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
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
|
/*
* Copyright (C) 2011 Citrix Ltd.
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
* Contributions after 2012-01-13 are licensed under the terms of the
* GNU GPL, version 2 or (at your option) any later version.
*/
#include "qemu/osdep.h"
#include "qemu/units.h"
#include "qemu/error-report.h"
#include <sys/resource.h>
#include "hw/xen/xen-legacy-backend.h"
#include "qemu/bitmap.h"
#include <xen/hvm/params.h>
#include "sysemu/xen-mapcache.h"
#include "trace.h"
//#define MAPCACHE_DEBUG
#ifdef MAPCACHE_DEBUG
# define DPRINTF(fmt, ...) do { \
fprintf(stderr, "xen_mapcache: " fmt, ## __VA_ARGS__); \
} while (0)
#else
# define DPRINTF(fmt, ...) do { } while (0)
#endif
#if HOST_LONG_BITS == 32
# define MCACHE_BUCKET_SHIFT 16
# define MCACHE_MAX_SIZE (1UL<<31) /* 2GB Cap */
#else
# define MCACHE_BUCKET_SHIFT 20
# define MCACHE_MAX_SIZE (1UL<<35) /* 32GB Cap */
#endif
#define MCACHE_BUCKET_SIZE (1UL << MCACHE_BUCKET_SHIFT)
/* This is the size of the virtual address space reserve to QEMU that will not
* be use by MapCache.
* From empirical tests I observed that qemu use 75MB more than the
* max_mcache_size.
*/
#define NON_MCACHE_MEMORY_SIZE (80 * MiB)
typedef struct MapCacheEntry {
hwaddr paddr_index;
uint8_t *vaddr_base;
unsigned long *valid_mapping;
uint8_t lock;
#define XEN_MAPCACHE_ENTRY_DUMMY (1 << 0)
uint8_t flags;
hwaddr size;
struct MapCacheEntry *next;
} MapCacheEntry;
typedef struct MapCacheRev {
uint8_t *vaddr_req;
hwaddr paddr_index;
hwaddr size;
QTAILQ_ENTRY(MapCacheRev) next;
bool dma;
} MapCacheRev;
typedef struct MapCache {
MapCacheEntry *entry;
unsigned long nr_buckets;
QTAILQ_HEAD(, MapCacheRev) locked_entries;
/* For most cases (>99.9%), the page address is the same. */
MapCacheEntry *last_entry;
unsigned long max_mcache_size;
unsigned int mcache_bucket_shift;
phys_offset_to_gaddr_t phys_offset_to_gaddr;
QemuMutex lock;
void *opaque;
} MapCache;
static MapCache *mapcache;
static inline void mapcache_lock(void)
{
qemu_mutex_lock(&mapcache->lock);
}
static inline void mapcache_unlock(void)
{
qemu_mutex_unlock(&mapcache->lock);
}
static inline int test_bits(int nr, int size, const unsigned long *addr)
{
unsigned long res = find_next_zero_bit(addr, size + nr, nr);
if (res >= nr + size)
return 1;
else
return 0;
}
void xen_map_cache_init(phys_offset_to_gaddr_t f, void *opaque)
{
unsigned long size;
struct rlimit rlimit_as;
mapcache = g_malloc0(sizeof (MapCache));
mapcache->phys_offset_to_gaddr = f;
mapcache->opaque = opaque;
qemu_mutex_init(&mapcache->lock);
QTAILQ_INIT(&mapcache->locked_entries);
if (geteuid() == 0) {
rlimit_as.rlim_cur = RLIM_INFINITY;
rlimit_as.rlim_max = RLIM_INFINITY;
mapcache->max_mcache_size = MCACHE_MAX_SIZE;
} else {
getrlimit(RLIMIT_AS, &rlimit_as);
rlimit_as.rlim_cur = rlimit_as.rlim_max;
if (rlimit_as.rlim_max != RLIM_INFINITY) {
warn_report("QEMU's maximum size of virtual"
" memory is not infinity");
}
if (rlimit_as.rlim_max < MCACHE_MAX_SIZE + NON_MCACHE_MEMORY_SIZE) {
mapcache->max_mcache_size = rlimit_as.rlim_max -
NON_MCACHE_MEMORY_SIZE;
} else {
mapcache->max_mcache_size = MCACHE_MAX_SIZE;
}
}
setrlimit(RLIMIT_AS, &rlimit_as);
mapcache->nr_buckets =
(((mapcache->max_mcache_size >> XC_PAGE_SHIFT) +
(1UL << (MCACHE_BUCKET_SHIFT - XC_PAGE_SHIFT)) - 1) >>
(MCACHE_BUCKET_SHIFT - XC_PAGE_SHIFT));
size = mapcache->nr_buckets * sizeof (MapCacheEntry);
size = (size + XC_PAGE_SIZE - 1) & ~(XC_PAGE_SIZE - 1);
DPRINTF("%s, nr_buckets = %lx size %lu\n", __func__,
mapcache->nr_buckets, size);
mapcache->entry = g_malloc0(size);
}
static void xen_remap_bucket(MapCacheEntry *entry,
void *vaddr,
hwaddr size,
hwaddr address_index,
bool dummy)
{
uint8_t *vaddr_base;
xen_pfn_t *pfns;
int *err;
unsigned int i;
hwaddr nb_pfn = size >> XC_PAGE_SHIFT;
trace_xen_remap_bucket(address_index);
pfns = g_malloc0(nb_pfn * sizeof (xen_pfn_t));
err = g_malloc0(nb_pfn * sizeof (int));
if (entry->vaddr_base != NULL) {
if (!(entry->flags & XEN_MAPCACHE_ENTRY_DUMMY)) {
ram_block_notify_remove(entry->vaddr_base, entry->size);
}
if (munmap(entry->vaddr_base, entry->size) != 0) {
perror("unmap fails");
exit(-1);
}
}
g_free(entry->valid_mapping);
entry->valid_mapping = NULL;
for (i = 0; i < nb_pfn; i++) {
pfns[i] = (address_index << (MCACHE_BUCKET_SHIFT-XC_PAGE_SHIFT)) + i;
}
/*
* If the caller has requested the mapping at a specific address use
* MAP_FIXED to make sure it's honored.
*/
if (!dummy) {
vaddr_base = xenforeignmemory_map2(xen_fmem, xen_domid, vaddr,
PROT_READ | PROT_WRITE,
vaddr ? MAP_FIXED : 0,
nb_pfn, pfns, err);
if (vaddr_base == NULL) {
perror("xenforeignmemory_map2");
exit(-1);
}
} else {
/*
* We create dummy mappings where we are unable to create a foreign
* mapping immediately due to certain circumstances (i.e. on resume now)
*/
vaddr_base = mmap(vaddr, size, PROT_READ | PROT_WRITE,
MAP_ANON | MAP_SHARED | (vaddr ? MAP_FIXED : 0),
-1, 0);
if (vaddr_base == MAP_FAILED) {
perror("mmap");
exit(-1);
}
}
if (!(entry->flags & XEN_MAPCACHE_ENTRY_DUMMY)) {
ram_block_notify_add(vaddr_base, size);
}
entry->vaddr_base = vaddr_base;
entry->paddr_index = address_index;
entry->size = size;
entry->valid_mapping = (unsigned long *) g_malloc0(sizeof(unsigned long) *
BITS_TO_LONGS(size >> XC_PAGE_SHIFT));
if (dummy) {
entry->flags |= XEN_MAPCACHE_ENTRY_DUMMY;
} else {
entry->flags &= ~(XEN_MAPCACHE_ENTRY_DUMMY);
}
bitmap_zero(entry->valid_mapping, nb_pfn);
for (i = 0; i < nb_pfn; i++) {
if (!err[i]) {
bitmap_set(entry->valid_mapping, i, 1);
}
}
g_free(pfns);
g_free(err);
}
static uint8_t *xen_map_cache_unlocked(hwaddr phys_addr, hwaddr size,
uint8_t lock, bool dma)
{
MapCacheEntry *entry, *pentry = NULL,
*free_entry = NULL, *free_pentry = NULL;
hwaddr address_index;
hwaddr address_offset;
hwaddr cache_size = size;
hwaddr test_bit_size;
bool translated G_GNUC_UNUSED = false;
bool dummy = false;
tryagain:
address_index = phys_addr >> MCACHE_BUCKET_SHIFT;
address_offset = phys_addr & (MCACHE_BUCKET_SIZE - 1);
trace_xen_map_cache(phys_addr);
/* test_bit_size is always a multiple of XC_PAGE_SIZE */
if (size) {
test_bit_size = size + (phys_addr & (XC_PAGE_SIZE - 1));
if (test_bit_size % XC_PAGE_SIZE) {
test_bit_size += XC_PAGE_SIZE - (test_bit_size % XC_PAGE_SIZE);
}
} else {
test_bit_size = XC_PAGE_SIZE;
}
if (mapcache->last_entry != NULL &&
mapcache->last_entry->paddr_index == address_index &&
!lock && !size &&
test_bits(address_offset >> XC_PAGE_SHIFT,
test_bit_size >> XC_PAGE_SHIFT,
mapcache->last_entry->valid_mapping)) {
trace_xen_map_cache_return(mapcache->last_entry->vaddr_base + address_offset);
return mapcache->last_entry->vaddr_base + address_offset;
}
/* size is always a multiple of MCACHE_BUCKET_SIZE */
if (size) {
cache_size = size + address_offset;
if (cache_size % MCACHE_BUCKET_SIZE) {
cache_size += MCACHE_BUCKET_SIZE - (cache_size % MCACHE_BUCKET_SIZE);
}
} else {
cache_size = MCACHE_BUCKET_SIZE;
}
entry = &mapcache->entry[address_index % mapcache->nr_buckets];
while (entry && (lock || entry->lock) && entry->vaddr_base &&
(entry->paddr_index != address_index || entry->size != cache_size ||
!test_bits(address_offset >> XC_PAGE_SHIFT,
test_bit_size >> XC_PAGE_SHIFT,
entry->valid_mapping))) {
if (!free_entry && !entry->lock) {
free_entry = entry;
free_pentry = pentry;
}
pentry = entry;
entry = entry->next;
}
if (!entry && free_entry) {
entry = free_entry;
pentry = free_pentry;
}
if (!entry) {
entry = g_malloc0(sizeof (MapCacheEntry));
pentry->next = entry;
xen_remap_bucket(entry, NULL, cache_size, address_index, dummy);
} else if (!entry->lock) {
if (!entry->vaddr_base || entry->paddr_index != address_index ||
entry->size != cache_size ||
!test_bits(address_offset >> XC_PAGE_SHIFT,
test_bit_size >> XC_PAGE_SHIFT,
entry->valid_mapping)) {
xen_remap_bucket(entry, NULL, cache_size, address_index, dummy);
}
}
if(!test_bits(address_offset >> XC_PAGE_SHIFT,
test_bit_size >> XC_PAGE_SHIFT,
entry->valid_mapping)) {
mapcache->last_entry = NULL;
#ifdef XEN_COMPAT_PHYSMAP
if (!translated && mapcache->phys_offset_to_gaddr) {
phys_addr = mapcache->phys_offset_to_gaddr(phys_addr, size);
translated = true;
goto tryagain;
}
#endif
if (!dummy && runstate_check(RUN_STATE_INMIGRATE)) {
dummy = true;
goto tryagain;
}
trace_xen_map_cache_return(NULL);
return NULL;
}
mapcache->last_entry = entry;
if (lock) {
MapCacheRev *reventry = g_malloc0(sizeof(MapCacheRev));
entry->lock++;
reventry->dma = dma;
reventry->vaddr_req = mapcache->last_entry->vaddr_base + address_offset;
reventry->paddr_index = mapcache->last_entry->paddr_index;
reventry->size = entry->size;
QTAILQ_INSERT_HEAD(&mapcache->locked_entries, reventry, next);
}
trace_xen_map_cache_return(mapcache->last_entry->vaddr_base + address_offset);
return mapcache->last_entry->vaddr_base + address_offset;
}
uint8_t *xen_map_cache(hwaddr phys_addr, hwaddr size,
uint8_t lock, bool dma)
{
uint8_t *p;
mapcache_lock();
p = xen_map_cache_unlocked(phys_addr, size, lock, dma);
mapcache_unlock();
return p;
}
ram_addr_t xen_ram_addr_from_mapcache(void *ptr)
{
MapCacheEntry *entry = NULL;
MapCacheRev *reventry;
hwaddr paddr_index;
hwaddr size;
ram_addr_t raddr;
int found = 0;
mapcache_lock();
QTAILQ_FOREACH(reventry, &mapcache->locked_entries, next) {
if (reventry->vaddr_req == ptr) {
paddr_index = reventry->paddr_index;
size = reventry->size;
found = 1;
break;
}
}
if (!found) {
fprintf(stderr, "%s, could not find %p\n", __func__, ptr);
QTAILQ_FOREACH(reventry, &mapcache->locked_entries, next) {
DPRINTF(" "TARGET_FMT_plx" -> %p is present\n", reventry->paddr_index,
reventry->vaddr_req);
}
abort();
return 0;
}
entry = &mapcache->entry[paddr_index % mapcache->nr_buckets];
while (entry && (entry->paddr_index != paddr_index || entry->size != size)) {
entry = entry->next;
}
if (!entry) {
DPRINTF("Trying to find address %p that is not in the mapcache!\n", ptr);
raddr = 0;
} else {
raddr = (reventry->paddr_index << MCACHE_BUCKET_SHIFT) +
((unsigned long) ptr - (unsigned long) entry->vaddr_base);
}
mapcache_unlock();
return raddr;
}
static void xen_invalidate_map_cache_entry_unlocked(uint8_t *buffer)
{
MapCacheEntry *entry = NULL, *pentry = NULL;
MapCacheRev *reventry;
hwaddr paddr_index;
hwaddr size;
int found = 0;
QTAILQ_FOREACH(reventry, &mapcache->locked_entries, next) {
if (reventry->vaddr_req == buffer) {
paddr_index = reventry->paddr_index;
size = reventry->size;
found = 1;
break;
}
}
if (!found) {
DPRINTF("%s, could not find %p\n", __func__, buffer);
QTAILQ_FOREACH(reventry, &mapcache->locked_entries, next) {
DPRINTF(" "TARGET_FMT_plx" -> %p is present\n", reventry->paddr_index, reventry->vaddr_req);
}
return;
}
QTAILQ_REMOVE(&mapcache->locked_entries, reventry, next);
g_free(reventry);
if (mapcache->last_entry != NULL &&
mapcache->last_entry->paddr_index == paddr_index) {
mapcache->last_entry = NULL;
}
entry = &mapcache->entry[paddr_index % mapcache->nr_buckets];
while (entry && (entry->paddr_index != paddr_index || entry->size != size)) {
pentry = entry;
entry = entry->next;
}
if (!entry) {
DPRINTF("Trying to unmap address %p that is not in the mapcache!\n", buffer);
return;
}
entry->lock--;
if (entry->lock > 0 || pentry == NULL) {
return;
}
pentry->next = entry->next;
ram_block_notify_remove(entry->vaddr_base, entry->size);
if (munmap(entry->vaddr_base, entry->size) != 0) {
perror("unmap fails");
exit(-1);
}
g_free(entry->valid_mapping);
g_free(entry);
}
void xen_invalidate_map_cache_entry(uint8_t *buffer)
{
mapcache_lock();
xen_invalidate_map_cache_entry_unlocked(buffer);
mapcache_unlock();
}
void xen_invalidate_map_cache(void)
{
unsigned long i;
MapCacheRev *reventry;
/* Flush pending AIO before destroying the mapcache */
bdrv_drain_all();
mapcache_lock();
QTAILQ_FOREACH(reventry, &mapcache->locked_entries, next) {
if (!reventry->dma) {
continue;
}
fprintf(stderr, "Locked DMA mapping while invalidating mapcache!"
" "TARGET_FMT_plx" -> %p is present\n",
reventry->paddr_index, reventry->vaddr_req);
}
for (i = 0; i < mapcache->nr_buckets; i++) {
MapCacheEntry *entry = &mapcache->entry[i];
if (entry->vaddr_base == NULL) {
continue;
}
if (entry->lock > 0) {
continue;
}
if (munmap(entry->vaddr_base, entry->size) != 0) {
perror("unmap fails");
exit(-1);
}
entry->paddr_index = 0;
entry->vaddr_base = NULL;
entry->size = 0;
g_free(entry->valid_mapping);
entry->valid_mapping = NULL;
}
mapcache->last_entry = NULL;
mapcache_unlock();
}
static uint8_t *xen_replace_cache_entry_unlocked(hwaddr old_phys_addr,
hwaddr new_phys_addr,
hwaddr size)
{
MapCacheEntry *entry;
hwaddr address_index, address_offset;
hwaddr test_bit_size, cache_size = size;
address_index = old_phys_addr >> MCACHE_BUCKET_SHIFT;
address_offset = old_phys_addr & (MCACHE_BUCKET_SIZE - 1);
assert(size);
/* test_bit_size is always a multiple of XC_PAGE_SIZE */
test_bit_size = size + (old_phys_addr & (XC_PAGE_SIZE - 1));
if (test_bit_size % XC_PAGE_SIZE) {
test_bit_size += XC_PAGE_SIZE - (test_bit_size % XC_PAGE_SIZE);
}
cache_size = size + address_offset;
if (cache_size % MCACHE_BUCKET_SIZE) {
cache_size += MCACHE_BUCKET_SIZE - (cache_size % MCACHE_BUCKET_SIZE);
}
entry = &mapcache->entry[address_index % mapcache->nr_buckets];
while (entry && !(entry->paddr_index == address_index &&
entry->size == cache_size)) {
entry = entry->next;
}
if (!entry) {
DPRINTF("Trying to update an entry for "TARGET_FMT_plx \
"that is not in the mapcache!\n", old_phys_addr);
return NULL;
}
address_index = new_phys_addr >> MCACHE_BUCKET_SHIFT;
address_offset = new_phys_addr & (MCACHE_BUCKET_SIZE - 1);
fprintf(stderr, "Replacing a dummy mapcache entry for "TARGET_FMT_plx \
" with "TARGET_FMT_plx"\n", old_phys_addr, new_phys_addr);
xen_remap_bucket(entry, entry->vaddr_base,
cache_size, address_index, false);
if (!test_bits(address_offset >> XC_PAGE_SHIFT,
test_bit_size >> XC_PAGE_SHIFT,
entry->valid_mapping)) {
DPRINTF("Unable to update a mapcache entry for "TARGET_FMT_plx"!\n",
old_phys_addr);
return NULL;
}
return entry->vaddr_base + address_offset;
}
uint8_t *xen_replace_cache_entry(hwaddr old_phys_addr,
hwaddr new_phys_addr,
hwaddr size)
{
uint8_t *p;
mapcache_lock();
p = xen_replace_cache_entry_unlocked(old_phys_addr, new_phys_addr, size);
mapcache_unlock();
return p;
}
|