summaryrefslogtreecommitdiff
path: root/arch/powerpc/kernel/rtas.c
blob: 8064d9c3de8620d27d9c87f829676ef048aeed40 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *
 * Procedures for interfacing to the RTAS on CHRP machines.
 *
 * Peter Bergner, IBM	March 2001.
 * Copyright (C) 2001 IBM.
 */

#define pr_fmt(fmt)	"rtas: " fmt

#include <linux/bsearch.h>
#include <linux/capability.h>
#include <linux/delay.h>
#include <linux/export.h>
#include <linux/init.h>
#include <linux/kconfig.h>
#include <linux/kernel.h>
#include <linux/lockdep.h>
#include <linux/memblock.h>
#include <linux/mutex.h>
#include <linux/of.h>
#include <linux/of_fdt.h>
#include <linux/reboot.h>
#include <linux/sched.h>
#include <linux/security.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/stdarg.h>
#include <linux/syscalls.h>
#include <linux/types.h>
#include <linux/uaccess.h>
#include <linux/xarray.h>

#include <asm/delay.h>
#include <asm/firmware.h>
#include <asm/interrupt.h>
#include <asm/machdep.h>
#include <asm/mmu.h>
#include <asm/page.h>
#include <asm/rtas-work-area.h>
#include <asm/rtas.h>
#include <asm/time.h>
#include <asm/trace.h>
#include <asm/udbg.h>

struct rtas_filter {
	/* Indexes into the args buffer, -1 if not used */
	const int buf_idx1;
	const int size_idx1;
	const int buf_idx2;
	const int size_idx2;
	/*
	 * Assumed buffer size per the spec if the function does not
	 * have a size parameter, e.g. ibm,errinjct. 0 if unused.
	 */
	const int fixed_size;
};

/**
 * struct rtas_function - Descriptor for RTAS functions.
 *
 * @token: Value of @name if it exists under the /rtas node.
 * @name: Function name.
 * @filter: If non-NULL, invoking this function via the rtas syscall is
 *          generally allowed, and @filter describes constraints on the
 *          arguments. See also @banned_for_syscall_on_le.
 * @banned_for_syscall_on_le: Set when call via sys_rtas is generally allowed
 *                            but specifically restricted on ppc64le. Such
 *                            functions are believed to have no users on
 *                            ppc64le, and we want to keep it that way. It does
 *                            not make sense for this to be set when @filter
 *                            is NULL.
 * @lock: Pointer to an optional dedicated per-function mutex. This
 *        should be set for functions that require multiple calls in
 *        sequence to complete a single operation, and such sequences
 *        will disrupt each other if allowed to interleave. Users of
 *        this function are required to hold the associated lock for
 *        the duration of the call sequence. Add an explanatory
 *        comment to the function table entry if setting this member.
 */
struct rtas_function {
	s32 token;
	const bool banned_for_syscall_on_le:1;
	const char * const name;
	const struct rtas_filter *filter;
	struct mutex *lock;
};

/*
 * Per-function locks for sequence-based RTAS functions.
 */
static DEFINE_MUTEX(rtas_ibm_activate_firmware_lock);
static DEFINE_MUTEX(rtas_ibm_get_dynamic_sensor_state_lock);
static DEFINE_MUTEX(rtas_ibm_get_indices_lock);
static DEFINE_MUTEX(rtas_ibm_lpar_perftools_lock);
static DEFINE_MUTEX(rtas_ibm_physical_attestation_lock);
static DEFINE_MUTEX(rtas_ibm_set_dynamic_indicator_lock);
DEFINE_MUTEX(rtas_ibm_get_vpd_lock);

static struct rtas_function rtas_function_table[] __ro_after_init = {
	[RTAS_FNIDX__CHECK_EXCEPTION] = {
		.name = "check-exception",
	},
	[RTAS_FNIDX__DISPLAY_CHARACTER] = {
		.name = "display-character",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = -1, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
	},
	[RTAS_FNIDX__EVENT_SCAN] = {
		.name = "event-scan",
	},
	[RTAS_FNIDX__FREEZE_TIME_BASE] = {
		.name = "freeze-time-base",
	},
	[RTAS_FNIDX__GET_POWER_LEVEL] = {
		.name = "get-power-level",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = -1, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
	},
	[RTAS_FNIDX__GET_SENSOR_STATE] = {
		.name = "get-sensor-state",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = -1, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
	},
	[RTAS_FNIDX__GET_TERM_CHAR] = {
		.name = "get-term-char",
	},
	[RTAS_FNIDX__GET_TIME_OF_DAY] = {
		.name = "get-time-of-day",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = -1, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
	},
	[RTAS_FNIDX__IBM_ACTIVATE_FIRMWARE] = {
		.name = "ibm,activate-firmware",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = -1, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
		/*
		 * PAPR+ as of v2.13 doesn't explicitly impose any
		 * restriction, but this typically requires multiple
		 * calls before success, and there's no reason to
		 * allow sequences to interleave.
		 */
		.lock = &rtas_ibm_activate_firmware_lock,
	},
	[RTAS_FNIDX__IBM_CBE_START_PTCAL] = {
		.name = "ibm,cbe-start-ptcal",
	},
	[RTAS_FNIDX__IBM_CBE_STOP_PTCAL] = {
		.name = "ibm,cbe-stop-ptcal",
	},
	[RTAS_FNIDX__IBM_CHANGE_MSI] = {
		.name = "ibm,change-msi",
	},
	[RTAS_FNIDX__IBM_CLOSE_ERRINJCT] = {
		.name = "ibm,close-errinjct",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = -1, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
	},
	[RTAS_FNIDX__IBM_CONFIGURE_BRIDGE] = {
		.name = "ibm,configure-bridge",
	},
	[RTAS_FNIDX__IBM_CONFIGURE_CONNECTOR] = {
		.name = "ibm,configure-connector",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = 0, .size_idx1 = -1,
			.buf_idx2 = 1, .size_idx2 = -1,
			.fixed_size = 4096,
		},
	},
	[RTAS_FNIDX__IBM_CONFIGURE_KERNEL_DUMP] = {
		.name = "ibm,configure-kernel-dump",
	},
	[RTAS_FNIDX__IBM_CONFIGURE_PE] = {
		.name = "ibm,configure-pe",
	},
	[RTAS_FNIDX__IBM_CREATE_PE_DMA_WINDOW] = {
		.name = "ibm,create-pe-dma-window",
	},
	[RTAS_FNIDX__IBM_DISPLAY_MESSAGE] = {
		.name = "ibm,display-message",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = 0, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
	},
	[RTAS_FNIDX__IBM_ERRINJCT] = {
		.name = "ibm,errinjct",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = 2, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
			.fixed_size = 1024,
		},
	},
	[RTAS_FNIDX__IBM_EXTI2C] = {
		.name = "ibm,exti2c",
	},
	[RTAS_FNIDX__IBM_GET_CONFIG_ADDR_INFO] = {
		.name = "ibm,get-config-addr-info",
	},
	[RTAS_FNIDX__IBM_GET_CONFIG_ADDR_INFO2] = {
		.name = "ibm,get-config-addr-info2",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = -1, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
	},
	[RTAS_FNIDX__IBM_GET_DYNAMIC_SENSOR_STATE] = {
		.name = "ibm,get-dynamic-sensor-state",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = 1, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
		/*
		 * PAPR+ v2.13 R1–7.3.19–3 is explicit that the OS
		 * must not call ibm,get-dynamic-sensor-state with
		 * different inputs until a non-retry status has been
		 * returned.
		 */
		.lock = &rtas_ibm_get_dynamic_sensor_state_lock,
	},
	[RTAS_FNIDX__IBM_GET_INDICES] = {
		.name = "ibm,get-indices",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = 2, .size_idx1 = 3,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
		/*
		 * PAPR+ v2.13 R1–7.3.17–2 says that the OS must not
		 * interleave ibm,get-indices call sequences with
		 * different inputs.
		 */
		.lock = &rtas_ibm_get_indices_lock,
	},
	[RTAS_FNIDX__IBM_GET_RIO_TOPOLOGY] = {
		.name = "ibm,get-rio-topology",
	},
	[RTAS_FNIDX__IBM_GET_SYSTEM_PARAMETER] = {
		.name = "ibm,get-system-parameter",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = 1, .size_idx1 = 2,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
	},
	[RTAS_FNIDX__IBM_GET_VPD] = {
		.name = "ibm,get-vpd",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = 0, .size_idx1 = -1,
			.buf_idx2 = 1, .size_idx2 = 2,
		},
		/*
		 * PAPR+ v2.13 R1–7.3.20–4 indicates that sequences
		 * should not be allowed to interleave.
		 */
		.lock = &rtas_ibm_get_vpd_lock,
	},
	[RTAS_FNIDX__IBM_GET_XIVE] = {
		.name = "ibm,get-xive",
	},
	[RTAS_FNIDX__IBM_INT_OFF] = {
		.name = "ibm,int-off",
	},
	[RTAS_FNIDX__IBM_INT_ON] = {
		.name = "ibm,int-on",
	},
	[RTAS_FNIDX__IBM_IO_QUIESCE_ACK] = {
		.name = "ibm,io-quiesce-ack",
	},
	[RTAS_FNIDX__IBM_LPAR_PERFTOOLS] = {
		.name = "ibm,lpar-perftools",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = 2, .size_idx1 = 3,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
		/*
		 * PAPR+ v2.13 R1–7.3.26–6 says the OS should allow
		 * only one call sequence in progress at a time.
		 */
		.lock = &rtas_ibm_lpar_perftools_lock,
	},
	[RTAS_FNIDX__IBM_MANAGE_FLASH_IMAGE] = {
		.name = "ibm,manage-flash-image",
	},
	[RTAS_FNIDX__IBM_MANAGE_STORAGE_PRESERVATION] = {
		.name = "ibm,manage-storage-preservation",
	},
	[RTAS_FNIDX__IBM_NMI_INTERLOCK] = {
		.name = "ibm,nmi-interlock",
	},
	[RTAS_FNIDX__IBM_NMI_REGISTER] = {
		.name = "ibm,nmi-register",
	},
	[RTAS_FNIDX__IBM_OPEN_ERRINJCT] = {
		.name = "ibm,open-errinjct",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = -1, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
	},
	[RTAS_FNIDX__IBM_OPEN_SRIOV_ALLOW_UNFREEZE] = {
		.name = "ibm,open-sriov-allow-unfreeze",
	},
	[RTAS_FNIDX__IBM_OPEN_SRIOV_MAP_PE_NUMBER] = {
		.name = "ibm,open-sriov-map-pe-number",
	},
	[RTAS_FNIDX__IBM_OS_TERM] = {
		.name = "ibm,os-term",
	},
	[RTAS_FNIDX__IBM_PARTNER_CONTROL] = {
		.name = "ibm,partner-control",
	},
	[RTAS_FNIDX__IBM_PHYSICAL_ATTESTATION] = {
		.name = "ibm,physical-attestation",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = 0, .size_idx1 = 1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
		/*
		 * This follows a sequence-based pattern similar to
		 * ibm,get-vpd et al. Since PAPR+ restricts
		 * interleaving call sequences for other functions of
		 * this style, assume the restriction applies here,
		 * even though it's not explicit in the spec.
		 */
		.lock = &rtas_ibm_physical_attestation_lock,
	},
	[RTAS_FNIDX__IBM_PLATFORM_DUMP] = {
		.name = "ibm,platform-dump",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = 4, .size_idx1 = 5,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
		/*
		 * PAPR+ v2.13 7.3.3.4.1 indicates that concurrent
		 * sequences of ibm,platform-dump are allowed if they
		 * are operating on different dump tags. So leave the
		 * lock pointer unset for now. This may need
		 * reconsideration if kernel-internal users appear.
		 */
	},
	[RTAS_FNIDX__IBM_POWER_OFF_UPS] = {
		.name = "ibm,power-off-ups",
	},
	[RTAS_FNIDX__IBM_QUERY_INTERRUPT_SOURCE_NUMBER] = {
		.name = "ibm,query-interrupt-source-number",
	},
	[RTAS_FNIDX__IBM_QUERY_PE_DMA_WINDOW] = {
		.name = "ibm,query-pe-dma-window",
	},
	[RTAS_FNIDX__IBM_READ_PCI_CONFIG] = {
		.name = "ibm,read-pci-config",
	},
	[RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE] = {
		.name = "ibm,read-slot-reset-state",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = -1, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
	},
	[RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2] = {
		.name = "ibm,read-slot-reset-state2",
	},
	[RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW] = {
		.name = "ibm,remove-pe-dma-window",
	},
	[RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW] = {
		/*
		 * Note: PAPR+ v2.13 7.3.31.4.1 spells this as
		 * "ibm,reset-pe-dma-windows" (plural), but RTAS
		 * implementations use the singular form in practice.
		 */
		.name = "ibm,reset-pe-dma-window",
	},
	[RTAS_FNIDX__IBM_SCAN_LOG_DUMP] = {
		.name = "ibm,scan-log-dump",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = 0, .size_idx1 = 1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
	},
	[RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR] = {
		.name = "ibm,set-dynamic-indicator",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = 2, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
		/*
		 * PAPR+ v2.13 R1–7.3.18–3 says the OS must not call
		 * this function with different inputs until a
		 * non-retry status has been returned.
		 */
		.lock = &rtas_ibm_set_dynamic_indicator_lock,
	},
	[RTAS_FNIDX__IBM_SET_EEH_OPTION] = {
		.name = "ibm,set-eeh-option",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = -1, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
	},
	[RTAS_FNIDX__IBM_SET_SLOT_RESET] = {
		.name = "ibm,set-slot-reset",
	},
	[RTAS_FNIDX__IBM_SET_SYSTEM_PARAMETER] = {
		.name = "ibm,set-system-parameter",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = 1, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
	},
	[RTAS_FNIDX__IBM_SET_XIVE] = {
		.name = "ibm,set-xive",
	},
	[RTAS_FNIDX__IBM_SLOT_ERROR_DETAIL] = {
		.name = "ibm,slot-error-detail",
	},
	[RTAS_FNIDX__IBM_SUSPEND_ME] = {
		.name = "ibm,suspend-me",
		.banned_for_syscall_on_le = true,
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = -1, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
	},
	[RTAS_FNIDX__IBM_TUNE_DMA_PARMS] = {
		.name = "ibm,tune-dma-parms",
	},
	[RTAS_FNIDX__IBM_UPDATE_FLASH_64_AND_REBOOT] = {
		.name = "ibm,update-flash-64-and-reboot",
	},
	[RTAS_FNIDX__IBM_UPDATE_NODES] = {
		.name = "ibm,update-nodes",
		.banned_for_syscall_on_le = true,
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = 0, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
			.fixed_size = 4096,
		},
	},
	[RTAS_FNIDX__IBM_UPDATE_PROPERTIES] = {
		.name = "ibm,update-properties",
		.banned_for_syscall_on_le = true,
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = 0, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
			.fixed_size = 4096,
		},
	},
	[RTAS_FNIDX__IBM_VALIDATE_FLASH_IMAGE] = {
		.name = "ibm,validate-flash-image",
	},
	[RTAS_FNIDX__IBM_WRITE_PCI_CONFIG] = {
		.name = "ibm,write-pci-config",
	},
	[RTAS_FNIDX__NVRAM_FETCH] = {
		.name = "nvram-fetch",
	},
	[RTAS_FNIDX__NVRAM_STORE] = {
		.name = "nvram-store",
	},
	[RTAS_FNIDX__POWER_OFF] = {
		.name = "power-off",
	},
	[RTAS_FNIDX__PUT_TERM_CHAR] = {
		.name = "put-term-char",
	},
	[RTAS_FNIDX__QUERY_CPU_STOPPED_STATE] = {
		.name = "query-cpu-stopped-state",
	},
	[RTAS_FNIDX__READ_PCI_CONFIG] = {
		.name = "read-pci-config",
	},
	[RTAS_FNIDX__RTAS_LAST_ERROR] = {
		.name = "rtas-last-error",
	},
	[RTAS_FNIDX__SET_INDICATOR] = {
		.name = "set-indicator",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = -1, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
	},
	[RTAS_FNIDX__SET_POWER_LEVEL] = {
		.name = "set-power-level",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = -1, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
	},
	[RTAS_FNIDX__SET_TIME_FOR_POWER_ON] = {
		.name = "set-time-for-power-on",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = -1, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
	},
	[RTAS_FNIDX__SET_TIME_OF_DAY] = {
		.name = "set-time-of-day",
		.filter = &(const struct rtas_filter) {
			.buf_idx1 = -1, .size_idx1 = -1,
			.buf_idx2 = -1, .size_idx2 = -1,
		},
	},
	[RTAS_FNIDX__START_CPU] = {
		.name = "start-cpu",
	},
	[RTAS_FNIDX__STOP_SELF] = {
		.name = "stop-self",
	},
	[RTAS_FNIDX__SYSTEM_REBOOT] = {
		.name = "system-reboot",
	},
	[RTAS_FNIDX__THAW_TIME_BASE] = {
		.name = "thaw-time-base",
	},
	[RTAS_FNIDX__WRITE_PCI_CONFIG] = {
		.name = "write-pci-config",
	},
};

#define for_each_rtas_function(funcp)                                       \
	for (funcp = &rtas_function_table[0];                               \
	     funcp < &rtas_function_table[ARRAY_SIZE(rtas_function_table)]; \
	     ++funcp)

/*
 * Nearly all RTAS calls need to be serialized. All uses of the
 * default rtas_args block must hold rtas_lock.
 *
 * Exceptions to the RTAS serialization requirement (e.g. stop-self)
 * must use a separate rtas_args structure.
 */
static DEFINE_RAW_SPINLOCK(rtas_lock);
static struct rtas_args rtas_args;

/**
 * rtas_function_token() - RTAS function token lookup.
 * @handle: Function handle, e.g. RTAS_FN_EVENT_SCAN.
 *
 * Context: Any context.
 * Return: the token value for the function if implemented by this platform,
 *         otherwise RTAS_UNKNOWN_SERVICE.
 */
s32 rtas_function_token(const rtas_fn_handle_t handle)
{
	const size_t index = handle.index;
	const bool out_of_bounds = index >= ARRAY_SIZE(rtas_function_table);

	if (WARN_ONCE(out_of_bounds, "invalid function index %zu", index))
		return RTAS_UNKNOWN_SERVICE;
	/*
	 * Various drivers attempt token lookups on non-RTAS
	 * platforms.
	 */
	if (!rtas.dev)
		return RTAS_UNKNOWN_SERVICE;

	return rtas_function_table[index].token;
}
EXPORT_SYMBOL_GPL(rtas_function_token);

static int rtas_function_cmp(const void *a, const void *b)
{
	const struct rtas_function *f1 = a;
	const struct rtas_function *f2 = b;

	return strcmp(f1->name, f2->name);
}

/*
 * Boot-time initialization of the function table needs the lookup to
 * return a non-const-qualified object. Use rtas_name_to_function()
 * in all other contexts.
 */
static struct rtas_function *__rtas_name_to_function(const char *name)
{
	const struct rtas_function key = {
		.name = name,
	};
	struct rtas_function *found;

	found = bsearch(&key, rtas_function_table, ARRAY_SIZE(rtas_function_table),
			sizeof(rtas_function_table[0]), rtas_function_cmp);

	return found;
}

static const struct rtas_function *rtas_name_to_function(const char *name)
{
	return __rtas_name_to_function(name);
}

static DEFINE_XARRAY(rtas_token_to_function_xarray);

static int __init rtas_token_to_function_xarray_init(void)
{
	const struct rtas_function *func;
	int err = 0;

	for_each_rtas_function(func) {
		const s32 token = func->token;

		if (token == RTAS_UNKNOWN_SERVICE)
			continue;

		err = xa_err(xa_store(&rtas_token_to_function_xarray,
				      token, (void *)func, GFP_KERNEL));
		if (err)
			break;
	}

	return err;
}
arch_initcall(rtas_token_to_function_xarray_init);

/*
 * For use by sys_rtas(), where the token value is provided by user
 * space and we don't want to warn on failed lookups.
 */
static const struct rtas_function *rtas_token_to_function_untrusted(s32 token)
{
	return xa_load(&rtas_token_to_function_xarray, token);
}

/*
 * Reverse lookup for deriving the function descriptor from a
 * known-good token value in contexts where the former is not already
 * available. @token must be valid, e.g. derived from the result of a
 * prior lookup against the function table.
 */
static const struct rtas_function *rtas_token_to_function(s32 token)
{
	const struct rtas_function *func;

	if (WARN_ONCE(token < 0, "invalid token %d", token))
		return NULL;

	func = rtas_token_to_function_untrusted(token);
	if (func)
		return func;
	/*
	 * Fall back to linear scan in case the reverse mapping hasn't
	 * been initialized yet.
	 */
	if (xa_empty(&rtas_token_to_function_xarray)) {
		for_each_rtas_function(func) {
			if (func->token == token)
				return func;
		}
	}

	WARN_ONCE(true, "unexpected failed lookup for token %d", token);
	return NULL;
}

/* This is here deliberately so it's only used in this file */
void enter_rtas(unsigned long);

static void __do_enter_rtas(struct rtas_args *args)
{
	enter_rtas(__pa(args));
	srr_regs_clobbered(); /* rtas uses SRRs, invalidate */
}

static void __do_enter_rtas_trace(struct rtas_args *args)
{
	const struct rtas_function *func = rtas_token_to_function(be32_to_cpu(args->token));

	/*
	 * If there is a per-function lock, it must be held by the
	 * caller.
	 */
	if (func->lock)
		lockdep_assert_held(func->lock);

	if (args == &rtas_args)
		lockdep_assert_held(&rtas_lock);

	trace_rtas_input(args, func->name);
	trace_rtas_ll_entry(args);

	__do_enter_rtas(args);

	trace_rtas_ll_exit(args);
	trace_rtas_output(args, func->name);
}

static void do_enter_rtas(struct rtas_args *args)
{
	const unsigned long msr = mfmsr();
	/*
	 * Situations where we want to skip any active tracepoints for
	 * safety reasons:
	 *
	 * 1. The last code executed on an offline CPU as it stops,
	 *    i.e. we're about to call stop-self. The tracepoints'
	 *    function name lookup uses xarray, which uses RCU, which
	 *    isn't valid to call on an offline CPU.  Any events
	 *    emitted on an offline CPU will be discarded anyway.
	 *
	 * 2. In real mode, as when invoking ibm,nmi-interlock from
	 *    the pseries MCE handler. We cannot count on trace
	 *    buffers or the entries in rtas_token_to_function_xarray
	 *    to be contained in the RMO.
	 */
	const unsigned long mask = MSR_IR | MSR_DR;
	const bool can_trace = likely(cpu_online(raw_smp_processor_id()) &&
				      (msr & mask) == mask);
	/*
	 * Make sure MSR[RI] is currently enabled as it will be forced later
	 * in enter_rtas.
	 */
	BUG_ON(!(msr & MSR_RI));

	BUG_ON(!irqs_disabled());

	hard_irq_disable(); /* Ensure MSR[EE] is disabled on PPC64 */

	if (can_trace)
		__do_enter_rtas_trace(args);
	else
		__do_enter_rtas(args);
}

struct rtas_t rtas;

DEFINE_SPINLOCK(rtas_data_buf_lock);
EXPORT_SYMBOL_GPL(rtas_data_buf_lock);

char rtas_data_buf[RTAS_DATA_BUF_SIZE] __aligned(SZ_4K);
EXPORT_SYMBOL_GPL(rtas_data_buf);

unsigned long rtas_rmo_buf;

/*
 * If non-NULL, this gets called when the kernel terminates.
 * This is done like this so rtas_flash can be a module.
 */
void (*rtas_flash_term_hook)(int);
EXPORT_SYMBOL_GPL(rtas_flash_term_hook);

/*
 * call_rtas_display_status and call_rtas_display_status_delay
 * are designed only for very early low-level debugging, which
 * is why the token is hard-coded to 10.
 */
static void call_rtas_display_status(unsigned char c)
{
	unsigned long flags;

	if (!rtas.base)
		return;

	raw_spin_lock_irqsave(&rtas_lock, flags);
	rtas_call_unlocked(&rtas_args, 10, 1, 1, NULL, c);
	raw_spin_unlock_irqrestore(&rtas_lock, flags);
}

static void call_rtas_display_status_delay(char c)
{
	static int pending_newline = 0;  /* did last write end with unprinted newline? */
	static int width = 16;

	if (c == '\n') {
		while (width-- > 0)
			call_rtas_display_status(' ');
		width = 16;
		mdelay(500);
		pending_newline = 1;
	} else {
		if (pending_newline) {
			call_rtas_display_status('\r');
			call_rtas_display_status('\n');
		}
		pending_newline = 0;
		if (width--) {
			call_rtas_display_status(c);
			udelay(10000);
		}
	}
}

void __init udbg_init_rtas_panel(void)
{
	udbg_putc = call_rtas_display_status_delay;
}

#ifdef CONFIG_UDBG_RTAS_CONSOLE

/* If you think you're dying before early_init_dt_scan_rtas() does its
 * work, you can hard code the token values for your firmware here and
 * hardcode rtas.base/entry etc.
 */
static unsigned int rtas_putchar_token = RTAS_UNKNOWN_SERVICE;
static unsigned int rtas_getchar_token = RTAS_UNKNOWN_SERVICE;

static void udbg_rtascon_putc(char c)
{
	int tries;

	if (!rtas.base)
		return;

	/* Add CRs before LFs */
	if (c == '\n')
		udbg_rtascon_putc('\r');

	/* if there is more than one character to be displayed, wait a bit */
	for (tries = 0; tries < 16; tries++) {
		if (rtas_call(rtas_putchar_token, 1, 1, NULL, c) == 0)
			break;
		udelay(1000);
	}
}

static int udbg_rtascon_getc_poll(void)
{
	int c;

	if (!rtas.base)
		return -1;

	if (rtas_call(rtas_getchar_token, 0, 2, &c))
		return -1;

	return c;
}

static int udbg_rtascon_getc(void)
{
	int c;

	while ((c = udbg_rtascon_getc_poll()) == -1)
		;

	return c;
}


void __init udbg_init_rtas_console(void)
{
	udbg_putc = udbg_rtascon_putc;
	udbg_getc = udbg_rtascon_getc;
	udbg_getc_poll = udbg_rtascon_getc_poll;
}
#endif /* CONFIG_UDBG_RTAS_CONSOLE */

void rtas_progress(char *s, unsigned short hex)
{
	struct device_node *root;
	int width;
	const __be32 *p;
	char *os;
	static int display_character, set_indicator;
	static int display_width, display_lines, form_feed;
	static const int *row_width;
	static DEFINE_SPINLOCK(progress_lock);
	static int current_line;
	static int pending_newline = 0;  /* did last write end with unprinted newline? */

	if (!rtas.base)
		return;

	if (display_width == 0) {
		display_width = 0x10;
		if ((root = of_find_node_by_path("/rtas"))) {
			if ((p = of_get_property(root,
					"ibm,display-line-length", NULL)))
				display_width = be32_to_cpu(*p);
			if ((p = of_get_property(root,
					"ibm,form-feed", NULL)))
				form_feed = be32_to_cpu(*p);
			if ((p = of_get_property(root,
					"ibm,display-number-of-lines", NULL)))
				display_lines = be32_to_cpu(*p);
			row_width = of_get_property(root,
					"ibm,display-truncation-length", NULL);
			of_node_put(root);
		}
		display_character = rtas_function_token(RTAS_FN_DISPLAY_CHARACTER);
		set_indicator = rtas_function_token(RTAS_FN_SET_INDICATOR);
	}

	if (display_character == RTAS_UNKNOWN_SERVICE) {
		/* use hex display if available */
		if (set_indicator != RTAS_UNKNOWN_SERVICE)
			rtas_call(set_indicator, 3, 1, NULL, 6, 0, hex);
		return;
	}

	spin_lock(&progress_lock);

	/*
	 * Last write ended with newline, but we didn't print it since
	 * it would just clear the bottom line of output. Print it now
	 * instead.
	 *
	 * If no newline is pending and form feed is supported, clear the
	 * display with a form feed; otherwise, print a CR to start output
	 * at the beginning of the line.
	 */
	if (pending_newline) {
		rtas_call(display_character, 1, 1, NULL, '\r');
		rtas_call(display_character, 1, 1, NULL, '\n');
		pending_newline = 0;
	} else {
		current_line = 0;
		if (form_feed)
			rtas_call(display_character, 1, 1, NULL,
				  (char)form_feed);
		else
			rtas_call(display_character, 1, 1, NULL, '\r');
	}

	if (row_width)
		width = row_width[current_line];
	else
		width = display_width;
	os = s;
	while (*os) {
		if (*os == '\n' || *os == '\r') {
			/* If newline is the last character, save it
			 * until next call to avoid bumping up the
			 * display output.
			 */
			if (*os == '\n' && !os[1]) {
				pending_newline = 1;
				current_line++;
				if (current_line > display_lines-1)
					current_line = display_lines-1;
				spin_unlock(&progress_lock);
				return;
			}

			/* RTAS wants CR-LF, not just LF */

			if (*os == '\n') {
				rtas_call(display_character, 1, 1, NULL, '\r');
				rtas_call(display_character, 1, 1, NULL, '\n');
			} else {
				/* CR might be used to re-draw a line, so we'll
				 * leave it alone and not add LF.
				 */
				rtas_call(display_character, 1, 1, NULL, *os);
			}

			if (row_width)
				width = row_width[current_line];
			else
				width = display_width;
		} else {
			width--;
			rtas_call(display_character, 1, 1, NULL, *os);
		}

		os++;

		/* if we overwrite the screen length */
		if (width <= 0)
			while ((*os != 0) && (*os != '\n') && (*os != '\r'))
				os++;
	}

	spin_unlock(&progress_lock);
}
EXPORT_SYMBOL_GPL(rtas_progress);		/* needed by rtas_flash module */

int rtas_token(const char *service)
{
	const struct rtas_function *func;
	const __be32 *tokp;

	if (rtas.dev == NULL)
		return RTAS_UNKNOWN_SERVICE;

	func = rtas_name_to_function(service);
	if (func)
		return func->token;
	/*
	 * The caller is looking up a name that is not known to be an
	 * RTAS function. Either it's a function that needs to be
	 * added to the table, or they're misusing rtas_token() to
	 * access non-function properties of the /rtas node. Warn and
	 * fall back to the legacy behavior.
	 */
	WARN_ONCE(1, "unknown function `%s`, should it be added to rtas_function_table?\n",
		  service);

	tokp = of_get_property(rtas.dev, service, NULL);
	return tokp ? be32_to_cpu(*tokp) : RTAS_UNKNOWN_SERVICE;
}
EXPORT_SYMBOL_GPL(rtas_token);

#ifdef CONFIG_RTAS_ERROR_LOGGING

static u32 rtas_error_log_max __ro_after_init = RTAS_ERROR_LOG_MAX;

/*
 * Return the firmware-specified size of the error log buffer
 *  for all rtas calls that require an error buffer argument.
 *  This includes 'check-exception' and 'rtas-last-error'.
 */
int rtas_get_error_log_max(void)
{
	return rtas_error_log_max;
}

static void __init init_error_log_max(void)
{
	static const char propname[] __initconst = "rtas-error-log-max";
	u32 max;

	if (of_property_read_u32(rtas.dev, propname, &max)) {
		pr_warn("%s not found, using default of %u\n",
			propname, RTAS_ERROR_LOG_MAX);
		max = RTAS_ERROR_LOG_MAX;
	}

	if (max > RTAS_ERROR_LOG_MAX) {
		pr_warn("%s = %u, clamping max error log size to %u\n",
			propname, max, RTAS_ERROR_LOG_MAX);
		max = RTAS_ERROR_LOG_MAX;
	}

	rtas_error_log_max = max;
}


static char rtas_err_buf[RTAS_ERROR_LOG_MAX];

/** Return a copy of the detailed error text associated with the
 *  most recent failed call to rtas.  Because the error text
 *  might go stale if there are any other intervening rtas calls,
 *  this routine must be called atomically with whatever produced
 *  the error (i.e. with rtas_lock still held from the previous call).
 */
static char *__fetch_rtas_last_error(char *altbuf)
{
	const s32 token = rtas_function_token(RTAS_FN_RTAS_LAST_ERROR);
	struct rtas_args err_args, save_args;
	u32 bufsz;
	char *buf = NULL;

	lockdep_assert_held(&rtas_lock);

	if (token == -1)
		return NULL;

	bufsz = rtas_get_error_log_max();

	err_args.token = cpu_to_be32(token);
	err_args.nargs = cpu_to_be32(2);
	err_args.nret = cpu_to_be32(1);
	err_args.args[0] = cpu_to_be32(__pa(rtas_err_buf));
	err_args.args[1] = cpu_to_be32(bufsz);
	err_args.args[2] = 0;

	save_args = rtas_args;
	rtas_args = err_args;

	do_enter_rtas(&rtas_args);

	err_args = rtas_args;
	rtas_args = save_args;

	/* Log the error in the unlikely case that there was one. */
	if (unlikely(err_args.args[2] == 0)) {
		if (altbuf) {
			buf = altbuf;
		} else {
			buf = rtas_err_buf;
			if (slab_is_available())
				buf = kmalloc(RTAS_ERROR_LOG_MAX, GFP_ATOMIC);
		}
		if (buf)
			memmove(buf, rtas_err_buf, RTAS_ERROR_LOG_MAX);
	}

	return buf;
}

#define get_errorlog_buffer()	kmalloc(RTAS_ERROR_LOG_MAX, GFP_KERNEL)

#else /* CONFIG_RTAS_ERROR_LOGGING */
#define __fetch_rtas_last_error(x)	NULL
#define get_errorlog_buffer()		NULL
static void __init init_error_log_max(void) {}
#endif


static void
va_rtas_call_unlocked(struct rtas_args *args, int token, int nargs, int nret,
		      va_list list)
{
	int i;

	args->token = cpu_to_be32(token);
	args->nargs = cpu_to_be32(nargs);
	args->nret  = cpu_to_be32(nret);
	args->rets  = &(args->args[nargs]);

	for (i = 0; i < nargs; ++i)
		args->args[i] = cpu_to_be32(va_arg(list, __u32));

	for (i = 0; i < nret; ++i)
		args->rets[i] = 0;

	do_enter_rtas(args);
}

/**
 * rtas_call_unlocked() - Invoke an RTAS firmware function without synchronization.
 * @args: RTAS parameter block to be used for the call, must obey RTAS addressing
 *        constraints.
 * @token: Identifies the function being invoked.
 * @nargs: Number of input parameters. Does not include token.
 * @nret: Number of output parameters, including the call status.
 * @....: List of @nargs input parameters.
 *
 * Invokes the RTAS function indicated by @token, which the caller
 * should obtain via rtas_function_token().
 *
 * This function is similar to rtas_call(), but must be used with a
 * limited set of RTAS calls specifically exempted from the general
 * requirement that only one RTAS call may be in progress at any
 * time. Examples include stop-self and ibm,nmi-interlock.
 */
void rtas_call_unlocked(struct rtas_args *args, int token, int nargs, int nret, ...)
{
	va_list list;

	va_start(list, nret);
	va_rtas_call_unlocked(args, token, nargs, nret, list);
	va_end(list);
}

static bool token_is_restricted_errinjct(s32 token)
{
	return token == rtas_function_token(RTAS_FN_IBM_OPEN_ERRINJCT) ||
	       token == rtas_function_token(RTAS_FN_IBM_ERRINJCT);
}

/**
 * rtas_call() - Invoke an RTAS firmware function.
 * @token: Identifies the function being invoked.
 * @nargs: Number of input parameters. Does not include token.
 * @nret: Number of output parameters, including the call status.
 * @outputs: Array of @nret output words.
 * @....: List of @nargs input parameters.
 *
 * Invokes the RTAS function indicated by @token, which the caller
 * should obtain via rtas_function_token().
 *
 * The @nargs and @nret arguments must match the number of input and
 * output parameters specified for the RTAS function.
 *
 * rtas_call() returns RTAS status codes, not conventional Linux errno
 * values. Callers must translate any failure to an appropriate errno
 * in syscall context. Most callers of RTAS functions that can return
 * -2 or 990x should use rtas_busy_delay() to correctly handle those
 * statuses before calling again.
 *
 * The return value descriptions are adapted from 7.2.8 [RTAS] Return
 * Codes of the PAPR and CHRP specifications.
 *
 * Context: Process context preferably, interrupt context if
 *          necessary.  Acquires an internal spinlock and may perform
 *          GFP_ATOMIC slab allocation in error path. Unsafe for NMI
 *          context.
 * Return:
 * *                          0 - RTAS function call succeeded.
 * *                         -1 - RTAS function encountered a hardware or
 *                                platform error, or the token is invalid,
 *                                or the function is restricted by kernel policy.
 * *                         -2 - Specs say "A necessary hardware device was busy,
 *                                and the requested function could not be
 *                                performed. The operation should be retried at
 *                                a later time." This is misleading, at least with
 *                                respect to current RTAS implementations. What it
 *                                usually means in practice is that the function
 *                                could not be completed while meeting RTAS's
 *                                deadline for returning control to the OS (250us
 *                                for PAPR/PowerVM, typically), but the call may be
 *                                immediately reattempted to resume work on it.
 * *                         -3 - Parameter error.
 * *                         -7 - Unexpected state change.
 * *                9000...9899 - Vendor-specific success codes.
 * *                9900...9905 - Advisory extended delay. Caller should try
 *                                again after ~10^x ms has elapsed, where x is
 *                                the last digit of the status [0-5]. Again going
 *                                beyond the PAPR text, 990x on PowerVM indicates
 *                                contention for RTAS-internal resources. Other
 *                                RTAS call sequences in progress should be
 *                                allowed to complete before reattempting the
 *                                call.
 * *                      -9000 - Multi-level isolation error.
 * *              -9999...-9004 - Vendor-specific error codes.
 * * Additional negative values - Function-specific error.
 * * Additional positive values - Function-specific success.
 */
int rtas_call(int token, int nargs, int nret, int *outputs, ...)
{
	struct pin_cookie cookie;
	va_list list;
	int i;
	unsigned long flags;
	struct rtas_args *args;
	char *buff_copy = NULL;
	int ret;

	if (!rtas.entry || token == RTAS_UNKNOWN_SERVICE)
		return -1;

	if (token_is_restricted_errinjct(token)) {
		/*
		 * It would be nicer to not discard the error value
		 * from security_locked_down(), but callers expect an
		 * RTAS status, not an errno.
		 */
		if (security_locked_down(LOCKDOWN_RTAS_ERROR_INJECTION))
			return -1;
	}

	if ((mfmsr() & (MSR_IR|MSR_DR)) != (MSR_IR|MSR_DR)) {
		WARN_ON_ONCE(1);
		return -1;
	}

	raw_spin_lock_irqsave(&rtas_lock, flags);
	cookie = lockdep_pin_lock(&rtas_lock);

	/* We use the global rtas args buffer */
	args = &rtas_args;

	va_start(list, outputs);
	va_rtas_call_unlocked(args, token, nargs, nret, list);
	va_end(list);

	/* A -1 return code indicates that the last command couldn't
	   be completed due to a hardware error. */
	if (be32_to_cpu(args->rets[0]) == -1)
		buff_copy = __fetch_rtas_last_error(NULL);

	if (nret > 1 && outputs != NULL)
		for (i = 0; i < nret-1; ++i)
			outputs[i] = be32_to_cpu(args->rets[i + 1]);
	ret = (nret > 0) ? be32_to_cpu(args->rets[0]) : 0;

	lockdep_unpin_lock(&rtas_lock, cookie);
	raw_spin_unlock_irqrestore(&rtas_lock, flags);

	if (buff_copy) {
		log_error(buff_copy, ERR_TYPE_RTAS_LOG, 0);
		if (slab_is_available())
			kfree(buff_copy);
	}
	return ret;
}
EXPORT_SYMBOL_GPL(rtas_call);

/**
 * rtas_busy_delay_time() - From an RTAS status value, calculate the
 *                          suggested delay time in milliseconds.
 *
 * @status: a value returned from rtas_call() or similar APIs which return
 *          the status of a RTAS function call.
 *
 * Context: Any context.
 *
 * Return:
 * * 100000 - If @status is 9905.
 * * 10000  - If @status is 9904.
 * * 1000   - If @status is 9903.
 * * 100    - If @status is 9902.
 * * 10     - If @status is 9901.
 * * 1      - If @status is either 9900 or -2. This is "wrong" for -2, but
 *            some callers depend on this behavior, and the worst outcome
 *            is that they will delay for longer than necessary.
 * * 0      - If @status is not a busy or extended delay value.
 */
unsigned int rtas_busy_delay_time(int status)
{
	int order;
	unsigned int ms = 0;

	if (status == RTAS_BUSY) {
		ms = 1;
	} else if (status >= RTAS_EXTENDED_DELAY_MIN &&
		   status <= RTAS_EXTENDED_DELAY_MAX) {
		order = status - RTAS_EXTENDED_DELAY_MIN;
		for (ms = 1; order > 0; order--)
			ms *= 10;
	}

	return ms;
}

/*
 * Early boot fallback for rtas_busy_delay().
 */
static bool __init rtas_busy_delay_early(int status)
{
	static size_t successive_ext_delays __initdata;
	bool retry;

	switch (status) {
	case RTAS_EXTENDED_DELAY_MIN...RTAS_EXTENDED_DELAY_MAX:
		/*
		 * In the unlikely case that we receive an extended
		 * delay status in early boot, the OS is probably not
		 * the cause, and there's nothing we can do to clear
		 * the condition. Best we can do is delay for a bit
		 * and hope it's transient. Lie to the caller if it
		 * seems like we're stuck in a retry loop.
		 */
		mdelay(1);
		retry = true;
		successive_ext_delays += 1;
		if (successive_ext_delays > 1000) {
			pr_err("too many extended delays, giving up\n");
			dump_stack();
			retry = false;
			successive_ext_delays = 0;
		}
		break;
	case RTAS_BUSY:
		retry = true;
		successive_ext_delays = 0;
		break;
	default:
		retry = false;
		successive_ext_delays = 0;
		break;
	}

	return retry;
}

/**
 * rtas_busy_delay() - helper for RTAS busy and extended delay statuses
 *
 * @status: a value returned from rtas_call() or similar APIs which return
 *          the status of a RTAS function call.
 *
 * Context: Process context. May sleep or schedule.
 *
 * Return:
 * * true  - @status is RTAS_BUSY or an extended delay hint. The
 *           caller may assume that the CPU has been yielded if necessary,
 *           and that an appropriate delay for @status has elapsed.
 *           Generally the caller should reattempt the RTAS call which
 *           yielded @status.
 *
 * * false - @status is not @RTAS_BUSY nor an extended delay hint. The
 *           caller is responsible for handling @status.
 */
bool __ref rtas_busy_delay(int status)
{
	unsigned int ms;
	bool ret;

	/*
	 * Can't do timed sleeps before timekeeping is up.
	 */
	if (system_state < SYSTEM_SCHEDULING)
		return rtas_busy_delay_early(status);

	switch (status) {
	case RTAS_EXTENDED_DELAY_MIN...RTAS_EXTENDED_DELAY_MAX:
		ret = true;
		ms = rtas_busy_delay_time(status);
		/*
		 * The extended delay hint can be as high as 100 seconds.
		 * Surely any function returning such a status is either
		 * buggy or isn't going to be significantly slowed by us
		 * polling at 1HZ. Clamp the sleep time to one second.
		 */
		ms = clamp(ms, 1U, 1000U);
		/*
		 * The delay hint is an order-of-magnitude suggestion, not
		 * a minimum. It is fine, possibly even advantageous, for
		 * us to pause for less time than hinted. For small values,
		 * use usleep_range() to ensure we don't sleep much longer
		 * than actually needed.
		 *
		 * See Documentation/timers/timers-howto.rst for
		 * explanation of the threshold used here. In effect we use
		 * usleep_range() for 9900 and 9901, msleep() for
		 * 9902-9905.
		 */
		if (ms <= 20)
			usleep_range(ms * 100, ms * 1000);
		else
			msleep(ms);
		break;
	case RTAS_BUSY:
		ret = true;
		/*
		 * We should call again immediately if there's no other
		 * work to do.
		 */
		cond_resched();
		break;
	default:
		ret = false;
		/*
		 * Not a busy or extended delay status; the caller should
		 * handle @status itself. Ensure we warn on misuses in
		 * atomic context regardless.
		 */
		might_sleep();
		break;
	}

	return ret;
}
EXPORT_SYMBOL_GPL(rtas_busy_delay);

int rtas_error_rc(int rtas_rc)
{
	int rc;

	switch (rtas_rc) {
	case RTAS_HARDWARE_ERROR:	/* Hardware Error */
		rc = -EIO;
		break;
	case RTAS_INVALID_PARAMETER:	/* Bad indicator/domain/etc */
		rc = -EINVAL;
		break;
	case -9000:			/* Isolation error */
		rc = -EFAULT;
		break;
	case -9001:			/* Outstanding TCE/PTE */
		rc = -EEXIST;
		break;
	case -9002:			/* No usable slot */
		rc = -ENODEV;
		break;
	default:
		pr_err("%s: unexpected error %d\n", __func__, rtas_rc);
		rc = -ERANGE;
		break;
	}
	return rc;
}
EXPORT_SYMBOL_GPL(rtas_error_rc);

int rtas_get_power_level(int powerdomain, int *level)
{
	int token = rtas_function_token(RTAS_FN_GET_POWER_LEVEL);
	int rc;

	if (token == RTAS_UNKNOWN_SERVICE)
		return -ENOENT;

	while ((rc = rtas_call(token, 1, 2, level, powerdomain)) == RTAS_BUSY)
		udelay(1);

	if (rc < 0)
		return rtas_error_rc(rc);
	return rc;
}
EXPORT_SYMBOL_GPL(rtas_get_power_level);

int rtas_set_power_level(int powerdomain, int level, int *setlevel)
{
	int token = rtas_function_token(RTAS_FN_SET_POWER_LEVEL);
	int rc;

	if (token == RTAS_UNKNOWN_SERVICE)
		return -ENOENT;

	do {
		rc = rtas_call(token, 2, 2, setlevel, powerdomain, level);
	} while (rtas_busy_delay(rc));

	if (rc < 0)
		return rtas_error_rc(rc);
	return rc;
}
EXPORT_SYMBOL_GPL(rtas_set_power_level);

int rtas_get_sensor(int sensor, int index, int *state)
{
	int token = rtas_function_token(RTAS_FN_GET_SENSOR_STATE);
	int rc;

	if (token == RTAS_UNKNOWN_SERVICE)
		return -ENOENT;

	do {
		rc = rtas_call(token, 2, 2, state, sensor, index);
	} while (rtas_busy_delay(rc));

	if (rc < 0)
		return rtas_error_rc(rc);
	return rc;
}
EXPORT_SYMBOL_GPL(rtas_get_sensor);

int rtas_get_sensor_fast(int sensor, int index, int *state)
{
	int token = rtas_function_token(RTAS_FN_GET_SENSOR_STATE);
	int rc;

	if (token == RTAS_UNKNOWN_SERVICE)
		return -ENOENT;

	rc = rtas_call(token, 2, 2, state, sensor, index);
	WARN_ON(rc == RTAS_BUSY || (rc >= RTAS_EXTENDED_DELAY_MIN &&
				    rc <= RTAS_EXTENDED_DELAY_MAX));

	if (rc < 0)
		return rtas_error_rc(rc);
	return rc;
}

bool rtas_indicator_present(int token, int *maxindex)
{
	int proplen, count, i;
	const struct indicator_elem {
		__be32 token;
		__be32 maxindex;
	} *indicators;

	indicators = of_get_property(rtas.dev, "rtas-indicators", &proplen);
	if (!indicators)
		return false;

	count = proplen / sizeof(struct indicator_elem);

	for (i = 0; i < count; i++) {
		if (__be32_to_cpu(indicators[i].token) != token)
			continue;
		if (maxindex)
			*maxindex = __be32_to_cpu(indicators[i].maxindex);
		return true;
	}

	return false;
}

int rtas_set_indicator(int indicator, int index, int new_value)
{
	int token = rtas_function_token(RTAS_FN_SET_INDICATOR);
	int rc;

	if (token == RTAS_UNKNOWN_SERVICE)
		return -ENOENT;

	do {
		rc = rtas_call(token, 3, 1, NULL, indicator, index, new_value);
	} while (rtas_busy_delay(rc));

	if (rc < 0)
		return rtas_error_rc(rc);
	return rc;
}
EXPORT_SYMBOL_GPL(rtas_set_indicator);

/*
 * Ignoring RTAS extended delay
 */
int rtas_set_indicator_fast(int indicator, int index, int new_value)
{
	int token = rtas_function_token(RTAS_FN_SET_INDICATOR);
	int rc;

	if (token == RTAS_UNKNOWN_SERVICE)
		return -ENOENT;

	rc = rtas_call(token, 3, 1, NULL, indicator, index, new_value);

	WARN_ON(rc == RTAS_BUSY || (rc >= RTAS_EXTENDED_DELAY_MIN &&
				    rc <= RTAS_EXTENDED_DELAY_MAX));

	if (rc < 0)
		return rtas_error_rc(rc);

	return rc;
}

/**
 * rtas_ibm_suspend_me() - Call ibm,suspend-me to suspend the LPAR.
 *
 * @fw_status: RTAS call status will be placed here if not NULL.
 *
 * rtas_ibm_suspend_me() should be called only on a CPU which has
 * received H_CONTINUE from the H_JOIN hcall. All other active CPUs
 * should be waiting to return from H_JOIN.
 *
 * rtas_ibm_suspend_me() may suspend execution of the OS
 * indefinitely. Callers should take appropriate measures upon return, such as
 * resetting watchdog facilities.
 *
 * Callers may choose to retry this call if @fw_status is
 * %RTAS_THREADS_ACTIVE.
 *
 * Return:
 * 0          - The partition has resumed from suspend, possibly after
 *              migration to a different host.
 * -ECANCELED - The operation was aborted.
 * -EAGAIN    - There were other CPUs not in H_JOIN at the time of the call.
 * -EBUSY     - Some other condition prevented the suspend from succeeding.
 * -EIO       - Hardware/platform error.
 */
int rtas_ibm_suspend_me(int *fw_status)
{
	int token = rtas_function_token(RTAS_FN_IBM_SUSPEND_ME);
	int fwrc;
	int ret;

	fwrc = rtas_call(token, 0, 1, NULL);

	switch (fwrc) {
	case 0:
		ret = 0;
		break;
	case RTAS_SUSPEND_ABORTED:
		ret = -ECANCELED;
		break;
	case RTAS_THREADS_ACTIVE:
		ret = -EAGAIN;
		break;
	case RTAS_NOT_SUSPENDABLE:
	case RTAS_OUTSTANDING_COPROC:
		ret = -EBUSY;
		break;
	case -1:
	default:
		ret = -EIO;
		break;
	}

	if (fw_status)
		*fw_status = fwrc;

	return ret;
}

void __noreturn rtas_restart(char *cmd)
{
	if (rtas_flash_term_hook)
		rtas_flash_term_hook(SYS_RESTART);
	pr_emerg("system-reboot returned %d\n",
		 rtas_call(rtas_function_token(RTAS_FN_SYSTEM_REBOOT), 0, 1, NULL));
	for (;;);
}

void rtas_power_off(void)
{
	if (rtas_flash_term_hook)
		rtas_flash_term_hook(SYS_POWER_OFF);
	/* allow power on only with power button press */
	pr_emerg("power-off returned %d\n",
		 rtas_call(rtas_function_token(RTAS_FN_POWER_OFF), 2, 1, NULL, -1, -1));
	for (;;);
}

void __noreturn rtas_halt(void)
{
	if (rtas_flash_term_hook)
		rtas_flash_term_hook(SYS_HALT);
	/* allow power on only with power button press */
	pr_emerg("power-off returned %d\n",
		 rtas_call(rtas_function_token(RTAS_FN_POWER_OFF), 2, 1, NULL, -1, -1));
	for (;;);
}

/* Must be in the RMO region, so we place it here */
static char rtas_os_term_buf[2048];
static bool ibm_extended_os_term;

void rtas_os_term(char *str)
{
	s32 token = rtas_function_token(RTAS_FN_IBM_OS_TERM);
	static struct rtas_args args;
	int status;

	/*
	 * Firmware with the ibm,extended-os-term property is guaranteed
	 * to always return from an ibm,os-term call. Earlier versions without
	 * this property may terminate the partition which we want to avoid
	 * since it interferes with panic_timeout.
	 */

	if (token == RTAS_UNKNOWN_SERVICE || !ibm_extended_os_term)
		return;

	snprintf(rtas_os_term_buf, 2048, "OS panic: %s", str);

	/*
	 * Keep calling as long as RTAS returns a "try again" status,
	 * but don't use rtas_busy_delay(), which potentially
	 * schedules.
	 */
	do {
		rtas_call_unlocked(&args, token, 1, 1, NULL, __pa(rtas_os_term_buf));
		status = be32_to_cpu(args.rets[0]);
	} while (rtas_busy_delay_time(status));

	if (status != 0)
		pr_emerg("ibm,os-term call failed %d\n", status);
}

/**
 * rtas_activate_firmware() - Activate a new version of firmware.
 *
 * Context: This function may sleep.
 *
 * Activate a new version of partition firmware. The OS must call this
 * after resuming from a partition hibernation or migration in order
 * to maintain the ability to perform live firmware updates. It's not
 * catastrophic for this method to be absent or to fail; just log the
 * condition in that case.
 */
void rtas_activate_firmware(void)
{
	int token = rtas_function_token(RTAS_FN_IBM_ACTIVATE_FIRMWARE);
	int fwrc;

	if (token == RTAS_UNKNOWN_SERVICE) {
		pr_notice("ibm,activate-firmware method unavailable\n");
		return;
	}

	mutex_lock(&rtas_ibm_activate_firmware_lock);

	do {
		fwrc = rtas_call(token, 0, 1, NULL);
	} while (rtas_busy_delay(fwrc));

	mutex_unlock(&rtas_ibm_activate_firmware_lock);

	if (fwrc)
		pr_err("ibm,activate-firmware failed (%i)\n", fwrc);
}

/**
 * get_pseries_errorlog() - Find a specific pseries error log in an RTAS
 *                          extended event log.
 * @log: RTAS error/event log
 * @section_id: two character section identifier
 *
 * Return: A pointer to the specified errorlog or NULL if not found.
 */
noinstr struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log,
						      uint16_t section_id)
{
	struct rtas_ext_event_log_v6 *ext_log =
		(struct rtas_ext_event_log_v6 *)log->buffer;
	struct pseries_errorlog *sect;
	unsigned char *p, *log_end;
	uint32_t ext_log_length = rtas_error_extended_log_length(log);
	uint8_t log_format = rtas_ext_event_log_format(ext_log);
	uint32_t company_id = rtas_ext_event_company_id(ext_log);

	/* Check that we understand the format */
	if (ext_log_length < sizeof(struct rtas_ext_event_log_v6) ||
	    log_format != RTAS_V6EXT_LOG_FORMAT_EVENT_LOG ||
	    company_id != RTAS_V6EXT_COMPANY_ID_IBM)
		return NULL;

	log_end = log->buffer + ext_log_length;
	p = ext_log->vendor_log;

	while (p < log_end) {
		sect = (struct pseries_errorlog *)p;
		if (pseries_errorlog_id(sect) == section_id)
			return sect;
		p += pseries_errorlog_length(sect);
	}

	return NULL;
}

/*
 * The sys_rtas syscall, as originally designed, allows root to pass
 * arbitrary physical addresses to RTAS calls. A number of RTAS calls
 * can be abused to write to arbitrary memory and do other things that
 * are potentially harmful to system integrity, and thus should only
 * be used inside the kernel and not exposed to userspace.
 *
 * All known legitimate users of the sys_rtas syscall will only ever
 * pass addresses that fall within the RMO buffer, and use a known
 * subset of RTAS calls.
 *
 * Accordingly, we filter RTAS requests to check that the call is
 * permitted, and that provided pointers fall within the RMO buffer.
 * If a function is allowed to be invoked via the syscall, then its
 * entry in the rtas_functions table points to a rtas_filter that
 * describes its constraints, with the indexes of the parameters which
 * are expected to contain addresses and sizes of buffers allocated
 * inside the RMO buffer.
 */

static bool in_rmo_buf(u32 base, u32 end)
{
	return base >= rtas_rmo_buf &&
		base < (rtas_rmo_buf + RTAS_USER_REGION_SIZE) &&
		base <= end &&
		end >= rtas_rmo_buf &&
		end < (rtas_rmo_buf + RTAS_USER_REGION_SIZE);
}

static bool block_rtas_call(const struct rtas_function *func, int nargs,
			    struct rtas_args *args)
{
	const struct rtas_filter *f;
	const bool is_platform_dump =
		func == &rtas_function_table[RTAS_FNIDX__IBM_PLATFORM_DUMP];
	const bool is_config_conn =
		func == &rtas_function_table[RTAS_FNIDX__IBM_CONFIGURE_CONNECTOR];
	u32 base, size, end;

	/*
	 * Only functions with filters attached are allowed.
	 */
	f = func->filter;
	if (!f)
		goto err;
	/*
	 * And some functions aren't allowed on LE.
	 */
	if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) && func->banned_for_syscall_on_le)
		goto err;

	if (f->buf_idx1 != -1) {
		base = be32_to_cpu(args->args[f->buf_idx1]);
		if (f->size_idx1 != -1)
			size = be32_to_cpu(args->args[f->size_idx1]);
		else if (f->fixed_size)
			size = f->fixed_size;
		else
			size = 1;

		end = base + size - 1;

		/*
		 * Special case for ibm,platform-dump - NULL buffer
		 * address is used to indicate end of dump processing
		 */
		if (is_platform_dump && base == 0)
			return false;

		if (!in_rmo_buf(base, end))
			goto err;
	}

	if (f->buf_idx2 != -1) {
		base = be32_to_cpu(args->args[f->buf_idx2]);
		if (f->size_idx2 != -1)
			size = be32_to_cpu(args->args[f->size_idx2]);
		else if (f->fixed_size)
			size = f->fixed_size;
		else
			size = 1;
		end = base + size - 1;

		/*
		 * Special case for ibm,configure-connector where the
		 * address can be 0
		 */
		if (is_config_conn && base == 0)
			return false;

		if (!in_rmo_buf(base, end))
			goto err;
	}

	return false;
err:
	pr_err_ratelimited("sys_rtas: RTAS call blocked - exploit attempt?\n");
	pr_err_ratelimited("sys_rtas: %s nargs=%d (called by %s)\n",
			   func->name, nargs, current->comm);
	return true;
}

/* We assume to be passed big endian arguments */
SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
{
	const struct rtas_function *func;
	struct pin_cookie cookie;
	struct rtas_args args;
	unsigned long flags;
	char *buff_copy, *errbuf = NULL;
	int nargs, nret, token;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (!rtas.entry)
		return -EINVAL;

	if (copy_from_user(&args, uargs, 3 * sizeof(u32)) != 0)
		return -EFAULT;

	nargs = be32_to_cpu(args.nargs);
	nret  = be32_to_cpu(args.nret);
	token = be32_to_cpu(args.token);

	if (nargs >= ARRAY_SIZE(args.args)
	    || nret > ARRAY_SIZE(args.args)
	    || nargs + nret > ARRAY_SIZE(args.args))
		return -EINVAL;

	/* Copy in args. */
	if (copy_from_user(args.args, uargs->args,
			   nargs * sizeof(rtas_arg_t)) != 0)
		return -EFAULT;

	/*
	 * If this token doesn't correspond to a function the kernel
	 * understands, you're not allowed to call it.
	 */
	func = rtas_token_to_function_untrusted(token);
	if (!func)
		return -EINVAL;

	args.rets = &args.args[nargs];
	memset(args.rets, 0, nret * sizeof(rtas_arg_t));

	if (block_rtas_call(func, nargs, &args))
		return -EINVAL;

	if (token_is_restricted_errinjct(token)) {
		int err;

		err = security_locked_down(LOCKDOWN_RTAS_ERROR_INJECTION);
		if (err)
			return err;
	}

	/* Need to handle ibm,suspend_me call specially */
	if (token == rtas_function_token(RTAS_FN_IBM_SUSPEND_ME)) {

		/*
		 * rtas_ibm_suspend_me assumes the streamid handle is in cpu
		 * endian, or at least the hcall within it requires it.
		 */
		int rc = 0;
		u64 handle = ((u64)be32_to_cpu(args.args[0]) << 32)
		              | be32_to_cpu(args.args[1]);
		rc = rtas_syscall_dispatch_ibm_suspend_me(handle);
		if (rc == -EAGAIN)
			args.rets[0] = cpu_to_be32(RTAS_NOT_SUSPENDABLE);
		else if (rc == -EIO)
			args.rets[0] = cpu_to_be32(-1);
		else if (rc)
			return rc;
		goto copy_return;
	}

	buff_copy = get_errorlog_buffer();

	/*
	 * If this function has a mutex assigned to it, we must
	 * acquire it to avoid interleaving with any kernel-based uses
	 * of the same function. Kernel-based sequences acquire the
	 * appropriate mutex explicitly.
	 */
	if (func->lock)
		mutex_lock(func->lock);

	raw_spin_lock_irqsave(&rtas_lock, flags);
	cookie = lockdep_pin_lock(&rtas_lock);

	rtas_args = args;
	do_enter_rtas(&rtas_args);
	args = rtas_args;

	/* A -1 return code indicates that the last command couldn't
	   be completed due to a hardware error. */
	if (be32_to_cpu(args.rets[0]) == -1)
		errbuf = __fetch_rtas_last_error(buff_copy);

	lockdep_unpin_lock(&rtas_lock, cookie);
	raw_spin_unlock_irqrestore(&rtas_lock, flags);

	if (func->lock)
		mutex_unlock(func->lock);

	if (buff_copy) {
		if (errbuf)
			log_error(errbuf, ERR_TYPE_RTAS_LOG, 0);
		kfree(buff_copy);
	}

 copy_return:
	/* Copy out args. */
	if (copy_to_user(uargs->args + nargs,
			 args.args + nargs,
			 nret * sizeof(rtas_arg_t)) != 0)
		return -EFAULT;

	return 0;
}

static void __init rtas_function_table_init(void)
{
	struct property *prop;

	for (size_t i = 0; i < ARRAY_SIZE(rtas_function_table); ++i) {
		struct rtas_function *curr = &rtas_function_table[i];
		struct rtas_function *prior;
		int cmp;

		curr->token = RTAS_UNKNOWN_SERVICE;

		if (i == 0)
			continue;
		/*
		 * Ensure table is sorted correctly for binary search
		 * on function names.
		 */
		prior = &rtas_function_table[i - 1];

		cmp = strcmp(prior->name, curr->name);
		if (cmp < 0)
			continue;

		if (cmp == 0) {
			pr_err("'%s' has duplicate function table entries\n",
			       curr->name);
		} else {
			pr_err("function table unsorted: '%s' wrongly precedes '%s'\n",
			       prior->name, curr->name);
		}
	}

	for_each_property_of_node(rtas.dev, prop) {
		struct rtas_function *func;

		if (prop->length != sizeof(u32))
			continue;

		func = __rtas_name_to_function(prop->name);
		if (!func)
			continue;

		func->token = be32_to_cpup((__be32 *)prop->value);

		pr_debug("function %s has token %u\n", func->name, func->token);
	}
}

/*
 * Call early during boot, before mem init, to retrieve the RTAS
 * information from the device-tree and allocate the RMO buffer for userland
 * accesses.
 */
void __init rtas_initialize(void)
{
	unsigned long rtas_region = RTAS_INSTANTIATE_MAX;
	u32 base, size, entry;
	int no_base, no_size, no_entry;

	/* Get RTAS dev node and fill up our "rtas" structure with infos
	 * about it.
	 */
	rtas.dev = of_find_node_by_name(NULL, "rtas");
	if (!rtas.dev)
		return;

	no_base = of_property_read_u32(rtas.dev, "linux,rtas-base", &base);
	no_size = of_property_read_u32(rtas.dev, "rtas-size", &size);
	if (no_base || no_size) {
		of_node_put(rtas.dev);
		rtas.dev = NULL;
		return;
	}

	rtas.base = base;
	rtas.size = size;
	no_entry = of_property_read_u32(rtas.dev, "linux,rtas-entry", &entry);
	rtas.entry = no_entry ? rtas.base : entry;

	init_error_log_max();

	/* Must be called before any function token lookups */
	rtas_function_table_init();

	/*
	 * Discover this now to avoid a device tree lookup in the
	 * panic path.
	 */
	ibm_extended_os_term = of_property_read_bool(rtas.dev, "ibm,extended-os-term");

	/* If RTAS was found, allocate the RMO buffer for it and look for
	 * the stop-self token if any
	 */
#ifdef CONFIG_PPC64
	if (firmware_has_feature(FW_FEATURE_LPAR))
		rtas_region = min(ppc64_rma_size, RTAS_INSTANTIATE_MAX);
#endif
	rtas_rmo_buf = memblock_phys_alloc_range(RTAS_USER_REGION_SIZE, PAGE_SIZE,
						 0, rtas_region);
	if (!rtas_rmo_buf)
		panic("ERROR: RTAS: Failed to allocate %lx bytes below %pa\n",
		      PAGE_SIZE, &rtas_region);

	rtas_work_area_reserve_arena(rtas_region);
}

int __init early_init_dt_scan_rtas(unsigned long node,
		const char *uname, int depth, void *data)
{
	const u32 *basep, *entryp, *sizep;

	if (depth != 1 || strcmp(uname, "rtas") != 0)
		return 0;

	basep  = of_get_flat_dt_prop(node, "linux,rtas-base", NULL);
	entryp = of_get_flat_dt_prop(node, "linux,rtas-entry", NULL);
	sizep  = of_get_flat_dt_prop(node, "rtas-size", NULL);

#ifdef CONFIG_PPC64
	/* need this feature to decide the crashkernel offset */
	if (of_get_flat_dt_prop(node, "ibm,hypertas-functions", NULL))
		powerpc_firmware_features |= FW_FEATURE_LPAR;
#endif

	if (basep && entryp && sizep) {
		rtas.base = *basep;
		rtas.entry = *entryp;
		rtas.size = *sizep;
	}

#ifdef CONFIG_UDBG_RTAS_CONSOLE
	basep = of_get_flat_dt_prop(node, "put-term-char", NULL);
	if (basep)
		rtas_putchar_token = *basep;

	basep = of_get_flat_dt_prop(node, "get-term-char", NULL);
	if (basep)
		rtas_getchar_token = *basep;

	if (rtas_putchar_token != RTAS_UNKNOWN_SERVICE &&
	    rtas_getchar_token != RTAS_UNKNOWN_SERVICE)
		udbg_init_rtas_console();

#endif

	/* break now */
	return 1;
}

static DEFINE_RAW_SPINLOCK(timebase_lock);
static u64 timebase = 0;

void rtas_give_timebase(void)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&timebase_lock, flags);
	hard_irq_disable();
	rtas_call(rtas_function_token(RTAS_FN_FREEZE_TIME_BASE), 0, 1, NULL);
	timebase = get_tb();
	raw_spin_unlock(&timebase_lock);

	while (timebase)
		barrier();
	rtas_call(rtas_function_token(RTAS_FN_THAW_TIME_BASE), 0, 1, NULL);
	local_irq_restore(flags);
}

void rtas_take_timebase(void)
{
	while (!timebase)
		barrier();
	raw_spin_lock(&timebase_lock);
	set_tb(timebase >> 32, timebase & 0xffffffff);
	timebase = 0;
	raw_spin_unlock(&timebase_lock);
}