aboutsummaryrefslogtreecommitdiff
path: root/accel/tcg/cputlb.c
blob: af57aca5e4e6ecd70a7a384b06e509cdf72e9adb (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
/*
 *  Common CPU TLB handling
 *
 *  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 "qemu/osdep.h"
#include "qemu/main-loop.h"
#include "cpu.h"
#include "exec/exec-all.h"
#include "exec/memory.h"
#include "exec/address-spaces.h"
#include "exec/cpu_ldst.h"
#include "exec/cputlb.h"
#include "exec/memory-internal.h"
#include "exec/ram_addr.h"
#include "tcg/tcg.h"
#include "qemu/error-report.h"
#include "exec/log.h"
#include "exec/helper-proto.h"
#include "qemu/atomic.h"
#include "qemu/atomic128.h"

/* DEBUG defines, enable DEBUG_TLB_LOG to log to the CPU_LOG_MMU target */
/* #define DEBUG_TLB */
/* #define DEBUG_TLB_LOG */

#ifdef DEBUG_TLB
# define DEBUG_TLB_GATE 1
# ifdef DEBUG_TLB_LOG
#  define DEBUG_TLB_LOG_GATE 1
# else
#  define DEBUG_TLB_LOG_GATE 0
# endif
#else
# define DEBUG_TLB_GATE 0
# define DEBUG_TLB_LOG_GATE 0
#endif

#define tlb_debug(fmt, ...) do { \
    if (DEBUG_TLB_LOG_GATE) { \
        qemu_log_mask(CPU_LOG_MMU, "%s: " fmt, __func__, \
                      ## __VA_ARGS__); \
    } else if (DEBUG_TLB_GATE) { \
        fprintf(stderr, "%s: " fmt, __func__, ## __VA_ARGS__); \
    } \
} while (0)

#define assert_cpu_is_self(cpu) do {                              \
        if (DEBUG_TLB_GATE) {                                     \
            g_assert(!(cpu)->created || qemu_cpu_is_self(cpu));   \
        }                                                         \
    } while (0)

/* run_on_cpu_data.target_ptr should always be big enough for a
 * target_ulong even on 32 bit builds */
QEMU_BUILD_BUG_ON(sizeof(target_ulong) > sizeof(run_on_cpu_data));

/* We currently can't handle more than 16 bits in the MMUIDX bitmask.
 */
QEMU_BUILD_BUG_ON(NB_MMU_MODES > 16);
#define ALL_MMUIDX_BITS ((1 << NB_MMU_MODES) - 1)

void tlb_init(CPUState *cpu)
{
    CPUArchState *env = cpu->env_ptr;

    qemu_spin_init(&env->tlb_lock);
}

/* flush_all_helper: run fn across all cpus
 *
 * If the wait flag is set then the src cpu's helper will be queued as
 * "safe" work and the loop exited creating a synchronisation point
 * where all queued work will be finished before execution starts
 * again.
 */
static void flush_all_helper(CPUState *src, run_on_cpu_func fn,
                             run_on_cpu_data d)
{
    CPUState *cpu;

    CPU_FOREACH(cpu) {
        if (cpu != src) {
            async_run_on_cpu(cpu, fn, d);
        }
    }
}

size_t tlb_flush_count(void)
{
    CPUState *cpu;
    size_t count = 0;

    CPU_FOREACH(cpu) {
        CPUArchState *env = cpu->env_ptr;

        count += atomic_read(&env->tlb_flush_count);
    }
    return count;
}

/* This is OK because CPU architectures generally permit an
 * implementation to drop entries from the TLB at any time, so
 * flushing more entries than required is only an efficiency issue,
 * not a correctness issue.
 */
static void tlb_flush_nocheck(CPUState *cpu)
{
    CPUArchState *env = cpu->env_ptr;

    /* The QOM tests will trigger tlb_flushes without setting up TCG
     * so we bug out here in that case.
     */
    if (!tcg_enabled()) {
        return;
    }

    assert_cpu_is_self(cpu);
    atomic_set(&env->tlb_flush_count, env->tlb_flush_count + 1);
    tlb_debug("(count: %zu)\n", tlb_flush_count());

    /*
     * tlb_table/tlb_v_table updates from any thread must hold tlb_lock.
     * However, updates from the owner thread (as is the case here; see the
     * above assert_cpu_is_self) do not need atomic_set because all reads
     * that do not hold the lock are performed by the same owner thread.
     */
    qemu_spin_lock(&env->tlb_lock);
    memset(env->tlb_table, -1, sizeof(env->tlb_table));
    memset(env->tlb_v_table, -1, sizeof(env->tlb_v_table));
    qemu_spin_unlock(&env->tlb_lock);

    cpu_tb_jmp_cache_clear(cpu);

    env->vtlb_index = 0;
    env->tlb_flush_addr = -1;
    env->tlb_flush_mask = 0;

    atomic_mb_set(&cpu->pending_tlb_flush, 0);
}

static void tlb_flush_global_async_work(CPUState *cpu, run_on_cpu_data data)
{
    tlb_flush_nocheck(cpu);
}

void tlb_flush(CPUState *cpu)
{
    if (cpu->created && !qemu_cpu_is_self(cpu)) {
        if (atomic_mb_read(&cpu->pending_tlb_flush) != ALL_MMUIDX_BITS) {
            atomic_mb_set(&cpu->pending_tlb_flush, ALL_MMUIDX_BITS);
            async_run_on_cpu(cpu, tlb_flush_global_async_work,
                             RUN_ON_CPU_NULL);
        }
    } else {
        tlb_flush_nocheck(cpu);
    }
}

void tlb_flush_all_cpus(CPUState *src_cpu)
{
    const run_on_cpu_func fn = tlb_flush_global_async_work;
    flush_all_helper(src_cpu, fn, RUN_ON_CPU_NULL);
    fn(src_cpu, RUN_ON_CPU_NULL);
}

void tlb_flush_all_cpus_synced(CPUState *src_cpu)
{
    const run_on_cpu_func fn = tlb_flush_global_async_work;
    flush_all_helper(src_cpu, fn, RUN_ON_CPU_NULL);
    async_safe_run_on_cpu(src_cpu, fn, RUN_ON_CPU_NULL);
}

static void tlb_flush_by_mmuidx_async_work(CPUState *cpu, run_on_cpu_data data)
{
    CPUArchState *env = cpu->env_ptr;
    unsigned long mmu_idx_bitmask = data.host_int;
    int mmu_idx;

    assert_cpu_is_self(cpu);

    tlb_debug("start: mmu_idx:0x%04lx\n", mmu_idx_bitmask);

    qemu_spin_lock(&env->tlb_lock);
    for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {

        if (test_bit(mmu_idx, &mmu_idx_bitmask)) {
            tlb_debug("%d\n", mmu_idx);

            memset(env->tlb_table[mmu_idx], -1, sizeof(env->tlb_table[0]));
            memset(env->tlb_v_table[mmu_idx], -1, sizeof(env->tlb_v_table[0]));
        }
    }
    qemu_spin_unlock(&env->tlb_lock);

    cpu_tb_jmp_cache_clear(cpu);

    tlb_debug("done\n");
}

void tlb_flush_by_mmuidx(CPUState *cpu, uint16_t idxmap)
{
    tlb_debug("mmu_idx: 0x%" PRIx16 "\n", idxmap);

    if (!qemu_cpu_is_self(cpu)) {
        uint16_t pending_flushes = idxmap;
        pending_flushes &= ~atomic_mb_read(&cpu->pending_tlb_flush);

        if (pending_flushes) {
            tlb_debug("reduced mmu_idx: 0x%" PRIx16 "\n", pending_flushes);

            atomic_or(&cpu->pending_tlb_flush, pending_flushes);
            async_run_on_cpu(cpu, tlb_flush_by_mmuidx_async_work,
                             RUN_ON_CPU_HOST_INT(pending_flushes));
        }
    } else {
        tlb_flush_by_mmuidx_async_work(cpu,
                                       RUN_ON_CPU_HOST_INT(idxmap));
    }
}

void tlb_flush_by_mmuidx_all_cpus(CPUState *src_cpu, uint16_t idxmap)
{
    const run_on_cpu_func fn = tlb_flush_by_mmuidx_async_work;

    tlb_debug("mmu_idx: 0x%"PRIx16"\n", idxmap);

    flush_all_helper(src_cpu, fn, RUN_ON_CPU_HOST_INT(idxmap));
    fn(src_cpu, RUN_ON_CPU_HOST_INT(idxmap));
}

void tlb_flush_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
                                                       uint16_t idxmap)
{
    const run_on_cpu_func fn = tlb_flush_by_mmuidx_async_work;

    tlb_debug("mmu_idx: 0x%"PRIx16"\n", idxmap);

    flush_all_helper(src_cpu, fn, RUN_ON_CPU_HOST_INT(idxmap));
    async_safe_run_on_cpu(src_cpu, fn, RUN_ON_CPU_HOST_INT(idxmap));
}

static inline bool tlb_hit_page_anyprot(CPUTLBEntry *tlb_entry,
                                        target_ulong page)
{
    return tlb_hit_page(tlb_entry->addr_read, page) ||
           tlb_hit_page(tlb_addr_write(tlb_entry), page) ||
           tlb_hit_page(tlb_entry->addr_code, page);
}

/* Called with tlb_lock held */
static inline void tlb_flush_entry_locked(CPUTLBEntry *tlb_entry,
                                          target_ulong page)
{
    if (tlb_hit_page_anyprot(tlb_entry, page)) {
        memset(tlb_entry, -1, sizeof(*tlb_entry));
    }
}

/* Called with tlb_lock held */
static inline void tlb_flush_vtlb_page_locked(CPUArchState *env, int mmu_idx,
                                              target_ulong page)
{
    int k;

    assert_cpu_is_self(ENV_GET_CPU(env));
    for (k = 0; k < CPU_VTLB_SIZE; k++) {
        tlb_flush_entry_locked(&env->tlb_v_table[mmu_idx][k], page);
    }
}

static void tlb_flush_page_async_work(CPUState *cpu, run_on_cpu_data data)
{
    CPUArchState *env = cpu->env_ptr;
    target_ulong addr = (target_ulong) data.target_ptr;
    int mmu_idx;

    assert_cpu_is_self(cpu);

    tlb_debug("page :" TARGET_FMT_lx "\n", addr);

    /* Check if we need to flush due to large pages.  */
    if ((addr & env->tlb_flush_mask) == env->tlb_flush_addr) {
        tlb_debug("forcing full flush ("
                  TARGET_FMT_lx "/" TARGET_FMT_lx ")\n",
                  env->tlb_flush_addr, env->tlb_flush_mask);

        tlb_flush(cpu);
        return;
    }

    addr &= TARGET_PAGE_MASK;
    qemu_spin_lock(&env->tlb_lock);
    for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
        tlb_flush_entry_locked(tlb_entry(env, mmu_idx, addr), addr);
        tlb_flush_vtlb_page_locked(env, mmu_idx, addr);
    }
    qemu_spin_unlock(&env->tlb_lock);

    tb_flush_jmp_cache(cpu, addr);
}

void tlb_flush_page(CPUState *cpu, target_ulong addr)
{
    tlb_debug("page :" TARGET_FMT_lx "\n", addr);

    if (!qemu_cpu_is_self(cpu)) {
        async_run_on_cpu(cpu, tlb_flush_page_async_work,
                         RUN_ON_CPU_TARGET_PTR(addr));
    } else {
        tlb_flush_page_async_work(cpu, RUN_ON_CPU_TARGET_PTR(addr));
    }
}

/* As we are going to hijack the bottom bits of the page address for a
 * mmuidx bit mask we need to fail to build if we can't do that
 */
QEMU_BUILD_BUG_ON(NB_MMU_MODES > TARGET_PAGE_BITS_MIN);

static void tlb_flush_page_by_mmuidx_async_work(CPUState *cpu,
                                                run_on_cpu_data data)
{
    CPUArchState *env = cpu->env_ptr;
    target_ulong addr_and_mmuidx = (target_ulong) data.target_ptr;
    target_ulong addr = addr_and_mmuidx & TARGET_PAGE_MASK;
    unsigned long mmu_idx_bitmap = addr_and_mmuidx & ALL_MMUIDX_BITS;
    int mmu_idx;

    assert_cpu_is_self(cpu);

    tlb_debug("flush page addr:"TARGET_FMT_lx" mmu_idx:0x%lx\n",
              addr, mmu_idx_bitmap);

    qemu_spin_lock(&env->tlb_lock);
    for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
        if (test_bit(mmu_idx, &mmu_idx_bitmap)) {
            tlb_flush_entry_locked(tlb_entry(env, mmu_idx, addr), addr);
            tlb_flush_vtlb_page_locked(env, mmu_idx, addr);
        }
    }
    qemu_spin_unlock(&env->tlb_lock);

    tb_flush_jmp_cache(cpu, addr);
}

static void tlb_check_page_and_flush_by_mmuidx_async_work(CPUState *cpu,
                                                          run_on_cpu_data data)
{
    CPUArchState *env = cpu->env_ptr;
    target_ulong addr_and_mmuidx = (target_ulong) data.target_ptr;
    target_ulong addr = addr_and_mmuidx & TARGET_PAGE_MASK;
    unsigned long mmu_idx_bitmap = addr_and_mmuidx & ALL_MMUIDX_BITS;

    tlb_debug("addr:"TARGET_FMT_lx" mmu_idx: %04lx\n", addr, mmu_idx_bitmap);

    /* Check if we need to flush due to large pages.  */
    if ((addr & env->tlb_flush_mask) == env->tlb_flush_addr) {
        tlb_debug("forced full flush ("
                  TARGET_FMT_lx "/" TARGET_FMT_lx ")\n",
                  env->tlb_flush_addr, env->tlb_flush_mask);

        tlb_flush_by_mmuidx_async_work(cpu,
                                       RUN_ON_CPU_HOST_INT(mmu_idx_bitmap));
    } else {
        tlb_flush_page_by_mmuidx_async_work(cpu, data);
    }
}

void tlb_flush_page_by_mmuidx(CPUState *cpu, target_ulong addr, uint16_t idxmap)
{
    target_ulong addr_and_mmu_idx;

    tlb_debug("addr: "TARGET_FMT_lx" mmu_idx:%" PRIx16 "\n", addr, idxmap);

    /* This should already be page aligned */
    addr_and_mmu_idx = addr & TARGET_PAGE_MASK;
    addr_and_mmu_idx |= idxmap;

    if (!qemu_cpu_is_self(cpu)) {
        async_run_on_cpu(cpu, tlb_check_page_and_flush_by_mmuidx_async_work,
                         RUN_ON_CPU_TARGET_PTR(addr_and_mmu_idx));
    } else {
        tlb_check_page_and_flush_by_mmuidx_async_work(
            cpu, RUN_ON_CPU_TARGET_PTR(addr_and_mmu_idx));
    }
}

void tlb_flush_page_by_mmuidx_all_cpus(CPUState *src_cpu, target_ulong addr,
                                       uint16_t idxmap)
{
    const run_on_cpu_func fn = tlb_check_page_and_flush_by_mmuidx_async_work;
    target_ulong addr_and_mmu_idx;

    tlb_debug("addr: "TARGET_FMT_lx" mmu_idx:%"PRIx16"\n", addr, idxmap);

    /* This should already be page aligned */
    addr_and_mmu_idx = addr & TARGET_PAGE_MASK;
    addr_and_mmu_idx |= idxmap;

    flush_all_helper(src_cpu, fn, RUN_ON_CPU_TARGET_PTR(addr_and_mmu_idx));
    fn(src_cpu, RUN_ON_CPU_TARGET_PTR(addr_and_mmu_idx));
}

void tlb_flush_page_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
                                                            target_ulong addr,
                                                            uint16_t idxmap)
{
    const run_on_cpu_func fn = tlb_check_page_and_flush_by_mmuidx_async_work;
    target_ulong addr_and_mmu_idx;

    tlb_debug("addr: "TARGET_FMT_lx" mmu_idx:%"PRIx16"\n", addr, idxmap);

    /* This should already be page aligned */
    addr_and_mmu_idx = addr & TARGET_PAGE_MASK;
    addr_and_mmu_idx |= idxmap;

    flush_all_helper(src_cpu, fn, RUN_ON_CPU_TARGET_PTR(addr_and_mmu_idx));
    async_safe_run_on_cpu(src_cpu, fn, RUN_ON_CPU_TARGET_PTR(addr_and_mmu_idx));
}

void tlb_flush_page_all_cpus(CPUState *src, target_ulong addr)
{
    const run_on_cpu_func fn = tlb_flush_page_async_work;

    flush_all_helper(src, fn, RUN_ON_CPU_TARGET_PTR(addr));
    fn(src, RUN_ON_CPU_TARGET_PTR(addr));
}

void tlb_flush_page_all_cpus_synced(CPUState *src,
                                                  target_ulong addr)
{
    const run_on_cpu_func fn = tlb_flush_page_async_work;

    flush_all_helper(src, fn, RUN_ON_CPU_TARGET_PTR(addr));
    async_safe_run_on_cpu(src, fn, RUN_ON_CPU_TARGET_PTR(addr));
}

/* update the TLBs so that writes to code in the virtual page 'addr'
   can be detected */
void tlb_protect_code(ram_addr_t ram_addr)
{
    cpu_physical_memory_test_and_clear_dirty(ram_addr, TARGET_PAGE_SIZE,
                                             DIRTY_MEMORY_CODE);
}

/* update the TLB so that writes in physical page 'phys_addr' are no longer
   tested for self modifying code */
void tlb_unprotect_code(ram_addr_t ram_addr)
{
    cpu_physical_memory_set_dirty_flag(ram_addr, DIRTY_MEMORY_CODE);
}


/*
 * Dirty write flag handling
 *
 * When the TCG code writes to a location it looks up the address in
 * the TLB and uses that data to compute the final address. If any of
 * the lower bits of the address are set then the slow path is forced.
 * There are a number of reasons to do this but for normal RAM the
 * most usual is detecting writes to code regions which may invalidate
 * generated code.
 *
 * Other vCPUs might be reading their TLBs during guest execution, so we update
 * te->addr_write with atomic_set. We don't need to worry about this for
 * oversized guests as MTTCG is disabled for them.
 *
 * Called with tlb_lock held.
 */
static void tlb_reset_dirty_range_locked(CPUTLBEntry *tlb_entry,
                                         uintptr_t start, uintptr_t length)
{
    uintptr_t addr = tlb_entry->addr_write;

    if ((addr & (TLB_INVALID_MASK | TLB_MMIO | TLB_NOTDIRTY)) == 0) {
        addr &= TARGET_PAGE_MASK;
        addr += tlb_entry->addend;
        if ((addr - start) < length) {
#if TCG_OVERSIZED_GUEST
            tlb_entry->addr_write |= TLB_NOTDIRTY;
#else
            atomic_set(&tlb_entry->addr_write,
                       tlb_entry->addr_write | TLB_NOTDIRTY);
#endif
        }
    }
}

/*
 * Called with tlb_lock held.
 * Called only from the vCPU context, i.e. the TLB's owner thread.
 */
static inline void copy_tlb_helper_locked(CPUTLBEntry *d, const CPUTLBEntry *s)
{
    *d = *s;
}

/* This is a cross vCPU call (i.e. another vCPU resetting the flags of
 * the target vCPU).
 * We must take tlb_lock to avoid racing with another vCPU update. The only
 * thing actually updated is the target TLB entry ->addr_write flags.
 */
void tlb_reset_dirty(CPUState *cpu, ram_addr_t start1, ram_addr_t length)
{
    CPUArchState *env;

    int mmu_idx;

    env = cpu->env_ptr;
    qemu_spin_lock(&env->tlb_lock);
    for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
        unsigned int i;

        for (i = 0; i < CPU_TLB_SIZE; i++) {
            tlb_reset_dirty_range_locked(&env->tlb_table[mmu_idx][i], start1,
                                         length);
        }

        for (i = 0; i < CPU_VTLB_SIZE; i++) {
            tlb_reset_dirty_range_locked(&env->tlb_v_table[mmu_idx][i], start1,
                                         length);
        }
    }
    qemu_spin_unlock(&env->tlb_lock);
}

/* Called with tlb_lock held */
static inline void tlb_set_dirty1_locked(CPUTLBEntry *tlb_entry,
                                         target_ulong vaddr)
{
    if (tlb_entry->addr_write == (vaddr | TLB_NOTDIRTY)) {
        tlb_entry->addr_write = vaddr;
    }
}

/* update the TLB corresponding to virtual page vaddr
   so that it is no longer dirty */
void tlb_set_dirty(CPUState *cpu, target_ulong vaddr)
{
    CPUArchState *env = cpu->env_ptr;
    int mmu_idx;

    assert_cpu_is_self(cpu);

    vaddr &= TARGET_PAGE_MASK;
    qemu_spin_lock(&env->tlb_lock);
    for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
        tlb_set_dirty1_locked(tlb_entry(env, mmu_idx, vaddr), vaddr);
    }

    for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
        int k;
        for (k = 0; k < CPU_VTLB_SIZE; k++) {
            tlb_set_dirty1_locked(&env->tlb_v_table[mmu_idx][k], vaddr);
        }
    }
    qemu_spin_unlock(&env->tlb_lock);
}

/* Our TLB does not support large pages, so remember the area covered by
   large pages and trigger a full TLB flush if these are invalidated.  */
static void tlb_add_large_page(CPUArchState *env, target_ulong vaddr,
                               target_ulong size)
{
    target_ulong mask = ~(size - 1);

    if (env->tlb_flush_addr == (target_ulong)-1) {
        env->tlb_flush_addr = vaddr & mask;
        env->tlb_flush_mask = mask;
        return;
    }
    /* Extend the existing region to include the new page.
       This is a compromise between unnecessary flushes and the cost
       of maintaining a full variable size TLB.  */
    mask &= env->tlb_flush_mask;
    while (((env->tlb_flush_addr ^ vaddr) & mask) != 0) {
        mask <<= 1;
    }
    env->tlb_flush_addr &= mask;
    env->tlb_flush_mask = mask;
}

/* Add a new TLB entry. At most one entry for a given virtual address
 * is permitted. Only a single TARGET_PAGE_SIZE region is mapped, the
 * supplied size is only used by tlb_flush_page.
 *
 * Called from TCG-generated code, which is under an RCU read-side
 * critical section.
 */
void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr,
                             hwaddr paddr, MemTxAttrs attrs, int prot,
                             int mmu_idx, target_ulong size)
{
    CPUArchState *env = cpu->env_ptr;
    MemoryRegionSection *section;
    unsigned int index;
    target_ulong address;
    target_ulong code_address;
    uintptr_t addend;
    CPUTLBEntry *te, tn;
    hwaddr iotlb, xlat, sz, paddr_page;
    target_ulong vaddr_page;
    int asidx = cpu_asidx_from_attrs(cpu, attrs);

    assert_cpu_is_self(cpu);

    if (size < TARGET_PAGE_SIZE) {
        sz = TARGET_PAGE_SIZE;
    } else {
        if (size > TARGET_PAGE_SIZE) {
            tlb_add_large_page(env, vaddr, size);
        }
        sz = size;
    }
    vaddr_page = vaddr & TARGET_PAGE_MASK;
    paddr_page = paddr & TARGET_PAGE_MASK;

    section = address_space_translate_for_iotlb(cpu, asidx, paddr_page,
                                                &xlat, &sz, attrs, &prot);
    assert(sz >= TARGET_PAGE_SIZE);

    tlb_debug("vaddr=" TARGET_FMT_lx " paddr=0x" TARGET_FMT_plx
              " prot=%x idx=%d\n",
              vaddr, paddr, prot, mmu_idx);

    address = vaddr_page;
    if (size < TARGET_PAGE_SIZE) {
        /*
         * Slow-path the TLB entries; we will repeat the MMU check and TLB
         * fill on every access.
         */
        address |= TLB_RECHECK;
    }
    if (!memory_region_is_ram(section->mr) &&
        !memory_region_is_romd(section->mr)) {
        /* IO memory case */
        address |= TLB_MMIO;
        addend = 0;
    } else {
        /* TLB_MMIO for rom/romd handled below */
        addend = (uintptr_t)memory_region_get_ram_ptr(section->mr) + xlat;
    }

    code_address = address;
    iotlb = memory_region_section_get_iotlb(cpu, section, vaddr_page,
                                            paddr_page, xlat, prot, &address);

    index = tlb_index(env, mmu_idx, vaddr_page);
    te = tlb_entry(env, mmu_idx, vaddr_page);

    /*
     * Hold the TLB lock for the rest of the function. We could acquire/release
     * the lock several times in the function, but it is faster to amortize the
     * acquisition cost by acquiring it just once. Note that this leads to
     * a longer critical section, but this is not a concern since the TLB lock
     * is unlikely to be contended.
     */
    qemu_spin_lock(&env->tlb_lock);

    /* Make sure there's no cached translation for the new page.  */
    tlb_flush_vtlb_page_locked(env, mmu_idx, vaddr_page);

    /*
     * Only evict the old entry to the victim tlb if it's for a
     * different page; otherwise just overwrite the stale data.
     */
    if (!tlb_hit_page_anyprot(te, vaddr_page)) {
        unsigned vidx = env->vtlb_index++ % CPU_VTLB_SIZE;
        CPUTLBEntry *tv = &env->tlb_v_table[mmu_idx][vidx];

        /* Evict the old entry into the victim tlb.  */
        copy_tlb_helper_locked(tv, te);
        env->iotlb_v[mmu_idx][vidx] = env->iotlb[mmu_idx][index];
    }

    /* refill the tlb */
    /*
     * At this point iotlb contains a physical section number in the lower
     * TARGET_PAGE_BITS, and either
     *  + the ram_addr_t of the page base of the target RAM (if NOTDIRTY or ROM)
     *  + the offset within section->mr of the page base (otherwise)
     * We subtract the vaddr_page (which is page aligned and thus won't
     * disturb the low bits) to give an offset which can be added to the
     * (non-page-aligned) vaddr of the eventual memory access to get
     * the MemoryRegion offset for the access. Note that the vaddr we
     * subtract here is that of the page base, and not the same as the
     * vaddr we add back in io_readx()/io_writex()/get_page_addr_code().
     */
    env->iotlb[mmu_idx][index].addr = iotlb - vaddr_page;
    env->iotlb[mmu_idx][index].attrs = attrs;

    /* Now calculate the new entry */
    tn.addend = addend - vaddr_page;
    if (prot & PAGE_READ) {
        tn.addr_read = address;
    } else {
        tn.addr_read = -1;
    }

    if (prot & PAGE_EXEC) {
        tn.addr_code = code_address;
    } else {
        tn.addr_code = -1;
    }

    tn.addr_write = -1;
    if (prot & PAGE_WRITE) {
        if ((memory_region_is_ram(section->mr) && section->readonly)
            || memory_region_is_romd(section->mr)) {
            /* Write access calls the I/O callback.  */
            tn.addr_write = address | TLB_MMIO;
        } else if (memory_region_is_ram(section->mr)
                   && cpu_physical_memory_is_clean(
                       memory_region_get_ram_addr(section->mr) + xlat)) {
            tn.addr_write = address | TLB_NOTDIRTY;
        } else {
            tn.addr_write = address;
        }
        if (prot & PAGE_WRITE_INV) {
            tn.addr_write |= TLB_INVALID_MASK;
        }
    }

    copy_tlb_helper_locked(te, &tn);
    qemu_spin_unlock(&env->tlb_lock);
}

/* Add a new TLB entry, but without specifying the memory
 * transaction attributes to be used.
 */
void tlb_set_page(CPUState *cpu, target_ulong vaddr,
                  hwaddr paddr, int prot,
                  int mmu_idx, target_ulong size)
{
    tlb_set_page_with_attrs(cpu, vaddr, paddr, MEMTXATTRS_UNSPECIFIED,
                            prot, mmu_idx, size);
}

static inline ram_addr_t qemu_ram_addr_from_host_nofail(void *ptr)
{
    ram_addr_t ram_addr;

    ram_addr = qemu_ram_addr_from_host(ptr);
    if (ram_addr == RAM_ADDR_INVALID) {
        error_report("Bad ram pointer %p", ptr);
        abort();
    }
    return ram_addr;
}

static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
                         int mmu_idx,
                         target_ulong addr, uintptr_t retaddr,
                         bool recheck, MMUAccessType access_type, int size)
{
    CPUState *cpu = ENV_GET_CPU(env);
    hwaddr mr_offset;
    MemoryRegionSection *section;
    MemoryRegion *mr;
    uint64_t val;
    bool locked = false;
    MemTxResult r;

    if (recheck) {
        /*
         * This is a TLB_RECHECK access, where the MMU protection
         * covers a smaller range than a target page, and we must
         * repeat the MMU check here. This tlb_fill() call might
         * longjump out if this access should cause a guest exception.
         */
        CPUTLBEntry *entry;
        target_ulong tlb_addr;

        tlb_fill(cpu, addr, size, MMU_DATA_LOAD, mmu_idx, retaddr);

        entry = tlb_entry(env, mmu_idx, addr);
        tlb_addr = entry->addr_read;
        if (!(tlb_addr & ~(TARGET_PAGE_MASK | TLB_RECHECK))) {
            /* RAM access */
            uintptr_t haddr = addr + entry->addend;

            return ldn_p((void *)haddr, size);
        }
        /* Fall through for handling IO accesses */
    }

    section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs);
    mr = section->mr;
    mr_offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr;
    cpu->mem_io_pc = retaddr;
    if (mr != &io_mem_rom && mr != &io_mem_notdirty && !cpu->can_do_io) {
        cpu_io_recompile(cpu, retaddr);
    }

    cpu->mem_io_vaddr = addr;
    cpu->mem_io_access_type = access_type;

    if (mr->global_locking && !qemu_mutex_iothread_locked()) {
        qemu_mutex_lock_iothread();
        locked = true;
    }
    r = memory_region_dispatch_read(mr, mr_offset,
                                    &val, size, iotlbentry->attrs);
    if (r != MEMTX_OK) {
        hwaddr physaddr = mr_offset +
            section->offset_within_address_space -
            section->offset_within_region;

        cpu_transaction_failed(cpu, physaddr, addr, size, access_type,
                               mmu_idx, iotlbentry->attrs, r, retaddr);
    }
    if (locked) {
        qemu_mutex_unlock_iothread();
    }

    return val;
}

static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
                      int mmu_idx,
                      uint64_t val, target_ulong addr,
                      uintptr_t retaddr, bool recheck, int size)
{
    CPUState *cpu = ENV_GET_CPU(env);
    hwaddr mr_offset;
    MemoryRegionSection *section;
    MemoryRegion *mr;
    bool locked = false;
    MemTxResult r;

    if (recheck) {
        /*
         * This is a TLB_RECHECK access, where the MMU protection
         * covers a smaller range than a target page, and we must
         * repeat the MMU check here. This tlb_fill() call might
         * longjump out if this access should cause a guest exception.
         */
        CPUTLBEntry *entry;
        target_ulong tlb_addr;

        tlb_fill(cpu, addr, size, MMU_DATA_STORE, mmu_idx, retaddr);

        entry = tlb_entry(env, mmu_idx, addr);
        tlb_addr = tlb_addr_write(entry);
        if (!(tlb_addr & ~(TARGET_PAGE_MASK | TLB_RECHECK))) {
            /* RAM access */
            uintptr_t haddr = addr + entry->addend;

            stn_p((void *)haddr, size, val);
            return;
        }
        /* Fall through for handling IO accesses */
    }

    section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs);
    mr = section->mr;
    mr_offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr;
    if (mr != &io_mem_rom && mr != &io_mem_notdirty && !cpu->can_do_io) {
        cpu_io_recompile(cpu, retaddr);
    }
    cpu->mem_io_vaddr = addr;
    cpu->mem_io_pc = retaddr;

    if (mr->global_locking && !qemu_mutex_iothread_locked()) {
        qemu_mutex_lock_iothread();
        locked = true;
    }
    r = memory_region_dispatch_write(mr, mr_offset,
                                     val, size, iotlbentry->attrs);
    if (r != MEMTX_OK) {
        hwaddr physaddr = mr_offset +
            section->offset_within_address_space -
            section->offset_within_region;

        cpu_transaction_failed(cpu, physaddr, addr, size, MMU_DATA_STORE,
                               mmu_idx, iotlbentry->attrs, r, retaddr);
    }
    if (locked) {
        qemu_mutex_unlock_iothread();
    }
}

/* Return true if ADDR is present in the victim tlb, and has been copied
   back to the main tlb.  */
static bool victim_tlb_hit(CPUArchState *env, size_t mmu_idx, size_t index,
                           size_t elt_ofs, target_ulong page)
{
    size_t vidx;

    assert_cpu_is_self(ENV_GET_CPU(env));
    for (vidx = 0; vidx < CPU_VTLB_SIZE; ++vidx) {
        CPUTLBEntry *vtlb = &env->tlb_v_table[mmu_idx][vidx];
        target_ulong cmp;

        /* elt_ofs might correspond to .addr_write, so use atomic_read */
#if TCG_OVERSIZED_GUEST
        cmp = *(target_ulong *)((uintptr_t)vtlb + elt_ofs);
#else
        cmp = atomic_read((target_ulong *)((uintptr_t)vtlb + elt_ofs));
#endif

        if (cmp == page) {
            /* Found entry in victim tlb, swap tlb and iotlb.  */
            CPUTLBEntry tmptlb, *tlb = &env->tlb_table[mmu_idx][index];

            qemu_spin_lock(&env->tlb_lock);
            copy_tlb_helper_locked(&tmptlb, tlb);
            copy_tlb_helper_locked(tlb, vtlb);
            copy_tlb_helper_locked(vtlb, &tmptlb);
            qemu_spin_unlock(&env->tlb_lock);

            CPUIOTLBEntry tmpio, *io = &env->iotlb[mmu_idx][index];
            CPUIOTLBEntry *vio = &env->iotlb_v[mmu_idx][vidx];
            tmpio = *io; *io = *vio; *vio = tmpio;
            return true;
        }
    }
    return false;
}

/* Macro to call the above, with local variables from the use context.  */
#define VICTIM_TLB_HIT(TY, ADDR) \
  victim_tlb_hit(env, mmu_idx, index, offsetof(CPUTLBEntry, TY), \
                 (ADDR) & TARGET_PAGE_MASK)

/* NOTE: this function can trigger an exception */
/* NOTE2: the returned address is not exactly the physical address: it
 * is actually a ram_addr_t (in system mode; the user mode emulation
 * version of this function returns a guest virtual address).
 */
tb_page_addr_t get_page_addr_code(CPUArchState *env, target_ulong addr)
{
    uintptr_t mmu_idx = cpu_mmu_index(env, true);
    uintptr_t index = tlb_index(env, mmu_idx, addr);
    CPUTLBEntry *entry = tlb_entry(env, mmu_idx, addr);
    void *p;

    if (unlikely(!tlb_hit(entry->addr_code, addr))) {
        if (!VICTIM_TLB_HIT(addr_code, addr)) {
            tlb_fill(ENV_GET_CPU(env), addr, 0, MMU_INST_FETCH, mmu_idx, 0);
        }
        assert(tlb_hit(entry->addr_code, addr));
    }

    if (unlikely(entry->addr_code & (TLB_RECHECK | TLB_MMIO))) {
        /*
         * Return -1 if we can't translate and execute from an entire
         * page of RAM here, which will cause us to execute by loading
         * and translating one insn at a time, without caching:
         *  - TLB_RECHECK: means the MMU protection covers a smaller range
         *    than a target page, so we must redo the MMU check every insn
         *  - TLB_MMIO: region is not backed by RAM
         */
        return -1;
    }

    p = (void *)((uintptr_t)addr + entry->addend);
    return qemu_ram_addr_from_host_nofail(p);
}

/* Probe for whether the specified guest write access is permitted.
 * If it is not permitted then an exception will be taken in the same
 * way as if this were a real write access (and we will not return).
 * Otherwise the function will return, and there will be a valid
 * entry in the TLB for this access.
 */
void probe_write(CPUArchState *env, target_ulong addr, int size, int mmu_idx,
                 uintptr_t retaddr)
{
    uintptr_t index = tlb_index(env, mmu_idx, addr);
    CPUTLBEntry *entry = tlb_entry(env, mmu_idx, addr);

    if (!tlb_hit(tlb_addr_write(entry), addr)) {
        /* TLB entry is for a different page */
        if (!VICTIM_TLB_HIT(addr_write, addr)) {
            tlb_fill(ENV_GET_CPU(env), addr, size, MMU_DATA_STORE,
                     mmu_idx, retaddr);
        }
    }
}

/* Probe for a read-modify-write atomic operation.  Do not allow unaligned
 * operations, or io operations to proceed.  Return the host address.  */
static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr,
                               TCGMemOpIdx oi, uintptr_t retaddr,
                               NotDirtyInfo *ndi)
{
    size_t mmu_idx = get_mmuidx(oi);
    uintptr_t index = tlb_index(env, mmu_idx, addr);
    CPUTLBEntry *tlbe = tlb_entry(env, mmu_idx, addr);
    target_ulong tlb_addr = tlb_addr_write(tlbe);
    TCGMemOp mop = get_memop(oi);
    int a_bits = get_alignment_bits(mop);
    int s_bits = mop & MO_SIZE;
    void *hostaddr;

    /* Adjust the given return address.  */
    retaddr -= GETPC_ADJ;

    /* Enforce guest required alignment.  */
    if (unlikely(a_bits > 0 && (addr & ((1 << a_bits) - 1)))) {
        /* ??? Maybe indicate atomic op to cpu_unaligned_access */
        cpu_unaligned_access(ENV_GET_CPU(env), addr, MMU_DATA_STORE,
                             mmu_idx, retaddr);
    }

    /* Enforce qemu required alignment.  */
    if (unlikely(addr & ((1 << s_bits) - 1))) {
        /* We get here if guest alignment was not requested,
           or was not enforced by cpu_unaligned_access above.
           We might widen the access and emulate, but for now
           mark an exception and exit the cpu loop.  */
        goto stop_the_world;
    }

    /* Check TLB entry and enforce page permissions.  */
    if (!tlb_hit(tlb_addr, addr)) {
        if (!VICTIM_TLB_HIT(addr_write, addr)) {
            tlb_fill(ENV_GET_CPU(env), addr, 1 << s_bits, MMU_DATA_STORE,
                     mmu_idx, retaddr);
        }
        tlb_addr = tlb_addr_write(tlbe) & ~TLB_INVALID_MASK;
    }

    /* Notice an IO access or a needs-MMU-lookup access */
    if (unlikely(tlb_addr & (TLB_MMIO | TLB_RECHECK))) {
        /* There's really nothing that can be done to
           support this apart from stop-the-world.  */
        goto stop_the_world;
    }

    /* Let the guest notice RMW on a write-only page.  */
    if (unlikely(tlbe->addr_read != (tlb_addr & ~TLB_NOTDIRTY))) {
        tlb_fill(ENV_GET_CPU(env), addr, 1 << s_bits, MMU_DATA_LOAD,
                 mmu_idx, retaddr);
        /* Since we don't support reads and writes to different addresses,
           and we do have the proper page loaded for write, this shouldn't
           ever return.  But just in case, handle via stop-the-world.  */
        goto stop_the_world;
    }

    hostaddr = (void *)((uintptr_t)addr + tlbe->addend);

    ndi->active = false;
    if (unlikely(tlb_addr & TLB_NOTDIRTY)) {
        ndi->active = true;
        memory_notdirty_write_prepare(ndi, ENV_GET_CPU(env), addr,
                                      qemu_ram_addr_from_host_nofail(hostaddr),
                                      1 << s_bits);
    }

    return hostaddr;

 stop_the_world:
    cpu_loop_exit_atomic(ENV_GET_CPU(env), retaddr);
}

#ifdef TARGET_WORDS_BIGENDIAN
# define TGT_BE(X)  (X)
# define TGT_LE(X)  BSWAP(X)
#else
# define TGT_BE(X)  BSWAP(X)
# define TGT_LE(X)  (X)
#endif

#define MMUSUFFIX _mmu

#define DATA_SIZE 1
#include "softmmu_template.h"

#define DATA_SIZE 2
#include "softmmu_template.h"

#define DATA_SIZE 4
#include "softmmu_template.h"

#define DATA_SIZE 8
#include "softmmu_template.h"

/* First set of helpers allows passing in of OI and RETADDR.  This makes
   them callable from other helpers.  */

#define EXTRA_ARGS     , TCGMemOpIdx oi, uintptr_t retaddr
#define ATOMIC_NAME(X) \
    HELPER(glue(glue(glue(atomic_ ## X, SUFFIX), END), _mmu))
#define ATOMIC_MMU_DECLS NotDirtyInfo ndi
#define ATOMIC_MMU_LOOKUP atomic_mmu_lookup(env, addr, oi, retaddr, &ndi)
#define ATOMIC_MMU_CLEANUP                              \
    do {                                                \
        if (unlikely(ndi.active)) {                     \
            memory_notdirty_write_complete(&ndi);       \
        }                                               \
    } while (0)

#define DATA_SIZE 1
#include "atomic_template.h"

#define DATA_SIZE 2
#include "atomic_template.h"

#define DATA_SIZE 4
#include "atomic_template.h"

#ifdef CONFIG_ATOMIC64
#define DATA_SIZE 8
#include "atomic_template.h"
#endif

#if HAVE_CMPXCHG128 || HAVE_ATOMIC128
#define DATA_SIZE 16
#include "atomic_template.h"
#endif

/* Second set of helpers are directly callable from TCG as helpers.  */

#undef EXTRA_ARGS
#undef ATOMIC_NAME
#undef ATOMIC_MMU_LOOKUP
#define EXTRA_ARGS         , TCGMemOpIdx oi
#define ATOMIC_NAME(X)     HELPER(glue(glue(atomic_ ## X, SUFFIX), END))
#define ATOMIC_MMU_LOOKUP  atomic_mmu_lookup(env, addr, oi, GETPC(), &ndi)

#define DATA_SIZE 1
#include "atomic_template.h"

#define DATA_SIZE 2
#include "atomic_template.h"

#define DATA_SIZE 4
#include "atomic_template.h"

#ifdef CONFIG_ATOMIC64
#define DATA_SIZE 8
#include "atomic_template.h"
#endif

/* Code access functions.  */

#undef MMUSUFFIX
#define MMUSUFFIX _cmmu
#undef GETPC
#define GETPC() ((uintptr_t)0)
#define SOFTMMU_CODE_ACCESS

#define DATA_SIZE 1
#include "softmmu_template.h"

#define DATA_SIZE 2
#include "softmmu_template.h"

#define DATA_SIZE 4
#include "softmmu_template.h"

#define DATA_SIZE 8
#include "softmmu_template.h"