aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm/mmu.c
blob: d3877dd713aef991043ff516677d52acdc77efad (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
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
6163
6164
6165
6166
6167
6168
6169
6170
6171
6172
6173
6174
6175
6176
6177
6178
6179
6180
6181
6182
6183
6184
6185
6186
6187
6188
6189
6190
6191
6192
6193
6194
6195
6196
6197
6198
6199
6200
6201
6202
6203
6204
6205
6206
6207
6208
6209
6210
6211
6212
6213
6214
6215
6216
6217
6218
6219
6220
6221
6222
6223
6224
6225
6226
6227
6228
6229
6230
6231
6232
6233
6234
6235
6236
6237
6238
6239
6240
6241
6242
6243
6244
6245
6246
6247
6248
6249
6250
6251
6252
6253
6254
6255
6256
6257
6258
6259
6260
6261
6262
6263
6264
6265
6266
6267
6268
6269
6270
6271
6272
6273
6274
6275
6276
6277
6278
6279
6280
6281
6282
6283
6284
6285
6286
6287
6288
6289
6290
6291
6292
6293
6294
6295
6296
6297
6298
6299
6300
6301
6302
6303
6304
6305
6306
6307
6308
6309
6310
6311
6312
6313
6314
6315
6316
6317
6318
6319
6320
6321
6322
6323
6324
6325
6326
6327
6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353
6354
6355
6356
6357
6358
6359
6360
6361
6362
6363
6364
6365
6366
6367
6368
6369
6370
6371
6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396
6397
6398
6399
6400
6401
6402
6403
6404
6405
6406
6407
6408
6409
6410
6411
6412
6413
6414
6415
6416
6417
6418
6419
6420
6421
6422
6423
6424
6425
6426
6427
6428
6429
6430
6431
6432
6433
6434
6435
6436
6437
6438
6439
6440
6441
6442
6443
6444
6445
6446
6447
6448
6449
6450
6451
6452
6453
6454
6455
6456
6457
6458
6459
6460
6461
6462
6463
6464
6465
6466
6467
6468
6469
6470
6471
6472
6473
6474
6475
6476
6477
6478
6479
6480
6481
6482
6483
6484
6485
6486
6487
6488
6489
6490
6491
6492
6493
6494
6495
6496
6497
6498
6499
6500
6501
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * This module enables machines with Intel VT-x extensions to run virtual
 * machines without emulation or binary translation.
 *
 * MMU support
 *
 * Copyright (C) 2006 Qumranet, Inc.
 * Copyright 2010 Red Hat, Inc. and/or its affiliates.
 *
 * Authors:
 *   Yaniv Kamay  <yaniv@qumranet.com>
 *   Avi Kivity   <avi@qumranet.com>
 */

#include "irq.h"
#include "mmu.h"
#include "x86.h"
#include "kvm_cache_regs.h"
#include "cpuid.h"

#include <linux/kvm_host.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/moduleparam.h>
#include <linux/export.h>
#include <linux/swap.h>
#include <linux/hugetlb.h>
#include <linux/compiler.h>
#include <linux/srcu.h>
#include <linux/slab.h>
#include <linux/sched/signal.h>
#include <linux/uaccess.h>
#include <linux/hash.h>
#include <linux/kern_levels.h>
#include <linux/kthread.h>

#include <asm/page.h>
#include <asm/pat.h>
#include <asm/cmpxchg.h>
#include <asm/e820/api.h>
#include <asm/io.h>
#include <asm/vmx.h>
#include <asm/kvm_page_track.h>
#include "trace.h"

extern bool itlb_multihit_kvm_mitigation;

static int __read_mostly nx_huge_pages = -1;
#ifdef CONFIG_PREEMPT_RT
/* Recovery can cause latency spikes, disable it for PREEMPT_RT.  */
static uint __read_mostly nx_huge_pages_recovery_ratio = 0;
#else
static uint __read_mostly nx_huge_pages_recovery_ratio = 60;
#endif

static int set_nx_huge_pages(const char *val, const struct kernel_param *kp);
static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp);

static struct kernel_param_ops nx_huge_pages_ops = {
	.set = set_nx_huge_pages,
	.get = param_get_bool,
};

static struct kernel_param_ops nx_huge_pages_recovery_ratio_ops = {
	.set = set_nx_huge_pages_recovery_ratio,
	.get = param_get_uint,
};

module_param_cb(nx_huge_pages, &nx_huge_pages_ops, &nx_huge_pages, 0644);
__MODULE_PARM_TYPE(nx_huge_pages, "bool");
module_param_cb(nx_huge_pages_recovery_ratio, &nx_huge_pages_recovery_ratio_ops,
		&nx_huge_pages_recovery_ratio, 0644);
__MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint");

/*
 * When setting this variable to true it enables Two-Dimensional-Paging
 * where the hardware walks 2 page tables:
 * 1. the guest-virtual to guest-physical
 * 2. while doing 1. it walks guest-physical to host-physical
 * If the hardware supports that we don't need to do shadow paging.
 */
bool tdp_enabled = false;

enum {
	AUDIT_PRE_PAGE_FAULT,
	AUDIT_POST_PAGE_FAULT,
	AUDIT_PRE_PTE_WRITE,
	AUDIT_POST_PTE_WRITE,
	AUDIT_PRE_SYNC,
	AUDIT_POST_SYNC
};

#undef MMU_DEBUG

#ifdef MMU_DEBUG
static bool dbg = 0;
module_param(dbg, bool, 0644);

#define pgprintk(x...) do { if (dbg) printk(x); } while (0)
#define rmap_printk(x...) do { if (dbg) printk(x); } while (0)
#define MMU_WARN_ON(x) WARN_ON(x)
#else
#define pgprintk(x...) do { } while (0)
#define rmap_printk(x...) do { } while (0)
#define MMU_WARN_ON(x) do { } while (0)
#endif

#define PTE_PREFETCH_NUM		8

#define PT_FIRST_AVAIL_BITS_SHIFT 10
#define PT64_SECOND_AVAIL_BITS_SHIFT 54

/*
 * The mask used to denote special SPTEs, which can be either MMIO SPTEs or
 * Access Tracking SPTEs.
 */
#define SPTE_SPECIAL_MASK (3ULL << 52)
#define SPTE_AD_ENABLED_MASK (0ULL << 52)
#define SPTE_AD_DISABLED_MASK (1ULL << 52)
#define SPTE_AD_WRPROT_ONLY_MASK (2ULL << 52)
#define SPTE_MMIO_MASK (3ULL << 52)

#define PT64_LEVEL_BITS 9

#define PT64_LEVEL_SHIFT(level) \
		(PAGE_SHIFT + (level - 1) * PT64_LEVEL_BITS)

#define PT64_INDEX(address, level)\
	(((address) >> PT64_LEVEL_SHIFT(level)) & ((1 << PT64_LEVEL_BITS) - 1))


#define PT32_LEVEL_BITS 10

#define PT32_LEVEL_SHIFT(level) \
		(PAGE_SHIFT + (level - 1) * PT32_LEVEL_BITS)

#define PT32_LVL_OFFSET_MASK(level) \
	(PT32_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \
						* PT32_LEVEL_BITS))) - 1))

#define PT32_INDEX(address, level)\
	(((address) >> PT32_LEVEL_SHIFT(level)) & ((1 << PT32_LEVEL_BITS) - 1))


#ifdef CONFIG_DYNAMIC_PHYSICAL_MASK
#define PT64_BASE_ADDR_MASK (physical_mask & ~(u64)(PAGE_SIZE-1))
#else
#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
#endif
#define PT64_LVL_ADDR_MASK(level) \
	(PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
						* PT64_LEVEL_BITS))) - 1))
#define PT64_LVL_OFFSET_MASK(level) \
	(PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \
						* PT64_LEVEL_BITS))) - 1))

#define PT32_BASE_ADDR_MASK PAGE_MASK
#define PT32_DIR_BASE_ADDR_MASK \
	(PAGE_MASK & ~((1ULL << (PAGE_SHIFT + PT32_LEVEL_BITS)) - 1))
#define PT32_LVL_ADDR_MASK(level) \
	(PAGE_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
					    * PT32_LEVEL_BITS))) - 1))

#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \
			| shadow_x_mask | shadow_nx_mask | shadow_me_mask)

#define ACC_EXEC_MASK    1
#define ACC_WRITE_MASK   PT_WRITABLE_MASK
#define ACC_USER_MASK    PT_USER_MASK
#define ACC_ALL          (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK)

/* The mask for the R/X bits in EPT PTEs */
#define PT64_EPT_READABLE_MASK			0x1ull
#define PT64_EPT_EXECUTABLE_MASK		0x4ull

#include <trace/events/kvm.h>

#define SPTE_HOST_WRITEABLE	(1ULL << PT_FIRST_AVAIL_BITS_SHIFT)
#define SPTE_MMU_WRITEABLE	(1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1))

#define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)

/* make pte_list_desc fit well in cache line */
#define PTE_LIST_EXT 3

/*
 * Return values of handle_mmio_page_fault and mmu.page_fault:
 * RET_PF_RETRY: let CPU fault again on the address.
 * RET_PF_EMULATE: mmio page fault, emulate the instruction directly.
 *
 * For handle_mmio_page_fault only:
 * RET_PF_INVALID: the spte is invalid, let the real page fault path update it.
 */
enum {
	RET_PF_RETRY = 0,
	RET_PF_EMULATE = 1,
	RET_PF_INVALID = 2,
};

struct pte_list_desc {
	u64 *sptes[PTE_LIST_EXT];
	struct pte_list_desc *more;
};

struct kvm_shadow_walk_iterator {
	u64 addr;
	hpa_t shadow_addr;
	u64 *sptep;
	int level;
	unsigned index;
};

static const union kvm_mmu_page_role mmu_base_role_mask = {
	.cr0_wp = 1,
	.gpte_is_8_bytes = 1,
	.nxe = 1,
	.smep_andnot_wp = 1,
	.smap_andnot_wp = 1,
	.smm = 1,
	.guest_mode = 1,
	.ad_disabled = 1,
};

#define for_each_shadow_entry_using_root(_vcpu, _root, _addr, _walker)     \
	for (shadow_walk_init_using_root(&(_walker), (_vcpu),              \
					 (_root), (_addr));                \
	     shadow_walk_okay(&(_walker));			           \
	     shadow_walk_next(&(_walker)))

#define for_each_shadow_entry(_vcpu, _addr, _walker)            \
	for (shadow_walk_init(&(_walker), _vcpu, _addr);	\
	     shadow_walk_okay(&(_walker));			\
	     shadow_walk_next(&(_walker)))

#define for_each_shadow_entry_lockless(_vcpu, _addr, _walker, spte)	\
	for (shadow_walk_init(&(_walker), _vcpu, _addr);		\
	     shadow_walk_okay(&(_walker)) &&				\
		({ spte = mmu_spte_get_lockless(_walker.sptep); 1; });	\
	     __shadow_walk_next(&(_walker), spte))

static struct kmem_cache *pte_list_desc_cache;
static struct kmem_cache *mmu_page_header_cache;
static struct percpu_counter kvm_total_used_mmu_pages;

static u64 __read_mostly shadow_nx_mask;
static u64 __read_mostly shadow_x_mask;	/* mutual exclusive with nx_mask */
static u64 __read_mostly shadow_user_mask;
static u64 __read_mostly shadow_accessed_mask;
static u64 __read_mostly shadow_dirty_mask;
static u64 __read_mostly shadow_mmio_mask;
static u64 __read_mostly shadow_mmio_value;
static u64 __read_mostly shadow_mmio_access_mask;
static u64 __read_mostly shadow_present_mask;
static u64 __read_mostly shadow_me_mask;

/*
 * SPTEs used by MMUs without A/D bits are marked with SPTE_AD_DISABLED_MASK;
 * shadow_acc_track_mask is the set of bits to be cleared in non-accessed
 * pages.
 */
static u64 __read_mostly shadow_acc_track_mask;

/*
 * The mask/shift to use for saving the original R/X bits when marking the PTE
 * as not-present for access tracking purposes. We do not save the W bit as the
 * PTEs being access tracked also need to be dirty tracked, so the W bit will be
 * restored only when a write is attempted to the page.
 */
static const u64 shadow_acc_track_saved_bits_mask = PT64_EPT_READABLE_MASK |
						    PT64_EPT_EXECUTABLE_MASK;
static const u64 shadow_acc_track_saved_bits_shift = PT64_SECOND_AVAIL_BITS_SHIFT;

/*
 * This mask must be set on all non-zero Non-Present or Reserved SPTEs in order
 * to guard against L1TF attacks.
 */
static u64 __read_mostly shadow_nonpresent_or_rsvd_mask;

/*
 * The number of high-order 1 bits to use in the mask above.
 */
static const u64 shadow_nonpresent_or_rsvd_mask_len = 5;

/*
 * In some cases, we need to preserve the GFN of a non-present or reserved
 * SPTE when we usurp the upper five bits of the physical address space to
 * defend against L1TF, e.g. for MMIO SPTEs.  To preserve the GFN, we'll
 * shift bits of the GFN that overlap with shadow_nonpresent_or_rsvd_mask
 * left into the reserved bits, i.e. the GFN in the SPTE will be split into
 * high and low parts.  This mask covers the lower bits of the GFN.
 */
static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;

/*
 * The number of non-reserved physical address bits irrespective of features
 * that repurpose legal bits, e.g. MKTME.
 */
static u8 __read_mostly shadow_phys_bits;

static void mmu_spte_set(u64 *sptep, u64 spte);
static bool is_executable_pte(u64 spte);
static union kvm_mmu_page_role
kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu);

#define CREATE_TRACE_POINTS
#include "mmutrace.h"


static inline bool kvm_available_flush_tlb_with_range(void)
{
	return kvm_x86_ops->tlb_remote_flush_with_range;
}

static void kvm_flush_remote_tlbs_with_range(struct kvm *kvm,
		struct kvm_tlb_range *range)
{
	int ret = -ENOTSUPP;

	if (range && kvm_x86_ops->tlb_remote_flush_with_range)
		ret = kvm_x86_ops->tlb_remote_flush_with_range(kvm, range);

	if (ret)
		kvm_flush_remote_tlbs(kvm);
}

static void kvm_flush_remote_tlbs_with_address(struct kvm *kvm,
		u64 start_gfn, u64 pages)
{
	struct kvm_tlb_range range;

	range.start_gfn = start_gfn;
	range.pages = pages;

	kvm_flush_remote_tlbs_with_range(kvm, &range);
}

void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask)
{
	BUG_ON((u64)(unsigned)access_mask != access_mask);
	BUG_ON((mmio_mask & mmio_value) != mmio_value);
	WARN_ON(mmio_value & (shadow_nonpresent_or_rsvd_mask << shadow_nonpresent_or_rsvd_mask_len));
	WARN_ON(mmio_value & shadow_nonpresent_or_rsvd_lower_gfn_mask);
	shadow_mmio_value = mmio_value | SPTE_MMIO_MASK;
	shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK;
	shadow_mmio_access_mask = access_mask;
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask);

static bool is_mmio_spte(u64 spte)
{
	return (spte & shadow_mmio_mask) == shadow_mmio_value;
}

static inline bool sp_ad_disabled(struct kvm_mmu_page *sp)
{
	return sp->role.ad_disabled;
}

static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu)
{
	/*
	 * When using the EPT page-modification log, the GPAs in the log
	 * would come from L2 rather than L1.  Therefore, we need to rely
	 * on write protection to record dirty pages.  This also bypasses
	 * PML, since writes now result in a vmexit.
	 */
	return vcpu->arch.mmu == &vcpu->arch.guest_mmu;
}

static inline bool spte_ad_enabled(u64 spte)
{
	MMU_WARN_ON(is_mmio_spte(spte));
	return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_DISABLED_MASK;
}

static inline bool spte_ad_need_write_protect(u64 spte)
{
	MMU_WARN_ON(is_mmio_spte(spte));
	return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_ENABLED_MASK;
}

static bool is_nx_huge_page_enabled(void)
{
	return READ_ONCE(nx_huge_pages);
}

static inline u64 spte_shadow_accessed_mask(u64 spte)
{
	MMU_WARN_ON(is_mmio_spte(spte));
	return spte_ad_enabled(spte) ? shadow_accessed_mask : 0;
}

static inline u64 spte_shadow_dirty_mask(u64 spte)
{
	MMU_WARN_ON(is_mmio_spte(spte));
	return spte_ad_enabled(spte) ? shadow_dirty_mask : 0;
}

static inline bool is_access_track_spte(u64 spte)
{
	return !spte_ad_enabled(spte) && (spte & shadow_acc_track_mask) == 0;
}

/*
 * Due to limited space in PTEs, the MMIO generation is a 18 bit subset of
 * the memslots generation and is derived as follows:
 *
 * Bits 0-8 of the MMIO generation are propagated to spte bits 3-11
 * Bits 9-17 of the MMIO generation are propagated to spte bits 54-62
 *
 * The KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS flag is intentionally not included in
 * the MMIO generation number, as doing so would require stealing a bit from
 * the "real" generation number and thus effectively halve the maximum number
 * of MMIO generations that can be handled before encountering a wrap (which
 * requires a full MMU zap).  The flag is instead explicitly queried when
 * checking for MMIO spte cache hits.
 */

#define MMIO_SPTE_GEN_LOW_START		3
#define MMIO_SPTE_GEN_LOW_END		11

#define MMIO_SPTE_GEN_HIGH_START	PT64_SECOND_AVAIL_BITS_SHIFT
#define MMIO_SPTE_GEN_HIGH_END		62

#define MMIO_SPTE_GEN_LOW_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \
						    MMIO_SPTE_GEN_LOW_START)
#define MMIO_SPTE_GEN_HIGH_MASK		GENMASK_ULL(MMIO_SPTE_GEN_HIGH_END, \
						    MMIO_SPTE_GEN_HIGH_START)

#define MMIO_SPTE_GEN_LOW_BITS		(MMIO_SPTE_GEN_LOW_END - MMIO_SPTE_GEN_LOW_START + 1)
#define MMIO_SPTE_GEN_HIGH_BITS		(MMIO_SPTE_GEN_HIGH_END - MMIO_SPTE_GEN_HIGH_START + 1)

/* remember to adjust the comment above as well if you change these */
static_assert(MMIO_SPTE_GEN_LOW_BITS == 9 && MMIO_SPTE_GEN_HIGH_BITS == 9);

#define MMIO_SPTE_GEN_LOW_SHIFT		(MMIO_SPTE_GEN_LOW_START - 0)
#define MMIO_SPTE_GEN_HIGH_SHIFT	(MMIO_SPTE_GEN_HIGH_START - MMIO_SPTE_GEN_LOW_BITS)

#define MMIO_SPTE_GEN_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_BITS + MMIO_SPTE_GEN_HIGH_BITS - 1, 0)

static u64 generation_mmio_spte_mask(u64 gen)
{
	u64 mask;

	WARN_ON(gen & ~MMIO_SPTE_GEN_MASK);
	BUILD_BUG_ON((MMIO_SPTE_GEN_HIGH_MASK | MMIO_SPTE_GEN_LOW_MASK) & SPTE_SPECIAL_MASK);

	mask = (gen << MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_SPTE_GEN_LOW_MASK;
	mask |= (gen << MMIO_SPTE_GEN_HIGH_SHIFT) & MMIO_SPTE_GEN_HIGH_MASK;
	return mask;
}

static u64 get_mmio_spte_generation(u64 spte)
{
	u64 gen;

	gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_SHIFT;
	gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_SHIFT;
	return gen;
}

static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn,
			   unsigned access)
{
	u64 gen = kvm_vcpu_memslots(vcpu)->generation & MMIO_SPTE_GEN_MASK;
	u64 mask = generation_mmio_spte_mask(gen);
	u64 gpa = gfn << PAGE_SHIFT;

	access &= shadow_mmio_access_mask;
	mask |= shadow_mmio_value | access;
	mask |= gpa | shadow_nonpresent_or_rsvd_mask;
	mask |= (gpa & shadow_nonpresent_or_rsvd_mask)
		<< shadow_nonpresent_or_rsvd_mask_len;

	trace_mark_mmio_spte(sptep, gfn, access, gen);
	mmu_spte_set(sptep, mask);
}

static gfn_t get_mmio_spte_gfn(u64 spte)
{
	u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask;

	gpa |= (spte >> shadow_nonpresent_or_rsvd_mask_len)
	       & shadow_nonpresent_or_rsvd_mask;

	return gpa >> PAGE_SHIFT;
}

static unsigned get_mmio_spte_access(u64 spte)
{
	return spte & shadow_mmio_access_mask;
}

static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
			  kvm_pfn_t pfn, unsigned access)
{
	if (unlikely(is_noslot_pfn(pfn))) {
		mark_mmio_spte(vcpu, sptep, gfn, access);
		return true;
	}

	return false;
}

static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte)
{
	u64 kvm_gen, spte_gen, gen;

	gen = kvm_vcpu_memslots(vcpu)->generation;
	if (unlikely(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS))
		return false;

	kvm_gen = gen & MMIO_SPTE_GEN_MASK;
	spte_gen = get_mmio_spte_generation(spte);

	trace_check_mmio_spte(spte, kvm_gen, spte_gen);
	return likely(kvm_gen == spte_gen);
}

/*
 * Sets the shadow PTE masks used by the MMU.
 *
 * Assumptions:
 *  - Setting either @accessed_mask or @dirty_mask requires setting both
 *  - At least one of @accessed_mask or @acc_track_mask must be set
 */
void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
		u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask,
		u64 acc_track_mask, u64 me_mask)
{
	BUG_ON(!dirty_mask != !accessed_mask);
	BUG_ON(!accessed_mask && !acc_track_mask);
	BUG_ON(acc_track_mask & SPTE_SPECIAL_MASK);

	shadow_user_mask = user_mask;
	shadow_accessed_mask = accessed_mask;
	shadow_dirty_mask = dirty_mask;
	shadow_nx_mask = nx_mask;
	shadow_x_mask = x_mask;
	shadow_present_mask = p_mask;
	shadow_acc_track_mask = acc_track_mask;
	shadow_me_mask = me_mask;
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);

static u8 kvm_get_shadow_phys_bits(void)
{
	/*
	 * boot_cpu_data.x86_phys_bits is reduced when MKTME or SME are detected
	 * in CPU detection code, but the processor treats those reduced bits as
	 * 'keyID' thus they are not reserved bits. Therefore KVM needs to look at
	 * the physical address bits reported by CPUID.
	 */
	if (likely(boot_cpu_data.extended_cpuid_level >= 0x80000008))
		return cpuid_eax(0x80000008) & 0xff;

	/*
	 * Quite weird to have VMX or SVM but not MAXPHYADDR; probably a VM with
	 * custom CPUID.  Proceed with whatever the kernel found since these features
	 * aren't virtualizable (SME/SEV also require CPUIDs higher than 0x80000008).
	 */
	return boot_cpu_data.x86_phys_bits;
}

static void kvm_mmu_reset_all_pte_masks(void)
{
	u8 low_phys_bits;

	shadow_user_mask = 0;
	shadow_accessed_mask = 0;
	shadow_dirty_mask = 0;
	shadow_nx_mask = 0;
	shadow_x_mask = 0;
	shadow_mmio_mask = 0;
	shadow_present_mask = 0;
	shadow_acc_track_mask = 0;

	shadow_phys_bits = kvm_get_shadow_phys_bits();

	/*
	 * If the CPU has 46 or less physical address bits, then set an
	 * appropriate mask to guard against L1TF attacks. Otherwise, it is
	 * assumed that the CPU is not vulnerable to L1TF.
	 *
	 * Some Intel CPUs address the L1 cache using more PA bits than are
	 * reported by CPUID. Use the PA width of the L1 cache when possible
	 * to achieve more effective mitigation, e.g. if system RAM overlaps
	 * the most significant bits of legal physical address space.
	 */
	shadow_nonpresent_or_rsvd_mask = 0;
	low_phys_bits = boot_cpu_data.x86_phys_bits;
	if (boot_cpu_has_bug(X86_BUG_L1TF) &&
	    !WARN_ON_ONCE(boot_cpu_data.x86_cache_bits >=
			  52 - shadow_nonpresent_or_rsvd_mask_len)) {
		low_phys_bits = boot_cpu_data.x86_cache_bits
			- shadow_nonpresent_or_rsvd_mask_len;
		shadow_nonpresent_or_rsvd_mask =
			rsvd_bits(low_phys_bits, boot_cpu_data.x86_cache_bits - 1);
	}

	shadow_nonpresent_or_rsvd_lower_gfn_mask =
		GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT);
}

static int is_cpuid_PSE36(void)
{
	return 1;
}

static int is_nx(struct kvm_vcpu *vcpu)
{
	return vcpu->arch.efer & EFER_NX;
}

static int is_shadow_present_pte(u64 pte)
{
	return (pte != 0) && !is_mmio_spte(pte);
}

static int is_large_pte(u64 pte)
{
	return pte & PT_PAGE_SIZE_MASK;
}

static int is_last_spte(u64 pte, int level)
{
	if (level == PT_PAGE_TABLE_LEVEL)
		return 1;
	if (is_large_pte(pte))
		return 1;
	return 0;
}

static bool is_executable_pte(u64 spte)
{
	return (spte & (shadow_x_mask | shadow_nx_mask)) == shadow_x_mask;
}

static kvm_pfn_t spte_to_pfn(u64 pte)
{
	return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
}

static gfn_t pse36_gfn_delta(u32 gpte)
{
	int shift = 32 - PT32_DIR_PSE36_SHIFT - PAGE_SHIFT;

	return (gpte & PT32_DIR_PSE36_MASK) << shift;
}

#ifdef CONFIG_X86_64
static void __set_spte(u64 *sptep, u64 spte)
{
	WRITE_ONCE(*sptep, spte);
}

static void __update_clear_spte_fast(u64 *sptep, u64 spte)
{
	WRITE_ONCE(*sptep, spte);
}

static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
{
	return xchg(sptep, spte);
}

static u64 __get_spte_lockless(u64 *sptep)
{
	return READ_ONCE(*sptep);
}
#else
union split_spte {
	struct {
		u32 spte_low;
		u32 spte_high;
	};
	u64 spte;
};

static void count_spte_clear(u64 *sptep, u64 spte)
{
	struct kvm_mmu_page *sp =  page_header(__pa(sptep));

	if (is_shadow_present_pte(spte))
		return;

	/* Ensure the spte is completely set before we increase the count */
	smp_wmb();
	sp->clear_spte_count++;
}

static void __set_spte(u64 *sptep, u64 spte)
{
	union split_spte *ssptep, sspte;

	ssptep = (union split_spte *)sptep;
	sspte = (union split_spte)spte;

	ssptep->spte_high = sspte.spte_high;

	/*
	 * If we map the spte from nonpresent to present, We should store
	 * the high bits firstly, then set present bit, so cpu can not
	 * fetch this spte while we are setting the spte.
	 */
	smp_wmb();

	WRITE_ONCE(ssptep->spte_low, sspte.spte_low);
}

static void __update_clear_spte_fast(u64 *sptep, u64 spte)
{
	union split_spte *ssptep, sspte;

	ssptep = (union split_spte *)sptep;
	sspte = (union split_spte)spte;

	WRITE_ONCE(ssptep->spte_low, sspte.spte_low);

	/*
	 * If we map the spte from present to nonpresent, we should clear
	 * present bit firstly to avoid vcpu fetch the old high bits.
	 */
	smp_wmb();

	ssptep->spte_high = sspte.spte_high;
	count_spte_clear(sptep, spte);
}

static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
{
	union split_spte *ssptep, sspte, orig;

	ssptep = (union split_spte *)sptep;
	sspte = (union split_spte)spte;

	/* xchg acts as a barrier before the setting of the high bits */
	orig.spte_low = xchg(&ssptep->spte_low, sspte.spte_low);
	orig.spte_high = ssptep->spte_high;
	ssptep->spte_high = sspte.spte_high;
	count_spte_clear(sptep, spte);

	return orig.spte;
}

/*
 * The idea using the light way get the spte on x86_32 guest is from
 * gup_get_pte (mm/gup.c).
 *
 * An spte tlb flush may be pending, because kvm_set_pte_rmapp
 * coalesces them and we are running out of the MMU lock.  Therefore
 * we need to protect against in-progress updates of the spte.
 *
 * Reading the spte while an update is in progress may get the old value
 * for the high part of the spte.  The race is fine for a present->non-present
 * change (because the high part of the spte is ignored for non-present spte),
 * but for a present->present change we must reread the spte.
 *
 * All such changes are done in two steps (present->non-present and
 * non-present->present), hence it is enough to count the number of
 * present->non-present updates: if it changed while reading the spte,
 * we might have hit the race.  This is done using clear_spte_count.
 */
static u64 __get_spte_lockless(u64 *sptep)
{
	struct kvm_mmu_page *sp =  page_header(__pa(sptep));
	union split_spte spte, *orig = (union split_spte *)sptep;
	int count;

retry:
	count = sp->clear_spte_count;
	smp_rmb();

	spte.spte_low = orig->spte_low;
	smp_rmb();

	spte.spte_high = orig->spte_high;
	smp_rmb();

	if (unlikely(spte.spte_low != orig->spte_low ||
	      count != sp->clear_spte_count))
		goto retry;

	return spte.spte;
}
#endif

static bool spte_can_locklessly_be_made_writable(u64 spte)
{
	return (spte & (SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE)) ==
		(SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE);
}

static bool spte_has_volatile_bits(u64 spte)
{
	if (!is_shadow_present_pte(spte))
		return false;

	/*
	 * Always atomically update spte if it can be updated
	 * out of mmu-lock, it can ensure dirty bit is not lost,
	 * also, it can help us to get a stable is_writable_pte()
	 * to ensure tlb flush is not missed.
	 */
	if (spte_can_locklessly_be_made_writable(spte) ||
	    is_access_track_spte(spte))
		return true;

	if (spte_ad_enabled(spte)) {
		if ((spte & shadow_accessed_mask) == 0 ||
	    	    (is_writable_pte(spte) && (spte & shadow_dirty_mask) == 0))
			return true;
	}

	return false;
}

static bool is_accessed_spte(u64 spte)
{
	u64 accessed_mask = spte_shadow_accessed_mask(spte);

	return accessed_mask ? spte & accessed_mask
			     : !is_access_track_spte(spte);
}

static bool is_dirty_spte(u64 spte)
{
	u64 dirty_mask = spte_shadow_dirty_mask(spte);

	return dirty_mask ? spte & dirty_mask : spte & PT_WRITABLE_MASK;
}

/* Rules for using mmu_spte_set:
 * Set the sptep from nonpresent to present.
 * Note: the sptep being assigned *must* be either not present
 * or in a state where the hardware will not attempt to update
 * the spte.
 */
static void mmu_spte_set(u64 *sptep, u64 new_spte)
{
	WARN_ON(is_shadow_present_pte(*sptep));
	__set_spte(sptep, new_spte);
}

/*
 * Update the SPTE (excluding the PFN), but do not track changes in its
 * accessed/dirty status.
 */
static u64 mmu_spte_update_no_track(u64 *sptep, u64 new_spte)
{
	u64 old_spte = *sptep;

	WARN_ON(!is_shadow_present_pte(new_spte));

	if (!is_shadow_present_pte(old_spte)) {
		mmu_spte_set(sptep, new_spte);
		return old_spte;
	}

	if (!spte_has_volatile_bits(old_spte))
		__update_clear_spte_fast(sptep, new_spte);
	else
		old_spte = __update_clear_spte_slow(sptep, new_spte);

	WARN_ON(spte_to_pfn(old_spte) != spte_to_pfn(new_spte));

	return old_spte;
}

/* Rules for using mmu_spte_update:
 * Update the state bits, it means the mapped pfn is not changed.
 *
 * Whenever we overwrite a writable spte with a read-only one we
 * should flush remote TLBs. Otherwise rmap_write_protect
 * will find a read-only spte, even though the writable spte
 * might be cached on a CPU's TLB, the return value indicates this
 * case.
 *
 * Returns true if the TLB needs to be flushed
 */
static bool mmu_spte_update(u64 *sptep, u64 new_spte)
{
	bool flush = false;
	u64 old_spte = mmu_spte_update_no_track(sptep, new_spte);

	if (!is_shadow_present_pte(old_spte))
		return false;

	/*
	 * For the spte updated out of mmu-lock is safe, since
	 * we always atomically update it, see the comments in
	 * spte_has_volatile_bits().
	 */
	if (spte_can_locklessly_be_made_writable(old_spte) &&
	      !is_writable_pte(new_spte))
		flush = true;

	/*
	 * Flush TLB when accessed/dirty states are changed in the page tables,
	 * to guarantee consistency between TLB and page tables.
	 */

	if (is_accessed_spte(old_spte) && !is_accessed_spte(new_spte)) {
		flush = true;
		kvm_set_pfn_accessed(spte_to_pfn(old_spte));
	}

	if (is_dirty_spte(old_spte) && !is_dirty_spte(new_spte)) {
		flush = true;
		kvm_set_pfn_dirty(spte_to_pfn(old_spte));
	}

	return flush;
}

/*
 * Rules for using mmu_spte_clear_track_bits:
 * It sets the sptep from present to nonpresent, and track the
 * state bits, it is used to clear the last level sptep.
 * Returns non-zero if the PTE was previously valid.
 */
static int mmu_spte_clear_track_bits(u64 *sptep)
{
	kvm_pfn_t pfn;
	u64 old_spte = *sptep;

	if (!spte_has_volatile_bits(old_spte))
		__update_clear_spte_fast(sptep, 0ull);
	else
		old_spte = __update_clear_spte_slow(sptep, 0ull);

	if (!is_shadow_present_pte(old_spte))
		return 0;

	pfn = spte_to_pfn(old_spte);

	/*
	 * KVM does not hold the refcount of the page used by
	 * kvm mmu, before reclaiming the page, we should
	 * unmap it from mmu first.
	 */
	WARN_ON(!kvm_is_reserved_pfn(pfn) && !page_count(pfn_to_page(pfn)));

	if (is_accessed_spte(old_spte))
		kvm_set_pfn_accessed(pfn);

	if (is_dirty_spte(old_spte))
		kvm_set_pfn_dirty(pfn);

	return 1;
}

/*
 * Rules for using mmu_spte_clear_no_track:
 * Directly clear spte without caring the state bits of sptep,
 * it is used to set the upper level spte.
 */
static void mmu_spte_clear_no_track(u64 *sptep)
{
	__update_clear_spte_fast(sptep, 0ull);
}

static u64 mmu_spte_get_lockless(u64 *sptep)
{
	return __get_spte_lockless(sptep);
}

static u64 mark_spte_for_access_track(u64 spte)
{
	if (spte_ad_enabled(spte))
		return spte & ~shadow_accessed_mask;

	if (is_access_track_spte(spte))
		return spte;

	/*
	 * Making an Access Tracking PTE will result in removal of write access
	 * from the PTE. So, verify that we will be able to restore the write
	 * access in the fast page fault path later on.
	 */
	WARN_ONCE((spte & PT_WRITABLE_MASK) &&
		  !spte_can_locklessly_be_made_writable(spte),
		  "kvm: Writable SPTE is not locklessly dirty-trackable\n");

	WARN_ONCE(spte & (shadow_acc_track_saved_bits_mask <<
			  shadow_acc_track_saved_bits_shift),
		  "kvm: Access Tracking saved bit locations are not zero\n");

	spte |= (spte & shadow_acc_track_saved_bits_mask) <<
		shadow_acc_track_saved_bits_shift;
	spte &= ~shadow_acc_track_mask;

	return spte;
}

/* Restore an acc-track PTE back to a regular PTE */
static u64 restore_acc_track_spte(u64 spte)
{
	u64 new_spte = spte;
	u64 saved_bits = (spte >> shadow_acc_track_saved_bits_shift)
			 & shadow_acc_track_saved_bits_mask;

	WARN_ON_ONCE(spte_ad_enabled(spte));
	WARN_ON_ONCE(!is_access_track_spte(spte));

	new_spte &= ~shadow_acc_track_mask;
	new_spte &= ~(shadow_acc_track_saved_bits_mask <<
		      shadow_acc_track_saved_bits_shift);
	new_spte |= saved_bits;

	return new_spte;
}

/* Returns the Accessed status of the PTE and resets it at the same time. */
static bool mmu_spte_age(u64 *sptep)
{
	u64 spte = mmu_spte_get_lockless(sptep);

	if (!is_accessed_spte(spte))
		return false;

	if (spte_ad_enabled(spte)) {
		clear_bit((ffs(shadow_accessed_mask) - 1),
			  (unsigned long *)sptep);
	} else {
		/*
		 * Capture the dirty status of the page, so that it doesn't get
		 * lost when the SPTE is marked for access tracking.
		 */
		if (is_writable_pte(spte))
			kvm_set_pfn_dirty(spte_to_pfn(spte));

		spte = mark_spte_for_access_track(spte);
		mmu_spte_update_no_track(sptep, spte);
	}

	return true;
}

static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu)
{
	/*
	 * Prevent page table teardown by making any free-er wait during
	 * kvm_flush_remote_tlbs() IPI to all active vcpus.
	 */
	local_irq_disable();

	/*
	 * Make sure a following spte read is not reordered ahead of the write
	 * to vcpu->mode.
	 */
	smp_store_mb(vcpu->mode, READING_SHADOW_PAGE_TABLES);
}

static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu)
{
	/*
	 * Make sure the write to vcpu->mode is not reordered in front of
	 * reads to sptes.  If it does, kvm_mmu_commit_zap_page() can see us
	 * OUTSIDE_GUEST_MODE and proceed to free the shadow page table.
	 */
	smp_store_release(&vcpu->mode, OUTSIDE_GUEST_MODE);
	local_irq_enable();
}

static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
				  struct kmem_cache *base_cache, int min)
{
	void *obj;

	if (cache->nobjs >= min)
		return 0;
	while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
		obj = kmem_cache_zalloc(base_cache, GFP_KERNEL_ACCOUNT);
		if (!obj)
			return cache->nobjs >= min ? 0 : -ENOMEM;
		cache->objects[cache->nobjs++] = obj;
	}
	return 0;
}

static int mmu_memory_cache_free_objects(struct kvm_mmu_memory_cache *cache)
{
	return cache->nobjs;
}

static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc,
				  struct kmem_cache *cache)
{
	while (mc->nobjs)
		kmem_cache_free(cache, mc->objects[--mc->nobjs]);
}

static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache,
				       int min)
{
	void *page;

	if (cache->nobjs >= min)
		return 0;
	while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
		page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT);
		if (!page)
			return cache->nobjs >= min ? 0 : -ENOMEM;
		cache->objects[cache->nobjs++] = page;
	}
	return 0;
}

static void mmu_free_memory_cache_page(struct kvm_mmu_memory_cache *mc)
{
	while (mc->nobjs)
		free_page((unsigned long)mc->objects[--mc->nobjs]);
}

static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu)
{
	int r;

	r = mmu_topup_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache,
				   pte_list_desc_cache, 8 + PTE_PREFETCH_NUM);
	if (r)
		goto out;
	r = mmu_topup_memory_cache_page(&vcpu->arch.mmu_page_cache, 8);
	if (r)
		goto out;
	r = mmu_topup_memory_cache(&vcpu->arch.mmu_page_header_cache,
				   mmu_page_header_cache, 4);
out:
	return r;
}

static void mmu_free_memory_caches(struct kvm_vcpu *vcpu)
{
	mmu_free_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache,
				pte_list_desc_cache);
	mmu_free_memory_cache_page(&vcpu->arch.mmu_page_cache);
	mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache,
				mmu_page_header_cache);
}

static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
{
	void *p;

	BUG_ON(!mc->nobjs);
	p = mc->objects[--mc->nobjs];
	return p;
}

static struct pte_list_desc *mmu_alloc_pte_list_desc(struct kvm_vcpu *vcpu)
{
	return mmu_memory_cache_alloc(&vcpu->arch.mmu_pte_list_desc_cache);
}

static void mmu_free_pte_list_desc(struct pte_list_desc *pte_list_desc)
{
	kmem_cache_free(pte_list_desc_cache, pte_list_desc);
}

static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index)
{
	if (!sp->role.direct)
		return sp->gfns[index];

	return sp->gfn + (index << ((sp->role.level - 1) * PT64_LEVEL_BITS));
}

static void kvm_mmu_page_set_gfn(struct kvm_mmu_page *sp, int index, gfn_t gfn)
{
	if (!sp->role.direct) {
		sp->gfns[index] = gfn;
		return;
	}

	if (WARN_ON(gfn != kvm_mmu_page_get_gfn(sp, index)))
		pr_err_ratelimited("gfn mismatch under direct page %llx "
				   "(expected %llx, got %llx)\n",
				   sp->gfn,
				   kvm_mmu_page_get_gfn(sp, index), gfn);
}

/*
 * Return the pointer to the large page information for a given gfn,
 * handling slots that are not large page aligned.
 */
static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn,
					      struct kvm_memory_slot *slot,
					      int level)
{
	unsigned long idx;

	idx = gfn_to_index(gfn, slot->base_gfn, level);
	return &slot->arch.lpage_info[level - 2][idx];
}

static void update_gfn_disallow_lpage_count(struct kvm_memory_slot *slot,
					    gfn_t gfn, int count)
{
	struct kvm_lpage_info *linfo;
	int i;

	for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
		linfo = lpage_info_slot(gfn, slot, i);
		linfo->disallow_lpage += count;
		WARN_ON(linfo->disallow_lpage < 0);
	}
}

void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn)
{
	update_gfn_disallow_lpage_count(slot, gfn, 1);
}

void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn)
{
	update_gfn_disallow_lpage_count(slot, gfn, -1);
}

static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
{
	struct kvm_memslots *slots;
	struct kvm_memory_slot *slot;
	gfn_t gfn;

	kvm->arch.indirect_shadow_pages++;
	gfn = sp->gfn;
	slots = kvm_memslots_for_spte_role(kvm, sp->role);
	slot = __gfn_to_memslot(slots, gfn);

	/* the non-leaf shadow pages are keeping readonly. */
	if (sp->role.level > PT_PAGE_TABLE_LEVEL)
		return kvm_slot_page_track_add_page(kvm, slot, gfn,
						    KVM_PAGE_TRACK_WRITE);

	kvm_mmu_gfn_disallow_lpage(slot, gfn);
}

static void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
	if (sp->lpage_disallowed)
		return;

	++kvm->stat.nx_lpage_splits;
	list_add_tail(&sp->lpage_disallowed_link,
		      &kvm->arch.lpage_disallowed_mmu_pages);
	sp->lpage_disallowed = true;
}

static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
{
	struct kvm_memslots *slots;
	struct kvm_memory_slot *slot;
	gfn_t gfn;

	kvm->arch.indirect_shadow_pages--;
	gfn = sp->gfn;
	slots = kvm_memslots_for_spte_role(kvm, sp->role);
	slot = __gfn_to_memslot(slots, gfn);
	if (sp->role.level > PT_PAGE_TABLE_LEVEL)
		return kvm_slot_page_track_remove_page(kvm, slot, gfn,
						       KVM_PAGE_TRACK_WRITE);

	kvm_mmu_gfn_allow_lpage(slot, gfn);
}

static void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
	--kvm->stat.nx_lpage_splits;
	sp->lpage_disallowed = false;
	list_del(&sp->lpage_disallowed_link);
}

static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level,
					  struct kvm_memory_slot *slot)
{
	struct kvm_lpage_info *linfo;

	if (slot) {
		linfo = lpage_info_slot(gfn, slot, level);
		return !!linfo->disallow_lpage;
	}

	return true;
}

static bool mmu_gfn_lpage_is_disallowed(struct kvm_vcpu *vcpu, gfn_t gfn,
					int level)
{
	struct kvm_memory_slot *slot;

	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
	return __mmu_gfn_lpage_is_disallowed(gfn, level, slot);
}

static int host_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn)
{
	unsigned long page_size;
	int i, ret = 0;

	page_size = kvm_host_page_size(vcpu, gfn);

	for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
		if (page_size >= KVM_HPAGE_SIZE(i))
			ret = i;
		else
			break;
	}

	return ret;
}

static inline bool memslot_valid_for_gpte(struct kvm_memory_slot *slot,
					  bool no_dirty_log)
{
	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
		return false;
	if (no_dirty_log && slot->dirty_bitmap)
		return false;

	return true;
}

static struct kvm_memory_slot *
gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
			    bool no_dirty_log)
{
	struct kvm_memory_slot *slot;

	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
	if (!memslot_valid_for_gpte(slot, no_dirty_log))
		slot = NULL;

	return slot;
}

static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn,
			 bool *force_pt_level)
{
	int host_level, level, max_level;
	struct kvm_memory_slot *slot;

	if (unlikely(*force_pt_level))
		return PT_PAGE_TABLE_LEVEL;

	slot = kvm_vcpu_gfn_to_memslot(vcpu, large_gfn);
	*force_pt_level = !memslot_valid_for_gpte(slot, true);
	if (unlikely(*force_pt_level))
		return PT_PAGE_TABLE_LEVEL;

	host_level = host_mapping_level(vcpu, large_gfn);

	if (host_level == PT_PAGE_TABLE_LEVEL)
		return host_level;

	max_level = min(kvm_x86_ops->get_lpage_level(), host_level);

	for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level)
		if (__mmu_gfn_lpage_is_disallowed(large_gfn, level, slot))
			break;

	return level - 1;
}

/*
 * About rmap_head encoding:
 *
 * If the bit zero of rmap_head->val is clear, then it points to the only spte
 * in this rmap chain. Otherwise, (rmap_head->val & ~1) points to a struct
 * pte_list_desc containing more mappings.
 */

/*
 * Returns the number of pointers in the rmap chain, not counting the new one.
 */
static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte,
			struct kvm_rmap_head *rmap_head)
{
	struct pte_list_desc *desc;
	int i, count = 0;

	if (!rmap_head->val) {
		rmap_printk("pte_list_add: %p %llx 0->1\n", spte, *spte);
		rmap_head->val = (unsigned long)spte;
	} else if (!(rmap_head->val & 1)) {
		rmap_printk("pte_list_add: %p %llx 1->many\n", spte, *spte);
		desc = mmu_alloc_pte_list_desc(vcpu);
		desc->sptes[0] = (u64 *)rmap_head->val;
		desc->sptes[1] = spte;
		rmap_head->val = (unsigned long)desc | 1;
		++count;
	} else {
		rmap_printk("pte_list_add: %p %llx many->many\n", spte, *spte);
		desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
		while (desc->sptes[PTE_LIST_EXT-1] && desc->more) {
			desc = desc->more;
			count += PTE_LIST_EXT;
		}
		if (desc->sptes[PTE_LIST_EXT-1]) {
			desc->more = mmu_alloc_pte_list_desc(vcpu);
			desc = desc->more;
		}
		for (i = 0; desc->sptes[i]; ++i)
			++count;
		desc->sptes[i] = spte;
	}
	return count;
}

static void
pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head,
			   struct pte_list_desc *desc, int i,
			   struct pte_list_desc *prev_desc)
{
	int j;

	for (j = PTE_LIST_EXT - 1; !desc->sptes[j] && j > i; --j)
		;
	desc->sptes[i] = desc->sptes[j];
	desc->sptes[j] = NULL;
	if (j != 0)
		return;
	if (!prev_desc && !desc->more)
		rmap_head->val = (unsigned long)desc->sptes[0];
	else
		if (prev_desc)
			prev_desc->more = desc->more;
		else
			rmap_head->val = (unsigned long)desc->more | 1;
	mmu_free_pte_list_desc(desc);
}

static void __pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head)
{
	struct pte_list_desc *desc;
	struct pte_list_desc *prev_desc;
	int i;

	if (!rmap_head->val) {
		pr_err("%s: %p 0->BUG\n", __func__, spte);
		BUG();
	} else if (!(rmap_head->val & 1)) {
		rmap_printk("%s:  %p 1->0\n", __func__, spte);
		if ((u64 *)rmap_head->val != spte) {
			pr_err("%s:  %p 1->BUG\n", __func__, spte);
			BUG();
		}
		rmap_head->val = 0;
	} else {
		rmap_printk("%s:  %p many->many\n", __func__, spte);
		desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
		prev_desc = NULL;
		while (desc) {
			for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i) {
				if (desc->sptes[i] == spte) {
					pte_list_desc_remove_entry(rmap_head,
							desc, i, prev_desc);
					return;
				}
			}
			prev_desc = desc;
			desc = desc->more;
		}
		pr_err("%s: %p many->many\n", __func__, spte);
		BUG();
	}
}

static void pte_list_remove(struct kvm_rmap_head *rmap_head, u64 *sptep)
{
	mmu_spte_clear_track_bits(sptep);
	__pte_list_remove(sptep, rmap_head);
}

static struct kvm_rmap_head *__gfn_to_rmap(gfn_t gfn, int level,
					   struct kvm_memory_slot *slot)
{
	unsigned long idx;

	idx = gfn_to_index(gfn, slot->base_gfn, level);
	return &slot->arch.rmap[level - PT_PAGE_TABLE_LEVEL][idx];
}

static struct kvm_rmap_head *gfn_to_rmap(struct kvm *kvm, gfn_t gfn,
					 struct kvm_mmu_page *sp)
{
	struct kvm_memslots *slots;
	struct kvm_memory_slot *slot;

	slots = kvm_memslots_for_spte_role(kvm, sp->role);
	slot = __gfn_to_memslot(slots, gfn);
	return __gfn_to_rmap(gfn, sp->role.level, slot);
}

static bool rmap_can_add(struct kvm_vcpu *vcpu)
{
	struct kvm_mmu_memory_cache *cache;

	cache = &vcpu->arch.mmu_pte_list_desc_cache;
	return mmu_memory_cache_free_objects(cache);
}

static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
{
	struct kvm_mmu_page *sp;
	struct kvm_rmap_head *rmap_head;

	sp = page_header(__pa(spte));
	kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn);
	rmap_head = gfn_to_rmap(vcpu->kvm, gfn, sp);
	return pte_list_add(vcpu, spte, rmap_head);
}

static void rmap_remove(struct kvm *kvm, u64 *spte)
{
	struct kvm_mmu_page *sp;
	gfn_t gfn;
	struct kvm_rmap_head *rmap_head;

	sp = page_header(__pa(spte));
	gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt);
	rmap_head = gfn_to_rmap(kvm, gfn, sp);
	__pte_list_remove(spte, rmap_head);
}

/*
 * Used by the following functions to iterate through the sptes linked by a
 * rmap.  All fields are private and not assumed to be used outside.
 */
struct rmap_iterator {
	/* private fields */
	struct pte_list_desc *desc;	/* holds the sptep if not NULL */
	int pos;			/* index of the sptep */
};

/*
 * Iteration must be started by this function.  This should also be used after
 * removing/dropping sptes from the rmap link because in such cases the
 * information in the itererator may not be valid.
 *
 * Returns sptep if found, NULL otherwise.
 */
static u64 *rmap_get_first(struct kvm_rmap_head *rmap_head,
			   struct rmap_iterator *iter)
{
	u64 *sptep;

	if (!rmap_head->val)
		return NULL;

	if (!(rmap_head->val & 1)) {
		iter->desc = NULL;
		sptep = (u64 *)rmap_head->val;
		goto out;
	}

	iter->desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
	iter->pos = 0;
	sptep = iter->desc->sptes[iter->pos];
out:
	BUG_ON(!is_shadow_present_pte(*sptep));
	return sptep;
}

/*
 * Must be used with a valid iterator: e.g. after rmap_get_first().
 *
 * Returns sptep if found, NULL otherwise.
 */
static u64 *rmap_get_next(struct rmap_iterator *iter)
{
	u64 *sptep;

	if (iter->desc) {
		if (iter->pos < PTE_LIST_EXT - 1) {
			++iter->pos;
			sptep = iter->desc->sptes[iter->pos];
			if (sptep)
				goto out;
		}

		iter->desc = iter->desc->more;

		if (iter->desc) {
			iter->pos = 0;
			/* desc->sptes[0] cannot be NULL */
			sptep = iter->desc->sptes[iter->pos];
			goto out;
		}
	}

	return NULL;
out:
	BUG_ON(!is_shadow_present_pte(*sptep));
	return sptep;
}

#define for_each_rmap_spte(_rmap_head_, _iter_, _spte_)			\
	for (_spte_ = rmap_get_first(_rmap_head_, _iter_);		\
	     _spte_; _spte_ = rmap_get_next(_iter_))

static void drop_spte(struct kvm *kvm, u64 *sptep)
{
	if (mmu_spte_clear_track_bits(sptep))
		rmap_remove(kvm, sptep);
}


static bool __drop_large_spte(struct kvm *kvm, u64 *sptep)
{
	if (is_large_pte(*sptep)) {
		WARN_ON(page_header(__pa(sptep))->role.level ==
			PT_PAGE_TABLE_LEVEL);
		drop_spte(kvm, sptep);
		--kvm->stat.lpages;
		return true;
	}

	return false;
}

static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep)
{
	if (__drop_large_spte(vcpu->kvm, sptep)) {
		struct kvm_mmu_page *sp = page_header(__pa(sptep));

		kvm_flush_remote_tlbs_with_address(vcpu->kvm, sp->gfn,
			KVM_PAGES_PER_HPAGE(sp->role.level));
	}
}

/*
 * Write-protect on the specified @sptep, @pt_protect indicates whether
 * spte write-protection is caused by protecting shadow page table.
 *
 * Note: write protection is difference between dirty logging and spte
 * protection:
 * - for dirty logging, the spte can be set to writable at anytime if
 *   its dirty bitmap is properly set.
 * - for spte protection, the spte can be writable only after unsync-ing
 *   shadow page.
 *
 * Return true if tlb need be flushed.
 */
static bool spte_write_protect(u64 *sptep, bool pt_protect)
{
	u64 spte = *sptep;

	if (!is_writable_pte(spte) &&
	      !(pt_protect && spte_can_locklessly_be_made_writable(spte)))
		return false;

	rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep);

	if (pt_protect)
		spte &= ~SPTE_MMU_WRITEABLE;
	spte = spte & ~PT_WRITABLE_MASK;

	return mmu_spte_update(sptep, spte);
}

static bool __rmap_write_protect(struct kvm *kvm,
				 struct kvm_rmap_head *rmap_head,
				 bool pt_protect)
{
	u64 *sptep;
	struct rmap_iterator iter;
	bool flush = false;

	for_each_rmap_spte(rmap_head, &iter, sptep)
		flush |= spte_write_protect(sptep, pt_protect);

	return flush;
}

static bool spte_clear_dirty(u64 *sptep)
{
	u64 spte = *sptep;

	rmap_printk("rmap_clear_dirty: spte %p %llx\n", sptep, *sptep);

	MMU_WARN_ON(!spte_ad_enabled(spte));
	spte &= ~shadow_dirty_mask;
	return mmu_spte_update(sptep, spte);
}

static bool spte_wrprot_for_clear_dirty(u64 *sptep)
{
	bool was_writable = test_and_clear_bit(PT_WRITABLE_SHIFT,
					       (unsigned long *)sptep);
	if (was_writable && !spte_ad_enabled(*sptep))
		kvm_set_pfn_dirty(spte_to_pfn(*sptep));

	return was_writable;
}

/*
 * Gets the GFN ready for another round of dirty logging by clearing the
 *	- D bit on ad-enabled SPTEs, and
 *	- W bit on ad-disabled SPTEs.
 * Returns true iff any D or W bits were cleared.
 */
static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
{
	u64 *sptep;
	struct rmap_iterator iter;
	bool flush = false;

	for_each_rmap_spte(rmap_head, &iter, sptep)
		if (spte_ad_need_write_protect(*sptep))
			flush |= spte_wrprot_for_clear_dirty(sptep);
		else
			flush |= spte_clear_dirty(sptep);

	return flush;
}

static bool spte_set_dirty(u64 *sptep)
{
	u64 spte = *sptep;

	rmap_printk("rmap_set_dirty: spte %p %llx\n", sptep, *sptep);

	/*
	 * Similar to the !kvm_x86_ops->slot_disable_log_dirty case,
	 * do not bother adding back write access to pages marked
	 * SPTE_AD_WRPROT_ONLY_MASK.
	 */
	spte |= shadow_dirty_mask;

	return mmu_spte_update(sptep, spte);
}

static bool __rmap_set_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
{
	u64 *sptep;
	struct rmap_iterator iter;
	bool flush = false;

	for_each_rmap_spte(rmap_head, &iter, sptep)
		if (spte_ad_enabled(*sptep))
			flush |= spte_set_dirty(sptep);

	return flush;
}

/**
 * kvm_mmu_write_protect_pt_masked - write protect selected PT level pages
 * @kvm: kvm instance
 * @slot: slot to protect
 * @gfn_offset: start of the BITS_PER_LONG pages we care about
 * @mask: indicates which pages we should protect
 *
 * Used when we do not need to care about huge page mappings: e.g. during dirty
 * logging we do not have any such mappings.
 */
static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
				     struct kvm_memory_slot *slot,
				     gfn_t gfn_offset, unsigned long mask)
{
	struct kvm_rmap_head *rmap_head;

	while (mask) {
		rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
					  PT_PAGE_TABLE_LEVEL, slot);
		__rmap_write_protect(kvm, rmap_head, false);

		/* clear the first set bit */
		mask &= mask - 1;
	}
}

/**
 * kvm_mmu_clear_dirty_pt_masked - clear MMU D-bit for PT level pages, or write
 * protect the page if the D-bit isn't supported.
 * @kvm: kvm instance
 * @slot: slot to clear D-bit
 * @gfn_offset: start of the BITS_PER_LONG pages we care about
 * @mask: indicates which pages we should clear D-bit
 *
 * Used for PML to re-log the dirty GPAs after userspace querying dirty_bitmap.
 */
void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
				     struct kvm_memory_slot *slot,
				     gfn_t gfn_offset, unsigned long mask)
{
	struct kvm_rmap_head *rmap_head;

	while (mask) {
		rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
					  PT_PAGE_TABLE_LEVEL, slot);
		__rmap_clear_dirty(kvm, rmap_head);

		/* clear the first set bit */
		mask &= mask - 1;
	}
}
EXPORT_SYMBOL_GPL(kvm_mmu_clear_dirty_pt_masked);

/**
 * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected
 * PT level pages.
 *
 * It calls kvm_mmu_write_protect_pt_masked to write protect selected pages to
 * enable dirty logging for them.
 *
 * Used when we do not need to care about huge page mappings: e.g. during dirty
 * logging we do not have any such mappings.
 */
void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
				struct kvm_memory_slot *slot,
				gfn_t gfn_offset, unsigned long mask)
{
	if (kvm_x86_ops->enable_log_dirty_pt_masked)
		kvm_x86_ops->enable_log_dirty_pt_masked(kvm, slot, gfn_offset,
				mask);
	else
		kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
}

/**
 * kvm_arch_write_log_dirty - emulate dirty page logging
 * @vcpu: Guest mode vcpu
 *
 * Emulate arch specific page modification logging for the
 * nested hypervisor
 */
int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa)
{
	if (kvm_x86_ops->write_log_dirty)
		return kvm_x86_ops->write_log_dirty(vcpu, l2_gpa);

	return 0;
}

bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
				    struct kvm_memory_slot *slot, u64 gfn)
{
	struct kvm_rmap_head *rmap_head;
	int i;
	bool write_protected = false;

	for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
		rmap_head = __gfn_to_rmap(gfn, i, slot);
		write_protected |= __rmap_write_protect(kvm, rmap_head, true);
	}

	return write_protected;
}

static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn)
{
	struct kvm_memory_slot *slot;

	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
	return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn);
}

static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
{
	u64 *sptep;
	struct rmap_iterator iter;
	bool flush = false;

	while ((sptep = rmap_get_first(rmap_head, &iter))) {
		rmap_printk("%s: spte %p %llx.\n", __func__, sptep, *sptep);

		pte_list_remove(rmap_head, sptep);
		flush = true;
	}

	return flush;
}

static int kvm_unmap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
			   struct kvm_memory_slot *slot, gfn_t gfn, int level,
			   unsigned long data)
{
	return kvm_zap_rmapp(kvm, rmap_head);
}

static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
			     struct kvm_memory_slot *slot, gfn_t gfn, int level,
			     unsigned long data)
{
	u64 *sptep;
	struct rmap_iterator iter;
	int need_flush = 0;
	u64 new_spte;
	pte_t *ptep = (pte_t *)data;
	kvm_pfn_t new_pfn;

	WARN_ON(pte_huge(*ptep));
	new_pfn = pte_pfn(*ptep);

restart:
	for_each_rmap_spte(rmap_head, &iter, sptep) {
		rmap_printk("kvm_set_pte_rmapp: spte %p %llx gfn %llx (%d)\n",
			    sptep, *sptep, gfn, level);

		need_flush = 1;

		if (pte_write(*ptep)) {
			pte_list_remove(rmap_head, sptep);
			goto restart;
		} else {
			new_spte = *sptep & ~PT64_BASE_ADDR_MASK;
			new_spte |= (u64)new_pfn << PAGE_SHIFT;

			new_spte &= ~PT_WRITABLE_MASK;
			new_spte &= ~SPTE_HOST_WRITEABLE;

			new_spte = mark_spte_for_access_track(new_spte);

			mmu_spte_clear_track_bits(sptep);
			mmu_spte_set(sptep, new_spte);
		}
	}

	if (need_flush && kvm_available_flush_tlb_with_range()) {
		kvm_flush_remote_tlbs_with_address(kvm, gfn, 1);
		return 0;
	}

	return need_flush;
}

struct slot_rmap_walk_iterator {
	/* input fields. */
	struct kvm_memory_slot *slot;
	gfn_t start_gfn;
	gfn_t end_gfn;
	int start_level;
	int end_level;

	/* output fields. */
	gfn_t gfn;
	struct kvm_rmap_head *rmap;
	int level;

	/* private field. */
	struct kvm_rmap_head *end_rmap;
};

static void
rmap_walk_init_level(struct slot_rmap_walk_iterator *iterator, int level)
{
	iterator->level = level;
	iterator->gfn = iterator->start_gfn;
	iterator->rmap = __gfn_to_rmap(iterator->gfn, level, iterator->slot);
	iterator->end_rmap = __gfn_to_rmap(iterator->end_gfn, level,
					   iterator->slot);
}

static void
slot_rmap_walk_init(struct slot_rmap_walk_iterator *iterator,
		    struct kvm_memory_slot *slot, int start_level,
		    int end_level, gfn_t start_gfn, gfn_t end_gfn)
{
	iterator->slot = slot;
	iterator->start_level = start_level;
	iterator->end_level = end_level;
	iterator->start_gfn = start_gfn;
	iterator->end_gfn = end_gfn;

	rmap_walk_init_level(iterator, iterator->start_level);
}

static bool slot_rmap_walk_okay(struct slot_rmap_walk_iterator *iterator)
{
	return !!iterator->rmap;
}

static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator)
{
	if (++iterator->rmap <= iterator->end_rmap) {
		iterator->gfn += (1UL << KVM_HPAGE_GFN_SHIFT(iterator->level));
		return;
	}

	if (++iterator->level > iterator->end_level) {
		iterator->rmap = NULL;
		return;
	}

	rmap_walk_init_level(iterator, iterator->level);
}

#define for_each_slot_rmap_range(_slot_, _start_level_, _end_level_,	\
	   _start_gfn, _end_gfn, _iter_)				\
	for (slot_rmap_walk_init(_iter_, _slot_, _start_level_,		\
				 _end_level_, _start_gfn, _end_gfn);	\
	     slot_rmap_walk_okay(_iter_);				\
	     slot_rmap_walk_next(_iter_))

static int kvm_handle_hva_range(struct kvm *kvm,
				unsigned long start,
				unsigned long end,
				unsigned long data,
				int (*handler)(struct kvm *kvm,
					       struct kvm_rmap_head *rmap_head,
					       struct kvm_memory_slot *slot,
					       gfn_t gfn,
					       int level,
					       unsigned long data))
{
	struct kvm_memslots *slots;
	struct kvm_memory_slot *memslot;
	struct slot_rmap_walk_iterator iterator;
	int ret = 0;
	int i;

	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
		slots = __kvm_memslots(kvm, i);
		kvm_for_each_memslot(memslot, slots) {
			unsigned long hva_start, hva_end;
			gfn_t gfn_start, gfn_end;

			hva_start = max(start, memslot->userspace_addr);
			hva_end = min(end, memslot->userspace_addr +
				      (memslot->npages << PAGE_SHIFT));
			if (hva_start >= hva_end)
				continue;
			/*
			 * {gfn(page) | page intersects with [hva_start, hva_end)} =
			 * {gfn_start, gfn_start+1, ..., gfn_end-1}.
			 */
			gfn_start = hva_to_gfn_memslot(hva_start, memslot);
			gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot);

			for_each_slot_rmap_range(memslot, PT_PAGE_TABLE_LEVEL,
						 PT_MAX_HUGEPAGE_LEVEL,
						 gfn_start, gfn_end - 1,
						 &iterator)
				ret |= handler(kvm, iterator.rmap, memslot,
					       iterator.gfn, iterator.level, data);
		}
	}

	return ret;
}

static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
			  unsigned long data,
			  int (*handler)(struct kvm *kvm,
					 struct kvm_rmap_head *rmap_head,
					 struct kvm_memory_slot *slot,
					 gfn_t gfn, int level,
					 unsigned long data))
{
	return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler);
}

int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end,
			unsigned flags)
{
	return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp);
}

int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
{
	return kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp);
}

static int kvm_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
			 struct kvm_memory_slot *slot, gfn_t gfn, int level,
			 unsigned long data)
{
	u64 *sptep;
	struct rmap_iterator uninitialized_var(iter);
	int young = 0;

	for_each_rmap_spte(rmap_head, &iter, sptep)
		young |= mmu_spte_age(sptep);

	trace_kvm_age_page(gfn, level, slot, young);
	return young;
}

static int kvm_test_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
			      struct kvm_memory_slot *slot, gfn_t gfn,
			      int level, unsigned long data)
{
	u64 *sptep;
	struct rmap_iterator iter;

	for_each_rmap_spte(rmap_head, &iter, sptep)
		if (is_accessed_spte(*sptep))
			return 1;
	return 0;
}

#define RMAP_RECYCLE_THRESHOLD 1000

static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
{
	struct kvm_rmap_head *rmap_head;
	struct kvm_mmu_page *sp;

	sp = page_header(__pa(spte));

	rmap_head = gfn_to_rmap(vcpu->kvm, gfn, sp);

	kvm_unmap_rmapp(vcpu->kvm, rmap_head, NULL, gfn, sp->role.level, 0);
	kvm_flush_remote_tlbs_with_address(vcpu->kvm, sp->gfn,
			KVM_PAGES_PER_HPAGE(sp->role.level));
}

int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
{
	return kvm_handle_hva_range(kvm, start, end, 0, kvm_age_rmapp);
}

int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
{
	return kvm_handle_hva(kvm, hva, 0, kvm_test_age_rmapp);
}

#ifdef MMU_DEBUG
static int is_empty_shadow_page(u64 *spt)
{
	u64 *pos;
	u64 *end;

	for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++)
		if (is_shadow_present_pte(*pos)) {
			printk(KERN_ERR "%s: %p %llx\n", __func__,
			       pos, *pos);
			return 0;
		}
	return 1;
}
#endif

/*
 * This value is the sum of all of the kvm instances's
 * kvm->arch.n_used_mmu_pages values.  We need a global,
 * aggregate version in order to make the slab shrinker
 * faster
 */
static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, long nr)
{
	kvm->arch.n_used_mmu_pages += nr;
	percpu_counter_add(&kvm_total_used_mmu_pages, nr);
}

static void kvm_mmu_free_page(struct kvm_mmu_page *sp)
{
	MMU_WARN_ON(!is_empty_shadow_page(sp->spt));
	hlist_del(&sp->hash_link);
	list_del(&sp->link);
	free_page((unsigned long)sp->spt);
	if (!sp->role.direct)
		free_page((unsigned long)sp->gfns);
	kmem_cache_free(mmu_page_header_cache, sp);
}

static unsigned kvm_page_table_hashfn(gfn_t gfn)
{
	return hash_64(gfn, KVM_MMU_HASH_SHIFT);
}

static void mmu_page_add_parent_pte(struct kvm_vcpu *vcpu,
				    struct kvm_mmu_page *sp, u64 *parent_pte)
{
	if (!parent_pte)
		return;

	pte_list_add(vcpu, parent_pte, &sp->parent_ptes);
}

static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp,
				       u64 *parent_pte)
{
	__pte_list_remove(parent_pte, &sp->parent_ptes);
}

static void drop_parent_pte(struct kvm_mmu_page *sp,
			    u64 *parent_pte)
{
	mmu_page_remove_parent_pte(sp, parent_pte);
	mmu_spte_clear_no_track(parent_pte);
}

static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, int direct)
{
	struct kvm_mmu_page *sp;

	sp = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_header_cache);
	sp->spt = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache);
	if (!direct)
		sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache);
	set_page_private(virt_to_page(sp->spt), (unsigned long)sp);

	/*
	 * active_mmu_pages must be a FIFO list, as kvm_zap_obsolete_pages()
	 * depends on valid pages being added to the head of the list.  See
	 * comments in kvm_zap_obsolete_pages().
	 */
	sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen;
	list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
	kvm_mod_used_mmu_pages(vcpu->kvm, +1);
	return sp;
}

static void mark_unsync(u64 *spte);
static void kvm_mmu_mark_parents_unsync(struct kvm_mmu_page *sp)
{
	u64 *sptep;
	struct rmap_iterator iter;

	for_each_rmap_spte(&sp->parent_ptes, &iter, sptep) {
		mark_unsync(sptep);
	}
}

static void mark_unsync(u64 *spte)
{
	struct kvm_mmu_page *sp;
	unsigned int index;

	sp = page_header(__pa(spte));
	index = spte - sp->spt;
	if (__test_and_set_bit(index, sp->unsync_child_bitmap))
		return;
	if (sp->unsync_children++)
		return;
	kvm_mmu_mark_parents_unsync(sp);
}

static int nonpaging_sync_page(struct kvm_vcpu *vcpu,
			       struct kvm_mmu_page *sp)
{
	return 0;
}

static void nonpaging_invlpg(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root)
{
}

#define KVM_PAGE_ARRAY_NR 16

struct kvm_mmu_pages {
	struct mmu_page_and_offset {
		struct kvm_mmu_page *sp;
		unsigned int idx;
	} page[KVM_PAGE_ARRAY_NR];
	unsigned int nr;
};

static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp,
			 int idx)
{
	int i;

	if (sp->unsync)
		for (i=0; i < pvec->nr; i++)
			if (pvec->page[i].sp == sp)
				return 0;

	pvec->page[pvec->nr].sp = sp;
	pvec->page[pvec->nr].idx = idx;
	pvec->nr++;
	return (pvec->nr == KVM_PAGE_ARRAY_NR);
}

static inline void clear_unsync_child_bit(struct kvm_mmu_page *sp, int idx)
{
	--sp->unsync_children;
	WARN_ON((int)sp->unsync_children < 0);
	__clear_bit(idx, sp->unsync_child_bitmap);
}

static int __mmu_unsync_walk(struct kvm_mmu_page *sp,
			   struct kvm_mmu_pages *pvec)
{
	int i, ret, nr_unsync_leaf = 0;

	for_each_set_bit(i, sp->unsync_child_bitmap, 512) {
		struct kvm_mmu_page *child;
		u64 ent = sp->spt[i];

		if (!is_shadow_present_pte(ent) || is_large_pte(ent)) {
			clear_unsync_child_bit(sp, i);
			continue;
		}

		child = page_header(ent & PT64_BASE_ADDR_MASK);

		if (child->unsync_children) {
			if (mmu_pages_add(pvec, child, i))
				return -ENOSPC;

			ret = __mmu_unsync_walk(child, pvec);
			if (!ret) {
				clear_unsync_child_bit(sp, i);
				continue;
			} else if (ret > 0) {
				nr_unsync_leaf += ret;
			} else
				return ret;
		} else if (child->unsync) {
			nr_unsync_leaf++;
			if (mmu_pages_add(pvec, child, i))
				return -ENOSPC;
		} else
			clear_unsync_child_bit(sp, i);
	}

	return nr_unsync_leaf;
}

#define INVALID_INDEX (-1)

static int mmu_unsync_walk(struct kvm_mmu_page *sp,
			   struct kvm_mmu_pages *pvec)
{
	pvec->nr = 0;
	if (!sp->unsync_children)
		return 0;

	mmu_pages_add(pvec, sp, INVALID_INDEX);
	return __mmu_unsync_walk(sp, pvec);
}

static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
	WARN_ON(!sp->unsync);
	trace_kvm_mmu_sync_page(sp);
	sp->unsync = 0;
	--kvm->stat.mmu_unsync;
}

static bool kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
				     struct list_head *invalid_list);
static void kvm_mmu_commit_zap_page(struct kvm *kvm,
				    struct list_head *invalid_list);


#define for_each_valid_sp(_kvm, _sp, _gfn)				\
	hlist_for_each_entry(_sp,					\
	  &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \
		if (is_obsolete_sp((_kvm), (_sp))) {			\
		} else

#define for_each_gfn_indirect_valid_sp(_kvm, _sp, _gfn)			\
	for_each_valid_sp(_kvm, _sp, _gfn)				\
		if ((_sp)->gfn != (_gfn) || (_sp)->role.direct) {} else

static inline bool is_ept_sp(struct kvm_mmu_page *sp)
{
	return sp->role.cr0_wp && sp->role.smap_andnot_wp;
}

/* @sp->gfn should be write-protected at the call site */
static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
			    struct list_head *invalid_list)
{
	if ((!is_ept_sp(sp) && sp->role.gpte_is_8_bytes != !!is_pae(vcpu)) ||
	    vcpu->arch.mmu->sync_page(vcpu, sp) == 0) {
		kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
		return false;
	}

	return true;
}

static bool kvm_mmu_remote_flush_or_zap(struct kvm *kvm,
					struct list_head *invalid_list,
					bool remote_flush)
{
	if (!remote_flush && list_empty(invalid_list))
		return false;

	if (!list_empty(invalid_list))
		kvm_mmu_commit_zap_page(kvm, invalid_list);
	else
		kvm_flush_remote_tlbs(kvm);
	return true;
}

static void kvm_mmu_flush_or_zap(struct kvm_vcpu *vcpu,
				 struct list_head *invalid_list,
				 bool remote_flush, bool local_flush)
{
	if (kvm_mmu_remote_flush_or_zap(vcpu->kvm, invalid_list, remote_flush))
		return;

	if (local_flush)
		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}

#ifdef CONFIG_KVM_MMU_AUDIT
#include "mmu_audit.c"
#else
static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { }
static void mmu_audit_disable(void) { }
#endif

static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
{
	return sp->role.invalid ||
	       unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
}

static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
			 struct list_head *invalid_list)
{
	kvm_unlink_unsync_page(vcpu->kvm, sp);
	return __kvm_sync_page(vcpu, sp, invalid_list);
}

/* @gfn should be write-protected at the call site */
static bool kvm_sync_pages(struct kvm_vcpu *vcpu, gfn_t gfn,
			   struct list_head *invalid_list)
{
	struct kvm_mmu_page *s;
	bool ret = false;

	for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
		if (!s->unsync)
			continue;

		WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL);
		ret |= kvm_sync_page(vcpu, s, invalid_list);
	}

	return ret;
}

struct mmu_page_path {
	struct kvm_mmu_page *parent[PT64_ROOT_MAX_LEVEL];
	unsigned int idx[PT64_ROOT_MAX_LEVEL];
};

#define for_each_sp(pvec, sp, parents, i)			\
		for (i = mmu_pages_first(&pvec, &parents);	\
			i < pvec.nr && ({ sp = pvec.page[i].sp; 1;});	\
			i = mmu_pages_next(&pvec, &parents, i))

static int mmu_pages_next(struct kvm_mmu_pages *pvec,
			  struct mmu_page_path *parents,
			  int i)
{
	int n;

	for (n = i+1; n < pvec->nr; n++) {
		struct kvm_mmu_page *sp = pvec->page[n].sp;
		unsigned idx = pvec->page[n].idx;
		int level = sp->role.level;

		parents->idx[level-1] = idx;
		if (level == PT_PAGE_TABLE_LEVEL)
			break;

		parents->parent[level-2] = sp;
	}

	return n;
}

static int mmu_pages_first(struct kvm_mmu_pages *pvec,
			   struct mmu_page_path *parents)
{
	struct kvm_mmu_page *sp;
	int level;

	if (pvec->nr == 0)
		return 0;

	WARN_ON(pvec->page[0].idx != INVALID_INDEX);

	sp = pvec->page[0].sp;
	level = sp->role.level;
	WARN_ON(level == PT_PAGE_TABLE_LEVEL);

	parents->parent[level-2] = sp;

	/* Also set up a sentinel.  Further entries in pvec are all
	 * children of sp, so this element is never overwritten.
	 */
	parents->parent[level-1] = NULL;
	return mmu_pages_next(pvec, parents, 0);
}

static void mmu_pages_clear_parents(struct mmu_page_path *parents)
{
	struct kvm_mmu_page *sp;
	unsigned int level = 0;

	do {
		unsigned int idx = parents->idx[level];
		sp = parents->parent[level];
		if (!sp)
			return;

		WARN_ON(idx == INVALID_INDEX);
		clear_unsync_child_bit(sp, idx);
		level++;
	} while (!sp->unsync_children);
}

static void mmu_sync_children(struct kvm_vcpu *vcpu,
			      struct kvm_mmu_page *parent)
{
	int i;
	struct kvm_mmu_page *sp;
	struct mmu_page_path parents;
	struct kvm_mmu_pages pages;
	LIST_HEAD(invalid_list);
	bool flush = false;

	while (mmu_unsync_walk(parent, &pages)) {
		bool protected = false;

		for_each_sp(pages, sp, parents, i)
			protected |= rmap_write_protect(vcpu, sp->gfn);

		if (protected) {
			kvm_flush_remote_tlbs(vcpu->kvm);
			flush = false;
		}

		for_each_sp(pages, sp, parents, i) {
			flush |= kvm_sync_page(vcpu, sp, &invalid_list);
			mmu_pages_clear_parents(&parents);
		}
		if (need_resched() || spin_needbreak(&vcpu->kvm->mmu_lock)) {
			kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
			cond_resched_lock(&vcpu->kvm->mmu_lock);
			flush = false;
		}
	}

	kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
}

static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp)
{
	atomic_set(&sp->write_flooding_count,  0);
}

static void clear_sp_write_flooding_count(u64 *spte)
{
	struct kvm_mmu_page *sp =  page_header(__pa(spte));

	__clear_sp_write_flooding_count(sp);
}

static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
					     gfn_t gfn,
					     gva_t gaddr,
					     unsigned level,
					     int direct,
					     unsigned access)
{
	union kvm_mmu_page_role role;
	unsigned quadrant;
	struct kvm_mmu_page *sp;
	bool need_sync = false;
	bool flush = false;
	int collisions = 0;
	LIST_HEAD(invalid_list);

	role = vcpu->arch.mmu->mmu_role.base;
	role.level = level;
	role.direct = direct;
	if (role.direct)
		role.gpte_is_8_bytes = true;
	role.access = access;
	if (!vcpu->arch.mmu->direct_map
	    && vcpu->arch.mmu->root_level <= PT32_ROOT_LEVEL) {
		quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level));
		quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
		role.quadrant = quadrant;
	}
	for_each_valid_sp(vcpu->kvm, sp, gfn) {
		if (sp->gfn != gfn) {
			collisions++;
			continue;
		}

		if (!need_sync && sp->unsync)
			need_sync = true;

		if (sp->role.word != role.word)
			continue;

		if (sp->unsync) {
			/* The page is good, but __kvm_sync_page might still end
			 * up zapping it.  If so, break in order to rebuild it.
			 */
			if (!__kvm_sync_page(vcpu, sp, &invalid_list))
				break;

			WARN_ON(!list_empty(&invalid_list));
			kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
		}

		if (sp->unsync_children)
			kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);

		__clear_sp_write_flooding_count(sp);
		trace_kvm_mmu_get_page(sp, false);
		goto out;
	}

	++vcpu->kvm->stat.mmu_cache_miss;

	sp = kvm_mmu_alloc_page(vcpu, direct);

	sp->gfn = gfn;
	sp->role = role;
	hlist_add_head(&sp->hash_link,
		&vcpu->kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)]);
	if (!direct) {
		/*
		 * we should do write protection before syncing pages
		 * otherwise the content of the synced shadow page may
		 * be inconsistent with guest page table.
		 */
		account_shadowed(vcpu->kvm, sp);
		if (level == PT_PAGE_TABLE_LEVEL &&
		      rmap_write_protect(vcpu, gfn))
			kvm_flush_remote_tlbs_with_address(vcpu->kvm, gfn, 1);

		if (level > PT_PAGE_TABLE_LEVEL && need_sync)
			flush |= kvm_sync_pages(vcpu, gfn, &invalid_list);
	}
	clear_page(sp->spt);
	trace_kvm_mmu_get_page(sp, true);

	kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
out:
	if (collisions > vcpu->kvm->stat.max_mmu_page_hash_collisions)
		vcpu->kvm->stat.max_mmu_page_hash_collisions = collisions;
	return sp;
}

static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterator,
					struct kvm_vcpu *vcpu, hpa_t root,
					u64 addr)
{
	iterator->addr = addr;
	iterator->shadow_addr = root;
	iterator->level = vcpu->arch.mmu->shadow_root_level;

	if (iterator->level == PT64_ROOT_4LEVEL &&
	    vcpu->arch.mmu->root_level < PT64_ROOT_4LEVEL &&
	    !vcpu->arch.mmu->direct_map)
		--iterator->level;

	if (iterator->level == PT32E_ROOT_LEVEL) {
		/*
		 * prev_root is currently only used for 64-bit hosts. So only
		 * the active root_hpa is valid here.
		 */
		BUG_ON(root != vcpu->arch.mmu->root_hpa);

		iterator->shadow_addr
			= vcpu->arch.mmu->pae_root[(addr >> 30) & 3];
		iterator->shadow_addr &= PT64_BASE_ADDR_MASK;
		--iterator->level;
		if (!iterator->shadow_addr)
			iterator->level = 0;
	}
}

static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator,
			     struct kvm_vcpu *vcpu, u64 addr)
{
	shadow_walk_init_using_root(iterator, vcpu, vcpu->arch.mmu->root_hpa,
				    addr);
}

static bool shadow_walk_okay(struct kvm_shadow_walk_iterator *iterator)
{
	if (iterator->level < PT_PAGE_TABLE_LEVEL)
		return false;

	iterator->index = SHADOW_PT_INDEX(iterator->addr, iterator->level);
	iterator->sptep	= ((u64 *)__va(iterator->shadow_addr)) + iterator->index;
	return true;
}

static void __shadow_walk_next(struct kvm_shadow_walk_iterator *iterator,
			       u64 spte)
{
	if (is_last_spte(spte, iterator->level)) {
		iterator->level = 0;
		return;
	}

	iterator->shadow_addr = spte & PT64_BASE_ADDR_MASK;
	--iterator->level;
}

static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator)
{
	__shadow_walk_next(iterator, *iterator->sptep);
}

static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep,
			     struct kvm_mmu_page *sp)
{
	u64 spte;

	BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);

	spte = __pa(sp->spt) | shadow_present_mask | PT_WRITABLE_MASK |
	       shadow_user_mask | shadow_x_mask | shadow_me_mask;

	if (sp_ad_disabled(sp))
		spte |= SPTE_AD_DISABLED_MASK;
	else
		spte |= shadow_accessed_mask;

	mmu_spte_set(sptep, spte);

	mmu_page_add_parent_pte(vcpu, sp, sptep);

	if (sp->unsync_children || sp->unsync)
		mark_unsync(sptep);
}

static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep,
				   unsigned direct_access)
{
	if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep)) {
		struct kvm_mmu_page *child;

		/*
		 * For the direct sp, if the guest pte's dirty bit
		 * changed form clean to dirty, it will corrupt the
		 * sp's access: allow writable in the read-only sp,
		 * so we should update the spte at this point to get
		 * a new sp with the correct access.
		 */
		child = page_header(*sptep & PT64_BASE_ADDR_MASK);
		if (child->role.access == direct_access)
			return;

		drop_parent_pte(child, sptep);
		kvm_flush_remote_tlbs_with_address(vcpu->kvm, child->gfn, 1);
	}
}

static bool mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
			     u64 *spte)
{
	u64 pte;
	struct kvm_mmu_page *child;

	pte = *spte;
	if (is_shadow_present_pte(pte)) {
		if (is_last_spte(pte, sp->role.level)) {
			drop_spte(kvm, spte);
			if (is_large_pte(pte))
				--kvm->stat.lpages;
		} else {
			child = page_header(pte & PT64_BASE_ADDR_MASK);
			drop_parent_pte(child, spte);
		}
		return true;
	}

	if (is_mmio_spte(pte))
		mmu_spte_clear_no_track(spte);

	return false;
}

static void kvm_mmu_page_unlink_children(struct kvm *kvm,
					 struct kvm_mmu_page *sp)
{
	unsigned i;

	for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
		mmu_page_zap_pte(kvm, sp, sp->spt + i);
}

static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp)
{
	u64 *sptep;
	struct rmap_iterator iter;

	while ((sptep = rmap_get_first(&sp->parent_ptes, &iter)))
		drop_parent_pte(sp, sptep);
}

static int mmu_zap_unsync_children(struct kvm *kvm,
				   struct kvm_mmu_page *parent,
				   struct list_head *invalid_list)
{
	int i, zapped = 0;
	struct mmu_page_path parents;
	struct kvm_mmu_pages pages;

	if (parent->role.level == PT_PAGE_TABLE_LEVEL)
		return 0;

	while (mmu_unsync_walk(parent, &pages)) {
		struct kvm_mmu_page *sp;

		for_each_sp(pages, sp, parents, i) {
			kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
			mmu_pages_clear_parents(&parents);
			zapped++;
		}
	}

	return zapped;
}

static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
				       struct kvm_mmu_page *sp,
				       struct list_head *invalid_list,
				       int *nr_zapped)
{
	bool list_unstable;

	trace_kvm_mmu_prepare_zap_page(sp);
	++kvm->stat.mmu_shadow_zapped;
	*nr_zapped = mmu_zap_unsync_children(kvm, sp, invalid_list);
	kvm_mmu_page_unlink_children(kvm, sp);
	kvm_mmu_unlink_parents(kvm, sp);

	/* Zapping children means active_mmu_pages has become unstable. */
	list_unstable = *nr_zapped;

	if (!sp->role.invalid && !sp->role.direct)
		unaccount_shadowed(kvm, sp);

	if (sp->unsync)
		kvm_unlink_unsync_page(kvm, sp);
	if (!sp->root_count) {
		/* Count self */
		(*nr_zapped)++;
		list_move(&sp->link, invalid_list);
		kvm_mod_used_mmu_pages(kvm, -1);
	} else {
		list_move(&sp->link, &kvm->arch.active_mmu_pages);

		/*
		 * Obsolete pages cannot be used on any vCPUs, see the comment
		 * in kvm_mmu_zap_all_fast().  Note, is_obsolete_sp() also
		 * treats invalid shadow pages as being obsolete.
		 */
		if (!is_obsolete_sp(kvm, sp))
			kvm_reload_remote_mmus(kvm);
	}

	if (sp->lpage_disallowed)
		unaccount_huge_nx_page(kvm, sp);

	sp->role.invalid = 1;
	return list_unstable;
}

static bool kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
				     struct list_head *invalid_list)
{
	int nr_zapped;

	__kvm_mmu_prepare_zap_page(kvm, sp, invalid_list, &nr_zapped);
	return nr_zapped;
}

static void kvm_mmu_commit_zap_page(struct kvm *kvm,
				    struct list_head *invalid_list)
{
	struct kvm_mmu_page *sp, *nsp;

	if (list_empty(invalid_list))
		return;

	/*
	 * We need to make sure everyone sees our modifications to
	 * the page tables and see changes to vcpu->mode here. The barrier
	 * in the kvm_flush_remote_tlbs() achieves this. This pairs
	 * with vcpu_enter_guest and walk_shadow_page_lockless_begin/end.
	 *
	 * In addition, kvm_flush_remote_tlbs waits for all vcpus to exit
	 * guest mode and/or lockless shadow page table walks.
	 */
	kvm_flush_remote_tlbs(kvm);

	list_for_each_entry_safe(sp, nsp, invalid_list, link) {
		WARN_ON(!sp->role.invalid || sp->root_count);
		kvm_mmu_free_page(sp);
	}
}

static bool prepare_zap_oldest_mmu_page(struct kvm *kvm,
					struct list_head *invalid_list)
{
	struct kvm_mmu_page *sp;

	if (list_empty(&kvm->arch.active_mmu_pages))
		return false;

	sp = list_last_entry(&kvm->arch.active_mmu_pages,
			     struct kvm_mmu_page, link);
	return kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
}

/*
 * Changing the number of mmu pages allocated to the vm
 * Note: if goal_nr_mmu_pages is too small, you will get dead lock
 */
void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages)
{
	LIST_HEAD(invalid_list);

	spin_lock(&kvm->mmu_lock);

	if (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages) {
		/* Need to free some mmu pages to achieve the goal. */
		while (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages)
			if (!prepare_zap_oldest_mmu_page(kvm, &invalid_list))
				break;

		kvm_mmu_commit_zap_page(kvm, &invalid_list);
		goal_nr_mmu_pages = kvm->arch.n_used_mmu_pages;
	}

	kvm->arch.n_max_mmu_pages = goal_nr_mmu_pages;

	spin_unlock(&kvm->mmu_lock);
}

int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
{
	struct kvm_mmu_page *sp;
	LIST_HEAD(invalid_list);
	int r;

	pgprintk("%s: looking for gfn %llx\n", __func__, gfn);
	r = 0;
	spin_lock(&kvm->mmu_lock);
	for_each_gfn_indirect_valid_sp(kvm, sp, gfn) {
		pgprintk("%s: gfn %llx role %x\n", __func__, gfn,
			 sp->role.word);
		r = 1;
		kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
	}
	kvm_mmu_commit_zap_page(kvm, &invalid_list);
	spin_unlock(&kvm->mmu_lock);

	return r;
}
EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page);

static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
	trace_kvm_mmu_unsync_page(sp);
	++vcpu->kvm->stat.mmu_unsync;
	sp->unsync = 1;

	kvm_mmu_mark_parents_unsync(sp);
}

static bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
				   bool can_unsync)
{
	struct kvm_mmu_page *sp;

	if (kvm_page_track_is_active(vcpu, gfn, KVM_PAGE_TRACK_WRITE))
		return true;

	for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
		if (!can_unsync)
			return true;

		if (sp->unsync)
			continue;

		WARN_ON(sp->role.level != PT_PAGE_TABLE_LEVEL);
		kvm_unsync_page(vcpu, sp);
	}

	/*
	 * We need to ensure that the marking of unsync pages is visible
	 * before the SPTE is updated to allow writes because
	 * kvm_mmu_sync_roots() checks the unsync flags without holding
	 * the MMU lock and so can race with this. If the SPTE was updated
	 * before the page had been marked as unsync-ed, something like the
	 * following could happen:
	 *
	 * CPU 1                    CPU 2
	 * ---------------------------------------------------------------------
	 * 1.2 Host updates SPTE
	 *     to be writable
	 *                      2.1 Guest writes a GPTE for GVA X.
	 *                          (GPTE being in the guest page table shadowed
	 *                           by the SP from CPU 1.)
	 *                          This reads SPTE during the page table walk.
	 *                          Since SPTE.W is read as 1, there is no
	 *                          fault.
	 *
	 *                      2.2 Guest issues TLB flush.
	 *                          That causes a VM Exit.
	 *
	 *                      2.3 kvm_mmu_sync_pages() reads sp->unsync.
	 *                          Since it is false, so it just returns.
	 *
	 *                      2.4 Guest accesses GVA X.
	 *                          Since the mapping in the SP was not updated,
	 *                          so the old mapping for GVA X incorrectly
	 *                          gets used.
	 * 1.1 Host marks SP
	 *     as unsync
	 *     (sp->unsync = true)
	 *
	 * The write barrier below ensures that 1.1 happens before 1.2 and thus
	 * the situation in 2.4 does not arise. The implicit barrier in 2.2
	 * pairs with this write barrier.
	 */
	smp_wmb();

	return false;
}

static bool kvm_is_mmio_pfn(kvm_pfn_t pfn)
{
	if (pfn_valid(pfn))
		return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)) &&
			/*
			 * Some reserved pages, such as those from NVDIMM
			 * DAX devices, are not for MMIO, and can be mapped
			 * with cached memory type for better performance.
			 * However, the above check misconceives those pages
			 * as MMIO, and results in KVM mapping them with UC
			 * memory type, which would hurt the performance.
			 * Therefore, we check the host memory type in addition
			 * and only treat UC/UC-/WC pages as MMIO.
			 */
			(!pat_enabled() || pat_pfn_immune_to_uc_mtrr(pfn));

	return !e820__mapped_raw_any(pfn_to_hpa(pfn),
				     pfn_to_hpa(pfn + 1) - 1,
				     E820_TYPE_RAM);
}

/* Bits which may be returned by set_spte() */
#define SET_SPTE_WRITE_PROTECTED_PT	BIT(0)
#define SET_SPTE_NEED_REMOTE_TLB_FLUSH	BIT(1)

static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
		    unsigned pte_access, int level,
		    gfn_t gfn, kvm_pfn_t pfn, bool speculative,
		    bool can_unsync, bool host_writable)
{
	u64 spte = 0;
	int ret = 0;
	struct kvm_mmu_page *sp;

	if (set_mmio_spte(vcpu, sptep, gfn, pfn, pte_access))
		return 0;

	sp = page_header(__pa(sptep));
	if (sp_ad_disabled(sp))
		spte |= SPTE_AD_DISABLED_MASK;
	else if (kvm_vcpu_ad_need_write_protect(vcpu))
		spte |= SPTE_AD_WRPROT_ONLY_MASK;

	/*
	 * For the EPT case, shadow_present_mask is 0 if hardware
	 * supports exec-only page table entries.  In that case,
	 * ACC_USER_MASK and shadow_user_mask are used to represent
	 * read access.  See FNAME(gpte_access) in paging_tmpl.h.
	 */
	spte |= shadow_present_mask;
	if (!speculative)
		spte |= spte_shadow_accessed_mask(spte);

	if (level > PT_PAGE_TABLE_LEVEL && (pte_access & ACC_EXEC_MASK) &&
	    is_nx_huge_page_enabled()) {
		pte_access &= ~ACC_EXEC_MASK;
	}

	if (pte_access & ACC_EXEC_MASK)
		spte |= shadow_x_mask;
	else
		spte |= shadow_nx_mask;

	if (pte_access & ACC_USER_MASK)
		spte |= shadow_user_mask;

	if (level > PT_PAGE_TABLE_LEVEL)
		spte |= PT_PAGE_SIZE_MASK;
	if (tdp_enabled)
		spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn,
			kvm_is_mmio_pfn(pfn));

	if (host_writable)
		spte |= SPTE_HOST_WRITEABLE;
	else
		pte_access &= ~ACC_WRITE_MASK;

	if (!kvm_is_mmio_pfn(pfn))
		spte |= shadow_me_mask;

	spte |= (u64)pfn << PAGE_SHIFT;

	if (pte_access & ACC_WRITE_MASK) {

		/*
		 * Other vcpu creates new sp in the window between
		 * mapping_level() and acquiring mmu-lock. We can
		 * allow guest to retry the access, the mapping can
		 * be fixed if guest refault.
		 */
		if (level > PT_PAGE_TABLE_LEVEL &&
		    mmu_gfn_lpage_is_disallowed(vcpu, gfn, level))
			goto done;

		spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE;

		/*
		 * Optimization: for pte sync, if spte was writable the hash
		 * lookup is unnecessary (and expensive). Write protection
		 * is responsibility of mmu_get_page / kvm_sync_page.
		 * Same reasoning can be applied to dirty page accounting.
		 */
		if (!can_unsync && is_writable_pte(*sptep))
			goto set_pte;

		if (mmu_need_write_protect(vcpu, gfn, can_unsync)) {
			pgprintk("%s: found shadow page for %llx, marking ro\n",
				 __func__, gfn);
			ret |= SET_SPTE_WRITE_PROTECTED_PT;
			pte_access &= ~ACC_WRITE_MASK;
			spte &= ~(PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE);
		}
	}

	if (pte_access & ACC_WRITE_MASK) {
		kvm_vcpu_mark_page_dirty(vcpu, gfn);
		spte |= spte_shadow_dirty_mask(spte);
	}

	if (speculative)
		spte = mark_spte_for_access_track(spte);

set_pte:
	if (mmu_spte_update(sptep, spte))
		ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH;
done:
	return ret;
}

static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access,
			int write_fault, int level, gfn_t gfn, kvm_pfn_t pfn,
		       	bool speculative, bool host_writable)
{
	int was_rmapped = 0;
	int rmap_count;
	int set_spte_ret;
	int ret = RET_PF_RETRY;
	bool flush = false;

	pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__,
		 *sptep, write_fault, gfn);

	if (is_shadow_present_pte(*sptep)) {
		/*
		 * If we overwrite a PTE page pointer with a 2MB PMD, unlink
		 * the parent of the now unreachable PTE.
		 */
		if (level > PT_PAGE_TABLE_LEVEL &&
		    !is_large_pte(*sptep)) {
			struct kvm_mmu_page *child;
			u64 pte = *sptep;

			child = page_header(pte & PT64_BASE_ADDR_MASK);
			drop_parent_pte(child, sptep);
			flush = true;
		} else if (pfn != spte_to_pfn(*sptep)) {
			pgprintk("hfn old %llx new %llx\n",
				 spte_to_pfn(*sptep), pfn);
			drop_spte(vcpu->kvm, sptep);
			flush = true;
		} else
			was_rmapped = 1;
	}

	set_spte_ret = set_spte(vcpu, sptep, pte_access, level, gfn, pfn,
				speculative, true, host_writable);
	if (set_spte_ret & SET_SPTE_WRITE_PROTECTED_PT) {
		if (write_fault)
			ret = RET_PF_EMULATE;
		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
	}

	if (set_spte_ret & SET_SPTE_NEED_REMOTE_TLB_FLUSH || flush)
		kvm_flush_remote_tlbs_with_address(vcpu->kvm, gfn,
				KVM_PAGES_PER_HPAGE(level));

	if (unlikely(is_mmio_spte(*sptep)))
		ret = RET_PF_EMULATE;

	pgprintk("%s: setting spte %llx\n", __func__, *sptep);
	trace_kvm_mmu_set_spte(level, gfn, sptep);
	if (!was_rmapped && is_large_pte(*sptep))
		++vcpu->kvm->stat.lpages;

	if (is_shadow_present_pte(*sptep)) {
		if (!was_rmapped) {
			rmap_count = rmap_add(vcpu, sptep, gfn);
			if (rmap_count > RMAP_RECYCLE_THRESHOLD)
				rmap_recycle(vcpu, sptep, gfn);
		}
	}

	return ret;
}

static kvm_pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
				     bool no_dirty_log)
{
	struct kvm_memory_slot *slot;

	slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, no_dirty_log);
	if (!slot)
		return KVM_PFN_ERR_FAULT;

	return gfn_to_pfn_memslot_atomic(slot, gfn);
}

static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
				    struct kvm_mmu_page *sp,
				    u64 *start, u64 *end)
{
	struct page *pages[PTE_PREFETCH_NUM];
	struct kvm_memory_slot *slot;
	unsigned access = sp->role.access;
	int i, ret;
	gfn_t gfn;

	gfn = kvm_mmu_page_get_gfn(sp, start - sp->spt);
	slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK);
	if (!slot)
		return -1;

	ret = gfn_to_page_many_atomic(slot, gfn, pages, end - start);
	if (ret <= 0)
		return -1;

	for (i = 0; i < ret; i++, gfn++, start++) {
		mmu_set_spte(vcpu, start, access, 0, sp->role.level, gfn,
			     page_to_pfn(pages[i]), true, true);
		put_page(pages[i]);
	}

	return 0;
}

static void __direct_pte_prefetch(struct kvm_vcpu *vcpu,
				  struct kvm_mmu_page *sp, u64 *sptep)
{
	u64 *spte, *start = NULL;
	int i;

	WARN_ON(!sp->role.direct);

	i = (sptep - sp->spt) & ~(PTE_PREFETCH_NUM - 1);
	spte = sp->spt + i;

	for (i = 0; i < PTE_PREFETCH_NUM; i++, spte++) {
		if (is_shadow_present_pte(*spte) || spte == sptep) {
			if (!start)
				continue;
			if (direct_pte_prefetch_many(vcpu, sp, start, spte) < 0)
				break;
			start = NULL;
		} else if (!start)
			start = spte;
	}
}

static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
{
	struct kvm_mmu_page *sp;

	sp = page_header(__pa(sptep));

	/*
	 * Without accessed bits, there's no way to distinguish between
	 * actually accessed translations and prefetched, so disable pte
	 * prefetch if accessed bits aren't available.
	 */
	if (sp_ad_disabled(sp))
		return;

	if (sp->role.level > PT_PAGE_TABLE_LEVEL)
		return;

	__direct_pte_prefetch(vcpu, sp, sptep);
}

static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it,
				       gfn_t gfn, kvm_pfn_t *pfnp, int *levelp)
{
	int level = *levelp;
	u64 spte = *it.sptep;

	if (it.level == level && level > PT_PAGE_TABLE_LEVEL &&
	    is_nx_huge_page_enabled() &&
	    is_shadow_present_pte(spte) &&
	    !is_large_pte(spte)) {
		/*
		 * A small SPTE exists for this pfn, but FNAME(fetch)
		 * and __direct_map would like to create a large PTE
		 * instead: just force them to go down another level,
		 * patching back for them into pfn the next 9 bits of
		 * the address.
		 */
		u64 page_mask = KVM_PAGES_PER_HPAGE(level) - KVM_PAGES_PER_HPAGE(level - 1);
		*pfnp |= gfn & page_mask;
		(*levelp)--;
	}
}

static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
			int map_writable, int level, kvm_pfn_t pfn,
			bool prefault, bool lpage_disallowed)
{
	struct kvm_shadow_walk_iterator it;
	struct kvm_mmu_page *sp;
	int ret;
	gfn_t gfn = gpa >> PAGE_SHIFT;
	gfn_t base_gfn = gfn;

	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
		return RET_PF_RETRY;

	trace_kvm_mmu_spte_requested(gpa, level, pfn);
	for_each_shadow_entry(vcpu, gpa, it) {
		/*
		 * We cannot overwrite existing page tables with an NX
		 * large page, as the leaf could be executable.
		 */
		disallowed_hugepage_adjust(it, gfn, &pfn, &level);

		base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
		if (it.level == level)
			break;

		drop_large_spte(vcpu, it.sptep);
		if (!is_shadow_present_pte(*it.sptep)) {
			sp = kvm_mmu_get_page(vcpu, base_gfn, it.addr,
					      it.level - 1, true, ACC_ALL);

			link_shadow_page(vcpu, it.sptep, sp);
			if (lpage_disallowed)
				account_huge_nx_page(vcpu->kvm, sp);
		}
	}

	ret = mmu_set_spte(vcpu, it.sptep, ACC_ALL,
			   write, level, base_gfn, pfn, prefault,
			   map_writable);
	direct_pte_prefetch(vcpu, it.sptep);
	++vcpu->stat.pf_fixed;
	return ret;
}

static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *tsk)
{
	send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, PAGE_SHIFT, tsk);
}

static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
{
	/*
	 * Do not cache the mmio info caused by writing the readonly gfn
	 * into the spte otherwise read access on readonly gfn also can
	 * caused mmio page fault and treat it as mmio access.
	 */
	if (pfn == KVM_PFN_ERR_RO_FAULT)
		return RET_PF_EMULATE;

	if (pfn == KVM_PFN_ERR_HWPOISON) {
		kvm_send_hwpoison_signal(kvm_vcpu_gfn_to_hva(vcpu, gfn), current);
		return RET_PF_RETRY;
	}

	return -EFAULT;
}

static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
					gfn_t gfn, kvm_pfn_t *pfnp,
					int *levelp)
{
	kvm_pfn_t pfn = *pfnp;
	int level = *levelp;

	/*
	 * Check if it's a transparent hugepage. If this would be an
	 * hugetlbfs page, level wouldn't be set to
	 * PT_PAGE_TABLE_LEVEL and there would be no adjustment done
	 * here.
	 */
	if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
	    !kvm_is_zone_device_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL &&
	    PageTransCompoundMap(pfn_to_page(pfn)) &&
	    !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) {
		unsigned long mask;
		/*
		 * mmu_notifier_retry was successful and we hold the
		 * mmu_lock here, so the pmd can't become splitting
		 * from under us, and in turn
		 * __split_huge_page_refcount() can't run from under
		 * us and we can safely transfer the refcount from
		 * PG_tail to PG_head as we switch the pfn to tail to
		 * head.
		 */
		*levelp = level = PT_DIRECTORY_LEVEL;
		mask = KVM_PAGES_PER_HPAGE(level) - 1;
		VM_BUG_ON((gfn & mask) != (pfn & mask));
		if (pfn & mask) {
			kvm_release_pfn_clean(pfn);
			pfn &= ~mask;
			kvm_get_pfn(pfn);
			*pfnp = pfn;
		}
	}
}

static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
				kvm_pfn_t pfn, unsigned access, int *ret_val)
{
	/* The pfn is invalid, report the error! */
	if (unlikely(is_error_pfn(pfn))) {
		*ret_val = kvm_handle_bad_page(vcpu, gfn, pfn);
		return true;
	}

	if (unlikely(is_noslot_pfn(pfn)))
		vcpu_cache_mmio_info(vcpu, gva, gfn,
				     access & shadow_mmio_access_mask);

	return false;
}

static bool page_fault_can_be_fast(u32 error_code)
{
	/*
	 * Do not fix the mmio spte with invalid generation number which
	 * need to be updated by slow page fault path.
	 */
	if (unlikely(error_code & PFERR_RSVD_MASK))
		return false;

	/* See if the page fault is due to an NX violation */
	if (unlikely(((error_code & (PFERR_FETCH_MASK | PFERR_PRESENT_MASK))
		      == (PFERR_FETCH_MASK | PFERR_PRESENT_MASK))))
		return false;

	/*
	 * #PF can be fast if:
	 * 1. The shadow page table entry is not present, which could mean that
	 *    the fault is potentially caused by access tracking (if enabled).
	 * 2. The shadow page table entry is present and the fault
	 *    is caused by write-protect, that means we just need change the W
	 *    bit of the spte which can be done out of mmu-lock.
	 *
	 * However, if access tracking is disabled we know that a non-present
	 * page must be a genuine page fault where we have to create a new SPTE.
	 * So, if access tracking is disabled, we return true only for write
	 * accesses to a present page.
	 */

	return shadow_acc_track_mask != 0 ||
	       ((error_code & (PFERR_WRITE_MASK | PFERR_PRESENT_MASK))
		== (PFERR_WRITE_MASK | PFERR_PRESENT_MASK));
}

/*
 * Returns true if the SPTE was fixed successfully. Otherwise,
 * someone else modified the SPTE from its original value.
 */
static bool
fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
			u64 *sptep, u64 old_spte, u64 new_spte)
{
	gfn_t gfn;

	WARN_ON(!sp->role.direct);

	/*
	 * Theoretically we could also set dirty bit (and flush TLB) here in
	 * order to eliminate unnecessary PML logging. See comments in
	 * set_spte. But fast_page_fault is very unlikely to happen with PML
	 * enabled, so we do not do this. This might result in the same GPA
	 * to be logged in PML buffer again when the write really happens, and
	 * eventually to be called by mark_page_dirty twice. But it's also no
	 * harm. This also avoids the TLB flush needed after setting dirty bit
	 * so non-PML cases won't be impacted.
	 *
	 * Compare with set_spte where instead shadow_dirty_mask is set.
	 */
	if (cmpxchg64(sptep, old_spte, new_spte) != old_spte)
		return false;

	if (is_writable_pte(new_spte) && !is_writable_pte(old_spte)) {
		/*
		 * The gfn of direct spte is stable since it is
		 * calculated by sp->gfn.
		 */
		gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt);
		kvm_vcpu_mark_page_dirty(vcpu, gfn);
	}

	return true;
}

static bool is_access_allowed(u32 fault_err_code, u64 spte)
{
	if (fault_err_code & PFERR_FETCH_MASK)
		return is_executable_pte(spte);

	if (fault_err_code & PFERR_WRITE_MASK)
		return is_writable_pte(spte);

	/* Fault was on Read access */
	return spte & PT_PRESENT_MASK;
}

/*
 * Return value:
 * - true: let the vcpu to access on the same address again.
 * - false: let the real page fault path to fix it.
 */
static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int level,
			    u32 error_code)
{
	struct kvm_shadow_walk_iterator iterator;
	struct kvm_mmu_page *sp;
	bool fault_handled = false;
	u64 spte = 0ull;
	uint retry_count = 0;

	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
		return false;

	if (!page_fault_can_be_fast(error_code))
		return false;

	walk_shadow_page_lockless_begin(vcpu);

	do {
		u64 new_spte;

		for_each_shadow_entry_lockless(vcpu, cr2_or_gpa, iterator, spte)
			if (!is_shadow_present_pte(spte) ||
			    iterator.level < level)
				break;

		sp = page_header(__pa(iterator.sptep));
		if (!is_last_spte(spte, sp->role.level))
			break;

		/*
		 * Check whether the memory access that caused the fault would
		 * still cause it if it were to be performed right now. If not,
		 * then this is a spurious fault caused by TLB lazily flushed,
		 * or some other CPU has already fixed the PTE after the
		 * current CPU took the fault.
		 *
		 * Need not check the access of upper level table entries since
		 * they are always ACC_ALL.
		 */
		if (is_access_allowed(error_code, spte)) {
			fault_handled = true;
			break;
		}

		new_spte = spte;

		if (is_access_track_spte(spte))
			new_spte = restore_acc_track_spte(new_spte);

		/*
		 * Currently, to simplify the code, write-protection can
		 * be removed in the fast path only if the SPTE was
		 * write-protected for dirty-logging or access tracking.
		 */
		if ((error_code & PFERR_WRITE_MASK) &&
		    spte_can_locklessly_be_made_writable(spte))
		{
			new_spte |= PT_WRITABLE_MASK;

			/*
			 * Do not fix write-permission on the large spte.  Since
			 * we only dirty the first page into the dirty-bitmap in
			 * fast_pf_fix_direct_spte(), other pages are missed
			 * if its slot has dirty logging enabled.
			 *
			 * Instead, we let the slow page fault path create a
			 * normal spte to fix the access.
			 *
			 * See the comments in kvm_arch_commit_memory_region().
			 */
			if (sp->role.level > PT_PAGE_TABLE_LEVEL)
				break;
		}

		/* Verify that the fault can be handled in the fast path */
		if (new_spte == spte ||
		    !is_access_allowed(error_code, new_spte))
			break;

		/*
		 * Currently, fast page fault only works for direct mapping
		 * since the gfn is not stable for indirect shadow page. See
		 * Documentation/virt/kvm/locking.txt to get more detail.
		 */
		fault_handled = fast_pf_fix_direct_spte(vcpu, sp,
							iterator.sptep, spte,
							new_spte);
		if (fault_handled)
			break;

		if (++retry_count > 4) {
			printk_once(KERN_WARNING
				"kvm: Fast #PF retrying more than 4 times.\n");
			break;
		}

	} while (true);

	trace_fast_page_fault(vcpu, cr2_or_gpa, error_code, iterator.sptep,
			      spte, fault_handled);
	walk_shadow_page_lockless_end(vcpu);

	return fault_handled;
}

static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
			 gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write,
			 bool *writable);
static int make_mmu_pages_available(struct kvm_vcpu *vcpu);

static int nonpaging_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
			 gfn_t gfn, bool prefault)
{
	int r;
	int level;
	bool force_pt_level;
	kvm_pfn_t pfn;
	unsigned long mmu_seq;
	bool map_writable, write = error_code & PFERR_WRITE_MASK;
	bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
				is_nx_huge_page_enabled();

	force_pt_level = lpage_disallowed;
	level = mapping_level(vcpu, gfn, &force_pt_level);
	if (likely(!force_pt_level)) {
		/*
		 * This path builds a PAE pagetable - so we can map
		 * 2mb pages at maximum. Therefore check if the level
		 * is larger than that.
		 */
		if (level > PT_DIRECTORY_LEVEL)
			level = PT_DIRECTORY_LEVEL;

		gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
	}

	if (fast_page_fault(vcpu, gpa, level, error_code))
		return RET_PF_RETRY;

	mmu_seq = vcpu->kvm->mmu_notifier_seq;
	smp_rmb();

	if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable))
		return RET_PF_RETRY;

	if (handle_abnormal_pfn(vcpu, gpa, gfn, pfn, ACC_ALL, &r))
		return r;

	r = RET_PF_RETRY;
	spin_lock(&vcpu->kvm->mmu_lock);
	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
		goto out_unlock;
	if (make_mmu_pages_available(vcpu) < 0)
		goto out_unlock;
	if (likely(!force_pt_level))
		transparent_hugepage_adjust(vcpu, gfn, &pfn, &level);
	r = __direct_map(vcpu, gpa, write, map_writable, level, pfn,
			 prefault, false);
out_unlock:
	spin_unlock(&vcpu->kvm->mmu_lock);
	kvm_release_pfn_clean(pfn);
	return r;
}

static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
			       struct list_head *invalid_list)
{
	struct kvm_mmu_page *sp;

	if (!VALID_PAGE(*root_hpa))
		return;

	sp = page_header(*root_hpa & PT64_BASE_ADDR_MASK);
	--sp->root_count;
	if (!sp->root_count && sp->role.invalid)
		kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);

	*root_hpa = INVALID_PAGE;
}

/* roots_to_free must be some combination of the KVM_MMU_ROOT_* flags */
void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
			ulong roots_to_free)
{
	int i;
	LIST_HEAD(invalid_list);
	bool free_active_root = roots_to_free & KVM_MMU_ROOT_CURRENT;

	BUILD_BUG_ON(KVM_MMU_NUM_PREV_ROOTS >= BITS_PER_LONG);

	/* Before acquiring the MMU lock, see if we need to do any real work. */
	if (!(free_active_root && VALID_PAGE(mmu->root_hpa))) {
		for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
			if ((roots_to_free & KVM_MMU_ROOT_PREVIOUS(i)) &&
			    VALID_PAGE(mmu->prev_roots[i].hpa))
				break;

		if (i == KVM_MMU_NUM_PREV_ROOTS)
			return;
	}

	spin_lock(&vcpu->kvm->mmu_lock);

	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
		if (roots_to_free & KVM_MMU_ROOT_PREVIOUS(i))
			mmu_free_root_page(vcpu->kvm, &mmu->prev_roots[i].hpa,
					   &invalid_list);

	if (free_active_root) {
		if (mmu->shadow_root_level >= PT64_ROOT_4LEVEL &&
		    (mmu->root_level >= PT64_ROOT_4LEVEL || mmu->direct_map)) {
			mmu_free_root_page(vcpu->kvm, &mmu->root_hpa,
					   &invalid_list);
		} else {
			for (i = 0; i < 4; ++i)
				if (mmu->pae_root[i] != 0)
					mmu_free_root_page(vcpu->kvm,
							   &mmu->pae_root[i],
							   &invalid_list);
			mmu->root_hpa = INVALID_PAGE;
		}
		mmu->root_cr3 = 0;
	}

	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
	spin_unlock(&vcpu->kvm->mmu_lock);
}
EXPORT_SYMBOL_GPL(kvm_mmu_free_roots);

static int mmu_check_root(struct kvm_vcpu *vcpu, gfn_t root_gfn)
{
	int ret = 0;

	if (!kvm_is_visible_gfn(vcpu->kvm, root_gfn)) {
		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
		ret = 1;
	}

	return ret;
}

static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
{
	struct kvm_mmu_page *sp;
	unsigned i;

	if (vcpu->arch.mmu->shadow_root_level >= PT64_ROOT_4LEVEL) {
		spin_lock(&vcpu->kvm->mmu_lock);
		if(make_mmu_pages_available(vcpu) < 0) {
			spin_unlock(&vcpu->kvm->mmu_lock);
			return -ENOSPC;
		}
		sp = kvm_mmu_get_page(vcpu, 0, 0,
				vcpu->arch.mmu->shadow_root_level, 1, ACC_ALL);
		++sp->root_count;
		spin_unlock(&vcpu->kvm->mmu_lock);
		vcpu->arch.mmu->root_hpa = __pa(sp->spt);
	} else if (vcpu->arch.mmu->shadow_root_level == PT32E_ROOT_LEVEL) {
		for (i = 0; i < 4; ++i) {
			hpa_t root = vcpu->arch.mmu->pae_root[i];

			MMU_WARN_ON(VALID_PAGE(root));
			spin_lock(&vcpu->kvm->mmu_lock);
			if (make_mmu_pages_available(vcpu) < 0) {
				spin_unlock(&vcpu->kvm->mmu_lock);
				return -ENOSPC;
			}
			sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT),
					i << 30, PT32_ROOT_LEVEL, 1, ACC_ALL);
			root = __pa(sp->spt);
			++sp->root_count;
			spin_unlock(&vcpu->kvm->mmu_lock);
			vcpu->arch.mmu->pae_root[i] = root | PT_PRESENT_MASK;
		}
		vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->pae_root);
	} else
		BUG();
	vcpu->arch.mmu->root_cr3 = vcpu->arch.mmu->get_cr3(vcpu);

	return 0;
}

static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
{
	struct kvm_mmu_page *sp;
	u64 pdptr, pm_mask;
	gfn_t root_gfn, root_cr3;
	int i;

	root_cr3 = vcpu->arch.mmu->get_cr3(vcpu);
	root_gfn = root_cr3 >> PAGE_SHIFT;

	if (mmu_check_root(vcpu, root_gfn))
		return 1;

	/*
	 * Do we shadow a long mode page table? If so we need to
	 * write-protect the guests page table root.
	 */
	if (vcpu->arch.mmu->root_level >= PT64_ROOT_4LEVEL) {
		hpa_t root = vcpu->arch.mmu->root_hpa;

		MMU_WARN_ON(VALID_PAGE(root));

		spin_lock(&vcpu->kvm->mmu_lock);
		if (make_mmu_pages_available(vcpu) < 0) {
			spin_unlock(&vcpu->kvm->mmu_lock);
			return -ENOSPC;
		}
		sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
				vcpu->arch.mmu->shadow_root_level, 0, ACC_ALL);
		root = __pa(sp->spt);
		++sp->root_count;
		spin_unlock(&vcpu->kvm->mmu_lock);
		vcpu->arch.mmu->root_hpa = root;
		goto set_root_cr3;
	}

	/*
	 * We shadow a 32 bit page table. This may be a legacy 2-level
	 * or a PAE 3-level page table. In either case we need to be aware that
	 * the shadow page table may be a PAE or a long mode page table.
	 */
	pm_mask = PT_PRESENT_MASK;
	if (vcpu->arch.mmu->shadow_root_level == PT64_ROOT_4LEVEL)
		pm_mask |= PT_ACCESSED_MASK | PT_WRITABLE_MASK | PT_USER_MASK;

	for (i = 0; i < 4; ++i) {
		hpa_t root = vcpu->arch.mmu->pae_root[i];

		MMU_WARN_ON(VALID_PAGE(root));
		if (vcpu->arch.mmu->root_level == PT32E_ROOT_LEVEL) {
			pdptr = vcpu->arch.mmu->get_pdptr(vcpu, i);
			if (!(pdptr & PT_PRESENT_MASK)) {
				vcpu->arch.mmu->pae_root[i] = 0;
				continue;
			}
			root_gfn = pdptr >> PAGE_SHIFT;
			if (mmu_check_root(vcpu, root_gfn))
				return 1;
		}
		spin_lock(&vcpu->kvm->mmu_lock);
		if (make_mmu_pages_available(vcpu) < 0) {
			spin_unlock(&vcpu->kvm->mmu_lock);
			return -ENOSPC;
		}
		sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, PT32_ROOT_LEVEL,
				      0, ACC_ALL);
		root = __pa(sp->spt);
		++sp->root_count;
		spin_unlock(&vcpu->kvm->mmu_lock);

		vcpu->arch.mmu->pae_root[i] = root | pm_mask;
	}
	vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->pae_root);

	/*
	 * If we shadow a 32 bit page table with a long mode page
	 * table we enter this path.
	 */
	if (vcpu->arch.mmu->shadow_root_level == PT64_ROOT_4LEVEL) {
		if (vcpu->arch.mmu->lm_root == NULL) {
			/*
			 * The additional page necessary for this is only
			 * allocated on demand.
			 */

			u64 *lm_root;

			lm_root = (void*)get_zeroed_page(GFP_KERNEL_ACCOUNT);
			if (lm_root == NULL)
				return 1;

			lm_root[0] = __pa(vcpu->arch.mmu->pae_root) | pm_mask;

			vcpu->arch.mmu->lm_root = lm_root;
		}

		vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->lm_root);
	}

set_root_cr3:
	vcpu->arch.mmu->root_cr3 = root_cr3;

	return 0;
}

static int mmu_alloc_roots(struct kvm_vcpu *vcpu)
{
	if (vcpu->arch.mmu->direct_map)
		return mmu_alloc_direct_roots(vcpu);
	else
		return mmu_alloc_shadow_roots(vcpu);
}

void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
{
	int i;
	struct kvm_mmu_page *sp;

	if (vcpu->arch.mmu->direct_map)
		return;

	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
		return;

	vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);

	if (vcpu->arch.mmu->root_level >= PT64_ROOT_4LEVEL) {
		hpa_t root = vcpu->arch.mmu->root_hpa;
		sp = page_header(root);

		/*
		 * Even if another CPU was marking the SP as unsync-ed
		 * simultaneously, any guest page table changes are not
		 * guaranteed to be visible anyway until this VCPU issues a TLB
		 * flush strictly after those changes are made. We only need to
		 * ensure that the other CPU sets these flags before any actual
		 * changes to the page tables are made. The comments in
		 * mmu_need_write_protect() describe what could go wrong if this
		 * requirement isn't satisfied.
		 */
		if (!smp_load_acquire(&sp->unsync) &&
		    !smp_load_acquire(&sp->unsync_children))
			return;

		spin_lock(&vcpu->kvm->mmu_lock);
		kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);

		mmu_sync_children(vcpu, sp);

		kvm_mmu_audit(vcpu, AUDIT_POST_SYNC);
		spin_unlock(&vcpu->kvm->mmu_lock);
		return;
	}

	spin_lock(&vcpu->kvm->mmu_lock);
	kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);

	for (i = 0; i < 4; ++i) {
		hpa_t root = vcpu->arch.mmu->pae_root[i];

		if (root && VALID_PAGE(root)) {
			root &= PT64_BASE_ADDR_MASK;
			sp = page_header(root);
			mmu_sync_children(vcpu, sp);
		}
	}

	kvm_mmu_audit(vcpu, AUDIT_POST_SYNC);
	spin_unlock(&vcpu->kvm->mmu_lock);
}
EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots);

static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr,
				  u32 access, struct x86_exception *exception)
{
	if (exception)
		exception->error_code = 0;
	return vaddr;
}

static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gpa_t vaddr,
					 u32 access,
					 struct x86_exception *exception)
{
	if (exception)
		exception->error_code = 0;
	return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access, exception);
}

static bool
__is_rsvd_bits_set(struct rsvd_bits_validate *rsvd_check, u64 pte, int level)
{
	int bit7 = (pte >> 7) & 1, low6 = pte & 0x3f;

	return (pte & rsvd_check->rsvd_bits_mask[bit7][level-1]) |
		((rsvd_check->bad_mt_xwr & (1ull << low6)) != 0);
}

static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level)
{
	return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level);
}

static bool is_shadow_zero_bits_set(struct kvm_mmu *mmu, u64 spte, int level)
{
	return __is_rsvd_bits_set(&mmu->shadow_zero_check, spte, level);
}

static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct)
{
	/*
	 * A nested guest cannot use the MMIO cache if it is using nested
	 * page tables, because cr2 is a nGPA while the cache stores GPAs.
	 */
	if (mmu_is_nested(vcpu))
		return false;

	if (direct)
		return vcpu_match_mmio_gpa(vcpu, addr);

	return vcpu_match_mmio_gva(vcpu, addr);
}

/* return true if reserved bit is detected on spte. */
static bool
walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
{
	struct kvm_shadow_walk_iterator iterator;
	u64 sptes[PT64_ROOT_MAX_LEVEL], spte = 0ull;
	int root, leaf;
	bool reserved = false;

	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
		goto exit;

	walk_shadow_page_lockless_begin(vcpu);

	for (shadow_walk_init(&iterator, vcpu, addr),
		 leaf = root = iterator.level;
	     shadow_walk_okay(&iterator);
	     __shadow_walk_next(&iterator, spte)) {
		spte = mmu_spte_get_lockless(iterator.sptep);

		sptes[leaf - 1] = spte;
		leaf--;

		if (!is_shadow_present_pte(spte))
			break;

		reserved |= is_shadow_zero_bits_set(vcpu->arch.mmu, spte,
						    iterator.level);
	}

	walk_shadow_page_lockless_end(vcpu);

	if (reserved) {
		pr_err("%s: detect reserved bits on spte, addr 0x%llx, dump hierarchy:\n",
		       __func__, addr);
		while (root > leaf) {
			pr_err("------ spte 0x%llx level %d.\n",
			       sptes[root - 1], root);
			root--;
		}
	}
exit:
	*sptep = spte;
	return reserved;
}

static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct)
{
	u64 spte;
	bool reserved;

	if (mmio_info_in_cache(vcpu, addr, direct))
		return RET_PF_EMULATE;

	reserved = walk_shadow_page_get_mmio_spte(vcpu, addr, &spte);
	if (WARN_ON(reserved))
		return -EINVAL;

	if (is_mmio_spte(spte)) {
		gfn_t gfn = get_mmio_spte_gfn(spte);
		unsigned access = get_mmio_spte_access(spte);

		if (!check_mmio_spte(vcpu, spte))
			return RET_PF_INVALID;

		if (direct)
			addr = 0;

		trace_handle_mmio_page_fault(addr, gfn, access);
		vcpu_cache_mmio_info(vcpu, addr, gfn, access);
		return RET_PF_EMULATE;
	}

	/*
	 * If the page table is zapped by other cpus, let CPU fault again on
	 * the address.
	 */
	return RET_PF_RETRY;
}

static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu,
					 u32 error_code, gfn_t gfn)
{
	if (unlikely(error_code & PFERR_RSVD_MASK))
		return false;

	if (!(error_code & PFERR_PRESENT_MASK) ||
	      !(error_code & PFERR_WRITE_MASK))
		return false;

	/*
	 * guest is writing the page which is write tracked which can
	 * not be fixed by page fault handler.
	 */
	if (kvm_page_track_is_active(vcpu, gfn, KVM_PAGE_TRACK_WRITE))
		return true;

	return false;
}

static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr)
{
	struct kvm_shadow_walk_iterator iterator;
	u64 spte;

	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
		return;

	walk_shadow_page_lockless_begin(vcpu);
	for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) {
		clear_sp_write_flooding_count(iterator.sptep);
		if (!is_shadow_present_pte(spte))
			break;
	}
	walk_shadow_page_lockless_end(vcpu);
}

static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa,
				u32 error_code, bool prefault)
{
	gfn_t gfn = gpa >> PAGE_SHIFT;
	int r;

	/* Note, paging is disabled, ergo gva == gpa. */
	pgprintk("%s: gva %lx error %x\n", __func__, gpa, error_code);

	if (page_fault_handle_page_track(vcpu, error_code, gfn))
		return RET_PF_EMULATE;

	r = mmu_topup_memory_caches(vcpu);
	if (r)
		return r;

	MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa));


	return nonpaging_map(vcpu, gpa & PAGE_MASK,
			     error_code, gfn, prefault);
}

static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
				   gfn_t gfn)
{
	struct kvm_arch_async_pf arch;

	arch.token = (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id;
	arch.gfn = gfn;
	arch.direct_map = vcpu->arch.mmu->direct_map;
	arch.cr3 = vcpu->arch.mmu->get_cr3(vcpu);

	return kvm_setup_async_pf(vcpu, cr2_or_gpa,
				  kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
}

static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
			 gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write,
			 bool *writable)
{
	struct kvm_memory_slot *slot;
	bool async;

	/*
	 * Don't expose private memslots to L2.
	 */
	if (is_guest_mode(vcpu) && !kvm_is_visible_gfn(vcpu->kvm, gfn)) {
		*pfn = KVM_PFN_NOSLOT;
		return false;
	}

	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
	async = false;
	*pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, write, writable);
	if (!async)
		return false; /* *pfn has correct page already */

	if (!prefault && kvm_can_do_async_pf(vcpu)) {
		trace_kvm_try_async_get_page(cr2_or_gpa, gfn);
		if (kvm_find_async_pf_gfn(vcpu, gfn)) {
			trace_kvm_async_pf_doublefault(cr2_or_gpa, gfn);
			kvm_make_request(KVM_REQ_APF_HALT, vcpu);
			return true;
		} else if (kvm_arch_setup_async_pf(vcpu, cr2_or_gpa, gfn))
			return true;
	}

	*pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL, write, writable);
	return false;
}

int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
				u64 fault_address, char *insn, int insn_len)
{
	int r = 1;

#ifndef CONFIG_X86_64
	/* A 64-bit CR2 should be impossible on 32-bit KVM. */
	if (WARN_ON_ONCE(fault_address >> 32))
		return -EFAULT;
#endif

	vcpu->arch.l1tf_flush_l1d = true;
	switch (vcpu->arch.apf.host_apf_reason) {
	default:
		trace_kvm_page_fault(fault_address, error_code);

		if (kvm_event_needs_reinjection(vcpu))
			kvm_mmu_unprotect_page_virt(vcpu, fault_address);
		r = kvm_mmu_page_fault(vcpu, fault_address, error_code, insn,
				insn_len);
		break;
	case KVM_PV_REASON_PAGE_NOT_PRESENT:
		vcpu->arch.apf.host_apf_reason = 0;
		local_irq_disable();
		kvm_async_pf_task_wait(fault_address, 0);
		local_irq_enable();
		break;
	case KVM_PV_REASON_PAGE_READY:
		vcpu->arch.apf.host_apf_reason = 0;
		local_irq_disable();
		kvm_async_pf_task_wake(fault_address);
		local_irq_enable();
		break;
	}
	return r;
}
EXPORT_SYMBOL_GPL(kvm_handle_page_fault);

static bool
check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level)
{
	int page_num = KVM_PAGES_PER_HPAGE(level);

	gfn &= ~(page_num - 1);

	return kvm_mtrr_check_gfn_range_consistency(vcpu, gfn, page_num);
}

static int tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
			  bool prefault)
{
	kvm_pfn_t pfn;
	int r;
	int level;
	bool force_pt_level;
	gfn_t gfn = gpa >> PAGE_SHIFT;
	unsigned long mmu_seq;
	int write = error_code & PFERR_WRITE_MASK;
	bool map_writable;
	bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
				is_nx_huge_page_enabled();

	MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa));

	if (page_fault_handle_page_track(vcpu, error_code, gfn))
		return RET_PF_EMULATE;

	r = mmu_topup_memory_caches(vcpu);
	if (r)
		return r;

	force_pt_level =
		lpage_disallowed ||
		!check_hugepage_cache_consistency(vcpu, gfn, PT_DIRECTORY_LEVEL);
	level = mapping_level(vcpu, gfn, &force_pt_level);
	if (likely(!force_pt_level)) {
		if (level > PT_DIRECTORY_LEVEL &&
		    !check_hugepage_cache_consistency(vcpu, gfn, level))
			level = PT_DIRECTORY_LEVEL;
		gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
	}

	if (fast_page_fault(vcpu, gpa, level, error_code))
		return RET_PF_RETRY;

	mmu_seq = vcpu->kvm->mmu_notifier_seq;
	smp_rmb();

	if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable))
		return RET_PF_RETRY;

	if (handle_abnormal_pfn(vcpu, 0, gfn, pfn, ACC_ALL, &r))
		return r;

	r = RET_PF_RETRY;
	spin_lock(&vcpu->kvm->mmu_lock);
	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
		goto out_unlock;
	if (make_mmu_pages_available(vcpu) < 0)
		goto out_unlock;
	if (likely(!force_pt_level))
		transparent_hugepage_adjust(vcpu, gfn, &pfn, &level);
	r = __direct_map(vcpu, gpa, write, map_writable, level, pfn,
			 prefault, lpage_disallowed);
out_unlock:
	spin_unlock(&vcpu->kvm->mmu_lock);
	kvm_release_pfn_clean(pfn);
	return r;
}

static void nonpaging_init_context(struct kvm_vcpu *vcpu,
				   struct kvm_mmu *context)
{
	context->page_fault = nonpaging_page_fault;
	context->gva_to_gpa = nonpaging_gva_to_gpa;
	context->sync_page = nonpaging_sync_page;
	context->invlpg = nonpaging_invlpg;
	context->root_level = 0;
	context->shadow_root_level = PT32E_ROOT_LEVEL;
	context->direct_map = true;
	context->nx = false;
}

/*
 * Find out if a previously cached root matching the new CR3/role is available.
 * The current root is also inserted into the cache.
 * If a matching root was found, it is assigned to kvm_mmu->root_hpa and true is
 * returned.
 * Otherwise, the LRU root from the cache is assigned to kvm_mmu->root_hpa and
 * false is returned. This root should now be freed by the caller.
 */
static bool cached_root_available(struct kvm_vcpu *vcpu, gpa_t new_cr3,
				  union kvm_mmu_page_role new_role)
{
	uint i;
	struct kvm_mmu_root_info root;
	struct kvm_mmu *mmu = vcpu->arch.mmu;

	root.cr3 = mmu->root_cr3;
	root.hpa = mmu->root_hpa;

	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) {
		swap(root, mmu->prev_roots[i]);

		if (new_cr3 == root.cr3 && VALID_PAGE(root.hpa) &&
		    page_header(root.hpa) != NULL &&
		    new_role.word == page_header(root.hpa)->role.word)
			break;
	}

	mmu->root_hpa = root.hpa;
	mmu->root_cr3 = root.cr3;

	return i < KVM_MMU_NUM_PREV_ROOTS;
}

static bool fast_cr3_switch(struct kvm_vcpu *vcpu, gpa_t new_cr3,
			    union kvm_mmu_page_role new_role,
			    bool skip_tlb_flush)
{
	struct kvm_mmu *mmu = vcpu->arch.mmu;

	/*
	 * For now, limit the fast switch to 64-bit hosts+VMs in order to avoid
	 * having to deal with PDPTEs. We may add support for 32-bit hosts/VMs
	 * later if necessary.
	 */
	if (mmu->shadow_root_level >= PT64_ROOT_4LEVEL &&
	    mmu->root_level >= PT64_ROOT_4LEVEL) {
		if (mmu_check_root(vcpu, new_cr3 >> PAGE_SHIFT))
			return false;

		if (cached_root_available(vcpu, new_cr3, new_role)) {
			/*
			 * It is possible that the cached previous root page is
			 * obsolete because of a change in the MMU generation
			 * number. However, changing the generation number is
			 * accompanied by KVM_REQ_MMU_RELOAD, which will free
			 * the root set here and allocate a new one.
			 */
			kvm_make_request(KVM_REQ_LOAD_CR3, vcpu);
			if (!skip_tlb_flush) {
				kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
				kvm_x86_ops->tlb_flush(vcpu, true);
			}

			/*
			 * The last MMIO access's GVA and GPA are cached in the
			 * VCPU. When switching to a new CR3, that GVA->GPA
			 * mapping may no longer be valid. So clear any cached
			 * MMIO info even when we don't need to sync the shadow
			 * page tables.
			 */
			vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);

			__clear_sp_write_flooding_count(
				page_header(mmu->root_hpa));

			return true;
		}
	}

	return false;
}

static void __kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3,
			      union kvm_mmu_page_role new_role,
			      bool skip_tlb_flush)
{
	if (!fast_cr3_switch(vcpu, new_cr3, new_role, skip_tlb_flush))
		kvm_mmu_free_roots(vcpu, vcpu->arch.mmu,
				   KVM_MMU_ROOT_CURRENT);
}

void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3, bool skip_tlb_flush)
{
	__kvm_mmu_new_cr3(vcpu, new_cr3, kvm_mmu_calc_root_page_role(vcpu),
			  skip_tlb_flush);
}
EXPORT_SYMBOL_GPL(kvm_mmu_new_cr3);

static unsigned long get_cr3(struct kvm_vcpu *vcpu)
{
	return kvm_read_cr3(vcpu);
}

static void inject_page_fault(struct kvm_vcpu *vcpu,
			      struct x86_exception *fault)
{
	vcpu->arch.mmu->inject_page_fault(vcpu, fault);
}

static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
			   unsigned access, int *nr_present)
{
	if (unlikely(is_mmio_spte(*sptep))) {
		if (gfn != get_mmio_spte_gfn(*sptep)) {
			mmu_spte_clear_no_track(sptep);
			return true;
		}

		(*nr_present)++;
		mark_mmio_spte(vcpu, sptep, gfn, access);
		return true;
	}

	return false;
}

static inline bool is_last_gpte(struct kvm_mmu *mmu,
				unsigned level, unsigned gpte)
{
	/*
	 * The RHS has bit 7 set iff level < mmu->last_nonleaf_level.
	 * If it is clear, there are no large pages at this level, so clear
	 * PT_PAGE_SIZE_MASK in gpte if that is the case.
	 */
	gpte &= level - mmu->last_nonleaf_level;

	/*
	 * PT_PAGE_TABLE_LEVEL always terminates.  The RHS has bit 7 set
	 * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means
	 * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then.
	 */
	gpte |= level - PT_PAGE_TABLE_LEVEL - 1;

	return gpte & PT_PAGE_SIZE_MASK;
}

#define PTTYPE_EPT 18 /* arbitrary */
#define PTTYPE PTTYPE_EPT
#include "paging_tmpl.h"
#undef PTTYPE

#define PTTYPE 64
#include "paging_tmpl.h"
#undef PTTYPE

#define PTTYPE 32
#include "paging_tmpl.h"
#undef PTTYPE

static void
__reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
			struct rsvd_bits_validate *rsvd_check,
			int maxphyaddr, int level, bool nx, bool gbpages,
			bool pse, bool amd)
{
	u64 exb_bit_rsvd = 0;
	u64 gbpages_bit_rsvd = 0;
	u64 nonleaf_bit8_rsvd = 0;

	rsvd_check->bad_mt_xwr = 0;

	if (!nx)
		exb_bit_rsvd = rsvd_bits(63, 63);
	if (!gbpages)
		gbpages_bit_rsvd = rsvd_bits(7, 7);

	/*
	 * Non-leaf PML4Es and PDPEs reserve bit 8 (which would be the G bit for
	 * leaf entries) on AMD CPUs only.
	 */
	if (amd)
		nonleaf_bit8_rsvd = rsvd_bits(8, 8);

	switch (level) {
	case PT32_ROOT_LEVEL:
		/* no rsvd bits for 2 level 4K page table entries */
		rsvd_check->rsvd_bits_mask[0][1] = 0;
		rsvd_check->rsvd_bits_mask[0][0] = 0;
		rsvd_check->rsvd_bits_mask[1][0] =
			rsvd_check->rsvd_bits_mask[0][0];

		if (!pse) {
			rsvd_check->rsvd_bits_mask[1][1] = 0;
			break;
		}

		if (is_cpuid_PSE36())
			/* 36bits PSE 4MB page */
			rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(17, 21);
		else
			/* 32 bits PSE 4MB page */
			rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(13, 21);
		break;
	case PT32E_ROOT_LEVEL:
		rsvd_check->rsvd_bits_mask[0][2] =
			rsvd_bits(maxphyaddr, 63) |
			rsvd_bits(5, 8) | rsvd_bits(1, 2);	/* PDPTE */
		rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd |
			rsvd_bits(maxphyaddr, 62);	/* PDE */
		rsvd_check->rsvd_bits_mask[0][0] = exb_bit_rsvd |
			rsvd_bits(maxphyaddr, 62); 	/* PTE */
		rsvd_check->rsvd_bits_mask[1][1] = exb_bit_rsvd |
			rsvd_bits(maxphyaddr, 62) |
			rsvd_bits(13, 20);		/* large page */
		rsvd_check->rsvd_bits_mask[1][0] =
			rsvd_check->rsvd_bits_mask[0][0];
		break;
	case PT64_ROOT_5LEVEL:
		rsvd_check->rsvd_bits_mask[0][4] = exb_bit_rsvd |
			nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
			rsvd_bits(maxphyaddr, 51);
		rsvd_check->rsvd_bits_mask[1][4] =
			rsvd_check->rsvd_bits_mask[0][4];
		/* fall through */
	case PT64_ROOT_4LEVEL:
		rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd |
			nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
			rsvd_bits(maxphyaddr, 51);
		rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd |
			gbpages_bit_rsvd |
			rsvd_bits(maxphyaddr, 51);
		rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd |
			rsvd_bits(maxphyaddr, 51);
		rsvd_check->rsvd_bits_mask[0][0] = exb_bit_rsvd |
			rsvd_bits(maxphyaddr, 51);
		rsvd_check->rsvd_bits_mask[1][3] =
			rsvd_check->rsvd_bits_mask[0][3];
		rsvd_check->rsvd_bits_mask[1][2] = exb_bit_rsvd |
			gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51) |
			rsvd_bits(13, 29);
		rsvd_check->rsvd_bits_mask[1][1] = exb_bit_rsvd |
			rsvd_bits(maxphyaddr, 51) |
			rsvd_bits(13, 20);		/* large page */
		rsvd_check->rsvd_bits_mask[1][0] =
			rsvd_check->rsvd_bits_mask[0][0];
		break;
	}
}

static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
				  struct kvm_mmu *context)
{
	__reset_rsvds_bits_mask(vcpu, &context->guest_rsvd_check,
				cpuid_maxphyaddr(vcpu), context->root_level,
				context->nx,
				guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES),
				is_pse(vcpu), guest_cpuid_is_amd(vcpu));
}

static void
__reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check,
			    int maxphyaddr, bool execonly)
{
	u64 bad_mt_xwr;

	rsvd_check->rsvd_bits_mask[0][4] =
		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7);
	rsvd_check->rsvd_bits_mask[0][3] =
		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7);
	rsvd_check->rsvd_bits_mask[0][2] =
		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6);
	rsvd_check->rsvd_bits_mask[0][1] =
		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6);
	rsvd_check->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51);

	/* large page */
	rsvd_check->rsvd_bits_mask[1][4] = rsvd_check->rsvd_bits_mask[0][4];
	rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3];
	rsvd_check->rsvd_bits_mask[1][2] =
		rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 29);
	rsvd_check->rsvd_bits_mask[1][1] =
		rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 20);
	rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0];

	bad_mt_xwr = 0xFFull << (2 * 8);	/* bits 3..5 must not be 2 */
	bad_mt_xwr |= 0xFFull << (3 * 8);	/* bits 3..5 must not be 3 */
	bad_mt_xwr |= 0xFFull << (7 * 8);	/* bits 3..5 must not be 7 */
	bad_mt_xwr |= REPEAT_BYTE(1ull << 2);	/* bits 0..2 must not be 010 */
	bad_mt_xwr |= REPEAT_BYTE(1ull << 6);	/* bits 0..2 must not be 110 */
	if (!execonly) {
		/* bits 0..2 must not be 100 unless VMX capabilities allow it */
		bad_mt_xwr |= REPEAT_BYTE(1ull << 4);
	}
	rsvd_check->bad_mt_xwr = bad_mt_xwr;
}

static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
		struct kvm_mmu *context, bool execonly)
{
	__reset_rsvds_bits_mask_ept(&context->guest_rsvd_check,
				    cpuid_maxphyaddr(vcpu), execonly);
}

/*
 * the page table on host is the shadow page table for the page
 * table in guest or amd nested guest, its mmu features completely
 * follow the features in guest.
 */
void
reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
{
	/*
	 * KVM uses NX when TDP is disabled to handle a variety of scenarios,
	 * notably for huge SPTEs if iTLB multi-hit mitigation is enabled and
	 * to generate correct permissions for CR0.WP=0/CR4.SMEP=1/EFER.NX=0.
	 * The iTLB multi-hit workaround can be toggled at any time, so assume
	 * NX can be used by any non-nested shadow MMU to avoid having to reset
	 * MMU contexts.  Note, KVM forces EFER.NX=1 when TDP is disabled.
	 */
	bool uses_nx = context->nx || !tdp_enabled ||
		context->mmu_role.base.smep_andnot_wp;
	struct rsvd_bits_validate *shadow_zero_check;
	int i;

	/*
	 * Passing "true" to the last argument is okay; it adds a check
	 * on bit 8 of the SPTEs which KVM doesn't use anyway.
	 */
	shadow_zero_check = &context->shadow_zero_check;
	__reset_rsvds_bits_mask(vcpu, shadow_zero_check,
				shadow_phys_bits,
				context->shadow_root_level, uses_nx,
				guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES),
				is_pse(vcpu), true);

	if (!shadow_me_mask)
		return;

	for (i = context->shadow_root_level; --i >= 0;) {
		shadow_zero_check->rsvd_bits_mask[0][i] &= ~shadow_me_mask;
		shadow_zero_check->rsvd_bits_mask[1][i] &= ~shadow_me_mask;
	}

}
EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask);

static inline bool boot_cpu_is_amd(void)
{
	WARN_ON_ONCE(!tdp_enabled);
	return shadow_x_mask == 0;
}

/*
 * the direct page table on host, use as much mmu features as
 * possible, however, kvm currently does not do execution-protection.
 */
static void
reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
				struct kvm_mmu *context)
{
	struct rsvd_bits_validate *shadow_zero_check;
	int i;

	shadow_zero_check = &context->shadow_zero_check;

	if (boot_cpu_is_amd())
		__reset_rsvds_bits_mask(vcpu, shadow_zero_check,
					shadow_phys_bits,
					context->shadow_root_level, false,
					boot_cpu_has(X86_FEATURE_GBPAGES),
					true, true);
	else
		__reset_rsvds_bits_mask_ept(shadow_zero_check,
					    shadow_phys_bits,
					    false);

	if (!shadow_me_mask)
		return;

	for (i = context->shadow_root_level; --i >= 0;) {
		shadow_zero_check->rsvd_bits_mask[0][i] &= ~shadow_me_mask;
		shadow_zero_check->rsvd_bits_mask[1][i] &= ~shadow_me_mask;
	}
}

/*
 * as the comments in reset_shadow_zero_bits_mask() except it
 * is the shadow page table for intel nested guest.
 */
static void
reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
				struct kvm_mmu *context, bool execonly)
{
	__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
				    shadow_phys_bits, execonly);
}

#define BYTE_MASK(access) \
	((1 & (access) ? 2 : 0) | \
	 (2 & (access) ? 4 : 0) | \
	 (3 & (access) ? 8 : 0) | \
	 (4 & (access) ? 16 : 0) | \
	 (5 & (access) ? 32 : 0) | \
	 (6 & (access) ? 64 : 0) | \
	 (7 & (access) ? 128 : 0))


static void update_permission_bitmask(struct kvm_vcpu *vcpu,
				      struct kvm_mmu *mmu, bool ept)
{
	unsigned byte;

	const u8 x = BYTE_MASK(ACC_EXEC_MASK);
	const u8 w = BYTE_MASK(ACC_WRITE_MASK);
	const u8 u = BYTE_MASK(ACC_USER_MASK);

	bool cr4_smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP) != 0;
	bool cr4_smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP) != 0;
	bool cr0_wp = is_write_protection(vcpu);

	for (byte = 0; byte < ARRAY_SIZE(mmu->permissions); ++byte) {
		unsigned pfec = byte << 1;

		/*
		 * Each "*f" variable has a 1 bit for each UWX value
		 * that causes a fault with the given PFEC.
		 */

		/* Faults from writes to non-writable pages */
		u8 wf = (pfec & PFERR_WRITE_MASK) ? (u8)~w : 0;
		/* Faults from user mode accesses to supervisor pages */
		u8 uf = (pfec & PFERR_USER_MASK) ? (u8)~u : 0;
		/* Faults from fetches of non-executable pages*/
		u8 ff = (pfec & PFERR_FETCH_MASK) ? (u8)~x : 0;
		/* Faults from kernel mode fetches of user pages */
		u8 smepf = 0;
		/* Faults from kernel mode accesses of user pages */
		u8 smapf = 0;

		if (!ept) {
			/* Faults from kernel mode accesses to user pages */
			u8 kf = (pfec & PFERR_USER_MASK) ? 0 : u;

			/* Not really needed: !nx will cause pte.nx to fault */
			if (!mmu->nx)
				ff = 0;

			/* Allow supervisor writes if !cr0.wp */
			if (!cr0_wp)
				wf = (pfec & PFERR_USER_MASK) ? wf : 0;

			/* Disallow supervisor fetches of user code if cr4.smep */
			if (cr4_smep)
				smepf = (pfec & PFERR_FETCH_MASK) ? kf : 0;

			/*
			 * SMAP:kernel-mode data accesses from user-mode
			 * mappings should fault. A fault is considered
			 * as a SMAP violation if all of the following
			 * conditions are true:
			 *   - X86_CR4_SMAP is set in CR4
			 *   - A user page is accessed
			 *   - The access is not a fetch
			 *   - Page fault in kernel mode
			 *   - if CPL = 3 or X86_EFLAGS_AC is clear
			 *
			 * Here, we cover the first three conditions.
			 * The fourth is computed dynamically in permission_fault();
			 * PFERR_RSVD_MASK bit will be set in PFEC if the access is
			 * *not* subject to SMAP restrictions.
			 */
			if (cr4_smap)
				smapf = (pfec & (PFERR_RSVD_MASK|PFERR_FETCH_MASK)) ? 0 : kf;
		}

		mmu->permissions[byte] = ff | uf | wf | smepf | smapf;
	}
}

/*
* PKU is an additional mechanism by which the paging controls access to
* user-mode addresses based on the value in the PKRU register.  Protection
* key violations are reported through a bit in the page fault error code.
* Unlike other bits of the error code, the PK bit is not known at the
* call site of e.g. gva_to_gpa; it must be computed directly in
* permission_fault based on two bits of PKRU, on some machine state (CR4,
* CR0, EFER, CPL), and on other bits of the error code and the page tables.
*
* In particular the following conditions come from the error code, the
* page tables and the machine state:
* - PK is always zero unless CR4.PKE=1 and EFER.LMA=1
* - PK is always zero if RSVD=1 (reserved bit set) or F=1 (instruction fetch)
* - PK is always zero if U=0 in the page tables
* - PKRU.WD is ignored if CR0.WP=0 and the access is a supervisor access.
*
* The PKRU bitmask caches the result of these four conditions.  The error
* code (minus the P bit) and the page table's U bit form an index into the
* PKRU bitmask.  Two bits of the PKRU bitmask are then extracted and ANDed
* with the two bits of the PKRU register corresponding to the protection key.
* For the first three conditions above the bits will be 00, thus masking
* away both AD and WD.  For all reads or if the last condition holds, WD
* only will be masked away.
*/
static void update_pkru_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
				bool ept)
{
	unsigned bit;
	bool wp;

	if (ept) {
		mmu->pkru_mask = 0;
		return;
	}

	/* PKEY is enabled only if CR4.PKE and EFER.LMA are both set. */
	if (!kvm_read_cr4_bits(vcpu, X86_CR4_PKE) || !is_long_mode(vcpu)) {
		mmu->pkru_mask = 0;
		return;
	}

	wp = is_write_protection(vcpu);

	for (bit = 0; bit < ARRAY_SIZE(mmu->permissions); ++bit) {
		unsigned pfec, pkey_bits;
		bool check_pkey, check_write, ff, uf, wf, pte_user;

		pfec = bit << 1;
		ff = pfec & PFERR_FETCH_MASK;
		uf = pfec & PFERR_USER_MASK;
		wf = pfec & PFERR_WRITE_MASK;

		/* PFEC.RSVD is replaced by ACC_USER_MASK. */
		pte_user = pfec & PFERR_RSVD_MASK;

		/*
		 * Only need to check the access which is not an
		 * instruction fetch and is to a user page.
		 */
		check_pkey = (!ff && pte_user);
		/*
		 * write access is controlled by PKRU if it is a
		 * user access or CR0.WP = 1.
		 */
		check_write = check_pkey && wf && (uf || wp);

		/* PKRU.AD stops both read and write access. */
		pkey_bits = !!check_pkey;
		/* PKRU.WD stops write access. */
		pkey_bits |= (!!check_write) << 1;

		mmu->pkru_mask |= (pkey_bits & 3) << pfec;
	}
}

static void update_last_nonleaf_level(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
{
	unsigned root_level = mmu->root_level;

	mmu->last_nonleaf_level = root_level;
	if (root_level == PT32_ROOT_LEVEL && is_pse(vcpu))
		mmu->last_nonleaf_level++;
}

static void paging64_init_context_common(struct kvm_vcpu *vcpu,
					 struct kvm_mmu *context,
					 int level)
{
	context->nx = is_nx(vcpu);
	context->root_level = level;

	reset_rsvds_bits_mask(vcpu, context);
	update_permission_bitmask(vcpu, context, false);
	update_pkru_bitmask(vcpu, context, false);
	update_last_nonleaf_level(vcpu, context);

	MMU_WARN_ON(!is_pae(vcpu));
	context->page_fault = paging64_page_fault;
	context->gva_to_gpa = paging64_gva_to_gpa;
	context->sync_page = paging64_sync_page;
	context->invlpg = paging64_invlpg;
	context->shadow_root_level = level;
	context->direct_map = false;
}

static void paging64_init_context(struct kvm_vcpu *vcpu,
				  struct kvm_mmu *context)
{
	int root_level = is_la57_mode(vcpu) ?
			 PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL;

	paging64_init_context_common(vcpu, context, root_level);
}

static void paging32_init_context(struct kvm_vcpu *vcpu,
				  struct kvm_mmu *context)
{
	context->nx = false;
	context->root_level = PT32_ROOT_LEVEL;

	reset_rsvds_bits_mask(vcpu, context);
	update_permission_bitmask(vcpu, context, false);
	update_pkru_bitmask(vcpu, context, false);
	update_last_nonleaf_level(vcpu, context);

	context->page_fault = paging32_page_fault;
	context->gva_to_gpa = paging32_gva_to_gpa;
	context->sync_page = paging32_sync_page;
	context->invlpg = paging32_invlpg;
	context->shadow_root_level = PT32E_ROOT_LEVEL;
	context->direct_map = false;
}

static void paging32E_init_context(struct kvm_vcpu *vcpu,
				   struct kvm_mmu *context)
{
	paging64_init_context_common(vcpu, context, PT32E_ROOT_LEVEL);
}

static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu)
{
	union kvm_mmu_extended_role ext = {0};

	ext.cr0_pg = !!is_paging(vcpu);
	ext.cr4_pae = !!is_pae(vcpu);
	ext.cr4_smep = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
	ext.cr4_smap = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
	ext.cr4_pse = !!is_pse(vcpu);
	ext.cr4_pke = !!kvm_read_cr4_bits(vcpu, X86_CR4_PKE);
	ext.cr4_la57 = !!kvm_read_cr4_bits(vcpu, X86_CR4_LA57);
	ext.maxphyaddr = cpuid_maxphyaddr(vcpu);

	ext.valid = 1;

	return ext;
}

static union kvm_mmu_role kvm_calc_mmu_role_common(struct kvm_vcpu *vcpu,
						   bool base_only)
{
	union kvm_mmu_role role = {0};

	role.base.access = ACC_ALL;
	role.base.nxe = !!is_nx(vcpu);
	role.base.cr0_wp = is_write_protection(vcpu);
	role.base.smm = is_smm(vcpu);
	role.base.guest_mode = is_guest_mode(vcpu);

	if (base_only)
		return role;

	role.ext = kvm_calc_mmu_role_ext(vcpu);

	return role;
}

static union kvm_mmu_role
kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only)
{
	union kvm_mmu_role role = kvm_calc_mmu_role_common(vcpu, base_only);

	role.base.ad_disabled = (shadow_accessed_mask == 0);
	role.base.level = kvm_x86_ops->get_tdp_level(vcpu);
	role.base.direct = true;
	role.base.gpte_is_8_bytes = true;

	return role;
}

static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
{
	struct kvm_mmu *context = vcpu->arch.mmu;
	union kvm_mmu_role new_role =
		kvm_calc_tdp_mmu_root_page_role(vcpu, false);

	new_role.base.word &= mmu_base_role_mask.word;
	if (new_role.as_u64 == context->mmu_role.as_u64)
		return;

	context->mmu_role.as_u64 = new_role.as_u64;
	context->page_fault = tdp_page_fault;
	context->sync_page = nonpaging_sync_page;
	context->invlpg = nonpaging_invlpg;
	context->shadow_root_level = kvm_x86_ops->get_tdp_level(vcpu);
	context->direct_map = true;
	context->set_cr3 = kvm_x86_ops->set_tdp_cr3;
	context->get_cr3 = get_cr3;
	context->get_pdptr = kvm_pdptr_read;
	context->inject_page_fault = kvm_inject_page_fault;

	if (!is_paging(vcpu)) {
		context->nx = false;
		context->gva_to_gpa = nonpaging_gva_to_gpa;
		context->root_level = 0;
	} else if (is_long_mode(vcpu)) {
		context->nx = is_nx(vcpu);
		context->root_level = is_la57_mode(vcpu) ?
				PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL;
		reset_rsvds_bits_mask(vcpu, context);
		context->gva_to_gpa = paging64_gva_to_gpa;
	} else if (is_pae(vcpu)) {
		context->nx = is_nx(vcpu);
		context->root_level = PT32E_ROOT_LEVEL;
		reset_rsvds_bits_mask(vcpu, context);
		context->gva_to_gpa = paging64_gva_to_gpa;
	} else {
		context->nx = false;
		context->root_level = PT32_ROOT_LEVEL;
		reset_rsvds_bits_mask(vcpu, context);
		context->gva_to_gpa = paging32_gva_to_gpa;
	}

	update_permission_bitmask(vcpu, context, false);
	update_pkru_bitmask(vcpu, context, false);
	update_last_nonleaf_level(vcpu, context);
	reset_tdp_shadow_zero_bits_mask(vcpu, context);
}

static union kvm_mmu_role
kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only)
{
	union kvm_mmu_role role = kvm_calc_mmu_role_common(vcpu, base_only);

	role.base.smep_andnot_wp = role.ext.cr4_smep &&
		!is_write_protection(vcpu);
	role.base.smap_andnot_wp = role.ext.cr4_smap &&
		!is_write_protection(vcpu);
	role.base.direct = !is_paging(vcpu);
	role.base.gpte_is_8_bytes = !!is_pae(vcpu);

	if (!is_long_mode(vcpu))
		role.base.level = PT32E_ROOT_LEVEL;
	else if (is_la57_mode(vcpu))
		role.base.level = PT64_ROOT_5LEVEL;
	else
		role.base.level = PT64_ROOT_4LEVEL;

	return role;
}

void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
{
	struct kvm_mmu *context = vcpu->arch.mmu;
	union kvm_mmu_role new_role =
		kvm_calc_shadow_mmu_root_page_role(vcpu, false);

	new_role.base.word &= mmu_base_role_mask.word;
	if (new_role.as_u64 == context->mmu_role.as_u64)
		return;

	if (!is_paging(vcpu))
		nonpaging_init_context(vcpu, context);
	else if (is_long_mode(vcpu))
		paging64_init_context(vcpu, context);
	else if (is_pae(vcpu))
		paging32E_init_context(vcpu, context);
	else
		paging32_init_context(vcpu, context);

	context->mmu_role.as_u64 = new_role.as_u64;
	reset_shadow_zero_bits_mask(vcpu, context);
}
EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);

static union kvm_mmu_role
kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty,
				   bool execonly)
{
	union kvm_mmu_role role = {0};

	/* SMM flag is inherited from root_mmu */
	role.base.smm = vcpu->arch.root_mmu.mmu_role.base.smm;

	role.base.level = PT64_ROOT_4LEVEL;
	role.base.gpte_is_8_bytes = true;
	role.base.direct = false;
	role.base.ad_disabled = !accessed_dirty;
	role.base.guest_mode = true;
	role.base.access = ACC_ALL;

	/*
	 * WP=1 and NOT_WP=1 is an impossible combination, use WP and the
	 * SMAP variation to denote shadow EPT entries.
	 */
	role.base.cr0_wp = true;
	role.base.smap_andnot_wp = true;

	role.ext = kvm_calc_mmu_role_ext(vcpu);
	role.ext.execonly = execonly;

	return role;
}

void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
			     bool accessed_dirty, gpa_t new_eptp)
{
	struct kvm_mmu *context = vcpu->arch.mmu;
	union kvm_mmu_role new_role =
		kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty,
						   execonly);

	__kvm_mmu_new_cr3(vcpu, new_eptp, new_role.base, false);

	new_role.base.word &= mmu_base_role_mask.word;
	if (new_role.as_u64 == context->mmu_role.as_u64)
		return;

	context->shadow_root_level = PT64_ROOT_4LEVEL;

	context->nx = true;
	context->ept_ad = accessed_dirty;
	context->page_fault = ept_page_fault;
	context->gva_to_gpa = ept_gva_to_gpa;
	context->sync_page = ept_sync_page;
	context->invlpg = ept_invlpg;
	context->root_level = PT64_ROOT_4LEVEL;
	context->direct_map = false;
	context->mmu_role.as_u64 = new_role.as_u64;

	update_permission_bitmask(vcpu, context, true);
	update_pkru_bitmask(vcpu, context, true);
	update_last_nonleaf_level(vcpu, context);
	reset_rsvds_bits_mask_ept(vcpu, context, execonly);
	reset_ept_shadow_zero_bits_mask(vcpu, context, execonly);
}
EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu);

static void init_kvm_softmmu(struct kvm_vcpu *vcpu)
{
	struct kvm_mmu *context = vcpu->arch.mmu;

	kvm_init_shadow_mmu(vcpu);
	context->set_cr3           = kvm_x86_ops->set_cr3;
	context->get_cr3           = get_cr3;
	context->get_pdptr         = kvm_pdptr_read;
	context->inject_page_fault = kvm_inject_page_fault;
}

static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
{
	union kvm_mmu_role new_role = kvm_calc_mmu_role_common(vcpu, false);
	struct kvm_mmu *g_context = &vcpu->arch.nested_mmu;

	new_role.base.word &= mmu_base_role_mask.word;
	if (new_role.as_u64 == g_context->mmu_role.as_u64)
		return;

	g_context->mmu_role.as_u64 = new_role.as_u64;
	g_context->get_cr3           = get_cr3;
	g_context->get_pdptr         = kvm_pdptr_read;
	g_context->inject_page_fault = kvm_inject_page_fault;

	/*
	 * Note that arch.mmu->gva_to_gpa translates l2_gpa to l1_gpa using
	 * L1's nested page tables (e.g. EPT12). The nested translation
	 * of l2_gva to l1_gpa is done by arch.nested_mmu.gva_to_gpa using
	 * L2's page tables as the first level of translation and L1's
	 * nested page tables as the second level of translation. Basically
	 * the gva_to_gpa functions between mmu and nested_mmu are swapped.
	 */
	if (!is_paging(vcpu)) {
		g_context->nx = false;
		g_context->root_level = 0;
		g_context->gva_to_gpa = nonpaging_gva_to_gpa_nested;
	} else if (is_long_mode(vcpu)) {
		g_context->nx = is_nx(vcpu);
		g_context->root_level = is_la57_mode(vcpu) ?
					PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL;
		reset_rsvds_bits_mask(vcpu, g_context);
		g_context->gva_to_gpa = paging64_gva_to_gpa_nested;
	} else if (is_pae(vcpu)) {
		g_context->nx = is_nx(vcpu);
		g_context->root_level = PT32E_ROOT_LEVEL;
		reset_rsvds_bits_mask(vcpu, g_context);
		g_context->gva_to_gpa = paging64_gva_to_gpa_nested;
	} else {
		g_context->nx = false;
		g_context->root_level = PT32_ROOT_LEVEL;
		reset_rsvds_bits_mask(vcpu, g_context);
		g_context->gva_to_gpa = paging32_gva_to_gpa_nested;
	}

	update_permission_bitmask(vcpu, g_context, false);
	update_pkru_bitmask(vcpu, g_context, false);
	update_last_nonleaf_level(vcpu, g_context);
}

void kvm_init_mmu(struct kvm_vcpu *vcpu, bool reset_roots)
{
	if (reset_roots) {
		uint i;

		vcpu->arch.mmu->root_hpa = INVALID_PAGE;

		for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
			vcpu->arch.mmu->prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
	}

	if (mmu_is_nested(vcpu))
		init_kvm_nested_mmu(vcpu);
	else if (tdp_enabled)
		init_kvm_tdp_mmu(vcpu);
	else
		init_kvm_softmmu(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_init_mmu);

static union kvm_mmu_page_role
kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu)
{
	union kvm_mmu_role role;

	if (tdp_enabled)
		role = kvm_calc_tdp_mmu_root_page_role(vcpu, true);
	else
		role = kvm_calc_shadow_mmu_root_page_role(vcpu, true);

	return role.base;
}

void kvm_mmu_reset_context(struct kvm_vcpu *vcpu)
{
	kvm_mmu_unload(vcpu);
	kvm_init_mmu(vcpu, true);
}
EXPORT_SYMBOL_GPL(kvm_mmu_reset_context);

int kvm_mmu_load(struct kvm_vcpu *vcpu)
{
	int r;

	r = mmu_topup_memory_caches(vcpu);
	if (r)
		goto out;
	r = mmu_alloc_roots(vcpu);
	kvm_mmu_sync_roots(vcpu);
	if (r)
		goto out;
	kvm_mmu_load_cr3(vcpu);
	kvm_x86_ops->tlb_flush(vcpu, true);
out:
	return r;
}
EXPORT_SYMBOL_GPL(kvm_mmu_load);

void kvm_mmu_unload(struct kvm_vcpu *vcpu)
{
	kvm_mmu_free_roots(vcpu, &vcpu->arch.root_mmu, KVM_MMU_ROOTS_ALL);
	WARN_ON(VALID_PAGE(vcpu->arch.root_mmu.root_hpa));
	kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
	WARN_ON(VALID_PAGE(vcpu->arch.guest_mmu.root_hpa));
}
EXPORT_SYMBOL_GPL(kvm_mmu_unload);

static bool need_remote_flush(u64 old, u64 new)
{
	if (!is_shadow_present_pte(old))
		return false;
	if (!is_shadow_present_pte(new))
		return true;
	if ((old ^ new) & PT64_BASE_ADDR_MASK)
		return true;
	old ^= shadow_nx_mask;
	new ^= shadow_nx_mask;
	return (old & ~new & PT64_PERM_MASK) != 0;
}

static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
				    int *bytes)
{
	u64 gentry = 0;
	int r;

	/*
	 * Assume that the pte write on a page table of the same type
	 * as the current vcpu paging mode since we update the sptes only
	 * when they have the same mode.
	 */
	if (is_pae(vcpu) && *bytes == 4) {
		/* Handle a 32-bit guest writing two halves of a 64-bit gpte */
		*gpa &= ~(gpa_t)7;
		*bytes = 8;
	}

	if (*bytes == 4 || *bytes == 8) {
		r = kvm_vcpu_read_guest_atomic(vcpu, *gpa, &gentry, *bytes);
		if (r)
			gentry = 0;
	}

	return gentry;
}

/*
 * If we're seeing too many writes to a page, it may no longer be a page table,
 * or we may be forking, in which case it is better to unmap the page.
 */
static bool detect_write_flooding(struct kvm_mmu_page *sp)
{
	/*
	 * Skip write-flooding detected for the sp whose level is 1, because
	 * it can become unsync, then the guest page is not write-protected.
	 */
	if (sp->role.level == PT_PAGE_TABLE_LEVEL)
		return false;

	atomic_inc(&sp->write_flooding_count);
	return atomic_read(&sp->write_flooding_count) >= 3;
}

/*
 * Misaligned accesses are too much trouble to fix up; also, they usually
 * indicate a page is not used as a page table.
 */
static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa,
				    int bytes)
{
	unsigned offset, pte_size, misaligned;

	pgprintk("misaligned: gpa %llx bytes %d role %x\n",
		 gpa, bytes, sp->role.word);

	offset = offset_in_page(gpa);
	pte_size = sp->role.gpte_is_8_bytes ? 8 : 4;

	/*
	 * Sometimes, the OS only writes the last one bytes to update status
	 * bits, for example, in linux, andb instruction is used in clear_bit().
	 */
	if (!(offset & (pte_size - 1)) && bytes == 1)
		return false;

	misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1);
	misaligned |= bytes < 4;

	return misaligned;
}

static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte)
{
	unsigned page_offset, quadrant;
	u64 *spte;
	int level;

	page_offset = offset_in_page(gpa);
	level = sp->role.level;
	*nspte = 1;
	if (!sp->role.gpte_is_8_bytes) {
		page_offset <<= 1;	/* 32->64 */
		/*
		 * A 32-bit pde maps 4MB while the shadow pdes map
		 * only 2MB.  So we need to double the offset again
		 * and zap two pdes instead of one.
		 */
		if (level == PT32_ROOT_LEVEL) {
			page_offset &= ~7; /* kill rounding error */
			page_offset <<= 1;
			*nspte = 2;
		}
		quadrant = page_offset >> PAGE_SHIFT;
		page_offset &= ~PAGE_MASK;
		if (quadrant != sp->role.quadrant)
			return NULL;
	}

	spte = &sp->spt[page_offset / sizeof(*spte)];
	return spte;
}

static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
			      const u8 *new, int bytes,
			      struct kvm_page_track_notifier_node *node)
{
	gfn_t gfn = gpa >> PAGE_SHIFT;
	struct kvm_mmu_page *sp;
	LIST_HEAD(invalid_list);
	u64 entry, gentry, *spte;
	int npte;
	bool remote_flush, local_flush;

	/*
	 * If we don't have indirect shadow pages, it means no page is
	 * write-protected, so we can exit simply.
	 */
	if (!READ_ONCE(vcpu->kvm->arch.indirect_shadow_pages))
		return;

	remote_flush = local_flush = false;

	pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);

	/*
	 * No need to care whether allocation memory is successful
	 * or not since pte prefetch is skiped if it does not have
	 * enough objects in the cache.
	 */
	mmu_topup_memory_caches(vcpu);

	spin_lock(&vcpu->kvm->mmu_lock);

	gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, &bytes);

	++vcpu->kvm->stat.mmu_pte_write;
	kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);

	for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
		if (detect_write_misaligned(sp, gpa, bytes) ||
		      detect_write_flooding(sp)) {
			kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list);
			++vcpu->kvm->stat.mmu_flooded;
			continue;
		}

		spte = get_written_sptes(sp, gpa, &npte);
		if (!spte)
			continue;

		local_flush = true;
		while (npte--) {
			entry = *spte;
			mmu_page_zap_pte(vcpu->kvm, sp, spte);
			if (gentry && sp->role.level != PG_LEVEL_4K)
				++vcpu->kvm->stat.mmu_pde_zapped;
			if (need_remote_flush(entry, *spte))
				remote_flush = true;
			++spte;
		}
	}
	kvm_mmu_flush_or_zap(vcpu, &invalid_list, remote_flush, local_flush);
	kvm_mmu_audit(vcpu, AUDIT_POST_PTE_WRITE);
	spin_unlock(&vcpu->kvm->mmu_lock);
}

int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
{
	gpa_t gpa;
	int r;

	if (vcpu->arch.mmu->direct_map)
		return 0;

	gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL);

	r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT);

	return r;
}
EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt);

static int make_mmu_pages_available(struct kvm_vcpu *vcpu)
{
	LIST_HEAD(invalid_list);

	if (likely(kvm_mmu_available_pages(vcpu->kvm) >= KVM_MIN_FREE_MMU_PAGES))
		return 0;

	while (kvm_mmu_available_pages(vcpu->kvm) < KVM_REFILL_PAGES) {
		if (!prepare_zap_oldest_mmu_page(vcpu->kvm, &invalid_list))
			break;

		++vcpu->kvm->stat.mmu_recycled;
	}
	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);

	if (!kvm_mmu_available_pages(vcpu->kvm))
		return -ENOSPC;
	return 0;
}

int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
		       void *insn, int insn_len)
{
	int r, emulation_type = 0;
	bool direct = vcpu->arch.mmu->direct_map;

	/* With shadow page tables, fault_address contains a GVA or nGPA.  */
	if (vcpu->arch.mmu->direct_map) {
		vcpu->arch.gpa_available = true;
		vcpu->arch.gpa_val = cr2_or_gpa;
	}

	r = RET_PF_INVALID;
	if (unlikely(error_code & PFERR_RSVD_MASK)) {
		r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct);
		if (r == RET_PF_EMULATE)
			goto emulate;
	}

	if (r == RET_PF_INVALID) {
		r = vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa,
					       lower_32_bits(error_code),
					       false);
		WARN_ON(r == RET_PF_INVALID);
	}

	if (r == RET_PF_RETRY)
		return 1;
	if (r < 0)
		return r;

	/*
	 * Before emulating the instruction, check if the error code
	 * was due to a RO violation while translating the guest page.
	 * This can occur when using nested virtualization with nested
	 * paging in both guests. If true, we simply unprotect the page
	 * and resume the guest.
	 */
	if (vcpu->arch.mmu->direct_map &&
	    (error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) {
		kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2_or_gpa));
		return 1;
	}

	/*
	 * vcpu->arch.mmu.page_fault returned RET_PF_EMULATE, but we can still
	 * optimistically try to just unprotect the page and let the processor
	 * re-execute the instruction that caused the page fault.  Do not allow
	 * retrying MMIO emulation, as it's not only pointless but could also
	 * cause us to enter an infinite loop because the processor will keep
	 * faulting on the non-existent MMIO address.  Retrying an instruction
	 * from a nested guest is also pointless and dangerous as we are only
	 * explicitly shadowing L1's page tables, i.e. unprotecting something
	 * for L1 isn't going to magically fix whatever issue cause L2 to fail.
	 */
	if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu))
		emulation_type = EMULTYPE_ALLOW_RETRY;
emulate:
	/*
	 * On AMD platforms, under certain conditions insn_len may be zero on #NPF.
	 * This can happen if a guest gets a page-fault on data access but the HW
	 * table walker is not able to read the instruction page (e.g instruction
	 * page is not present in memory). In those cases we simply restart the
	 * guest, with the exception of AMD Erratum 1096 which is unrecoverable.
	 */
	if (unlikely(insn && !insn_len)) {
		if (!kvm_x86_ops->need_emulation_on_page_fault(vcpu))
			return 1;
	}

	return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn,
				       insn_len);
}
EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);

void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
{
	struct kvm_mmu *mmu = vcpu->arch.mmu;
	int i;

	/* INVLPG on a * non-canonical address is a NOP according to the SDM.  */
	if (is_noncanonical_address(gva, vcpu))
		return;

	mmu->invlpg(vcpu, gva, mmu->root_hpa);

	/*
	 * INVLPG is required to invalidate any global mappings for the VA,
	 * irrespective of PCID. Since it would take us roughly similar amount
	 * of work to determine whether any of the prev_root mappings of the VA
	 * is marked global, or to just sync it blindly, so we might as well
	 * just always sync it.
	 *
	 * Mappings not reachable via the current cr3 or the prev_roots will be
	 * synced when switching to that cr3, so nothing needs to be done here
	 * for them.
	 */
	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
		if (VALID_PAGE(mmu->prev_roots[i].hpa))
			mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa);

	kvm_x86_ops->tlb_flush_gva(vcpu, gva);
	++vcpu->stat.invlpg;
}
EXPORT_SYMBOL_GPL(kvm_mmu_invlpg);

void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid)
{
	struct kvm_mmu *mmu = vcpu->arch.mmu;
	bool tlb_flush = false;
	uint i;

	if (pcid == kvm_get_active_pcid(vcpu)) {
		mmu->invlpg(vcpu, gva, mmu->root_hpa);
		tlb_flush = true;
	}

	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) {
		if (VALID_PAGE(mmu->prev_roots[i].hpa) &&
		    pcid == kvm_get_pcid(vcpu, mmu->prev_roots[i].cr3)) {
			mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa);
			tlb_flush = true;
		}
	}

	if (tlb_flush)
		kvm_x86_ops->tlb_flush_gva(vcpu, gva);

	++vcpu->stat.invlpg;

	/*
	 * Mappings not reachable via the current cr3 or the prev_roots will be
	 * synced when switching to that cr3, so nothing needs to be done here
	 * for them.
	 */
}
EXPORT_SYMBOL_GPL(kvm_mmu_invpcid_gva);

void kvm_enable_tdp(void)
{
	tdp_enabled = true;
}
EXPORT_SYMBOL_GPL(kvm_enable_tdp);

void kvm_disable_tdp(void)
{
	tdp_enabled = false;
}
EXPORT_SYMBOL_GPL(kvm_disable_tdp);


/* The return value indicates if tlb flush on all vcpus is needed. */
typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head);

/* The caller should hold mmu-lock before calling this function. */
static __always_inline bool
slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot,
			slot_level_handler fn, int start_level, int end_level,
			gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb)
{
	struct slot_rmap_walk_iterator iterator;
	bool flush = false;

	for_each_slot_rmap_range(memslot, start_level, end_level, start_gfn,
			end_gfn, &iterator) {
		if (iterator.rmap)
			flush |= fn(kvm, iterator.rmap);

		if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
			if (flush && lock_flush_tlb) {
				kvm_flush_remote_tlbs_with_address(kvm,
						start_gfn,
						iterator.gfn - start_gfn + 1);
				flush = false;
			}
			cond_resched_lock(&kvm->mmu_lock);
		}
	}

	if (flush && lock_flush_tlb) {
		kvm_flush_remote_tlbs_with_address(kvm, start_gfn,
						   end_gfn - start_gfn + 1);
		flush = false;
	}

	return flush;
}

static __always_inline bool
slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
		  slot_level_handler fn, int start_level, int end_level,
		  bool lock_flush_tlb)
{
	return slot_handle_level_range(kvm, memslot, fn, start_level,
			end_level, memslot->base_gfn,
			memslot->base_gfn + memslot->npages - 1,
			lock_flush_tlb);
}

static __always_inline bool
slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
		      slot_level_handler fn, bool lock_flush_tlb)
{
	return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL,
				 PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb);
}

static __always_inline bool
slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
			slot_level_handler fn, bool lock_flush_tlb)
{
	return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL + 1,
				 PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb);
}

static __always_inline bool
slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot,
		 slot_level_handler fn, bool lock_flush_tlb)
{
	return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL,
				 PT_PAGE_TABLE_LEVEL, lock_flush_tlb);
}

static void free_mmu_pages(struct kvm_mmu *mmu)
{
	free_page((unsigned long)mmu->pae_root);
	free_page((unsigned long)mmu->lm_root);
}

static int alloc_mmu_pages(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
{
	struct page *page;
	int i;

	/*
	 * When using PAE paging, the four PDPTEs are treated as 'root' pages,
	 * while the PDP table is a per-vCPU construct that's allocated at MMU
	 * creation.  When emulating 32-bit mode, cr3 is only 32 bits even on
	 * x86_64.  Therefore we need to allocate the PDP table in the first
	 * 4GB of memory, which happens to fit the DMA32 zone.  Except for
	 * SVM's 32-bit NPT support, TDP paging doesn't use PAE paging and can
	 * skip allocating the PDP table.
	 */
	if (tdp_enabled && kvm_x86_ops->get_tdp_level(vcpu) > PT32E_ROOT_LEVEL)
		return 0;

	page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_DMA32);
	if (!page)
		return -ENOMEM;

	mmu->pae_root = page_address(page);
	for (i = 0; i < 4; ++i)
		mmu->pae_root[i] = INVALID_PAGE;

	return 0;
}

int kvm_mmu_create(struct kvm_vcpu *vcpu)
{
	uint i;
	int ret;

	vcpu->arch.mmu = &vcpu->arch.root_mmu;
	vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;

	vcpu->arch.root_mmu.root_hpa = INVALID_PAGE;
	vcpu->arch.root_mmu.root_cr3 = 0;
	vcpu->arch.root_mmu.translate_gpa = translate_gpa;
	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
		vcpu->arch.root_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;

	vcpu->arch.guest_mmu.root_hpa = INVALID_PAGE;
	vcpu->arch.guest_mmu.root_cr3 = 0;
	vcpu->arch.guest_mmu.translate_gpa = translate_gpa;
	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
		vcpu->arch.guest_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;

	vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa;

	ret = alloc_mmu_pages(vcpu, &vcpu->arch.guest_mmu);
	if (ret)
		return ret;

	ret = alloc_mmu_pages(vcpu, &vcpu->arch.root_mmu);
	if (ret)
		goto fail_allocate_root;

	return ret;
 fail_allocate_root:
	free_mmu_pages(&vcpu->arch.guest_mmu);
	return ret;
}

#define BATCH_ZAP_PAGES	10
static void kvm_zap_obsolete_pages(struct kvm *kvm)
{
	struct kvm_mmu_page *sp, *node;
	int nr_zapped, batch = 0;

restart:
	list_for_each_entry_safe_reverse(sp, node,
	      &kvm->arch.active_mmu_pages, link) {
		/*
		 * No obsolete valid page exists before a newly created page
		 * since active_mmu_pages is a FIFO list.
		 */
		if (!is_obsolete_sp(kvm, sp))
			break;

		/*
		 * Skip invalid pages with a non-zero root count, zapping pages
		 * with a non-zero root count will never succeed, i.e. the page
		 * will get thrown back on active_mmu_pages and we'll get stuck
		 * in an infinite loop.
		 */
		if (sp->role.invalid && sp->root_count)
			continue;

		/*
		 * No need to flush the TLB since we're only zapping shadow
		 * pages with an obsolete generation number and all vCPUS have
		 * loaded a new root, i.e. the shadow pages being zapped cannot
		 * be in active use by the guest.
		 */
		if (batch >= BATCH_ZAP_PAGES &&
		    cond_resched_lock(&kvm->mmu_lock)) {
			batch = 0;
			goto restart;
		}

		if (__kvm_mmu_prepare_zap_page(kvm, sp,
				&kvm->arch.zapped_obsolete_pages, &nr_zapped)) {
			batch += nr_zapped;
			goto restart;
		}
	}

	/*
	 * Trigger a remote TLB flush before freeing the page tables to ensure
	 * KVM is not in the middle of a lockless shadow page table walk, which
	 * may reference the pages.
	 */
	kvm_mmu_commit_zap_page(kvm, &kvm->arch.zapped_obsolete_pages);
}

/*
 * Fast invalidate all shadow pages and use lock-break technique
 * to zap obsolete pages.
 *
 * It's required when memslot is being deleted or VM is being
 * destroyed, in these cases, we should ensure that KVM MMU does
 * not use any resource of the being-deleted slot or all slots
 * after calling the function.
 */
static void kvm_mmu_zap_all_fast(struct kvm *kvm)
{
	lockdep_assert_held(&kvm->slots_lock);

	spin_lock(&kvm->mmu_lock);
	trace_kvm_mmu_zap_all_fast(kvm);

	/*
	 * Toggle mmu_valid_gen between '0' and '1'.  Because slots_lock is
	 * held for the entire duration of zapping obsolete pages, it's
	 * impossible for there to be multiple invalid generations associated
	 * with *valid* shadow pages at any given time, i.e. there is exactly
	 * one valid generation and (at most) one invalid generation.
	 */
	kvm->arch.mmu_valid_gen = kvm->arch.mmu_valid_gen ? 0 : 1;

	/*
	 * Notify all vcpus to reload its shadow page table and flush TLB.
	 * Then all vcpus will switch to new shadow page table with the new
	 * mmu_valid_gen.
	 *
	 * Note: we need to do this under the protection of mmu_lock,
	 * otherwise, vcpu would purge shadow page but miss tlb flush.
	 */
	kvm_reload_remote_mmus(kvm);

	kvm_zap_obsolete_pages(kvm);
	spin_unlock(&kvm->mmu_lock);
}

static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)
{
	return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages));
}

static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm,
			struct kvm_memory_slot *slot,
			struct kvm_page_track_notifier_node *node)
{
	kvm_mmu_zap_all_fast(kvm);
}

void kvm_mmu_init_vm(struct kvm *kvm)
{
	struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;

	node->track_write = kvm_mmu_pte_write;
	node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot;
	kvm_page_track_register_notifier(kvm, node);
}

void kvm_mmu_uninit_vm(struct kvm *kvm)
{
	struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;

	kvm_page_track_unregister_notifier(kvm, node);
}

void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
{
	struct kvm_memslots *slots;
	struct kvm_memory_slot *memslot;
	int i;

	spin_lock(&kvm->mmu_lock);
	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
		slots = __kvm_memslots(kvm, i);
		kvm_for_each_memslot(memslot, slots) {
			gfn_t start, end;

			start = max(gfn_start, memslot->base_gfn);
			end = min(gfn_end, memslot->base_gfn + memslot->npages);
			if (start >= end)
				continue;

			slot_handle_level_range(kvm, memslot, kvm_zap_rmapp,
						PT_PAGE_TABLE_LEVEL, PT_MAX_HUGEPAGE_LEVEL,
						start, end - 1, true);
		}
	}

	spin_unlock(&kvm->mmu_lock);
}

static bool slot_rmap_write_protect(struct kvm *kvm,
				    struct kvm_rmap_head *rmap_head)
{
	return __rmap_write_protect(kvm, rmap_head, false);
}

void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
				      struct kvm_memory_slot *memslot)
{
	bool flush;

	spin_lock(&kvm->mmu_lock);
	flush = slot_handle_all_level(kvm, memslot, slot_rmap_write_protect,
				      false);
	spin_unlock(&kvm->mmu_lock);

	/*
	 * kvm_mmu_slot_remove_write_access() and kvm_vm_ioctl_get_dirty_log()
	 * which do tlb flush out of mmu-lock should be serialized by
	 * kvm->slots_lock otherwise tlb flush would be missed.
	 */
	lockdep_assert_held(&kvm->slots_lock);

	/*
	 * We can flush all the TLBs out of the mmu lock without TLB
	 * corruption since we just change the spte from writable to
	 * readonly so that we only need to care the case of changing
	 * spte from present to present (changing the spte from present
	 * to nonpresent will flush all the TLBs immediately), in other
	 * words, the only case we care is mmu_spte_update() where we
	 * have checked SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE
	 * instead of PT_WRITABLE_MASK, that means it does not depend
	 * on PT_WRITABLE_MASK anymore.
	 */
	if (flush)
		kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn,
			memslot->npages);
}

static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
					 struct kvm_rmap_head *rmap_head)
{
	u64 *sptep;
	struct rmap_iterator iter;
	int need_tlb_flush = 0;
	kvm_pfn_t pfn;
	struct kvm_mmu_page *sp;

restart:
	for_each_rmap_spte(rmap_head, &iter, sptep) {
		sp = page_header(__pa(sptep));
		pfn = spte_to_pfn(*sptep);

		/*
		 * We cannot do huge page mapping for indirect shadow pages,
		 * which are found on the last rmap (level = 1) when not using
		 * tdp; such shadow pages are synced with the page table in
		 * the guest, and the guest page table is using 4K page size
		 * mapping if the indirect sp has level = 1.
		 */
		if (sp->role.direct && !kvm_is_reserved_pfn(pfn) &&
		    !kvm_is_zone_device_pfn(pfn) &&
		    PageTransCompoundMap(pfn_to_page(pfn))) {
			pte_list_remove(rmap_head, sptep);

			if (kvm_available_flush_tlb_with_range())
				kvm_flush_remote_tlbs_with_address(kvm, sp->gfn,
					KVM_PAGES_PER_HPAGE(sp->role.level));
			else
				need_tlb_flush = 1;

			goto restart;
		}
	}

	return need_tlb_flush;
}

void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
				   const struct kvm_memory_slot *memslot)
{
	/* FIXME: const-ify all uses of struct kvm_memory_slot.  */
	spin_lock(&kvm->mmu_lock);
	slot_handle_leaf(kvm, (struct kvm_memory_slot *)memslot,
			 kvm_mmu_zap_collapsible_spte, true);
	spin_unlock(&kvm->mmu_lock);
}

void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
				   struct kvm_memory_slot *memslot)
{
	bool flush;

	spin_lock(&kvm->mmu_lock);
	flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, false);
	spin_unlock(&kvm->mmu_lock);

	lockdep_assert_held(&kvm->slots_lock);

	/*
	 * It's also safe to flush TLBs out of mmu lock here as currently this
	 * function is only used for dirty logging, in which case flushing TLB
	 * out of mmu lock also guarantees no dirty pages will be lost in
	 * dirty_bitmap.
	 */
	if (flush)
		kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn,
				memslot->npages);
}
EXPORT_SYMBOL_GPL(kvm_mmu_slot_leaf_clear_dirty);

void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm,
					struct kvm_memory_slot *memslot)
{
	bool flush;

	spin_lock(&kvm->mmu_lock);
	flush = slot_handle_large_level(kvm, memslot, slot_rmap_write_protect,
					false);
	spin_unlock(&kvm->mmu_lock);

	/* see kvm_mmu_slot_remove_write_access */
	lockdep_assert_held(&kvm->slots_lock);

	if (flush)
		kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn,
				memslot->npages);
}
EXPORT_SYMBOL_GPL(kvm_mmu_slot_largepage_remove_write_access);

void kvm_mmu_slot_set_dirty(struct kvm *kvm,
			    struct kvm_memory_slot *memslot)
{
	bool flush;

	spin_lock(&kvm->mmu_lock);
	flush = slot_handle_all_level(kvm, memslot, __rmap_set_dirty, false);
	spin_unlock(&kvm->mmu_lock);

	lockdep_assert_held(&kvm->slots_lock);

	/* see kvm_mmu_slot_leaf_clear_dirty */
	if (flush)
		kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn,
				memslot->npages);
}
EXPORT_SYMBOL_GPL(kvm_mmu_slot_set_dirty);

void kvm_mmu_zap_all(struct kvm *kvm)
{
	struct kvm_mmu_page *sp, *node;
	LIST_HEAD(invalid_list);
	int ign;

	spin_lock(&kvm->mmu_lock);
restart:
	list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) {
		if (sp->role.invalid && sp->root_count)
			continue;
		if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &ign))
			goto restart;
		if (cond_resched_lock(&kvm->mmu_lock))
			goto restart;
	}

	kvm_mmu_commit_zap_page(kvm, &invalid_list);
	spin_unlock(&kvm->mmu_lock);
}

void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen)
{
	WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS);

	gen &= MMIO_SPTE_GEN_MASK;

	/*
	 * Generation numbers are incremented in multiples of the number of
	 * address spaces in order to provide unique generations across all
	 * address spaces.  Strip what is effectively the address space
	 * modifier prior to checking for a wrap of the MMIO generation so
	 * that a wrap in any address space is detected.
	 */
	gen &= ~((u64)KVM_ADDRESS_SPACE_NUM - 1);

	/*
	 * The very rare case: if the MMIO generation number has wrapped,
	 * zap all shadow pages.
	 */
	if (unlikely(gen == 0)) {
		kvm_debug_ratelimited("kvm: zapping shadow pages for mmio generation wraparound\n");
		kvm_mmu_zap_all_fast(kvm);
	}
}

static unsigned long
mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
	struct kvm *kvm;
	int nr_to_scan = sc->nr_to_scan;
	unsigned long freed = 0;

	mutex_lock(&kvm_lock);

	list_for_each_entry(kvm, &vm_list, vm_list) {
		int idx;
		LIST_HEAD(invalid_list);

		/*
		 * Never scan more than sc->nr_to_scan VM instances.
		 * Will not hit this condition practically since we do not try
		 * to shrink more than one VM and it is very unlikely to see
		 * !n_used_mmu_pages so many times.
		 */
		if (!nr_to_scan--)
			break;
		/*
		 * n_used_mmu_pages is accessed without holding kvm->mmu_lock
		 * here. We may skip a VM instance errorneosly, but we do not
		 * want to shrink a VM that only started to populate its MMU
		 * anyway.
		 */
		if (!kvm->arch.n_used_mmu_pages &&
		    !kvm_has_zapped_obsolete_pages(kvm))
			continue;

		idx = srcu_read_lock(&kvm->srcu);
		spin_lock(&kvm->mmu_lock);

		if (kvm_has_zapped_obsolete_pages(kvm)) {
			kvm_mmu_commit_zap_page(kvm,
			      &kvm->arch.zapped_obsolete_pages);
			goto unlock;
		}

		if (prepare_zap_oldest_mmu_page(kvm, &invalid_list))
			freed++;
		kvm_mmu_commit_zap_page(kvm, &invalid_list);

unlock:
		spin_unlock(&kvm->mmu_lock);
		srcu_read_unlock(&kvm->srcu, idx);

		/*
		 * unfair on small ones
		 * per-vm shrinkers cry out
		 * sadness comes quickly
		 */
		list_move_tail(&kvm->vm_list, &vm_list);
		break;
	}

	mutex_unlock(&kvm_lock);
	return freed;
}

static unsigned long
mmu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
{
	return percpu_counter_read_positive(&kvm_total_used_mmu_pages);
}

static struct shrinker mmu_shrinker = {
	.count_objects = mmu_shrink_count,
	.scan_objects = mmu_shrink_scan,
	.seeks = DEFAULT_SEEKS * 10,
};

static void mmu_destroy_caches(void)
{
	kmem_cache_destroy(pte_list_desc_cache);
	kmem_cache_destroy(mmu_page_header_cache);
}

static void kvm_set_mmio_spte_mask(void)
{
	u64 mask;

	/*
	 * Set a reserved PA bit in MMIO SPTEs to generate page faults with
	 * PFEC.RSVD=1 on MMIO accesses.  64-bit PTEs (PAE, x86-64, and EPT
	 * paging) support a maximum of 52 bits of PA, i.e. if the CPU supports
	 * 52-bit physical addresses then there are no reserved PA bits in the
	 * PTEs and so the reserved PA approach must be disabled.
	 */
	if (shadow_phys_bits < 52)
		mask = BIT_ULL(51) | PT_PRESENT_MASK;
	else
		mask = 0;

	kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK);
}

static bool get_nx_auto_mode(void)
{
	/* Return true when CPU has the bug, and mitigations are ON */
	return boot_cpu_has_bug(X86_BUG_ITLB_MULTIHIT) && !cpu_mitigations_off();
}

static void __set_nx_huge_pages(bool val)
{
	nx_huge_pages = itlb_multihit_kvm_mitigation = val;
}

static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
{
	bool old_val = nx_huge_pages;
	bool new_val;

	/* In "auto" mode deploy workaround only if CPU has the bug. */
	if (sysfs_streq(val, "off"))
		new_val = 0;
	else if (sysfs_streq(val, "force"))
		new_val = 1;
	else if (sysfs_streq(val, "auto"))
		new_val = get_nx_auto_mode();
	else if (strtobool(val, &new_val) < 0)
		return -EINVAL;

	__set_nx_huge_pages(new_val);

	if (new_val != old_val) {
		struct kvm *kvm;

		mutex_lock(&kvm_lock);

		list_for_each_entry(kvm, &vm_list, vm_list) {
			mutex_lock(&kvm->slots_lock);
			kvm_mmu_zap_all_fast(kvm);
			mutex_unlock(&kvm->slots_lock);

			wake_up_process(kvm->arch.nx_lpage_recovery_thread);
		}
		mutex_unlock(&kvm_lock);
	}

	return 0;
}

int kvm_mmu_module_init(void)
{
	int ret = -ENOMEM;

	if (nx_huge_pages == -1)
		__set_nx_huge_pages(get_nx_auto_mode());

	/*
	 * MMU roles use union aliasing which is, generally speaking, an
	 * undefined behavior. However, we supposedly know how compilers behave
	 * and the current status quo is unlikely to change. Guardians below are
	 * supposed to let us know if the assumption becomes false.
	 */
	BUILD_BUG_ON(sizeof(union kvm_mmu_page_role) != sizeof(u32));
	BUILD_BUG_ON(sizeof(union kvm_mmu_extended_role) != sizeof(u32));
	BUILD_BUG_ON(sizeof(union kvm_mmu_role) != sizeof(u64));

	kvm_mmu_reset_all_pte_masks();

	kvm_set_mmio_spte_mask();

	pte_list_desc_cache = kmem_cache_create("pte_list_desc",
					    sizeof(struct pte_list_desc),
					    0, SLAB_ACCOUNT, NULL);
	if (!pte_list_desc_cache)
		goto out;

	mmu_page_header_cache = kmem_cache_create("kvm_mmu_page_header",
						  sizeof(struct kvm_mmu_page),
						  0, SLAB_ACCOUNT, NULL);
	if (!mmu_page_header_cache)
		goto out;

	if (percpu_counter_init(&kvm_total_used_mmu_pages, 0, GFP_KERNEL))
		goto out;

	ret = register_shrinker(&mmu_shrinker);
	if (ret)
		goto out;

	return 0;

out:
	mmu_destroy_caches();
	return ret;
}

/*
 * Calculate mmu pages needed for kvm.
 */
unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
{
	unsigned long nr_mmu_pages;
	unsigned long nr_pages = 0;
	struct kvm_memslots *slots;
	struct kvm_memory_slot *memslot;
	int i;

	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
		slots = __kvm_memslots(kvm, i);

		kvm_for_each_memslot(memslot, slots)
			nr_pages += memslot->npages;
	}

	nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000;
	nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES);

	return nr_mmu_pages;
}

void kvm_mmu_destroy(struct kvm_vcpu *vcpu)
{
	kvm_mmu_unload(vcpu);
	free_mmu_pages(&vcpu->arch.root_mmu);
	free_mmu_pages(&vcpu->arch.guest_mmu);
	mmu_free_memory_caches(vcpu);
}

void kvm_mmu_module_exit(void)
{
	mmu_destroy_caches();
	percpu_counter_destroy(&kvm_total_used_mmu_pages);
	unregister_shrinker(&mmu_shrinker);
	mmu_audit_disable();
}

static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp)
{
	unsigned int old_val;
	int err;

	old_val = nx_huge_pages_recovery_ratio;
	err = param_set_uint(val, kp);
	if (err)
		return err;

	if (READ_ONCE(nx_huge_pages) &&
	    !old_val && nx_huge_pages_recovery_ratio) {
		struct kvm *kvm;

		mutex_lock(&kvm_lock);

		list_for_each_entry(kvm, &vm_list, vm_list)
			wake_up_process(kvm->arch.nx_lpage_recovery_thread);

		mutex_unlock(&kvm_lock);
	}

	return err;
}

static void kvm_recover_nx_lpages(struct kvm *kvm)
{
	int rcu_idx;
	struct kvm_mmu_page *sp;
	unsigned int ratio;
	LIST_HEAD(invalid_list);
	ulong to_zap;

	rcu_idx = srcu_read_lock(&kvm->srcu);
	spin_lock(&kvm->mmu_lock);

	ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
	to_zap = ratio ? DIV_ROUND_UP(kvm->stat.nx_lpage_splits, ratio) : 0;
	while (to_zap && !list_empty(&kvm->arch.lpage_disallowed_mmu_pages)) {
		/*
		 * We use a separate list instead of just using active_mmu_pages
		 * because the number of lpage_disallowed pages is expected to
		 * be relatively small compared to the total.
		 */
		sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages,
				      struct kvm_mmu_page,
				      lpage_disallowed_link);
		WARN_ON_ONCE(!sp->lpage_disallowed);
		kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
		WARN_ON_ONCE(sp->lpage_disallowed);

		if (!--to_zap || need_resched() || spin_needbreak(&kvm->mmu_lock)) {
			kvm_mmu_commit_zap_page(kvm, &invalid_list);
			if (to_zap)
				cond_resched_lock(&kvm->mmu_lock);
		}
	}
	kvm_mmu_commit_zap_page(kvm, &invalid_list);

	spin_unlock(&kvm->mmu_lock);
	srcu_read_unlock(&kvm->srcu, rcu_idx);
}

static long get_nx_lpage_recovery_timeout(u64 start_time)
{
	return READ_ONCE(nx_huge_pages) && READ_ONCE(nx_huge_pages_recovery_ratio)
		? start_time + 60 * HZ - get_jiffies_64()
		: MAX_SCHEDULE_TIMEOUT;
}

static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data)
{
	u64 start_time;
	long remaining_time;

	while (true) {
		start_time = get_jiffies_64();
		remaining_time = get_nx_lpage_recovery_timeout(start_time);

		set_current_state(TASK_INTERRUPTIBLE);
		while (!kthread_should_stop() && remaining_time > 0) {
			schedule_timeout(remaining_time);
			remaining_time = get_nx_lpage_recovery_timeout(start_time);
			set_current_state(TASK_INTERRUPTIBLE);
		}

		set_current_state(TASK_RUNNING);

		if (kthread_should_stop())
			return 0;

		kvm_recover_nx_lpages(kvm);
	}
}

int kvm_mmu_post_init_vm(struct kvm *kvm)
{
	int err;

	err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0,
					  "kvm-nx-lpage-recovery",
					  &kvm->arch.nx_lpage_recovery_thread);
	if (!err)
		kthread_unpark(kvm->arch.nx_lpage_recovery_thread);

	return err;
}

void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
{
	if (kvm->arch.nx_lpage_recovery_thread)
		kthread_stop(kvm->arch.nx_lpage_recovery_thread);
}