aboutsummaryrefslogtreecommitdiff
path: root/accel/tcg/translate-all.c
blob: e7f0329a52cc19b3e8180de2e7a34bba4279a037 (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
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
/*
 *  Host code generation
 *
 *  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/>.
 */
#ifdef _WIN32
#include <windows.h>
#endif
#include "qemu/osdep.h"


#include "qemu-common.h"
#define NO_CPU_IO_DEFS
#include "cpu.h"
#include "trace.h"
#include "disas/disas.h"
#include "exec/exec-all.h"
#include "tcg.h"
#if defined(CONFIG_USER_ONLY)
#include "qemu.h"
#include "exec/exec-all.h"
#if defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
#include <sys/param.h>
#if __FreeBSD_version >= 700104
#define HAVE_KINFO_GETVMMAP
#define sigqueue sigqueue_freebsd  /* avoid redefinition */
#include <sys/proc.h>
#include <machine/profile.h>
#define _KERNEL
#include <sys/user.h>
#undef _KERNEL
#undef sigqueue
#include <libutil.h>
#endif
#endif
#else
#include "exec/address-spaces.h"
#endif

#include "exec/cputlb.h"
#include "exec/tb-hash.h"
#include "translate-all.h"
#include "qemu/bitmap.h"
#include "qemu/error-report.h"
#include "qemu/timer.h"
#include "qemu/main-loop.h"
#include "exec/log.h"
#include "sysemu/cpus.h"

/* #define DEBUG_TB_INVALIDATE */
/* #define DEBUG_TB_FLUSH */
/* make various TB consistency checks */
/* #define DEBUG_TB_CHECK */

#ifdef DEBUG_TB_INVALIDATE
#define DEBUG_TB_INVALIDATE_GATE 1
#else
#define DEBUG_TB_INVALIDATE_GATE 0
#endif

#ifdef DEBUG_TB_FLUSH
#define DEBUG_TB_FLUSH_GATE 1
#else
#define DEBUG_TB_FLUSH_GATE 0
#endif

#if !defined(CONFIG_USER_ONLY)
/* TB consistency checks only implemented for usermode emulation.  */
#undef DEBUG_TB_CHECK
#endif

#ifdef DEBUG_TB_CHECK
#define DEBUG_TB_CHECK_GATE 1
#else
#define DEBUG_TB_CHECK_GATE 0
#endif

/* Access to the various translations structures need to be serialised via locks
 * for consistency. This is automatic for SoftMMU based system
 * emulation due to its single threaded nature. In user-mode emulation
 * access to the memory related structures are protected with the
 * mmap_lock.
 */
#ifdef CONFIG_SOFTMMU
#define assert_memory_lock() tcg_debug_assert(have_tb_lock)
#else
#define assert_memory_lock() tcg_debug_assert(have_mmap_lock())
#endif

#define SMC_BITMAP_USE_THRESHOLD 10

typedef struct PageDesc {
    /* list of TBs intersecting this ram page */
    TranslationBlock *first_tb;
#ifdef CONFIG_SOFTMMU
    /* in order to optimize self modifying code, we count the number
       of lookups we do to a given page to use a bitmap */
    unsigned int code_write_count;
    unsigned long *code_bitmap;
#else
    unsigned long flags;
#endif
} PageDesc;

/* In system mode we want L1_MAP to be based on ram offsets,
   while in user mode we want it to be based on virtual addresses.  */
#if !defined(CONFIG_USER_ONLY)
#if HOST_LONG_BITS < TARGET_PHYS_ADDR_SPACE_BITS
# define L1_MAP_ADDR_SPACE_BITS  HOST_LONG_BITS
#else
# define L1_MAP_ADDR_SPACE_BITS  TARGET_PHYS_ADDR_SPACE_BITS
#endif
#else
# define L1_MAP_ADDR_SPACE_BITS  TARGET_VIRT_ADDR_SPACE_BITS
#endif

/* Size of the L2 (and L3, etc) page tables.  */
#define V_L2_BITS 10
#define V_L2_SIZE (1 << V_L2_BITS)

/* Make sure all possible CPU event bits fit in tb->trace_vcpu_dstate */
QEMU_BUILD_BUG_ON(CPU_TRACE_DSTATE_MAX_EVENTS >
                  sizeof(((TranslationBlock *)0)->trace_vcpu_dstate)
                  * BITS_PER_BYTE);

/*
 * L1 Mapping properties
 */
static int v_l1_size;
static int v_l1_shift;
static int v_l2_levels;

/* The bottom level has pointers to PageDesc, and is indexed by
 * anything from 4 to (V_L2_BITS + 3) bits, depending on target page size.
 */
#define V_L1_MIN_BITS 4
#define V_L1_MAX_BITS (V_L2_BITS + 3)
#define V_L1_MAX_SIZE (1 << V_L1_MAX_BITS)

static void *l1_map[V_L1_MAX_SIZE];

/* code generation context */
TCGContext tcg_init_ctx;
__thread TCGContext *tcg_ctx;
TBContext tb_ctx;
bool parallel_cpus;

/* translation block context */
static __thread int have_tb_lock;

static void page_table_config_init(void)
{
    uint32_t v_l1_bits;

    assert(TARGET_PAGE_BITS);
    /* The bits remaining after N lower levels of page tables.  */
    v_l1_bits = (L1_MAP_ADDR_SPACE_BITS - TARGET_PAGE_BITS) % V_L2_BITS;
    if (v_l1_bits < V_L1_MIN_BITS) {
        v_l1_bits += V_L2_BITS;
    }

    v_l1_size = 1 << v_l1_bits;
    v_l1_shift = L1_MAP_ADDR_SPACE_BITS - TARGET_PAGE_BITS - v_l1_bits;
    v_l2_levels = v_l1_shift / V_L2_BITS - 1;

    assert(v_l1_bits <= V_L1_MAX_BITS);
    assert(v_l1_shift % V_L2_BITS == 0);
    assert(v_l2_levels >= 0);
}

#define assert_tb_locked() tcg_debug_assert(have_tb_lock)
#define assert_tb_unlocked() tcg_debug_assert(!have_tb_lock)

void tb_lock(void)
{
    assert_tb_unlocked();
    qemu_mutex_lock(&tb_ctx.tb_lock);
    have_tb_lock++;
}

void tb_unlock(void)
{
    assert_tb_locked();
    have_tb_lock--;
    qemu_mutex_unlock(&tb_ctx.tb_lock);
}

void tb_lock_reset(void)
{
    if (have_tb_lock) {
        qemu_mutex_unlock(&tb_ctx.tb_lock);
        have_tb_lock = 0;
    }
}

static TranslationBlock *tb_find_pc(uintptr_t tc_ptr);

void cpu_gen_init(void)
{
    tcg_context_init(&tcg_init_ctx);
}

/* Encode VAL as a signed leb128 sequence at P.
   Return P incremented past the encoded value.  */
static uint8_t *encode_sleb128(uint8_t *p, target_long val)
{
    int more, byte;

    do {
        byte = val & 0x7f;
        val >>= 7;
        more = !((val == 0 && (byte & 0x40) == 0)
                 || (val == -1 && (byte & 0x40) != 0));
        if (more) {
            byte |= 0x80;
        }
        *p++ = byte;
    } while (more);

    return p;
}

/* Decode a signed leb128 sequence at *PP; increment *PP past the
   decoded value.  Return the decoded value.  */
static target_long decode_sleb128(uint8_t **pp)
{
    uint8_t *p = *pp;
    target_long val = 0;
    int byte, shift = 0;

    do {
        byte = *p++;
        val |= (target_ulong)(byte & 0x7f) << shift;
        shift += 7;
    } while (byte & 0x80);
    if (shift < TARGET_LONG_BITS && (byte & 0x40)) {
        val |= -(target_ulong)1 << shift;
    }

    *pp = p;
    return val;
}

/* Encode the data collected about the instructions while compiling TB.
   Place the data at BLOCK, and return the number of bytes consumed.

   The logical table consisits of TARGET_INSN_START_WORDS target_ulong's,
   which come from the target's insn_start data, followed by a uintptr_t
   which comes from the host pc of the end of the code implementing the insn.

   Each line of the table is encoded as sleb128 deltas from the previous
   line.  The seed for the first line is { tb->pc, 0..., tb->tc.ptr }.
   That is, the first column is seeded with the guest pc, the last column
   with the host pc, and the middle columns with zeros.  */

static int encode_search(TranslationBlock *tb, uint8_t *block)
{
    uint8_t *highwater = tcg_ctx->code_gen_highwater;
    uint8_t *p = block;
    int i, j, n;

    for (i = 0, n = tb->icount; i < n; ++i) {
        target_ulong prev;

        for (j = 0; j < TARGET_INSN_START_WORDS; ++j) {
            if (i == 0) {
                prev = (j == 0 ? tb->pc : 0);
            } else {
                prev = tcg_ctx->gen_insn_data[i - 1][j];
            }
            p = encode_sleb128(p, tcg_ctx->gen_insn_data[i][j] - prev);
        }
        prev = (i == 0 ? 0 : tcg_ctx->gen_insn_end_off[i - 1]);
        p = encode_sleb128(p, tcg_ctx->gen_insn_end_off[i] - prev);

        /* Test for (pending) buffer overflow.  The assumption is that any
           one row beginning below the high water mark cannot overrun
           the buffer completely.  Thus we can test for overflow after
           encoding a row without having to check during encoding.  */
        if (unlikely(p > highwater)) {
            return -1;
        }
    }

    return p - block;
}

/* The cpu state corresponding to 'searched_pc' is restored.
 * Called with tb_lock held.
 */
static int cpu_restore_state_from_tb(CPUState *cpu, TranslationBlock *tb,
                                     uintptr_t searched_pc)
{
    target_ulong data[TARGET_INSN_START_WORDS] = { tb->pc };
    uintptr_t host_pc = (uintptr_t)tb->tc.ptr;
    CPUArchState *env = cpu->env_ptr;
    uint8_t *p = tb->tc.ptr + tb->tc.size;
    int i, j, num_insns = tb->icount;
#ifdef CONFIG_PROFILER
    TCGProfile *prof = &tcg_ctx->prof;
    int64_t ti = profile_getclock();
#endif

    searched_pc -= GETPC_ADJ;

    if (searched_pc < host_pc) {
        return -1;
    }

    /* Reconstruct the stored insn data while looking for the point at
       which the end of the insn exceeds the searched_pc.  */
    for (i = 0; i < num_insns; ++i) {
        for (j = 0; j < TARGET_INSN_START_WORDS; ++j) {
            data[j] += decode_sleb128(&p);
        }
        host_pc += decode_sleb128(&p);
        if (host_pc > searched_pc) {
            goto found;
        }
    }
    return -1;

 found:
    if (tb->cflags & CF_USE_ICOUNT) {
        assert(use_icount);
        /* Reset the cycle counter to the start of the block.  */
        cpu->icount_decr.u16.low += num_insns;
        /* Clear the IO flag.  */
        cpu->can_do_io = 0;
    }
    cpu->icount_decr.u16.low -= i;
    restore_state_to_opc(env, tb, data);

#ifdef CONFIG_PROFILER
    atomic_set(&prof->restore_time,
                prof->restore_time + profile_getclock() - ti);
    atomic_set(&prof->restore_count, prof->restore_count + 1);
#endif
    return 0;
}

bool cpu_restore_state(CPUState *cpu, uintptr_t host_pc)
{
    TranslationBlock *tb;
    bool r = false;
    uintptr_t check_offset;

    /* The host_pc has to be in the region of current code buffer. If
     * it is not we will not be able to resolve it here. The two cases
     * where host_pc will not be correct are:
     *
     *  - fault during translation (instruction fetch)
     *  - fault from helper (not using GETPC() macro)
     *
     * Either way we need return early to avoid blowing up on a
     * recursive tb_lock() as we can't resolve it here.
     *
     * We are using unsigned arithmetic so if host_pc <
     * tcg_init_ctx.code_gen_buffer check_offset will wrap to way
     * above the code_gen_buffer_size
     */
    check_offset = host_pc - (uintptr_t) tcg_init_ctx.code_gen_buffer;

    if (check_offset < tcg_init_ctx.code_gen_buffer_size) {
        tb_lock();
        tb = tb_find_pc(host_pc);
        if (tb) {
            cpu_restore_state_from_tb(cpu, tb, host_pc);
            if (tb->cflags & CF_NOCACHE) {
                /* one-shot translation, invalidate it immediately */
                tb_phys_invalidate(tb, -1);
                tb_remove(tb);
            }
            r = true;
        }
        tb_unlock();
    }

    return r;
}

static void page_init(void)
{
    page_size_init();
    page_table_config_init();

#if defined(CONFIG_BSD) && defined(CONFIG_USER_ONLY)
    {
#ifdef HAVE_KINFO_GETVMMAP
        struct kinfo_vmentry *freep;
        int i, cnt;

        freep = kinfo_getvmmap(getpid(), &cnt);
        if (freep) {
            mmap_lock();
            for (i = 0; i < cnt; i++) {
                unsigned long startaddr, endaddr;

                startaddr = freep[i].kve_start;
                endaddr = freep[i].kve_end;
                if (h2g_valid(startaddr)) {
                    startaddr = h2g(startaddr) & TARGET_PAGE_MASK;

                    if (h2g_valid(endaddr)) {
                        endaddr = h2g(endaddr);
                        page_set_flags(startaddr, endaddr, PAGE_RESERVED);
                    } else {
#if TARGET_ABI_BITS <= L1_MAP_ADDR_SPACE_BITS
                        endaddr = ~0ul;
                        page_set_flags(startaddr, endaddr, PAGE_RESERVED);
#endif
                    }
                }
            }
            free(freep);
            mmap_unlock();
        }
#else
        FILE *f;

        last_brk = (unsigned long)sbrk(0);

        f = fopen("/compat/linux/proc/self/maps", "r");
        if (f) {
            mmap_lock();

            do {
                unsigned long startaddr, endaddr;
                int n;

                n = fscanf(f, "%lx-%lx %*[^\n]\n", &startaddr, &endaddr);

                if (n == 2 && h2g_valid(startaddr)) {
                    startaddr = h2g(startaddr) & TARGET_PAGE_MASK;

                    if (h2g_valid(endaddr)) {
                        endaddr = h2g(endaddr);
                    } else {
                        endaddr = ~0ul;
                    }
                    page_set_flags(startaddr, endaddr, PAGE_RESERVED);
                }
            } while (!feof(f));

            fclose(f);
            mmap_unlock();
        }
#endif
    }
#endif
}

/* If alloc=1:
 * Called with tb_lock held for system emulation.
 * Called with mmap_lock held for user-mode emulation.
 */
static PageDesc *page_find_alloc(tb_page_addr_t index, int alloc)
{
    PageDesc *pd;
    void **lp;
    int i;

    if (alloc) {
        assert_memory_lock();
    }

    /* Level 1.  Always allocated.  */
    lp = l1_map + ((index >> v_l1_shift) & (v_l1_size - 1));

    /* Level 2..N-1.  */
    for (i = v_l2_levels; i > 0; i--) {
        void **p = atomic_rcu_read(lp);

        if (p == NULL) {
            if (!alloc) {
                return NULL;
            }
            p = g_new0(void *, V_L2_SIZE);
            atomic_rcu_set(lp, p);
        }

        lp = p + ((index >> (i * V_L2_BITS)) & (V_L2_SIZE - 1));
    }

    pd = atomic_rcu_read(lp);
    if (pd == NULL) {
        if (!alloc) {
            return NULL;
        }
        pd = g_new0(PageDesc, V_L2_SIZE);
        atomic_rcu_set(lp, pd);
    }

    return pd + (index & (V_L2_SIZE - 1));
}

static inline PageDesc *page_find(tb_page_addr_t index)
{
    return page_find_alloc(index, 0);
}

#if defined(CONFIG_USER_ONLY)
/* Currently it is not recommended to allocate big chunks of data in
   user mode. It will change when a dedicated libc will be used.  */
/* ??? 64-bit hosts ought to have no problem mmaping data outside the
   region in which the guest needs to run.  Revisit this.  */
#define USE_STATIC_CODE_GEN_BUFFER
#endif

/* Minimum size of the code gen buffer.  This number is randomly chosen,
   but not so small that we can't have a fair number of TB's live.  */
#define MIN_CODE_GEN_BUFFER_SIZE     (1024u * 1024)

/* Maximum size of the code gen buffer we'd like to use.  Unless otherwise
   indicated, this is constrained by the range of direct branches on the
   host cpu, as used by the TCG implementation of goto_tb.  */
#if defined(__x86_64__)
# define MAX_CODE_GEN_BUFFER_SIZE  (2ul * 1024 * 1024 * 1024)
#elif defined(__sparc__)
# define MAX_CODE_GEN_BUFFER_SIZE  (2ul * 1024 * 1024 * 1024)
#elif defined(__powerpc64__)
# define MAX_CODE_GEN_BUFFER_SIZE  (2ul * 1024 * 1024 * 1024)
#elif defined(__powerpc__)
# define MAX_CODE_GEN_BUFFER_SIZE  (32u * 1024 * 1024)
#elif defined(__aarch64__)
# define MAX_CODE_GEN_BUFFER_SIZE  (2ul * 1024 * 1024 * 1024)
#elif defined(__s390x__)
  /* We have a +- 4GB range on the branches; leave some slop.  */
# define MAX_CODE_GEN_BUFFER_SIZE  (3ul * 1024 * 1024 * 1024)
#elif defined(__mips__)
  /* We have a 256MB branch region, but leave room to make sure the
     main executable is also within that region.  */
# define MAX_CODE_GEN_BUFFER_SIZE  (128ul * 1024 * 1024)
#else
# define MAX_CODE_GEN_BUFFER_SIZE  ((size_t)-1)
#endif

#define DEFAULT_CODE_GEN_BUFFER_SIZE_1 (32u * 1024 * 1024)

#define DEFAULT_CODE_GEN_BUFFER_SIZE \
  (DEFAULT_CODE_GEN_BUFFER_SIZE_1 < MAX_CODE_GEN_BUFFER_SIZE \
   ? DEFAULT_CODE_GEN_BUFFER_SIZE_1 : MAX_CODE_GEN_BUFFER_SIZE)

static inline size_t size_code_gen_buffer(size_t tb_size)
{
    /* Size the buffer.  */
    if (tb_size == 0) {
#ifdef USE_STATIC_CODE_GEN_BUFFER
        tb_size = DEFAULT_CODE_GEN_BUFFER_SIZE;
#else
        /* ??? Needs adjustments.  */
        /* ??? If we relax the requirement that CONFIG_USER_ONLY use the
           static buffer, we could size this on RESERVED_VA, on the text
           segment size of the executable, or continue to use the default.  */
        tb_size = (unsigned long)(ram_size / 4);
#endif
    }
    if (tb_size < MIN_CODE_GEN_BUFFER_SIZE) {
        tb_size = MIN_CODE_GEN_BUFFER_SIZE;
    }
    if (tb_size > MAX_CODE_GEN_BUFFER_SIZE) {
        tb_size = MAX_CODE_GEN_BUFFER_SIZE;
    }
    return tb_size;
}

#ifdef __mips__
/* In order to use J and JAL within the code_gen_buffer, we require
   that the buffer not cross a 256MB boundary.  */
static inline bool cross_256mb(void *addr, size_t size)
{
    return ((uintptr_t)addr ^ ((uintptr_t)addr + size)) & ~0x0ffffffful;
}

/* We weren't able to allocate a buffer without crossing that boundary,
   so make do with the larger portion of the buffer that doesn't cross.
   Returns the new base of the buffer, and adjusts code_gen_buffer_size.  */
static inline void *split_cross_256mb(void *buf1, size_t size1)
{
    void *buf2 = (void *)(((uintptr_t)buf1 + size1) & ~0x0ffffffful);
    size_t size2 = buf1 + size1 - buf2;

    size1 = buf2 - buf1;
    if (size1 < size2) {
        size1 = size2;
        buf1 = buf2;
    }

    tcg_ctx->code_gen_buffer_size = size1;
    return buf1;
}
#endif

#ifdef USE_STATIC_CODE_GEN_BUFFER
static uint8_t static_code_gen_buffer[DEFAULT_CODE_GEN_BUFFER_SIZE]
    __attribute__((aligned(CODE_GEN_ALIGN)));

static inline void *alloc_code_gen_buffer(void)
{
    void *buf = static_code_gen_buffer;
    void *end = static_code_gen_buffer + sizeof(static_code_gen_buffer);
    size_t size;

    /* page-align the beginning and end of the buffer */
    buf = QEMU_ALIGN_PTR_UP(buf, qemu_real_host_page_size);
    end = QEMU_ALIGN_PTR_DOWN(end, qemu_real_host_page_size);

    size = end - buf;

    /* Honor a command-line option limiting the size of the buffer.  */
    if (size > tcg_ctx->code_gen_buffer_size) {
        size = QEMU_ALIGN_DOWN(tcg_ctx->code_gen_buffer_size,
                               qemu_real_host_page_size);
    }
    tcg_ctx->code_gen_buffer_size = size;

#ifdef __mips__
    if (cross_256mb(buf, size)) {
        buf = split_cross_256mb(buf, size);
        size = tcg_ctx->code_gen_buffer_size;
    }
#endif

    if (qemu_mprotect_rwx(buf, size)) {
        abort();
    }
    qemu_madvise(buf, size, QEMU_MADV_HUGEPAGE);

    return buf;
}
#elif defined(_WIN32)
static inline void *alloc_code_gen_buffer(void)
{
    size_t size = tcg_ctx->code_gen_buffer_size;
    void *buf;

    buf = VirtualAlloc(NULL, size, MEM_RESERVE | MEM_COMMIT,
                        PAGE_EXECUTE_READWRITE);
    return buf;
}
#else
static inline void *alloc_code_gen_buffer(void)
{
    int prot = PROT_WRITE | PROT_READ | PROT_EXEC;
    int flags = MAP_PRIVATE | MAP_ANONYMOUS;
    uintptr_t start = 0;
    size_t size = tcg_ctx->code_gen_buffer_size;
    void *buf;

    /* Constrain the position of the buffer based on the host cpu.
       Note that these addresses are chosen in concert with the
       addresses assigned in the relevant linker script file.  */
# if defined(__PIE__) || defined(__PIC__)
    /* Don't bother setting a preferred location if we're building
       a position-independent executable.  We're more likely to get
       an address near the main executable if we let the kernel
       choose the address.  */
# elif defined(__x86_64__) && defined(MAP_32BIT)
    /* Force the memory down into low memory with the executable.
       Leave the choice of exact location with the kernel.  */
    flags |= MAP_32BIT;
    /* Cannot expect to map more than 800MB in low memory.  */
    if (size > 800u * 1024 * 1024) {
        tcg_ctx->code_gen_buffer_size = size = 800u * 1024 * 1024;
    }
# elif defined(__sparc__)
    start = 0x40000000ul;
# elif defined(__s390x__)
    start = 0x90000000ul;
# elif defined(__mips__)
#  if _MIPS_SIM == _ABI64
    start = 0x128000000ul;
#  else
    start = 0x08000000ul;
#  endif
# endif

    buf = mmap((void *)start, size, prot, flags, -1, 0);
    if (buf == MAP_FAILED) {
        return NULL;
    }

#ifdef __mips__
    if (cross_256mb(buf, size)) {
        /* Try again, with the original still mapped, to avoid re-acquiring
           that 256mb crossing.  This time don't specify an address.  */
        size_t size2;
        void *buf2 = mmap(NULL, size, prot, flags, -1, 0);
        switch ((int)(buf2 != MAP_FAILED)) {
        case 1:
            if (!cross_256mb(buf2, size)) {
                /* Success!  Use the new buffer.  */
                munmap(buf, size);
                break;
            }
            /* Failure.  Work with what we had.  */
            munmap(buf2, size);
            /* fallthru */
        default:
            /* Split the original buffer.  Free the smaller half.  */
            buf2 = split_cross_256mb(buf, size);
            size2 = tcg_ctx->code_gen_buffer_size;
            if (buf == buf2) {
                munmap(buf + size2, size - size2);
            } else {
                munmap(buf, size - size2);
            }
            size = size2;
            break;
        }
        buf = buf2;
    }
#endif

    /* Request large pages for the buffer.  */
    qemu_madvise(buf, size, QEMU_MADV_HUGEPAGE);

    return buf;
}
#endif /* USE_STATIC_CODE_GEN_BUFFER, WIN32, POSIX */

/* compare a pointer @ptr and a tb_tc @s */
static int ptr_cmp_tb_tc(const void *ptr, const struct tb_tc *s)
{
    if (ptr >= s->ptr + s->size) {
        return 1;
    } else if (ptr < s->ptr) {
        return -1;
    }
    return 0;
}

static gint tb_tc_cmp(gconstpointer ap, gconstpointer bp)
{
    const struct tb_tc *a = ap;
    const struct tb_tc *b = bp;

    /*
     * When both sizes are set, we know this isn't a lookup.
     * This is the most likely case: every TB must be inserted; lookups
     * are a lot less frequent.
     */
    if (likely(a->size && b->size)) {
        if (a->ptr > b->ptr) {
            return 1;
        } else if (a->ptr < b->ptr) {
            return -1;
        }
        /* a->ptr == b->ptr should happen only on deletions */
        g_assert(a->size == b->size);
        return 0;
    }
    /*
     * All lookups have either .size field set to 0.
     * From the glib sources we see that @ap is always the lookup key. However
     * the docs provide no guarantee, so we just mark this case as likely.
     */
    if (likely(a->size == 0)) {
        return ptr_cmp_tb_tc(a->ptr, b);
    }
    return ptr_cmp_tb_tc(b->ptr, a);
}

static inline void code_gen_alloc(size_t tb_size)
{
    tcg_ctx->code_gen_buffer_size = size_code_gen_buffer(tb_size);
    tcg_ctx->code_gen_buffer = alloc_code_gen_buffer();
    if (tcg_ctx->code_gen_buffer == NULL) {
        fprintf(stderr, "Could not allocate dynamic translator buffer\n");
        exit(1);
    }
    tb_ctx.tb_tree = g_tree_new(tb_tc_cmp);
    qemu_mutex_init(&tb_ctx.tb_lock);
}

static void tb_htable_init(void)
{
    unsigned int mode = QHT_MODE_AUTO_RESIZE;

    qht_init(&tb_ctx.htable, CODE_GEN_HTABLE_SIZE, mode);
}

/* Must be called before using the QEMU cpus. 'tb_size' is the size
   (in bytes) allocated to the translation buffer. Zero means default
   size. */
void tcg_exec_init(unsigned long tb_size)
{
    tcg_allowed = true;
    cpu_gen_init();
    page_init();
    tb_htable_init();
    code_gen_alloc(tb_size);
#if defined(CONFIG_SOFTMMU)
    /* There's no guest base to take into account, so go ahead and
       initialize the prologue now.  */
    tcg_prologue_init(tcg_ctx);
#endif
}

/*
 * Allocate a new translation block. Flush the translation buffer if
 * too many translation blocks or too much generated code.
 *
 * Called with tb_lock held.
 */
static TranslationBlock *tb_alloc(target_ulong pc)
{
    TranslationBlock *tb;

    assert_tb_locked();

    tb = tcg_tb_alloc(tcg_ctx);
    if (unlikely(tb == NULL)) {
        return NULL;
    }
    return tb;
}

/* Called with tb_lock held.  */
void tb_remove(TranslationBlock *tb)
{
    assert_tb_locked();

    g_tree_remove(tb_ctx.tb_tree, &tb->tc);
}

static inline void invalidate_page_bitmap(PageDesc *p)
{
#ifdef CONFIG_SOFTMMU
    g_free(p->code_bitmap);
    p->code_bitmap = NULL;
    p->code_write_count = 0;
#endif
}

/* Set to NULL all the 'first_tb' fields in all PageDescs. */
static void page_flush_tb_1(int level, void **lp)
{
    int i;

    if (*lp == NULL) {
        return;
    }
    if (level == 0) {
        PageDesc *pd = *lp;

        for (i = 0; i < V_L2_SIZE; ++i) {
            pd[i].first_tb = NULL;
            invalidate_page_bitmap(pd + i);
        }
    } else {
        void **pp = *lp;

        for (i = 0; i < V_L2_SIZE; ++i) {
            page_flush_tb_1(level - 1, pp + i);
        }
    }
}

static void page_flush_tb(void)
{
    int i, l1_sz = v_l1_size;

    for (i = 0; i < l1_sz; i++) {
        page_flush_tb_1(v_l2_levels, l1_map + i);
    }
}

static gboolean tb_host_size_iter(gpointer key, gpointer value, gpointer data)
{
    const TranslationBlock *tb = value;
    size_t *size = data;

    *size += tb->tc.size;
    return false;
}

/* flush all the translation blocks */
static void do_tb_flush(CPUState *cpu, run_on_cpu_data tb_flush_count)
{
    tb_lock();

    /* If it is already been done on request of another CPU,
     * just retry.
     */
    if (tb_ctx.tb_flush_count != tb_flush_count.host_int) {
        goto done;
    }

    if (DEBUG_TB_FLUSH_GATE) {
        size_t nb_tbs = g_tree_nnodes(tb_ctx.tb_tree);
        size_t host_size = 0;

        g_tree_foreach(tb_ctx.tb_tree, tb_host_size_iter, &host_size);
        printf("qemu: flush code_size=%zu nb_tbs=%zu avg_tb_size=%zu\n",
               tcg_code_size(), nb_tbs, nb_tbs > 0 ? host_size / nb_tbs : 0);
    }

    CPU_FOREACH(cpu) {
        cpu_tb_jmp_cache_clear(cpu);
    }

    /* Increment the refcount first so that destroy acts as a reset */
    g_tree_ref(tb_ctx.tb_tree);
    g_tree_destroy(tb_ctx.tb_tree);

    qht_reset_size(&tb_ctx.htable, CODE_GEN_HTABLE_SIZE);
    page_flush_tb();

    tcg_region_reset_all();
    /* XXX: flush processor icache at this point if cache flush is
       expensive */
    atomic_mb_set(&tb_ctx.tb_flush_count, tb_ctx.tb_flush_count + 1);

done:
    tb_unlock();
}

void tb_flush(CPUState *cpu)
{
    if (tcg_enabled()) {
        unsigned tb_flush_count = atomic_mb_read(&tb_ctx.tb_flush_count);
        async_safe_run_on_cpu(cpu, do_tb_flush,
                              RUN_ON_CPU_HOST_INT(tb_flush_count));
    }
}

/*
 * Formerly ifdef DEBUG_TB_CHECK. These debug functions are user-mode-only,
 * so in order to prevent bit rot we compile them unconditionally in user-mode,
 * and let the optimizer get rid of them by wrapping their user-only callers
 * with if (DEBUG_TB_CHECK_GATE).
 */
#ifdef CONFIG_USER_ONLY

static void
do_tb_invalidate_check(struct qht *ht, void *p, uint32_t hash, void *userp)
{
    TranslationBlock *tb = p;
    target_ulong addr = *(target_ulong *)userp;

    if (!(addr + TARGET_PAGE_SIZE <= tb->pc || addr >= tb->pc + tb->size)) {
        printf("ERROR invalidate: address=" TARGET_FMT_lx
               " PC=%08lx size=%04x\n", addr, (long)tb->pc, tb->size);
    }
}

/* verify that all the pages have correct rights for code
 *
 * Called with tb_lock held.
 */
static void tb_invalidate_check(target_ulong address)
{
    address &= TARGET_PAGE_MASK;
    qht_iter(&tb_ctx.htable, do_tb_invalidate_check, &address);
}

static void
do_tb_page_check(struct qht *ht, void *p, uint32_t hash, void *userp)
{
    TranslationBlock *tb = p;
    int flags1, flags2;

    flags1 = page_get_flags(tb->pc);
    flags2 = page_get_flags(tb->pc + tb->size - 1);
    if ((flags1 & PAGE_WRITE) || (flags2 & PAGE_WRITE)) {
        printf("ERROR page flags: PC=%08lx size=%04x f1=%x f2=%x\n",
               (long)tb->pc, tb->size, flags1, flags2);
    }
}

/* verify that all the pages have correct rights for code */
static void tb_page_check(void)
{
    qht_iter(&tb_ctx.htable, do_tb_page_check, NULL);
}

#endif /* CONFIG_USER_ONLY */

static inline void tb_page_remove(TranslationBlock **ptb, TranslationBlock *tb)
{
    TranslationBlock *tb1;
    unsigned int n1;

    for (;;) {
        tb1 = *ptb;
        n1 = (uintptr_t)tb1 & 3;
        tb1 = (TranslationBlock *)((uintptr_t)tb1 & ~3);
        if (tb1 == tb) {
            *ptb = tb1->page_next[n1];
            break;
        }
        ptb = &tb1->page_next[n1];
    }
}

/* remove the TB from a list of TBs jumping to the n-th jump target of the TB */
static inline void tb_remove_from_jmp_list(TranslationBlock *tb, int n)
{
    TranslationBlock *tb1;
    uintptr_t *ptb, ntb;
    unsigned int n1;

    ptb = &tb->jmp_list_next[n];
    if (*ptb) {
        /* find tb(n) in circular list */
        for (;;) {
            ntb = *ptb;
            n1 = ntb & 3;
            tb1 = (TranslationBlock *)(ntb & ~3);
            if (n1 == n && tb1 == tb) {
                break;
            }
            if (n1 == 2) {
                ptb = &tb1->jmp_list_first;
            } else {
                ptb = &tb1->jmp_list_next[n1];
            }
        }
        /* now we can suppress tb(n) from the list */
        *ptb = tb->jmp_list_next[n];

        tb->jmp_list_next[n] = (uintptr_t)NULL;
    }
}

/* reset the jump entry 'n' of a TB so that it is not chained to
   another TB */
static inline void tb_reset_jump(TranslationBlock *tb, int n)
{
    uintptr_t addr = (uintptr_t)(tb->tc.ptr + tb->jmp_reset_offset[n]);
    tb_set_jmp_target(tb, n, addr);
}

/* remove any jumps to the TB */
static inline void tb_jmp_unlink(TranslationBlock *tb)
{
    TranslationBlock *tb1;
    uintptr_t *ptb, ntb;
    unsigned int n1;

    ptb = &tb->jmp_list_first;
    for (;;) {
        ntb = *ptb;
        n1 = ntb & 3;
        tb1 = (TranslationBlock *)(ntb & ~3);
        if (n1 == 2) {
            break;
        }
        tb_reset_jump(tb1, n1);
        *ptb = tb1->jmp_list_next[n1];
        tb1->jmp_list_next[n1] = (uintptr_t)NULL;
    }
}

/* invalidate one TB
 *
 * Called with tb_lock held.
 */
void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr)
{
    CPUState *cpu;
    PageDesc *p;
    uint32_t h;
    tb_page_addr_t phys_pc;

    assert_tb_locked();

    atomic_set(&tb->cflags, tb->cflags | CF_INVALID);

    /* remove the TB from the hash list */
    phys_pc = tb->page_addr[0] + (tb->pc & ~TARGET_PAGE_MASK);
    h = tb_hash_func(phys_pc, tb->pc, tb->flags, tb->cflags & CF_HASH_MASK,
                     tb->trace_vcpu_dstate);
    if (!qht_remove(&tb_ctx.htable, tb, h)) {
        return;
    }

    /* remove the TB from the page list */
    if (tb->page_addr[0] != page_addr) {
        p = page_find(tb->page_addr[0] >> TARGET_PAGE_BITS);
        tb_page_remove(&p->first_tb, tb);
        invalidate_page_bitmap(p);
    }
    if (tb->page_addr[1] != -1 && tb->page_addr[1] != page_addr) {
        p = page_find(tb->page_addr[1] >> TARGET_PAGE_BITS);
        tb_page_remove(&p->first_tb, tb);
        invalidate_page_bitmap(p);
    }

    /* remove the TB from the hash list */
    h = tb_jmp_cache_hash_func(tb->pc);
    CPU_FOREACH(cpu) {
        if (atomic_read(&cpu->tb_jmp_cache[h]) == tb) {
            atomic_set(&cpu->tb_jmp_cache[h], NULL);
        }
    }

    /* suppress this TB from the two jump lists */
    tb_remove_from_jmp_list(tb, 0);
    tb_remove_from_jmp_list(tb, 1);

    /* suppress any remaining jumps to this TB */
    tb_jmp_unlink(tb);

    tb_ctx.tb_phys_invalidate_count++;
}

#ifdef CONFIG_SOFTMMU
static void build_page_bitmap(PageDesc *p)
{
    int n, tb_start, tb_end;
    TranslationBlock *tb;

    p->code_bitmap = bitmap_new(TARGET_PAGE_SIZE);

    tb = p->first_tb;
    while (tb != NULL) {
        n = (uintptr_t)tb & 3;
        tb = (TranslationBlock *)((uintptr_t)tb & ~3);
        /* NOTE: this is subtle as a TB may span two physical pages */
        if (n == 0) {
            /* NOTE: tb_end may be after the end of the page, but
               it is not a problem */
            tb_start = tb->pc & ~TARGET_PAGE_MASK;
            tb_end = tb_start + tb->size;
            if (tb_end > TARGET_PAGE_SIZE) {
                tb_end = TARGET_PAGE_SIZE;
             }
        } else {
            tb_start = 0;
            tb_end = ((tb->pc + tb->size) & ~TARGET_PAGE_MASK);
        }
        bitmap_set(p->code_bitmap, tb_start, tb_end - tb_start);
        tb = tb->page_next[n];
    }
}
#endif

/* add the tb in the target page and protect it if necessary
 *
 * Called with mmap_lock held for user-mode emulation.
 */
static inline void tb_alloc_page(TranslationBlock *tb,
                                 unsigned int n, tb_page_addr_t page_addr)
{
    PageDesc *p;
#ifndef CONFIG_USER_ONLY
    bool page_already_protected;
#endif

    assert_memory_lock();

    tb->page_addr[n] = page_addr;
    p = page_find_alloc(page_addr >> TARGET_PAGE_BITS, 1);
    tb->page_next[n] = p->first_tb;
#ifndef CONFIG_USER_ONLY
    page_already_protected = p->first_tb != NULL;
#endif
    p->first_tb = (TranslationBlock *)((uintptr_t)tb | n);
    invalidate_page_bitmap(p);

#if defined(CONFIG_USER_ONLY)
    if (p->flags & PAGE_WRITE) {
        target_ulong addr;
        PageDesc *p2;
        int prot;

        /* force the host page as non writable (writes will have a
           page fault + mprotect overhead) */
        page_addr &= qemu_host_page_mask;
        prot = 0;
        for (addr = page_addr; addr < page_addr + qemu_host_page_size;
            addr += TARGET_PAGE_SIZE) {

            p2 = page_find(addr >> TARGET_PAGE_BITS);
            if (!p2) {
                continue;
            }
            prot |= p2->flags;
            p2->flags &= ~PAGE_WRITE;
          }
        mprotect(g2h(page_addr), qemu_host_page_size,
                 (prot & PAGE_BITS) & ~PAGE_WRITE);
        if (DEBUG_TB_INVALIDATE_GATE) {
            printf("protecting code page: 0x" TB_PAGE_ADDR_FMT "\n", page_addr);
        }
    }
#else
    /* if some code is already present, then the pages are already
       protected. So we handle the case where only the first TB is
       allocated in a physical page */
    if (!page_already_protected) {
        tlb_protect_code(page_addr);
    }
#endif
}

/* add a new TB and link it to the physical page tables. phys_page2 is
 * (-1) to indicate that only one page contains the TB.
 *
 * Called with mmap_lock held for user-mode emulation.
 */
static void tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc,
                         tb_page_addr_t phys_page2)
{
    uint32_t h;

    assert_memory_lock();

    /* add in the page list */
    tb_alloc_page(tb, 0, phys_pc & TARGET_PAGE_MASK);
    if (phys_page2 != -1) {
        tb_alloc_page(tb, 1, phys_page2);
    } else {
        tb->page_addr[1] = -1;
    }

    /* add in the hash table */
    h = tb_hash_func(phys_pc, tb->pc, tb->flags, tb->cflags & CF_HASH_MASK,
                     tb->trace_vcpu_dstate);
    qht_insert(&tb_ctx.htable, tb, h);

#ifdef CONFIG_USER_ONLY
    if (DEBUG_TB_CHECK_GATE) {
        tb_page_check();
    }
#endif
}

/* Called with mmap_lock held for user mode emulation.  */
TranslationBlock *tb_gen_code(CPUState *cpu,
                              target_ulong pc, target_ulong cs_base,
                              uint32_t flags, int cflags)
{
    CPUArchState *env = cpu->env_ptr;
    TranslationBlock *tb;
    tb_page_addr_t phys_pc, phys_page2;
    target_ulong virt_page2;
    tcg_insn_unit *gen_code_buf;
    int gen_code_size, search_size;
#ifdef CONFIG_PROFILER
    TCGProfile *prof = &tcg_ctx->prof;
    int64_t ti;
#endif
    assert_memory_lock();

    phys_pc = get_page_addr_code(env, pc);

 buffer_overflow:
    tb = tb_alloc(pc);
    if (unlikely(!tb)) {
        /* flush must be done */
        tb_flush(cpu);
        mmap_unlock();
        /* Make the execution loop process the flush as soon as possible.  */
        cpu->exception_index = EXCP_INTERRUPT;
        cpu_loop_exit(cpu);
    }

    gen_code_buf = tcg_ctx->code_gen_ptr;
    tb->tc.ptr = gen_code_buf;
    tb->pc = pc;
    tb->cs_base = cs_base;
    tb->flags = flags;
    tb->cflags = cflags;
    tb->trace_vcpu_dstate = *cpu->trace_dstate;
    tcg_ctx->tb_cflags = cflags;

#ifdef CONFIG_PROFILER
    /* includes aborted translations because of exceptions */
    atomic_set(&prof->tb_count1, prof->tb_count1 + 1);
    ti = profile_getclock();
#endif

    tcg_func_start(tcg_ctx);

    tcg_ctx->cpu = ENV_GET_CPU(env);
    gen_intermediate_code(cpu, tb);
    tcg_ctx->cpu = NULL;

    trace_translate_block(tb, tb->pc, tb->tc.ptr);

    /* generate machine code */
    tb->jmp_reset_offset[0] = TB_JMP_RESET_OFFSET_INVALID;
    tb->jmp_reset_offset[1] = TB_JMP_RESET_OFFSET_INVALID;
    tcg_ctx->tb_jmp_reset_offset = tb->jmp_reset_offset;
    if (TCG_TARGET_HAS_direct_jump) {
        tcg_ctx->tb_jmp_insn_offset = tb->jmp_target_arg;
        tcg_ctx->tb_jmp_target_addr = NULL;
    } else {
        tcg_ctx->tb_jmp_insn_offset = NULL;
        tcg_ctx->tb_jmp_target_addr = tb->jmp_target_arg;
    }

#ifdef CONFIG_PROFILER
    atomic_set(&prof->tb_count, prof->tb_count + 1);
    atomic_set(&prof->interm_time, prof->interm_time + profile_getclock() - ti);
    ti = profile_getclock();
#endif

    /* ??? Overflow could be handled better here.  In particular, we
       don't need to re-do gen_intermediate_code, nor should we re-do
       the tcg optimization currently hidden inside tcg_gen_code.  All
       that should be required is to flush the TBs, allocate a new TB,
       re-initialize it per above, and re-do the actual code generation.  */
    gen_code_size = tcg_gen_code(tcg_ctx, tb);
    if (unlikely(gen_code_size < 0)) {
        goto buffer_overflow;
    }
    search_size = encode_search(tb, (void *)gen_code_buf + gen_code_size);
    if (unlikely(search_size < 0)) {
        goto buffer_overflow;
    }
    tb->tc.size = gen_code_size;

#ifdef CONFIG_PROFILER
    atomic_set(&prof->code_time, prof->code_time + profile_getclock() - ti);
    atomic_set(&prof->code_in_len, prof->code_in_len + tb->size);
    atomic_set(&prof->code_out_len, prof->code_out_len + gen_code_size);
    atomic_set(&prof->search_out_len, prof->search_out_len + search_size);
#endif

#ifdef DEBUG_DISAS
    if (qemu_loglevel_mask(CPU_LOG_TB_OUT_ASM) &&
        qemu_log_in_addr_range(tb->pc)) {
        qemu_log_lock();
        qemu_log("OUT: [size=%d]\n", gen_code_size);
        if (tcg_ctx->data_gen_ptr) {
            size_t code_size = tcg_ctx->data_gen_ptr - tb->tc.ptr;
            size_t data_size = gen_code_size - code_size;
            size_t i;

            log_disas(tb->tc.ptr, code_size);

            for (i = 0; i < data_size; i += sizeof(tcg_target_ulong)) {
                if (sizeof(tcg_target_ulong) == 8) {
                    qemu_log("0x%08" PRIxPTR ":  .quad  0x%016" PRIx64 "\n",
                             (uintptr_t)tcg_ctx->data_gen_ptr + i,
                             *(uint64_t *)(tcg_ctx->data_gen_ptr + i));
                } else {
                    qemu_log("0x%08" PRIxPTR ":  .long  0x%08x\n",
                             (uintptr_t)tcg_ctx->data_gen_ptr + i,
                             *(uint32_t *)(tcg_ctx->data_gen_ptr + i));
                }
            }
        } else {
            log_disas(tb->tc.ptr, gen_code_size);
        }
        qemu_log("\n");
        qemu_log_flush();
        qemu_log_unlock();
    }
#endif

    atomic_set(&tcg_ctx->code_gen_ptr, (void *)
        ROUND_UP((uintptr_t)gen_code_buf + gen_code_size + search_size,
                 CODE_GEN_ALIGN));

    /* init jump list */
    assert(((uintptr_t)tb & 3) == 0);
    tb->jmp_list_first = (uintptr_t)tb | 2;
    tb->jmp_list_next[0] = (uintptr_t)NULL;
    tb->jmp_list_next[1] = (uintptr_t)NULL;

    /* init original jump addresses wich has been set during tcg_gen_code() */
    if (tb->jmp_reset_offset[0] != TB_JMP_RESET_OFFSET_INVALID) {
        tb_reset_jump(tb, 0);
    }
    if (tb->jmp_reset_offset[1] != TB_JMP_RESET_OFFSET_INVALID) {
        tb_reset_jump(tb, 1);
    }

    /* check next page if needed */
    virt_page2 = (pc + tb->size - 1) & TARGET_PAGE_MASK;
    phys_page2 = -1;
    if ((pc & TARGET_PAGE_MASK) != virt_page2) {
        phys_page2 = get_page_addr_code(env, virt_page2);
    }
    /* As long as consistency of the TB stuff is provided by tb_lock in user
     * mode and is implicit in single-threaded softmmu emulation, no explicit
     * memory barrier is required before tb_link_page() makes the TB visible
     * through the physical hash table and physical page list.
     */
    tb_link_page(tb, phys_pc, phys_page2);
    g_tree_insert(tb_ctx.tb_tree, &tb->tc, tb);
    return tb;
}

/*
 * Invalidate all TBs which intersect with the target physical address range
 * [start;end[. NOTE: start and end may refer to *different* physical pages.
 * 'is_cpu_write_access' should be true if called from a real cpu write
 * access: the virtual CPU will exit the current TB if code is modified inside
 * this TB.
 *
 * Called with mmap_lock held for user-mode emulation, grabs tb_lock
 * Called with tb_lock held for system-mode emulation
 */
static void tb_invalidate_phys_range_1(tb_page_addr_t start, tb_page_addr_t end)
{
    while (start < end) {
        tb_invalidate_phys_page_range(start, end, 0);
        start &= TARGET_PAGE_MASK;
        start += TARGET_PAGE_SIZE;
    }
}

#ifdef CONFIG_SOFTMMU
void tb_invalidate_phys_range(tb_page_addr_t start, tb_page_addr_t end)
{
    assert_tb_locked();
    tb_invalidate_phys_range_1(start, end);
}
#else
void tb_invalidate_phys_range(tb_page_addr_t start, tb_page_addr_t end)
{
    assert_memory_lock();
    tb_lock();
    tb_invalidate_phys_range_1(start, end);
    tb_unlock();
}
#endif
/*
 * Invalidate all TBs which intersect with the target physical address range
 * [start;end[. NOTE: start and end must refer to the *same* physical page.
 * 'is_cpu_write_access' should be true if called from a real cpu write
 * access: the virtual CPU will exit the current TB if code is modified inside
 * this TB.
 *
 * Called with tb_lock/mmap_lock held for user-mode emulation
 * Called with tb_lock held for system-mode emulation
 */
void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t end,
                                   int is_cpu_write_access)
{
    TranslationBlock *tb, *tb_next;
    tb_page_addr_t tb_start, tb_end;
    PageDesc *p;
    int n;
#ifdef TARGET_HAS_PRECISE_SMC
    CPUState *cpu = current_cpu;
    CPUArchState *env = NULL;
    int current_tb_not_found = is_cpu_write_access;
    TranslationBlock *current_tb = NULL;
    int current_tb_modified = 0;
    target_ulong current_pc = 0;
    target_ulong current_cs_base = 0;
    uint32_t current_flags = 0;
#endif /* TARGET_HAS_PRECISE_SMC */

    assert_memory_lock();
    assert_tb_locked();

    p = page_find(start >> TARGET_PAGE_BITS);
    if (!p) {
        return;
    }
#if defined(TARGET_HAS_PRECISE_SMC)
    if (cpu != NULL) {
        env = cpu->env_ptr;
    }
#endif

    /* we remove all the TBs in the range [start, end[ */
    /* XXX: see if in some cases it could be faster to invalidate all
       the code */
    tb = p->first_tb;
    while (tb != NULL) {
        n = (uintptr_t)tb & 3;
        tb = (TranslationBlock *)((uintptr_t)tb & ~3);
        tb_next = tb->page_next[n];
        /* NOTE: this is subtle as a TB may span two physical pages */
        if (n == 0) {
            /* NOTE: tb_end may be after the end of the page, but
               it is not a problem */
            tb_start = tb->page_addr[0] + (tb->pc & ~TARGET_PAGE_MASK);
            tb_end = tb_start + tb->size;
        } else {
            tb_start = tb->page_addr[1];
            tb_end = tb_start + ((tb->pc + tb->size) & ~TARGET_PAGE_MASK);
        }
        if (!(tb_end <= start || tb_start >= end)) {
#ifdef TARGET_HAS_PRECISE_SMC
            if (current_tb_not_found) {
                current_tb_not_found = 0;
                current_tb = NULL;
                if (cpu->mem_io_pc) {
                    /* now we have a real cpu fault */
                    current_tb = tb_find_pc(cpu->mem_io_pc);
                }
            }
            if (current_tb == tb &&
                (current_tb->cflags & CF_COUNT_MASK) != 1) {
                /* If we are modifying the current TB, we must stop
                its execution. We could be more precise by checking
                that the modification is after the current PC, but it
                would require a specialized function to partially
                restore the CPU state */

                current_tb_modified = 1;
                cpu_restore_state_from_tb(cpu, current_tb, cpu->mem_io_pc);
                cpu_get_tb_cpu_state(env, &current_pc, &current_cs_base,
                                     &current_flags);
            }
#endif /* TARGET_HAS_PRECISE_SMC */
            tb_phys_invalidate(tb, -1);
        }
        tb = tb_next;
    }
#if !defined(CONFIG_USER_ONLY)
    /* if no code remaining, no need to continue to use slow writes */
    if (!p->first_tb) {
        invalidate_page_bitmap(p);
        tlb_unprotect_code(start);
    }
#endif
#ifdef TARGET_HAS_PRECISE_SMC
    if (current_tb_modified) {
        /* Force execution of one insn next time.  */
        cpu->cflags_next_tb = 1 | curr_cflags();
        cpu_loop_exit_noexc(cpu);
    }
#endif
}

#ifdef CONFIG_SOFTMMU
/* len must be <= 8 and start must be a multiple of len.
 * Called via softmmu_template.h when code areas are written to with
 * iothread mutex not held.
 */
void tb_invalidate_phys_page_fast(tb_page_addr_t start, int len)
{
    PageDesc *p;

#if 0
    if (1) {
        qemu_log("modifying code at 0x%x size=%d EIP=%x PC=%08x\n",
                  cpu_single_env->mem_io_vaddr, len,
                  cpu_single_env->eip,
                  cpu_single_env->eip +
                  (intptr_t)cpu_single_env->segs[R_CS].base);
    }
#endif
    assert_memory_lock();

    p = page_find(start >> TARGET_PAGE_BITS);
    if (!p) {
        return;
    }
    if (!p->code_bitmap &&
        ++p->code_write_count >= SMC_BITMAP_USE_THRESHOLD) {
        /* build code bitmap.  FIXME: writes should be protected by
         * tb_lock, reads by tb_lock or RCU.
         */
        build_page_bitmap(p);
    }
    if (p->code_bitmap) {
        unsigned int nr;
        unsigned long b;

        nr = start & ~TARGET_PAGE_MASK;
        b = p->code_bitmap[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG - 1));
        if (b & ((1 << len) - 1)) {
            goto do_invalidate;
        }
    } else {
    do_invalidate:
        tb_invalidate_phys_page_range(start, start + len, 1);
    }
}
#else
/* Called with mmap_lock held. If pc is not 0 then it indicates the
 * host PC of the faulting store instruction that caused this invalidate.
 * Returns true if the caller needs to abort execution of the current
 * TB (because it was modified by this store and the guest CPU has
 * precise-SMC semantics).
 */
static bool tb_invalidate_phys_page(tb_page_addr_t addr, uintptr_t pc)
{
    TranslationBlock *tb;
    PageDesc *p;
    int n;
#ifdef TARGET_HAS_PRECISE_SMC
    TranslationBlock *current_tb = NULL;
    CPUState *cpu = current_cpu;
    CPUArchState *env = NULL;
    int current_tb_modified = 0;
    target_ulong current_pc = 0;
    target_ulong current_cs_base = 0;
    uint32_t current_flags = 0;
#endif

    assert_memory_lock();

    addr &= TARGET_PAGE_MASK;
    p = page_find(addr >> TARGET_PAGE_BITS);
    if (!p) {
        return false;
    }

    tb_lock();
    tb = p->first_tb;
#ifdef TARGET_HAS_PRECISE_SMC
    if (tb && pc != 0) {
        current_tb = tb_find_pc(pc);
    }
    if (cpu != NULL) {
        env = cpu->env_ptr;
    }
#endif
    while (tb != NULL) {
        n = (uintptr_t)tb & 3;
        tb = (TranslationBlock *)((uintptr_t)tb & ~3);
#ifdef TARGET_HAS_PRECISE_SMC
        if (current_tb == tb &&
            (current_tb->cflags & CF_COUNT_MASK) != 1) {
                /* If we are modifying the current TB, we must stop
                   its execution. We could be more precise by checking
                   that the modification is after the current PC, but it
                   would require a specialized function to partially
                   restore the CPU state */

            current_tb_modified = 1;
            cpu_restore_state_from_tb(cpu, current_tb, pc);
            cpu_get_tb_cpu_state(env, &current_pc, &current_cs_base,
                                 &current_flags);
        }
#endif /* TARGET_HAS_PRECISE_SMC */
        tb_phys_invalidate(tb, addr);
        tb = tb->page_next[n];
    }
    p->first_tb = NULL;
#ifdef TARGET_HAS_PRECISE_SMC
    if (current_tb_modified) {
        /* Force execution of one insn next time.  */
        cpu->cflags_next_tb = 1 | curr_cflags();
        /* tb_lock will be reset after cpu_loop_exit_noexc longjmps
         * back into the cpu_exec loop. */
        return true;
    }
#endif
    tb_unlock();

    return false;
}
#endif

/*
 * Find the TB 'tb' such that
 * tb->tc.ptr <= tc_ptr < tb->tc.ptr + tb->tc.size
 * Return NULL if not found.
 */
static TranslationBlock *tb_find_pc(uintptr_t tc_ptr)
{
    struct tb_tc s = { .ptr = (void *)tc_ptr };

    return g_tree_lookup(tb_ctx.tb_tree, &s);
}

#if !defined(CONFIG_USER_ONLY)
void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr)
{
    ram_addr_t ram_addr;
    MemoryRegion *mr;
    hwaddr l = 1;

    rcu_read_lock();
    mr = address_space_translate(as, addr, &addr, &l, false);
    if (!(memory_region_is_ram(mr)
          || memory_region_is_romd(mr))) {
        rcu_read_unlock();
        return;
    }
    ram_addr = memory_region_get_ram_addr(mr) + addr;
    tb_lock();
    tb_invalidate_phys_page_range(ram_addr, ram_addr + 1, 0);
    tb_unlock();
    rcu_read_unlock();
}
#endif /* !defined(CONFIG_USER_ONLY) */

/* Called with tb_lock held.  */
void tb_check_watchpoint(CPUState *cpu)
{
    TranslationBlock *tb;

    tb = tb_find_pc(cpu->mem_io_pc);
    if (tb) {
        /* We can use retranslation to find the PC.  */
        cpu_restore_state_from_tb(cpu, tb, cpu->mem_io_pc);
        tb_phys_invalidate(tb, -1);
    } else {
        /* The exception probably happened in a helper.  The CPU state should
           have been saved before calling it. Fetch the PC from there.  */
        CPUArchState *env = cpu->env_ptr;
        target_ulong pc, cs_base;
        tb_page_addr_t addr;
        uint32_t flags;

        cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags);
        addr = get_page_addr_code(env, pc);
        tb_invalidate_phys_range(addr, addr + 1);
    }
}

#ifndef CONFIG_USER_ONLY
/* in deterministic execution mode, instructions doing device I/Os
 * must be at the end of the TB.
 *
 * Called by softmmu_template.h, with iothread mutex not held.
 */
void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr)
{
#if defined(TARGET_MIPS) || defined(TARGET_SH4)
    CPUArchState *env = cpu->env_ptr;
#endif
    TranslationBlock *tb;
    uint32_t n;

    tb_lock();
    tb = tb_find_pc(retaddr);
    if (!tb) {
        cpu_abort(cpu, "cpu_io_recompile: could not find TB for pc=%p",
                  (void *)retaddr);
    }
    n = cpu->icount_decr.u16.low + tb->icount;
    cpu_restore_state_from_tb(cpu, tb, retaddr);
    /* Calculate how many instructions had been executed before the fault
       occurred.  */
    n = n - cpu->icount_decr.u16.low;
    /* Generate a new TB ending on the I/O insn.  */
    n++;
    /* On MIPS and SH, delay slot instructions can only be restarted if
       they were already the first instruction in the TB.  If this is not
       the first instruction in a TB then re-execute the preceding
       branch.  */
#if defined(TARGET_MIPS)
    if ((env->hflags & MIPS_HFLAG_BMASK) != 0 && n > 1) {
        env->active_tc.PC -= (env->hflags & MIPS_HFLAG_B16 ? 2 : 4);
        cpu->icount_decr.u16.low++;
        env->hflags &= ~MIPS_HFLAG_BMASK;
    }
#elif defined(TARGET_SH4)
    if ((env->flags & ((DELAY_SLOT | DELAY_SLOT_CONDITIONAL))) != 0
            && n > 1) {
        env->pc -= 2;
        cpu->icount_decr.u16.low++;
        env->flags &= ~(DELAY_SLOT | DELAY_SLOT_CONDITIONAL);
    }
#endif
    /* This should never happen.  */
    if (n > CF_COUNT_MASK) {
        cpu_abort(cpu, "TB too big during recompile");
    }

    /* Adjust the execution state of the next TB.  */
    cpu->cflags_next_tb = curr_cflags() | CF_LAST_IO | n;

    if (tb->cflags & CF_NOCACHE) {
        if (tb->orig_tb) {
            /* Invalidate original TB if this TB was generated in
             * cpu_exec_nocache() */
            tb_phys_invalidate(tb->orig_tb, -1);
        }
        tb_remove(tb);
    }

    /* TODO: If env->pc != tb->pc (i.e. the faulting instruction was not
     * the first in the TB) then we end up generating a whole new TB and
     *  repeating the fault, which is horribly inefficient.
     *  Better would be to execute just this insn uncached, or generate a
     *  second new TB.
     *
     * cpu_loop_exit_noexc will longjmp back to cpu_exec where the
     * tb_lock gets reset.
     */
    cpu_loop_exit_noexc(cpu);
}

static void tb_jmp_cache_clear_page(CPUState *cpu, target_ulong page_addr)
{
    unsigned int i, i0 = tb_jmp_cache_hash_page(page_addr);

    for (i = 0; i < TB_JMP_PAGE_SIZE; i++) {
        atomic_set(&cpu->tb_jmp_cache[i0 + i], NULL);
    }
}

void tb_flush_jmp_cache(CPUState *cpu, target_ulong addr)
{
    /* Discard jump cache entries for any tb which might potentially
       overlap the flushed page.  */
    tb_jmp_cache_clear_page(cpu, addr - TARGET_PAGE_SIZE);
    tb_jmp_cache_clear_page(cpu, addr);
}

static void print_qht_statistics(FILE *f, fprintf_function cpu_fprintf,
                                 struct qht_stats hst)
{
    uint32_t hgram_opts;
    size_t hgram_bins;
    char *hgram;

    if (!hst.head_buckets) {
        return;
    }
    cpu_fprintf(f, "TB hash buckets     %zu/%zu (%0.2f%% head buckets used)\n",
                hst.used_head_buckets, hst.head_buckets,
                (double)hst.used_head_buckets / hst.head_buckets * 100);

    hgram_opts =  QDIST_PR_BORDER | QDIST_PR_LABELS;
    hgram_opts |= QDIST_PR_100X   | QDIST_PR_PERCENT;
    if (qdist_xmax(&hst.occupancy) - qdist_xmin(&hst.occupancy) == 1) {
        hgram_opts |= QDIST_PR_NODECIMAL;
    }
    hgram = qdist_pr(&hst.occupancy, 10, hgram_opts);
    cpu_fprintf(f, "TB hash occupancy   %0.2f%% avg chain occ. Histogram: %s\n",
                qdist_avg(&hst.occupancy) * 100, hgram);
    g_free(hgram);

    hgram_opts = QDIST_PR_BORDER | QDIST_PR_LABELS;
    hgram_bins = qdist_xmax(&hst.chain) - qdist_xmin(&hst.chain);
    if (hgram_bins > 10) {
        hgram_bins = 10;
    } else {
        hgram_bins = 0;
        hgram_opts |= QDIST_PR_NODECIMAL | QDIST_PR_NOBINRANGE;
    }
    hgram = qdist_pr(&hst.chain, hgram_bins, hgram_opts);
    cpu_fprintf(f, "TB hash avg chain   %0.3f buckets. Histogram: %s\n",
                qdist_avg(&hst.chain), hgram);
    g_free(hgram);
}

struct tb_tree_stats {
    size_t host_size;
    size_t target_size;
    size_t max_target_size;
    size_t direct_jmp_count;
    size_t direct_jmp2_count;
    size_t cross_page;
};

static gboolean tb_tree_stats_iter(gpointer key, gpointer value, gpointer data)
{
    const TranslationBlock *tb = value;
    struct tb_tree_stats *tst = data;

    tst->host_size += tb->tc.size;
    tst->target_size += tb->size;
    if (tb->size > tst->max_target_size) {
        tst->max_target_size = tb->size;
    }
    if (tb->page_addr[1] != -1) {
        tst->cross_page++;
    }
    if (tb->jmp_reset_offset[0] != TB_JMP_RESET_OFFSET_INVALID) {
        tst->direct_jmp_count++;
        if (tb->jmp_reset_offset[1] != TB_JMP_RESET_OFFSET_INVALID) {
            tst->direct_jmp2_count++;
        }
    }
    return false;
}

void dump_exec_info(FILE *f, fprintf_function cpu_fprintf)
{
    struct tb_tree_stats tst = {};
    struct qht_stats hst;
    size_t nb_tbs;

    tb_lock();

    nb_tbs = g_tree_nnodes(tb_ctx.tb_tree);
    g_tree_foreach(tb_ctx.tb_tree, tb_tree_stats_iter, &tst);
    /* XXX: avoid using doubles ? */
    cpu_fprintf(f, "Translation buffer state:\n");
    /*
     * Report total code size including the padding and TB structs;
     * otherwise users might think "-tb-size" is not honoured.
     * For avg host size we use the precise numbers from tb_tree_stats though.
     */
    cpu_fprintf(f, "gen code size       %zu/%zu\n",
                tcg_code_size(), tcg_code_capacity());
    cpu_fprintf(f, "TB count            %zu\n", nb_tbs);
    cpu_fprintf(f, "TB avg target size  %zu max=%zu bytes\n",
                nb_tbs ? tst.target_size / nb_tbs : 0,
                tst.max_target_size);
    cpu_fprintf(f, "TB avg host size    %zu bytes (expansion ratio: %0.1f)\n",
                nb_tbs ? tst.host_size / nb_tbs : 0,
                tst.target_size ? (double)tst.host_size / tst.target_size : 0);
    cpu_fprintf(f, "cross page TB count %zu (%zu%%)\n", tst.cross_page,
            nb_tbs ? (tst.cross_page * 100) / nb_tbs : 0);
    cpu_fprintf(f, "direct jump count   %zu (%zu%%) (2 jumps=%zu %zu%%)\n",
                tst.direct_jmp_count,
                nb_tbs ? (tst.direct_jmp_count * 100) / nb_tbs : 0,
                tst.direct_jmp2_count,
                nb_tbs ? (tst.direct_jmp2_count * 100) / nb_tbs : 0);

    qht_statistics_init(&tb_ctx.htable, &hst);
    print_qht_statistics(f, cpu_fprintf, hst);
    qht_statistics_destroy(&hst);

    cpu_fprintf(f, "\nStatistics:\n");
    cpu_fprintf(f, "TB flush count      %u\n",
                atomic_read(&tb_ctx.tb_flush_count));
    cpu_fprintf(f, "TB invalidate count %d\n", tb_ctx.tb_phys_invalidate_count);
    cpu_fprintf(f, "TLB flush count     %zu\n", tlb_flush_count());
    tcg_dump_info(f, cpu_fprintf);

    tb_unlock();
}

void dump_opcount_info(FILE *f, fprintf_function cpu_fprintf)
{
    tcg_dump_op_count(f, cpu_fprintf);
}

#else /* CONFIG_USER_ONLY */

void cpu_interrupt(CPUState *cpu, int mask)
{
    g_assert(qemu_mutex_iothread_locked());
    cpu->interrupt_request |= mask;
    cpu->icount_decr.u16.high = -1;
}

/*
 * Walks guest process memory "regions" one by one
 * and calls callback function 'fn' for each region.
 */
struct walk_memory_regions_data {
    walk_memory_regions_fn fn;
    void *priv;
    target_ulong start;
    int prot;
};

static int walk_memory_regions_end(struct walk_memory_regions_data *data,
                                   target_ulong end, int new_prot)
{
    if (data->start != -1u) {
        int rc = data->fn(data->priv, data->start, end, data->prot);
        if (rc != 0) {
            return rc;
        }
    }

    data->start = (new_prot ? end : -1u);
    data->prot = new_prot;

    return 0;
}

static int walk_memory_regions_1(struct walk_memory_regions_data *data,
                                 target_ulong base, int level, void **lp)
{
    target_ulong pa;
    int i, rc;

    if (*lp == NULL) {
        return walk_memory_regions_end(data, base, 0);
    }

    if (level == 0) {
        PageDesc *pd = *lp;

        for (i = 0; i < V_L2_SIZE; ++i) {
            int prot = pd[i].flags;

            pa = base | (i << TARGET_PAGE_BITS);
            if (prot != data->prot) {
                rc = walk_memory_regions_end(data, pa, prot);
                if (rc != 0) {
                    return rc;
                }
            }
        }
    } else {
        void **pp = *lp;

        for (i = 0; i < V_L2_SIZE; ++i) {
            pa = base | ((target_ulong)i <<
                (TARGET_PAGE_BITS + V_L2_BITS * level));
            rc = walk_memory_regions_1(data, pa, level - 1, pp + i);
            if (rc != 0) {
                return rc;
            }
        }
    }

    return 0;
}

int walk_memory_regions(void *priv, walk_memory_regions_fn fn)
{
    struct walk_memory_regions_data data;
    uintptr_t i, l1_sz = v_l1_size;

    data.fn = fn;
    data.priv = priv;
    data.start = -1u;
    data.prot = 0;

    for (i = 0; i < l1_sz; i++) {
        target_ulong base = i << (v_l1_shift + TARGET_PAGE_BITS);
        int rc = walk_memory_regions_1(&data, base, v_l2_levels, l1_map + i);
        if (rc != 0) {
            return rc;
        }
    }

    return walk_memory_regions_end(&data, 0, 0);
}

static int dump_region(void *priv, target_ulong start,
    target_ulong end, unsigned long prot)
{
    FILE *f = (FILE *)priv;

    (void) fprintf(f, TARGET_FMT_lx"-"TARGET_FMT_lx
        " "TARGET_FMT_lx" %c%c%c\n",
        start, end, end - start,
        ((prot & PAGE_READ) ? 'r' : '-'),
        ((prot & PAGE_WRITE) ? 'w' : '-'),
        ((prot & PAGE_EXEC) ? 'x' : '-'));

    return 0;
}

/* dump memory mappings */
void page_dump(FILE *f)
{
    const int length = sizeof(target_ulong) * 2;
    (void) fprintf(f, "%-*s %-*s %-*s %s\n",
            length, "start", length, "end", length, "size", "prot");
    walk_memory_regions(f, dump_region);
}

int page_get_flags(target_ulong address)
{
    PageDesc *p;

    p = page_find(address >> TARGET_PAGE_BITS);
    if (!p) {
        return 0;
    }
    return p->flags;
}

/* Modify the flags of a page and invalidate the code if necessary.
   The flag PAGE_WRITE_ORG is positioned automatically depending
   on PAGE_WRITE.  The mmap_lock should already be held.  */
void page_set_flags(target_ulong start, target_ulong end, int flags)
{
    target_ulong addr, len;

    /* This function should never be called with addresses outside the
       guest address space.  If this assert fires, it probably indicates
       a missing call to h2g_valid.  */
#if TARGET_ABI_BITS > L1_MAP_ADDR_SPACE_BITS
    assert(end <= ((target_ulong)1 << L1_MAP_ADDR_SPACE_BITS));
#endif
    assert(start < end);
    assert_memory_lock();

    start = start & TARGET_PAGE_MASK;
    end = TARGET_PAGE_ALIGN(end);

    if (flags & PAGE_WRITE) {
        flags |= PAGE_WRITE_ORG;
    }

    for (addr = start, len = end - start;
         len != 0;
         len -= TARGET_PAGE_SIZE, addr += TARGET_PAGE_SIZE) {
        PageDesc *p = page_find_alloc(addr >> TARGET_PAGE_BITS, 1);

        /* If the write protection bit is set, then we invalidate
           the code inside.  */
        if (!(p->flags & PAGE_WRITE) &&
            (flags & PAGE_WRITE) &&
            p->first_tb) {
            tb_invalidate_phys_page(addr, 0);
        }
        p->flags = flags;
    }
}

int page_check_range(target_ulong start, target_ulong len, int flags)
{
    PageDesc *p;
    target_ulong end;
    target_ulong addr;

    /* This function should never be called with addresses outside the
       guest address space.  If this assert fires, it probably indicates
       a missing call to h2g_valid.  */
#if TARGET_ABI_BITS > L1_MAP_ADDR_SPACE_BITS
    assert(start < ((target_ulong)1 << L1_MAP_ADDR_SPACE_BITS));
#endif

    if (len == 0) {
        return 0;
    }
    if (start + len - 1 < start) {
        /* We've wrapped around.  */
        return -1;
    }

    /* must do before we loose bits in the next step */
    end = TARGET_PAGE_ALIGN(start + len);
    start = start & TARGET_PAGE_MASK;

    for (addr = start, len = end - start;
         len != 0;
         len -= TARGET_PAGE_SIZE, addr += TARGET_PAGE_SIZE) {
        p = page_find(addr >> TARGET_PAGE_BITS);
        if (!p) {
            return -1;
        }
        if (!(p->flags & PAGE_VALID)) {
            return -1;
        }

        if ((flags & PAGE_READ) && !(p->flags & PAGE_READ)) {
            return -1;
        }
        if (flags & PAGE_WRITE) {
            if (!(p->flags & PAGE_WRITE_ORG)) {
                return -1;
            }
            /* unprotect the page if it was put read-only because it
               contains translated code */
            if (!(p->flags & PAGE_WRITE)) {
                if (!page_unprotect(addr, 0)) {
                    return -1;
                }
            }
        }
    }
    return 0;
}

/* called from signal handler: invalidate the code and unprotect the
 * page. Return 0 if the fault was not handled, 1 if it was handled,
 * and 2 if it was handled but the caller must cause the TB to be
 * immediately exited. (We can only return 2 if the 'pc' argument is
 * non-zero.)
 */
int page_unprotect(target_ulong address, uintptr_t pc)
{
    unsigned int prot;
    bool current_tb_invalidated;
    PageDesc *p;
    target_ulong host_start, host_end, addr;

    /* Technically this isn't safe inside a signal handler.  However we
       know this only ever happens in a synchronous SEGV handler, so in
       practice it seems to be ok.  */
    mmap_lock();

    p = page_find(address >> TARGET_PAGE_BITS);
    if (!p) {
        mmap_unlock();
        return 0;
    }

    /* if the page was really writable, then we change its
       protection back to writable */
    if ((p->flags & PAGE_WRITE_ORG) && !(p->flags & PAGE_WRITE)) {
        host_start = address & qemu_host_page_mask;
        host_end = host_start + qemu_host_page_size;

        prot = 0;
        current_tb_invalidated = false;
        for (addr = host_start ; addr < host_end ; addr += TARGET_PAGE_SIZE) {
            p = page_find(addr >> TARGET_PAGE_BITS);
            p->flags |= PAGE_WRITE;
            prot |= p->flags;

            /* and since the content will be modified, we must invalidate
               the corresponding translated code. */
            current_tb_invalidated |= tb_invalidate_phys_page(addr, pc);
#ifdef CONFIG_USER_ONLY
            if (DEBUG_TB_CHECK_GATE) {
                tb_invalidate_check(addr);
            }
#endif
        }
        mprotect((void *)g2h(host_start), qemu_host_page_size,
                 prot & PAGE_BITS);

        mmap_unlock();
        /* If current TB was invalidated return to main loop */
        return current_tb_invalidated ? 2 : 1;
    }
    mmap_unlock();
    return 0;
}
#endif /* CONFIG_USER_ONLY */

/* This is a wrapper for common code that can not use CONFIG_SOFTMMU */
void tcg_flush_softmmu_tlb(CPUState *cs)
{
#ifdef CONFIG_SOFTMMU
    tlb_flush(cs);
#endif
}