forked from awilliam/qemu-vfio
-
Notifications
You must be signed in to change notification settings - Fork 0
/
exec.c
2618 lines (2289 loc) · 73.6 KB
/
exec.c
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
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* Virtual page mapping
*
* Copyright (c) 2003 Fabrice Bellard
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This library 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
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, see <http://www.gnu.org/licenses/>.
*/
#include "config.h"
#ifdef _WIN32
#include <windows.h>
#else
#include <sys/types.h>
#include <sys/mman.h>
#endif
#include "qemu-common.h"
#include "cpu.h"
#include "tcg.h"
#include "hw/hw.h"
#include "hw/qdev.h"
#include "qemu/osdep.h"
#include "sysemu/kvm.h"
#include "hw/xen.h"
#include "qemu/timer.h"
#include "qemu/config-file.h"
#include "exec/memory.h"
#include "sysemu/dma.h"
#include "exec/address-spaces.h"
#if defined(CONFIG_USER_ONLY)
#include <qemu.h>
#else /* !CONFIG_USER_ONLY */
#include "sysemu/xen-mapcache.h"
#include "trace.h"
#endif
#include "exec/cpu-all.h"
#include "exec/cputlb.h"
#include "translate-all.h"
#include "exec/memory-internal.h"
//#define DEBUG_UNASSIGNED
//#define DEBUG_SUBPAGE
#if !defined(CONFIG_USER_ONLY)
int phys_ram_fd;
static int in_migration;
RAMList ram_list = { .blocks = QTAILQ_HEAD_INITIALIZER(ram_list.blocks) };
static MemoryRegion *system_memory;
static MemoryRegion *system_io;
AddressSpace address_space_io;
AddressSpace address_space_memory;
DMAContext dma_context_memory;
MemoryRegion io_mem_ram, io_mem_rom, io_mem_unassigned, io_mem_notdirty;
static MemoryRegion io_mem_subpage_ram;
#endif
CPUArchState *first_cpu;
/* current CPU in the current thread. It is only valid inside
cpu_exec() */
DEFINE_TLS(CPUArchState *,cpu_single_env);
/* 0 = Do not count executed instructions.
1 = Precise instruction counting.
2 = Adaptive rate instruction counting. */
int use_icount;
#if !defined(CONFIG_USER_ONLY)
static MemoryRegionSection *phys_sections;
static unsigned phys_sections_nb, phys_sections_nb_alloc;
static uint16_t phys_section_unassigned;
static uint16_t phys_section_notdirty;
static uint16_t phys_section_rom;
static uint16_t phys_section_watch;
/* Simple allocator for PhysPageEntry nodes */
static PhysPageEntry (*phys_map_nodes)[L2_SIZE];
static unsigned phys_map_nodes_nb, phys_map_nodes_nb_alloc;
#define PHYS_MAP_NODE_NIL (((uint16_t)~0) >> 1)
static void io_mem_init(void);
static void memory_map_init(void);
static void *qemu_safe_ram_ptr(ram_addr_t addr);
static MemoryRegion io_mem_watch;
#endif
#if !defined(CONFIG_USER_ONLY)
static void phys_map_node_reserve(unsigned nodes)
{
if (phys_map_nodes_nb + nodes > phys_map_nodes_nb_alloc) {
typedef PhysPageEntry Node[L2_SIZE];
phys_map_nodes_nb_alloc = MAX(phys_map_nodes_nb_alloc * 2, 16);
phys_map_nodes_nb_alloc = MAX(phys_map_nodes_nb_alloc,
phys_map_nodes_nb + nodes);
phys_map_nodes = g_renew(Node, phys_map_nodes,
phys_map_nodes_nb_alloc);
}
}
static uint16_t phys_map_node_alloc(void)
{
unsigned i;
uint16_t ret;
ret = phys_map_nodes_nb++;
assert(ret != PHYS_MAP_NODE_NIL);
assert(ret != phys_map_nodes_nb_alloc);
for (i = 0; i < L2_SIZE; ++i) {
phys_map_nodes[ret][i].is_leaf = 0;
phys_map_nodes[ret][i].ptr = PHYS_MAP_NODE_NIL;
}
return ret;
}
static void phys_map_nodes_reset(void)
{
phys_map_nodes_nb = 0;
}
static void phys_page_set_level(PhysPageEntry *lp, hwaddr *index,
hwaddr *nb, uint16_t leaf,
int level)
{
PhysPageEntry *p;
int i;
hwaddr step = (hwaddr)1 << (level * L2_BITS);
if (!lp->is_leaf && lp->ptr == PHYS_MAP_NODE_NIL) {
lp->ptr = phys_map_node_alloc();
p = phys_map_nodes[lp->ptr];
if (level == 0) {
for (i = 0; i < L2_SIZE; i++) {
p[i].is_leaf = 1;
p[i].ptr = phys_section_unassigned;
}
}
} else {
p = phys_map_nodes[lp->ptr];
}
lp = &p[(*index >> (level * L2_BITS)) & (L2_SIZE - 1)];
while (*nb && lp < &p[L2_SIZE]) {
if ((*index & (step - 1)) == 0 && *nb >= step) {
lp->is_leaf = true;
lp->ptr = leaf;
*index += step;
*nb -= step;
} else {
phys_page_set_level(lp, index, nb, leaf, level - 1);
}
++lp;
}
}
static void phys_page_set(AddressSpaceDispatch *d,
hwaddr index, hwaddr nb,
uint16_t leaf)
{
/* Wildly overreserve - it doesn't matter much. */
phys_map_node_reserve(3 * P_L2_LEVELS);
phys_page_set_level(&d->phys_map, &index, &nb, leaf, P_L2_LEVELS - 1);
}
MemoryRegionSection *phys_page_find(AddressSpaceDispatch *d, hwaddr index)
{
PhysPageEntry lp = d->phys_map;
PhysPageEntry *p;
int i;
uint16_t s_index = phys_section_unassigned;
for (i = P_L2_LEVELS - 1; i >= 0 && !lp.is_leaf; i--) {
if (lp.ptr == PHYS_MAP_NODE_NIL) {
goto not_found;
}
p = phys_map_nodes[lp.ptr];
lp = p[(index >> (i * L2_BITS)) & (L2_SIZE - 1)];
}
s_index = lp.ptr;
not_found:
return &phys_sections[s_index];
}
bool memory_region_is_unassigned(MemoryRegion *mr)
{
return mr != &io_mem_ram && mr != &io_mem_rom
&& mr != &io_mem_notdirty && !mr->rom_device
&& mr != &io_mem_watch;
}
#endif
void cpu_exec_init_all(void)
{
#if !defined(CONFIG_USER_ONLY)
qemu_mutex_init(&ram_list.mutex);
memory_map_init();
io_mem_init();
#endif
}
#if defined(CPU_SAVE_VERSION) && !defined(CONFIG_USER_ONLY)
static int cpu_common_post_load(void *opaque, int version_id)
{
CPUArchState *env = opaque;
/* 0x01 was CPU_INTERRUPT_EXIT. This line can be removed when the
version_id is increased. */
env->interrupt_request &= ~0x01;
tlb_flush(env, 1);
return 0;
}
static const VMStateDescription vmstate_cpu_common = {
.name = "cpu_common",
.version_id = 1,
.minimum_version_id = 1,
.minimum_version_id_old = 1,
.post_load = cpu_common_post_load,
.fields = (VMStateField []) {
VMSTATE_UINT32(halted, CPUArchState),
VMSTATE_UINT32(interrupt_request, CPUArchState),
VMSTATE_END_OF_LIST()
}
};
#endif
CPUState *qemu_get_cpu(int index)
{
CPUArchState *env = first_cpu;
CPUState *cpu = NULL;
while (env) {
cpu = ENV_GET_CPU(env);
if (cpu->cpu_index == index) {
break;
}
env = env->next_cpu;
}
return cpu;
}
void cpu_exec_init(CPUArchState *env)
{
CPUState *cpu = ENV_GET_CPU(env);
CPUArchState **penv;
int cpu_index;
#if defined(CONFIG_USER_ONLY)
cpu_list_lock();
#endif
env->next_cpu = NULL;
penv = &first_cpu;
cpu_index = 0;
while (*penv != NULL) {
penv = &(*penv)->next_cpu;
cpu_index++;
}
cpu->cpu_index = cpu_index;
cpu->numa_node = 0;
QTAILQ_INIT(&env->breakpoints);
QTAILQ_INIT(&env->watchpoints);
#ifndef CONFIG_USER_ONLY
cpu->thread_id = qemu_get_thread_id();
#endif
*penv = env;
#if defined(CONFIG_USER_ONLY)
cpu_list_unlock();
#endif
#if defined(CPU_SAVE_VERSION) && !defined(CONFIG_USER_ONLY)
vmstate_register(NULL, cpu_index, &vmstate_cpu_common, env);
register_savevm(NULL, "cpu", cpu_index, CPU_SAVE_VERSION,
cpu_save, cpu_load, env);
#endif
}
#if defined(TARGET_HAS_ICE)
#if defined(CONFIG_USER_ONLY)
static void breakpoint_invalidate(CPUArchState *env, target_ulong pc)
{
tb_invalidate_phys_page_range(pc, pc + 1, 0);
}
#else
static void breakpoint_invalidate(CPUArchState *env, target_ulong pc)
{
tb_invalidate_phys_addr(cpu_get_phys_page_debug(env, pc) |
(pc & ~TARGET_PAGE_MASK));
}
#endif
#endif /* TARGET_HAS_ICE */
#if defined(CONFIG_USER_ONLY)
void cpu_watchpoint_remove_all(CPUArchState *env, int mask)
{
}
int cpu_watchpoint_insert(CPUArchState *env, target_ulong addr, target_ulong len,
int flags, CPUWatchpoint **watchpoint)
{
return -ENOSYS;
}
#else
/* Add a watchpoint. */
int cpu_watchpoint_insert(CPUArchState *env, target_ulong addr, target_ulong len,
int flags, CPUWatchpoint **watchpoint)
{
target_ulong len_mask = ~(len - 1);
CPUWatchpoint *wp;
/* sanity checks: allow power-of-2 lengths, deny unaligned watchpoints */
if ((len & (len - 1)) || (addr & ~len_mask) ||
len == 0 || len > TARGET_PAGE_SIZE) {
fprintf(stderr, "qemu: tried to set invalid watchpoint at "
TARGET_FMT_lx ", len=" TARGET_FMT_lu "\n", addr, len);
return -EINVAL;
}
wp = g_malloc(sizeof(*wp));
wp->vaddr = addr;
wp->len_mask = len_mask;
wp->flags = flags;
/* keep all GDB-injected watchpoints in front */
if (flags & BP_GDB)
QTAILQ_INSERT_HEAD(&env->watchpoints, wp, entry);
else
QTAILQ_INSERT_TAIL(&env->watchpoints, wp, entry);
tlb_flush_page(env, addr);
if (watchpoint)
*watchpoint = wp;
return 0;
}
/* Remove a specific watchpoint. */
int cpu_watchpoint_remove(CPUArchState *env, target_ulong addr, target_ulong len,
int flags)
{
target_ulong len_mask = ~(len - 1);
CPUWatchpoint *wp;
QTAILQ_FOREACH(wp, &env->watchpoints, entry) {
if (addr == wp->vaddr && len_mask == wp->len_mask
&& flags == (wp->flags & ~BP_WATCHPOINT_HIT)) {
cpu_watchpoint_remove_by_ref(env, wp);
return 0;
}
}
return -ENOENT;
}
/* Remove a specific watchpoint by reference. */
void cpu_watchpoint_remove_by_ref(CPUArchState *env, CPUWatchpoint *watchpoint)
{
QTAILQ_REMOVE(&env->watchpoints, watchpoint, entry);
tlb_flush_page(env, watchpoint->vaddr);
g_free(watchpoint);
}
/* Remove all matching watchpoints. */
void cpu_watchpoint_remove_all(CPUArchState *env, int mask)
{
CPUWatchpoint *wp, *next;
QTAILQ_FOREACH_SAFE(wp, &env->watchpoints, entry, next) {
if (wp->flags & mask)
cpu_watchpoint_remove_by_ref(env, wp);
}
}
#endif
/* Add a breakpoint. */
int cpu_breakpoint_insert(CPUArchState *env, target_ulong pc, int flags,
CPUBreakpoint **breakpoint)
{
#if defined(TARGET_HAS_ICE)
CPUBreakpoint *bp;
bp = g_malloc(sizeof(*bp));
bp->pc = pc;
bp->flags = flags;
/* keep all GDB-injected breakpoints in front */
if (flags & BP_GDB)
QTAILQ_INSERT_HEAD(&env->breakpoints, bp, entry);
else
QTAILQ_INSERT_TAIL(&env->breakpoints, bp, entry);
breakpoint_invalidate(env, pc);
if (breakpoint)
*breakpoint = bp;
return 0;
#else
return -ENOSYS;
#endif
}
/* Remove a specific breakpoint. */
int cpu_breakpoint_remove(CPUArchState *env, target_ulong pc, int flags)
{
#if defined(TARGET_HAS_ICE)
CPUBreakpoint *bp;
QTAILQ_FOREACH(bp, &env->breakpoints, entry) {
if (bp->pc == pc && bp->flags == flags) {
cpu_breakpoint_remove_by_ref(env, bp);
return 0;
}
}
return -ENOENT;
#else
return -ENOSYS;
#endif
}
/* Remove a specific breakpoint by reference. */
void cpu_breakpoint_remove_by_ref(CPUArchState *env, CPUBreakpoint *breakpoint)
{
#if defined(TARGET_HAS_ICE)
QTAILQ_REMOVE(&env->breakpoints, breakpoint, entry);
breakpoint_invalidate(env, breakpoint->pc);
g_free(breakpoint);
#endif
}
/* Remove all matching breakpoints. */
void cpu_breakpoint_remove_all(CPUArchState *env, int mask)
{
#if defined(TARGET_HAS_ICE)
CPUBreakpoint *bp, *next;
QTAILQ_FOREACH_SAFE(bp, &env->breakpoints, entry, next) {
if (bp->flags & mask)
cpu_breakpoint_remove_by_ref(env, bp);
}
#endif
}
/* enable or disable single step mode. EXCP_DEBUG is returned by the
CPU loop after each instruction */
void cpu_single_step(CPUArchState *env, int enabled)
{
#if defined(TARGET_HAS_ICE)
if (env->singlestep_enabled != enabled) {
env->singlestep_enabled = enabled;
if (kvm_enabled())
kvm_update_guest_debug(env, 0);
else {
/* must flush all the translated code to avoid inconsistencies */
/* XXX: only flush what is necessary */
tb_flush(env);
}
}
#endif
}
void cpu_reset_interrupt(CPUArchState *env, int mask)
{
env->interrupt_request &= ~mask;
}
void cpu_exit(CPUArchState *env)
{
CPUState *cpu = ENV_GET_CPU(env);
cpu->exit_request = 1;
cpu->tcg_exit_req = 1;
}
void cpu_abort(CPUArchState *env, const char *fmt, ...)
{
va_list ap;
va_list ap2;
va_start(ap, fmt);
va_copy(ap2, ap);
fprintf(stderr, "qemu: fatal: ");
vfprintf(stderr, fmt, ap);
fprintf(stderr, "\n");
cpu_dump_state(env, stderr, fprintf, CPU_DUMP_FPU | CPU_DUMP_CCOP);
if (qemu_log_enabled()) {
qemu_log("qemu: fatal: ");
qemu_log_vprintf(fmt, ap2);
qemu_log("\n");
log_cpu_state(env, CPU_DUMP_FPU | CPU_DUMP_CCOP);
qemu_log_flush();
qemu_log_close();
}
va_end(ap2);
va_end(ap);
#if defined(CONFIG_USER_ONLY)
{
struct sigaction act;
sigfillset(&act.sa_mask);
act.sa_handler = SIG_DFL;
sigaction(SIGABRT, &act, NULL);
}
#endif
abort();
}
CPUArchState *cpu_copy(CPUArchState *env)
{
CPUArchState *new_env = cpu_init(env->cpu_model_str);
CPUArchState *next_cpu = new_env->next_cpu;
#if defined(TARGET_HAS_ICE)
CPUBreakpoint *bp;
CPUWatchpoint *wp;
#endif
memcpy(new_env, env, sizeof(CPUArchState));
/* Preserve chaining. */
new_env->next_cpu = next_cpu;
/* Clone all break/watchpoints.
Note: Once we support ptrace with hw-debug register access, make sure
BP_CPU break/watchpoints are handled correctly on clone. */
QTAILQ_INIT(&env->breakpoints);
QTAILQ_INIT(&env->watchpoints);
#if defined(TARGET_HAS_ICE)
QTAILQ_FOREACH(bp, &env->breakpoints, entry) {
cpu_breakpoint_insert(new_env, bp->pc, bp->flags, NULL);
}
QTAILQ_FOREACH(wp, &env->watchpoints, entry) {
cpu_watchpoint_insert(new_env, wp->vaddr, (~wp->len_mask) + 1,
wp->flags, NULL);
}
#endif
return new_env;
}
#if !defined(CONFIG_USER_ONLY)
static void tlb_reset_dirty_range_all(ram_addr_t start, ram_addr_t end,
uintptr_t length)
{
uintptr_t start1;
/* we modify the TLB cache so that the dirty bit will be set again
when accessing the range */
start1 = (uintptr_t)qemu_safe_ram_ptr(start);
/* Check that we don't span multiple blocks - this breaks the
address comparisons below. */
if ((uintptr_t)qemu_safe_ram_ptr(end - 1) - start1
!= (end - 1) - start) {
abort();
}
cpu_tlb_reset_dirty_all(start1, length);
}
/* Note: start and end must be within the same ram block. */
void cpu_physical_memory_reset_dirty(ram_addr_t start, ram_addr_t end,
int dirty_flags)
{
uintptr_t length;
start &= TARGET_PAGE_MASK;
end = TARGET_PAGE_ALIGN(end);
length = end - start;
if (length == 0)
return;
cpu_physical_memory_mask_dirty_range(start, length, dirty_flags);
if (tcg_enabled()) {
tlb_reset_dirty_range_all(start, end, length);
}
}
static int cpu_physical_memory_set_dirty_tracking(int enable)
{
int ret = 0;
in_migration = enable;
return ret;
}
hwaddr memory_region_section_get_iotlb(CPUArchState *env,
MemoryRegionSection *section,
target_ulong vaddr,
hwaddr paddr,
int prot,
target_ulong *address)
{
hwaddr iotlb;
CPUWatchpoint *wp;
if (memory_region_is_ram(section->mr)) {
/* Normal RAM. */
iotlb = (memory_region_get_ram_addr(section->mr) & TARGET_PAGE_MASK)
+ memory_region_section_addr(section, paddr);
if (!section->readonly) {
iotlb |= phys_section_notdirty;
} else {
iotlb |= phys_section_rom;
}
} else {
/* IO handlers are currently passed a physical address.
It would be nice to pass an offset from the base address
of that region. This would avoid having to special case RAM,
and avoid full address decoding in every device.
We can't use the high bits of pd for this because
IO_MEM_ROMD uses these as a ram address. */
iotlb = section - phys_sections;
iotlb += memory_region_section_addr(section, paddr);
}
/* Make accesses to pages with watchpoints go via the
watchpoint trap routines. */
QTAILQ_FOREACH(wp, &env->watchpoints, entry) {
if (vaddr == (wp->vaddr & TARGET_PAGE_MASK)) {
/* Avoid trapping reads of pages with a write breakpoint. */
if ((prot & PAGE_WRITE) || (wp->flags & BP_MEM_READ)) {
iotlb = phys_section_watch + paddr;
*address |= TLB_MMIO;
break;
}
}
}
return iotlb;
}
#endif /* defined(CONFIG_USER_ONLY) */
#if !defined(CONFIG_USER_ONLY)
#define SUBPAGE_IDX(addr) ((addr) & ~TARGET_PAGE_MASK)
typedef struct subpage_t {
MemoryRegion iomem;
hwaddr base;
uint16_t sub_section[TARGET_PAGE_SIZE];
} subpage_t;
static int subpage_register (subpage_t *mmio, uint32_t start, uint32_t end,
uint16_t section);
static subpage_t *subpage_init(hwaddr base);
static void destroy_page_desc(uint16_t section_index)
{
MemoryRegionSection *section = &phys_sections[section_index];
MemoryRegion *mr = section->mr;
if (mr->subpage) {
subpage_t *subpage = container_of(mr, subpage_t, iomem);
memory_region_destroy(&subpage->iomem);
g_free(subpage);
}
}
static void destroy_l2_mapping(PhysPageEntry *lp, unsigned level)
{
unsigned i;
PhysPageEntry *p;
if (lp->ptr == PHYS_MAP_NODE_NIL) {
return;
}
p = phys_map_nodes[lp->ptr];
for (i = 0; i < L2_SIZE; ++i) {
if (!p[i].is_leaf) {
destroy_l2_mapping(&p[i], level - 1);
} else {
destroy_page_desc(p[i].ptr);
}
}
lp->is_leaf = 0;
lp->ptr = PHYS_MAP_NODE_NIL;
}
static void destroy_all_mappings(AddressSpaceDispatch *d)
{
destroy_l2_mapping(&d->phys_map, P_L2_LEVELS - 1);
phys_map_nodes_reset();
}
static uint16_t phys_section_add(MemoryRegionSection *section)
{
if (phys_sections_nb == phys_sections_nb_alloc) {
phys_sections_nb_alloc = MAX(phys_sections_nb_alloc * 2, 16);
phys_sections = g_renew(MemoryRegionSection, phys_sections,
phys_sections_nb_alloc);
}
phys_sections[phys_sections_nb] = *section;
return phys_sections_nb++;
}
static void phys_sections_clear(void)
{
phys_sections_nb = 0;
}
static void register_subpage(AddressSpaceDispatch *d, MemoryRegionSection *section)
{
subpage_t *subpage;
hwaddr base = section->offset_within_address_space
& TARGET_PAGE_MASK;
MemoryRegionSection *existing = phys_page_find(d, base >> TARGET_PAGE_BITS);
MemoryRegionSection subsection = {
.offset_within_address_space = base,
.size = TARGET_PAGE_SIZE,
};
hwaddr start, end;
assert(existing->mr->subpage || existing->mr == &io_mem_unassigned);
if (!(existing->mr->subpage)) {
subpage = subpage_init(base);
subsection.mr = &subpage->iomem;
phys_page_set(d, base >> TARGET_PAGE_BITS, 1,
phys_section_add(&subsection));
} else {
subpage = container_of(existing->mr, subpage_t, iomem);
}
start = section->offset_within_address_space & ~TARGET_PAGE_MASK;
end = start + section->size - 1;
subpage_register(subpage, start, end, phys_section_add(section));
}
static void register_multipage(AddressSpaceDispatch *d, MemoryRegionSection *section)
{
hwaddr start_addr = section->offset_within_address_space;
ram_addr_t size = section->size;
hwaddr addr;
uint16_t section_index = phys_section_add(section);
assert(size);
addr = start_addr;
phys_page_set(d, addr >> TARGET_PAGE_BITS, size >> TARGET_PAGE_BITS,
section_index);
}
static void mem_add(MemoryListener *listener, MemoryRegionSection *section)
{
AddressSpaceDispatch *d = container_of(listener, AddressSpaceDispatch, listener);
MemoryRegionSection now = *section, remain = *section;
if ((now.offset_within_address_space & ~TARGET_PAGE_MASK)
|| (now.size < TARGET_PAGE_SIZE)) {
now.size = MIN(TARGET_PAGE_ALIGN(now.offset_within_address_space)
- now.offset_within_address_space,
now.size);
register_subpage(d, &now);
remain.size -= now.size;
remain.offset_within_address_space += now.size;
remain.offset_within_region += now.size;
}
while (remain.size >= TARGET_PAGE_SIZE) {
now = remain;
if (remain.offset_within_region & ~TARGET_PAGE_MASK) {
now.size = TARGET_PAGE_SIZE;
register_subpage(d, &now);
} else {
now.size &= TARGET_PAGE_MASK;
register_multipage(d, &now);
}
remain.size -= now.size;
remain.offset_within_address_space += now.size;
remain.offset_within_region += now.size;
}
now = remain;
if (now.size) {
register_subpage(d, &now);
}
}
void qemu_flush_coalesced_mmio_buffer(void)
{
if (kvm_enabled())
kvm_flush_coalesced_mmio_buffer();
}
void qemu_mutex_lock_ramlist(void)
{
qemu_mutex_lock(&ram_list.mutex);
}
void qemu_mutex_unlock_ramlist(void)
{
qemu_mutex_unlock(&ram_list.mutex);
}
#if defined(__linux__) && !defined(TARGET_S390X)
#include <sys/vfs.h>
#define HUGETLBFS_MAGIC 0x958458f6
static long gethugepagesize(const char *path)
{
struct statfs fs;
int ret;
do {
ret = statfs(path, &fs);
} while (ret != 0 && errno == EINTR);
if (ret != 0) {
perror(path);
return 0;
}
if (fs.f_type != HUGETLBFS_MAGIC)
fprintf(stderr, "Warning: path not on HugeTLBFS: %s\n", path);
return fs.f_bsize;
}
static void *file_ram_alloc(RAMBlock *block,
ram_addr_t memory,
const char *path)
{
char *filename;
void *area;
int fd;
#ifdef MAP_POPULATE
int flags;
#endif
unsigned long hpagesize;
hpagesize = gethugepagesize(path);
if (!hpagesize) {
return NULL;
}
if (memory < hpagesize) {
return NULL;
}
if (kvm_enabled() && !kvm_has_sync_mmu()) {
fprintf(stderr, "host lacks kvm mmu notifiers, -mem-path unsupported\n");
return NULL;
}
filename = g_strdup_printf("%s/qemu_back_mem.XXXXXX", path);
fd = mkstemp(filename);
if (fd < 0) {
perror("unable to create backing store for hugepages");
g_free(filename);
return NULL;
}
unlink(filename);
g_free(filename);
memory = (memory+hpagesize-1) & ~(hpagesize-1);
/*
* ftruncate is not supported by hugetlbfs in older
* hosts, so don't bother bailing out on errors.
* If anything goes wrong with it under other filesystems,
* mmap will fail.
*/
if (ftruncate(fd, memory))
perror("ftruncate");
#ifdef MAP_POPULATE
/* NB: MAP_POPULATE won't exhaustively alloc all phys pages in the case
* MAP_PRIVATE is requested. For mem_prealloc we mmap as MAP_SHARED
* to sidestep this quirk.
*/
flags = mem_prealloc ? MAP_POPULATE | MAP_SHARED : MAP_PRIVATE;
area = mmap(0, memory, PROT_READ | PROT_WRITE, flags, fd, 0);
#else
area = mmap(0, memory, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
#endif
if (area == MAP_FAILED) {
perror("file_ram_alloc: can't mmap RAM pages");
close(fd);
return (NULL);
}
block->fd = fd;
return area;
}
#endif
static ram_addr_t find_ram_offset(ram_addr_t size)
{
RAMBlock *block, *next_block;
ram_addr_t offset = RAM_ADDR_MAX, mingap = RAM_ADDR_MAX;
if (QTAILQ_EMPTY(&ram_list.blocks))
return 0;
QTAILQ_FOREACH(block, &ram_list.blocks, next) {
ram_addr_t end, next = RAM_ADDR_MAX;
end = block->offset + block->length;
QTAILQ_FOREACH(next_block, &ram_list.blocks, next) {
if (next_block->offset >= end) {
next = MIN(next, next_block->offset);
}
}
if (next - end >= size && next - end < mingap) {
offset = end;
mingap = next - end;
}
}
if (offset == RAM_ADDR_MAX) {
fprintf(stderr, "Failed to find gap of requested size: %" PRIu64 "\n",
(uint64_t)size);
abort();
}
return offset;
}
ram_addr_t last_ram_offset(void)
{
RAMBlock *block;
ram_addr_t last = 0;
QTAILQ_FOREACH(block, &ram_list.blocks, next)
last = MAX(last, block->offset + block->length);
return last;
}
static void qemu_ram_setup_dump(void *addr, ram_addr_t size)
{
int ret;
QemuOpts *machine_opts;
/* Use MADV_DONTDUMP, if user doesn't want the guest memory in the core */
machine_opts = qemu_opts_find(qemu_find_opts("machine"), 0);
if (machine_opts &&
!qemu_opt_get_bool(machine_opts, "dump-guest-core", true)) {
ret = qemu_madvise(addr, size, QEMU_MADV_DONTDUMP);
if (ret) {
perror("qemu_madvise");
fprintf(stderr, "madvise doesn't support MADV_DONTDUMP, "
"but dump_guest_core=off specified\n");
}
}
}
void qemu_ram_set_idstr(ram_addr_t addr, const char *name, DeviceState *dev)
{
RAMBlock *new_block, *block;
new_block = NULL;
QTAILQ_FOREACH(block, &ram_list.blocks, next) {
if (block->offset == addr) {
new_block = block;
break;
}
}
assert(new_block);
assert(!new_block->idstr[0]);
if (dev) {
char *id = qdev_get_dev_path(dev);
if (id) {
snprintf(new_block->idstr, sizeof(new_block->idstr), "%s/", id);
g_free(id);
}
}
pstrcat(new_block->idstr, sizeof(new_block->idstr), name);
/* This assumes the iothread lock is taken here too. */
qemu_mutex_lock_ramlist();
QTAILQ_FOREACH(block, &ram_list.blocks, next) {
if (block != new_block && !strcmp(block->idstr, new_block->idstr)) {
fprintf(stderr, "RAMBlock \"%s\" already registered, abort!\n",
new_block->idstr);