprintk_slb(a, ...) do { } while(0)
#endif
void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
{
ppc_md.hpte_invalidate(pte->slot, pte->host_va,
MMU_PAGE_4K, MMU_SEGSIZE_256M,
false);
}
/* We keep 512 gvsid->hvsid entries, mapping the guest ones to the array using
* a hash, so we don't waste cycles on looping */
static u16 kvmppc_sid_hash(struct kvm_vcpu *vcpu, u64 gvsid)
{
return hash_64(gvsid, SID_MAP_BITS);
}
static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid)
{
struct kvmppc_sid_map *map;
u16 sid_map_mask;
if (vcpu->arch.msr & MSR_PR)
gvsid |= VSID_PR;
sid_map_mask = kvmppc_sid_hash(vcpu, gvsid);
map = &to_book3s(vcpu)->sid_map[sid_map_mask];
if (map->guest_vsid == gvsid) {
dprintk_slb("SLB: Searching: 0x%llx -> 0x%llx\n",
gvsid, map->host_vsid);
return map;
}
map = &to_book3s(vcpu)->sid_map[SID_MAP_MASK - sid_map_mask];
if (map->guest_vsid == gvsid) {
dprintk_slb("SLB: Searching 0x%llx -> 0x%llx\n",
gvsid, map->host_vsid);
return map;
}
dprintk_slb("SLB: Searching %d/%d: 0x%llx -> not found\n",
sid_map_mask, SID_MAP_MASK - sid_map_mask, gvsid);
return NULL;
}
int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
{
pfn_t hpaddr;
ulong hash, hpteg, va;
u64 vsid;
int ret;
int rflags = 0x192;
int vflags = 0;
int attempt = 0;
struct kvmppc_sid_map *map;
/* Get host physical address for gpa */
hpaddr = gfn_to_pfn(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT);
if (kvm_is_error_hva(hpaddr)) {
printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", orig_pte->eaddr);
return -EINVAL;
}
hpaddr <<= PAGE_SHIFT;
#if PAGE_SHIFT == 12
#elif PAGE_SHIFT == 16
hpaddr |= orig_pte->raddr & 0xf000;
#else
#error Unknown page size
#endif
/* and write the mapping ea -> hpa into the pt */
vcpu->arch.mmu.esid_to_vsid(vcpu, orig_pte->eaddr >> SID_SHIFT, &vsid);
map = find_sid_vsid(vcpu, vsid);
if (!map) {
ret = kvmppc_mmu_map_segment(vcpu, orig_pte->eaddr);
WARN_ON(ret < 0);
map = find_sid_vsid(vcpu, vsid);
}
if (!map) {
printk(KERN_ERR "KVM: Segment map for 0x%llx (0x%lx) failed\n",
vsid, orig_pte->eaddr);
WARN_ON(true);
return -EINVAL;
}
vsid = map->host_vsid;
va = hpt_va(orig_pte->eaddr, vsid, MMU_SEGSIZE_256M);
if (!orig_pte->may_write)
rflags |= HPTE_R_PP;
else
mark_page_dirty(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT);
if (!orig_pte->may_execute)
rflags |= HPTE_R_N;
hash = hpt_hash(va, PTE_SIZE, MMU_SEGSIZE_256M);
map_again:
hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
/* In case we tried normal mapping already, let's nuke old entries */
if (attempt > 1)
if (ppc_md.hpte_remove(hpteg) < 0)
return -1;
ret = ppc_md.hpte_insert(hpteg, va, hpaddr, rflags, vflags, MMU_PAGE_4K, MMU_SEGSIZE_256M);
if (ret < 0) {
/* If we couldn't map a primary PTE, try a secondary */
hash = ~hash;
vflags ^= HPTE_V_SECONDARY;
attempt++;
goto map_again;
} else {
struct hpte_cache *pte = kvmppc_mmu_hpte_cache_next(vcpu);
dprintk_mmu("KVM: %c%c Map 0x%lx: [%lx] 0x%lx (0x%llx) -> %lx\n",
((rflags & HPTE_R_PP) == 3) ? '-' : 'w',
(rflags & HPTE_R_N) ? '-' : 'x',
orig_pte->eaddr, hpteg, va, orig_pte->vpage, hpaddr);
/* The ppc_md code may give us a secondary entry even though we
asked for a primary. Fix up. */
if ((ret & _PTEIDX_SECONDARY) && !(vflags & HPTE_V_SECONDARY)) {
hash = ~hash;
hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
}
pte->slot = hpteg + (ret & 7);
pte->host_va = va;
pte->pte = *orig_pte;
pte->pfn = hpaddr >> PAGE_SHIFT;
kvmppc_mmu_hpte_cache_map(vcpu, pte);
}
return 0;
}
static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
{
struct kvmppc_sid_map *map;
struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
u16 sid_map_mask;
static int backwards_map = 0;
if (vcpu->arch.msr & MSR_PR)
gvsid |= VSID_PR;
/* We might get collisions that trap in preceding order, so let's
map them differently */
sid_map_mask = kvmppc_sid_hash(vcpu, gvsid);
if (backwards_map)
sid_map_mask = SID_MAP_MASK - sid_map_mask;
map = &to_book3s(vcpu)->sid_map[sid_map_mask];
/* Make sure we're taking the other map next time */
backwards_map = !backwards_map;
/* Uh-oh ... out of mappings. Let's flush! */
if (vcpu_book3s->vsid_next == vcpu_book3s->vsid_max) {
vcpu_book3s->vsid_next = vcpu_book3s->vsid_first;
memset(vcpu_book3s->sid_map, 0,
sizeof(struct kvmppc_sid_map) * SID_MAP_NUM);
kvmppc_mmu_pte_flush(vcpu, 0, 0);
kvmppc_mmu_flush_segments(vcpu);
}
map->host_vsid = vcpu_book3s->vsid_next++;
map->guest_vsid = gvsid;
map->valid = true;
dprintk_slb("SLB: New mapping at %d: 0x%llx -> 0x%llx\n",
sid_map_mask, gvsid, map->host_vsid);
return map;
}
static int kvmppc_mmu_next_segment(struct kvm_vcpu *vcpu, ulong esid)
{
int i;
int max_slb_size = 64;
int found_inval = -1;
int r;
if (!to_svcpu(vcpu)->slb_max)
to_svcpu(vcpu)->slb_max = 1;
/* Are we overwriting? */
for (i = 1; i < to_svcpu(vcpu)->slb_max; i++) {
if (!(to_svcpu(vcpu)->slb[i].esid & SLB_ESID_V))
found_inval = i;
else if ((to_svcpu(vcpu)->slb[i].esid & ESID_MASK) == esid)
return i;
}
/* Found a spare entry that was invalidated before */
if (found_inval > 0)
return found_inval;
/* No spare invalid entry, so create one */
if (mmu_slb_size < 64)
max_slb_size = mmu_slb_size;
/* Overflowing -> purge */
if ((to_svcpu(vcpu)->slb_max) == max_slb_size)
kvmppc_mmu_flush_segments(vcpu);
r = to_svcpu(vcpu)->slb_max;
to_svcpu(vcpu)->slb_max++;
return r;
}
int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr)
{
u64 esid = eaddr >> SID_SHIFT;
u64 slb_esid = (eaddr & ESID_MASK) | SLB_ESID_V;
u64 slb_vsid = SLB_VSID_USER;
u64 gvsid;
int slb_index;
struct kvmppc_sid_map *map;
slb_index = kvmppc_mmu_next_segment(vcpu, eaddr & ESID_MASK);
if (vcpu->arch.mmu.esid_to_vsid(vcpu, esid, &gvsid)) {
/* Invalidate an entry */
to_svcpu(vcpu)->slb[slb_index].esid = 0;
return -ENOENT;
}
map = find_sid_vsid(vcpu, gvsid);
if (!map)
map = create_sid_map(vcpu, gvsid);
map->guest_esid = esid;
slb_vsid |= (map->host_vsid << 12);
slb_vsid &= ~SLB_VSID_KP;
slb_esid |= slb_index;
to_svcpu(vcpu)->slb[slb_index].esid = slb_esid;
to_svcpu(vcpu)->slb[slb_index].vsid = slb_vsid;
dprintk_slb("slbmte %#llx, %#llx\n", slb_vsid, slb_esid);
return 0;
}
void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu)
{
to_svcpu(vcpu)->slb_max = 1;
to_svcpu(vcpu)->slb[0].esid = 0;
}
void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
{
kvmppc_mmu_hpte_destroy(vcpu);
__destroy_context(to_book3s(vcpu)->context_id);
}
int kvmppc_mmu_init(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
int err;
err = __init_new_context();
if (err < 0)
return -1;
vcpu3s->context_id = err;
vcpu3s->vsid_max = ((vcpu3s->context_id + 1) << USER_ESID_BITS) - 1;
vcpu3s->vsid_first = vcpu3s->context_id << USER_ESID_BITS;
vcpu3s->vsid_next = vcpu3s->vsid_first;
kvmppc_mmu_hpte_init(vcpu);
return 0;
}
|
