summaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm/mmu.c
blob: f83fc6c5e0bad6712e9f172acaba931c47cd32cd (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
/*
 * 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>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

#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/module.h>
#include <linux/swap.h>
#include <linux/hugetlb.h>
#include <linux/compiler.h>
#include <linux/srcu.h>
#include <linux/slab.h>
#include <linux/uaccess.h>

#include <asm/page.h>
#include <asm/cmpxchg.h>
#include <asm/io.h>
#include <asm/vmx.h>

/*
 * 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

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

#else

#define pgprintk(x...) do { } while (0)
#define rmap_printk(x...) do { } while (0)

#endif

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

#ifndef MMU_DEBUG
#define ASSERT(x) do { } while (0)
#else
#define ASSERT(x)							\
	if (!(x)) {							\
		printk(KERN_WARNING "assertion failed %s:%d: %s\n",	\
		       __FILE__, __LINE__, #x);				\
	}
#endif

#define PTE_PREFETCH_NUM		8

#define PT_FIRST_AVAIL_BITS_SHIFT 10
#define PT64_SECOND_AVAIL_BITS_SHIFT 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))


#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
#define PT64_DIR_BASE_ADDR_MASK \
	(PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + PT64_LEVEL_BITS)) - 1))
#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)

#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)

#include <trace/events/kvm.h>

#define CREATE_TRACE_POINTS
#include "mmutrace.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

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;
};

#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 void mmu_spte_set(u64 *sptep, u64 spte);
static void mmu_free_roots(struct kvm_vcpu *vcpu);

void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask)
{
	shadow_mmio_mask = mmio_mask;
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask);

/*
 * the low bit of the generation number is always presumed to be zero.
 * This disables mmio caching during memslot updates.  The concept is
 * similar to a seqcount but instead of retrying the access we just punt
 * and ignore the cache.
 *
 * spte bits 3-11 are used as bits 1-9 of the generation number,
 * the bits 52-61 are used as bits 10-19 of the generation number.
 */
#define MMIO_SPTE_GEN_LOW_SHIFT		2
#define MMIO_SPTE_GEN_HIGH_SHIFT	52

#define MMIO_GEN_SHIFT			20
#define MMIO_GEN_LOW_SHIFT		10
#define MMIO_GEN_LOW_MASK		((1 << MMIO_GEN_LOW_SHIFT) - 2)
#define MMIO_GEN_MASK			((1 << MMIO_GEN_SHIFT) - 1)

static u64 generation_mmio_spte_mask(unsigned int gen)
{
	u64 mask;

	WARN_ON(gen & ~MMIO_GEN_MASK);

	mask = (gen & MMIO_GEN_LOW_MASK) << MMIO_SPTE_GEN_LOW_SHIFT;
	mask |= ((u64)gen >> MMIO_GEN_LOW_SHIFT) << MMIO_SPTE_GEN_HIGH_SHIFT;
	return mask;
}

static unsigned int get_mmio_spte_generation(u64 spte)
{
	unsigned int gen;

	spte &= ~shadow_mmio_mask;

	gen = (spte >> MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_GEN_LOW_MASK;
	gen |= (spte >> MMIO_SPTE_GEN_HIGH_SHIFT) << MMIO_GEN_LOW_SHIFT;
	return gen;
}

static unsigned int kvm_current_mmio_generation(struct kvm *kvm)
{
	return kvm_memslots(kvm)->generation & MMIO_GEN_MASK;
}

static void mark_mmio_spte(struct kvm *kvm, u64 *sptep, u64 gfn,
			   unsigned access)
{
	unsigned int gen = kvm_current_mmio_generation(kvm);
	u64 mask = generation_mmio_spte_mask(gen);

	access &= ACC_WRITE_MASK | ACC_USER_MASK;
	mask |= shadow_mmio_mask | access | gfn << PAGE_SHIFT;

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

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

static gfn_t get_mmio_spte_gfn(u64 spte)
{
	u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask;
	return (spte & ~mask) >> PAGE_SHIFT;
}

static unsigned get_mmio_spte_access(u64 spte)
{
	u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask;
	return (spte & ~mask) & ~PAGE_MASK;
}

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

	return false;
}

static bool check_mmio_spte(struct kvm *kvm, u64 spte)
{
	unsigned int kvm_gen, spte_gen;

	kvm_gen = kvm_current_mmio_generation(kvm);
	spte_gen = get_mmio_spte_generation(spte);

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

void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
		u64 dirty_mask, u64 nx_mask, u64 x_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;
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);

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 & PT_PRESENT_MASK && !is_mmio_spte(pte);
}

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

static int is_rmap_spte(u64 pte)
{
	return is_shadow_present_pte(pte);
}

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 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)
{
	*sptep = spte;
}

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

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

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

static bool __check_direct_spte_mmio_pf(u64 spte)
{
	/* It is valid if the spte is zapped. */
	return spte == 0ull;
}
#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();

	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;

	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(arch/x86/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;
}

static bool __check_direct_spte_mmio_pf(u64 spte)
{
	union split_spte sspte = (union split_spte)spte;
	u32 high_mmio_mask = shadow_mmio_mask >> 32;

	/* It is valid if the spte is zapped. */
	if (spte == 0ull)
		return true;

	/* It is valid if the spte is being zapped. */
	if (sspte.spte_low == 0ull &&
	    (sspte.spte_high & high_mmio_mask) == high_mmio_mask)
		return true;

	return false;
}
#endif

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

static bool spte_has_volatile_bits(u64 spte)
{
	/*
	 * Always atomicly 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_is_locklessly_modifiable(spte))
		return true;

	if (!shadow_accessed_mask)
		return false;

	if (!is_shadow_present_pte(spte))
		return false;

	if ((spte & shadow_accessed_mask) &&
	      (!is_writable_pte(spte) || (spte & shadow_dirty_mask)))
		return false;

	return true;
}

static bool spte_is_bit_cleared(u64 old_spte, u64 new_spte, u64 bit_mask)
{
	return (old_spte & bit_mask) && !(new_spte & bit_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);
}

/* Rules for using mmu_spte_update:
 * Update the state bits, it means the mapped pfn is not changged.
 *
 * 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.
 */
static bool mmu_spte_update(u64 *sptep, u64 new_spte)
{
	u64 old_spte = *sptep;
	bool ret = false;

	WARN_ON(!is_rmap_spte(new_spte));

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

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

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

	if (!shadow_accessed_mask)
		return ret;

	if (spte_is_bit_cleared(old_spte, new_spte, shadow_accessed_mask))
		kvm_set_pfn_accessed(spte_to_pfn(old_spte));
	if (spte_is_bit_cleared(old_spte, new_spte, shadow_dirty_mask))
		kvm_set_pfn_dirty(spte_to_pfn(old_spte));

	return ret;
}

/*
 * 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.
 */
static int mmu_spte_clear_track_bits(u64 *sptep)
{
	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_rmap_spte(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 (!shadow_accessed_mask || old_spte & shadow_accessed_mask)
		kvm_set_pfn_accessed(pfn);
	if (!shadow_dirty_mask || (old_spte & shadow_dirty_mask))
		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 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();
	vcpu->mode = READING_SHADOW_PAGE_TABLES;
	/*
	 * Make sure a following spte read is not reordered ahead of the write
	 * to vcpu->mode.
	 */
	smp_mb();
}

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_commit_zap_page() can see us
	 * OUTSIDE_GUEST_MODE and proceed to free the shadow page table.
	 */
	smp_mb();
	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);
		if (!obj)
			return -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);
		if (!page)
			return -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)
		BUG_ON(gfn != kvm_mmu_page_get_gfn(sp, index));
	else
		sp->gfns[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 account_shadowed(struct kvm *kvm, gfn_t gfn)
{
	struct kvm_memory_slot *slot;
	struct kvm_lpage_info *linfo;
	int i;

	slot = gfn_to_memslot(kvm, gfn);
	for (i = PT_DIRECTORY_LEVEL;
	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
		linfo = lpage_info_slot(gfn, slot, i);
		linfo->write_count += 1;
	}
	kvm->arch.indirect_shadow_pages++;
}

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

	slot = gfn_to_memslot(kvm, gfn);
	for (i = PT_DIRECTORY_LEVEL;
	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
		linfo = lpage_info_slot(gfn, slot, i);
		linfo->write_count -= 1;
		WARN_ON(linfo->write_count < 0);
	}
	kvm->arch.indirect_shadow_pages--;
}

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

	slot = gfn_to_memslot(kvm, gfn);
	if (slot) {
		linfo = lpage_info_slot(gfn, slot, level);
		return linfo->write_count;
	}

	return 1;
}

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

	page_size = kvm_host_page_size(kvm, gfn);

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

	return ret;
}

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 = gfn_to_memslot(vcpu->kvm, gfn);
	if (!slot || slot->flags & KVM_MEMSLOT_INVALID ||
	      (no_dirty_log && slot->dirty_bitmap))
		slot = NULL;

	return slot;
}

static bool mapping_level_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t large_gfn)
{
	return !gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true);
}

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

	host_level = host_mapping_level(vcpu->kvm, 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 (has_wrprotected_page(vcpu->kvm, large_gfn, level))
			break;

	return level - 1;
}

/*
 * Pte mapping structures:
 *
 * If pte_list bit zero is zero, then pte_list point to the spte.
 *
 * If pte_list bit zero is one, (then pte_list & ~1) points to a struct
 * pte_list_desc containing more mappings.
 *
 * Returns the number of pte entries before the spte was added or zero if
 * the spte was not added.
 *
 */
static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte,
			unsigned long *pte_list)
{
	struct pte_list_desc *desc;
	int i, count = 0;

	if (!*pte_list) {
		rmap_printk("pte_list_add: %p %llx 0->1\n", spte, *spte);
		*pte_list = (unsigned long)spte;
	} else if (!(*pte_list & 1)) {
		rmap_printk("pte_list_add: %p %llx 1->many\n", spte, *spte);
		desc = mmu_alloc_pte_list_desc(vcpu);
		desc->sptes[0] = (u64 *)*pte_list;
		desc->sptes[1] = spte;
		*pte_list = (unsigned long)desc | 1;
		++count;
	} else {
		rmap_printk("pte_list_add: %p %llx many->many\n", spte, *spte);
		desc = (struct pte_list_desc *)(*pte_list & ~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(unsigned long *pte_list, 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)
		*pte_list = (unsigned long)desc->sptes[0];
	else
		if (prev_desc)
			prev_desc->more = desc->more;
		else
			*pte_list = (unsigned long)desc->more | 1;
	mmu_free_pte_list_desc(desc);
}

static void pte_list_remove(u64 *spte, unsigned long *pte_list)
{
	struct pte_list_desc *desc;
	struct pte_list_desc *prev_desc;
	int i;

	if (!*pte_list) {
		printk(KERN_ERR "pte_list_remove: %p 0->BUG\n", spte);
		BUG();
	} else if (!(*pte_list & 1)) {
		rmap_printk("pte_list_remove:  %p 1->0\n", spte);
		if ((u64 *)*pte_list != spte) {
			printk(KERN_ERR "pte_list_remove:  %p 1->BUG\n", spte);
			BUG();
		}
		*pte_list = 0;
	} else {
		rmap_printk("pte_list_remove:  %p many->many\n", spte);
		desc = (struct pte_list_desc *)(*pte_list & ~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(pte_list,
							       desc, i,
							       prev_desc);
					return;
				}
			prev_desc = desc;
			desc = desc->more;
		}
		pr_err("pte_list_remove: %p many->many\n", spte);
		BUG();
	}
}

typedef void (*pte_list_walk_fn) (u64 *spte);
static void pte_list_walk(unsigned long *pte_list, pte_list_walk_fn fn)
{
	struct pte_list_desc *desc;
	int i;

	if (!*pte_list)
		return;

	if (!(*pte_list & 1))
		return fn((u64 *)*pte_list);

	desc = (struct pte_list_desc *)(*pte_list & ~1ul);
	while (desc) {
		for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i)
			fn(desc->sptes[i]);
		desc = desc->more;
	}
}

static unsigned long *__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];
}

/*
 * Take gfn and return the reverse mapping to it.
 */
static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level)
{
	struct kvm_memory_slot *slot;

	slot = gfn_to_memslot(kvm, gfn);
	return __gfn_to_rmap(gfn, 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;
	unsigned long *rmapp;

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

static void rmap_remove(struct kvm *kvm, u64 *spte)
{
	struct kvm_mmu_page *sp;
	gfn_t gfn;
	unsigned long *rmapp;

	sp = page_header(__pa(spte));
	gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt);
	rmapp = gfn_to_rmap(kvm, gfn, sp->role.level);
	pte_list_remove(spte, rmapp);
}

/*
 * 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(unsigned long rmap, struct rmap_iterator *iter)
{
	if (!rmap)
		return NULL;

	if (!(rmap & 1)) {
		iter->desc = NULL;
		return (u64 *)rmap;
	}

	iter->desc = (struct pte_list_desc *)(rmap & ~1ul);
	iter->pos = 0;
	return iter->desc->sptes[iter->pos];
}

/*
 * 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)
{
	if (iter->desc) {
		if (iter->pos < PTE_LIST_EXT - 1) {
			u64 *sptep;

			++iter->pos;
			sptep = iter->desc->sptes[iter->pos];
			if (sptep)
				return sptep;
		}

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

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

	return NULL;
}

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))
		kvm_flush_remote_tlbs(vcpu->kvm);
}

/*
 * 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(struct kvm *kvm, u64 *sptep, bool pt_protect)
{
	u64 spte = *sptep;

	if (!is_writable_pte(spte) &&
	      !(pt_protect && spte_is_locklessly_modifiable(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, unsigned long *rmapp,
				 bool pt_protect)
{
	u64 *sptep;
	struct rmap_iterator iter;
	bool flush = false;

	for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
		BUG_ON(!(*sptep & PT_PRESENT_MASK));

		flush |= spte_write_protect(kvm, sptep, pt_protect);
		sptep = rmap_get_next(&iter);
	}

	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.
 */
void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
				     struct kvm_memory_slot *slot,
				     gfn_t gfn_offset, unsigned long mask)
{
	unsigned long *rmapp;

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

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

static bool rmap_write_protect(struct kvm *kvm, u64 gfn)
{
	struct kvm_memory_slot *slot;
	unsigned long *rmapp;
	int i;
	bool write_protected = false;

	slot = gfn_to_memslot(kvm, gfn);

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

	return write_protected;
}

static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
			   struct kvm_memory_slot *slot, gfn_t gfn, int level,
			   unsigned long data)
{
	u64 *sptep;
	struct rmap_iterator iter;
	int need_tlb_flush = 0;

	while ((sptep = rmap_get_first(*rmapp, &iter))) {
		BUG_ON(!(*sptep & PT_PRESENT_MASK));
		rmap_printk("kvm_rmap_unmap_hva: spte %p %llx gfn %llx (%d)\n",
			     sptep, *sptep, gfn, level);

		drop_spte(kvm, sptep);
		need_tlb_flush = 1;
	}

	return need_tlb_flush;
}

static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
			     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;
	pfn_t new_pfn;

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

	for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
		BUG_ON(!is_shadow_present_pte(*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)) {
			drop_spte(kvm, sptep);
			sptep = rmap_get_first(*rmapp, &iter);
		} 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 &= ~shadow_accessed_mask;

			mmu_spte_clear_track_bits(sptep);
			mmu_spte_set(sptep, new_spte);
			sptep = rmap_get_next(&iter);
		}
	}

	if (need_flush)
		kvm_flush_remote_tlbs(kvm);

	return 0;
}

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

	slots = kvm_memslots(kvm);

	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 (j = PT_PAGE_TABLE_LEVEL;
		     j < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++j) {
			unsigned long idx, idx_end;
			unsigned long *rmapp;
			gfn_t gfn = gfn_start;

			/*
			 * {idx(page_j) | page_j intersects with
			 *  [hva_start, hva_end)} = {idx, idx+1, ..., idx_end}.
			 */
			idx = gfn_to_index(gfn_start, memslot->base_gfn, j);
			idx_end = gfn_to_index(gfn_end - 1, memslot->base_gfn, j);

			rmapp = __gfn_to_rmap(gfn_start, j, memslot);

			for (; idx <= idx_end;
			       ++idx, gfn += (1UL << KVM_HPAGE_GFN_SHIFT(j)))
				ret |= handler(kvm, rmapp++, memslot,
					       gfn, j, data);
		}
	}

	return ret;
}

static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
			  unsigned long data,
			  int (*handler)(struct kvm *kvm, unsigned long *rmapp,
					 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(struct kvm *kvm, unsigned long hva)
{
	return kvm_handle_hva(kvm, hva, 0, kvm_unmap_rmapp);
}

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

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

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

	BUG_ON(!shadow_accessed_mask);

	for (sptep = rmap_get_first(*rmapp, &iter); sptep;
	     sptep = rmap_get_next(&iter)) {
		BUG_ON(!is_shadow_present_pte(*sptep));

		if (*sptep & shadow_accessed_mask) {
			young = 1;
			clear_bit((ffs(shadow_accessed_mask) - 1),
				 (unsigned long *)sptep);
		}
	}
	trace_kvm_age_page(gfn, level, slot, young);
	return young;
}

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

	/*
	 * If there's no access bit in the secondary pte set by the
	 * hardware it's up to gup-fast/gup to set the access bit in
	 * the primary pte or in the page structure.
	 */
	if (!shadow_accessed_mask)
		goto out;

	for (sptep = rmap_get_first(*rmapp, &iter); sptep;
	     sptep = rmap_get_next(&iter)) {
		BUG_ON(!is_shadow_present_pte(*sptep));

		if (*sptep & shadow_accessed_mask) {
			young = 1;
			break;
		}
	}
out:
	return young;
}

#define RMAP_RECYCLE_THRESHOLD 1000

static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
{
	unsigned long *rmapp;
	struct kvm_mmu_page *sp;

	sp = page_header(__pa(spte));

	rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level);

	kvm_unmap_rmapp(vcpu->kvm, rmapp, NULL, gfn, sp->role.level, 0);
	kvm_flush_remote_tlbs(vcpu->kvm);
}

int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
{
	/*
	 * In case of absence of EPT Access and Dirty Bits supports,
	 * emulate the accessed bit for EPT, by checking if this page has
	 * an EPT mapping, and clearing it if it does. On the next access,
	 * a new EPT mapping will be established.
	 * This has some overhead, but not as much as the cost of swapping
	 * out actively used pages or breaking up actively used hugepages.
	 */
	if (!shadow_accessed_mask) {
		/*
		 * We are holding the kvm->mmu_lock, and we are blowing up
		 * shadow PTEs. MMU notifier consumers need to be kept at bay.
		 * This is correct as long as we don't decouple the mmu_lock
		 * protected regions (like invalidate_range_start|end does).
		 */
		kvm->mmu_notifier_seq++;
		return kvm_handle_hva_range(kvm, start, end, 0,
					    kvm_unmap_rmapp);
	}

	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, int 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)
{
	ASSERT(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 gfn & ((1 << KVM_MMU_HASH_SHIFT) - 1);
}

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,
					       u64 *parent_pte, 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);

	/*
	 * The active_mmu_pages list is the FIFO list, do not move the
	 * page until it is zapped. kvm_zap_obsolete_pages depends on
	 * this feature. See the comments in kvm_zap_obsolete_pages().
	 */
	list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
	sp->parent_ptes = 0;
	mmu_page_add_parent_pte(vcpu, sp, parent_pte);
	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)
{
	pte_list_walk(&sp->parent_ptes, mark_unsync);
}

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 1;
}

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

static void nonpaging_update_pte(struct kvm_vcpu *vcpu,
				 struct kvm_mmu_page *sp, u64 *spte,
				 const void *pte)
{
	WARN_ON(1);
}

#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 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))
			goto clear_child_bitmap;

		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)
				goto clear_child_bitmap;
			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
			 goto clear_child_bitmap;

		continue;

clear_child_bitmap:
		__clear_bit(i, sp->unsync_child_bitmap);
		sp->unsync_children--;
		WARN_ON((int)sp->unsync_children < 0);
	}


	return nr_unsync_leaf;
}

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

	mmu_pages_add(pvec, sp, 0);
	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 int 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);

/*
 * NOTE: we should pay more attention on the zapped-obsolete page
 * (is_obsolete_sp(sp) && sp->role.invalid) when you do hash list walk
 * since it has been deleted from active_mmu_pages but still can be found
 * at hast list.
 *
 * for_each_gfn_indirect_valid_sp has skipped that kind of page and
 * kvm_mmu_get_page(), the only user of for_each_gfn_sp(), has skipped
 * all the obsolete pages.
 */
#define for_each_gfn_sp(_kvm, _sp, _gfn)				\
	hlist_for_each_entry(_sp,					\
	  &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \
		if ((_sp)->gfn != (_gfn)) {} else

#define for_each_gfn_indirect_valid_sp(_kvm, _sp, _gfn)			\
	for_each_gfn_sp(_kvm, _sp, _gfn)				\
		if ((_sp)->role.direct || (_sp)->role.invalid) {} else

/* @sp->gfn should be write-protected at the call site */
static int __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
			   struct list_head *invalid_list, bool clear_unsync)
{
	if (sp->role.cr4_pae != !!is_pae(vcpu)) {
		kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
		return 1;
	}

	if (clear_unsync)
		kvm_unlink_unsync_page(vcpu->kvm, sp);

	if (vcpu->arch.mmu.sync_page(vcpu, sp)) {
		kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
		return 1;
	}

	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
	return 0;
}

static int kvm_sync_page_transient(struct kvm_vcpu *vcpu,
				   struct kvm_mmu_page *sp)
{
	LIST_HEAD(invalid_list);
	int ret;

	ret = __kvm_sync_page(vcpu, sp, &invalid_list, false);
	if (ret)
		kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);

	return ret;
}

#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 int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
			 struct list_head *invalid_list)
{
	return __kvm_sync_page(vcpu, sp, invalid_list, true);
}

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

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

		WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL);
		kvm_unlink_unsync_page(vcpu->kvm, s);
		if ((s->role.cr4_pae != !!is_pae(vcpu)) ||
			(vcpu->arch.mmu.sync_page(vcpu, s))) {
			kvm_mmu_prepare_zap_page(vcpu->kvm, s, &invalid_list);
			continue;
		}
		flush = true;
	}

	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
	if (flush)
		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}

struct mmu_page_path {
	struct kvm_mmu_page *parent[PT64_ROOT_LEVEL-1];
	unsigned int idx[PT64_ROOT_LEVEL-1];
};

#define for_each_sp(pvec, sp, parents, i)			\
		for (i = mmu_pages_next(&pvec, &parents, -1),	\
			sp = pvec.page[i].sp;			\
			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;

		if (sp->role.level == PT_PAGE_TABLE_LEVEL) {
			parents->idx[0] = pvec->page[n].idx;
			return n;
		}

		parents->parent[sp->role.level-2] = sp;
		parents->idx[sp->role.level-1] = pvec->page[n].idx;
	}

	return n;
}

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;

		--sp->unsync_children;
		WARN_ON((int)sp->unsync_children < 0);
		__clear_bit(idx, sp->unsync_child_bitmap);
		level++;
	} while (level < PT64_ROOT_LEVEL-1 && !sp->unsync_children);
}

static void kvm_mmu_pages_init(struct kvm_mmu_page *parent,
			       struct mmu_page_path *parents,
			       struct kvm_mmu_pages *pvec)
{
	parents->parent[parent->role.level-1] = NULL;
	pvec->nr = 0;
}

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);

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

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

		if (protected)
			kvm_flush_remote_tlbs(vcpu->kvm);

		for_each_sp(pages, sp, parents, i) {
			kvm_sync_page(vcpu, sp, &invalid_list);
			mmu_pages_clear_parents(&parents);
		}
		kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
		cond_resched_lock(&vcpu->kvm->mmu_lock);
		kvm_mmu_pages_init(parent, &parents, &pages);
	}
}

static void init_shadow_page_table(struct kvm_mmu_page *sp)
{
	int i;

	for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
		sp->spt[i] = 0ull;
}

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

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,
					     u64 *parent_pte)
{
	union kvm_mmu_page_role role;
	unsigned quadrant;
	struct kvm_mmu_page *sp;
	bool need_sync = false;

	role = vcpu->arch.mmu.base_role;
	role.level = level;
	role.direct = direct;
	if (role.direct)
		role.cr4_pae = 0;
	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_gfn_sp(vcpu->kvm, sp, gfn) {
		if (is_obsolete_sp(vcpu->kvm, sp))
			continue;

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

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

		if (sp->unsync && kvm_sync_page_transient(vcpu, sp))
			break;

		mmu_page_add_parent_pte(vcpu, sp, parent_pte);
		if (sp->unsync_children) {
			kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
			kvm_mmu_mark_parents_unsync(sp);
		} else if (sp->unsync)
			kvm_mmu_mark_parents_unsync(sp);

		__clear_sp_write_flooding_count(sp);
		trace_kvm_mmu_get_page(sp, false);
		return sp;
	}
	++vcpu->kvm->stat.mmu_cache_miss;
	sp = kvm_mmu_alloc_page(vcpu, parent_pte, direct);
	if (!sp)
		return sp;
	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) {
		if (rmap_write_protect(vcpu->kvm, gfn))
			kvm_flush_remote_tlbs(vcpu->kvm);
		if (level > PT_PAGE_TABLE_LEVEL && need_sync)
			kvm_sync_pages(vcpu, gfn);

		account_shadowed(vcpu->kvm, gfn);
	}
	sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen;
	init_shadow_page_table(sp);
	trace_kvm_mmu_get_page(sp, true);
	return sp;
}

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

	if (iterator->level == PT64_ROOT_LEVEL &&
	    vcpu->arch.mmu.root_level < PT64_ROOT_LEVEL &&
	    !vcpu->arch.mmu.direct_map)
		--iterator->level;

	if (iterator->level == PT32E_ROOT_LEVEL) {
		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 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)
{
	return __shadow_walk_next(iterator, *iterator->sptep);
}

static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp, bool accessed)
{
	u64 spte;

	BUILD_BUG_ON(VMX_EPT_READABLE_MASK != PT_PRESENT_MASK ||
			VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);

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

	if (accessed)
		spte |= shadow_accessed_mask;

	mmu_spte_set(sptep, spte);
}

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(vcpu->kvm);
	}
}

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_put_page(struct kvm_mmu_page *sp, u64 *parent_pte)
{
	mmu_page_remove_parent_pte(sp, parent_pte);
}

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;

	kvm_mmu_pages_init(parent, &parents, &pages);
	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++;
		}
		kvm_mmu_pages_init(parent, &parents, &pages);
	}

	return zapped;
}

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

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

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

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

		/*
		 * The obsolete pages can not be used on any vcpus.
		 * See the comments in kvm_mmu_invalidate_zap_all_pages().
		 */
		if (!sp->role.invalid && !is_obsolete_sp(kvm, sp))
			kvm_reload_remote_mmus(kvm);
	}

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

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;

	/*
	 * wmb: make sure everyone sees our modifications to the page tables
	 * rmb: make sure we see changes to vcpu->mode
	 */
	smp_mb();

	/*
	 * Wait 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_entry(kvm->arch.active_mmu_pages.prev,
			struct kvm_mmu_page, link);
	kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);

	return true;
}

/*
 * 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 int 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);

/*
 * The function is based on mtrr_type_lookup() in
 * arch/x86/kernel/cpu/mtrr/generic.c
 */
static int get_mtrr_type(struct mtrr_state_type *mtrr_state,
			 u64 start, u64 end)
{
	int i;
	u64 base, mask;
	u8 prev_match, curr_match;
	int num_var_ranges = KVM_NR_VAR_MTRR;

	if (!mtrr_state->enabled)
		return 0xFF;

	/* Make end inclusive end, instead of exclusive */
	end--;

	/* Look in fixed ranges. Just return the type as per start */
	if (mtrr_state->have_fixed && (start < 0x100000)) {
		int idx;

		if (start < 0x80000) {
			idx = 0;
			idx += (start >> 16);
			return mtrr_state->fixed_ranges[idx];
		} else if (start < 0xC0000) {
			idx = 1 * 8;
			idx += ((start - 0x80000) >> 14);
			return mtrr_state->fixed_ranges[idx];
		} else if (start < 0x1000000) {
			idx = 3 * 8;
			idx += ((start - 0xC0000) >> 12);
			return mtrr_state->fixed_ranges[idx];
		}
	}

	/*
	 * Look in variable ranges
	 * Look of multiple ranges matching this address and pick type
	 * as per MTRR precedence
	 */
	if (!(mtrr_state->enabled & 2))
		return mtrr_state->def_type;

	prev_match = 0xFF;
	for (i = 0; i < num_var_ranges; ++i) {
		unsigned short start_state, end_state;

		if (!(mtrr_state->var_ranges[i].mask_lo & (1 << 11)))
			continue;

		base = (((u64)mtrr_state->var_ranges[i].base_hi) << 32) +
		       (mtrr_state->var_ranges[i].base_lo & PAGE_MASK);
		mask = (((u64)mtrr_state->var_ranges[i].mask_hi) << 32) +
		       (mtrr_state->var_ranges[i].mask_lo & PAGE_MASK);

		start_state = ((start & mask) == (base & mask));
		end_state = ((end & mask) == (base & mask));
		if (start_state != end_state)
			return 0xFE;

		if ((start & mask) != (base & mask))
			continue;

		curr_match = mtrr_state->var_ranges[i].base_lo & 0xff;
		if (prev_match == 0xFF) {
			prev_match = curr_match;
			continue;
		}

		if (prev_match == MTRR_TYPE_UNCACHABLE ||
		    curr_match == MTRR_TYPE_UNCACHABLE)
			return MTRR_TYPE_UNCACHABLE;

		if ((prev_match == MTRR_TYPE_WRBACK &&
		     curr_match == MTRR_TYPE_WRTHROUGH) ||
		    (prev_match == MTRR_TYPE_WRTHROUGH &&
		     curr_match == MTRR_TYPE_WRBACK)) {
			prev_match = MTRR_TYPE_WRTHROUGH;
			curr_match = MTRR_TYPE_WRTHROUGH;
		}

		if (prev_match != curr_match)
			return MTRR_TYPE_UNCACHABLE;
	}

	if (prev_match != 0xFF)
		return prev_match;

	return mtrr_state->def_type;
}

u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
{
	u8 mtrr;

	mtrr = get_mtrr_type(&vcpu->arch.mtrr_state, gfn << PAGE_SHIFT,
			     (gfn << PAGE_SHIFT) + PAGE_SIZE);
	if (mtrr == 0xfe || mtrr == 0xff)
		mtrr = MTRR_TYPE_WRBACK;
	return mtrr;
}
EXPORT_SYMBOL_GPL(kvm_get_guest_memory_type);

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 void kvm_unsync_pages(struct kvm_vcpu *vcpu,  gfn_t gfn)
{
	struct kvm_mmu_page *s;

	for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
		if (s->unsync)
			continue;
		WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL);
		__kvm_unsync_page(vcpu, s);
	}
}

static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
				  bool can_unsync)
{
	struct kvm_mmu_page *s;
	bool need_unsync = false;

	for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
		if (!can_unsync)
			return 1;

		if (s->role.level != PT_PAGE_TABLE_LEVEL)
			return 1;

		if (!s->unsync)
			need_unsync = true;
	}
	if (need_unsync)
		kvm_unsync_pages(vcpu, gfn);
	return 0;
}

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

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

	spte = PT_PRESENT_MASK;
	if (!speculative)
		spte |= shadow_accessed_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_reserved_pfn(pfn));

	if (host_writable)
		spte |= SPTE_HOST_WRITEABLE;
	else
		pte_access &= ~ACC_WRITE_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 &&
		    has_wrprotected_page(vcpu->kvm, 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 = 1;
			pte_access &= ~ACC_WRITE_MASK;
			spte &= ~(PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE);
		}
	}

	if (pte_access & ACC_WRITE_MASK)
		mark_page_dirty(vcpu->kvm, gfn);

set_pte:
	if (mmu_spte_update(sptep, spte))
		kvm_flush_remote_tlbs(vcpu->kvm);
done:
	return ret;
}

static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
			 unsigned pte_access, int write_fault, int *emulate,
			 int level, gfn_t gfn, pfn_t pfn, bool speculative,
			 bool host_writable)
{
	int was_rmapped = 0;
	int rmap_count;

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

	if (is_rmap_spte(*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);
			kvm_flush_remote_tlbs(vcpu->kvm);
		} else if (pfn != spte_to_pfn(*sptep)) {
			pgprintk("hfn old %llx new %llx\n",
				 spte_to_pfn(*sptep), pfn);
			drop_spte(vcpu->kvm, sptep);
			kvm_flush_remote_tlbs(vcpu->kvm);
		} else
			was_rmapped = 1;
	}

	if (set_spte(vcpu, sptep, pte_access, level, gfn, pfn, speculative,
	      true, host_writable)) {
		if (write_fault)
			*emulate = 1;
		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
	}

	if (unlikely(is_mmio_spte(*sptep) && emulate))
		*emulate = 1;

	pgprintk("%s: setting spte %llx\n", __func__, *sptep);
	pgprintk("instantiating %s PTE (%s) at %llx (%llx) addr %p\n",
		 is_large_pte(*sptep)? "2MB" : "4kB",
		 *sptep & PT_PRESENT_MASK ?"RW":"R", gfn,
		 *sptep, 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);
		}
	}

	kvm_release_pfn_clean(pfn);
}

static 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];
	unsigned access = sp->role.access;
	int i, ret;
	gfn_t gfn;

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

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

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

	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;

	/*
	 * Since it's no accessed bit on EPT, it's no way to
	 * distinguish between actually accessed translations
	 * and prefetched, so disable pte prefetch if EPT is
	 * enabled.
	 */
	if (!shadow_accessed_mask)
		return;

	sp = page_header(__pa(sptep));
	if (sp->role.level > PT_PAGE_TABLE_LEVEL)
		return;

	__direct_pte_prefetch(vcpu, sp, sptep);
}

static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
			int map_writable, int level, gfn_t gfn, pfn_t pfn,
			bool prefault)
{
	struct kvm_shadow_walk_iterator iterator;
	struct kvm_mmu_page *sp;
	int emulate = 0;
	gfn_t pseudo_gfn;

	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
		return 0;

	for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
		if (iterator.level == level) {
			mmu_set_spte(vcpu, iterator.sptep, ACC_ALL,
				     write, &emulate, level, gfn, pfn,
				     prefault, map_writable);
			direct_pte_prefetch(vcpu, iterator.sptep);
			++vcpu->stat.pf_fixed;
			break;
		}

		drop_large_spte(vcpu, iterator.sptep);
		if (!is_shadow_present_pte(*iterator.sptep)) {
			u64 base_addr = iterator.addr;

			base_addr &= PT64_LVL_ADDR_MASK(iterator.level);
			pseudo_gfn = base_addr >> PAGE_SHIFT;
			sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr,
					      iterator.level - 1,
					      1, ACC_ALL, iterator.sptep);

			link_shadow_page(iterator.sptep, sp, true);
		}
	}
	return emulate;
}

static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *tsk)
{
	siginfo_t info;

	info.si_signo	= SIGBUS;
	info.si_errno	= 0;
	info.si_code	= BUS_MCEERR_AR;
	info.si_addr	= (void __user *)address;
	info.si_addr_lsb = PAGE_SHIFT;

	send_sig_info(SIGBUS, &info, tsk);
}

static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, 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.
	 * Return 1 to tell kvm to emulate it.
	 */
	if (pfn == KVM_PFN_ERR_RO_FAULT)
		return 1;

	if (pfn == KVM_PFN_ERR_HWPOISON) {
		kvm_send_hwpoison_signal(gfn_to_hva(vcpu->kvm, gfn), current);
		return 0;
	}

	return -EFAULT;
}

static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
					gfn_t *gfnp, pfn_t *pfnp, int *levelp)
{
	pfn_t pfn = *pfnp;
	gfn_t gfn = *gfnp;
	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) &&
	    level == PT_PAGE_TABLE_LEVEL &&
	    PageTransCompound(pfn_to_page(pfn)) &&
	    !has_wrprotected_page(vcpu->kvm, 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) {
			gfn &= ~mask;
			*gfnp = gfn;
			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,
				pfn_t pfn, unsigned access, int *ret_val)
{
	bool ret = true;

	/* The pfn is invalid, report the error! */
	if (unlikely(is_error_pfn(pfn))) {
		*ret_val = kvm_handle_bad_page(vcpu, gfn, pfn);
		goto exit;
	}

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

	ret = false;
exit:
	return ret;
}

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;

	/*
	 * #PF can be fast only if the shadow page table is present and it
	 * 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.
	 */
	if (!(error_code & PFERR_PRESENT_MASK) ||
	      !(error_code & PFERR_WRITE_MASK))
		return false;

	return true;
}

static bool
fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
			u64 *sptep, u64 spte)
{
	gfn_t gfn;

	WARN_ON(!sp->role.direct);

	/*
	 * The gfn of direct spte is stable since it is calculated
	 * by sp->gfn.
	 */
	gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt);

	if (cmpxchg64(sptep, spte, spte | PT_WRITABLE_MASK) == spte)
		mark_page_dirty(vcpu->kvm, gfn);

	return true;
}

/*
 * 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, gva_t gva, int level,
			    u32 error_code)
{
	struct kvm_shadow_walk_iterator iterator;
	struct kvm_mmu_page *sp;
	bool ret = false;
	u64 spte = 0ull;

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

	/*
	 * If the mapping has been changed, let the vcpu fault on the
	 * same address again.
	 */
	if (!is_rmap_spte(spte)) {
		ret = true;
		goto exit;
	}

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

	/*
	 * Check if it is a spurious fault caused by TLB lazily flushed.
	 *
	 * Need not check the access of upper level table entries since
	 * they are always ACC_ALL.
	 */
	 if (is_writable_pte(spte)) {
		ret = true;
		goto exit;
	}

	/*
	 * Currently, to simplify the code, only the spte write-protected
	 * by dirty-log can be fast fixed.
	 */
	if (!spte_is_locklessly_modifiable(spte))
		goto exit;

	/*
	 * 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()
	 * that means other pages are missed if its slot is dirty-logged.
	 *
	 * 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)
		goto exit;

	/*
	 * Currently, fast page fault only works for direct mapping since
	 * the gfn is not stable for indirect shadow page.
	 * See Documentation/virtual/kvm/locking.txt to get more detail.
	 */
	ret = fast_pf_fix_direct_spte(vcpu, sp, iterator.sptep, spte);
exit:
	trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep,
			      spte, ret);
	walk_shadow_page_lockless_end(vcpu);

	return ret;
}

static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
			 gva_t gva, pfn_t *pfn, bool write, bool *writable);
static void make_mmu_pages_available(struct kvm_vcpu *vcpu);

static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
			 gfn_t gfn, bool prefault)
{
	int r;
	int level;
	int force_pt_level;
	pfn_t pfn;
	unsigned long mmu_seq;
	bool map_writable, write = error_code & PFERR_WRITE_MASK;

	force_pt_level = mapping_level_dirty_bitmap(vcpu, gfn);
	if (likely(!force_pt_level)) {
		level = mapping_level(vcpu, gfn);
		/*
		 * 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);
	} else
		level = PT_PAGE_TABLE_LEVEL;

	if (fast_page_fault(vcpu, v, level, error_code))
		return 0;

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

	if (try_async_pf(vcpu, prefault, gfn, v, &pfn, write, &map_writable))
		return 0;

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

	spin_lock(&vcpu->kvm->mmu_lock);
	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
		goto out_unlock;
	make_mmu_pages_available(vcpu);
	if (likely(!force_pt_level))
		transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level);
	r = __direct_map(vcpu, v, write, map_writable, level, gfn, pfn,
			 prefault);
	spin_unlock(&vcpu->kvm->mmu_lock);


	return r;

out_unlock:
	spin_unlock(&vcpu->kvm->mmu_lock);
	kvm_release_pfn_clean(pfn);
	return 0;
}


static void mmu_free_roots(struct kvm_vcpu *vcpu)
{
	int i;
	struct kvm_mmu_page *sp;
	LIST_HEAD(invalid_list);

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

	if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL &&
	    (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL ||
	     vcpu->arch.mmu.direct_map)) {
		hpa_t root = vcpu->arch.mmu.root_hpa;

		spin_lock(&vcpu->kvm->mmu_lock);
		sp = page_header(root);
		--sp->root_count;
		if (!sp->root_count && sp->role.invalid) {
			kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list);
			kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
		}
		spin_unlock(&vcpu->kvm->mmu_lock);
		vcpu->arch.mmu.root_hpa = INVALID_PAGE;
		return;
	}

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

		if (root) {
			root &= PT64_BASE_ADDR_MASK;
			sp = page_header(root);
			--sp->root_count;
			if (!sp->root_count && sp->role.invalid)
				kvm_mmu_prepare_zap_page(vcpu->kvm, sp,
							 &invalid_list);
		}
		vcpu->arch.mmu.pae_root[i] = INVALID_PAGE;
	}
	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
	spin_unlock(&vcpu->kvm->mmu_lock);
	vcpu->arch.mmu.root_hpa = INVALID_PAGE;
}

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_LEVEL) {
		spin_lock(&vcpu->kvm->mmu_lock);
		make_mmu_pages_available(vcpu);
		sp = kvm_mmu_get_page(vcpu, 0, 0, PT64_ROOT_LEVEL,
				      1, ACC_ALL, NULL);
		++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];

			ASSERT(!VALID_PAGE(root));
			spin_lock(&vcpu->kvm->mmu_lock);
			make_mmu_pages_available(vcpu);
			sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT),
					      i << 30,
					      PT32_ROOT_LEVEL, 1, ACC_ALL,
					      NULL);
			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();

	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;
	int i;

	root_gfn = vcpu->arch.mmu.get_cr3(vcpu) >> 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_LEVEL) {
		hpa_t root = vcpu->arch.mmu.root_hpa;

		ASSERT(!VALID_PAGE(root));

		spin_lock(&vcpu->kvm->mmu_lock);
		make_mmu_pages_available(vcpu);
		sp = kvm_mmu_get_page(vcpu, root_gfn, 0, PT64_ROOT_LEVEL,
				      0, ACC_ALL, NULL);
		root = __pa(sp->spt);
		++sp->root_count;
		spin_unlock(&vcpu->kvm->mmu_lock);
		vcpu->arch.mmu.root_hpa = root;
		return 0;
	}

	/*
	 * 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_LEVEL)
		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];

		ASSERT(!VALID_PAGE(root));
		if (vcpu->arch.mmu.root_level == PT32E_ROOT_LEVEL) {
			pdptr = vcpu->arch.mmu.get_pdptr(vcpu, i);
			if (!is_present_gpte(pdptr)) {
				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);
		make_mmu_pages_available(vcpu);
		sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30,
				      PT32_ROOT_LEVEL, 0,
				      ACC_ALL, NULL);
		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_LEVEL) {
		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);
			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);
	}

	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);
}

static void 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);
	kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
	if (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL) {
		hpa_t root = vcpu->arch.mmu.root_hpa;
		sp = page_header(root);
		mmu_sync_children(vcpu, sp);
		kvm_mmu_audit(vcpu, AUDIT_POST_SYNC);
		return;
	}
	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);
}

void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
{
	spin_lock(&vcpu->kvm->mmu_lock);
	mmu_sync_roots(vcpu);
	spin_unlock(&vcpu->kvm->mmu_lock);
}
EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots);

static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_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, gva_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 quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct)
{
	if (direct)
		return vcpu_match_mmio_gpa(vcpu, addr);

	return vcpu_match_mmio_gva(vcpu, addr);
}


/*
 * On direct hosts, the last spte is only allows two states
 * for mmio page fault:
 *   - It is the mmio spte
 *   - It is zapped or it is being zapped.
 *
 * This function completely checks the spte when the last spte
 * is not the mmio spte.
 */
static bool check_direct_spte_mmio_pf(u64 spte)
{
	return __check_direct_spte_mmio_pf(spte);
}

static u64 walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr)
{
	struct kvm_shadow_walk_iterator iterator;
	u64 spte = 0ull;

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

	walk_shadow_page_lockless_begin(vcpu);
	for_each_shadow_entry_lockless(vcpu, addr, iterator, spte)
		if (!is_shadow_present_pte(spte))
			break;
	walk_shadow_page_lockless_end(vcpu);

	return spte;
}

int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct)
{
	u64 spte;

	if (quickly_check_mmio_pf(vcpu, addr, direct))
		return RET_MMIO_PF_EMULATE;

	spte = walk_shadow_page_get_mmio_spte(vcpu, addr);

	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->kvm, spte))
			return RET_MMIO_PF_INVALID;

		if (direct)
			addr = 0;

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

	/*
	 * It's ok if the gva is remapped by other cpus on shadow guest,
	 * it's a BUG if the gfn is not a mmio page.
	 */
	if (direct && !check_direct_spte_mmio_pf(spte))
		return RET_MMIO_PF_BUG;

	/*
	 * If the page table is zapped by other cpus, let CPU fault again on
	 * the address.
	 */
	return RET_MMIO_PF_RETRY;
}
EXPORT_SYMBOL_GPL(handle_mmio_page_fault_common);

static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr,
				  u32 error_code, bool direct)
{
	int ret;

	ret = handle_mmio_page_fault_common(vcpu, addr, direct);
	WARN_ON(ret == RET_MMIO_PF_BUG);
	return ret;
}

static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
				u32 error_code, bool prefault)
{
	gfn_t gfn;
	int r;

	pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code);

	if (unlikely(error_code & PFERR_RSVD_MASK)) {
		r = handle_mmio_page_fault(vcpu, gva, error_code, true);

		if (likely(r != RET_MMIO_PF_INVALID))
			return r;
	}

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

	ASSERT(vcpu);
	ASSERT(VALID_PAGE(vcpu->arch.mmu.root_hpa));

	gfn = gva >> PAGE_SHIFT;

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

static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, 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, gva, gfn_to_hva(vcpu->kvm, gfn), &arch);
}

static bool can_do_async_pf(struct kvm_vcpu *vcpu)
{
	if (unlikely(!irqchip_in_kernel(vcpu->kvm) ||
		     kvm_event_needs_reinjection(vcpu)))
		return false;

	return kvm_x86_ops->interrupt_allowed(vcpu);
}

static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
			 gva_t gva, pfn_t *pfn, bool write, bool *writable)
{
	bool async;

	*pfn = gfn_to_pfn_async(vcpu->kvm, gfn, &async, write, writable);

	if (!async)
		return false; /* *pfn has correct page already */

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

	*pfn = gfn_to_pfn_prot(vcpu->kvm, gfn, write, writable);

	return false;
}

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

	ASSERT(vcpu);
	ASSERT(VALID_PAGE(vcpu->arch.mmu.root_hpa));

	if (unlikely(error_code & PFERR_RSVD_MASK)) {
		r = handle_mmio_page_fault(vcpu, gpa, error_code, true);

		if (likely(r != RET_MMIO_PF_INVALID))
			return r;
	}

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

	force_pt_level = mapping_level_dirty_bitmap(vcpu, gfn);
	if (likely(!force_pt_level)) {
		level = mapping_level(vcpu, gfn);
		gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
	} else
		level = PT_PAGE_TABLE_LEVEL;

	if (fast_page_fault(vcpu, gpa, level, error_code))
		return 0;

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

	if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable))
		return 0;

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

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

	return r;

out_unlock:
	spin_unlock(&vcpu->kvm->mmu_lock);
	kvm_release_pfn_clean(pfn);
	return 0;
}

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->update_pte = nonpaging_update_pte;
	context->root_level = 0;
	context->shadow_root_level = PT32E_ROOT_LEVEL;
	context->root_hpa = INVALID_PAGE;
	context->direct_map = true;
	context->nx = false;
}

void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu)
{
	mmu_free_roots(vcpu);
}

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 *kvm, 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(kvm, sptep, gfn, access);
		return true;
	}

	return false;
}

static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gpte)
{
	unsigned index;

	index = level - 1;
	index |= (gpte & PT_PAGE_SIZE_MASK) >> (PT_PAGE_SIZE_SHIFT - 2);
	return mmu->last_pte_bitmap & (1 << index);
}

#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 kvm_mmu *context)
{
	int maxphyaddr = cpuid_maxphyaddr(vcpu);
	u64 exb_bit_rsvd = 0;
	u64 gbpages_bit_rsvd = 0;
	u64 nonleaf_bit8_rsvd = 0;

	context->bad_mt_xwr = 0;

	if (!context->nx)
		exb_bit_rsvd = rsvd_bits(63, 63);
	if (!guest_cpuid_has_gbpages(vcpu))
		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 (guest_cpuid_is_amd(vcpu))
		nonleaf_bit8_rsvd = rsvd_bits(8, 8);

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

		if (!is_pse(vcpu)) {
			context->rsvd_bits_mask[1][1] = 0;
			break;
		}

		if (is_cpuid_PSE36())
			/* 36bits PSE 4MB page */
			context->rsvd_bits_mask[1][1] = rsvd_bits(17, 21);
		else
			/* 32 bits PSE 4MB page */
			context->rsvd_bits_mask[1][1] = rsvd_bits(13, 21);
		break;
	case PT32E_ROOT_LEVEL:
		context->rsvd_bits_mask[0][2] =
			rsvd_bits(maxphyaddr, 63) |
			rsvd_bits(5, 8) | rsvd_bits(1, 2);	/* PDPTE */
		context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
			rsvd_bits(maxphyaddr, 62);	/* PDE */
		context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
			rsvd_bits(maxphyaddr, 62); 	/* PTE */
		context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
			rsvd_bits(maxphyaddr, 62) |
			rsvd_bits(13, 20);		/* large page */
		context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
		break;
	case PT64_ROOT_LEVEL:
		context->rsvd_bits_mask[0][3] = exb_bit_rsvd |
			nonleaf_bit8_rsvd | rsvd_bits(7, 7) | rsvd_bits(maxphyaddr, 51);
		context->rsvd_bits_mask[0][2] = exb_bit_rsvd |
			nonleaf_bit8_rsvd | gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51);
		context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
			rsvd_bits(maxphyaddr, 51);
		context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
			rsvd_bits(maxphyaddr, 51);
		context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3];
		context->rsvd_bits_mask[1][2] = exb_bit_rsvd |
			gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51) |
			rsvd_bits(13, 29);
		context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
			rsvd_bits(maxphyaddr, 51) |
			rsvd_bits(13, 20);		/* large page */
		context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
		break;
	}
}

static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
		struct kvm_mmu *context, bool execonly)
{
	int maxphyaddr = cpuid_maxphyaddr(vcpu);
	int pte;

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

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

	for (pte = 0; pte < 64; pte++) {
		int rwx_bits = pte & 7;
		int mt = pte >> 3;
		if (mt == 0x2 || mt == 0x3 || mt == 0x7 ||
				rwx_bits == 0x2 || rwx_bits == 0x6 ||
				(rwx_bits == 0x4 && !execonly))
			context->bad_mt_xwr |= (1ull << pte);
	}
}

void update_permission_bitmask(struct kvm_vcpu *vcpu,
		struct kvm_mmu *mmu, bool ept)
{
	unsigned bit, byte, pfec;
	u8 map;
	bool fault, x, w, u, wf, uf, ff, smapf, cr4_smap, cr4_smep, smap = 0;

	cr4_smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
	cr4_smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
	for (byte = 0; byte < ARRAY_SIZE(mmu->permissions); ++byte) {
		pfec = byte << 1;
		map = 0;
		wf = pfec & PFERR_WRITE_MASK;
		uf = pfec & PFERR_USER_MASK;
		ff = pfec & PFERR_FETCH_MASK;
		/*
		 * PFERR_RSVD_MASK bit is set in PFEC if the access is not
		 * subject to SMAP restrictions, and cleared otherwise. The
		 * bit is only meaningful if the SMAP bit is set in CR4.
		 */
		smapf = !(pfec & PFERR_RSVD_MASK);
		for (bit = 0; bit < 8; ++bit) {
			x = bit & ACC_EXEC_MASK;
			w = bit & ACC_WRITE_MASK;
			u = bit & ACC_USER_MASK;

			if (!ept) {
				/* Not really needed: !nx will cause pte.nx to fault */
				x |= !mmu->nx;
				/* Allow supervisor writes if !cr0.wp */
				w |= !is_write_protection(vcpu) && !uf;
				/* Disallow supervisor fetches of user code if cr4.smep */
				x &= !(cr4_smep && u && !uf);

				/*
				 * 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 ture:
				 *   - X86_CR4_SMAP is set in CR4
				 *   - An user page is accessed
				 *   - 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() and is in smapf.
				 *
				 *   Also, SMAP does not affect instruction
				 *   fetches, add the !ff check here to make it
				 *   clearer.
				 */
				smap = cr4_smap && u && !uf && !ff;
			} else
				/* Not really needed: no U/S accesses on ept  */
				u = 1;

			fault = (ff && !x) || (uf && !u) || (wf && !w) ||
				(smapf && smap);
			map |= fault << bit;
		}
		mmu->permissions[byte] = map;
	}
}

static void update_last_pte_bitmap(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
{
	u8 map;
	unsigned level, root_level = mmu->root_level;
	const unsigned ps_set_index = 1 << 2;  /* bit 2 of index: ps */

	if (root_level == PT32E_ROOT_LEVEL)
		--root_level;
	/* PT_PAGE_TABLE_LEVEL always terminates */
	map = 1 | (1 << ps_set_index);
	for (level = PT_DIRECTORY_LEVEL; level <= root_level; ++level) {
		if (level <= PT_PDPE_LEVEL
		    && (mmu->root_level >= PT32E_ROOT_LEVEL || is_pse(vcpu)))
			map |= 1 << (ps_set_index | (level - 1));
	}
	mmu->last_pte_bitmap = map;
}

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_last_pte_bitmap(vcpu, context);

	ASSERT(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->update_pte = paging64_update_pte;
	context->shadow_root_level = level;
	context->root_hpa = INVALID_PAGE;
	context->direct_map = false;
}

static void paging64_init_context(struct kvm_vcpu *vcpu,
				  struct kvm_mmu *context)
{
	paging64_init_context_common(vcpu, context, PT64_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_last_pte_bitmap(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->update_pte = paging32_update_pte;
	context->shadow_root_level = PT32E_ROOT_LEVEL;
	context->root_hpa = INVALID_PAGE;
	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 void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
{
	struct kvm_mmu *context = vcpu->arch.walk_mmu;

	context->base_role.word = 0;
	context->page_fault = tdp_page_fault;
	context->sync_page = nonpaging_sync_page;
	context->invlpg = nonpaging_invlpg;
	context->update_pte = nonpaging_update_pte;
	context->shadow_root_level = kvm_x86_ops->get_tdp_level();
	context->root_hpa = INVALID_PAGE;
	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 = PT64_ROOT_LEVEL;
		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_last_pte_bitmap(vcpu, context);
}

void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
{
	bool smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
	ASSERT(vcpu);
	ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa));

	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);

	vcpu->arch.mmu.base_role.nxe = is_nx(vcpu);
	vcpu->arch.mmu.base_role.cr4_pae = !!is_pae(vcpu);
	vcpu->arch.mmu.base_role.cr0_wp  = is_write_protection(vcpu);
	vcpu->arch.mmu.base_role.smep_andnot_wp
		= smep && !is_write_protection(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);

void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context,
		bool execonly)
{
	ASSERT(vcpu);
	ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa));

	context->shadow_root_level = kvm_x86_ops->get_tdp_level();

	context->nx = true;
	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->update_pte = ept_update_pte;
	context->root_level = context->shadow_root_level;
	context->root_hpa = INVALID_PAGE;
	context->direct_map = false;

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

static void init_kvm_softmmu(struct kvm_vcpu *vcpu)
{
	kvm_init_shadow_mmu(vcpu, vcpu->arch.walk_mmu);
	vcpu->arch.walk_mmu->set_cr3           = kvm_x86_ops->set_cr3;
	vcpu->arch.walk_mmu->get_cr3           = get_cr3;
	vcpu->arch.walk_mmu->get_pdptr         = kvm_pdptr_read;
	vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
}

static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
{
	struct kvm_mmu *g_context = &vcpu->arch.nested_mmu;

	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_gva to l1_gpa. The
	 * translation of l2_gpa to l1_gpa addresses is done using the
	 * arch.nested_mmu.gva_to_gpa function. 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 = PT64_ROOT_LEVEL;
		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_last_pte_bitmap(vcpu, g_context);
}

static void init_kvm_mmu(struct kvm_vcpu *vcpu)
{
	if (mmu_is_nested(vcpu))
		return init_kvm_nested_mmu(vcpu);
	else if (tdp_enabled)
		return init_kvm_tdp_mmu(vcpu);
	else
		return init_kvm_softmmu(vcpu);
}

void kvm_mmu_reset_context(struct kvm_vcpu *vcpu)
{
	ASSERT(vcpu);

	kvm_mmu_unload(vcpu);
	init_kvm_mmu(vcpu);
}
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;
	/* set_cr3() should ensure TLB has been flushed */
	vcpu->arch.mmu.set_cr3(vcpu, vcpu->arch.mmu.root_hpa);
out:
	return r;
}
EXPORT_SYMBOL_GPL(kvm_mmu_load);

void kvm_mmu_unload(struct kvm_vcpu *vcpu)
{
	mmu_free_roots(vcpu);
	WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa));
}
EXPORT_SYMBOL_GPL(kvm_mmu_unload);

static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
				  struct kvm_mmu_page *sp, u64 *spte,
				  const void *new)
{
	if (sp->role.level != PT_PAGE_TABLE_LEVEL) {
		++vcpu->kvm->stat.mmu_pde_zapped;
		return;
        }

	++vcpu->kvm->stat.mmu_pte_updated;
	vcpu->arch.mmu.update_pte(vcpu, sp, spte, new);
}

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 void mmu_pte_write_flush_tlb(struct kvm_vcpu *vcpu, bool zap_page,
				    bool remote_flush, bool local_flush)
{
	if (zap_page)
		return;

	if (remote_flush)
		kvm_flush_remote_tlbs(vcpu->kvm);
	else if (local_flush)
		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}

static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
				    const u8 *new, int *bytes)
{
	u64 gentry;
	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;
		r = kvm_read_guest(vcpu->kvm, *gpa, &gentry, 8);
		if (r)
			gentry = 0;
		new = (const u8 *)&gentry;
	}

	switch (*bytes) {
	case 4:
		gentry = *(const u32 *)new;
		break;
	case 8:
		gentry = *(const u64 *)new;
		break;
	default:
		gentry = 0;
		break;
	}

	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;

	return ++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.cr4_pae ? 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.cr4_pae) {
		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;
}

void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
		       const u8 *new, int bytes)
{
	gfn_t gfn = gpa >> PAGE_SHIFT;
	union kvm_mmu_page_role mask = { .word = 0 };
	struct kvm_mmu_page *sp;
	LIST_HEAD(invalid_list);
	u64 entry, gentry, *spte;
	int npte;
	bool remote_flush, local_flush, zap_page;

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

	zap_page = remote_flush = local_flush = false;

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

	gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, new, &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);
	++vcpu->kvm->stat.mmu_pte_write;
	kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);

	mask.cr0_wp = mask.cr4_pae = mask.nxe = 1;
	for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
		if (detect_write_misaligned(sp, gpa, bytes) ||
		      detect_write_flooding(sp)) {
			zap_page |= !!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.word ^ vcpu->arch.mmu.base_role.word)
			      & mask.word) && rmap_can_add(vcpu))
				mmu_pte_write_new_pte(vcpu, sp, spte, &gentry);
			if (need_remote_flush(entry, *spte))
				remote_flush = true;
			++spte;
		}
	}
	mmu_pte_write_flush_tlb(vcpu, zap_page, remote_flush, local_flush);
	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
	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 void 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;

	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);
}

static bool is_mmio_page_fault(struct kvm_vcpu *vcpu, gva_t addr)
{
	if (vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu))
		return vcpu_match_mmio_gpa(vcpu, addr);

	return vcpu_match_mmio_gva(vcpu, addr);
}

int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
		       void *insn, int insn_len)
{
	int r, emulation_type = EMULTYPE_RETRY;
	enum emulation_result er;

	r = vcpu->arch.mmu.page_fault(vcpu, cr2, error_code, false);
	if (r < 0)
		goto out;

	if (!r) {
		r = 1;
		goto out;
	}

	if (is_mmio_page_fault(vcpu, cr2))
		emulation_type = 0;

	er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len);

	switch (er) {
	case EMULATE_DONE:
		return 1;
	case EMULATE_USER_EXIT:
		++vcpu->stat.mmio_exits;
		/* fall through */
	case EMULATE_FAIL:
		return 0;
	default:
		BUG();
	}
out:
	return r;
}
EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);

void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
{
	vcpu->arch.mmu.invlpg(vcpu, gva);
	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
	++vcpu->stat.invlpg;
}
EXPORT_SYMBOL_GPL(kvm_mmu_invlpg);

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);

static void free_mmu_pages(struct kvm_vcpu *vcpu)
{
	free_page((unsigned long)vcpu->arch.mmu.pae_root);
	if (vcpu->arch.mmu.lm_root != NULL)
		free_page((unsigned long)vcpu->arch.mmu.lm_root);
}

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

	ASSERT(vcpu);

	/*
	 * When emulating 32-bit mode, cr3 is only 32 bits even on x86_64.
	 * Therefore we need to allocate shadow page tables in the first
	 * 4GB of memory, which happens to fit the DMA32 zone.
	 */
	page = alloc_page(GFP_KERNEL | __GFP_DMA32);
	if (!page)
		return -ENOMEM;

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

	return 0;
}

int kvm_mmu_create(struct kvm_vcpu *vcpu)
{
	ASSERT(vcpu);

	vcpu->arch.walk_mmu = &vcpu->arch.mmu;
	vcpu->arch.mmu.root_hpa = INVALID_PAGE;
	vcpu->arch.mmu.translate_gpa = translate_gpa;
	vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa;

	return alloc_mmu_pages(vcpu);
}

void kvm_mmu_setup(struct kvm_vcpu *vcpu)
{
	ASSERT(vcpu);
	ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa));

	init_kvm_mmu(vcpu);
}

void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot)
{
	struct kvm_memory_slot *memslot;
	gfn_t last_gfn;
	int i;

	memslot = id_to_memslot(kvm->memslots, slot);
	last_gfn = memslot->base_gfn + memslot->npages - 1;

	spin_lock(&kvm->mmu_lock);

	for (i = PT_PAGE_TABLE_LEVEL;
	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
		unsigned long *rmapp;
		unsigned long last_index, index;

		rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL];
		last_index = gfn_to_index(last_gfn, memslot->base_gfn, i);

		for (index = 0; index <= last_index; ++index, ++rmapp) {
			if (*rmapp)
				__rmap_write_protect(kvm, rmapp, false);

			if (need_resched() || spin_needbreak(&kvm->mmu_lock))
				cond_resched_lock(&kvm->mmu_lock);
		}
	}

	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
	 * haved checked SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE
	 * instead of PT_WRITABLE_MASK, that means it does not depend
	 * on PT_WRITABLE_MASK anymore.
	 */
	kvm_flush_remote_tlbs(kvm);
}

#define BATCH_ZAP_PAGES	10
static void kvm_zap_obsolete_pages(struct kvm *kvm)
{
	struct kvm_mmu_page *sp, *node;
	int batch = 0;

restart:
	list_for_each_entry_safe_reverse(sp, node,
	      &kvm->arch.active_mmu_pages, link) {
		int ret;

		/*
		 * No obsolete page exists before new created page since
		 * active_mmu_pages is the FIFO list.
		 */
		if (!is_obsolete_sp(kvm, sp))
			break;

		/*
		 * Since we are reversely walking the list and the invalid
		 * list will be moved to the head, skip the invalid page
		 * can help us to avoid the infinity list walking.
		 */
		if (sp->role.invalid)
			continue;

		/*
		 * Need not flush tlb since we only zap the sp with invalid
		 * generation number.
		 */
		if (batch >= BATCH_ZAP_PAGES &&
		      cond_resched_lock(&kvm->mmu_lock)) {
			batch = 0;
			goto restart;
		}

		ret = kvm_mmu_prepare_zap_page(kvm, sp,
				&kvm->arch.zapped_obsolete_pages);
		batch += ret;

		if (ret)
			goto restart;
	}

	/*
	 * Should flush tlb before free page tables since lockless-walking
	 * may use 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.
 */
void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm)
{
	spin_lock(&kvm->mmu_lock);
	trace_kvm_mmu_invalidate_zap_all_pages(kvm);
	kvm->arch.mmu_valid_gen++;

	/*
	 * 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 should 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));
}

void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm)
{
	/*
	 * The very rare case: if the generation-number is round,
	 * zap all shadow pages.
	 */
	if (unlikely(kvm_current_mmio_generation(kvm) == 0)) {
		printk_ratelimited(KERN_DEBUG "kvm: zapping shadow pages for mmio generation wraparound\n");
		kvm_mmu_invalidate_zap_all_pages(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;

	spin_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;
	}

	spin_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)
{
	if (pte_list_desc_cache)
		kmem_cache_destroy(pte_list_desc_cache);
	if (mmu_page_header_cache)
		kmem_cache_destroy(mmu_page_header_cache);
}

int kvm_mmu_module_init(void)
{
	pte_list_desc_cache = kmem_cache_create("pte_list_desc",
					    sizeof(struct pte_list_desc),
					    0, 0, NULL);
	if (!pte_list_desc_cache)
		goto nomem;

	mmu_page_header_cache = kmem_cache_create("kvm_mmu_page_header",
						  sizeof(struct kvm_mmu_page),
						  0, 0, NULL);
	if (!mmu_page_header_cache)
		goto nomem;

	if (percpu_counter_init(&kvm_total_used_mmu_pages, 0, GFP_KERNEL))
		goto nomem;

	register_shrinker(&mmu_shrinker);

	return 0;

nomem:
	mmu_destroy_caches();
	return -ENOMEM;
}

/*
 * Caculate mmu pages needed for kvm.
 */
unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
{
	unsigned int nr_mmu_pages;
	unsigned int  nr_pages = 0;
	struct kvm_memslots *slots;
	struct kvm_memory_slot *memslot;

	slots = kvm_memslots(kvm);

	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,
			(unsigned int) KVM_MIN_ALLOC_MMU_PAGES);

	return nr_mmu_pages;
}

int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4])
{
	struct kvm_shadow_walk_iterator iterator;
	u64 spte;
	int nr_sptes = 0;

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

	walk_shadow_page_lockless_begin(vcpu);
	for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) {
		sptes[iterator.level-1] = spte;
		nr_sptes++;
		if (!is_shadow_present_pte(spte))
			break;
	}
	walk_shadow_page_lockless_end(vcpu);

	return nr_sptes;
}
EXPORT_SYMBOL_GPL(kvm_mmu_get_spte_hierarchy);

void kvm_mmu_destroy(struct kvm_vcpu *vcpu)
{
	ASSERT(vcpu);

	kvm_mmu_unload(vcpu);
	free_mmu_pages(vcpu);
	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();
}