summaryrefslogtreecommitdiff
path: root/arch/s390/mm/gmap.c
blob: 906a7bfc2a7874052c0c381354098dcd37e8be19 (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
// SPDX-License-Identifier: GPL-2.0
/*
 *  KVM guest address space mapping code
 *
 *    Copyright IBM Corp. 2007, 2020
 *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
 *		 David Hildenbrand <david@redhat.com>
 *		 Janosch Frank <frankja@linux.vnet.ibm.com>
 */

#include <linux/kernel.h>
#include <linux/pagewalk.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/swapops.h>
#include <linux/ksm.h>
#include <linux/mman.h>
#include <linux/pgtable.h>

#include <asm/pgalloc.h>
#include <asm/gmap.h>
#include <asm/tlb.h>

#define GMAP_SHADOW_FAKE_TABLE 1ULL

/**
 * gmap_alloc - allocate and initialize a guest address space
 * @limit: maximum address of the gmap address space
 *
 * Returns a guest address space structure.
 */
static struct gmap *gmap_alloc(unsigned long limit)
{
	struct gmap *gmap;
	struct page *page;
	unsigned long *table;
	unsigned long etype, atype;

	if (limit < _REGION3_SIZE) {
		limit = _REGION3_SIZE - 1;
		atype = _ASCE_TYPE_SEGMENT;
		etype = _SEGMENT_ENTRY_EMPTY;
	} else if (limit < _REGION2_SIZE) {
		limit = _REGION2_SIZE - 1;
		atype = _ASCE_TYPE_REGION3;
		etype = _REGION3_ENTRY_EMPTY;
	} else if (limit < _REGION1_SIZE) {
		limit = _REGION1_SIZE - 1;
		atype = _ASCE_TYPE_REGION2;
		etype = _REGION2_ENTRY_EMPTY;
	} else {
		limit = -1UL;
		atype = _ASCE_TYPE_REGION1;
		etype = _REGION1_ENTRY_EMPTY;
	}
	gmap = kzalloc(sizeof(struct gmap), GFP_KERNEL_ACCOUNT);
	if (!gmap)
		goto out;
	INIT_LIST_HEAD(&gmap->crst_list);
	INIT_LIST_HEAD(&gmap->children);
	INIT_LIST_HEAD(&gmap->pt_list);
	INIT_RADIX_TREE(&gmap->guest_to_host, GFP_KERNEL_ACCOUNT);
	INIT_RADIX_TREE(&gmap->host_to_guest, GFP_ATOMIC | __GFP_ACCOUNT);
	INIT_RADIX_TREE(&gmap->host_to_rmap, GFP_ATOMIC | __GFP_ACCOUNT);
	spin_lock_init(&gmap->guest_table_lock);
	spin_lock_init(&gmap->shadow_lock);
	refcount_set(&gmap->ref_count, 1);
	page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER);
	if (!page)
		goto out_free;
	page->index = 0;
	list_add(&page->lru, &gmap->crst_list);
	table = page_to_virt(page);
	crst_table_init(table, etype);
	gmap->table = table;
	gmap->asce = atype | _ASCE_TABLE_LENGTH |
		_ASCE_USER_BITS | __pa(table);
	gmap->asce_end = limit;
	return gmap;

out_free:
	kfree(gmap);
out:
	return NULL;
}

/**
 * gmap_create - create a guest address space
 * @mm: pointer to the parent mm_struct
 * @limit: maximum size of the gmap address space
 *
 * Returns a guest address space structure.
 */
struct gmap *gmap_create(struct mm_struct *mm, unsigned long limit)
{
	struct gmap *gmap;
	unsigned long gmap_asce;

	gmap = gmap_alloc(limit);
	if (!gmap)
		return NULL;
	gmap->mm = mm;
	spin_lock(&mm->context.lock);
	list_add_rcu(&gmap->list, &mm->context.gmap_list);
	if (list_is_singular(&mm->context.gmap_list))
		gmap_asce = gmap->asce;
	else
		gmap_asce = -1UL;
	WRITE_ONCE(mm->context.gmap_asce, gmap_asce);
	spin_unlock(&mm->context.lock);
	return gmap;
}
EXPORT_SYMBOL_GPL(gmap_create);

static void gmap_flush_tlb(struct gmap *gmap)
{
	if (MACHINE_HAS_IDTE)
		__tlb_flush_idte(gmap->asce);
	else
		__tlb_flush_global();
}

static void gmap_radix_tree_free(struct radix_tree_root *root)
{
	struct radix_tree_iter iter;
	unsigned long indices[16];
	unsigned long index;
	void __rcu **slot;
	int i, nr;

	/* A radix tree is freed by deleting all of its entries */
	index = 0;
	do {
		nr = 0;
		radix_tree_for_each_slot(slot, root, &iter, index) {
			indices[nr] = iter.index;
			if (++nr == 16)
				break;
		}
		for (i = 0; i < nr; i++) {
			index = indices[i];
			radix_tree_delete(root, index);
		}
	} while (nr > 0);
}

static void gmap_rmap_radix_tree_free(struct radix_tree_root *root)
{
	struct gmap_rmap *rmap, *rnext, *head;
	struct radix_tree_iter iter;
	unsigned long indices[16];
	unsigned long index;
	void __rcu **slot;
	int i, nr;

	/* A radix tree is freed by deleting all of its entries */
	index = 0;
	do {
		nr = 0;
		radix_tree_for_each_slot(slot, root, &iter, index) {
			indices[nr] = iter.index;
			if (++nr == 16)
				break;
		}
		for (i = 0; i < nr; i++) {
			index = indices[i];
			head = radix_tree_delete(root, index);
			gmap_for_each_rmap_safe(rmap, rnext, head)
				kfree(rmap);
		}
	} while (nr > 0);
}

/**
 * gmap_free - free a guest address space
 * @gmap: pointer to the guest address space structure
 *
 * No locks required. There are no references to this gmap anymore.
 */
static void gmap_free(struct gmap *gmap)
{
	struct page *page, *next;

	/* Flush tlb of all gmaps (if not already done for shadows) */
	if (!(gmap_is_shadow(gmap) && gmap->removed))
		gmap_flush_tlb(gmap);
	/* Free all segment & region tables. */
	list_for_each_entry_safe(page, next, &gmap->crst_list, lru)
		__free_pages(page, CRST_ALLOC_ORDER);
	gmap_radix_tree_free(&gmap->guest_to_host);
	gmap_radix_tree_free(&gmap->host_to_guest);

	/* Free additional data for a shadow gmap */
	if (gmap_is_shadow(gmap)) {
		/* Free all page tables. */
		list_for_each_entry_safe(page, next, &gmap->pt_list, lru)
			page_table_free_pgste(page);
		gmap_rmap_radix_tree_free(&gmap->host_to_rmap);
		/* Release reference to the parent */
		gmap_put(gmap->parent);
	}

	kfree(gmap);
}

/**
 * gmap_get - increase reference counter for guest address space
 * @gmap: pointer to the guest address space structure
 *
 * Returns the gmap pointer
 */
struct gmap *gmap_get(struct gmap *gmap)
{
	refcount_inc(&gmap->ref_count);
	return gmap;
}
EXPORT_SYMBOL_GPL(gmap_get);

/**
 * gmap_put - decrease reference counter for guest address space
 * @gmap: pointer to the guest address space structure
 *
 * If the reference counter reaches zero the guest address space is freed.
 */
void gmap_put(struct gmap *gmap)
{
	if (refcount_dec_and_test(&gmap->ref_count))
		gmap_free(gmap);
}
EXPORT_SYMBOL_GPL(gmap_put);

/**
 * gmap_remove - remove a guest address space but do not free it yet
 * @gmap: pointer to the guest address space structure
 */
void gmap_remove(struct gmap *gmap)
{
	struct gmap *sg, *next;
	unsigned long gmap_asce;

	/* Remove all shadow gmaps linked to this gmap */
	if (!list_empty(&gmap->children)) {
		spin_lock(&gmap->shadow_lock);
		list_for_each_entry_safe(sg, next, &gmap->children, list) {
			list_del(&sg->list);
			gmap_put(sg);
		}
		spin_unlock(&gmap->shadow_lock);
	}
	/* Remove gmap from the pre-mm list */
	spin_lock(&gmap->mm->context.lock);
	list_del_rcu(&gmap->list);
	if (list_empty(&gmap->mm->context.gmap_list))
		gmap_asce = 0;
	else if (list_is_singular(&gmap->mm->context.gmap_list))
		gmap_asce = list_first_entry(&gmap->mm->context.gmap_list,
					     struct gmap, list)->asce;
	else
		gmap_asce = -1UL;
	WRITE_ONCE(gmap->mm->context.gmap_asce, gmap_asce);
	spin_unlock(&gmap->mm->context.lock);
	synchronize_rcu();
	/* Put reference */
	gmap_put(gmap);
}
EXPORT_SYMBOL_GPL(gmap_remove);

/**
 * gmap_enable - switch primary space to the guest address space
 * @gmap: pointer to the guest address space structure
 */
void gmap_enable(struct gmap *gmap)
{
	S390_lowcore.gmap = (unsigned long) gmap;
}
EXPORT_SYMBOL_GPL(gmap_enable);

/**
 * gmap_disable - switch back to the standard primary address space
 * @gmap: pointer to the guest address space structure
 */
void gmap_disable(struct gmap *gmap)
{
	S390_lowcore.gmap = 0UL;
}
EXPORT_SYMBOL_GPL(gmap_disable);

/**
 * gmap_get_enabled - get a pointer to the currently enabled gmap
 *
 * Returns a pointer to the currently enabled gmap. 0 if none is enabled.
 */
struct gmap *gmap_get_enabled(void)
{
	return (struct gmap *) S390_lowcore.gmap;
}
EXPORT_SYMBOL_GPL(gmap_get_enabled);

/*
 * gmap_alloc_table is assumed to be called with mmap_lock held
 */
static int gmap_alloc_table(struct gmap *gmap, unsigned long *table,
			    unsigned long init, unsigned long gaddr)
{
	struct page *page;
	unsigned long *new;

	/* since we dont free the gmap table until gmap_free we can unlock */
	page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER);
	if (!page)
		return -ENOMEM;
	new = page_to_virt(page);
	crst_table_init(new, init);
	spin_lock(&gmap->guest_table_lock);
	if (*table & _REGION_ENTRY_INVALID) {
		list_add(&page->lru, &gmap->crst_list);
		*table = __pa(new) | _REGION_ENTRY_LENGTH |
			(*table & _REGION_ENTRY_TYPE_MASK);
		page->index = gaddr;
		page = NULL;
	}
	spin_unlock(&gmap->guest_table_lock);
	if (page)
		__free_pages(page, CRST_ALLOC_ORDER);
	return 0;
}

/**
 * __gmap_segment_gaddr - find virtual address from segment pointer
 * @entry: pointer to a segment table entry in the guest address space
 *
 * Returns the virtual address in the guest address space for the segment
 */
static unsigned long __gmap_segment_gaddr(unsigned long *entry)
{
	struct page *page;
	unsigned long offset;

	offset = (unsigned long) entry / sizeof(unsigned long);
	offset = (offset & (PTRS_PER_PMD - 1)) * PMD_SIZE;
	page = pmd_pgtable_page((pmd_t *) entry);
	return page->index + offset;
}

/**
 * __gmap_unlink_by_vmaddr - unlink a single segment via a host address
 * @gmap: pointer to the guest address space structure
 * @vmaddr: address in the host process address space
 *
 * Returns 1 if a TLB flush is required
 */
static int __gmap_unlink_by_vmaddr(struct gmap *gmap, unsigned long vmaddr)
{
	unsigned long *entry;
	int flush = 0;

	BUG_ON(gmap_is_shadow(gmap));
	spin_lock(&gmap->guest_table_lock);
	entry = radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT);
	if (entry) {
		flush = (*entry != _SEGMENT_ENTRY_EMPTY);
		*entry = _SEGMENT_ENTRY_EMPTY;
	}
	spin_unlock(&gmap->guest_table_lock);
	return flush;
}

/**
 * __gmap_unmap_by_gaddr - unmap a single segment via a guest address
 * @gmap: pointer to the guest address space structure
 * @gaddr: address in the guest address space
 *
 * Returns 1 if a TLB flush is required
 */
static int __gmap_unmap_by_gaddr(struct gmap *gmap, unsigned long gaddr)
{
	unsigned long vmaddr;

	vmaddr = (unsigned long) radix_tree_delete(&gmap->guest_to_host,
						   gaddr >> PMD_SHIFT);
	return vmaddr ? __gmap_unlink_by_vmaddr(gmap, vmaddr) : 0;
}

/**
 * gmap_unmap_segment - unmap segment from the guest address space
 * @gmap: pointer to the guest address space structure
 * @to: address in the guest address space
 * @len: length of the memory area to unmap
 *
 * Returns 0 if the unmap succeeded, -EINVAL if not.
 */
int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len)
{
	unsigned long off;
	int flush;

	BUG_ON(gmap_is_shadow(gmap));
	if ((to | len) & (PMD_SIZE - 1))
		return -EINVAL;
	if (len == 0 || to + len < to)
		return -EINVAL;

	flush = 0;
	mmap_write_lock(gmap->mm);
	for (off = 0; off < len; off += PMD_SIZE)
		flush |= __gmap_unmap_by_gaddr(gmap, to + off);
	mmap_write_unlock(gmap->mm);
	if (flush)
		gmap_flush_tlb(gmap);
	return 0;
}
EXPORT_SYMBOL_GPL(gmap_unmap_segment);

/**
 * gmap_map_segment - map a segment to the guest address space
 * @gmap: pointer to the guest address space structure
 * @from: source address in the parent address space
 * @to: target address in the guest address space
 * @len: length of the memory area to map
 *
 * Returns 0 if the mmap succeeded, -EINVAL or -ENOMEM if not.
 */
int gmap_map_segment(struct gmap *gmap, unsigned long from,
		     unsigned long to, unsigned long len)
{
	unsigned long off;
	int flush;

	BUG_ON(gmap_is_shadow(gmap));
	if ((from | to | len) & (PMD_SIZE - 1))
		return -EINVAL;
	if (len == 0 || from + len < from || to + len < to ||
	    from + len - 1 > TASK_SIZE_MAX || to + len - 1 > gmap->asce_end)
		return -EINVAL;

	flush = 0;
	mmap_write_lock(gmap->mm);
	for (off = 0; off < len; off += PMD_SIZE) {
		/* Remove old translation */
		flush |= __gmap_unmap_by_gaddr(gmap, to + off);
		/* Store new translation */
		if (radix_tree_insert(&gmap->guest_to_host,
				      (to + off) >> PMD_SHIFT,
				      (void *) from + off))
			break;
	}
	mmap_write_unlock(gmap->mm);
	if (flush)
		gmap_flush_tlb(gmap);
	if (off >= len)
		return 0;
	gmap_unmap_segment(gmap, to, len);
	return -ENOMEM;
}
EXPORT_SYMBOL_GPL(gmap_map_segment);

/**
 * __gmap_translate - translate a guest address to a user space address
 * @gmap: pointer to guest mapping meta data structure
 * @gaddr: guest address
 *
 * Returns user space address which corresponds to the guest address or
 * -EFAULT if no such mapping exists.
 * This function does not establish potentially missing page table entries.
 * The mmap_lock of the mm that belongs to the address space must be held
 * when this function gets called.
 *
 * Note: Can also be called for shadow gmaps.
 */
unsigned long __gmap_translate(struct gmap *gmap, unsigned long gaddr)
{
	unsigned long vmaddr;

	vmaddr = (unsigned long)
		radix_tree_lookup(&gmap->guest_to_host, gaddr >> PMD_SHIFT);
	/* Note: guest_to_host is empty for a shadow gmap */
	return vmaddr ? (vmaddr | (gaddr & ~PMD_MASK)) : -EFAULT;
}
EXPORT_SYMBOL_GPL(__gmap_translate);

/**
 * gmap_translate - translate a guest address to a user space address
 * @gmap: pointer to guest mapping meta data structure
 * @gaddr: guest address
 *
 * Returns user space address which corresponds to the guest address or
 * -EFAULT if no such mapping exists.
 * This function does not establish potentially missing page table entries.
 */
unsigned long gmap_translate(struct gmap *gmap, unsigned long gaddr)
{
	unsigned long rc;

	mmap_read_lock(gmap->mm);
	rc = __gmap_translate(gmap, gaddr);
	mmap_read_unlock(gmap->mm);
	return rc;
}
EXPORT_SYMBOL_GPL(gmap_translate);

/**
 * gmap_unlink - disconnect a page table from the gmap shadow tables
 * @mm: pointer to the parent mm_struct
 * @table: pointer to the host page table
 * @vmaddr: vm address associated with the host page table
 */
void gmap_unlink(struct mm_struct *mm, unsigned long *table,
		 unsigned long vmaddr)
{
	struct gmap *gmap;
	int flush;

	rcu_read_lock();
	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
		flush = __gmap_unlink_by_vmaddr(gmap, vmaddr);
		if (flush)
			gmap_flush_tlb(gmap);
	}
	rcu_read_unlock();
}

static void gmap_pmdp_xchg(struct gmap *gmap, pmd_t *old, pmd_t new,
			   unsigned long gaddr);

/**
 * __gmap_link - set up shadow page tables to connect a host to a guest address
 * @gmap: pointer to guest mapping meta data structure
 * @gaddr: guest address
 * @vmaddr: vm address
 *
 * Returns 0 on success, -ENOMEM for out of memory conditions, and -EFAULT
 * if the vm address is already mapped to a different guest segment.
 * The mmap_lock of the mm that belongs to the address space must be held
 * when this function gets called.
 */
int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
{
	struct mm_struct *mm;
	unsigned long *table;
	spinlock_t *ptl;
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;
	u64 unprot;
	int rc;

	BUG_ON(gmap_is_shadow(gmap));
	/* Create higher level tables in the gmap page table */
	table = gmap->table;
	if ((gmap->asce & _ASCE_TYPE_MASK) >= _ASCE_TYPE_REGION1) {
		table += (gaddr & _REGION1_INDEX) >> _REGION1_SHIFT;
		if ((*table & _REGION_ENTRY_INVALID) &&
		    gmap_alloc_table(gmap, table, _REGION2_ENTRY_EMPTY,
				     gaddr & _REGION1_MASK))
			return -ENOMEM;
		table = __va(*table & _REGION_ENTRY_ORIGIN);
	}
	if ((gmap->asce & _ASCE_TYPE_MASK) >= _ASCE_TYPE_REGION2) {
		table += (gaddr & _REGION2_INDEX) >> _REGION2_SHIFT;
		if ((*table & _REGION_ENTRY_INVALID) &&
		    gmap_alloc_table(gmap, table, _REGION3_ENTRY_EMPTY,
				     gaddr & _REGION2_MASK))
			return -ENOMEM;
		table = __va(*table & _REGION_ENTRY_ORIGIN);
	}
	if ((gmap->asce & _ASCE_TYPE_MASK) >= _ASCE_TYPE_REGION3) {
		table += (gaddr & _REGION3_INDEX) >> _REGION3_SHIFT;
		if ((*table & _REGION_ENTRY_INVALID) &&
		    gmap_alloc_table(gmap, table, _SEGMENT_ENTRY_EMPTY,
				     gaddr & _REGION3_MASK))
			return -ENOMEM;
		table = __va(*table & _REGION_ENTRY_ORIGIN);
	}
	table += (gaddr & _SEGMENT_INDEX) >> _SEGMENT_SHIFT;
	/* Walk the parent mm page table */
	mm = gmap->mm;
	pgd = pgd_offset(mm, vmaddr);
	VM_BUG_ON(pgd_none(*pgd));
	p4d = p4d_offset(pgd, vmaddr);
	VM_BUG_ON(p4d_none(*p4d));
	pud = pud_offset(p4d, vmaddr);
	VM_BUG_ON(pud_none(*pud));
	/* large puds cannot yet be handled */
	if (pud_large(*pud))
		return -EFAULT;
	pmd = pmd_offset(pud, vmaddr);
	VM_BUG_ON(pmd_none(*pmd));
	/* Are we allowed to use huge pages? */
	if (pmd_large(*pmd) && !gmap->mm->context.allow_gmap_hpage_1m)
		return -EFAULT;
	/* Link gmap segment table entry location to page table. */
	rc = radix_tree_preload(GFP_KERNEL_ACCOUNT);
	if (rc)
		return rc;
	ptl = pmd_lock(mm, pmd);
	spin_lock(&gmap->guest_table_lock);
	if (*table == _SEGMENT_ENTRY_EMPTY) {
		rc = radix_tree_insert(&gmap->host_to_guest,
				       vmaddr >> PMD_SHIFT, table);
		if (!rc) {
			if (pmd_large(*pmd)) {
				*table = (pmd_val(*pmd) &
					  _SEGMENT_ENTRY_HARDWARE_BITS_LARGE)
					| _SEGMENT_ENTRY_GMAP_UC;
			} else
				*table = pmd_val(*pmd) &
					_SEGMENT_ENTRY_HARDWARE_BITS;
		}
	} else if (*table & _SEGMENT_ENTRY_PROTECT &&
		   !(pmd_val(*pmd) & _SEGMENT_ENTRY_PROTECT)) {
		unprot = (u64)*table;
		unprot &= ~_SEGMENT_ENTRY_PROTECT;
		unprot |= _SEGMENT_ENTRY_GMAP_UC;
		gmap_pmdp_xchg(gmap, (pmd_t *)table, __pmd(unprot), gaddr);
	}
	spin_unlock(&gmap->guest_table_lock);
	spin_unlock(ptl);
	radix_tree_preload_end();
	return rc;
}

/**
 * gmap_fault - resolve a fault on a guest address
 * @gmap: pointer to guest mapping meta data structure
 * @gaddr: guest address
 * @fault_flags: flags to pass down to handle_mm_fault()
 *
 * Returns 0 on success, -ENOMEM for out of memory conditions, and -EFAULT
 * if the vm address is already mapped to a different guest segment.
 */
int gmap_fault(struct gmap *gmap, unsigned long gaddr,
	       unsigned int fault_flags)
{
	unsigned long vmaddr;
	int rc;
	bool unlocked;

	mmap_read_lock(gmap->mm);

retry:
	unlocked = false;
	vmaddr = __gmap_translate(gmap, gaddr);
	if (IS_ERR_VALUE(vmaddr)) {
		rc = vmaddr;
		goto out_up;
	}
	if (fixup_user_fault(gmap->mm, vmaddr, fault_flags,
			     &unlocked)) {
		rc = -EFAULT;
		goto out_up;
	}
	/*
	 * In the case that fixup_user_fault unlocked the mmap_lock during
	 * faultin redo __gmap_translate to not race with a map/unmap_segment.
	 */
	if (unlocked)
		goto retry;

	rc = __gmap_link(gmap, gaddr, vmaddr);
out_up:
	mmap_read_unlock(gmap->mm);
	return rc;
}
EXPORT_SYMBOL_GPL(gmap_fault);

/*
 * this function is assumed to be called with mmap_lock held
 */
void __gmap_zap(struct gmap *gmap, unsigned long gaddr)
{
	struct vm_area_struct *vma;
	unsigned long vmaddr;
	spinlock_t *ptl;
	pte_t *ptep;

	/* Find the vm address for the guest address */
	vmaddr = (unsigned long) radix_tree_lookup(&gmap->guest_to_host,
						   gaddr >> PMD_SHIFT);
	if (vmaddr) {
		vmaddr |= gaddr & ~PMD_MASK;

		vma = vma_lookup(gmap->mm, vmaddr);
		if (!vma || is_vm_hugetlb_page(vma))
			return;

		/* Get pointer to the page table entry */
		ptep = get_locked_pte(gmap->mm, vmaddr, &ptl);
		if (likely(ptep)) {
			ptep_zap_unused(gmap->mm, vmaddr, ptep, 0);
			pte_unmap_unlock(ptep, ptl);
		}
	}
}
EXPORT_SYMBOL_GPL(__gmap_zap);

void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to)
{
	unsigned long gaddr, vmaddr, size;
	struct vm_area_struct *vma;

	mmap_read_lock(gmap->mm);
	for (gaddr = from; gaddr < to;
	     gaddr = (gaddr + PMD_SIZE) & PMD_MASK) {
		/* Find the vm address for the guest address */
		vmaddr = (unsigned long)
			radix_tree_lookup(&gmap->guest_to_host,
					  gaddr >> PMD_SHIFT);
		if (!vmaddr)
			continue;
		vmaddr |= gaddr & ~PMD_MASK;
		/* Find vma in the parent mm */
		vma = find_vma(gmap->mm, vmaddr);
		if (!vma)
			continue;
		/*
		 * We do not discard pages that are backed by
		 * hugetlbfs, so we don't have to refault them.
		 */
		if (is_vm_hugetlb_page(vma))
			continue;
		size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK));
		zap_page_range_single(vma, vmaddr, size, NULL);
	}
	mmap_read_unlock(gmap->mm);
}
EXPORT_SYMBOL_GPL(gmap_discard);

static LIST_HEAD(gmap_notifier_list);
static DEFINE_SPINLOCK(gmap_notifier_lock);

/**
 * gmap_register_pte_notifier - register a pte invalidation callback
 * @nb: pointer to the gmap notifier block
 */
void gmap_register_pte_notifier(struct gmap_notifier *nb)
{
	spin_lock(&gmap_notifier_lock);
	list_add_rcu(&nb->list, &gmap_notifier_list);
	spin_unlock(&gmap_notifier_lock);
}
EXPORT_SYMBOL_GPL(gmap_register_pte_notifier);

/**
 * gmap_unregister_pte_notifier - remove a pte invalidation callback
 * @nb: pointer to the gmap notifier block
 */
void gmap_unregister_pte_notifier(struct gmap_notifier *nb)
{
	spin_lock(&gmap_notifier_lock);
	list_del_rcu(&nb->list);
	spin_unlock(&gmap_notifier_lock);
	synchronize_rcu();
}
EXPORT_SYMBOL_GPL(gmap_unregister_pte_notifier);

/**
 * gmap_call_notifier - call all registered invalidation callbacks
 * @gmap: pointer to guest mapping meta data structure
 * @start: start virtual address in the guest address space
 * @end: end virtual address in the guest address space
 */
static void gmap_call_notifier(struct gmap *gmap, unsigned long start,
			       unsigned long end)
{
	struct gmap_notifier *nb;

	list_for_each_entry(nb, &gmap_notifier_list, list)
		nb->notifier_call(gmap, start, end);
}

/**
 * gmap_table_walk - walk the gmap page tables
 * @gmap: pointer to guest mapping meta data structure
 * @gaddr: virtual address in the guest address space
 * @level: page table level to stop at
 *
 * Returns a table entry pointer for the given guest address and @level
 * @level=0 : returns a pointer to a page table table entry (or NULL)
 * @level=1 : returns a pointer to a segment table entry (or NULL)
 * @level=2 : returns a pointer to a region-3 table entry (or NULL)
 * @level=3 : returns a pointer to a region-2 table entry (or NULL)
 * @level=4 : returns a pointer to a region-1 table entry (or NULL)
 *
 * Returns NULL if the gmap page tables could not be walked to the
 * requested level.
 *
 * Note: Can also be called for shadow gmaps.
 */
static inline unsigned long *gmap_table_walk(struct gmap *gmap,
					     unsigned long gaddr, int level)
{
	const int asce_type = gmap->asce & _ASCE_TYPE_MASK;
	unsigned long *table = gmap->table;

	if (gmap_is_shadow(gmap) && gmap->removed)
		return NULL;

	if (WARN_ON_ONCE(level > (asce_type >> 2) + 1))
		return NULL;

	if (asce_type != _ASCE_TYPE_REGION1 &&
	    gaddr & (-1UL << (31 + (asce_type >> 2) * 11)))
		return NULL;

	switch (asce_type) {
	case _ASCE_TYPE_REGION1:
		table += (gaddr & _REGION1_INDEX) >> _REGION1_SHIFT;
		if (level == 4)
			break;
		if (*table & _REGION_ENTRY_INVALID)
			return NULL;
		table = __va(*table & _REGION_ENTRY_ORIGIN);
		fallthrough;
	case _ASCE_TYPE_REGION2:
		table += (gaddr & _REGION2_INDEX) >> _REGION2_SHIFT;
		if (level == 3)
			break;
		if (*table & _REGION_ENTRY_INVALID)
			return NULL;
		table = __va(*table & _REGION_ENTRY_ORIGIN);
		fallthrough;
	case _ASCE_TYPE_REGION3:
		table += (gaddr & _REGION3_INDEX) >> _REGION3_SHIFT;
		if (level == 2)
			break;
		if (*table & _REGION_ENTRY_INVALID)
			return NULL;
		table = __va(*table & _REGION_ENTRY_ORIGIN);
		fallthrough;
	case _ASCE_TYPE_SEGMENT:
		table += (gaddr & _SEGMENT_INDEX) >> _SEGMENT_SHIFT;
		if (level == 1)
			break;
		if (*table & _REGION_ENTRY_INVALID)
			return NULL;
		table = __va(*table & _SEGMENT_ENTRY_ORIGIN);
		table += (gaddr & _PAGE_INDEX) >> _PAGE_SHIFT;
	}
	return table;
}

/**
 * gmap_pte_op_walk - walk the gmap page table, get the page table lock
 *		      and return the pte pointer
 * @gmap: pointer to guest mapping meta data structure
 * @gaddr: virtual address in the guest address space
 * @ptl: pointer to the spinlock pointer
 *
 * Returns a pointer to the locked pte for a guest address, or NULL
 */
static pte_t *gmap_pte_op_walk(struct gmap *gmap, unsigned long gaddr,
			       spinlock_t **ptl)
{
	unsigned long *table;

	BUG_ON(gmap_is_shadow(gmap));
	/* Walk the gmap page table, lock and get pte pointer */
	table = gmap_table_walk(gmap, gaddr, 1); /* get segment pointer */
	if (!table || *table & _SEGMENT_ENTRY_INVALID)
		return NULL;
	return pte_alloc_map_lock(gmap->mm, (pmd_t *) table, gaddr, ptl);
}

/**
 * gmap_pte_op_fixup - force a page in and connect the gmap page table
 * @gmap: pointer to guest mapping meta data structure
 * @gaddr: virtual address in the guest address space
 * @vmaddr: address in the host process address space
 * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
 *
 * Returns 0 if the caller can retry __gmap_translate (might fail again),
 * -ENOMEM if out of memory and -EFAULT if anything goes wrong while fixing
 * up or connecting the gmap page table.
 */
static int gmap_pte_op_fixup(struct gmap *gmap, unsigned long gaddr,
			     unsigned long vmaddr, int prot)
{
	struct mm_struct *mm = gmap->mm;
	unsigned int fault_flags;
	bool unlocked = false;

	BUG_ON(gmap_is_shadow(gmap));
	fault_flags = (prot == PROT_WRITE) ? FAULT_FLAG_WRITE : 0;
	if (fixup_user_fault(mm, vmaddr, fault_flags, &unlocked))
		return -EFAULT;
	if (unlocked)
		/* lost mmap_lock, caller has to retry __gmap_translate */
		return 0;
	/* Connect the page tables */
	return __gmap_link(gmap, gaddr, vmaddr);
}

/**
 * gmap_pte_op_end - release the page table lock
 * @ptep: pointer to the locked pte
 * @ptl: pointer to the page table spinlock
 */
static void gmap_pte_op_end(pte_t *ptep, spinlock_t *ptl)
{
	pte_unmap_unlock(ptep, ptl);
}

/**
 * gmap_pmd_op_walk - walk the gmap tables, get the guest table lock
 *		      and return the pmd pointer
 * @gmap: pointer to guest mapping meta data structure
 * @gaddr: virtual address in the guest address space
 *
 * Returns a pointer to the pmd for a guest address, or NULL
 */
static inline pmd_t *gmap_pmd_op_walk(struct gmap *gmap, unsigned long gaddr)
{
	pmd_t *pmdp;

	BUG_ON(gmap_is_shadow(gmap));
	pmdp = (pmd_t *) gmap_table_walk(gmap, gaddr, 1);
	if (!pmdp)
		return NULL;

	/* without huge pages, there is no need to take the table lock */
	if (!gmap->mm->context.allow_gmap_hpage_1m)
		return pmd_none(*pmdp) ? NULL : pmdp;

	spin_lock(&gmap->guest_table_lock);
	if (pmd_none(*pmdp)) {
		spin_unlock(&gmap->guest_table_lock);
		return NULL;
	}

	/* 4k page table entries are locked via the pte (pte_alloc_map_lock). */
	if (!pmd_large(*pmdp))
		spin_unlock(&gmap->guest_table_lock);
	return pmdp;
}

/**
 * gmap_pmd_op_end - release the guest_table_lock if needed
 * @gmap: pointer to the guest mapping meta data structure
 * @pmdp: pointer to the pmd
 */
static inline void gmap_pmd_op_end(struct gmap *gmap, pmd_t *pmdp)
{
	if (pmd_large(*pmdp))
		spin_unlock(&gmap->guest_table_lock);
}

/*
 * gmap_protect_pmd - remove access rights to memory and set pmd notification bits
 * @pmdp: pointer to the pmd to be protected
 * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
 * @bits: notification bits to set
 *
 * Returns:
 * 0 if successfully protected
 * -EAGAIN if a fixup is needed
 * -EINVAL if unsupported notifier bits have been specified
 *
 * Expected to be called with sg->mm->mmap_lock in read and
 * guest_table_lock held.
 */
static int gmap_protect_pmd(struct gmap *gmap, unsigned long gaddr,
			    pmd_t *pmdp, int prot, unsigned long bits)
{
	int pmd_i = pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID;
	int pmd_p = pmd_val(*pmdp) & _SEGMENT_ENTRY_PROTECT;
	pmd_t new = *pmdp;

	/* Fixup needed */
	if ((pmd_i && (prot != PROT_NONE)) || (pmd_p && (prot == PROT_WRITE)))
		return -EAGAIN;

	if (prot == PROT_NONE && !pmd_i) {
		new = set_pmd_bit(new, __pgprot(_SEGMENT_ENTRY_INVALID));
		gmap_pmdp_xchg(gmap, pmdp, new, gaddr);
	}

	if (prot == PROT_READ && !pmd_p) {
		new = clear_pmd_bit(new, __pgprot(_SEGMENT_ENTRY_INVALID));
		new = set_pmd_bit(new, __pgprot(_SEGMENT_ENTRY_PROTECT));
		gmap_pmdp_xchg(gmap, pmdp, new, gaddr);
	}

	if (bits & GMAP_NOTIFY_MPROT)
		set_pmd(pmdp, set_pmd_bit(*pmdp, __pgprot(_SEGMENT_ENTRY_GMAP_IN)));

	/* Shadow GMAP protection needs split PMDs */
	if (bits & GMAP_NOTIFY_SHADOW)
		return -EINVAL;

	return 0;
}

/*
 * gmap_protect_pte - remove access rights to memory and set pgste bits
 * @gmap: pointer to guest mapping meta data structure
 * @gaddr: virtual address in the guest address space
 * @pmdp: pointer to the pmd associated with the pte
 * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
 * @bits: notification bits to set
 *
 * Returns 0 if successfully protected, -ENOMEM if out of memory and
 * -EAGAIN if a fixup is needed.
 *
 * Expected to be called with sg->mm->mmap_lock in read
 */
static int gmap_protect_pte(struct gmap *gmap, unsigned long gaddr,
			    pmd_t *pmdp, int prot, unsigned long bits)
{
	int rc;
	pte_t *ptep;
	spinlock_t *ptl;
	unsigned long pbits = 0;

	if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
		return -EAGAIN;

	ptep = pte_alloc_map_lock(gmap->mm, pmdp, gaddr, &ptl);
	if (!ptep)
		return -ENOMEM;

	pbits |= (bits & GMAP_NOTIFY_MPROT) ? PGSTE_IN_BIT : 0;
	pbits |= (bits & GMAP_NOTIFY_SHADOW) ? PGSTE_VSIE_BIT : 0;
	/* Protect and unlock. */
	rc = ptep_force_prot(gmap->mm, gaddr, ptep, prot, pbits);
	gmap_pte_op_end(ptep, ptl);
	return rc;
}

/*
 * gmap_protect_range - remove access rights to memory and set pgste bits
 * @gmap: pointer to guest mapping meta data structure
 * @gaddr: virtual address in the guest address space
 * @len: size of area
 * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
 * @bits: pgste notification bits to set
 *
 * Returns 0 if successfully protected, -ENOMEM if out of memory and
 * -EFAULT if gaddr is invalid (or mapping for shadows is missing).
 *
 * Called with sg->mm->mmap_lock in read.
 */
static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr,
			      unsigned long len, int prot, unsigned long bits)
{
	unsigned long vmaddr, dist;
	pmd_t *pmdp;
	int rc;

	BUG_ON(gmap_is_shadow(gmap));
	while (len) {
		rc = -EAGAIN;
		pmdp = gmap_pmd_op_walk(gmap, gaddr);
		if (pmdp) {
			if (!pmd_large(*pmdp)) {
				rc = gmap_protect_pte(gmap, gaddr, pmdp, prot,
						      bits);
				if (!rc) {
					len -= PAGE_SIZE;
					gaddr += PAGE_SIZE;
				}
			} else {
				rc = gmap_protect_pmd(gmap, gaddr, pmdp, prot,
						      bits);
				if (!rc) {
					dist = HPAGE_SIZE - (gaddr & ~HPAGE_MASK);
					len = len < dist ? 0 : len - dist;
					gaddr = (gaddr & HPAGE_MASK) + HPAGE_SIZE;
				}
			}
			gmap_pmd_op_end(gmap, pmdp);
		}
		if (rc) {
			if (rc == -EINVAL)
				return rc;

			/* -EAGAIN, fixup of userspace mm and gmap */
			vmaddr = __gmap_translate(gmap, gaddr);
			if (IS_ERR_VALUE(vmaddr))
				return vmaddr;
			rc = gmap_pte_op_fixup(gmap, gaddr, vmaddr, prot);
			if (rc)
				return rc;
		}
	}
	return 0;
}

/**
 * gmap_mprotect_notify - change access rights for a range of ptes and
 *                        call the notifier if any pte changes again
 * @gmap: pointer to guest mapping meta data structure
 * @gaddr: virtual address in the guest address space
 * @len: size of area
 * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
 *
 * Returns 0 if for each page in the given range a gmap mapping exists,
 * the new access rights could be set and the notifier could be armed.
 * If the gmap mapping is missing for one or more pages -EFAULT is
 * returned. If no memory could be allocated -ENOMEM is returned.
 * This function establishes missing page table entries.
 */
int gmap_mprotect_notify(struct gmap *gmap, unsigned long gaddr,
			 unsigned long len, int prot)
{
	int rc;

	if ((gaddr & ~PAGE_MASK) || (len & ~PAGE_MASK) || gmap_is_shadow(gmap))
		return -EINVAL;
	if (!MACHINE_HAS_ESOP && prot == PROT_READ)
		return -EINVAL;
	mmap_read_lock(gmap->mm);
	rc = gmap_protect_range(gmap, gaddr, len, prot, GMAP_NOTIFY_MPROT);
	mmap_read_unlock(gmap->mm);
	return rc;
}
EXPORT_SYMBOL_GPL(gmap_mprotect_notify);

/**
 * gmap_read_table - get an unsigned long value from a guest page table using
 *                   absolute addressing, without marking the page referenced.
 * @gmap: pointer to guest mapping meta data structure
 * @gaddr: virtual address in the guest address space
 * @val: pointer to the unsigned long value to return
 *
 * Returns 0 if the value was read, -ENOMEM if out of memory and -EFAULT
 * if reading using the virtual address failed. -EINVAL if called on a gmap
 * shadow.
 *
 * Called with gmap->mm->mmap_lock in read.
 */
int gmap_read_table(struct gmap *gmap, unsigned long gaddr, unsigned long *val)
{
	unsigned long address, vmaddr;
	spinlock_t *ptl;
	pte_t *ptep, pte;
	int rc;

	if (gmap_is_shadow(gmap))
		return -EINVAL;

	while (1) {
		rc = -EAGAIN;
		ptep = gmap_pte_op_walk(gmap, gaddr, &ptl);
		if (ptep) {
			pte = *ptep;
			if (pte_present(pte) && (pte_val(pte) & _PAGE_READ)) {
				address = pte_val(pte) & PAGE_MASK;
				address += gaddr & ~PAGE_MASK;
				*val = *(unsigned long *)__va(address);
				set_pte(ptep, set_pte_bit(*ptep, __pgprot(_PAGE_YOUNG)));
				/* Do *NOT* clear the _PAGE_INVALID bit! */
				rc = 0;
			}
			gmap_pte_op_end(ptep, ptl);
		}
		if (!rc)
			break;
		vmaddr = __gmap_translate(gmap, gaddr);
		if (IS_ERR_VALUE(vmaddr)) {
			rc = vmaddr;
			break;
		}
		rc = gmap_pte_op_fixup(gmap, gaddr, vmaddr, PROT_READ);
		if (rc)
			break;
	}
	return rc;
}
EXPORT_SYMBOL_GPL(gmap_read_table);

/**
 * gmap_insert_rmap - add a rmap to the host_to_rmap radix tree
 * @sg: pointer to the shadow guest address space structure
 * @vmaddr: vm address associated with the rmap
 * @rmap: pointer to the rmap structure
 *
 * Called with the sg->guest_table_lock
 */
static inline void gmap_insert_rmap(struct gmap *sg, unsigned long vmaddr,
				    struct gmap_rmap *rmap)
{
	struct gmap_rmap *temp;
	void __rcu **slot;

	BUG_ON(!gmap_is_shadow(sg));
	slot = radix_tree_lookup_slot(&sg->host_to_rmap, vmaddr >> PAGE_SHIFT);
	if (slot) {
		rmap->next = radix_tree_deref_slot_protected(slot,
							&sg->guest_table_lock);
		for (temp = rmap->next; temp; temp = temp->next) {
			if (temp->raddr == rmap->raddr) {
				kfree(rmap);
				return;
			}
		}
		radix_tree_replace_slot(&sg->host_to_rmap, slot, rmap);
	} else {
		rmap->next = NULL;
		radix_tree_insert(&sg->host_to_rmap, vmaddr >> PAGE_SHIFT,
				  rmap);
	}
}

/**
 * gmap_protect_rmap - restrict access rights to memory (RO) and create an rmap
 * @sg: pointer to the shadow guest address space structure
 * @raddr: rmap address in the shadow gmap
 * @paddr: address in the parent guest address space
 * @len: length of the memory area to protect
 *
 * Returns 0 if successfully protected and the rmap was created, -ENOMEM
 * if out of memory and -EFAULT if paddr is invalid.
 */
static int gmap_protect_rmap(struct gmap *sg, unsigned long raddr,
			     unsigned long paddr, unsigned long len)
{
	struct gmap *parent;
	struct gmap_rmap *rmap;
	unsigned long vmaddr;
	spinlock_t *ptl;
	pte_t *ptep;
	int rc;

	BUG_ON(!gmap_is_shadow(sg));
	parent = sg->parent;
	while (len) {
		vmaddr = __gmap_translate(parent, paddr);
		if (IS_ERR_VALUE(vmaddr))
			return vmaddr;
		rmap = kzalloc(sizeof(*rmap), GFP_KERNEL_ACCOUNT);
		if (!rmap)
			return -ENOMEM;
		rmap->raddr = raddr;
		rc = radix_tree_preload(GFP_KERNEL_ACCOUNT);
		if (rc) {
			kfree(rmap);
			return rc;
		}
		rc = -EAGAIN;
		ptep = gmap_pte_op_walk(parent, paddr, &ptl);
		if (ptep) {
			spin_lock(&sg->guest_table_lock);
			rc = ptep_force_prot(parent->mm, paddr, ptep, PROT_READ,
					     PGSTE_VSIE_BIT);
			if (!rc)
				gmap_insert_rmap(sg, vmaddr, rmap);
			spin_unlock(&sg->guest_table_lock);
			gmap_pte_op_end(ptep, ptl);
		}
		radix_tree_preload_end();
		if (rc) {
			kfree(rmap);
			rc = gmap_pte_op_fixup(parent, paddr, vmaddr, PROT_READ);
			if (rc)
				return rc;
			continue;
		}
		paddr += PAGE_SIZE;
		len -= PAGE_SIZE;
	}
	return 0;
}

#define _SHADOW_RMAP_MASK	0x7
#define _SHADOW_RMAP_REGION1	0x5
#define _SHADOW_RMAP_REGION2	0x4
#define _SHADOW_RMAP_REGION3	0x3
#define _SHADOW_RMAP_SEGMENT	0x2
#define _SHADOW_RMAP_PGTABLE	0x1

/**
 * gmap_idte_one - invalidate a single region or segment table entry
 * @asce: region or segment table *origin* + table-type bits
 * @vaddr: virtual address to identify the table entry to flush
 *
 * The invalid bit of a single region or segment table entry is set
 * and the associated TLB entries depending on the entry are flushed.
 * The table-type of the @asce identifies the portion of the @vaddr
 * that is used as the invalidation index.
 */
static inline void gmap_idte_one(unsigned long asce, unsigned long vaddr)
{
	asm volatile(
		"	idte	%0,0,%1"
		: : "a" (asce), "a" (vaddr) : "cc", "memory");
}

/**
 * gmap_unshadow_page - remove a page from a shadow page table
 * @sg: pointer to the shadow guest address space structure
 * @raddr: rmap address in the shadow guest address space
 *
 * Called with the sg->guest_table_lock
 */
static void gmap_unshadow_page(struct gmap *sg, unsigned long raddr)
{
	unsigned long *table;

	BUG_ON(!gmap_is_shadow(sg));
	table = gmap_table_walk(sg, raddr, 0); /* get page table pointer */
	if (!table || *table & _PAGE_INVALID)
		return;
	gmap_call_notifier(sg, raddr, raddr + _PAGE_SIZE - 1);
	ptep_unshadow_pte(sg->mm, raddr, (pte_t *) table);
}

/**
 * __gmap_unshadow_pgt - remove all entries from a shadow page table
 * @sg: pointer to the shadow guest address space structure
 * @raddr: rmap address in the shadow guest address space
 * @pgt: pointer to the start of a shadow page table
 *
 * Called with the sg->guest_table_lock
 */
static void __gmap_unshadow_pgt(struct gmap *sg, unsigned long raddr,
				unsigned long *pgt)
{
	int i;

	BUG_ON(!gmap_is_shadow(sg));
	for (i = 0; i < _PAGE_ENTRIES; i++, raddr += _PAGE_SIZE)
		pgt[i] = _PAGE_INVALID;
}

/**
 * gmap_unshadow_pgt - remove a shadow page table from a segment entry
 * @sg: pointer to the shadow guest address space structure
 * @raddr: address in the shadow guest address space
 *
 * Called with the sg->guest_table_lock
 */
static void gmap_unshadow_pgt(struct gmap *sg, unsigned long raddr)
{
	unsigned long *ste;
	phys_addr_t sto, pgt;
	struct page *page;

	BUG_ON(!gmap_is_shadow(sg));
	ste = gmap_table_walk(sg, raddr, 1); /* get segment pointer */
	if (!ste || !(*ste & _SEGMENT_ENTRY_ORIGIN))
		return;
	gmap_call_notifier(sg, raddr, raddr + _SEGMENT_SIZE - 1);
	sto = __pa(ste - ((raddr & _SEGMENT_INDEX) >> _SEGMENT_SHIFT));
	gmap_idte_one(sto | _ASCE_TYPE_SEGMENT, raddr);
	pgt = *ste & _SEGMENT_ENTRY_ORIGIN;
	*ste = _SEGMENT_ENTRY_EMPTY;
	__gmap_unshadow_pgt(sg, raddr, __va(pgt));
	/* Free page table */
	page = phys_to_page(pgt);
	list_del(&page->lru);
	page_table_free_pgste(page);
}

/**
 * __gmap_unshadow_sgt - remove all entries from a shadow segment table
 * @sg: pointer to the shadow guest address space structure
 * @raddr: rmap address in the shadow guest address space
 * @sgt: pointer to the start of a shadow segment table
 *
 * Called with the sg->guest_table_lock
 */
static void __gmap_unshadow_sgt(struct gmap *sg, unsigned long raddr,
				unsigned long *sgt)
{
	struct page *page;
	phys_addr_t pgt;
	int i;

	BUG_ON(!gmap_is_shadow(sg));
	for (i = 0; i < _CRST_ENTRIES; i++, raddr += _SEGMENT_SIZE) {
		if (!(sgt[i] & _SEGMENT_ENTRY_ORIGIN))
			continue;
		pgt = sgt[i] & _REGION_ENTRY_ORIGIN;
		sgt[i] = _SEGMENT_ENTRY_EMPTY;
		__gmap_unshadow_pgt(sg, raddr, __va(pgt));
		/* Free page table */
		page = phys_to_page(pgt);
		list_del(&page->lru);
		page_table_free_pgste(page);
	}
}

/**
 * gmap_unshadow_sgt - remove a shadow segment table from a region-3 entry
 * @sg: pointer to the shadow guest address space structure
 * @raddr: rmap address in the shadow guest address space
 *
 * Called with the shadow->guest_table_lock
 */
static void gmap_unshadow_sgt(struct gmap *sg, unsigned long raddr)
{
	unsigned long r3o, *r3e;
	phys_addr_t sgt;
	struct page *page;

	BUG_ON(!gmap_is_shadow(sg));
	r3e = gmap_table_walk(sg, raddr, 2); /* get region-3 pointer */
	if (!r3e || !(*r3e & _REGION_ENTRY_ORIGIN))
		return;
	gmap_call_notifier(sg, raddr, raddr + _REGION3_SIZE - 1);
	r3o = (unsigned long) (r3e - ((raddr & _REGION3_INDEX) >> _REGION3_SHIFT));
	gmap_idte_one(__pa(r3o) | _ASCE_TYPE_REGION3, raddr);
	sgt = *r3e & _REGION_ENTRY_ORIGIN;
	*r3e = _REGION3_ENTRY_EMPTY;
	__gmap_unshadow_sgt(sg, raddr, __va(sgt));
	/* Free segment table */
	page = phys_to_page(sgt);
	list_del(&page->lru);
	__free_pages(page, CRST_ALLOC_ORDER);
}

/**
 * __gmap_unshadow_r3t - remove all entries from a shadow region-3 table
 * @sg: pointer to the shadow guest address space structure
 * @raddr: address in the shadow guest address space
 * @r3t: pointer to the start of a shadow region-3 table
 *
 * Called with the sg->guest_table_lock
 */
static void __gmap_unshadow_r3t(struct gmap *sg, unsigned long raddr,
				unsigned long *r3t)
{
	struct page *page;
	phys_addr_t sgt;
	int i;

	BUG_ON(!gmap_is_shadow(sg));
	for (i = 0; i < _CRST_ENTRIES; i++, raddr += _REGION3_SIZE) {
		if (!(r3t[i] & _REGION_ENTRY_ORIGIN))
			continue;
		sgt = r3t[i] & _REGION_ENTRY_ORIGIN;
		r3t[i] = _REGION3_ENTRY_EMPTY;
		__gmap_unshadow_sgt(sg, raddr, __va(sgt));
		/* Free segment table */
		page = phys_to_page(sgt);
		list_del(&page->lru);
		__free_pages(page, CRST_ALLOC_ORDER);
	}
}

/**
 * gmap_unshadow_r3t - remove a shadow region-3 table from a region-2 entry
 * @sg: pointer to the shadow guest address space structure
 * @raddr: rmap address in the shadow guest address space
 *
 * Called with the sg->guest_table_lock
 */
static void gmap_unshadow_r3t(struct gmap *sg, unsigned long raddr)
{
	unsigned long r2o, *r2e;
	phys_addr_t r3t;
	struct page *page;

	BUG_ON(!gmap_is_shadow(sg));
	r2e = gmap_table_walk(sg, raddr, 3); /* get region-2 pointer */
	if (!r2e || !(*r2e & _REGION_ENTRY_ORIGIN))
		return;
	gmap_call_notifier(sg, raddr, raddr + _REGION2_SIZE - 1);
	r2o = (unsigned long) (r2e - ((raddr & _REGION2_INDEX) >> _REGION2_SHIFT));
	gmap_idte_one(__pa(r2o) | _ASCE_TYPE_REGION2, raddr);
	r3t = *r2e & _REGION_ENTRY_ORIGIN;
	*r2e = _REGION2_ENTRY_EMPTY;
	__gmap_unshadow_r3t(sg, raddr, __va(r3t));
	/* Free region 3 table */
	page = phys_to_page(r3t);
	list_del(&page->lru);
	__free_pages(page, CRST_ALLOC_ORDER);
}

/**
 * __gmap_unshadow_r2t - remove all entries from a shadow region-2 table
 * @sg: pointer to the shadow guest address space structure
 * @raddr: rmap address in the shadow guest address space
 * @r2t: pointer to the start of a shadow region-2 table
 *
 * Called with the sg->guest_table_lock
 */
static void __gmap_unshadow_r2t(struct gmap *sg, unsigned long raddr,
				unsigned long *r2t)
{
	phys_addr_t r3t;
	struct page *page;
	int i;

	BUG_ON(!gmap_is_shadow(sg));
	for (i = 0; i < _CRST_ENTRIES; i++, raddr += _REGION2_SIZE) {
		if (!(r2t[i] & _REGION_ENTRY_ORIGIN))
			continue;
		r3t = r2t[i] & _REGION_ENTRY_ORIGIN;
		r2t[i] = _REGION2_ENTRY_EMPTY;
		__gmap_unshadow_r3t(sg, raddr, __va(r3t));
		/* Free region 3 table */
		page = phys_to_page(r3t);
		list_del(&page->lru);
		__free_pages(page, CRST_ALLOC_ORDER);
	}
}

/**
 * gmap_unshadow_r2t - remove a shadow region-2 table from a region-1 entry
 * @sg: pointer to the shadow guest address space structure
 * @raddr: rmap address in the shadow guest address space
 *
 * Called with the sg->guest_table_lock
 */
static void gmap_unshadow_r2t(struct gmap *sg, unsigned long raddr)
{
	unsigned long r1o, *r1e;
	struct page *page;
	phys_addr_t r2t;

	BUG_ON(!gmap_is_shadow(sg));
	r1e = gmap_table_walk(sg, raddr, 4); /* get region-1 pointer */
	if (!r1e || !(*r1e & _REGION_ENTRY_ORIGIN))
		return;
	gmap_call_notifier(sg, raddr, raddr + _REGION1_SIZE - 1);
	r1o = (unsigned long) (r1e - ((raddr & _REGION1_INDEX) >> _REGION1_SHIFT));
	gmap_idte_one(__pa(r1o) | _ASCE_TYPE_REGION1, raddr);
	r2t = *r1e & _REGION_ENTRY_ORIGIN;
	*r1e = _REGION1_ENTRY_EMPTY;
	__gmap_unshadow_r2t(sg, raddr, __va(r2t));
	/* Free region 2 table */
	page = phys_to_page(r2t);
	list_del(&page->lru);
	__free_pages(page, CRST_ALLOC_ORDER);
}

/**
 * __gmap_unshadow_r1t - remove all entries from a shadow region-1 table
 * @sg: pointer to the shadow guest address space structure
 * @raddr: rmap address in the shadow guest address space
 * @r1t: pointer to the start of a shadow region-1 table
 *
 * Called with the shadow->guest_table_lock
 */
static void __gmap_unshadow_r1t(struct gmap *sg, unsigned long raddr,
				unsigned long *r1t)
{
	unsigned long asce;
	struct page *page;
	phys_addr_t r2t;
	int i;

	BUG_ON(!gmap_is_shadow(sg));
	asce = __pa(r1t) | _ASCE_TYPE_REGION1;
	for (i = 0; i < _CRST_ENTRIES; i++, raddr += _REGION1_SIZE) {
		if (!(r1t[i] & _REGION_ENTRY_ORIGIN))
			continue;
		r2t = r1t[i] & _REGION_ENTRY_ORIGIN;
		__gmap_unshadow_r2t(sg, raddr, __va(r2t));
		/* Clear entry and flush translation r1t -> r2t */
		gmap_idte_one(asce, raddr);
		r1t[i] = _REGION1_ENTRY_EMPTY;
		/* Free region 2 table */
		page = phys_to_page(r2t);
		list_del(&page->lru);
		__free_pages(page, CRST_ALLOC_ORDER);
	}
}

/**
 * gmap_unshadow - remove a shadow page table completely
 * @sg: pointer to the shadow guest address space structure
 *
 * Called with sg->guest_table_lock
 */
static void gmap_unshadow(struct gmap *sg)
{
	unsigned long *table;

	BUG_ON(!gmap_is_shadow(sg));
	if (sg->removed)
		return;
	sg->removed = 1;
	gmap_call_notifier(sg, 0, -1UL);
	gmap_flush_tlb(sg);
	table = __va(sg->asce & _ASCE_ORIGIN);
	switch (sg->asce & _ASCE_TYPE_MASK) {
	case _ASCE_TYPE_REGION1:
		__gmap_unshadow_r1t(sg, 0, table);
		break;
	case _ASCE_TYPE_REGION2:
		__gmap_unshadow_r2t(sg, 0, table);
		break;
	case _ASCE_TYPE_REGION3:
		__gmap_unshadow_r3t(sg, 0, table);
		break;
	case _ASCE_TYPE_SEGMENT:
		__gmap_unshadow_sgt(sg, 0, table);
		break;
	}
}

/**
 * gmap_find_shadow - find a specific asce in the list of shadow tables
 * @parent: pointer to the parent gmap
 * @asce: ASCE for which the shadow table is created
 * @edat_level: edat level to be used for the shadow translation
 *
 * Returns the pointer to a gmap if a shadow table with the given asce is
 * already available, ERR_PTR(-EAGAIN) if another one is just being created,
 * otherwise NULL
 */
static struct gmap *gmap_find_shadow(struct gmap *parent, unsigned long asce,
				     int edat_level)
{
	struct gmap *sg;

	list_for_each_entry(sg, &parent->children, list) {
		if (sg->orig_asce != asce || sg->edat_level != edat_level ||
		    sg->removed)
			continue;
		if (!sg->initialized)
			return ERR_PTR(-EAGAIN);
		refcount_inc(&sg->ref_count);
		return sg;
	}
	return NULL;
}

/**
 * gmap_shadow_valid - check if a shadow guest address space matches the
 *                     given properties and is still valid
 * @sg: pointer to the shadow guest address space structure
 * @asce: ASCE for which the shadow table is requested
 * @edat_level: edat level to be used for the shadow translation
 *
 * Returns 1 if the gmap shadow is still valid and matches the given
 * properties, the caller can continue using it. Returns 0 otherwise, the
 * caller has to request a new shadow gmap in this case.
 *
 */
int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level)
{
	if (sg->removed)
		return 0;
	return sg->orig_asce == asce && sg->edat_level == edat_level;
}
EXPORT_SYMBOL_GPL(gmap_shadow_valid);

/**
 * gmap_shadow - create/find a shadow guest address space
 * @parent: pointer to the parent gmap
 * @asce: ASCE for which the shadow table is created
 * @edat_level: edat level to be used for the shadow translation
 *
 * The pages of the top level page table referred by the asce parameter
 * will be set to read-only and marked in the PGSTEs of the kvm process.
 * The shadow table will be removed automatically on any change to the
 * PTE mapping for the source table.
 *
 * Returns a guest address space structure, ERR_PTR(-ENOMEM) if out of memory,
 * ERR_PTR(-EAGAIN) if the caller has to retry and ERR_PTR(-EFAULT) if the
 * parent gmap table could not be protected.
 */
struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce,
			 int edat_level)
{
	struct gmap *sg, *new;
	unsigned long limit;
	int rc;

	BUG_ON(parent->mm->context.allow_gmap_hpage_1m);
	BUG_ON(gmap_is_shadow(parent));
	spin_lock(&parent->shadow_lock);
	sg = gmap_find_shadow(parent, asce, edat_level);
	spin_unlock(&parent->shadow_lock);
	if (sg)
		return sg;
	/* Create a new shadow gmap */
	limit = -1UL >> (33 - (((asce & _ASCE_TYPE_MASK) >> 2) * 11));
	if (asce & _ASCE_REAL_SPACE)
		limit = -1UL;
	new = gmap_alloc(limit);
	if (!new)
		return ERR_PTR(-ENOMEM);
	new->mm = parent->mm;
	new->parent = gmap_get(parent);
	new->orig_asce = asce;
	new->edat_level = edat_level;
	new->initialized = false;
	spin_lock(&parent->shadow_lock);
	/* Recheck if another CPU created the same shadow */
	sg = gmap_find_shadow(parent, asce, edat_level);
	if (sg) {
		spin_unlock(&parent->shadow_lock);
		gmap_free(new);
		return sg;
	}
	if (asce & _ASCE_REAL_SPACE) {
		/* only allow one real-space gmap shadow */
		list_for_each_entry(sg, &parent->children, list) {
			if (sg->orig_asce & _ASCE_REAL_SPACE) {
				spin_lock(&sg->guest_table_lock);
				gmap_unshadow(sg);
				spin_unlock(&sg->guest_table_lock);
				list_del(&sg->list);
				gmap_put(sg);
				break;
			}
		}
	}
	refcount_set(&new->ref_count, 2);
	list_add(&new->list, &parent->children);
	if (asce & _ASCE_REAL_SPACE) {
		/* nothing to protect, return right away */
		new->initialized = true;
		spin_unlock(&parent->shadow_lock);
		return new;
	}
	spin_unlock(&parent->shadow_lock);
	/* protect after insertion, so it will get properly invalidated */
	mmap_read_lock(parent->mm);
	rc = gmap_protect_range(parent, asce & _ASCE_ORIGIN,
				((asce & _ASCE_TABLE_LENGTH) + 1) * PAGE_SIZE,
				PROT_READ, GMAP_NOTIFY_SHADOW);
	mmap_read_unlock(parent->mm);
	spin_lock(&parent->shadow_lock);
	new->initialized = true;
	if (rc) {
		list_del(&new->list);
		gmap_free(new);
		new = ERR_PTR(rc);
	}
	spin_unlock(&parent->shadow_lock);
	return new;
}
EXPORT_SYMBOL_GPL(gmap_shadow);

/**
 * gmap_shadow_r2t - create an empty shadow region 2 table
 * @sg: pointer to the shadow guest address space structure
 * @saddr: faulting address in the shadow gmap
 * @r2t: parent gmap address of the region 2 table to get shadowed
 * @fake: r2t references contiguous guest memory block, not a r2t
 *
 * The r2t parameter specifies the address of the source table. The
 * four pages of the source table are made read-only in the parent gmap
 * address space. A write to the source table area @r2t will automatically
 * remove the shadow r2 table and all of its descendants.
 *
 * Returns 0 if successfully shadowed or already shadowed, -EAGAIN if the
 * shadow table structure is incomplete, -ENOMEM if out of memory and
 * -EFAULT if an address in the parent gmap could not be resolved.
 *
 * Called with sg->mm->mmap_lock in read.
 */
int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t,
		    int fake)
{
	unsigned long raddr, origin, offset, len;
	unsigned long *table;
	phys_addr_t s_r2t;
	struct page *page;
	int rc;

	BUG_ON(!gmap_is_shadow(sg));
	/* Allocate a shadow region second table */
	page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER);
	if (!page)
		return -ENOMEM;
	page->index = r2t & _REGION_ENTRY_ORIGIN;
	if (fake)
		page->index |= GMAP_SHADOW_FAKE_TABLE;
	s_r2t = page_to_phys(page);
	/* Install shadow region second table */
	spin_lock(&sg->guest_table_lock);
	table = gmap_table_walk(sg, saddr, 4); /* get region-1 pointer */
	if (!table) {
		rc = -EAGAIN;		/* Race with unshadow */
		goto out_free;
	}
	if (!(*table & _REGION_ENTRY_INVALID)) {
		rc = 0;			/* Already established */
		goto out_free;
	} else if (*table & _REGION_ENTRY_ORIGIN) {
		rc = -EAGAIN;		/* Race with shadow */
		goto out_free;
	}
	crst_table_init(__va(s_r2t), _REGION2_ENTRY_EMPTY);
	/* mark as invalid as long as the parent table is not protected */
	*table = s_r2t | _REGION_ENTRY_LENGTH |
		 _REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_INVALID;
	if (sg->edat_level >= 1)
		*table |= (r2t & _REGION_ENTRY_PROTECT);
	list_add(&page->lru, &sg->crst_list);
	if (fake) {
		/* nothing to protect for fake tables */
		*table &= ~_REGION_ENTRY_INVALID;
		spin_unlock(&sg->guest_table_lock);
		return 0;
	}
	spin_unlock(&sg->guest_table_lock);
	/* Make r2t read-only in parent gmap page table */
	raddr = (saddr & _REGION1_MASK) | _SHADOW_RMAP_REGION1;
	origin = r2t & _REGION_ENTRY_ORIGIN;
	offset = ((r2t & _REGION_ENTRY_OFFSET) >> 6) * PAGE_SIZE;
	len = ((r2t & _REGION_ENTRY_LENGTH) + 1) * PAGE_SIZE - offset;
	rc = gmap_protect_rmap(sg, raddr, origin + offset, len);
	spin_lock(&sg->guest_table_lock);
	if (!rc) {
		table = gmap_table_walk(sg, saddr, 4);
		if (!table || (*table & _REGION_ENTRY_ORIGIN) != s_r2t)
			rc = -EAGAIN;		/* Race with unshadow */
		else
			*table &= ~_REGION_ENTRY_INVALID;
	} else {
		gmap_unshadow_r2t(sg, raddr);
	}
	spin_unlock(&sg->guest_table_lock);
	return rc;
out_free:
	spin_unlock(&sg->guest_table_lock);
	__free_pages(page, CRST_ALLOC_ORDER);
	return rc;
}
EXPORT_SYMBOL_GPL(gmap_shadow_r2t);

/**
 * gmap_shadow_r3t - create a shadow region 3 table
 * @sg: pointer to the shadow guest address space structure
 * @saddr: faulting address in the shadow gmap
 * @r3t: parent gmap address of the region 3 table to get shadowed
 * @fake: r3t references contiguous guest memory block, not a r3t
 *
 * Returns 0 if successfully shadowed or already shadowed, -EAGAIN if the
 * shadow table structure is incomplete, -ENOMEM if out of memory and
 * -EFAULT if an address in the parent gmap could not be resolved.
 *
 * Called with sg->mm->mmap_lock in read.
 */
int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t,
		    int fake)
{
	unsigned long raddr, origin, offset, len;
	unsigned long *table;
	phys_addr_t s_r3t;
	struct page *page;
	int rc;

	BUG_ON(!gmap_is_shadow(sg));
	/* Allocate a shadow region second table */
	page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER);
	if (!page)
		return -ENOMEM;
	page->index = r3t & _REGION_ENTRY_ORIGIN;
	if (fake)
		page->index |= GMAP_SHADOW_FAKE_TABLE;
	s_r3t = page_to_phys(page);
	/* Install shadow region second table */
	spin_lock(&sg->guest_table_lock);
	table = gmap_table_walk(sg, saddr, 3); /* get region-2 pointer */
	if (!table) {
		rc = -EAGAIN;		/* Race with unshadow */
		goto out_free;
	}
	if (!(*table & _REGION_ENTRY_INVALID)) {
		rc = 0;			/* Already established */
		goto out_free;
	} else if (*table & _REGION_ENTRY_ORIGIN) {
		rc = -EAGAIN;		/* Race with shadow */
		goto out_free;
	}
	crst_table_init(__va(s_r3t), _REGION3_ENTRY_EMPTY);
	/* mark as invalid as long as the parent table is not protected */
	*table = s_r3t | _REGION_ENTRY_LENGTH |
		 _REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_INVALID;
	if (sg->edat_level >= 1)
		*table |= (r3t & _REGION_ENTRY_PROTECT);
	list_add(&page->lru, &sg->crst_list);
	if (fake) {
		/* nothing to protect for fake tables */
		*table &= ~_REGION_ENTRY_INVALID;
		spin_unlock(&sg->guest_table_lock);
		return 0;
	}
	spin_unlock(&sg->guest_table_lock);
	/* Make r3t read-only in parent gmap page table */
	raddr = (saddr & _REGION2_MASK) | _SHADOW_RMAP_REGION2;
	origin = r3t & _REGION_ENTRY_ORIGIN;
	offset = ((r3t & _REGION_ENTRY_OFFSET) >> 6) * PAGE_SIZE;
	len = ((r3t & _REGION_ENTRY_LENGTH) + 1) * PAGE_SIZE - offset;
	rc = gmap_protect_rmap(sg, raddr, origin + offset, len);
	spin_lock(&sg->guest_table_lock);
	if (!rc) {
		table = gmap_table_walk(sg, saddr, 3);
		if (!table || (*table & _REGION_ENTRY_ORIGIN) != s_r3t)
			rc = -EAGAIN;		/* Race with unshadow */
		else
			*table &= ~_REGION_ENTRY_INVALID;
	} else {
		gmap_unshadow_r3t(sg, raddr);
	}
	spin_unlock(&sg->guest_table_lock);
	return rc;
out_free:
	spin_unlock(&sg->guest_table_lock);
	__free_pages(page, CRST_ALLOC_ORDER);
	return rc;
}
EXPORT_SYMBOL_GPL(gmap_shadow_r3t);

/**
 * gmap_shadow_sgt - create a shadow segment table
 * @sg: pointer to the shadow guest address space structure
 * @saddr: faulting address in the shadow gmap
 * @sgt: parent gmap address of the segment table to get shadowed
 * @fake: sgt references contiguous guest memory block, not a sgt
 *
 * Returns: 0 if successfully shadowed or already shadowed, -EAGAIN if the
 * shadow table structure is incomplete, -ENOMEM if out of memory and
 * -EFAULT if an address in the parent gmap could not be resolved.
 *
 * Called with sg->mm->mmap_lock in read.
 */
int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt,
		    int fake)
{
	unsigned long raddr, origin, offset, len;
	unsigned long *table;
	phys_addr_t s_sgt;
	struct page *page;
	int rc;

	BUG_ON(!gmap_is_shadow(sg) || (sgt & _REGION3_ENTRY_LARGE));
	/* Allocate a shadow segment table */
	page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER);
	if (!page)
		return -ENOMEM;
	page->index = sgt & _REGION_ENTRY_ORIGIN;
	if (fake)
		page->index |= GMAP_SHADOW_FAKE_TABLE;
	s_sgt = page_to_phys(page);
	/* Install shadow region second table */
	spin_lock(&sg->guest_table_lock);
	table = gmap_table_walk(sg, saddr, 2); /* get region-3 pointer */
	if (!table) {
		rc = -EAGAIN;		/* Race with unshadow */
		goto out_free;
	}
	if (!(*table & _REGION_ENTRY_INVALID)) {
		rc = 0;			/* Already established */
		goto out_free;
	} else if (*table & _REGION_ENTRY_ORIGIN) {
		rc = -EAGAIN;		/* Race with shadow */
		goto out_free;
	}
	crst_table_init(__va(s_sgt), _SEGMENT_ENTRY_EMPTY);
	/* mark as invalid as long as the parent table is not protected */
	*table = s_sgt | _REGION_ENTRY_LENGTH |
		 _REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INVALID;
	if (sg->edat_level >= 1)
		*table |= sgt & _REGION_ENTRY_PROTECT;
	list_add(&page->lru, &sg->crst_list);
	if (fake) {
		/* nothing to protect for fake tables */
		*table &= ~_REGION_ENTRY_INVALID;
		spin_unlock(&sg->guest_table_lock);
		return 0;
	}
	spin_unlock(&sg->guest_table_lock);
	/* Make sgt read-only in parent gmap page table */
	raddr = (saddr & _REGION3_MASK) | _SHADOW_RMAP_REGION3;
	origin = sgt & _REGION_ENTRY_ORIGIN;
	offset = ((sgt & _REGION_ENTRY_OFFSET) >> 6) * PAGE_SIZE;
	len = ((sgt & _REGION_ENTRY_LENGTH) + 1) * PAGE_SIZE - offset;
	rc = gmap_protect_rmap(sg, raddr, origin + offset, len);
	spin_lock(&sg->guest_table_lock);
	if (!rc) {
		table = gmap_table_walk(sg, saddr, 2);
		if (!table || (*table & _REGION_ENTRY_ORIGIN) != s_sgt)
			rc = -EAGAIN;		/* Race with unshadow */
		else
			*table &= ~_REGION_ENTRY_INVALID;
	} else {
		gmap_unshadow_sgt(sg, raddr);
	}
	spin_unlock(&sg->guest_table_lock);
	return rc;
out_free:
	spin_unlock(&sg->guest_table_lock);
	__free_pages(page, CRST_ALLOC_ORDER);
	return rc;
}
EXPORT_SYMBOL_GPL(gmap_shadow_sgt);

/**
 * gmap_shadow_pgt_lookup - find a shadow page table
 * @sg: pointer to the shadow guest address space structure
 * @saddr: the address in the shadow aguest address space
 * @pgt: parent gmap address of the page table to get shadowed
 * @dat_protection: if the pgtable is marked as protected by dat
 * @fake: pgt references contiguous guest memory block, not a pgtable
 *
 * Returns 0 if the shadow page table was found and -EAGAIN if the page
 * table was not found.
 *
 * Called with sg->mm->mmap_lock in read.
 */
int gmap_shadow_pgt_lookup(struct gmap *sg, unsigned long saddr,
			   unsigned long *pgt, int *dat_protection,
			   int *fake)
{
	unsigned long *table;
	struct page *page;
	int rc;

	BUG_ON(!gmap_is_shadow(sg));
	spin_lock(&sg->guest_table_lock);
	table = gmap_table_walk(sg, saddr, 1); /* get segment pointer */
	if (table && !(*table & _SEGMENT_ENTRY_INVALID)) {
		/* Shadow page tables are full pages (pte+pgste) */
		page = pfn_to_page(*table >> PAGE_SHIFT);
		*pgt = page->index & ~GMAP_SHADOW_FAKE_TABLE;
		*dat_protection = !!(*table & _SEGMENT_ENTRY_PROTECT);
		*fake = !!(page->index & GMAP_SHADOW_FAKE_TABLE);
		rc = 0;
	} else  {
		rc = -EAGAIN;
	}
	spin_unlock(&sg->guest_table_lock);
	return rc;

}
EXPORT_SYMBOL_GPL(gmap_shadow_pgt_lookup);

/**
 * gmap_shadow_pgt - instantiate a shadow page table
 * @sg: pointer to the shadow guest address space structure
 * @saddr: faulting address in the shadow gmap
 * @pgt: parent gmap address of the page table to get shadowed
 * @fake: pgt references contiguous guest memory block, not a pgtable
 *
 * Returns 0 if successfully shadowed or already shadowed, -EAGAIN if the
 * shadow table structure is incomplete, -ENOMEM if out of memory,
 * -EFAULT if an address in the parent gmap could not be resolved and
 *
 * Called with gmap->mm->mmap_lock in read
 */
int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt,
		    int fake)
{
	unsigned long raddr, origin;
	unsigned long *table;
	struct page *page;
	phys_addr_t s_pgt;
	int rc;

	BUG_ON(!gmap_is_shadow(sg) || (pgt & _SEGMENT_ENTRY_LARGE));
	/* Allocate a shadow page table */
	page = page_table_alloc_pgste(sg->mm);
	if (!page)
		return -ENOMEM;
	page->index = pgt & _SEGMENT_ENTRY_ORIGIN;
	if (fake)
		page->index |= GMAP_SHADOW_FAKE_TABLE;
	s_pgt = page_to_phys(page);
	/* Install shadow page table */
	spin_lock(&sg->guest_table_lock);
	table = gmap_table_walk(sg, saddr, 1); /* get segment pointer */
	if (!table) {
		rc = -EAGAIN;		/* Race with unshadow */
		goto out_free;
	}
	if (!(*table & _SEGMENT_ENTRY_INVALID)) {
		rc = 0;			/* Already established */
		goto out_free;
	} else if (*table & _SEGMENT_ENTRY_ORIGIN) {
		rc = -EAGAIN;		/* Race with shadow */
		goto out_free;
	}
	/* mark as invalid as long as the parent table is not protected */
	*table = (unsigned long) s_pgt | _SEGMENT_ENTRY |
		 (pgt & _SEGMENT_ENTRY_PROTECT) | _SEGMENT_ENTRY_INVALID;
	list_add(&page->lru, &sg->pt_list);
	if (fake) {
		/* nothing to protect for fake tables */
		*table &= ~_SEGMENT_ENTRY_INVALID;
		spin_unlock(&sg->guest_table_lock);
		return 0;
	}
	spin_unlock(&sg->guest_table_lock);
	/* Make pgt read-only in parent gmap page table (not the pgste) */
	raddr = (saddr & _SEGMENT_MASK) | _SHADOW_RMAP_SEGMENT;
	origin = pgt & _SEGMENT_ENTRY_ORIGIN & PAGE_MASK;
	rc = gmap_protect_rmap(sg, raddr, origin, PAGE_SIZE);
	spin_lock(&sg->guest_table_lock);
	if (!rc) {
		table = gmap_table_walk(sg, saddr, 1);
		if (!table || (*table & _SEGMENT_ENTRY_ORIGIN) != s_pgt)
			rc = -EAGAIN;		/* Race with unshadow */
		else
			*table &= ~_SEGMENT_ENTRY_INVALID;
	} else {
		gmap_unshadow_pgt(sg, raddr);
	}
	spin_unlock(&sg->guest_table_lock);
	return rc;
out_free:
	spin_unlock(&sg->guest_table_lock);
	page_table_free_pgste(page);
	return rc;

}
EXPORT_SYMBOL_GPL(gmap_shadow_pgt);

/**
 * gmap_shadow_page - create a shadow page mapping
 * @sg: pointer to the shadow guest address space structure
 * @saddr: faulting address in the shadow gmap
 * @pte: pte in parent gmap address space to get shadowed
 *
 * Returns 0 if successfully shadowed or already shadowed, -EAGAIN if the
 * shadow table structure is incomplete, -ENOMEM if out of memory and
 * -EFAULT if an address in the parent gmap could not be resolved.
 *
 * Called with sg->mm->mmap_lock in read.
 */
int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte)
{
	struct gmap *parent;
	struct gmap_rmap *rmap;
	unsigned long vmaddr, paddr;
	spinlock_t *ptl;
	pte_t *sptep, *tptep;
	int prot;
	int rc;

	BUG_ON(!gmap_is_shadow(sg));
	parent = sg->parent;
	prot = (pte_val(pte) & _PAGE_PROTECT) ? PROT_READ : PROT_WRITE;

	rmap = kzalloc(sizeof(*rmap), GFP_KERNEL_ACCOUNT);
	if (!rmap)
		return -ENOMEM;
	rmap->raddr = (saddr & PAGE_MASK) | _SHADOW_RMAP_PGTABLE;

	while (1) {
		paddr = pte_val(pte) & PAGE_MASK;
		vmaddr = __gmap_translate(parent, paddr);
		if (IS_ERR_VALUE(vmaddr)) {
			rc = vmaddr;
			break;
		}
		rc = radix_tree_preload(GFP_KERNEL_ACCOUNT);
		if (rc)
			break;
		rc = -EAGAIN;
		sptep = gmap_pte_op_walk(parent, paddr, &ptl);
		if (sptep) {
			spin_lock(&sg->guest_table_lock);
			/* Get page table pointer */
			tptep = (pte_t *) gmap_table_walk(sg, saddr, 0);
			if (!tptep) {
				spin_unlock(&sg->guest_table_lock);
				gmap_pte_op_end(sptep, ptl);
				radix_tree_preload_end();
				break;
			}
			rc = ptep_shadow_pte(sg->mm, saddr, sptep, tptep, pte);
			if (rc > 0) {
				/* Success and a new mapping */
				gmap_insert_rmap(sg, vmaddr, rmap);
				rmap = NULL;
				rc = 0;
			}
			gmap_pte_op_end(sptep, ptl);
			spin_unlock(&sg->guest_table_lock);
		}
		radix_tree_preload_end();
		if (!rc)
			break;
		rc = gmap_pte_op_fixup(parent, paddr, vmaddr, prot);
		if (rc)
			break;
	}
	kfree(rmap);
	return rc;
}
EXPORT_SYMBOL_GPL(gmap_shadow_page);

/*
 * gmap_shadow_notify - handle notifications for shadow gmap
 *
 * Called with sg->parent->shadow_lock.
 */
static void gmap_shadow_notify(struct gmap *sg, unsigned long vmaddr,
			       unsigned long gaddr)
{
	struct gmap_rmap *rmap, *rnext, *head;
	unsigned long start, end, bits, raddr;

	BUG_ON(!gmap_is_shadow(sg));

	spin_lock(&sg->guest_table_lock);
	if (sg->removed) {
		spin_unlock(&sg->guest_table_lock);
		return;
	}
	/* Check for top level table */
	start = sg->orig_asce & _ASCE_ORIGIN;
	end = start + ((sg->orig_asce & _ASCE_TABLE_LENGTH) + 1) * PAGE_SIZE;
	if (!(sg->orig_asce & _ASCE_REAL_SPACE) && gaddr >= start &&
	    gaddr < end) {
		/* The complete shadow table has to go */
		gmap_unshadow(sg);
		spin_unlock(&sg->guest_table_lock);
		list_del(&sg->list);
		gmap_put(sg);
		return;
	}
	/* Remove the page table tree from on specific entry */
	head = radix_tree_delete(&sg->host_to_rmap, vmaddr >> PAGE_SHIFT);
	gmap_for_each_rmap_safe(rmap, rnext, head) {
		bits = rmap->raddr & _SHADOW_RMAP_MASK;
		raddr = rmap->raddr ^ bits;
		switch (bits) {
		case _SHADOW_RMAP_REGION1:
			gmap_unshadow_r2t(sg, raddr);
			break;
		case _SHADOW_RMAP_REGION2:
			gmap_unshadow_r3t(sg, raddr);
			break;
		case _SHADOW_RMAP_REGION3:
			gmap_unshadow_sgt(sg, raddr);
			break;
		case _SHADOW_RMAP_SEGMENT:
			gmap_unshadow_pgt(sg, raddr);
			break;
		case _SHADOW_RMAP_PGTABLE:
			gmap_unshadow_page(sg, raddr);
			break;
		}
		kfree(rmap);
	}
	spin_unlock(&sg->guest_table_lock);
}

/**
 * ptep_notify - call all invalidation callbacks for a specific pte.
 * @mm: pointer to the process mm_struct
 * @vmaddr: virtual address in the process address space
 * @pte: pointer to the page table entry
 * @bits: bits from the pgste that caused the notify call
 *
 * This function is assumed to be called with the page table lock held
 * for the pte to notify.
 */
void ptep_notify(struct mm_struct *mm, unsigned long vmaddr,
		 pte_t *pte, unsigned long bits)
{
	unsigned long offset, gaddr = 0;
	unsigned long *table;
	struct gmap *gmap, *sg, *next;

	offset = ((unsigned long) pte) & (255 * sizeof(pte_t));
	offset = offset * (PAGE_SIZE / sizeof(pte_t));
	rcu_read_lock();
	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
		spin_lock(&gmap->guest_table_lock);
		table = radix_tree_lookup(&gmap->host_to_guest,
					  vmaddr >> PMD_SHIFT);
		if (table)
			gaddr = __gmap_segment_gaddr(table) + offset;
		spin_unlock(&gmap->guest_table_lock);
		if (!table)
			continue;

		if (!list_empty(&gmap->children) && (bits & PGSTE_VSIE_BIT)) {
			spin_lock(&gmap->shadow_lock);
			list_for_each_entry_safe(sg, next,
						 &gmap->children, list)
				gmap_shadow_notify(sg, vmaddr, gaddr);
			spin_unlock(&gmap->shadow_lock);
		}
		if (bits & PGSTE_IN_BIT)
			gmap_call_notifier(gmap, gaddr, gaddr + PAGE_SIZE - 1);
	}
	rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(ptep_notify);

static void pmdp_notify_gmap(struct gmap *gmap, pmd_t *pmdp,
			     unsigned long gaddr)
{
	set_pmd(pmdp, clear_pmd_bit(*pmdp, __pgprot(_SEGMENT_ENTRY_GMAP_IN)));
	gmap_call_notifier(gmap, gaddr, gaddr + HPAGE_SIZE - 1);
}

/**
 * gmap_pmdp_xchg - exchange a gmap pmd with another
 * @gmap: pointer to the guest address space structure
 * @pmdp: pointer to the pmd entry
 * @new: replacement entry
 * @gaddr: the affected guest address
 *
 * This function is assumed to be called with the guest_table_lock
 * held.
 */
static void gmap_pmdp_xchg(struct gmap *gmap, pmd_t *pmdp, pmd_t new,
			   unsigned long gaddr)
{
	gaddr &= HPAGE_MASK;
	pmdp_notify_gmap(gmap, pmdp, gaddr);
	new = clear_pmd_bit(new, __pgprot(_SEGMENT_ENTRY_GMAP_IN));
	if (MACHINE_HAS_TLB_GUEST)
		__pmdp_idte(gaddr, (pmd_t *)pmdp, IDTE_GUEST_ASCE, gmap->asce,
			    IDTE_GLOBAL);
	else if (MACHINE_HAS_IDTE)
		__pmdp_idte(gaddr, (pmd_t *)pmdp, 0, 0, IDTE_GLOBAL);
	else
		__pmdp_csp(pmdp);
	set_pmd(pmdp, new);
}

static void gmap_pmdp_clear(struct mm_struct *mm, unsigned long vmaddr,
			    int purge)
{
	pmd_t *pmdp;
	struct gmap *gmap;
	unsigned long gaddr;

	rcu_read_lock();
	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
		spin_lock(&gmap->guest_table_lock);
		pmdp = (pmd_t *)radix_tree_delete(&gmap->host_to_guest,
						  vmaddr >> PMD_SHIFT);
		if (pmdp) {
			gaddr = __gmap_segment_gaddr((unsigned long *)pmdp);
			pmdp_notify_gmap(gmap, pmdp, gaddr);
			WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
						   _SEGMENT_ENTRY_GMAP_UC));
			if (purge)
				__pmdp_csp(pmdp);
			set_pmd(pmdp, __pmd(_SEGMENT_ENTRY_EMPTY));
		}
		spin_unlock(&gmap->guest_table_lock);
	}
	rcu_read_unlock();
}

/**
 * gmap_pmdp_invalidate - invalidate all affected guest pmd entries without
 *                        flushing
 * @mm: pointer to the process mm_struct
 * @vmaddr: virtual address in the process address space
 */
void gmap_pmdp_invalidate(struct mm_struct *mm, unsigned long vmaddr)
{
	gmap_pmdp_clear(mm, vmaddr, 0);
}
EXPORT_SYMBOL_GPL(gmap_pmdp_invalidate);

/**
 * gmap_pmdp_csp - csp all affected guest pmd entries
 * @mm: pointer to the process mm_struct
 * @vmaddr: virtual address in the process address space
 */
void gmap_pmdp_csp(struct mm_struct *mm, unsigned long vmaddr)
{
	gmap_pmdp_clear(mm, vmaddr, 1);
}
EXPORT_SYMBOL_GPL(gmap_pmdp_csp);

/**
 * gmap_pmdp_idte_local - invalidate and clear a guest pmd entry
 * @mm: pointer to the process mm_struct
 * @vmaddr: virtual address in the process address space
 */
void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr)
{
	unsigned long *entry, gaddr;
	struct gmap *gmap;
	pmd_t *pmdp;

	rcu_read_lock();
	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
		spin_lock(&gmap->guest_table_lock);
		entry = radix_tree_delete(&gmap->host_to_guest,
					  vmaddr >> PMD_SHIFT);
		if (entry) {
			pmdp = (pmd_t *)entry;
			gaddr = __gmap_segment_gaddr(entry);
			pmdp_notify_gmap(gmap, pmdp, gaddr);
			WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
					   _SEGMENT_ENTRY_GMAP_UC));
			if (MACHINE_HAS_TLB_GUEST)
				__pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE,
					    gmap->asce, IDTE_LOCAL);
			else if (MACHINE_HAS_IDTE)
				__pmdp_idte(gaddr, pmdp, 0, 0, IDTE_LOCAL);
			*entry = _SEGMENT_ENTRY_EMPTY;
		}
		spin_unlock(&gmap->guest_table_lock);
	}
	rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(gmap_pmdp_idte_local);

/**
 * gmap_pmdp_idte_global - invalidate and clear a guest pmd entry
 * @mm: pointer to the process mm_struct
 * @vmaddr: virtual address in the process address space
 */
void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr)
{
	unsigned long *entry, gaddr;
	struct gmap *gmap;
	pmd_t *pmdp;

	rcu_read_lock();
	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
		spin_lock(&gmap->guest_table_lock);
		entry = radix_tree_delete(&gmap->host_to_guest,
					  vmaddr >> PMD_SHIFT);
		if (entry) {
			pmdp = (pmd_t *)entry;
			gaddr = __gmap_segment_gaddr(entry);
			pmdp_notify_gmap(gmap, pmdp, gaddr);
			WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
					   _SEGMENT_ENTRY_GMAP_UC));
			if (MACHINE_HAS_TLB_GUEST)
				__pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE,
					    gmap->asce, IDTE_GLOBAL);
			else if (MACHINE_HAS_IDTE)
				__pmdp_idte(gaddr, pmdp, 0, 0, IDTE_GLOBAL);
			else
				__pmdp_csp(pmdp);
			*entry = _SEGMENT_ENTRY_EMPTY;
		}
		spin_unlock(&gmap->guest_table_lock);
	}
	rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(gmap_pmdp_idte_global);

/**
 * gmap_test_and_clear_dirty_pmd - test and reset segment dirty status
 * @gmap: pointer to guest address space
 * @pmdp: pointer to the pmd to be tested
 * @gaddr: virtual address in the guest address space
 *
 * This function is assumed to be called with the guest_table_lock
 * held.
 */
static bool gmap_test_and_clear_dirty_pmd(struct gmap *gmap, pmd_t *pmdp,
					  unsigned long gaddr)
{
	if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
		return false;

	/* Already protected memory, which did not change is clean */
	if (pmd_val(*pmdp) & _SEGMENT_ENTRY_PROTECT &&
	    !(pmd_val(*pmdp) & _SEGMENT_ENTRY_GMAP_UC))
		return false;

	/* Clear UC indication and reset protection */
	set_pmd(pmdp, clear_pmd_bit(*pmdp, __pgprot(_SEGMENT_ENTRY_GMAP_UC)));
	gmap_protect_pmd(gmap, gaddr, pmdp, PROT_READ, 0);
	return true;
}

/**
 * gmap_sync_dirty_log_pmd - set bitmap based on dirty status of segment
 * @gmap: pointer to guest address space
 * @bitmap: dirty bitmap for this pmd
 * @gaddr: virtual address in the guest address space
 * @vmaddr: virtual address in the host address space
 *
 * This function is assumed to be called with the guest_table_lock
 * held.
 */
void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long bitmap[4],
			     unsigned long gaddr, unsigned long vmaddr)
{
	int i;
	pmd_t *pmdp;
	pte_t *ptep;
	spinlock_t *ptl;

	pmdp = gmap_pmd_op_walk(gmap, gaddr);
	if (!pmdp)
		return;

	if (pmd_large(*pmdp)) {
		if (gmap_test_and_clear_dirty_pmd(gmap, pmdp, gaddr))
			bitmap_fill(bitmap, _PAGE_ENTRIES);
	} else {
		for (i = 0; i < _PAGE_ENTRIES; i++, vmaddr += PAGE_SIZE) {
			ptep = pte_alloc_map_lock(gmap->mm, pmdp, vmaddr, &ptl);
			if (!ptep)
				continue;
			if (ptep_test_and_clear_uc(gmap->mm, vmaddr, ptep))
				set_bit(i, bitmap);
			pte_unmap_unlock(ptep, ptl);
		}
	}
	gmap_pmd_op_end(gmap, pmdp);
}
EXPORT_SYMBOL_GPL(gmap_sync_dirty_log_pmd);

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static int thp_split_walk_pmd_entry(pmd_t *pmd, unsigned long addr,
				    unsigned long end, struct mm_walk *walk)
{
	struct vm_area_struct *vma = walk->vma;

	split_huge_pmd(vma, pmd, addr);
	return 0;
}

static const struct mm_walk_ops thp_split_walk_ops = {
	.pmd_entry	= thp_split_walk_pmd_entry,
	.walk_lock	= PGWALK_WRLOCK_VERIFY,
};

static inline void thp_split_mm(struct mm_struct *mm)
{
	struct vm_area_struct *vma;
	VMA_ITERATOR(vmi, mm, 0);

	for_each_vma(vmi, vma) {
		vm_flags_mod(vma, VM_NOHUGEPAGE, VM_HUGEPAGE);
		walk_page_vma(vma, &thp_split_walk_ops, NULL);
	}
	mm->def_flags |= VM_NOHUGEPAGE;
}
#else
static inline void thp_split_mm(struct mm_struct *mm)
{
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

/*
 * Remove all empty zero pages from the mapping for lazy refaulting
 * - This must be called after mm->context.has_pgste is set, to avoid
 *   future creation of zero pages
 * - This must be called after THP was disabled.
 *
 * mm contracts with s390, that even if mm were to remove a page table,
 * racing with the loop below and so causing pte_offset_map_lock() to fail,
 * it will never insert a page table containing empty zero pages once
 * mm_forbids_zeropage(mm) i.e. mm->context.has_pgste is set.
 */
static int __zap_zero_pages(pmd_t *pmd, unsigned long start,
			   unsigned long end, struct mm_walk *walk)
{
	unsigned long addr;

	for (addr = start; addr != end; addr += PAGE_SIZE) {
		pte_t *ptep;
		spinlock_t *ptl;

		ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
		if (!ptep)
			break;
		if (is_zero_pfn(pte_pfn(*ptep)))
			ptep_xchg_direct(walk->mm, addr, ptep, __pte(_PAGE_INVALID));
		pte_unmap_unlock(ptep, ptl);
	}
	return 0;
}

static const struct mm_walk_ops zap_zero_walk_ops = {
	.pmd_entry	= __zap_zero_pages,
	.walk_lock	= PGWALK_WRLOCK,
};

/*
 * switch on pgstes for its userspace process (for kvm)
 */
int s390_enable_sie(void)
{
	struct mm_struct *mm = current->mm;

	/* Do we have pgstes? if yes, we are done */
	if (mm_has_pgste(mm))
		return 0;
	/* Fail if the page tables are 2K */
	if (!mm_alloc_pgste(mm))
		return -EINVAL;
	mmap_write_lock(mm);
	mm->context.has_pgste = 1;
	/* split thp mappings and disable thp for future mappings */
	thp_split_mm(mm);
	walk_page_range(mm, 0, TASK_SIZE, &zap_zero_walk_ops, NULL);
	mmap_write_unlock(mm);
	return 0;
}
EXPORT_SYMBOL_GPL(s390_enable_sie);

int gmap_mark_unmergeable(void)
{
	/*
	 * Make sure to disable KSM (if enabled for the whole process or
	 * individual VMAs). Note that nothing currently hinders user space
	 * from re-enabling it.
	 */
	return ksm_disable(current->mm);
}
EXPORT_SYMBOL_GPL(gmap_mark_unmergeable);

/*
 * Enable storage key handling from now on and initialize the storage
 * keys with the default key.
 */
static int __s390_enable_skey_pte(pte_t *pte, unsigned long addr,
				  unsigned long next, struct mm_walk *walk)
{
	/* Clear storage key */
	ptep_zap_key(walk->mm, addr, pte);
	return 0;
}

/*
 * Give a chance to schedule after setting a key to 256 pages.
 * We only hold the mm lock, which is a rwsem and the kvm srcu.
 * Both can sleep.
 */
static int __s390_enable_skey_pmd(pmd_t *pmd, unsigned long addr,
				  unsigned long next, struct mm_walk *walk)
{
	cond_resched();
	return 0;
}

static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr,
				      unsigned long hmask, unsigned long next,
				      struct mm_walk *walk)
{
	pmd_t *pmd = (pmd_t *)pte;
	unsigned long start, end;
	struct page *page = pmd_page(*pmd);

	/*
	 * The write check makes sure we do not set a key on shared
	 * memory. This is needed as the walker does not differentiate
	 * between actual guest memory and the process executable or
	 * shared libraries.
	 */
	if (pmd_val(*pmd) & _SEGMENT_ENTRY_INVALID ||
	    !(pmd_val(*pmd) & _SEGMENT_ENTRY_WRITE))
		return 0;

	start = pmd_val(*pmd) & HPAGE_MASK;
	end = start + HPAGE_SIZE - 1;
	__storage_key_init_range(start, end);
	set_bit(PG_arch_1, &page->flags);
	cond_resched();
	return 0;
}

static const struct mm_walk_ops enable_skey_walk_ops = {
	.hugetlb_entry		= __s390_enable_skey_hugetlb,
	.pte_entry		= __s390_enable_skey_pte,
	.pmd_entry		= __s390_enable_skey_pmd,
	.walk_lock		= PGWALK_WRLOCK,
};

int s390_enable_skey(void)
{
	struct mm_struct *mm = current->mm;
	int rc = 0;

	mmap_write_lock(mm);
	if (mm_uses_skeys(mm))
		goto out_up;

	mm->context.uses_skeys = 1;
	rc = gmap_mark_unmergeable();
	if (rc) {
		mm->context.uses_skeys = 0;
		goto out_up;
	}
	walk_page_range(mm, 0, TASK_SIZE, &enable_skey_walk_ops, NULL);

out_up:
	mmap_write_unlock(mm);
	return rc;
}
EXPORT_SYMBOL_GPL(s390_enable_skey);

/*
 * Reset CMMA state, make all pages stable again.
 */
static int __s390_reset_cmma(pte_t *pte, unsigned long addr,
			     unsigned long next, struct mm_walk *walk)
{
	ptep_zap_unused(walk->mm, addr, pte, 1);
	return 0;
}

static const struct mm_walk_ops reset_cmma_walk_ops = {
	.pte_entry		= __s390_reset_cmma,
	.walk_lock		= PGWALK_WRLOCK,
};

void s390_reset_cmma(struct mm_struct *mm)
{
	mmap_write_lock(mm);
	walk_page_range(mm, 0, TASK_SIZE, &reset_cmma_walk_ops, NULL);
	mmap_write_unlock(mm);
}
EXPORT_SYMBOL_GPL(s390_reset_cmma);

#define GATHER_GET_PAGES 32

struct reset_walk_state {
	unsigned long next;
	unsigned long count;
	unsigned long pfns[GATHER_GET_PAGES];
};

static int s390_gather_pages(pte_t *ptep, unsigned long addr,
			     unsigned long next, struct mm_walk *walk)
{
	struct reset_walk_state *p = walk->private;
	pte_t pte = READ_ONCE(*ptep);

	if (pte_present(pte)) {
		/* we have a reference from the mapping, take an extra one */
		get_page(phys_to_page(pte_val(pte)));
		p->pfns[p->count] = phys_to_pfn(pte_val(pte));
		p->next = next;
		p->count++;
	}
	return p->count >= GATHER_GET_PAGES;
}

static const struct mm_walk_ops gather_pages_ops = {
	.pte_entry = s390_gather_pages,
	.walk_lock = PGWALK_RDLOCK,
};

/*
 * Call the Destroy secure page UVC on each page in the given array of PFNs.
 * Each page needs to have an extra reference, which will be released here.
 */
void s390_uv_destroy_pfns(unsigned long count, unsigned long *pfns)
{
	unsigned long i;

	for (i = 0; i < count; i++) {
		/* we always have an extra reference */
		uv_destroy_owned_page(pfn_to_phys(pfns[i]));
		/* get rid of the extra reference */
		put_page(pfn_to_page(pfns[i]));
		cond_resched();
	}
}
EXPORT_SYMBOL_GPL(s390_uv_destroy_pfns);

/**
 * __s390_uv_destroy_range - Call the destroy secure page UVC on each page
 * in the given range of the given address space.
 * @mm: the mm to operate on
 * @start: the start of the range
 * @end: the end of the range
 * @interruptible: if not 0, stop when a fatal signal is received
 *
 * Walk the given range of the given address space and call the destroy
 * secure page UVC on each page. Optionally exit early if a fatal signal is
 * pending.
 *
 * Return: 0 on success, -EINTR if the function stopped before completing
 */
int __s390_uv_destroy_range(struct mm_struct *mm, unsigned long start,
			    unsigned long end, bool interruptible)
{
	struct reset_walk_state state = { .next = start };
	int r = 1;

	while (r > 0) {
		state.count = 0;
		mmap_read_lock(mm);
		r = walk_page_range(mm, state.next, end, &gather_pages_ops, &state);
		mmap_read_unlock(mm);
		cond_resched();
		s390_uv_destroy_pfns(state.count, state.pfns);
		if (interruptible && fatal_signal_pending(current))
			return -EINTR;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(__s390_uv_destroy_range);

/**
 * s390_unlist_old_asce - Remove the topmost level of page tables from the
 * list of page tables of the gmap.
 * @gmap: the gmap whose table is to be removed
 *
 * On s390x, KVM keeps a list of all pages containing the page tables of the
 * gmap (the CRST list). This list is used at tear down time to free all
 * pages that are now not needed anymore.
 *
 * This function removes the topmost page of the tree (the one pointed to by
 * the ASCE) from the CRST list.
 *
 * This means that it will not be freed when the VM is torn down, and needs
 * to be handled separately by the caller, unless a leak is actually
 * intended. Notice that this function will only remove the page from the
 * list, the page will still be used as a top level page table (and ASCE).
 */
void s390_unlist_old_asce(struct gmap *gmap)
{
	struct page *old;

	old = virt_to_page(gmap->table);
	spin_lock(&gmap->guest_table_lock);
	list_del(&old->lru);
	/*
	 * Sometimes the topmost page might need to be "removed" multiple
	 * times, for example if the VM is rebooted into secure mode several
	 * times concurrently, or if s390_replace_asce fails after calling
	 * s390_remove_old_asce and is attempted again later. In that case
	 * the old asce has been removed from the list, and therefore it
	 * will not be freed when the VM terminates, but the ASCE is still
	 * in use and still pointed to.
	 * A subsequent call to replace_asce will follow the pointer and try
	 * to remove the same page from the list again.
	 * Therefore it's necessary that the page of the ASCE has valid
	 * pointers, so list_del can work (and do nothing) without
	 * dereferencing stale or invalid pointers.
	 */
	INIT_LIST_HEAD(&old->lru);
	spin_unlock(&gmap->guest_table_lock);
}
EXPORT_SYMBOL_GPL(s390_unlist_old_asce);

/**
 * s390_replace_asce - Try to replace the current ASCE of a gmap with a copy
 * @gmap: the gmap whose ASCE needs to be replaced
 *
 * If the ASCE is a SEGMENT type then this function will return -EINVAL,
 * otherwise the pointers in the host_to_guest radix tree will keep pointing
 * to the wrong pages, causing use-after-free and memory corruption.
 * If the allocation of the new top level page table fails, the ASCE is not
 * replaced.
 * In any case, the old ASCE is always removed from the gmap CRST list.
 * Therefore the caller has to make sure to save a pointer to it
 * beforehand, unless a leak is actually intended.
 */
int s390_replace_asce(struct gmap *gmap)
{
	unsigned long asce;
	struct page *page;
	void *table;

	s390_unlist_old_asce(gmap);

	/* Replacing segment type ASCEs would cause serious issues */
	if ((gmap->asce & _ASCE_TYPE_MASK) == _ASCE_TYPE_SEGMENT)
		return -EINVAL;

	page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER);
	if (!page)
		return -ENOMEM;
	page->index = 0;
	table = page_to_virt(page);
	memcpy(table, gmap->table, 1UL << (CRST_ALLOC_ORDER + PAGE_SHIFT));

	/*
	 * The caller has to deal with the old ASCE, but here we make sure
	 * the new one is properly added to the CRST list, so that
	 * it will be freed when the VM is torn down.
	 */
	spin_lock(&gmap->guest_table_lock);
	list_add(&page->lru, &gmap->crst_list);
	spin_unlock(&gmap->guest_table_lock);

	/* Set new table origin while preserving existing ASCE control bits */
	asce = (gmap->asce & ~_ASCE_ORIGIN) | __pa(table);
	WRITE_ONCE(gmap->asce, asce);
	WRITE_ONCE(gmap->mm->context.gmap_asce, asce);
	WRITE_ONCE(gmap->table, table);

	return 0;
}
EXPORT_SYMBOL_GPL(s390_replace_asce);