aboutsummaryrefslogtreecommitdiff
path: root/accel/tcg/cputlb.c
blob: c2b81ec5692e8c414af59fc92d09b25f84c64012 (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
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
/*
 *  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 2.1 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 "hw/core/tcg-cpu-ops.h"
#include "exec/exec-all.h"
#include "exec/memory.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-common.h"
#include "qemu/atomic.h"
#include "qemu/atomic128.h"
#include "exec/translate-all.h"
#include "trace.h"
#include "tb-hash.h"
#include "internal.h"
#ifdef CONFIG_PLUGIN
#include "qemu/plugin-memory.h"
#endif
#include "tcg/tcg-ldst.h"
#include "tcg/oversized-guest.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)

static inline size_t tlb_n_entries(CPUTLBDescFast *fast)
{
    return (fast->mask >> CPU_TLB_ENTRY_BITS) + 1;
}

static inline size_t sizeof_tlb(CPUTLBDescFast *fast)
{
    return fast->mask + (1 << CPU_TLB_ENTRY_BITS);
}

static void tlb_window_reset(CPUTLBDesc *desc, int64_t ns,
                             size_t max_entries)
{
    desc->window_begin_ns = ns;
    desc->window_max_entries = max_entries;
}

static void tb_jmp_cache_clear_page(CPUState *cpu, vaddr page_addr)
{
    CPUJumpCache *jc = cpu->tb_jmp_cache;
    int i, i0;

    if (unlikely(!jc)) {
        return;
    }

    i0 = tb_jmp_cache_hash_page(page_addr);
    for (i = 0; i < TB_JMP_PAGE_SIZE; i++) {
        qatomic_set(&jc->array[i0 + i].tb, NULL);
    }
}

/**
 * tlb_mmu_resize_locked() - perform TLB resize bookkeeping; resize if necessary
 * @desc: The CPUTLBDesc portion of the TLB
 * @fast: The CPUTLBDescFast portion of the same TLB
 *
 * Called with tlb_lock_held.
 *
 * We have two main constraints when resizing a TLB: (1) we only resize it
 * on a TLB flush (otherwise we'd have to take a perf hit by either rehashing
 * the array or unnecessarily flushing it), which means we do not control how
 * frequently the resizing can occur; (2) we don't have access to the guest's
 * future scheduling decisions, and therefore have to decide the magnitude of
 * the resize based on past observations.
 *
 * In general, a memory-hungry process can benefit greatly from an appropriately
 * sized TLB, since a guest TLB miss is very expensive. This doesn't mean that
 * we just have to make the TLB as large as possible; while an oversized TLB
 * results in minimal TLB miss rates, it also takes longer to be flushed
 * (flushes can be _very_ frequent), and the reduced locality can also hurt
 * performance.
 *
 * To achieve near-optimal performance for all kinds of workloads, we:
 *
 * 1. Aggressively increase the size of the TLB when the use rate of the
 * TLB being flushed is high, since it is likely that in the near future this
 * memory-hungry process will execute again, and its memory hungriness will
 * probably be similar.
 *
 * 2. Slowly reduce the size of the TLB as the use rate declines over a
 * reasonably large time window. The rationale is that if in such a time window
 * we have not observed a high TLB use rate, it is likely that we won't observe
 * it in the near future. In that case, once a time window expires we downsize
 * the TLB to match the maximum use rate observed in the window.
 *
 * 3. Try to keep the maximum use rate in a time window in the 30-70% range,
 * since in that range performance is likely near-optimal. Recall that the TLB
 * is direct mapped, so we want the use rate to be low (or at least not too
 * high), since otherwise we are likely to have a significant amount of
 * conflict misses.
 */
static void tlb_mmu_resize_locked(CPUTLBDesc *desc, CPUTLBDescFast *fast,
                                  int64_t now)
{
    size_t old_size = tlb_n_entries(fast);
    size_t rate;
    size_t new_size = old_size;
    int64_t window_len_ms = 100;
    int64_t window_len_ns = window_len_ms * 1000 * 1000;
    bool window_expired = now > desc->window_begin_ns + window_len_ns;

    if (desc->n_used_entries > desc->window_max_entries) {
        desc->window_max_entries = desc->n_used_entries;
    }
    rate = desc->window_max_entries * 100 / old_size;

    if (rate > 70) {
        new_size = MIN(old_size << 1, 1 << CPU_TLB_DYN_MAX_BITS);
    } else if (rate < 30 && window_expired) {
        size_t ceil = pow2ceil(desc->window_max_entries);
        size_t expected_rate = desc->window_max_entries * 100 / ceil;

        /*
         * Avoid undersizing when the max number of entries seen is just below
         * a pow2. For instance, if max_entries == 1025, the expected use rate
         * would be 1025/2048==50%. However, if max_entries == 1023, we'd get
         * 1023/1024==99.9% use rate, so we'd likely end up doubling the size
         * later. Thus, make sure that the expected use rate remains below 70%.
         * (and since we double the size, that means the lowest rate we'd
         * expect to get is 35%, which is still in the 30-70% range where
         * we consider that the size is appropriate.)
         */
        if (expected_rate > 70) {
            ceil *= 2;
        }
        new_size = MAX(ceil, 1 << CPU_TLB_DYN_MIN_BITS);
    }

    if (new_size == old_size) {
        if (window_expired) {
            tlb_window_reset(desc, now, desc->n_used_entries);
        }
        return;
    }

    g_free(fast->table);
    g_free(desc->fulltlb);

    tlb_window_reset(desc, now, 0);
    /* desc->n_used_entries is cleared by the caller */
    fast->mask = (new_size - 1) << CPU_TLB_ENTRY_BITS;
    fast->table = g_try_new(CPUTLBEntry, new_size);
    desc->fulltlb = g_try_new(CPUTLBEntryFull, new_size);

    /*
     * If the allocations fail, try smaller sizes. We just freed some
     * memory, so going back to half of new_size has a good chance of working.
     * Increased memory pressure elsewhere in the system might cause the
     * allocations to fail though, so we progressively reduce the allocation
     * size, aborting if we cannot even allocate the smallest TLB we support.
     */
    while (fast->table == NULL || desc->fulltlb == NULL) {
        if (new_size == (1 << CPU_TLB_DYN_MIN_BITS)) {
            error_report("%s: %s", __func__, strerror(errno));
            abort();
        }
        new_size = MAX(new_size >> 1, 1 << CPU_TLB_DYN_MIN_BITS);
        fast->mask = (new_size - 1) << CPU_TLB_ENTRY_BITS;

        g_free(fast->table);
        g_free(desc->fulltlb);
        fast->table = g_try_new(CPUTLBEntry, new_size);
        desc->fulltlb = g_try_new(CPUTLBEntryFull, new_size);
    }
}

static void tlb_mmu_flush_locked(CPUTLBDesc *desc, CPUTLBDescFast *fast)
{
    desc->n_used_entries = 0;
    desc->large_page_addr = -1;
    desc->large_page_mask = -1;
    desc->vindex = 0;
    memset(fast->table, -1, sizeof_tlb(fast));
    memset(desc->vtable, -1, sizeof(desc->vtable));
}

static void tlb_flush_one_mmuidx_locked(CPUArchState *env, int mmu_idx,
                                        int64_t now)
{
    CPUTLBDesc *desc = &env_tlb(env)->d[mmu_idx];
    CPUTLBDescFast *fast = &env_tlb(env)->f[mmu_idx];

    tlb_mmu_resize_locked(desc, fast, now);
    tlb_mmu_flush_locked(desc, fast);
}

static void tlb_mmu_init(CPUTLBDesc *desc, CPUTLBDescFast *fast, int64_t now)
{
    size_t n_entries = 1 << CPU_TLB_DYN_DEFAULT_BITS;

    tlb_window_reset(desc, now, 0);
    desc->n_used_entries = 0;
    fast->mask = (n_entries - 1) << CPU_TLB_ENTRY_BITS;
    fast->table = g_new(CPUTLBEntry, n_entries);
    desc->fulltlb = g_new(CPUTLBEntryFull, n_entries);
    tlb_mmu_flush_locked(desc, fast);
}

static inline void tlb_n_used_entries_inc(CPUArchState *env, uintptr_t mmu_idx)
{
    env_tlb(env)->d[mmu_idx].n_used_entries++;
}

static inline void tlb_n_used_entries_dec(CPUArchState *env, uintptr_t mmu_idx)
{
    env_tlb(env)->d[mmu_idx].n_used_entries--;
}

void tlb_init(CPUState *cpu)
{
    CPUArchState *env = cpu->env_ptr;
    int64_t now = get_clock_realtime();
    int i;

    qemu_spin_init(&env_tlb(env)->c.lock);

    /* All tlbs are initialized flushed. */
    env_tlb(env)->c.dirty = 0;

    for (i = 0; i < NB_MMU_MODES; i++) {
        tlb_mmu_init(&env_tlb(env)->d[i], &env_tlb(env)->f[i], now);
    }
}

void tlb_destroy(CPUState *cpu)
{
    CPUArchState *env = cpu->env_ptr;
    int i;

    qemu_spin_destroy(&env_tlb(env)->c.lock);
    for (i = 0; i < NB_MMU_MODES; i++) {
        CPUTLBDesc *desc = &env_tlb(env)->d[i];
        CPUTLBDescFast *fast = &env_tlb(env)->f[i];

        g_free(fast->table);
        g_free(desc->fulltlb);
    }
}

/* 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);
        }
    }
}

void tlb_flush_counts(size_t *pfull, size_t *ppart, size_t *pelide)
{
    CPUState *cpu;
    size_t full = 0, part = 0, elide = 0;

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

        full += qatomic_read(&env_tlb(env)->c.full_flush_count);
        part += qatomic_read(&env_tlb(env)->c.part_flush_count);
        elide += qatomic_read(&env_tlb(env)->c.elide_flush_count);
    }
    *pfull = full;
    *ppart = part;
    *pelide = elide;
}

static void tlb_flush_by_mmuidx_async_work(CPUState *cpu, run_on_cpu_data data)
{
    CPUArchState *env = cpu->env_ptr;
    uint16_t asked = data.host_int;
    uint16_t all_dirty, work, to_clean;
    int64_t now = get_clock_realtime();

    assert_cpu_is_self(cpu);

    tlb_debug("mmu_idx:0x%04" PRIx16 "\n", asked);

    qemu_spin_lock(&env_tlb(env)->c.lock);

    all_dirty = env_tlb(env)->c.dirty;
    to_clean = asked & all_dirty;
    all_dirty &= ~to_clean;
    env_tlb(env)->c.dirty = all_dirty;

    for (work = to_clean; work != 0; work &= work - 1) {
        int mmu_idx = ctz32(work);
        tlb_flush_one_mmuidx_locked(env, mmu_idx, now);
    }

    qemu_spin_unlock(&env_tlb(env)->c.lock);

    tcg_flush_jmp_cache(cpu);

    if (to_clean == ALL_MMUIDX_BITS) {
        qatomic_set(&env_tlb(env)->c.full_flush_count,
                   env_tlb(env)->c.full_flush_count + 1);
    } else {
        qatomic_set(&env_tlb(env)->c.part_flush_count,
                   env_tlb(env)->c.part_flush_count + ctpop16(to_clean));
        if (to_clean != asked) {
            qatomic_set(&env_tlb(env)->c.elide_flush_count,
                       env_tlb(env)->c.elide_flush_count +
                       ctpop16(asked & ~to_clean));
        }
    }
}

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

    if (cpu->created && !qemu_cpu_is_self(cpu)) {
        async_run_on_cpu(cpu, tlb_flush_by_mmuidx_async_work,
                         RUN_ON_CPU_HOST_INT(idxmap));
    } else {
        tlb_flush_by_mmuidx_async_work(cpu, RUN_ON_CPU_HOST_INT(idxmap));
    }
}

void tlb_flush(CPUState *cpu)
{
    tlb_flush_by_mmuidx(cpu, ALL_MMUIDX_BITS);
}

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_all_cpus(CPUState *src_cpu)
{
    tlb_flush_by_mmuidx_all_cpus(src_cpu, ALL_MMUIDX_BITS);
}

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));
}

void tlb_flush_all_cpus_synced(CPUState *src_cpu)
{
    tlb_flush_by_mmuidx_all_cpus_synced(src_cpu, ALL_MMUIDX_BITS);
}

static bool tlb_hit_page_mask_anyprot(CPUTLBEntry *tlb_entry,
                                      vaddr page, vaddr mask)
{
    page &= mask;
    mask &= TARGET_PAGE_MASK | TLB_INVALID_MASK;

    return (page == (tlb_entry->addr_read & mask) ||
            page == (tlb_addr_write(tlb_entry) & mask) ||
            page == (tlb_entry->addr_code & mask));
}

static inline bool tlb_hit_page_anyprot(CPUTLBEntry *tlb_entry, vaddr page)
{
    return tlb_hit_page_mask_anyprot(tlb_entry, page, -1);
}

/**
 * tlb_entry_is_empty - return true if the entry is not in use
 * @te: pointer to CPUTLBEntry
 */
static inline bool tlb_entry_is_empty(const CPUTLBEntry *te)
{
    return te->addr_read == -1 && te->addr_write == -1 && te->addr_code == -1;
}

/* Called with tlb_c.lock held */
static bool tlb_flush_entry_mask_locked(CPUTLBEntry *tlb_entry,
                                        vaddr page,
                                        vaddr mask)
{
    if (tlb_hit_page_mask_anyprot(tlb_entry, page, mask)) {
        memset(tlb_entry, -1, sizeof(*tlb_entry));
        return true;
    }
    return false;
}

static inline bool tlb_flush_entry_locked(CPUTLBEntry *tlb_entry, vaddr page)
{
    return tlb_flush_entry_mask_locked(tlb_entry, page, -1);
}

/* Called with tlb_c.lock held */
static void tlb_flush_vtlb_page_mask_locked(CPUArchState *env, int mmu_idx,
                                            vaddr page,
                                            vaddr mask)
{
    CPUTLBDesc *d = &env_tlb(env)->d[mmu_idx];
    int k;

    assert_cpu_is_self(env_cpu(env));
    for (k = 0; k < CPU_VTLB_SIZE; k++) {
        if (tlb_flush_entry_mask_locked(&d->vtable[k], page, mask)) {
            tlb_n_used_entries_dec(env, mmu_idx);
        }
    }
}

static inline void tlb_flush_vtlb_page_locked(CPUArchState *env, int mmu_idx,
                                              vaddr page)
{
    tlb_flush_vtlb_page_mask_locked(env, mmu_idx, page, -1);
}

static void tlb_flush_page_locked(CPUArchState *env, int midx, vaddr page)
{
    vaddr lp_addr = env_tlb(env)->d[midx].large_page_addr;
    vaddr lp_mask = env_tlb(env)->d[midx].large_page_mask;

    /* Check if we need to flush due to large pages.  */
    if ((page & lp_mask) == lp_addr) {
        tlb_debug("forcing full flush midx %d (%"
                  VADDR_PRIx "/%" VADDR_PRIx ")\n",
                  midx, lp_addr, lp_mask);
        tlb_flush_one_mmuidx_locked(env, midx, get_clock_realtime());
    } else {
        if (tlb_flush_entry_locked(tlb_entry(env, midx, page), page)) {
            tlb_n_used_entries_dec(env, midx);
        }
        tlb_flush_vtlb_page_locked(env, midx, page);
    }
}

/**
 * tlb_flush_page_by_mmuidx_async_0:
 * @cpu: cpu on which to flush
 * @addr: page of virtual address to flush
 * @idxmap: set of mmu_idx to flush
 *
 * Helper for tlb_flush_page_by_mmuidx and friends, flush one page
 * at @addr from the tlbs indicated by @idxmap from @cpu.
 */
static void tlb_flush_page_by_mmuidx_async_0(CPUState *cpu,
                                             vaddr addr,
                                             uint16_t idxmap)
{
    CPUArchState *env = cpu->env_ptr;
    int mmu_idx;

    assert_cpu_is_self(cpu);

    tlb_debug("page addr: %" VADDR_PRIx " mmu_map:0x%x\n", addr, idxmap);

    qemu_spin_lock(&env_tlb(env)->c.lock);
    for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
        if ((idxmap >> mmu_idx) & 1) {
            tlb_flush_page_locked(env, mmu_idx, addr);
        }
    }
    qemu_spin_unlock(&env_tlb(env)->c.lock);

    /*
     * Discard jump cache entries for any tb which might potentially
     * overlap the flushed page, which includes the previous.
     */
    tb_jmp_cache_clear_page(cpu, addr - TARGET_PAGE_SIZE);
    tb_jmp_cache_clear_page(cpu, addr);
}

/**
 * tlb_flush_page_by_mmuidx_async_1:
 * @cpu: cpu on which to flush
 * @data: encoded addr + idxmap
 *
 * Helper for tlb_flush_page_by_mmuidx and friends, called through
 * async_run_on_cpu.  The idxmap parameter is encoded in the page
 * offset of the target_ptr field.  This limits the set of mmu_idx
 * that can be passed via this method.
 */
static void tlb_flush_page_by_mmuidx_async_1(CPUState *cpu,
                                             run_on_cpu_data data)
{
    vaddr addr_and_idxmap = data.target_ptr;
    vaddr addr = addr_and_idxmap & TARGET_PAGE_MASK;
    uint16_t idxmap = addr_and_idxmap & ~TARGET_PAGE_MASK;

    tlb_flush_page_by_mmuidx_async_0(cpu, addr, idxmap);
}

typedef struct {
    vaddr addr;
    uint16_t idxmap;
} TLBFlushPageByMMUIdxData;

/**
 * tlb_flush_page_by_mmuidx_async_2:
 * @cpu: cpu on which to flush
 * @data: allocated addr + idxmap
 *
 * Helper for tlb_flush_page_by_mmuidx and friends, called through
 * async_run_on_cpu.  The addr+idxmap parameters are stored in a
 * TLBFlushPageByMMUIdxData structure that has been allocated
 * specifically for this helper.  Free the structure when done.
 */
static void tlb_flush_page_by_mmuidx_async_2(CPUState *cpu,
                                             run_on_cpu_data data)
{
    TLBFlushPageByMMUIdxData *d = data.host_ptr;

    tlb_flush_page_by_mmuidx_async_0(cpu, d->addr, d->idxmap);
    g_free(d);
}

void tlb_flush_page_by_mmuidx(CPUState *cpu, vaddr addr, uint16_t idxmap)
{
    tlb_debug("addr: %" VADDR_PRIx " mmu_idx:%" PRIx16 "\n", addr, idxmap);

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

    if (qemu_cpu_is_self(cpu)) {
        tlb_flush_page_by_mmuidx_async_0(cpu, addr, idxmap);
    } else if (idxmap < TARGET_PAGE_SIZE) {
        /*
         * Most targets have only a few mmu_idx.  In the case where
         * we can stuff idxmap into the low TARGET_PAGE_BITS, avoid
         * allocating memory for this operation.
         */
        async_run_on_cpu(cpu, tlb_flush_page_by_mmuidx_async_1,
                         RUN_ON_CPU_TARGET_PTR(addr | idxmap));
    } else {
        TLBFlushPageByMMUIdxData *d = g_new(TLBFlushPageByMMUIdxData, 1);

        /* Otherwise allocate a structure, freed by the worker.  */
        d->addr = addr;
        d->idxmap = idxmap;
        async_run_on_cpu(cpu, tlb_flush_page_by_mmuidx_async_2,
                         RUN_ON_CPU_HOST_PTR(d));
    }
}

void tlb_flush_page(CPUState *cpu, vaddr addr)
{
    tlb_flush_page_by_mmuidx(cpu, addr, ALL_MMUIDX_BITS);
}

void tlb_flush_page_by_mmuidx_all_cpus(CPUState *src_cpu, vaddr addr,
                                       uint16_t idxmap)
{
    tlb_debug("addr: %" VADDR_PRIx " mmu_idx:%"PRIx16"\n", addr, idxmap);

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

    /*
     * Allocate memory to hold addr+idxmap only when needed.
     * See tlb_flush_page_by_mmuidx for details.
     */
    if (idxmap < TARGET_PAGE_SIZE) {
        flush_all_helper(src_cpu, tlb_flush_page_by_mmuidx_async_1,
                         RUN_ON_CPU_TARGET_PTR(addr | idxmap));
    } else {
        CPUState *dst_cpu;

        /* Allocate a separate data block for each destination cpu.  */
        CPU_FOREACH(dst_cpu) {
            if (dst_cpu != src_cpu) {
                TLBFlushPageByMMUIdxData *d
                    = g_new(TLBFlushPageByMMUIdxData, 1);

                d->addr = addr;
                d->idxmap = idxmap;
                async_run_on_cpu(dst_cpu, tlb_flush_page_by_mmuidx_async_2,
                                 RUN_ON_CPU_HOST_PTR(d));
            }
        }
    }

    tlb_flush_page_by_mmuidx_async_0(src_cpu, addr, idxmap);
}

void tlb_flush_page_all_cpus(CPUState *src, vaddr addr)
{
    tlb_flush_page_by_mmuidx_all_cpus(src, addr, ALL_MMUIDX_BITS);
}

void tlb_flush_page_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
                                              vaddr addr,
                                              uint16_t idxmap)
{
    tlb_debug("addr: %" VADDR_PRIx " mmu_idx:%"PRIx16"\n", addr, idxmap);

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

    /*
     * Allocate memory to hold addr+idxmap only when needed.
     * See tlb_flush_page_by_mmuidx for details.
     */
    if (idxmap < TARGET_PAGE_SIZE) {
        flush_all_helper(src_cpu, tlb_flush_page_by_mmuidx_async_1,
                         RUN_ON_CPU_TARGET_PTR(addr | idxmap));
        async_safe_run_on_cpu(src_cpu, tlb_flush_page_by_mmuidx_async_1,
                              RUN_ON_CPU_TARGET_PTR(addr | idxmap));
    } else {
        CPUState *dst_cpu;
        TLBFlushPageByMMUIdxData *d;

        /* Allocate a separate data block for each destination cpu.  */
        CPU_FOREACH(dst_cpu) {
            if (dst_cpu != src_cpu) {
                d = g_new(TLBFlushPageByMMUIdxData, 1);
                d->addr = addr;
                d->idxmap = idxmap;
                async_run_on_cpu(dst_cpu, tlb_flush_page_by_mmuidx_async_2,
                                 RUN_ON_CPU_HOST_PTR(d));
            }
        }

        d = g_new(TLBFlushPageByMMUIdxData, 1);
        d->addr = addr;
        d->idxmap = idxmap;
        async_safe_run_on_cpu(src_cpu, tlb_flush_page_by_mmuidx_async_2,
                              RUN_ON_CPU_HOST_PTR(d));
    }
}

void tlb_flush_page_all_cpus_synced(CPUState *src, vaddr addr)
{
    tlb_flush_page_by_mmuidx_all_cpus_synced(src, addr, ALL_MMUIDX_BITS);
}

static void tlb_flush_range_locked(CPUArchState *env, int midx,
                                   vaddr addr, vaddr len,
                                   unsigned bits)
{
    CPUTLBDesc *d = &env_tlb(env)->d[midx];
    CPUTLBDescFast *f = &env_tlb(env)->f[midx];
    vaddr mask = MAKE_64BIT_MASK(0, bits);

    /*
     * If @bits is smaller than the tlb size, there may be multiple entries
     * within the TLB; otherwise all addresses that match under @mask hit
     * the same TLB entry.
     * TODO: Perhaps allow bits to be a few bits less than the size.
     * For now, just flush the entire TLB.
     *
     * If @len is larger than the tlb size, then it will take longer to
     * test all of the entries in the TLB than it will to flush it all.
     */
    if (mask < f->mask || len > f->mask) {
        tlb_debug("forcing full flush midx %d ("
                  "%" VADDR_PRIx "/%" VADDR_PRIx "+%" VADDR_PRIx ")\n",
                  midx, addr, mask, len);
        tlb_flush_one_mmuidx_locked(env, midx, get_clock_realtime());
        return;
    }

    /*
     * Check if we need to flush due to large pages.
     * Because large_page_mask contains all 1's from the msb,
     * we only need to test the end of the range.
     */
    if (((addr + len - 1) & d->large_page_mask) == d->large_page_addr) {
        tlb_debug("forcing full flush midx %d ("
                  "%" VADDR_PRIx "/%" VADDR_PRIx ")\n",
                  midx, d->large_page_addr, d->large_page_mask);
        tlb_flush_one_mmuidx_locked(env, midx, get_clock_realtime());
        return;
    }

    for (vaddr i = 0; i < len; i += TARGET_PAGE_SIZE) {
        vaddr page = addr + i;
        CPUTLBEntry *entry = tlb_entry(env, midx, page);

        if (tlb_flush_entry_mask_locked(entry, page, mask)) {
            tlb_n_used_entries_dec(env, midx);
        }
        tlb_flush_vtlb_page_mask_locked(env, midx, page, mask);
    }
}

typedef struct {
    vaddr addr;
    vaddr len;
    uint16_t idxmap;
    uint16_t bits;
} TLBFlushRangeData;

static void tlb_flush_range_by_mmuidx_async_0(CPUState *cpu,
                                              TLBFlushRangeData d)
{
    CPUArchState *env = cpu->env_ptr;
    int mmu_idx;

    assert_cpu_is_self(cpu);

    tlb_debug("range: %" VADDR_PRIx "/%u+%" VADDR_PRIx " mmu_map:0x%x\n",
              d.addr, d.bits, d.len, d.idxmap);

    qemu_spin_lock(&env_tlb(env)->c.lock);
    for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
        if ((d.idxmap >> mmu_idx) & 1) {
            tlb_flush_range_locked(env, mmu_idx, d.addr, d.len, d.bits);
        }
    }
    qemu_spin_unlock(&env_tlb(env)->c.lock);

    /*
     * If the length is larger than the jump cache size, then it will take
     * longer to clear each entry individually than it will to clear it all.
     */
    if (d.len >= (TARGET_PAGE_SIZE * TB_JMP_CACHE_SIZE)) {
        tcg_flush_jmp_cache(cpu);
        return;
    }

    /*
     * Discard jump cache entries for any tb which might potentially
     * overlap the flushed pages, which includes the previous.
     */
    d.addr -= TARGET_PAGE_SIZE;
    for (vaddr i = 0, n = d.len / TARGET_PAGE_SIZE + 1; i < n; i++) {
        tb_jmp_cache_clear_page(cpu, d.addr);
        d.addr += TARGET_PAGE_SIZE;
    }
}

static void tlb_flush_range_by_mmuidx_async_1(CPUState *cpu,
                                              run_on_cpu_data data)
{
    TLBFlushRangeData *d = data.host_ptr;
    tlb_flush_range_by_mmuidx_async_0(cpu, *d);
    g_free(d);
}

void tlb_flush_range_by_mmuidx(CPUState *cpu, vaddr addr,
                               vaddr len, uint16_t idxmap,
                               unsigned bits)
{
    TLBFlushRangeData d;

    /*
     * If all bits are significant, and len is small,
     * this devolves to tlb_flush_page.
     */
    if (bits >= TARGET_LONG_BITS && len <= TARGET_PAGE_SIZE) {
        tlb_flush_page_by_mmuidx(cpu, addr, idxmap);
        return;
    }
    /* If no page bits are significant, this devolves to tlb_flush. */
    if (bits < TARGET_PAGE_BITS) {
        tlb_flush_by_mmuidx(cpu, idxmap);
        return;
    }

    /* This should already be page aligned */
    d.addr = addr & TARGET_PAGE_MASK;
    d.len = len;
    d.idxmap = idxmap;
    d.bits = bits;

    if (qemu_cpu_is_self(cpu)) {
        tlb_flush_range_by_mmuidx_async_0(cpu, d);
    } else {
        /* Otherwise allocate a structure, freed by the worker.  */
        TLBFlushRangeData *p = g_memdup(&d, sizeof(d));
        async_run_on_cpu(cpu, tlb_flush_range_by_mmuidx_async_1,
                         RUN_ON_CPU_HOST_PTR(p));
    }
}

void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, vaddr addr,
                                   uint16_t idxmap, unsigned bits)
{
    tlb_flush_range_by_mmuidx(cpu, addr, TARGET_PAGE_SIZE, idxmap, bits);
}

void tlb_flush_range_by_mmuidx_all_cpus(CPUState *src_cpu,
                                        vaddr addr, vaddr len,
                                        uint16_t idxmap, unsigned bits)
{
    TLBFlushRangeData d;
    CPUState *dst_cpu;

    /*
     * If all bits are significant, and len is small,
     * this devolves to tlb_flush_page.
     */
    if (bits >= TARGET_LONG_BITS && len <= TARGET_PAGE_SIZE) {
        tlb_flush_page_by_mmuidx_all_cpus(src_cpu, addr, idxmap);
        return;
    }
    /* If no page bits are significant, this devolves to tlb_flush. */
    if (bits < TARGET_PAGE_BITS) {
        tlb_flush_by_mmuidx_all_cpus(src_cpu, idxmap);
        return;
    }

    /* This should already be page aligned */
    d.addr = addr & TARGET_PAGE_MASK;
    d.len = len;
    d.idxmap = idxmap;
    d.bits = bits;

    /* Allocate a separate data block for each destination cpu.  */
    CPU_FOREACH(dst_cpu) {
        if (dst_cpu != src_cpu) {
            TLBFlushRangeData *p = g_memdup(&d, sizeof(d));
            async_run_on_cpu(dst_cpu,
                             tlb_flush_range_by_mmuidx_async_1,
                             RUN_ON_CPU_HOST_PTR(p));
        }
    }

    tlb_flush_range_by_mmuidx_async_0(src_cpu, d);
}

void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu,
                                            vaddr addr, uint16_t idxmap,
                                            unsigned bits)
{
    tlb_flush_range_by_mmuidx_all_cpus(src_cpu, addr, TARGET_PAGE_SIZE,
                                       idxmap, bits);
}

void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
                                               vaddr addr,
                                               vaddr len,
                                               uint16_t idxmap,
                                               unsigned bits)
{
    TLBFlushRangeData d, *p;
    CPUState *dst_cpu;

    /*
     * If all bits are significant, and len is small,
     * this devolves to tlb_flush_page.
     */
    if (bits >= TARGET_LONG_BITS && len <= TARGET_PAGE_SIZE) {
        tlb_flush_page_by_mmuidx_all_cpus_synced(src_cpu, addr, idxmap);
        return;
    }
    /* If no page bits are significant, this devolves to tlb_flush. */
    if (bits < TARGET_PAGE_BITS) {
        tlb_flush_by_mmuidx_all_cpus_synced(src_cpu, idxmap);
        return;
    }

    /* This should already be page aligned */
    d.addr = addr & TARGET_PAGE_MASK;
    d.len = len;
    d.idxmap = idxmap;
    d.bits = bits;

    /* Allocate a separate data block for each destination cpu.  */
    CPU_FOREACH(dst_cpu) {
        if (dst_cpu != src_cpu) {
            p = g_memdup(&d, sizeof(d));
            async_run_on_cpu(dst_cpu, tlb_flush_range_by_mmuidx_async_1,
                             RUN_ON_CPU_HOST_PTR(p));
        }
    }

    p = g_memdup(&d, sizeof(d));
    async_safe_run_on_cpu(src_cpu, tlb_flush_range_by_mmuidx_async_1,
                          RUN_ON_CPU_HOST_PTR(p));
}

void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
                                                   vaddr addr,
                                                   uint16_t idxmap,
                                                   unsigned bits)
{
    tlb_flush_range_by_mmuidx_all_cpus_synced(src_cpu, addr, TARGET_PAGE_SIZE,
                                              idxmap, bits);
}

/* 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_MASK,
                                             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 qatomic_set. We don't need to worry about this for
 * oversized guests as MTTCG is disabled for them.
 *
 * Called with tlb_c.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_DISCARD_WRITE | TLB_NOTDIRTY)) == 0) {
        addr &= TARGET_PAGE_MASK;
        addr += tlb_entry->addend;
        if ((addr - start) < length) {
#if TARGET_LONG_BITS == 32
            uint32_t *ptr_write = (uint32_t *)&tlb_entry->addr_write;
            ptr_write += HOST_BIG_ENDIAN;
            qatomic_set(ptr_write, *ptr_write | TLB_NOTDIRTY);
#elif TCG_OVERSIZED_GUEST
            tlb_entry->addr_write |= TLB_NOTDIRTY;
#else
            qatomic_set(&tlb_entry->addr_write,
                        tlb_entry->addr_write | TLB_NOTDIRTY);
#endif
        }
    }
}

/*
 * Called with tlb_c.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_c.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(env)->c.lock);
    for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
        unsigned int i;
        unsigned int n = tlb_n_entries(&env_tlb(env)->f[mmu_idx]);

        for (i = 0; i < n; i++) {
            tlb_reset_dirty_range_locked(&env_tlb(env)->f[mmu_idx].table[i],
                                         start1, length);
        }

        for (i = 0; i < CPU_VTLB_SIZE; i++) {
            tlb_reset_dirty_range_locked(&env_tlb(env)->d[mmu_idx].vtable[i],
                                         start1, length);
        }
    }
    qemu_spin_unlock(&env_tlb(env)->c.lock);
}

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

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

    assert_cpu_is_self(cpu);

    addr &= TARGET_PAGE_MASK;
    qemu_spin_lock(&env_tlb(env)->c.lock);
    for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
        tlb_set_dirty1_locked(tlb_entry(env, mmu_idx, addr), addr);
    }

    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(env)->d[mmu_idx].vtable[k], addr);
        }
    }
    qemu_spin_unlock(&env_tlb(env)->c.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, int mmu_idx,
                               vaddr addr, uint64_t size)
{
    vaddr lp_addr = env_tlb(env)->d[mmu_idx].large_page_addr;
    vaddr lp_mask = ~(size - 1);

    if (lp_addr == (vaddr)-1) {
        /* No previous large page.  */
        lp_addr = addr;
    } else {
        /* 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.  */
        lp_mask &= env_tlb(env)->d[mmu_idx].large_page_mask;
        while (((lp_addr ^ addr) & lp_mask) != 0) {
            lp_mask <<= 1;
        }
    }
    env_tlb(env)->d[mmu_idx].large_page_addr = lp_addr & lp_mask;
    env_tlb(env)->d[mmu_idx].large_page_mask = lp_mask;
}

static inline void tlb_set_compare(CPUTLBEntryFull *full, CPUTLBEntry *ent,
                                   target_ulong address, int flags,
                                   MMUAccessType access_type, bool enable)
{
    if (enable) {
        address |= flags & TLB_FLAGS_MASK;
        flags &= TLB_SLOW_FLAGS_MASK;
        if (flags) {
            address |= TLB_FORCE_SLOW;
        }
    } else {
        address = -1;
        flags = 0;
    }
    ent->addr_idx[access_type] = address;
    full->slow_flags[access_type] = flags;
}

/*
 * 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_full(CPUState *cpu, int mmu_idx,
                       vaddr addr, CPUTLBEntryFull *full)
{
    CPUArchState *env = cpu->env_ptr;
    CPUTLB *tlb = env_tlb(env);
    CPUTLBDesc *desc = &tlb->d[mmu_idx];
    MemoryRegionSection *section;
    unsigned int index, read_flags, write_flags;
    uintptr_t addend;
    CPUTLBEntry *te, tn;
    hwaddr iotlb, xlat, sz, paddr_page;
    vaddr addr_page;
    int asidx, wp_flags, prot;
    bool is_ram, is_romd;

    assert_cpu_is_self(cpu);

    if (full->lg_page_size <= TARGET_PAGE_BITS) {
        sz = TARGET_PAGE_SIZE;
    } else {
        sz = (hwaddr)1 << full->lg_page_size;
        tlb_add_large_page(env, mmu_idx, addr, sz);
    }
    addr_page = addr & TARGET_PAGE_MASK;
    paddr_page = full->phys_addr & TARGET_PAGE_MASK;

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

    tlb_debug("vaddr=%" VADDR_PRIx " paddr=0x" HWADDR_FMT_plx
              " prot=%x idx=%d\n",
              addr, full->phys_addr, prot, mmu_idx);

    read_flags = 0;
    if (full->lg_page_size < TARGET_PAGE_BITS) {
        /* Repeat the MMU check and TLB fill on every access.  */
        read_flags |= TLB_INVALID_MASK;
    }
    if (full->attrs.byte_swap) {
        read_flags |= TLB_BSWAP;
    }

    is_ram = memory_region_is_ram(section->mr);
    is_romd = memory_region_is_romd(section->mr);

    if (is_ram || is_romd) {
        /* RAM and ROMD both have associated host memory. */
        addend = (uintptr_t)memory_region_get_ram_ptr(section->mr) + xlat;
    } else {
        /* I/O does not; force the host address to NULL. */
        addend = 0;
    }

    write_flags = read_flags;
    if (is_ram) {
        iotlb = memory_region_get_ram_addr(section->mr) + xlat;
        /*
         * Computing is_clean is expensive; avoid all that unless
         * the page is actually writable.
         */
        if (prot & PAGE_WRITE) {
            if (section->readonly) {
                write_flags |= TLB_DISCARD_WRITE;
            } else if (cpu_physical_memory_is_clean(iotlb)) {
                write_flags |= TLB_NOTDIRTY;
            }
        }
    } else {
        /* I/O or ROMD */
        iotlb = memory_region_section_get_iotlb(cpu, section) + xlat;
        /*
         * Writes to romd devices must go through MMIO to enable write.
         * Reads to romd devices go through the ram_ptr found above,
         * but of course reads to I/O must go through MMIO.
         */
        write_flags |= TLB_MMIO;
        if (!is_romd) {
            read_flags = write_flags;
        }
    }

    wp_flags = cpu_watchpoint_address_matches(cpu, addr_page,
                                              TARGET_PAGE_SIZE);

    index = tlb_index(env, mmu_idx, addr_page);
    te = tlb_entry(env, mmu_idx, addr_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(&tlb->c.lock);

    /* Note that the tlb is no longer clean.  */
    tlb->c.dirty |= 1 << mmu_idx;

    /* Make sure there's no cached translation for the new page.  */
    tlb_flush_vtlb_page_locked(env, mmu_idx, addr_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, addr_page) && !tlb_entry_is_empty(te)) {
        unsigned vidx = desc->vindex++ % CPU_VTLB_SIZE;
        CPUTLBEntry *tv = &desc->vtable[vidx];

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

    /* 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 (RAM)
     *  + the offset within section->mr of the page base (I/O, ROMD)
     * We subtract addr_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().
     */
    desc->fulltlb[index] = *full;
    full = &desc->fulltlb[index];
    full->xlat_section = iotlb - addr_page;
    full->phys_addr = paddr_page;

    /* Now calculate the new entry */
    tn.addend = addend - addr_page;

    tlb_set_compare(full, &tn, addr_page, read_flags,
                    MMU_INST_FETCH, prot & PAGE_EXEC);

    if (wp_flags & BP_MEM_READ) {
        read_flags |= TLB_WATCHPOINT;
    }
    tlb_set_compare(full, &tn, addr_page, read_flags,
                    MMU_DATA_LOAD, prot & PAGE_READ);

    if (prot & PAGE_WRITE_INV) {
        write_flags |= TLB_INVALID_MASK;
    }
    if (wp_flags & BP_MEM_WRITE) {
        write_flags |= TLB_WATCHPOINT;
    }
    tlb_set_compare(full, &tn, addr_page, write_flags,
                    MMU_DATA_STORE, prot & PAGE_WRITE);

    copy_tlb_helper_locked(te, &tn);
    tlb_n_used_entries_inc(env, mmu_idx);
    qemu_spin_unlock(&tlb->c.lock);
}

void tlb_set_page_with_attrs(CPUState *cpu, vaddr addr,
                             hwaddr paddr, MemTxAttrs attrs, int prot,
                             int mmu_idx, uint64_t size)
{
    CPUTLBEntryFull full = {
        .phys_addr = paddr,
        .attrs = attrs,
        .prot = prot,
        .lg_page_size = ctz64(size)
    };

    assert(is_power_of_2(size));
    tlb_set_page_full(cpu, mmu_idx, addr, &full);
}

void tlb_set_page(CPUState *cpu, vaddr addr,
                  hwaddr paddr, int prot,
                  int mmu_idx, uint64_t size)
{
    tlb_set_page_with_attrs(cpu, addr, paddr, MEMTXATTRS_UNSPECIFIED,
                            prot, mmu_idx, size);
}

/*
 * Note: tlb_fill() can trigger a resize of the TLB. This means that all of the
 * caller's prior references to the TLB table (e.g. CPUTLBEntry pointers) must
 * be discarded and looked up again (e.g. via tlb_entry()).
 */
static void tlb_fill(CPUState *cpu, vaddr addr, int size,
                     MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
{
    bool ok;

    /*
     * This is not a probe, so only valid return is success; failure
     * should result in exception + longjmp to the cpu loop.
     */
    ok = cpu->cc->tcg_ops->tlb_fill(cpu, addr, size,
                                    access_type, mmu_idx, false, retaddr);
    assert(ok);
}

static inline void cpu_unaligned_access(CPUState *cpu, vaddr addr,
                                        MMUAccessType access_type,
                                        int mmu_idx, uintptr_t retaddr)
{
    cpu->cc->tcg_ops->do_unaligned_access(cpu, addr, access_type,
                                          mmu_idx, retaddr);
}

static inline void cpu_transaction_failed(CPUState *cpu, hwaddr physaddr,
                                          vaddr addr, unsigned size,
                                          MMUAccessType access_type,
                                          int mmu_idx, MemTxAttrs attrs,
                                          MemTxResult response,
                                          uintptr_t retaddr)
{
    CPUClass *cc = CPU_GET_CLASS(cpu);

    if (!cpu->ignore_memory_transaction_failures &&
        cc->tcg_ops->do_transaction_failed) {
        cc->tcg_ops->do_transaction_failed(cpu, physaddr, addr, size,
                                           access_type, mmu_idx, attrs,
                                           response, retaddr);
    }
}

static uint64_t io_readx(CPUArchState *env, CPUTLBEntryFull *full,
                         int mmu_idx, vaddr addr, uintptr_t retaddr,
                         MMUAccessType access_type, MemOp op)
{
    CPUState *cpu = env_cpu(env);
    hwaddr mr_offset;
    MemoryRegionSection *section;
    MemoryRegion *mr;
    uint64_t val;
    MemTxResult r;

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

    {
        QEMU_IOTHREAD_LOCK_GUARD();
        r = memory_region_dispatch_read(mr, mr_offset, &val, op, full->attrs);
    }

    if (r != MEMTX_OK) {
        hwaddr physaddr = mr_offset +
            section->offset_within_address_space -
            section->offset_within_region;

        cpu_transaction_failed(cpu, physaddr, addr, memop_size(op), access_type,
                               mmu_idx, full->attrs, r, retaddr);
    }
    return val;
}

/*
 * Save a potentially trashed CPUTLBEntryFull for later lookup by plugin.
 * This is read by tlb_plugin_lookup if the fulltlb entry doesn't match
 * because of the side effect of io_writex changing memory layout.
 */
static void save_iotlb_data(CPUState *cs, MemoryRegionSection *section,
                            hwaddr mr_offset)
{
#ifdef CONFIG_PLUGIN
    SavedIOTLB *saved = &cs->saved_iotlb;
    saved->section = section;
    saved->mr_offset = mr_offset;
#endif
}

static void io_writex(CPUArchState *env, CPUTLBEntryFull *full,
                      int mmu_idx, uint64_t val, vaddr addr,
                      uintptr_t retaddr, MemOp op)
{
    CPUState *cpu = env_cpu(env);
    hwaddr mr_offset;
    MemoryRegionSection *section;
    MemoryRegion *mr;
    MemTxResult r;

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

    /*
     * The memory_region_dispatch may trigger a flush/resize
     * so for plugins we save the iotlb_data just in case.
     */
    save_iotlb_data(cpu, section, mr_offset);

    {
        QEMU_IOTHREAD_LOCK_GUARD();
        r = memory_region_dispatch_write(mr, mr_offset, val, op, full->attrs);
    }

    if (r != MEMTX_OK) {
        hwaddr physaddr = mr_offset +
            section->offset_within_address_space -
            section->offset_within_region;

        cpu_transaction_failed(cpu, physaddr, addr, memop_size(op),
                               MMU_DATA_STORE, mmu_idx, full->attrs, r,
                               retaddr);
    }
}

/* 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,
                           MMUAccessType access_type, vaddr page)
{
    size_t vidx;

    assert_cpu_is_self(env_cpu(env));
    for (vidx = 0; vidx < CPU_VTLB_SIZE; ++vidx) {
        CPUTLBEntry *vtlb = &env_tlb(env)->d[mmu_idx].vtable[vidx];
        uint64_t cmp = tlb_read_idx(vtlb, access_type);

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

            qemu_spin_lock(&env_tlb(env)->c.lock);
            copy_tlb_helper_locked(&tmptlb, tlb);
            copy_tlb_helper_locked(tlb, vtlb);
            copy_tlb_helper_locked(vtlb, &tmptlb);
            qemu_spin_unlock(&env_tlb(env)->c.lock);

            CPUTLBEntryFull *f1 = &env_tlb(env)->d[mmu_idx].fulltlb[index];
            CPUTLBEntryFull *f2 = &env_tlb(env)->d[mmu_idx].vfulltlb[vidx];
            CPUTLBEntryFull tmpf;
            tmpf = *f1; *f1 = *f2; *f2 = tmpf;
            return true;
        }
    }
    return false;
}

static void notdirty_write(CPUState *cpu, vaddr mem_vaddr, unsigned size,
                           CPUTLBEntryFull *full, uintptr_t retaddr)
{
    ram_addr_t ram_addr = mem_vaddr + full->xlat_section;

    trace_memory_notdirty_write_access(mem_vaddr, ram_addr, size);

    if (!cpu_physical_memory_get_dirty_flag(ram_addr, DIRTY_MEMORY_CODE)) {
        tb_invalidate_phys_range_fast(ram_addr, size, retaddr);
    }

    /*
     * Set both VGA and migration bits for simplicity and to remove
     * the notdirty callback faster.
     */
    cpu_physical_memory_set_dirty_range(ram_addr, size, DIRTY_CLIENTS_NOCODE);

    /* We remove the notdirty callback only if the code has been flushed. */
    if (!cpu_physical_memory_is_clean(ram_addr)) {
        trace_memory_notdirty_set_dirty(mem_vaddr);
        tlb_set_dirty(cpu, mem_vaddr);
    }
}

static int probe_access_internal(CPUArchState *env, vaddr addr,
                                 int fault_size, MMUAccessType access_type,
                                 int mmu_idx, bool nonfault,
                                 void **phost, CPUTLBEntryFull **pfull,
                                 uintptr_t retaddr, bool check_mem_cbs)
{
    uintptr_t index = tlb_index(env, mmu_idx, addr);
    CPUTLBEntry *entry = tlb_entry(env, mmu_idx, addr);
    uint64_t tlb_addr = tlb_read_idx(entry, access_type);
    vaddr page_addr = addr & TARGET_PAGE_MASK;
    int flags = TLB_FLAGS_MASK & ~TLB_FORCE_SLOW;
    bool force_mmio = check_mem_cbs && cpu_plugin_mem_cbs_enabled(env_cpu(env));
    CPUTLBEntryFull *full;

    if (!tlb_hit_page(tlb_addr, page_addr)) {
        if (!victim_tlb_hit(env, mmu_idx, index, access_type, page_addr)) {
            CPUState *cs = env_cpu(env);

            if (!cs->cc->tcg_ops->tlb_fill(cs, addr, fault_size, access_type,
                                           mmu_idx, nonfault, retaddr)) {
                /* Non-faulting page table read failed.  */
                *phost = NULL;
                *pfull = NULL;
                return TLB_INVALID_MASK;
            }

            /* TLB resize via tlb_fill may have moved the entry.  */
            index = tlb_index(env, mmu_idx, addr);
            entry = tlb_entry(env, mmu_idx, addr);

            /*
             * With PAGE_WRITE_INV, we set TLB_INVALID_MASK immediately,
             * to force the next access through tlb_fill.  We've just
             * called tlb_fill, so we know that this entry *is* valid.
             */
            flags &= ~TLB_INVALID_MASK;
        }
        tlb_addr = tlb_read_idx(entry, access_type);
    }
    flags &= tlb_addr;

    *pfull = full = &env_tlb(env)->d[mmu_idx].fulltlb[index];
    flags |= full->slow_flags[access_type];

    /* Fold all "mmio-like" bits into TLB_MMIO.  This is not RAM.  */
    if (unlikely(flags & ~(TLB_WATCHPOINT | TLB_NOTDIRTY))
        ||
        (access_type != MMU_INST_FETCH && force_mmio)) {
        *phost = NULL;
        return TLB_MMIO;
    }

    /* Everything else is RAM. */
    *phost = (void *)((uintptr_t)addr + entry->addend);
    return flags;
}

int probe_access_full(CPUArchState *env, vaddr addr, int size,
                      MMUAccessType access_type, int mmu_idx,
                      bool nonfault, void **phost, CPUTLBEntryFull **pfull,
                      uintptr_t retaddr)
{
    int flags = probe_access_internal(env, addr, size, access_type, mmu_idx,
                                      nonfault, phost, pfull, retaddr, true);

    /* Handle clean RAM pages.  */
    if (unlikely(flags & TLB_NOTDIRTY)) {
        notdirty_write(env_cpu(env), addr, 1, *pfull, retaddr);
        flags &= ~TLB_NOTDIRTY;
    }

    return flags;
}

int probe_access_full_mmu(CPUArchState *env, vaddr addr, int size,
                          MMUAccessType access_type, int mmu_idx,
                          void **phost, CPUTLBEntryFull **pfull)
{
    void *discard_phost;
    CPUTLBEntryFull *discard_tlb;

    /* privately handle users that don't need full results */
    phost = phost ? phost : &discard_phost;
    pfull = pfull ? pfull : &discard_tlb;

    int flags = probe_access_internal(env, addr, size, access_type, mmu_idx,
                                      true, phost, pfull, 0, false);

    /* Handle clean RAM pages.  */
    if (unlikely(flags & TLB_NOTDIRTY)) {
        notdirty_write(env_cpu(env), addr, 1, *pfull, 0);
        flags &= ~TLB_NOTDIRTY;
    }

    return flags;
}

int probe_access_flags(CPUArchState *env, vaddr addr, int size,
                       MMUAccessType access_type, int mmu_idx,
                       bool nonfault, void **phost, uintptr_t retaddr)
{
    CPUTLBEntryFull *full;
    int flags;

    g_assert(-(addr | TARGET_PAGE_MASK) >= size);

    flags = probe_access_internal(env, addr, size, access_type, mmu_idx,
                                  nonfault, phost, &full, retaddr, true);

    /* Handle clean RAM pages. */
    if (unlikely(flags & TLB_NOTDIRTY)) {
        notdirty_write(env_cpu(env), addr, 1, full, retaddr);
        flags &= ~TLB_NOTDIRTY;
    }

    return flags;
}

void *probe_access(CPUArchState *env, vaddr addr, int size,
                   MMUAccessType access_type, int mmu_idx, uintptr_t retaddr)
{
    CPUTLBEntryFull *full;
    void *host;
    int flags;

    g_assert(-(addr | TARGET_PAGE_MASK) >= size);

    flags = probe_access_internal(env, addr, size, access_type, mmu_idx,
                                  false, &host, &full, retaddr, true);

    /* Per the interface, size == 0 merely faults the access. */
    if (size == 0) {
        return NULL;
    }

    if (unlikely(flags & (TLB_NOTDIRTY | TLB_WATCHPOINT))) {
        /* Handle watchpoints.  */
        if (flags & TLB_WATCHPOINT) {
            int wp_access = (access_type == MMU_DATA_STORE
                             ? BP_MEM_WRITE : BP_MEM_READ);
            cpu_check_watchpoint(env_cpu(env), addr, size,
                                 full->attrs, wp_access, retaddr);
        }

        /* Handle clean RAM pages.  */
        if (flags & TLB_NOTDIRTY) {
            notdirty_write(env_cpu(env), addr, 1, full, retaddr);
        }
    }

    return host;
}

void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr,
                        MMUAccessType access_type, int mmu_idx)
{
    CPUTLBEntryFull *full;
    void *host;
    int flags;

    flags = probe_access_internal(env, addr, 0, access_type,
                                  mmu_idx, true, &host, &full, 0, false);

    /* No combination of flags are expected by the caller. */
    return flags ? NULL : host;
}

/*
 * Return a ram_addr_t for the virtual address for execution.
 *
 * Return -1 if we can't translate and execute from an entire page
 * of RAM.  This will force us to execute by loading and translating
 * one insn at a time, without caching.
 *
 * NOTE: This function will trigger an exception if the page is
 * not executable.
 */
tb_page_addr_t get_page_addr_code_hostp(CPUArchState *env, vaddr addr,
                                        void **hostp)
{
    CPUTLBEntryFull *full;
    void *p;

    (void)probe_access_internal(env, addr, 1, MMU_INST_FETCH,
                                cpu_mmu_index(env, true), false,
                                &p, &full, 0, false);
    if (p == NULL) {
        return -1;
    }

    if (full->lg_page_size < TARGET_PAGE_BITS) {
        return -1;
    }

    if (hostp) {
        *hostp = p;
    }
    return qemu_ram_addr_from_host_nofail(p);
}

/* Load/store with atomicity primitives. */
#include "ldst_atomicity.c.inc"

#ifdef CONFIG_PLUGIN
/*
 * Perform a TLB lookup and populate the qemu_plugin_hwaddr structure.
 * This should be a hot path as we will have just looked this path up
 * in the softmmu lookup code (or helper). We don't handle re-fills or
 * checking the victim table. This is purely informational.
 *
 * This almost never fails as the memory access being instrumented
 * should have just filled the TLB. The one corner case is io_writex
 * which can cause TLB flushes and potential resizing of the TLBs
 * losing the information we need. In those cases we need to recover
 * data from a copy of the CPUTLBEntryFull. As long as this always occurs
 * from the same thread (which a mem callback will be) this is safe.
 */

bool tlb_plugin_lookup(CPUState *cpu, vaddr addr, int mmu_idx,
                       bool is_store, struct qemu_plugin_hwaddr *data)
{
    CPUArchState *env = cpu->env_ptr;
    CPUTLBEntry *tlbe = tlb_entry(env, mmu_idx, addr);
    uintptr_t index = tlb_index(env, mmu_idx, addr);
    uint64_t tlb_addr = is_store ? tlb_addr_write(tlbe) : tlbe->addr_read;

    if (likely(tlb_hit(tlb_addr, addr))) {
        /* We must have an iotlb entry for MMIO */
        if (tlb_addr & TLB_MMIO) {
            CPUTLBEntryFull *full;
            full = &env_tlb(env)->d[mmu_idx].fulltlb[index];
            data->is_io = true;
            data->v.io.section =
                iotlb_to_section(cpu, full->xlat_section, full->attrs);
            data->v.io.offset = (full->xlat_section & TARGET_PAGE_MASK) + addr;
        } else {
            data->is_io = false;
            data->v.ram.hostaddr = (void *)((uintptr_t)addr + tlbe->addend);
        }
        return true;
    } else {
        SavedIOTLB *saved = &cpu->saved_iotlb;
        data->is_io = true;
        data->v.io.section = saved->section;
        data->v.io.offset = saved->mr_offset;
        return true;
    }
}

#endif

/*
 * Probe for a load/store operation.
 * Return the host address and into @flags.
 */

typedef struct MMULookupPageData {
    CPUTLBEntryFull *full;
    void *haddr;
    vaddr addr;
    int flags;
    int size;
} MMULookupPageData;

typedef struct MMULookupLocals {
    MMULookupPageData page[2];
    MemOp memop;
    int mmu_idx;
} MMULookupLocals;

/**
 * mmu_lookup1: translate one page
 * @env: cpu context
 * @data: lookup parameters
 * @mmu_idx: virtual address context
 * @access_type: load/store/code
 * @ra: return address into tcg generated code, or 0
 *
 * Resolve the translation for the one page at @data.addr, filling in
 * the rest of @data with the results.  If the translation fails,
 * tlb_fill will longjmp out.  Return true if the softmmu tlb for
 * @mmu_idx may have resized.
 */
static bool mmu_lookup1(CPUArchState *env, MMULookupPageData *data,
                        int mmu_idx, MMUAccessType access_type, uintptr_t ra)
{
    vaddr addr = data->addr;
    uintptr_t index = tlb_index(env, mmu_idx, addr);
    CPUTLBEntry *entry = tlb_entry(env, mmu_idx, addr);
    uint64_t tlb_addr = tlb_read_idx(entry, access_type);
    bool maybe_resized = false;
    CPUTLBEntryFull *full;
    int flags;

    /* If the TLB entry is for a different page, reload and try again.  */
    if (!tlb_hit(tlb_addr, addr)) {
        if (!victim_tlb_hit(env, mmu_idx, index, access_type,
                            addr & TARGET_PAGE_MASK)) {
            tlb_fill(env_cpu(env), addr, data->size, access_type, mmu_idx, ra);
            maybe_resized = true;
            index = tlb_index(env, mmu_idx, addr);
            entry = tlb_entry(env, mmu_idx, addr);
        }
        tlb_addr = tlb_read_idx(entry, access_type) & ~TLB_INVALID_MASK;
    }

    full = &env_tlb(env)->d[mmu_idx].fulltlb[index];
    flags = tlb_addr & (TLB_FLAGS_MASK & ~TLB_FORCE_SLOW);
    flags |= full->slow_flags[access_type];

    data->full = full;
    data->flags = flags;
    /* Compute haddr speculatively; depending on flags it might be invalid. */
    data->haddr = (void *)((uintptr_t)addr + entry->addend);

    return maybe_resized;
}

/**
 * mmu_watch_or_dirty
 * @env: cpu context
 * @data: lookup parameters
 * @access_type: load/store/code
 * @ra: return address into tcg generated code, or 0
 *
 * Trigger watchpoints for @data.addr:@data.size;
 * record writes to protected clean pages.
 */
static void mmu_watch_or_dirty(CPUArchState *env, MMULookupPageData *data,
                               MMUAccessType access_type, uintptr_t ra)
{
    CPUTLBEntryFull *full = data->full;
    vaddr addr = data->addr;
    int flags = data->flags;
    int size = data->size;

    /* On watchpoint hit, this will longjmp out.  */
    if (flags & TLB_WATCHPOINT) {
        int wp = access_type == MMU_DATA_STORE ? BP_MEM_WRITE : BP_MEM_READ;
        cpu_check_watchpoint(env_cpu(env), addr, size, full->attrs, wp, ra);
        flags &= ~TLB_WATCHPOINT;
    }

    /* Note that notdirty is only set for writes. */
    if (flags & TLB_NOTDIRTY) {
        notdirty_write(env_cpu(env), addr, size, full, ra);
        flags &= ~TLB_NOTDIRTY;
    }
    data->flags = flags;
}

/**
 * mmu_lookup: translate page(s)
 * @env: cpu context
 * @addr: virtual address
 * @oi: combined mmu_idx and MemOp
 * @ra: return address into tcg generated code, or 0
 * @access_type: load/store/code
 * @l: output result
 *
 * Resolve the translation for the page(s) beginning at @addr, for MemOp.size
 * bytes.  Return true if the lookup crosses a page boundary.
 */
static bool mmu_lookup(CPUArchState *env, vaddr addr, MemOpIdx oi,
                       uintptr_t ra, MMUAccessType type, MMULookupLocals *l)
{
    unsigned a_bits;
    bool crosspage;
    int flags;

    l->memop = get_memop(oi);
    l->mmu_idx = get_mmuidx(oi);

    tcg_debug_assert(l->mmu_idx < NB_MMU_MODES);

    /* Handle CPU specific unaligned behaviour */
    a_bits = get_alignment_bits(l->memop);
    if (addr & ((1 << a_bits) - 1)) {
        cpu_unaligned_access(env_cpu(env), addr, type, l->mmu_idx, ra);
    }

    l->page[0].addr = addr;
    l->page[0].size = memop_size(l->memop);
    l->page[1].addr = (addr + l->page[0].size - 1) & TARGET_PAGE_MASK;
    l->page[1].size = 0;
    crosspage = (addr ^ l->page[1].addr) & TARGET_PAGE_MASK;

    if (likely(!crosspage)) {
        mmu_lookup1(env, &l->page[0], l->mmu_idx, type, ra);

        flags = l->page[0].flags;
        if (unlikely(flags & (TLB_WATCHPOINT | TLB_NOTDIRTY))) {
            mmu_watch_or_dirty(env, &l->page[0], type, ra);
        }
        if (unlikely(flags & TLB_BSWAP)) {
            l->memop ^= MO_BSWAP;
        }
    } else {
        /* Finish compute of page crossing. */
        int size0 = l->page[1].addr - addr;
        l->page[1].size = l->page[0].size - size0;
        l->page[0].size = size0;

        /*
         * Lookup both pages, recognizing exceptions from either.  If the
         * second lookup potentially resized, refresh first CPUTLBEntryFull.
         */
        mmu_lookup1(env, &l->page[0], l->mmu_idx, type, ra);
        if (mmu_lookup1(env, &l->page[1], l->mmu_idx, type, ra)) {
            uintptr_t index = tlb_index(env, l->mmu_idx, addr);
            l->page[0].full = &env_tlb(env)->d[l->mmu_idx].fulltlb[index];
        }

        flags = l->page[0].flags | l->page[1].flags;
        if (unlikely(flags & (TLB_WATCHPOINT | TLB_NOTDIRTY))) {
            mmu_watch_or_dirty(env, &l->page[0], type, ra);
            mmu_watch_or_dirty(env, &l->page[1], type, ra);
        }

        /*
         * Since target/sparc is the only user of TLB_BSWAP, and all
         * Sparc accesses are aligned, any treatment across two pages
         * would be arbitrary.  Refuse it until there's a use.
         */
        tcg_debug_assert((flags & TLB_BSWAP) == 0);
    }

    return crosspage;
}

/*
 * Probe for an atomic operation.  Do not allow unaligned operations,
 * or io operations to proceed.  Return the host address.
 */
static void *atomic_mmu_lookup(CPUArchState *env, vaddr addr, MemOpIdx oi,
                               int size, uintptr_t retaddr)
{
    uintptr_t mmu_idx = get_mmuidx(oi);
    MemOp mop = get_memop(oi);
    int a_bits = get_alignment_bits(mop);
    uintptr_t index;
    CPUTLBEntry *tlbe;
    vaddr tlb_addr;
    void *hostaddr;
    CPUTLBEntryFull *full;

    tcg_debug_assert(mmu_idx < NB_MMU_MODES);

    /* 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_cpu(env), addr, MMU_DATA_STORE,
                             mmu_idx, retaddr);
    }

    /* Enforce qemu required alignment.  */
    if (unlikely(addr & (size - 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;
    }

    index = tlb_index(env, mmu_idx, addr);
    tlbe = tlb_entry(env, mmu_idx, addr);

    /* Check TLB entry and enforce page permissions.  */
    tlb_addr = tlb_addr_write(tlbe);
    if (!tlb_hit(tlb_addr, addr)) {
        if (!victim_tlb_hit(env, mmu_idx, index, MMU_DATA_STORE,
                            addr & TARGET_PAGE_MASK)) {
            tlb_fill(env_cpu(env), addr, size,
                     MMU_DATA_STORE, mmu_idx, retaddr);
            index = tlb_index(env, mmu_idx, addr);
            tlbe = tlb_entry(env, mmu_idx, addr);
        }
        tlb_addr = tlb_addr_write(tlbe) & ~TLB_INVALID_MASK;
    }

    /*
     * Let the guest notice RMW on a write-only page.
     * We have just verified that the page is writable.
     * Subpage lookups may have left TLB_INVALID_MASK set,
     * but addr_read will only be -1 if PAGE_READ was unset.
     */
    if (unlikely(tlbe->addr_read == -1)) {
        tlb_fill(env_cpu(env), addr, size, 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;
    }
    /* Collect tlb flags for read. */
    tlb_addr |= tlbe->addr_read;

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

    hostaddr = (void *)((uintptr_t)addr + tlbe->addend);
    full = &env_tlb(env)->d[mmu_idx].fulltlb[index];

    if (unlikely(tlb_addr & TLB_NOTDIRTY)) {
        notdirty_write(env_cpu(env), addr, size, full, retaddr);
    }

    if (unlikely(tlb_addr & TLB_FORCE_SLOW)) {
        int wp_flags = 0;

        if (full->slow_flags[MMU_DATA_STORE] & TLB_WATCHPOINT) {
            wp_flags |= BP_MEM_WRITE;
        }
        if (full->slow_flags[MMU_DATA_LOAD] & TLB_WATCHPOINT) {
            wp_flags |= BP_MEM_READ;
        }
        if (wp_flags) {
            cpu_check_watchpoint(env_cpu(env), addr, size,
                                 full->attrs, wp_flags, retaddr);
        }
    }

    return hostaddr;

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

/*
 * Load Helpers
 *
 * We support two different access types. SOFTMMU_CODE_ACCESS is
 * specifically for reading instructions from system memory. It is
 * called by the translation loop and in some helpers where the code
 * is disassembled. It shouldn't be called directly by guest code.
 *
 * For the benefit of TCG generated code, we want to avoid the
 * complication of ABI-specific return type promotion and always
 * return a value extended to the register size of the host. This is
 * tcg_target_long, except in the case of a 32-bit host and 64-bit
 * data, and for that we always have uint64_t.
 *
 * We don't bother with this widened value for SOFTMMU_CODE_ACCESS.
 */

/**
 * do_ld_mmio_beN:
 * @env: cpu context
 * @p: translation parameters
 * @ret_be: accumulated data
 * @mmu_idx: virtual address context
 * @ra: return address into tcg generated code, or 0
 *
 * Load @p->size bytes from @p->addr, which is memory-mapped i/o.
 * The bytes are concatenated in big-endian order with @ret_be.
 */
static uint64_t do_ld_mmio_beN(CPUArchState *env, MMULookupPageData *p,
                               uint64_t ret_be, int mmu_idx,
                               MMUAccessType type, uintptr_t ra)
{
    CPUTLBEntryFull *full = p->full;
    vaddr addr = p->addr;
    int i, size = p->size;

    QEMU_IOTHREAD_LOCK_GUARD();
    for (i = 0; i < size; i++) {
        uint8_t x = io_readx(env, full, mmu_idx, addr + i, ra, type, MO_UB);
        ret_be = (ret_be << 8) | x;
    }
    return ret_be;
}

/**
 * do_ld_bytes_beN
 * @p: translation parameters
 * @ret_be: accumulated data
 *
 * Load @p->size bytes from @p->haddr, which is RAM.
 * The bytes to concatenated in big-endian order with @ret_be.
 */
static uint64_t do_ld_bytes_beN(MMULookupPageData *p, uint64_t ret_be)
{
    uint8_t *haddr = p->haddr;
    int i, size = p->size;

    for (i = 0; i < size; i++) {
        ret_be = (ret_be << 8) | haddr[i];
    }
    return ret_be;
}

/**
 * do_ld_parts_beN
 * @p: translation parameters
 * @ret_be: accumulated data
 *
 * As do_ld_bytes_beN, but atomically on each aligned part.
 */
static uint64_t do_ld_parts_beN(MMULookupPageData *p, uint64_t ret_be)
{
    void *haddr = p->haddr;
    int size = p->size;

    do {
        uint64_t x;
        int n;

        /*
         * Find minimum of alignment and size.
         * This is slightly stronger than required by MO_ATOM_SUBALIGN, which
         * would have only checked the low bits of addr|size once at the start,
         * but is just as easy.
         */
        switch (((uintptr_t)haddr | size) & 7) {
        case 4:
            x = cpu_to_be32(load_atomic4(haddr));
            ret_be = (ret_be << 32) | x;
            n = 4;
            break;
        case 2:
        case 6:
            x = cpu_to_be16(load_atomic2(haddr));
            ret_be = (ret_be << 16) | x;
            n = 2;
            break;
        default:
            x = *(uint8_t *)haddr;
            ret_be = (ret_be << 8) | x;
            n = 1;
            break;
        case 0:
            g_assert_not_reached();
        }
        haddr += n;
        size -= n;
    } while (size != 0);
    return ret_be;
}

/**
 * do_ld_parts_be4
 * @p: translation parameters
 * @ret_be: accumulated data
 *
 * As do_ld_bytes_beN, but with one atomic load.
 * Four aligned bytes are guaranteed to cover the load.
 */
static uint64_t do_ld_whole_be4(MMULookupPageData *p, uint64_t ret_be)
{
    int o = p->addr & 3;
    uint32_t x = load_atomic4(p->haddr - o);

    x = cpu_to_be32(x);
    x <<= o * 8;
    x >>= (4 - p->size) * 8;
    return (ret_be << (p->size * 8)) | x;
}

/**
 * do_ld_parts_be8
 * @p: translation parameters
 * @ret_be: accumulated data
 *
 * As do_ld_bytes_beN, but with one atomic load.
 * Eight aligned bytes are guaranteed to cover the load.
 */
static uint64_t do_ld_whole_be8(CPUArchState *env, uintptr_t ra,
                                MMULookupPageData *p, uint64_t ret_be)
{
    int o = p->addr & 7;
    uint64_t x = load_atomic8_or_exit(env, ra, p->haddr - o);

    x = cpu_to_be64(x);
    x <<= o * 8;
    x >>= (8 - p->size) * 8;
    return (ret_be << (p->size * 8)) | x;
}

/**
 * do_ld_parts_be16
 * @p: translation parameters
 * @ret_be: accumulated data
 *
 * As do_ld_bytes_beN, but with one atomic load.
 * 16 aligned bytes are guaranteed to cover the load.
 */
static Int128 do_ld_whole_be16(CPUArchState *env, uintptr_t ra,
                               MMULookupPageData *p, uint64_t ret_be)
{
    int o = p->addr & 15;
    Int128 x, y = load_atomic16_or_exit(env, ra, p->haddr - o);
    int size = p->size;

    if (!HOST_BIG_ENDIAN) {
        y = bswap128(y);
    }
    y = int128_lshift(y, o * 8);
    y = int128_urshift(y, (16 - size) * 8);
    x = int128_make64(ret_be);
    x = int128_lshift(x, size * 8);
    return int128_or(x, y);
}

/*
 * Wrapper for the above.
 */
static uint64_t do_ld_beN(CPUArchState *env, MMULookupPageData *p,
                          uint64_t ret_be, int mmu_idx, MMUAccessType type,
                          MemOp mop, uintptr_t ra)
{
    MemOp atom;
    unsigned tmp, half_size;

    if (unlikely(p->flags & TLB_MMIO)) {
        return do_ld_mmio_beN(env, p, ret_be, mmu_idx, type, ra);
    }

    /*
     * It is a given that we cross a page and therefore there is no
     * atomicity for the load as a whole, but subobjects may need attention.
     */
    atom = mop & MO_ATOM_MASK;
    switch (atom) {
    case MO_ATOM_SUBALIGN:
        return do_ld_parts_beN(p, ret_be);

    case MO_ATOM_IFALIGN_PAIR:
    case MO_ATOM_WITHIN16_PAIR:
        tmp = mop & MO_SIZE;
        tmp = tmp ? tmp - 1 : 0;
        half_size = 1 << tmp;
        if (atom == MO_ATOM_IFALIGN_PAIR
            ? p->size == half_size
            : p->size >= half_size) {
            if (!HAVE_al8_fast && p->size < 4) {
                return do_ld_whole_be4(p, ret_be);
            } else {
                return do_ld_whole_be8(env, ra, p, ret_be);
            }
        }
        /* fall through */

    case MO_ATOM_IFALIGN:
    case MO_ATOM_WITHIN16:
    case MO_ATOM_NONE:
        return do_ld_bytes_beN(p, ret_be);

    default:
        g_assert_not_reached();
    }
}

/*
 * Wrapper for the above, for 8 < size < 16.
 */
static Int128 do_ld16_beN(CPUArchState *env, MMULookupPageData *p,
                          uint64_t a, int mmu_idx, MemOp mop, uintptr_t ra)
{
    int size = p->size;
    uint64_t b;
    MemOp atom;

    if (unlikely(p->flags & TLB_MMIO)) {
        p->size = size - 8;
        a = do_ld_mmio_beN(env, p, a, mmu_idx, MMU_DATA_LOAD, ra);
        p->addr += p->size;
        p->size = 8;
        b = do_ld_mmio_beN(env, p, 0, mmu_idx, MMU_DATA_LOAD, ra);
        return int128_make128(b, a);
    }

    /*
     * It is a given that we cross a page and therefore there is no
     * atomicity for the load as a whole, but subobjects may need attention.
     */
    atom = mop & MO_ATOM_MASK;
    switch (atom) {
    case MO_ATOM_SUBALIGN:
        p->size = size - 8;
        a = do_ld_parts_beN(p, a);
        p->haddr += size - 8;
        p->size = 8;
        b = do_ld_parts_beN(p, 0);
        break;

    case MO_ATOM_WITHIN16_PAIR:
        /* Since size > 8, this is the half that must be atomic. */
        return do_ld_whole_be16(env, ra, p, a);

    case MO_ATOM_IFALIGN_PAIR:
        /*
         * Since size > 8, both halves are misaligned,
         * and so neither is atomic.
         */
    case MO_ATOM_IFALIGN:
    case MO_ATOM_WITHIN16:
    case MO_ATOM_NONE:
        p->size = size - 8;
        a = do_ld_bytes_beN(p, a);
        b = ldq_be_p(p->haddr + size - 8);
        break;

    default:
        g_assert_not_reached();
    }

    return int128_make128(b, a);
}

static uint8_t do_ld_1(CPUArchState *env, MMULookupPageData *p, int mmu_idx,
                       MMUAccessType type, uintptr_t ra)
{
    if (unlikely(p->flags & TLB_MMIO)) {
        return io_readx(env, p->full, mmu_idx, p->addr, ra, type, MO_UB);
    } else {
        return *(uint8_t *)p->haddr;
    }
}

static uint16_t do_ld_2(CPUArchState *env, MMULookupPageData *p, int mmu_idx,
                        MMUAccessType type, MemOp memop, uintptr_t ra)
{
    uint64_t ret;

    if (unlikely(p->flags & TLB_MMIO)) {
        return io_readx(env, p->full, mmu_idx, p->addr, ra, type, memop);
    }

    /* Perform the load host endian, then swap if necessary. */
    ret = load_atom_2(env, ra, p->haddr, memop);
    if (memop & MO_BSWAP) {
        ret = bswap16(ret);
    }
    return ret;
}

static uint32_t do_ld_4(CPUArchState *env, MMULookupPageData *p, int mmu_idx,
                        MMUAccessType type, MemOp memop, uintptr_t ra)
{
    uint32_t ret;

    if (unlikely(p->flags & TLB_MMIO)) {
        return io_readx(env, p->full, mmu_idx, p->addr, ra, type, memop);
    }

    /* Perform the load host endian. */
    ret = load_atom_4(env, ra, p->haddr, memop);
    if (memop & MO_BSWAP) {
        ret = bswap32(ret);
    }
    return ret;
}

static uint64_t do_ld_8(CPUArchState *env, MMULookupPageData *p, int mmu_idx,
                        MMUAccessType type, MemOp memop, uintptr_t ra)
{
    uint64_t ret;

    if (unlikely(p->flags & TLB_MMIO)) {
        return io_readx(env, p->full, mmu_idx, p->addr, ra, type, memop);
    }

    /* Perform the load host endian. */
    ret = load_atom_8(env, ra, p->haddr, memop);
    if (memop & MO_BSWAP) {
        ret = bswap64(ret);
    }
    return ret;
}

static uint8_t do_ld1_mmu(CPUArchState *env, vaddr addr, MemOpIdx oi,
                          uintptr_t ra, MMUAccessType access_type)
{
    MMULookupLocals l;
    bool crosspage;

    cpu_req_mo(TCG_MO_LD_LD | TCG_MO_ST_LD);
    crosspage = mmu_lookup(env, addr, oi, ra, access_type, &l);
    tcg_debug_assert(!crosspage);

    return do_ld_1(env, &l.page[0], l.mmu_idx, access_type, ra);
}

tcg_target_ulong helper_ldub_mmu(CPUArchState *env, uint64_t addr,
                                 MemOpIdx oi, uintptr_t retaddr)
{
    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_8);
    return do_ld1_mmu(env, addr, oi, retaddr, MMU_DATA_LOAD);
}

static uint16_t do_ld2_mmu(CPUArchState *env, vaddr addr, MemOpIdx oi,
                           uintptr_t ra, MMUAccessType access_type)
{
    MMULookupLocals l;
    bool crosspage;
    uint16_t ret;
    uint8_t a, b;

    cpu_req_mo(TCG_MO_LD_LD | TCG_MO_ST_LD);
    crosspage = mmu_lookup(env, addr, oi, ra, access_type, &l);
    if (likely(!crosspage)) {
        return do_ld_2(env, &l.page[0], l.mmu_idx, access_type, l.memop, ra);
    }

    a = do_ld_1(env, &l.page[0], l.mmu_idx, access_type, ra);
    b = do_ld_1(env, &l.page[1], l.mmu_idx, access_type, ra);

    if ((l.memop & MO_BSWAP) == MO_LE) {
        ret = a | (b << 8);
    } else {
        ret = b | (a << 8);
    }
    return ret;
}

tcg_target_ulong helper_lduw_mmu(CPUArchState *env, uint64_t addr,
                                 MemOpIdx oi, uintptr_t retaddr)
{
    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_16);
    return do_ld2_mmu(env, addr, oi, retaddr, MMU_DATA_LOAD);
}

static uint32_t do_ld4_mmu(CPUArchState *env, vaddr addr, MemOpIdx oi,
                           uintptr_t ra, MMUAccessType access_type)
{
    MMULookupLocals l;
    bool crosspage;
    uint32_t ret;

    cpu_req_mo(TCG_MO_LD_LD | TCG_MO_ST_LD);
    crosspage = mmu_lookup(env, addr, oi, ra, access_type, &l);
    if (likely(!crosspage)) {
        return do_ld_4(env, &l.page[0], l.mmu_idx, access_type, l.memop, ra);
    }

    ret = do_ld_beN(env, &l.page[0], 0, l.mmu_idx, access_type, l.memop, ra);
    ret = do_ld_beN(env, &l.page[1], ret, l.mmu_idx, access_type, l.memop, ra);
    if ((l.memop & MO_BSWAP) == MO_LE) {
        ret = bswap32(ret);
    }
    return ret;
}

tcg_target_ulong helper_ldul_mmu(CPUArchState *env, uint64_t addr,
                                 MemOpIdx oi, uintptr_t retaddr)
{
    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_32);
    return do_ld4_mmu(env, addr, oi, retaddr, MMU_DATA_LOAD);
}

static uint64_t do_ld8_mmu(CPUArchState *env, vaddr addr, MemOpIdx oi,
                           uintptr_t ra, MMUAccessType access_type)
{
    MMULookupLocals l;
    bool crosspage;
    uint64_t ret;

    cpu_req_mo(TCG_MO_LD_LD | TCG_MO_ST_LD);
    crosspage = mmu_lookup(env, addr, oi, ra, access_type, &l);
    if (likely(!crosspage)) {
        return do_ld_8(env, &l.page[0], l.mmu_idx, access_type, l.memop, ra);
    }

    ret = do_ld_beN(env, &l.page[0], 0, l.mmu_idx, access_type, l.memop, ra);
    ret = do_ld_beN(env, &l.page[1], ret, l.mmu_idx, access_type, l.memop, ra);
    if ((l.memop & MO_BSWAP) == MO_LE) {
        ret = bswap64(ret);
    }
    return ret;
}

uint64_t helper_ldq_mmu(CPUArchState *env, uint64_t addr,
                        MemOpIdx oi, uintptr_t retaddr)
{
    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_64);
    return do_ld8_mmu(env, addr, oi, retaddr, MMU_DATA_LOAD);
}

/*
 * Provide signed versions of the load routines as well.  We can of course
 * avoid this for 64-bit data, or for 32-bit data on 32-bit host.
 */

tcg_target_ulong helper_ldsb_mmu(CPUArchState *env, uint64_t addr,
                                 MemOpIdx oi, uintptr_t retaddr)
{
    return (int8_t)helper_ldub_mmu(env, addr, oi, retaddr);
}

tcg_target_ulong helper_ldsw_mmu(CPUArchState *env, uint64_t addr,
                                 MemOpIdx oi, uintptr_t retaddr)
{
    return (int16_t)helper_lduw_mmu(env, addr, oi, retaddr);
}

tcg_target_ulong helper_ldsl_mmu(CPUArchState *env, uint64_t addr,
                                 MemOpIdx oi, uintptr_t retaddr)
{
    return (int32_t)helper_ldul_mmu(env, addr, oi, retaddr);
}

static Int128 do_ld16_mmu(CPUArchState *env, vaddr addr,
                          MemOpIdx oi, uintptr_t ra)
{
    MMULookupLocals l;
    bool crosspage;
    uint64_t a, b;
    Int128 ret;
    int first;

    cpu_req_mo(TCG_MO_LD_LD | TCG_MO_ST_LD);
    crosspage = mmu_lookup(env, addr, oi, ra, MMU_DATA_LOAD, &l);
    if (likely(!crosspage)) {
        /* Perform the load host endian. */
        if (unlikely(l.page[0].flags & TLB_MMIO)) {
            QEMU_IOTHREAD_LOCK_GUARD();
            a = io_readx(env, l.page[0].full, l.mmu_idx, addr,
                         ra, MMU_DATA_LOAD, MO_64);
            b = io_readx(env, l.page[0].full, l.mmu_idx, addr + 8,
                         ra, MMU_DATA_LOAD, MO_64);
            ret = int128_make128(HOST_BIG_ENDIAN ? b : a,
                                 HOST_BIG_ENDIAN ? a : b);
        } else {
            ret = load_atom_16(env, ra, l.page[0].haddr, l.memop);
        }
        if (l.memop & MO_BSWAP) {
            ret = bswap128(ret);
        }
        return ret;
    }

    first = l.page[0].size;
    if (first == 8) {
        MemOp mop8 = (l.memop & ~MO_SIZE) | MO_64;

        a = do_ld_8(env, &l.page[0], l.mmu_idx, MMU_DATA_LOAD, mop8, ra);
        b = do_ld_8(env, &l.page[1], l.mmu_idx, MMU_DATA_LOAD, mop8, ra);
        if ((mop8 & MO_BSWAP) == MO_LE) {
            ret = int128_make128(a, b);
        } else {
            ret = int128_make128(b, a);
        }
        return ret;
    }

    if (first < 8) {
        a = do_ld_beN(env, &l.page[0], 0, l.mmu_idx,
                      MMU_DATA_LOAD, l.memop, ra);
        ret = do_ld16_beN(env, &l.page[1], a, l.mmu_idx, l.memop, ra);
    } else {
        ret = do_ld16_beN(env, &l.page[0], 0, l.mmu_idx, l.memop, ra);
        b = int128_getlo(ret);
        ret = int128_lshift(ret, l.page[1].size * 8);
        a = int128_gethi(ret);
        b = do_ld_beN(env, &l.page[1], b, l.mmu_idx,
                      MMU_DATA_LOAD, l.memop, ra);
        ret = int128_make128(b, a);
    }
    if ((l.memop & MO_BSWAP) == MO_LE) {
        ret = bswap128(ret);
    }
    return ret;
}

Int128 helper_ld16_mmu(CPUArchState *env, uint64_t addr,
                       uint32_t oi, uintptr_t retaddr)
{
    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_128);
    return do_ld16_mmu(env, addr, oi, retaddr);
}

Int128 helper_ld_i128(CPUArchState *env, uint64_t addr, uint32_t oi)
{
    return helper_ld16_mmu(env, addr, oi, GETPC());
}

/*
 * Load helpers for cpu_ldst.h.
 */

static void plugin_load_cb(CPUArchState *env, abi_ptr addr, MemOpIdx oi)
{
    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
}

uint8_t cpu_ldb_mmu(CPUArchState *env, abi_ptr addr, MemOpIdx oi, uintptr_t ra)
{
    uint8_t ret;

    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_UB);
    ret = do_ld1_mmu(env, addr, oi, ra, MMU_DATA_LOAD);
    plugin_load_cb(env, addr, oi);
    return ret;
}

uint16_t cpu_ldw_mmu(CPUArchState *env, abi_ptr addr,
                     MemOpIdx oi, uintptr_t ra)
{
    uint16_t ret;

    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_16);
    ret = do_ld2_mmu(env, addr, oi, ra, MMU_DATA_LOAD);
    plugin_load_cb(env, addr, oi);
    return ret;
}

uint32_t cpu_ldl_mmu(CPUArchState *env, abi_ptr addr,
                     MemOpIdx oi, uintptr_t ra)
{
    uint32_t ret;

    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_32);
    ret = do_ld4_mmu(env, addr, oi, ra, MMU_DATA_LOAD);
    plugin_load_cb(env, addr, oi);
    return ret;
}

uint64_t cpu_ldq_mmu(CPUArchState *env, abi_ptr addr,
                     MemOpIdx oi, uintptr_t ra)
{
    uint64_t ret;

    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_64);
    ret = do_ld8_mmu(env, addr, oi, ra, MMU_DATA_LOAD);
    plugin_load_cb(env, addr, oi);
    return ret;
}

Int128 cpu_ld16_mmu(CPUArchState *env, abi_ptr addr,
                    MemOpIdx oi, uintptr_t ra)
{
    Int128 ret;

    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_128);
    ret = do_ld16_mmu(env, addr, oi, ra);
    plugin_load_cb(env, addr, oi);
    return ret;
}

/*
 * Store Helpers
 */

/**
 * do_st_mmio_leN:
 * @env: cpu context
 * @p: translation parameters
 * @val_le: data to store
 * @mmu_idx: virtual address context
 * @ra: return address into tcg generated code, or 0
 *
 * Store @p->size bytes at @p->addr, which is memory-mapped i/o.
 * The bytes to store are extracted in little-endian order from @val_le;
 * return the bytes of @val_le beyond @p->size that have not been stored.
 */
static uint64_t do_st_mmio_leN(CPUArchState *env, MMULookupPageData *p,
                               uint64_t val_le, int mmu_idx, uintptr_t ra)
{
    CPUTLBEntryFull *full = p->full;
    vaddr addr = p->addr;
    int i, size = p->size;

    QEMU_IOTHREAD_LOCK_GUARD();
    for (i = 0; i < size; i++, val_le >>= 8) {
        io_writex(env, full, mmu_idx, val_le, addr + i, ra, MO_UB);
    }
    return val_le;
}

/*
 * Wrapper for the above.
 */
static uint64_t do_st_leN(CPUArchState *env, MMULookupPageData *p,
                          uint64_t val_le, int mmu_idx,
                          MemOp mop, uintptr_t ra)
{
    MemOp atom;
    unsigned tmp, half_size;

    if (unlikely(p->flags & TLB_MMIO)) {
        return do_st_mmio_leN(env, p, val_le, mmu_idx, ra);
    } else if (unlikely(p->flags & TLB_DISCARD_WRITE)) {
        return val_le >> (p->size * 8);
    }

    /*
     * It is a given that we cross a page and therefore there is no atomicity
     * for the store as a whole, but subobjects may need attention.
     */
    atom = mop & MO_ATOM_MASK;
    switch (atom) {
    case MO_ATOM_SUBALIGN:
        return store_parts_leN(p->haddr, p->size, val_le);

    case MO_ATOM_IFALIGN_PAIR:
    case MO_ATOM_WITHIN16_PAIR:
        tmp = mop & MO_SIZE;
        tmp = tmp ? tmp - 1 : 0;
        half_size = 1 << tmp;
        if (atom == MO_ATOM_IFALIGN_PAIR
            ? p->size == half_size
            : p->size >= half_size) {
            if (!HAVE_al8_fast && p->size <= 4) {
                return store_whole_le4(p->haddr, p->size, val_le);
            } else if (HAVE_al8) {
                return store_whole_le8(p->haddr, p->size, val_le);
            } else {
                cpu_loop_exit_atomic(env_cpu(env), ra);
            }
        }
        /* fall through */

    case MO_ATOM_IFALIGN:
    case MO_ATOM_WITHIN16:
    case MO_ATOM_NONE:
        return store_bytes_leN(p->haddr, p->size, val_le);

    default:
        g_assert_not_reached();
    }
}

/*
 * Wrapper for the above, for 8 < size < 16.
 */
static uint64_t do_st16_leN(CPUArchState *env, MMULookupPageData *p,
                            Int128 val_le, int mmu_idx,
                            MemOp mop, uintptr_t ra)
{
    int size = p->size;
    MemOp atom;

    if (unlikely(p->flags & TLB_MMIO)) {
        p->size = 8;
        do_st_mmio_leN(env, p, int128_getlo(val_le), mmu_idx, ra);
        p->size = size - 8;
        p->addr += 8;
        return do_st_mmio_leN(env, p, int128_gethi(val_le), mmu_idx, ra);
    } else if (unlikely(p->flags & TLB_DISCARD_WRITE)) {
        return int128_gethi(val_le) >> ((size - 8) * 8);
    }

    /*
     * It is a given that we cross a page and therefore there is no atomicity
     * for the store as a whole, but subobjects may need attention.
     */
    atom = mop & MO_ATOM_MASK;
    switch (atom) {
    case MO_ATOM_SUBALIGN:
        store_parts_leN(p->haddr, 8, int128_getlo(val_le));
        return store_parts_leN(p->haddr + 8, p->size - 8,
                               int128_gethi(val_le));

    case MO_ATOM_WITHIN16_PAIR:
        /* Since size > 8, this is the half that must be atomic. */
        if (!HAVE_ATOMIC128_RW) {
            cpu_loop_exit_atomic(env_cpu(env), ra);
        }
        return store_whole_le16(p->haddr, p->size, val_le);

    case MO_ATOM_IFALIGN_PAIR:
        /*
         * Since size > 8, both halves are misaligned,
         * and so neither is atomic.
         */
    case MO_ATOM_IFALIGN:
    case MO_ATOM_WITHIN16:
    case MO_ATOM_NONE:
        stq_le_p(p->haddr, int128_getlo(val_le));
        return store_bytes_leN(p->haddr + 8, p->size - 8,
                               int128_gethi(val_le));

    default:
        g_assert_not_reached();
    }
}

static void do_st_1(CPUArchState *env, MMULookupPageData *p, uint8_t val,
                    int mmu_idx, uintptr_t ra)
{
    if (unlikely(p->flags & TLB_MMIO)) {
        io_writex(env, p->full, mmu_idx, val, p->addr, ra, MO_UB);
    } else if (unlikely(p->flags & TLB_DISCARD_WRITE)) {
        /* nothing */
    } else {
        *(uint8_t *)p->haddr = val;
    }
}

static void do_st_2(CPUArchState *env, MMULookupPageData *p, uint16_t val,
                    int mmu_idx, MemOp memop, uintptr_t ra)
{
    if (unlikely(p->flags & TLB_MMIO)) {
        io_writex(env, p->full, mmu_idx, val, p->addr, ra, memop);
    } else if (unlikely(p->flags & TLB_DISCARD_WRITE)) {
        /* nothing */
    } else {
        /* Swap to host endian if necessary, then store. */
        if (memop & MO_BSWAP) {
            val = bswap16(val);
        }
        store_atom_2(env, ra, p->haddr, memop, val);
    }
}

static void do_st_4(CPUArchState *env, MMULookupPageData *p, uint32_t val,
                    int mmu_idx, MemOp memop, uintptr_t ra)
{
    if (unlikely(p->flags & TLB_MMIO)) {
        io_writex(env, p->full, mmu_idx, val, p->addr, ra, memop);
    } else if (unlikely(p->flags & TLB_DISCARD_WRITE)) {
        /* nothing */
    } else {
        /* Swap to host endian if necessary, then store. */
        if (memop & MO_BSWAP) {
            val = bswap32(val);
        }
        store_atom_4(env, ra, p->haddr, memop, val);
    }
}

static void do_st_8(CPUArchState *env, MMULookupPageData *p, uint64_t val,
                    int mmu_idx, MemOp memop, uintptr_t ra)
{
    if (unlikely(p->flags & TLB_MMIO)) {
        io_writex(env, p->full, mmu_idx, val, p->addr, ra, memop);
    } else if (unlikely(p->flags & TLB_DISCARD_WRITE)) {
        /* nothing */
    } else {
        /* Swap to host endian if necessary, then store. */
        if (memop & MO_BSWAP) {
            val = bswap64(val);
        }
        store_atom_8(env, ra, p->haddr, memop, val);
    }
}

void helper_stb_mmu(CPUArchState *env, uint64_t addr, uint32_t val,
                    MemOpIdx oi, uintptr_t ra)
{
    MMULookupLocals l;
    bool crosspage;

    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_8);
    cpu_req_mo(TCG_MO_LD_ST | TCG_MO_ST_ST);
    crosspage = mmu_lookup(env, addr, oi, ra, MMU_DATA_STORE, &l);
    tcg_debug_assert(!crosspage);

    do_st_1(env, &l.page[0], val, l.mmu_idx, ra);
}

static void do_st2_mmu(CPUArchState *env, vaddr addr, uint16_t val,
                       MemOpIdx oi, uintptr_t ra)
{
    MMULookupLocals l;
    bool crosspage;
    uint8_t a, b;

    cpu_req_mo(TCG_MO_LD_ST | TCG_MO_ST_ST);
    crosspage = mmu_lookup(env, addr, oi, ra, MMU_DATA_STORE, &l);
    if (likely(!crosspage)) {
        do_st_2(env, &l.page[0], val, l.mmu_idx, l.memop, ra);
        return;
    }

    if ((l.memop & MO_BSWAP) == MO_LE) {
        a = val, b = val >> 8;
    } else {
        b = val, a = val >> 8;
    }
    do_st_1(env, &l.page[0], a, l.mmu_idx, ra);
    do_st_1(env, &l.page[1], b, l.mmu_idx, ra);
}

void helper_stw_mmu(CPUArchState *env, uint64_t addr, uint32_t val,
                    MemOpIdx oi, uintptr_t retaddr)
{
    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_16);
    do_st2_mmu(env, addr, val, oi, retaddr);
}

static void do_st4_mmu(CPUArchState *env, vaddr addr, uint32_t val,
                       MemOpIdx oi, uintptr_t ra)
{
    MMULookupLocals l;
    bool crosspage;

    cpu_req_mo(TCG_MO_LD_ST | TCG_MO_ST_ST);
    crosspage = mmu_lookup(env, addr, oi, ra, MMU_DATA_STORE, &l);
    if (likely(!crosspage)) {
        do_st_4(env, &l.page[0], val, l.mmu_idx, l.memop, ra);
        return;
    }

    /* Swap to little endian for simplicity, then store by bytes. */
    if ((l.memop & MO_BSWAP) != MO_LE) {
        val = bswap32(val);
    }
    val = do_st_leN(env, &l.page[0], val, l.mmu_idx, l.memop, ra);
    (void) do_st_leN(env, &l.page[1], val, l.mmu_idx, l.memop, ra);
}

void helper_stl_mmu(CPUArchState *env, uint64_t addr, uint32_t val,
                    MemOpIdx oi, uintptr_t retaddr)
{
    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_32);
    do_st4_mmu(env, addr, val, oi, retaddr);
}

static void do_st8_mmu(CPUArchState *env, vaddr addr, uint64_t val,
                       MemOpIdx oi, uintptr_t ra)
{
    MMULookupLocals l;
    bool crosspage;

    cpu_req_mo(TCG_MO_LD_ST | TCG_MO_ST_ST);
    crosspage = mmu_lookup(env, addr, oi, ra, MMU_DATA_STORE, &l);
    if (likely(!crosspage)) {
        do_st_8(env, &l.page[0], val, l.mmu_idx, l.memop, ra);
        return;
    }

    /* Swap to little endian for simplicity, then store by bytes. */
    if ((l.memop & MO_BSWAP) != MO_LE) {
        val = bswap64(val);
    }
    val = do_st_leN(env, &l.page[0], val, l.mmu_idx, l.memop, ra);
    (void) do_st_leN(env, &l.page[1], val, l.mmu_idx, l.memop, ra);
}

void helper_stq_mmu(CPUArchState *env, uint64_t addr, uint64_t val,
                    MemOpIdx oi, uintptr_t retaddr)
{
    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_64);
    do_st8_mmu(env, addr, val, oi, retaddr);
}

static void do_st16_mmu(CPUArchState *env, vaddr addr, Int128 val,
                        MemOpIdx oi, uintptr_t ra)
{
    MMULookupLocals l;
    bool crosspage;
    uint64_t a, b;
    int first;

    cpu_req_mo(TCG_MO_LD_ST | TCG_MO_ST_ST);
    crosspage = mmu_lookup(env, addr, oi, ra, MMU_DATA_STORE, &l);
    if (likely(!crosspage)) {
        /* Swap to host endian if necessary, then store. */
        if (l.memop & MO_BSWAP) {
            val = bswap128(val);
        }
        if (unlikely(l.page[0].flags & TLB_MMIO)) {
            QEMU_IOTHREAD_LOCK_GUARD();
            if (HOST_BIG_ENDIAN) {
                b = int128_getlo(val), a = int128_gethi(val);
            } else {
                a = int128_getlo(val), b = int128_gethi(val);
            }
            io_writex(env, l.page[0].full, l.mmu_idx, a, addr, ra, MO_64);
            io_writex(env, l.page[0].full, l.mmu_idx, b, addr + 8, ra, MO_64);
        } else if (unlikely(l.page[0].flags & TLB_DISCARD_WRITE)) {
            /* nothing */
        } else {
            store_atom_16(env, ra, l.page[0].haddr, l.memop, val);
        }
        return;
    }

    first = l.page[0].size;
    if (first == 8) {
        MemOp mop8 = (l.memop & ~(MO_SIZE | MO_BSWAP)) | MO_64;

        if (l.memop & MO_BSWAP) {
            val = bswap128(val);
        }
        if (HOST_BIG_ENDIAN) {
            b = int128_getlo(val), a = int128_gethi(val);
        } else {
            a = int128_getlo(val), b = int128_gethi(val);
        }
        do_st_8(env, &l.page[0], a, l.mmu_idx, mop8, ra);
        do_st_8(env, &l.page[1], b, l.mmu_idx, mop8, ra);
        return;
    }

    if ((l.memop & MO_BSWAP) != MO_LE) {
        val = bswap128(val);
    }
    if (first < 8) {
        do_st_leN(env, &l.page[0], int128_getlo(val), l.mmu_idx, l.memop, ra);
        val = int128_urshift(val, first * 8);
        do_st16_leN(env, &l.page[1], val, l.mmu_idx, l.memop, ra);
    } else {
        b = do_st16_leN(env, &l.page[0], val, l.mmu_idx, l.memop, ra);
        do_st_leN(env, &l.page[1], b, l.mmu_idx, l.memop, ra);
    }
}

void helper_st16_mmu(CPUArchState *env, uint64_t addr, Int128 val,
                     MemOpIdx oi, uintptr_t retaddr)
{
    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_128);
    do_st16_mmu(env, addr, val, oi, retaddr);
}

void helper_st_i128(CPUArchState *env, uint64_t addr, Int128 val, MemOpIdx oi)
{
    helper_st16_mmu(env, addr, val, oi, GETPC());
}

/*
 * Store Helpers for cpu_ldst.h
 */

static void plugin_store_cb(CPUArchState *env, abi_ptr addr, MemOpIdx oi)
{
    qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
}

void cpu_stb_mmu(CPUArchState *env, target_ulong addr, uint8_t val,
                 MemOpIdx oi, uintptr_t retaddr)
{
    helper_stb_mmu(env, addr, val, oi, retaddr);
    plugin_store_cb(env, addr, oi);
}

void cpu_stw_mmu(CPUArchState *env, target_ulong addr, uint16_t val,
                 MemOpIdx oi, uintptr_t retaddr)
{
    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_16);
    do_st2_mmu(env, addr, val, oi, retaddr);
    plugin_store_cb(env, addr, oi);
}

void cpu_stl_mmu(CPUArchState *env, target_ulong addr, uint32_t val,
                    MemOpIdx oi, uintptr_t retaddr)
{
    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_32);
    do_st4_mmu(env, addr, val, oi, retaddr);
    plugin_store_cb(env, addr, oi);
}

void cpu_stq_mmu(CPUArchState *env, target_ulong addr, uint64_t val,
                 MemOpIdx oi, uintptr_t retaddr)
{
    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_64);
    do_st8_mmu(env, addr, val, oi, retaddr);
    plugin_store_cb(env, addr, oi);
}

void cpu_st16_mmu(CPUArchState *env, target_ulong addr, Int128 val,
                  MemOpIdx oi, uintptr_t retaddr)
{
    tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_128);
    do_st16_mmu(env, addr, val, oi, retaddr);
    plugin_store_cb(env, addr, oi);
}

#include "ldst_common.c.inc"

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

#define ATOMIC_NAME(X) \
    glue(glue(glue(cpu_atomic_ ## X, SUFFIX), END), _mmu)

#define ATOMIC_MMU_CLEANUP

#include "atomic_common.c.inc"

#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 defined(CONFIG_ATOMIC128) || defined(CONFIG_CMPXCHG128)
#define DATA_SIZE 16
#include "atomic_template.h"
#endif

/* Code access functions.  */

uint32_t cpu_ldub_code(CPUArchState *env, abi_ptr addr)
{
    MemOpIdx oi = make_memop_idx(MO_UB, cpu_mmu_index(env, true));
    return do_ld1_mmu(env, addr, oi, 0, MMU_INST_FETCH);
}

uint32_t cpu_lduw_code(CPUArchState *env, abi_ptr addr)
{
    MemOpIdx oi = make_memop_idx(MO_TEUW, cpu_mmu_index(env, true));
    return do_ld2_mmu(env, addr, oi, 0, MMU_INST_FETCH);
}

uint32_t cpu_ldl_code(CPUArchState *env, abi_ptr addr)
{
    MemOpIdx oi = make_memop_idx(MO_TEUL, cpu_mmu_index(env, true));
    return do_ld4_mmu(env, addr, oi, 0, MMU_INST_FETCH);
}

uint64_t cpu_ldq_code(CPUArchState *env, abi_ptr addr)
{
    MemOpIdx oi = make_memop_idx(MO_TEUQ, cpu_mmu_index(env, true));
    return do_ld8_mmu(env, addr, oi, 0, MMU_INST_FETCH);
}

uint8_t cpu_ldb_code_mmu(CPUArchState *env, abi_ptr addr,
                         MemOpIdx oi, uintptr_t retaddr)
{
    return do_ld1_mmu(env, addr, oi, retaddr, MMU_INST_FETCH);
}

uint16_t cpu_ldw_code_mmu(CPUArchState *env, abi_ptr addr,
                          MemOpIdx oi, uintptr_t retaddr)
{
    return do_ld2_mmu(env, addr, oi, retaddr, MMU_INST_FETCH);
}

uint32_t cpu_ldl_code_mmu(CPUArchState *env, abi_ptr addr,
                          MemOpIdx oi, uintptr_t retaddr)
{
    return do_ld4_mmu(env, addr, oi, retaddr, MMU_INST_FETCH);
}

uint64_t cpu_ldq_code_mmu(CPUArchState *env, abi_ptr addr,
                          MemOpIdx oi, uintptr_t retaddr)
{
    return do_ld8_mmu(env, addr, oi, retaddr, MMU_INST_FETCH);
}