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
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* scsi_error.c Copyright (C) 1997 Eric Youngdale
*
* SCSI error/timeout handling
* Initial versions: Eric Youngdale. Based upon conversations with
* Leonard Zubkoff and David Miller at Linux Expo,
* ideas originating from all over the place.
*
* Restructured scsi_unjam_host and associated functions.
* September 04, 2002 Mike Anderson (andmike@us.ibm.com)
*
* Forward port of Russell King's (rmk@arm.linux.org.uk) changes and
* minor cleanups.
* September 30, 2002 Mike Anderson (andmike@us.ibm.com)
*/
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/gfp.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/kernel.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/interrupt.h>
#include <linux/blkdev.h>
#include <linux/delay.h>
#include <linux/jiffies.h>
#include <scsi/scsi.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_dbg.h>
#include <scsi/scsi_device.h>
#include <scsi/scsi_driver.h>
#include <scsi/scsi_eh.h>
#include <scsi/scsi_common.h>
#include <scsi/scsi_transport.h>
#include <scsi/scsi_host.h>
#include <scsi/scsi_ioctl.h>
#include <scsi/scsi_dh.h>
#include <scsi/scsi_devinfo.h>
#include <scsi/sg.h>
#include "scsi_priv.h"
#include "scsi_logging.h"
#include "scsi_transport_api.h"
#include <trace/events/scsi.h>
#include <asm/unaligned.h>
/*
* These should *probably* be handled by the host itself.
* Since it is allowed to sleep, it probably should.
*/
#define BUS_RESET_SETTLE_TIME (10)
#define HOST_RESET_SETTLE_TIME (10)
static int scsi_eh_try_stu(struct scsi_cmnd *scmd);
static enum scsi_disposition scsi_try_to_abort_cmd(struct scsi_host_template *,
struct scsi_cmnd *);
void scsi_eh_wakeup(struct Scsi_Host *shost)
{
lockdep_assert_held(shost->host_lock);
if (scsi_host_busy(shost) == shost->host_failed) {
trace_scsi_eh_wakeup(shost);
wake_up_process(shost->ehandler);
SCSI_LOG_ERROR_RECOVERY(5, shost_printk(KERN_INFO, shost,
"Waking error handler thread\n"));
}
}
/**
* scsi_schedule_eh - schedule EH for SCSI host
* @shost: SCSI host to invoke error handling on.
*
* Schedule SCSI EH without scmd.
*/
void scsi_schedule_eh(struct Scsi_Host *shost)
{
unsigned long flags;
spin_lock_irqsave(shost->host_lock, flags);
if (scsi_host_set_state(shost, SHOST_RECOVERY) == 0 ||
scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY) == 0) {
shost->host_eh_scheduled++;
scsi_eh_wakeup(shost);
}
spin_unlock_irqrestore(shost->host_lock, flags);
}
EXPORT_SYMBOL_GPL(scsi_schedule_eh);
static int scsi_host_eh_past_deadline(struct Scsi_Host *shost)
{
if (!shost->last_reset || shost->eh_deadline == -1)
return 0;
/*
* 32bit accesses are guaranteed to be atomic
* (on all supported architectures), so instead
* of using a spinlock we can as well double check
* if eh_deadline has been set to 'off' during the
* time_before call.
*/
if (time_before(jiffies, shost->last_reset + shost->eh_deadline) &&
shost->eh_deadline > -1)
return 0;
return 1;
}
static bool scsi_cmd_retry_allowed(struct scsi_cmnd *cmd)
{
if (cmd->allowed == SCSI_CMD_RETRIES_NO_LIMIT)
return true;
return ++cmd->retries <= cmd->allowed;
}
static bool scsi_eh_should_retry_cmd(struct scsi_cmnd *cmd)
{
struct scsi_device *sdev = cmd->device;
struct Scsi_Host *host = sdev->host;
if (host->hostt->eh_should_retry_cmd)
return host->hostt->eh_should_retry_cmd(cmd);
return true;
}
/**
* scmd_eh_abort_handler - Handle command aborts
* @work: command to be aborted.
*
* Note: this function must be called only for a command that has timed out.
* Because the block layer marks a request as complete before it calls
* scsi_timeout(), a .scsi_done() call from the LLD for a command that has
* timed out do not have any effect. Hence it is safe to call
* scsi_finish_command() from this function.
*/
void
scmd_eh_abort_handler(struct work_struct *work)
{
struct scsi_cmnd *scmd =
container_of(work, struct scsi_cmnd, abort_work.work);
struct scsi_device *sdev = scmd->device;
struct Scsi_Host *shost = sdev->host;
enum scsi_disposition rtn;
unsigned long flags;
if (scsi_host_eh_past_deadline(shost)) {
SCSI_LOG_ERROR_RECOVERY(3,
scmd_printk(KERN_INFO, scmd,
"eh timeout, not aborting\n"));
goto out;
}
SCSI_LOG_ERROR_RECOVERY(3,
scmd_printk(KERN_INFO, scmd,
"aborting command\n"));
rtn = scsi_try_to_abort_cmd(shost->hostt, scmd);
if (rtn != SUCCESS) {
SCSI_LOG_ERROR_RECOVERY(3,
scmd_printk(KERN_INFO, scmd,
"cmd abort %s\n",
(rtn == FAST_IO_FAIL) ?
"not send" : "failed"));
goto out;
}
set_host_byte(scmd, DID_TIME_OUT);
if (scsi_host_eh_past_deadline(shost)) {
SCSI_LOG_ERROR_RECOVERY(3,
scmd_printk(KERN_INFO, scmd,
"eh timeout, not retrying "
"aborted command\n"));
goto out;
}
spin_lock_irqsave(shost->host_lock, flags);
list_del_init(&scmd->eh_entry);
/*
* If the abort succeeds, and there is no further
* EH action, clear the ->last_reset time.
*/
if (list_empty(&shost->eh_abort_list) &&
list_empty(&shost->eh_cmd_q))
if (shost->eh_deadline != -1)
shost->last_reset = 0;
spin_unlock_irqrestore(shost->host_lock, flags);
if (!scsi_noretry_cmd(scmd) &&
scsi_cmd_retry_allowed(scmd) &&
scsi_eh_should_retry_cmd(scmd)) {
SCSI_LOG_ERROR_RECOVERY(3,
scmd_printk(KERN_WARNING, scmd,
"retry aborted command\n"));
scsi_queue_insert(scmd, SCSI_MLQUEUE_EH_RETRY);
} else {
SCSI_LOG_ERROR_RECOVERY(3,
scmd_printk(KERN_WARNING, scmd,
"finish aborted command\n"));
scsi_finish_command(scmd);
}
return;
out:
spin_lock_irqsave(shost->host_lock, flags);
list_del_init(&scmd->eh_entry);
spin_unlock_irqrestore(shost->host_lock, flags);
scsi_eh_scmd_add(scmd);
}
/**
* scsi_abort_command - schedule a command abort
* @scmd: scmd to abort.
*
* We only need to abort commands after a command timeout
*/
static int
scsi_abort_command(struct scsi_cmnd *scmd)
{
struct scsi_device *sdev = scmd->device;
struct Scsi_Host *shost = sdev->host;
unsigned long flags;
if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) {
/*
* Retry after abort failed, escalate to next level.
*/
SCSI_LOG_ERROR_RECOVERY(3,
scmd_printk(KERN_INFO, scmd,
"previous abort failed\n"));
BUG_ON(delayed_work_pending(&scmd->abort_work));
return FAILED;
}
spin_lock_irqsave(shost->host_lock, flags);
if (shost->eh_deadline != -1 && !shost->last_reset)
shost->last_reset = jiffies;
BUG_ON(!list_empty(&scmd->eh_entry));
list_add_tail(&scmd->eh_entry, &shost->eh_abort_list);
spin_unlock_irqrestore(shost->host_lock, flags);
scmd->eh_eflags |= SCSI_EH_ABORT_SCHEDULED;
SCSI_LOG_ERROR_RECOVERY(3,
scmd_printk(KERN_INFO, scmd, "abort scheduled\n"));
queue_delayed_work(shost->tmf_work_q, &scmd->abort_work, HZ / 100);
return SUCCESS;
}
/**
* scsi_eh_reset - call into ->eh_action to reset internal counters
* @scmd: scmd to run eh on.
*
* The scsi driver might be carrying internal state about the
* devices, so we need to call into the driver to reset the
* internal state once the error handler is started.
*/
static void scsi_eh_reset(struct scsi_cmnd *scmd)
{
if (!blk_rq_is_passthrough(scsi_cmd_to_rq(scmd))) {
struct scsi_driver *sdrv = scsi_cmd_to_driver(scmd);
if (sdrv->eh_reset)
sdrv->eh_reset(scmd);
}
}
static void scsi_eh_inc_host_failed(struct rcu_head *head)
{
struct scsi_cmnd *scmd = container_of(head, typeof(*scmd), rcu);
struct Scsi_Host *shost = scmd->device->host;
unsigned long flags;
spin_lock_irqsave(shost->host_lock, flags);
shost->host_failed++;
scsi_eh_wakeup(shost);
spin_unlock_irqrestore(shost->host_lock, flags);
}
/**
* scsi_eh_scmd_add - add scsi cmd to error handling.
* @scmd: scmd to run eh on.
*/
void scsi_eh_scmd_add(struct scsi_cmnd *scmd)
{
struct Scsi_Host *shost = scmd->device->host;
unsigned long flags;
int ret;
WARN_ON_ONCE(!shost->ehandler);
spin_lock_irqsave(shost->host_lock, flags);
if (scsi_host_set_state(shost, SHOST_RECOVERY)) {
ret = scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY);
WARN_ON_ONCE(ret);
}
if (shost->eh_deadline != -1 && !shost->last_reset)
shost->last_reset = jiffies;
scsi_eh_reset(scmd);
list_add_tail(&scmd->eh_entry, &shost->eh_cmd_q);
spin_unlock_irqrestore(shost->host_lock, flags);
/*
* Ensure that all tasks observe the host state change before the
* host_failed change.
*/
call_rcu(&scmd->rcu, scsi_eh_inc_host_failed);
}
/**
* scsi_timeout - Timeout function for normal scsi commands.
* @req: request that is timing out.
*
* Notes:
* We do not need to lock this. There is the potential for a race
* only in that the normal completion handling might run, but if the
* normal completion function determines that the timer has already
* fired, then it mustn't do anything.
*/
enum blk_eh_timer_return scsi_timeout(struct request *req)
{
struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(req);
enum blk_eh_timer_return rtn = BLK_EH_DONE;
struct Scsi_Host *host = scmd->device->host;
trace_scsi_dispatch_cmd_timeout(scmd);
scsi_log_completion(scmd, TIMEOUT_ERROR);
if (host->eh_deadline != -1 && !host->last_reset)
host->last_reset = jiffies;
if (host->hostt->eh_timed_out)
rtn = host->hostt->eh_timed_out(scmd);
if (rtn == BLK_EH_DONE) {
/*
* Set the command to complete first in order to prevent a real
* completion from releasing the command while error handling
* is using it. If the command was already completed, then the
* lower level driver beat the timeout handler, and it is safe
* to return without escalating error recovery.
*
* If timeout handling lost the race to a real completion, the
* block layer may ignore that due to a fake timeout injection,
* so return RESET_TIMER to allow error handling another shot
* at this command.
*/
if (test_and_set_bit(SCMD_STATE_COMPLETE, &scmd->state))
return BLK_EH_RESET_TIMER;
if (scsi_abort_command(scmd) != SUCCESS) {
set_host_byte(scmd, DID_TIME_OUT);
scsi_eh_scmd_add(scmd);
}
}
return rtn;
}
/**
* scsi_block_when_processing_errors - Prevent cmds from being queued.
* @sdev: Device on which we are performing recovery.
*
* Description:
* We block until the host is out of error recovery, and then check to
* see whether the host or the device is offline.
*
* Return value:
* 0 when dev was taken offline by error recovery. 1 OK to proceed.
*/
int scsi_block_when_processing_errors(struct scsi_device *sdev)
{
int online;
wait_event(sdev->host->host_wait, !scsi_host_in_recovery(sdev->host));
online = scsi_device_online(sdev);
return online;
}
EXPORT_SYMBOL(scsi_block_when_processing_errors);
#ifdef CONFIG_SCSI_LOGGING
/**
* scsi_eh_prt_fail_stats - Log info on failures.
* @shost: scsi host being recovered.
* @work_q: Queue of scsi cmds to process.
*/
static inline void scsi_eh_prt_fail_stats(struct Scsi_Host *shost,
struct list_head *work_q)
{
struct scsi_cmnd *scmd;
struct scsi_device *sdev;
int total_failures = 0;
int cmd_failed = 0;
int cmd_cancel = 0;
int devices_failed = 0;
shost_for_each_device(sdev, shost) {
list_for_each_entry(scmd, work_q, eh_entry) {
if (scmd->device == sdev) {
++total_failures;
if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED)
++cmd_cancel;
else
++cmd_failed;
}
}
if (cmd_cancel || cmd_failed) {
SCSI_LOG_ERROR_RECOVERY(3,
shost_printk(KERN_INFO, shost,
"%s: cmds failed: %d, cancel: %d\n",
__func__, cmd_failed,
cmd_cancel));
cmd_cancel = 0;
cmd_failed = 0;
++devices_failed;
}
}
SCSI_LOG_ERROR_RECOVERY(2, shost_printk(KERN_INFO, shost,
"Total of %d commands on %d"
" devices require eh work\n",
total_failures, devices_failed));
}
#endif
/**
* scsi_report_lun_change - Set flag on all *other* devices on the same target
* to indicate that a UNIT ATTENTION is expected.
* @sdev: Device reporting the UNIT ATTENTION
*/
static void scsi_report_lun_change(struct scsi_device *sdev)
{
sdev->sdev_target->expecting_lun_change = 1;
}
/**
* scsi_report_sense - Examine scsi sense information and log messages for
* certain conditions, also issue uevents for some of them.
* @sdev: Device reporting the sense code
* @sshdr: sshdr to be examined
*/
static void scsi_report_sense(struct scsi_device *sdev,
struct scsi_sense_hdr *sshdr)
{
enum scsi_device_event evt_type = SDEV_EVT_MAXBITS; /* i.e. none */
if (sshdr->sense_key == UNIT_ATTENTION) {
if (sshdr->asc == 0x3f && sshdr->ascq == 0x03) {
evt_type = SDEV_EVT_INQUIRY_CHANGE_REPORTED;
sdev_printk(KERN_WARNING, sdev,
"Inquiry data has changed");
} else if (sshdr->asc == 0x3f && sshdr->ascq == 0x0e) {
evt_type = SDEV_EVT_LUN_CHANGE_REPORTED;
scsi_report_lun_change(sdev);
sdev_printk(KERN_WARNING, sdev,
"LUN assignments on this target have "
"changed. The Linux SCSI layer does not "
"automatically remap LUN assignments.\n");
} else if (sshdr->asc == 0x3f)
sdev_printk(KERN_WARNING, sdev,
"Operating parameters on this target have "
"changed. The Linux SCSI layer does not "
"automatically adjust these parameters.\n");
if (sshdr->asc == 0x38 && sshdr->ascq == 0x07) {
evt_type = SDEV_EVT_SOFT_THRESHOLD_REACHED_REPORTED;
sdev_printk(KERN_WARNING, sdev,
"Warning! Received an indication that the "
"LUN reached a thin provisioning soft "
"threshold.\n");
}
if (sshdr->asc == 0x29) {
evt_type = SDEV_EVT_POWER_ON_RESET_OCCURRED;
/*
* Do not print message if it is an expected side-effect
* of runtime PM.
*/
if (!sdev->silence_suspend)
sdev_printk(KERN_WARNING, sdev,
"Power-on or device reset occurred\n");
}
if (sshdr->asc == 0x2a && sshdr->ascq == 0x01) {
evt_type = SDEV_EVT_MODE_PARAMETER_CHANGE_REPORTED;
sdev_printk(KERN_WARNING, sdev,
"Mode parameters changed");
} else if (sshdr->asc == 0x2a && sshdr->ascq == 0x06) {
evt_type = SDEV_EVT_ALUA_STATE_CHANGE_REPORTED;
sdev_printk(KERN_WARNING, sdev,
"Asymmetric access state changed");
} else if (sshdr->asc == 0x2a && sshdr->ascq == 0x09) {
evt_type = SDEV_EVT_CAPACITY_CHANGE_REPORTED;
sdev_printk(KERN_WARNING, sdev,
"Capacity data has changed");
} else if (sshdr->asc == 0x2a)
sdev_printk(KERN_WARNING, sdev,
"Parameters changed");
}
if (evt_type != SDEV_EVT_MAXBITS) {
set_bit(evt_type, sdev->pending_events);
schedule_work(&sdev->event_work);
}
}
/**
* scsi_check_sense - Examine scsi cmd sense
* @scmd: Cmd to have sense checked.
*
* Return value:
* SUCCESS or FAILED or NEEDS_RETRY or ADD_TO_MLQUEUE
*
* Notes:
* When a deferred error is detected the current command has
* not been executed and needs retrying.
*/
enum scsi_disposition scsi_check_sense(struct scsi_cmnd *scmd)
{
struct scsi_device *sdev = scmd->device;
struct scsi_sense_hdr sshdr;
if (! scsi_command_normalize_sense(scmd, &sshdr))
return FAILED; /* no valid sense data */
scsi_report_sense(sdev, &sshdr);
if (scsi_sense_is_deferred(&sshdr))
return NEEDS_RETRY;
if (sdev->handler && sdev->handler->check_sense) {
enum scsi_disposition rc;
rc = sdev->handler->check_sense(sdev, &sshdr);
if (rc != SCSI_RETURN_NOT_HANDLED)
return rc;
/* handler does not care. Drop down to default handling */
}
if (scmd->cmnd[0] == TEST_UNIT_READY &&
scmd->submitter != SUBMITTED_BY_SCSI_ERROR_HANDLER)
/*
* nasty: for mid-layer issued TURs, we need to return the
* actual sense data without any recovery attempt. For eh
* issued ones, we need to try to recover and interpret
*/
return SUCCESS;
/*
* Previous logic looked for FILEMARK, EOM or ILI which are
* mainly associated with tapes and returned SUCCESS.
*/
if (sshdr.response_code == 0x70) {
/* fixed format */
if (scmd->sense_buffer[2] & 0xe0)
return SUCCESS;
} else {
/*
* descriptor format: look for "stream commands sense data
* descriptor" (see SSC-3). Assume single sense data
* descriptor. Ignore ILI from SBC-2 READ LONG and WRITE LONG.
*/
if ((sshdr.additional_length > 3) &&
(scmd->sense_buffer[8] == 0x4) &&
(scmd->sense_buffer[11] & 0xe0))
return SUCCESS;
}
switch (sshdr.sense_key) {
case NO_SENSE:
return SUCCESS;
case RECOVERED_ERROR:
return /* soft_error */ SUCCESS;
case ABORTED_COMMAND:
if (sshdr.asc == 0x10) /* DIF */
return SUCCESS;
if (sshdr.asc == 0x44 && sdev->sdev_bflags & BLIST_RETRY_ITF)
return ADD_TO_MLQUEUE;
if (sshdr.asc == 0xc1 && sshdr.ascq == 0x01 &&
sdev->sdev_bflags & BLIST_RETRY_ASC_C1)
return ADD_TO_MLQUEUE;
return NEEDS_RETRY;
case NOT_READY:
case UNIT_ATTENTION:
/*
* if we are expecting a cc/ua because of a bus reset that we
* performed, treat this just as a retry. otherwise this is
* information that we should pass up to the upper-level driver
* so that we can deal with it there.
*/
if (scmd->device->expecting_cc_ua) {
/*
* Because some device does not queue unit
* attentions correctly, we carefully check
* additional sense code and qualifier so as
* not to squash media change unit attention.
*/
if (sshdr.asc != 0x28 || sshdr.ascq != 0x00) {
scmd->device->expecting_cc_ua = 0;
return NEEDS_RETRY;
}
}
/*
* we might also expect a cc/ua if another LUN on the target
* reported a UA with an ASC/ASCQ of 3F 0E -
* REPORTED LUNS DATA HAS CHANGED.
*/
if (scmd->device->sdev_target->expecting_lun_change &&
sshdr.asc == 0x3f && sshdr.ascq == 0x0e)
return NEEDS_RETRY;
/*
* if the device is in the process of becoming ready, we
* should retry.
*/
if ((sshdr.asc == 0x04) && (sshdr.ascq == 0x01))
return NEEDS_RETRY;
/*
* if the device is not started, we need to wake
* the error handler to start the motor
*/
if (scmd->device->allow_restart &&
(sshdr.asc == 0x04) && (sshdr.ascq == 0x02))
return FAILED;
/*
* Pass the UA upwards for a determination in the completion
* functions.
*/
return SUCCESS;
/* these are not supported */
case DATA_PROTECT:
if (sshdr.asc == 0x27 && sshdr.ascq == 0x07) {
/* Thin provisioning hard threshold reached */
set_host_byte(scmd, DID_ALLOC_FAILURE);
return SUCCESS;
}
fallthrough;
case COPY_ABORTED:
case VOLUME_OVERFLOW:
case MISCOMPARE:
case BLANK_CHECK:
set_host_byte(scmd, DID_TARGET_FAILURE);
return SUCCESS;
case MEDIUM_ERROR:
if (sshdr.asc == 0x11 || /* UNRECOVERED READ ERR */
sshdr.asc == 0x13 || /* AMNF DATA FIELD */
sshdr.asc == 0x14) { /* RECORD NOT FOUND */
set_host_byte(scmd, DID_MEDIUM_ERROR);
return SUCCESS;
}
return NEEDS_RETRY;
case HARDWARE_ERROR:
if (scmd->device->retry_hwerror)
return ADD_TO_MLQUEUE;
else
set_host_byte(scmd, DID_TARGET_FAILURE);
fallthrough;
case ILLEGAL_REQUEST:
if (sshdr.asc == 0x20 || /* Invalid command operation code */
sshdr.asc == 0x21 || /* Logical block address out of range */
sshdr.asc == 0x22 || /* Invalid function */
sshdr.asc == 0x24 || /* Invalid field in cdb */
sshdr.asc == 0x26 || /* Parameter value invalid */
sshdr.asc == 0x27) { /* Write protected */
set_host_byte(scmd, DID_TARGET_FAILURE);
}
return SUCCESS;
default:
return SUCCESS;
}
}
EXPORT_SYMBOL_GPL(scsi_check_sense);
static void scsi_handle_queue_ramp_up(struct scsi_device *sdev)
{
struct scsi_host_template *sht = sdev->host->hostt;
struct scsi_device *tmp_sdev;
if (!sht->track_queue_depth ||
sdev->queue_depth >= sdev->max_queue_depth)
return;
if (time_before(jiffies,
sdev->last_queue_ramp_up + sdev->queue_ramp_up_period))
return;
if (time_before(jiffies,
sdev->last_queue_full_time + sdev->queue_ramp_up_period))
return;
/*
* Walk all devices of a target and do
* ramp up on them.
*/
shost_for_each_device(tmp_sdev, sdev->host) {
if (tmp_sdev->channel != sdev->channel ||
tmp_sdev->id != sdev->id ||
tmp_sdev->queue_depth == sdev->max_queue_depth)
continue;
scsi_change_queue_depth(tmp_sdev, tmp_sdev->queue_depth + 1);
sdev->last_queue_ramp_up = jiffies;
}
}
static void scsi_handle_queue_full(struct scsi_device *sdev)
{
struct scsi_host_template *sht = sdev->host->hostt;
struct scsi_device *tmp_sdev;
if (!sht->track_queue_depth)
return;
shost_for_each_device(tmp_sdev, sdev->host) {
if (tmp_sdev->channel != sdev->channel ||
tmp_sdev->id != sdev->id)
continue;
/*
* We do not know the number of commands that were at
* the device when we got the queue full so we start
* from the highest possible value and work our way down.
*/
scsi_track_queue_full(tmp_sdev, tmp_sdev->queue_depth - 1);
}
}
/**
* scsi_eh_completed_normally - Disposition a eh cmd on return from LLD.
* @scmd: SCSI cmd to examine.
*
* Notes:
* This is *only* called when we are examining the status of commands
* queued during error recovery. the main difference here is that we
* don't allow for the possibility of retries here, and we are a lot
* more restrictive about what we consider acceptable.
*/
static enum scsi_disposition scsi_eh_completed_normally(struct scsi_cmnd *scmd)
{
/*
* first check the host byte, to see if there is anything in there
* that would indicate what we need to do.
*/
if (host_byte(scmd->result) == DID_RESET) {
/*
* rats. we are already in the error handler, so we now
* get to try and figure out what to do next. if the sense
* is valid, we have a pretty good idea of what to do.
* if not, we mark it as FAILED.
*/
return scsi_check_sense(scmd);
}
if (host_byte(scmd->result) != DID_OK)
return FAILED;
/*
* now, check the status byte to see if this indicates
* anything special.
*/
switch (get_status_byte(scmd)) {
case SAM_STAT_GOOD:
scsi_handle_queue_ramp_up(scmd->device);
fallthrough;
case SAM_STAT_COMMAND_TERMINATED:
return SUCCESS;
case SAM_STAT_CHECK_CONDITION:
return scsi_check_sense(scmd);
case SAM_STAT_CONDITION_MET:
case SAM_STAT_INTERMEDIATE:
case SAM_STAT_INTERMEDIATE_CONDITION_MET:
/*
* who knows? FIXME(eric)
*/
return SUCCESS;
case SAM_STAT_RESERVATION_CONFLICT:
if (scmd->cmnd[0] == TEST_UNIT_READY)
/* it is a success, we probed the device and
* found it */
return SUCCESS;
/* otherwise, we failed to send the command */
return FAILED;
case SAM_STAT_TASK_SET_FULL:
scsi_handle_queue_full(scmd->device);
fallthrough;
case SAM_STAT_BUSY:
return NEEDS_RETRY;
default:
return FAILED;
}
return FAILED;
}
/**
* scsi_eh_done - Completion function for error handling.
* @scmd: Cmd that is done.
*/
void scsi_eh_done(struct scsi_cmnd *scmd)
{
struct completion *eh_action;
SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd,
"%s result: %x\n", __func__, scmd->result));
eh_action = scmd->device->host->eh_action;
if (eh_action)
complete(eh_action);
}
/**
* scsi_try_host_reset - ask host adapter to reset itself
* @scmd: SCSI cmd to send host reset.
*/
static enum scsi_disposition scsi_try_host_reset(struct scsi_cmnd *scmd)
{
unsigned long flags;
enum scsi_disposition rtn;
struct Scsi_Host *host = scmd->device->host;
struct scsi_host_template *hostt = host->hostt;
SCSI_LOG_ERROR_RECOVERY(3,
shost_printk(KERN_INFO, host, "Snd Host RST\n"));
if (!hostt->eh_host_reset_handler)
return FAILED;
rtn = hostt->eh_host_reset_handler(scmd);
if (rtn == SUCCESS) {
if (!hostt->skip_settle_delay)
ssleep(HOST_RESET_SETTLE_TIME);
spin_lock_irqsave(host->host_lock, flags);
scsi_report_bus_reset(host, scmd_channel(scmd));
spin_unlock_irqrestore(host->host_lock, flags);
}
return rtn;
}
/**
* scsi_try_bus_reset - ask host to perform a bus reset
* @scmd: SCSI cmd to send bus reset.
*/
static enum scsi_disposition scsi_try_bus_reset(struct scsi_cmnd *scmd)
{
unsigned long flags;
enum scsi_disposition rtn;
struct Scsi_Host *host = scmd->device->host;
struct scsi_host_template *hostt = host->hostt;
SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd,
"%s: Snd Bus RST\n", __func__));
if (!hostt->eh_bus_reset_handler)
return FAILED;
rtn = hostt->eh_bus_reset_handler(scmd);
if (rtn == SUCCESS) {
if (!hostt->skip_settle_delay)
ssleep(BUS_RESET_SETTLE_TIME);
spin_lock_irqsave(host->host_lock, flags);
scsi_report_bus_reset(host, scmd_channel(scmd));
spin_unlock_irqrestore(host->host_lock, flags);
}
return rtn;
}
static void __scsi_report_device_reset(struct scsi_device *sdev, void *data)
{
sdev->was_reset = 1;
sdev->expecting_cc_ua = 1;
}
/**
* scsi_try_target_reset - Ask host to perform a target reset
* @scmd: SCSI cmd used to send a target reset
*
* Notes:
* There is no timeout for this operation. if this operation is
* unreliable for a given host, then the host itself needs to put a
* timer on it, and set the host back to a consistent state prior to
* returning.
*/
static enum scsi_disposition scsi_try_target_reset(struct scsi_cmnd *scmd)
{
unsigned long flags;
enum scsi_disposition rtn;
struct Scsi_Host *host = scmd->device->host;
struct scsi_host_template *hostt = host->hostt;
if (!hostt->eh_target_reset_handler)
return FAILED;
rtn = hostt->eh_target_reset_handler(scmd);
if (rtn == SUCCESS) {
spin_lock_irqsave(host->host_lock, flags);
__starget_for_each_device(scsi_target(scmd->device), NULL,
__scsi_report_device_reset);
spin_unlock_irqrestore(host->host_lock, flags);
}
return rtn;
}
/**
* scsi_try_bus_device_reset - Ask host to perform a BDR on a dev
* @scmd: SCSI cmd used to send BDR
*
* Notes:
* There is no timeout for this operation. if this operation is
* unreliable for a given host, then the host itself needs to put a
* timer on it, and set the host back to a consistent state prior to
* returning.
*/
static enum scsi_disposition scsi_try_bus_device_reset(struct scsi_cmnd *scmd)
{
enum scsi_disposition rtn;
struct scsi_host_template *hostt = scmd->device->host->hostt;
if (!hostt->eh_device_reset_handler)
return FAILED;
rtn = hostt->eh_device_reset_handler(scmd);
if (rtn == SUCCESS)
__scsi_report_device_reset(scmd->device, NULL);
return rtn;
}
/**
* scsi_try_to_abort_cmd - Ask host to abort a SCSI command
* @hostt: SCSI driver host template
* @scmd: SCSI cmd used to send a target reset
*
* Return value:
* SUCCESS, FAILED, or FAST_IO_FAIL
*
* Notes:
* SUCCESS does not necessarily indicate that the command
* has been aborted; it only indicates that the LLDDs
* has cleared all references to that command.
* LLDDs should return FAILED only if an abort was required
* but could not be executed. LLDDs should return FAST_IO_FAIL
* if the device is temporarily unavailable (eg due to a
* link down on FibreChannel)
*/
static enum scsi_disposition
scsi_try_to_abort_cmd(struct scsi_host_template *hostt, struct scsi_cmnd *scmd)
{
if (!hostt->eh_abort_handler)
return FAILED;
return hostt->eh_abort_handler(scmd);
}
static void scsi_abort_eh_cmnd(struct scsi_cmnd *scmd)
{
if (scsi_try_to_abort_cmd(scmd->device->host->hostt, scmd) != SUCCESS)
if (scsi_try_bus_device_reset(scmd) != SUCCESS)
if (scsi_try_target_reset(scmd) != SUCCESS)
if (scsi_try_bus_reset(scmd) != SUCCESS)
scsi_try_host_reset(scmd);
}
/**
* scsi_eh_prep_cmnd - Save a scsi command info as part of error recovery
* @scmd: SCSI command structure to hijack
* @ses: structure to save restore information
* @cmnd: CDB to send. Can be NULL if no new cmnd is needed
* @cmnd_size: size in bytes of @cmnd (must be <= MAX_COMMAND_SIZE)
* @sense_bytes: size of sense data to copy. or 0 (if != 0 @cmnd is ignored)
*
* This function is used to save a scsi command information before re-execution
* as part of the error recovery process. If @sense_bytes is 0 the command
* sent must be one that does not transfer any data. If @sense_bytes != 0
* @cmnd is ignored and this functions sets up a REQUEST_SENSE command
* and cmnd buffers to read @sense_bytes into @scmd->sense_buffer.
*/
void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses,
unsigned char *cmnd, int cmnd_size, unsigned sense_bytes)
{
struct scsi_device *sdev = scmd->device;
/*
* We need saved copies of a number of fields - this is because
* error handling may need to overwrite these with different values
* to run different commands, and once error handling is complete,
* we will need to restore these values prior to running the actual
* command.
*/
ses->cmd_len = scmd->cmd_len;
ses->data_direction = scmd->sc_data_direction;
ses->sdb = scmd->sdb;
ses->result = scmd->result;
ses->resid_len = scmd->resid_len;
ses->underflow = scmd->underflow;
ses->prot_op = scmd->prot_op;
ses->eh_eflags = scmd->eh_eflags;
scmd->prot_op = SCSI_PROT_NORMAL;
scmd->eh_eflags = 0;
memcpy(ses->cmnd, scmd->cmnd, sizeof(ses->cmnd));
memset(scmd->cmnd, 0, sizeof(scmd->cmnd));
memset(&scmd->sdb, 0, sizeof(scmd->sdb));
scmd->result = 0;
scmd->resid_len = 0;
if (sense_bytes) {
scmd->sdb.length = min_t(unsigned, SCSI_SENSE_BUFFERSIZE,
sense_bytes);
sg_init_one(&ses->sense_sgl, scmd->sense_buffer,
scmd->sdb.length);
scmd->sdb.table.sgl = &ses->sense_sgl;
scmd->sc_data_direction = DMA_FROM_DEVICE;
scmd->sdb.table.nents = scmd->sdb.table.orig_nents = 1;
scmd->cmnd[0] = REQUEST_SENSE;
scmd->cmnd[4] = scmd->sdb.length;
scmd->cmd_len = COMMAND_SIZE(scmd->cmnd[0]);
} else {
scmd->sc_data_direction = DMA_NONE;
if (cmnd) {
BUG_ON(cmnd_size > sizeof(scmd->cmnd));
memcpy(scmd->cmnd, cmnd, cmnd_size);
scmd->cmd_len = COMMAND_SIZE(scmd->cmnd[0]);
}
}
scmd->underflow = 0;
if (sdev->scsi_level <= SCSI_2 && sdev->scsi_level != SCSI_UNKNOWN)
scmd->cmnd[1] = (scmd->cmnd[1] & 0x1f) |
(sdev->lun << 5 & 0xe0);
/*
* Zero the sense buffer. The scsi spec mandates that any
* untransferred sense data should be interpreted as being zero.
*/
memset(scmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE);
}
EXPORT_SYMBOL(scsi_eh_prep_cmnd);
/**
* scsi_eh_restore_cmnd - Restore a scsi command info as part of error recovery
* @scmd: SCSI command structure to restore
* @ses: saved information from a coresponding call to scsi_eh_prep_cmnd
*
* Undo any damage done by above scsi_eh_prep_cmnd().
*/
void scsi_eh_restore_cmnd(struct scsi_cmnd* scmd, struct scsi_eh_save *ses)
{
/*
* Restore original data
*/
scmd->cmd_len = ses->cmd_len;
memcpy(scmd->cmnd, ses->cmnd, sizeof(ses->cmnd));
scmd->sc_data_direction = ses->data_direction;
scmd->sdb = ses->sdb;
scmd->result = ses->result;
scmd->resid_len = ses->resid_len;
scmd->underflow = ses->underflow;
scmd->prot_op = ses->prot_op;
scmd->eh_eflags = ses->eh_eflags;
}
EXPORT_SYMBOL(scsi_eh_restore_cmnd);
/**
* scsi_send_eh_cmnd - submit a scsi command as part of error recovery
* @scmd: SCSI command structure to hijack
* @cmnd: CDB to send
* @cmnd_size: size in bytes of @cmnd
* @timeout: timeout for this request
* @sense_bytes: size of sense data to copy or 0
*
* This function is used to send a scsi command down to a target device
* as part of the error recovery process. See also scsi_eh_prep_cmnd() above.
*
* Return value:
* SUCCESS or FAILED or NEEDS_RETRY
*/
static enum scsi_disposition scsi_send_eh_cmnd(struct scsi_cmnd *scmd,
unsigned char *cmnd, int cmnd_size, int timeout, unsigned sense_bytes)
{
struct scsi_device *sdev = scmd->device;
struct Scsi_Host *shost = sdev->host;
DECLARE_COMPLETION_ONSTACK(done);
unsigned long timeleft = timeout, delay;
struct scsi_eh_save ses;
const unsigned long stall_for = msecs_to_jiffies(100);
int rtn;
retry:
scsi_eh_prep_cmnd(scmd, &ses, cmnd, cmnd_size, sense_bytes);
shost->eh_action = &done;
scsi_log_send(scmd);
scmd->submitter = SUBMITTED_BY_SCSI_ERROR_HANDLER;
/*
* Lock sdev->state_mutex to avoid that scsi_device_quiesce() can
* change the SCSI device state after we have examined it and before
* .queuecommand() is called.
*/
mutex_lock(&sdev->state_mutex);
while (sdev->sdev_state == SDEV_BLOCK && timeleft > 0) {
mutex_unlock(&sdev->state_mutex);
SCSI_LOG_ERROR_RECOVERY(5, sdev_printk(KERN_DEBUG, sdev,
"%s: state %d <> %d\n", __func__, sdev->sdev_state,
SDEV_BLOCK));
delay = min(timeleft, stall_for);
timeleft -= delay;
msleep(jiffies_to_msecs(delay));
mutex_lock(&sdev->state_mutex);
}
if (sdev->sdev_state != SDEV_BLOCK)
rtn = shost->hostt->queuecommand(shost, scmd);
else
rtn = FAILED;
mutex_unlock(&sdev->state_mutex);
if (rtn) {
if (timeleft > stall_for) {
scsi_eh_restore_cmnd(scmd, &ses);
timeleft -= stall_for;
msleep(jiffies_to_msecs(stall_for));
goto retry;
}
/* signal not to enter either branch of the if () below */
timeleft = 0;
rtn = FAILED;
} else {
timeleft = wait_for_completion_timeout(&done, timeout);
rtn = SUCCESS;
}
shost->eh_action = NULL;
scsi_log_completion(scmd, rtn);
SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd,
"%s timeleft: %ld\n",
__func__, timeleft));
/*
* If there is time left scsi_eh_done got called, and we will examine
* the actual status codes to see whether the command actually did
* complete normally, else if we have a zero return and no time left,
* the command must still be pending, so abort it and return FAILED.
* If we never actually managed to issue the command, because
* ->queuecommand() kept returning non zero, use the rtn = FAILED
* value above (so don't execute either branch of the if)
*/
if (timeleft) {
rtn = scsi_eh_completed_normally(scmd);
SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd,
"%s: scsi_eh_completed_normally %x\n", __func__, rtn));
switch (rtn) {
case SUCCESS:
case NEEDS_RETRY:
case FAILED:
break;
case ADD_TO_MLQUEUE:
rtn = NEEDS_RETRY;
break;
default:
rtn = FAILED;
break;
}
} else if (rtn != FAILED) {
scsi_abort_eh_cmnd(scmd);
rtn = FAILED;
}
scsi_eh_restore_cmnd(scmd, &ses);
return rtn;
}
/**
* scsi_request_sense - Request sense data from a particular target.
* @scmd: SCSI cmd for request sense.
*
* Notes:
* Some hosts automatically obtain this information, others require
* that we obtain it on our own. This function will *not* return until
* the command either times out, or it completes.
*/
static enum scsi_disposition scsi_request_sense(struct scsi_cmnd *scmd)
{
return scsi_send_eh_cmnd(scmd, NULL, 0, scmd->device->eh_timeout, ~0);
}
static enum scsi_disposition
scsi_eh_action(struct scsi_cmnd *scmd, enum scsi_disposition rtn)
{
if (!blk_rq_is_passthrough(scsi_cmd_to_rq(scmd))) {
struct scsi_driver *sdrv = scsi_cmd_to_driver(scmd);
if (sdrv->eh_action)
rtn = sdrv->eh_action(scmd, rtn);
}
return rtn;
}
/**
* scsi_eh_finish_cmd - Handle a cmd that eh is finished with.
* @scmd: Original SCSI cmd that eh has finished.
* @done_q: Queue for processed commands.
*
* Notes:
* We don't want to use the normal command completion while we are are
* still handling errors - it may cause other commands to be queued,
* and that would disturb what we are doing. Thus we really want to
* keep a list of pending commands for final completion, and once we
* are ready to leave error handling we handle completion for real.
*/
void scsi_eh_finish_cmd(struct scsi_cmnd *scmd, struct list_head *done_q)
{
list_move_tail(&scmd->eh_entry, done_q);
}
EXPORT_SYMBOL(scsi_eh_finish_cmd);
/**
* scsi_eh_get_sense - Get device sense data.
* @work_q: Queue of commands to process.
* @done_q: Queue of processed commands.
*
* Description:
* See if we need to request sense information. if so, then get it
* now, so we have a better idea of what to do.
*
* Notes:
* This has the unfortunate side effect that if a shost adapter does
* not automatically request sense information, we end up shutting
* it down before we request it.
*
* All drivers should request sense information internally these days,
* so for now all I have to say is tough noogies if you end up in here.
*
* XXX: Long term this code should go away, but that needs an audit of
* all LLDDs first.
*/
int scsi_eh_get_sense(struct list_head *work_q,
struct list_head *done_q)
{
struct scsi_cmnd *scmd, *next;
struct Scsi_Host *shost;
enum scsi_disposition rtn;
/*
* If SCSI_EH_ABORT_SCHEDULED has been set, it is timeout IO,
* should not get sense.
*/
list_for_each_entry_safe(scmd, next, work_q, eh_entry) {
if ((scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) ||
SCSI_SENSE_VALID(scmd))
continue;
shost = scmd->device->host;
if (scsi_host_eh_past_deadline(shost)) {
SCSI_LOG_ERROR_RECOVERY(3,
scmd_printk(KERN_INFO, scmd,
"%s: skip request sense, past eh deadline\n",
current->comm));
break;
}
if (!scsi_status_is_check_condition(scmd->result))
/*
* don't request sense if there's no check condition
* status because the error we're processing isn't one
* that has a sense code (and some devices get
* confused by sense requests out of the blue)
*/
continue;
SCSI_LOG_ERROR_RECOVERY(2, scmd_printk(KERN_INFO, scmd,
"%s: requesting sense\n",
current->comm));
rtn = scsi_request_sense(scmd);
if (rtn != SUCCESS)
continue;
SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd,
"sense requested, result %x\n", scmd->result));
SCSI_LOG_ERROR_RECOVERY(3, scsi_print_sense(scmd));
rtn = scsi_decide_disposition(scmd);
/*
* if the result was normal, then just pass it along to the
* upper level.
*/
if (rtn == SUCCESS)
/*
* We don't want this command reissued, just finished
* with the sense data, so set retries to the max
* allowed to ensure it won't get reissued. If the user
* has requested infinite retries, we also want to
* finish this command, so force completion by setting
* retries and allowed to the same value.
*/
if (scmd->allowed == SCSI_CMD_RETRIES_NO_LIMIT)
scmd->retries = scmd->allowed = 1;
else
scmd->retries = scmd->allowed;
else if (rtn != NEEDS_RETRY)
continue;
scsi_eh_finish_cmd(scmd, done_q);
}
return list_empty(work_q);
}
EXPORT_SYMBOL_GPL(scsi_eh_get_sense);
/**
* scsi_eh_tur - Send TUR to device.
* @scmd: &scsi_cmnd to send TUR
*
* Return value:
* 0 - Device is ready. 1 - Device NOT ready.
*/
static int scsi_eh_tur(struct scsi_cmnd *scmd)
{
static unsigned char tur_command[6] = {TEST_UNIT_READY, 0, 0, 0, 0, 0};
int retry_cnt = 1;
enum scsi_disposition rtn;
retry_tur:
rtn = scsi_send_eh_cmnd(scmd, tur_command, 6,
scmd->device->eh_timeout, 0);
SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd,
"%s return: %x\n", __func__, rtn));
switch (rtn) {
case NEEDS_RETRY:
if (retry_cnt--)
goto retry_tur;
fallthrough;
case SUCCESS:
return 0;
default:
return 1;
}
}
/**
* scsi_eh_test_devices - check if devices are responding from error recovery.
* @cmd_list: scsi commands in error recovery.
* @work_q: queue for commands which still need more error recovery
* @done_q: queue for commands which are finished
* @try_stu: boolean on if a STU command should be tried in addition to TUR.
*
* Decription:
* Tests if devices are in a working state. Commands to devices now in
* a working state are sent to the done_q while commands to devices which
* are still failing to respond are returned to the work_q for more
* processing.
**/
static int scsi_eh_test_devices(struct list_head *cmd_list,
struct list_head *work_q,
struct list_head *done_q, int try_stu)
{
struct scsi_cmnd *scmd, *next;
struct scsi_device *sdev;
int finish_cmds;
while (!list_empty(cmd_list)) {
scmd = list_entry(cmd_list->next, struct scsi_cmnd, eh_entry);
sdev = scmd->device;
if (!try_stu) {
if (scsi_host_eh_past_deadline(sdev->host)) {
/* Push items back onto work_q */
list_splice_init(cmd_list, work_q);
SCSI_LOG_ERROR_RECOVERY(3,
sdev_printk(KERN_INFO, sdev,
"%s: skip test device, past eh deadline",
current->comm));
break;
}
}
finish_cmds = !scsi_device_online(scmd->device) ||
(try_stu && !scsi_eh_try_stu(scmd) &&
!scsi_eh_tur(scmd)) ||
!scsi_eh_tur(scmd);
list_for_each_entry_safe(scmd, next, cmd_list, eh_entry)
if (scmd->device == sdev) {
if (finish_cmds &&
(try_stu ||
scsi_eh_action(scmd, SUCCESS) == SUCCESS))
scsi_eh_finish_cmd(scmd, done_q);
else
list_move_tail(&scmd->eh_entry, work_q);
}
}
return list_empty(work_q);
}
/**
* scsi_eh_try_stu - Send START_UNIT to device.
* @scmd: &scsi_cmnd to send START_UNIT
*
* Return value:
* 0 - Device is ready. 1 - Device NOT ready.
*/
static int scsi_eh_try_stu(struct scsi_cmnd *scmd)
{
static unsigned char stu_command[6] = {START_STOP, 0, 0, 0, 1, 0};
if (scmd->device->allow_restart) {
int i;
enum scsi_disposition rtn = NEEDS_RETRY;
for (i = 0; rtn == NEEDS_RETRY && i < 2; i++)
rtn = scsi_send_eh_cmnd(scmd, stu_command, 6,
scmd->device->eh_timeout, 0);
if (rtn == SUCCESS)
return 0;
}
return 1;
}
/**
* scsi_eh_stu - send START_UNIT if needed
* @shost: &scsi host being recovered.
* @work_q: &list_head for pending commands.
* @done_q: &list_head for processed commands.
*
* Notes:
* If commands are failing due to not ready, initializing command required,
* try revalidating the device, which will end up sending a start unit.
*/
static int scsi_eh_stu(struct Scsi_Host *shost,
struct list_head *work_q,
struct list_head *done_q)
{
struct scsi_cmnd *scmd, *stu_scmd, *next;
struct scsi_device *sdev;
shost_for_each_device(sdev, shost) {
if (scsi_host_eh_past_deadline(shost)) {
SCSI_LOG_ERROR_RECOVERY(3,
sdev_printk(KERN_INFO, sdev,
"%s: skip START_UNIT, past eh deadline\n",
current->comm));
scsi_device_put(sdev);
break;
}
stu_scmd = NULL;
list_for_each_entry(scmd, work_q, eh_entry)
if (scmd->device == sdev && SCSI_SENSE_VALID(scmd) &&
scsi_check_sense(scmd) == FAILED ) {
stu_scmd = scmd;
break;
}
if (!stu_scmd)
continue;
SCSI_LOG_ERROR_RECOVERY(3,
sdev_printk(KERN_INFO, sdev,
"%s: Sending START_UNIT\n",
current->comm));
if (!scsi_eh_try_stu(stu_scmd)) {
if (!scsi_device_online(sdev) ||
!scsi_eh_tur(stu_scmd)) {
list_for_each_entry_safe(scmd, next,
work_q, eh_entry) {
if (scmd->device == sdev &&
scsi_eh_action(scmd, SUCCESS) == SUCCESS)
scsi_eh_finish_cmd(scmd, done_q);
}
}
} else {
SCSI_LOG_ERROR_RECOVERY(3,
sdev_printk(KERN_INFO, sdev,
"%s: START_UNIT failed\n",
current->comm));
}
}
return list_empty(work_q);
}
/**
* scsi_eh_bus_device_reset - send bdr if needed
* @shost: scsi host being recovered.
* @work_q: &list_head for pending commands.
* @done_q: &list_head for processed commands.
*
* Notes:
* Try a bus device reset. Still, look to see whether we have multiple
* devices that are jammed or not - if we have multiple devices, it
* makes no sense to try bus_device_reset - we really would need to try
* a bus_reset instead.
*/
static int scsi_eh_bus_device_reset(struct Scsi_Host *shost,
struct list_head *work_q,
struct list_head *done_q)
{
struct scsi_cmnd *scmd, *bdr_scmd, *next;
struct scsi_device *sdev;
enum scsi_disposition rtn;
shost_for_each_device(sdev, shost) {
if (scsi_host_eh_past_deadline(shost)) {
SCSI_LOG_ERROR_RECOVERY(3,
sdev_printk(KERN_INFO, sdev,
"%s: skip BDR, past eh deadline\n",
current->comm));
scsi_device_put(sdev);
break;
}
bdr_scmd = NULL;
list_for_each_entry(scmd, work_q, eh_entry)
if (scmd->device == sdev) {
bdr_scmd = scmd;
break;
}
if (!bdr_scmd)
continue;
SCSI_LOG_ERROR_RECOVERY(3,
sdev_printk(KERN_INFO, sdev,
"%s: Sending BDR\n", current->comm));
rtn = scsi_try_bus_device_reset(bdr_scmd);
if (rtn == SUCCESS || rtn == FAST_IO_FAIL) {
if (!scsi_device_online(sdev) ||
rtn == FAST_IO_FAIL ||
!scsi_eh_tur(bdr_scmd)) {
list_for_each_entry_safe(scmd, next,
work_q, eh_entry) {
if (scmd->device == sdev &&
scsi_eh_action(scmd, rtn) != FAILED)
scsi_eh_finish_cmd(scmd,
done_q);
}
}
} else {
SCSI_LOG_ERROR_RECOVERY(3,
sdev_printk(KERN_INFO, sdev,
"%s: BDR failed\n", current->comm));
}
}
return list_empty(work_q);
}
/**
* scsi_eh_target_reset - send target reset if needed
* @shost: scsi host being recovered.
* @work_q: &list_head for pending commands.
* @done_q: &list_head for processed commands.
*
* Notes:
* Try a target reset.
*/
static int scsi_eh_target_reset(struct Scsi_Host *shost,
struct list_head *work_q,
struct list_head *done_q)
{
LIST_HEAD(tmp_list);
LIST_HEAD(check_list);
list_splice_init(work_q, &tmp_list);
while (!list_empty(&tmp_list)) {
struct scsi_cmnd *next, *scmd;
enum scsi_disposition rtn;
unsigned int id;
if (scsi_host_eh_past_deadline(shost)) {
/* push back on work queue for further processing */
list_splice_init(&check_list, work_q);
list_splice_init(&tmp_list, work_q);
SCSI_LOG_ERROR_RECOVERY(3,
shost_printk(KERN_INFO, shost,
"%s: Skip target reset, past eh deadline\n",
current->comm));
return list_empty(work_q);
}
scmd = list_entry(tmp_list.next, struct scsi_cmnd, eh_entry);
id = scmd_id(scmd);
SCSI_LOG_ERROR_RECOVERY(3,
shost_printk(KERN_INFO, shost,
"%s: Sending target reset to target %d\n",
current->comm, id));
rtn = scsi_try_target_reset(scmd);
if (rtn != SUCCESS && rtn != FAST_IO_FAIL)
SCSI_LOG_ERROR_RECOVERY(3,
shost_printk(KERN_INFO, shost,
"%s: Target reset failed"
" target: %d\n",
current->comm, id));
list_for_each_entry_safe(scmd, next, &tmp_list, eh_entry) {
if (scmd_id(scmd) != id)
continue;
if (rtn == SUCCESS)
list_move_tail(&scmd->eh_entry, &check_list);
else if (rtn == FAST_IO_FAIL)
scsi_eh_finish_cmd(scmd, done_q);
else
/* push back on work queue for further processing */
list_move(&scmd->eh_entry, work_q);
}
}
return scsi_eh_test_devices(&check_list, work_q, done_q, 0);
}
/**
* scsi_eh_bus_reset - send a bus reset
* @shost: &scsi host being recovered.
* @work_q: &list_head for pending commands.
* @done_q: &list_head for processed commands.
*/
static int scsi_eh_bus_reset(struct Scsi_Host *shost,
struct list_head *work_q,
struct list_head *done_q)
{
struct scsi_cmnd *scmd, *chan_scmd, *next;
LIST_HEAD(check_list);
unsigned int channel;
enum scsi_disposition rtn;
/*
* we really want to loop over the various channels, and do this on
* a channel by channel basis. we should also check to see if any
* of the failed commands are on soft_reset devices, and if so, skip
* the reset.
*/
for (channel = 0; channel <= shost->max_channel; channel++) {
if (scsi_host_eh_past_deadline(shost)) {
list_splice_init(&check_list, work_q);
SCSI_LOG_ERROR_RECOVERY(3,
shost_printk(KERN_INFO, shost,
"%s: skip BRST, past eh deadline\n",
current->comm));
return list_empty(work_q);
}
chan_scmd = NULL;
list_for_each_entry(scmd, work_q, eh_entry) {
if (channel == scmd_channel(scmd)) {
chan_scmd = scmd;
break;
/*
* FIXME add back in some support for
* soft_reset devices.
*/
}
}
if (!chan_scmd)
continue;
SCSI_LOG_ERROR_RECOVERY(3,
shost_printk(KERN_INFO, shost,
"%s: Sending BRST chan: %d\n",
current->comm, channel));
rtn = scsi_try_bus_reset(chan_scmd);
if (rtn == SUCCESS || rtn == FAST_IO_FAIL) {
list_for_each_entry_safe(scmd, next, work_q, eh_entry) {
if (channel == scmd_channel(scmd)) {
if (rtn == FAST_IO_FAIL)
scsi_eh_finish_cmd(scmd,
done_q);
else
list_move_tail(&scmd->eh_entry,
&check_list);
}
}
} else {
SCSI_LOG_ERROR_RECOVERY(3,
shost_printk(KERN_INFO, shost,
"%s: BRST failed chan: %d\n",
current->comm, channel));
}
}
return scsi_eh_test_devices(&check_list, work_q, done_q, 0);
}
/**
* scsi_eh_host_reset - send a host reset
* @shost: host to be reset.
* @work_q: &list_head for pending commands.
* @done_q: &list_head for processed commands.
*/
static int scsi_eh_host_reset(struct Scsi_Host *shost,
struct list_head *work_q,
struct list_head *done_q)
{
struct scsi_cmnd *scmd, *next;
LIST_HEAD(check_list);
enum scsi_disposition rtn;
if (!list_empty(work_q)) {
scmd = list_entry(work_q->next,
struct scsi_cmnd, eh_entry);
SCSI_LOG_ERROR_RECOVERY(3,
shost_printk(KERN_INFO, shost,
"%s: Sending HRST\n",
current->comm));
rtn = scsi_try_host_reset(scmd);
if (rtn == SUCCESS) {
list_splice_init(work_q, &check_list);
} else if (rtn == FAST_IO_FAIL) {
list_for_each_entry_safe(scmd, next, work_q, eh_entry) {
scsi_eh_finish_cmd(scmd, done_q);
}
} else {
SCSI_LOG_ERROR_RECOVERY(3,
shost_printk(KERN_INFO, shost,
"%s: HRST failed\n",
current->comm));
}
}
return scsi_eh_test_devices(&check_list, work_q, done_q, 1);
}
/**
* scsi_eh_offline_sdevs - offline scsi devices that fail to recover
* @work_q: &list_head for pending commands.
* @done_q: &list_head for processed commands.
*/
static void scsi_eh_offline_sdevs(struct list_head *work_q,
struct list_head *done_q)
{
struct scsi_cmnd *scmd, *next;
struct scsi_device *sdev;
list_for_each_entry_safe(scmd, next, work_q, eh_entry) {
sdev_printk(KERN_INFO, scmd->device, "Device offlined - "
"not ready after error recovery\n");
sdev = scmd->device;
mutex_lock(&sdev->state_mutex);
scsi_device_set_state(sdev, SDEV_OFFLINE);
mutex_unlock(&sdev->state_mutex);
scsi_eh_finish_cmd(scmd, done_q);
}
return;
}
/**
* scsi_noretry_cmd - determine if command should be failed fast
* @scmd: SCSI cmd to examine.
*/
bool scsi_noretry_cmd(struct scsi_cmnd *scmd)
{
struct request *req = scsi_cmd_to_rq(scmd);
switch (host_byte(scmd->result)) {
case DID_OK:
break;
case DID_TIME_OUT:
goto check_type;
case DID_BUS_BUSY:
return !!(req->cmd_flags & REQ_FAILFAST_TRANSPORT);
case DID_PARITY:
return !!(req->cmd_flags & REQ_FAILFAST_DEV);
case DID_ERROR:
if (get_status_byte(scmd) == SAM_STAT_RESERVATION_CONFLICT)
return false;
fallthrough;
case DID_SOFT_ERROR:
return !!(req->cmd_flags & REQ_FAILFAST_DRIVER);
}
if (!scsi_status_is_check_condition(scmd->result))
return false;
check_type:
/*
* assume caller has checked sense and determined
* the check condition was retryable.
*/
if (req->cmd_flags & REQ_FAILFAST_DEV || blk_rq_is_passthrough(req))
return true;
return false;
}
/**
* scsi_decide_disposition - Disposition a cmd on return from LLD.
* @scmd: SCSI cmd to examine.
*
* Notes:
* This is *only* called when we are examining the status after sending
* out the actual data command. any commands that are queued for error
* recovery (e.g. test_unit_ready) do *not* come through here.
*
* When this routine returns failed, it means the error handler thread
* is woken. In cases where the error code indicates an error that
* doesn't require the error handler read (i.e. we don't need to
* abort/reset), this function should return SUCCESS.
*/
enum scsi_disposition scsi_decide_disposition(struct scsi_cmnd *scmd)
{
enum scsi_disposition rtn;
/*
* if the device is offline, then we clearly just pass the result back
* up to the top level.
*/
if (!scsi_device_online(scmd->device)) {
SCSI_LOG_ERROR_RECOVERY(5, scmd_printk(KERN_INFO, scmd,
"%s: device offline - report as SUCCESS\n", __func__));
return SUCCESS;
}
/*
* first check the host byte, to see if there is anything in there
* that would indicate what we need to do.
*/
switch (host_byte(scmd->result)) {
case DID_PASSTHROUGH:
/*
* no matter what, pass this through to the upper layer.
* nuke this special code so that it looks like we are saying
* did_ok.
*/
scmd->result &= 0xff00ffff;
return SUCCESS;
case DID_OK:
/*
* looks good. drop through, and check the next byte.
*/
break;
case DID_ABORT:
if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) {
set_host_byte(scmd, DID_TIME_OUT);
return SUCCESS;
}
fallthrough;
case DID_NO_CONNECT:
case DID_BAD_TARGET:
/*
* note - this means that we just report the status back
* to the top level driver, not that we actually think
* that it indicates SUCCESS.
*/
return SUCCESS;
case DID_SOFT_ERROR:
/*
* when the low level driver returns did_soft_error,
* it is responsible for keeping an internal retry counter
* in order to avoid endless loops (db)
*/
goto maybe_retry;
case DID_IMM_RETRY:
return NEEDS_RETRY;
case DID_REQUEUE:
return ADD_TO_MLQUEUE;
case DID_TRANSPORT_DISRUPTED:
/*
* LLD/transport was disrupted during processing of the IO.
* The transport class is now blocked/blocking,
* and the transport will decide what to do with the IO
* based on its timers and recovery capablilities if
* there are enough retries.
*/
goto maybe_retry;
case DID_TRANSPORT_FAILFAST:
/*
* The transport decided to failfast the IO (most likely
* the fast io fail tmo fired), so send IO directly upwards.
*/
return SUCCESS;
case DID_TRANSPORT_MARGINAL:
/*
* caller has decided not to do retries on
* abort success, so send IO directly upwards
*/
return SUCCESS;
case DID_ERROR:
if (get_status_byte(scmd) == SAM_STAT_RESERVATION_CONFLICT)
/*
* execute reservation conflict processing code
* lower down
*/
break;
fallthrough;
case DID_BUS_BUSY:
case DID_PARITY:
goto maybe_retry;
case DID_TIME_OUT:
/*
* when we scan the bus, we get timeout messages for
* these commands if there is no device available.
* other hosts report did_no_connect for the same thing.
*/
if ((scmd->cmnd[0] == TEST_UNIT_READY ||
scmd->cmnd[0] == INQUIRY)) {
return SUCCESS;
} else {
return FAILED;
}
case DID_RESET:
return SUCCESS;
default:
return FAILED;
}
/*
* check the status byte to see if this indicates anything special.
*/
switch (get_status_byte(scmd)) {
case SAM_STAT_TASK_SET_FULL:
scsi_handle_queue_full(scmd->device);
/*
* the case of trying to send too many commands to a
* tagged queueing device.
*/
fallthrough;
case SAM_STAT_BUSY:
/*
* device can't talk to us at the moment. Should only
* occur (SAM-3) when the task queue is empty, so will cause
* the empty queue handling to trigger a stall in the
* device.
*/
return ADD_TO_MLQUEUE;
case SAM_STAT_GOOD:
if (scmd->cmnd[0] == REPORT_LUNS)
scmd->device->sdev_target->expecting_lun_change = 0;
scsi_handle_queue_ramp_up(scmd->device);
fallthrough;
case SAM_STAT_COMMAND_TERMINATED:
return SUCCESS;
case SAM_STAT_TASK_ABORTED:
goto maybe_retry;
case SAM_STAT_CHECK_CONDITION:
rtn = scsi_check_sense(scmd);
if (rtn == NEEDS_RETRY)
goto maybe_retry;
/* if rtn == FAILED, we have no sense information;
* returning FAILED will wake the error handler thread
* to collect the sense and redo the decide
* disposition */
return rtn;
case SAM_STAT_CONDITION_MET:
case SAM_STAT_INTERMEDIATE:
case SAM_STAT_INTERMEDIATE_CONDITION_MET:
case SAM_STAT_ACA_ACTIVE:
/*
* who knows? FIXME(eric)
*/
return SUCCESS;
case SAM_STAT_RESERVATION_CONFLICT:
sdev_printk(KERN_INFO, scmd->device,
"reservation conflict\n");
set_host_byte(scmd, DID_NEXUS_FAILURE);
return SUCCESS; /* causes immediate i/o error */
}
return FAILED;
maybe_retry:
/* we requeue for retry because the error was retryable, and
* the request was not marked fast fail. Note that above,
* even if the request is marked fast fail, we still requeue
* for queue congestion conditions (QUEUE_FULL or BUSY) */
if (scsi_cmd_retry_allowed(scmd) && !scsi_noretry_cmd(scmd)) {
return NEEDS_RETRY;
} else {
/*
* no more retries - report this one back to upper level.
*/
return SUCCESS;
}
}
static void eh_lock_door_done(struct request *req, blk_status_t status)
{
blk_mq_free_request(req);
}
/**
* scsi_eh_lock_door - Prevent medium removal for the specified device
* @sdev: SCSI device to prevent medium removal
*
* Locking:
* We must be called from process context.
*
* Notes:
* We queue up an asynchronous "ALLOW MEDIUM REMOVAL" request on the
* head of the devices request queue, and continue.
*/
static void scsi_eh_lock_door(struct scsi_device *sdev)
{
struct scsi_cmnd *scmd;
struct request *req;
req = scsi_alloc_request(sdev->request_queue, REQ_OP_DRV_IN, 0);
if (IS_ERR(req))
return;
scmd = blk_mq_rq_to_pdu(req);
scmd->cmnd[0] = ALLOW_MEDIUM_REMOVAL;
scmd->cmnd[1] = 0;
scmd->cmnd[2] = 0;
scmd->cmnd[3] = 0;
scmd->cmnd[4] = SCSI_REMOVAL_PREVENT;
scmd->cmnd[5] = 0;
scmd->cmd_len = COMMAND_SIZE(scmd->cmnd[0]);
scmd->allowed = 5;
req->rq_flags |= RQF_QUIET;
req->timeout = 10 * HZ;
req->end_io = eh_lock_door_done;
blk_execute_rq_nowait(req, true);
}
/**
* scsi_restart_operations - restart io operations to the specified host.
* @shost: Host we are restarting.
*
* Notes:
* When we entered the error handler, we blocked all further i/o to
* this device. we need to 'reverse' this process.
*/
static void scsi_restart_operations(struct Scsi_Host *shost)
{
struct scsi_device *sdev;
unsigned long flags;
/*
* If the door was locked, we need to insert a door lock request
* onto the head of the SCSI request queue for the device. There
* is no point trying to lock the door of an off-line device.
*/
shost_for_each_device(sdev, shost) {
if (scsi_device_online(sdev) && sdev->was_reset && sdev->locked) {
scsi_eh_lock_door(sdev);
sdev->was_reset = 0;
}
}
/*
* next free up anything directly waiting upon the host. this
* will be requests for character device operations, and also for
* ioctls to queued block devices.
*/
SCSI_LOG_ERROR_RECOVERY(3,
shost_printk(KERN_INFO, shost, "waking up host to restart\n"));
spin_lock_irqsave(shost->host_lock, flags);
if (scsi_host_set_state(shost, SHOST_RUNNING))
if (scsi_host_set_state(shost, SHOST_CANCEL))
BUG_ON(scsi_host_set_state(shost, SHOST_DEL));
spin_unlock_irqrestore(shost->host_lock, flags);
wake_up(&shost->host_wait);
/*
* finally we need to re-initiate requests that may be pending. we will
* have had everything blocked while error handling is taking place, and
* now that error recovery is done, we will need to ensure that these
* requests are started.
*/
scsi_run_host_queues(shost);
/*
* if eh is active and host_eh_scheduled is pending we need to re-run
* recovery. we do this check after scsi_run_host_queues() to allow
* everything pent up since the last eh run a chance to make forward
* progress before we sync again. Either we'll immediately re-run
* recovery or scsi_device_unbusy() will wake us again when these
* pending commands complete.
*/
spin_lock_irqsave(shost->host_lock, flags);
if (shost->host_eh_scheduled)
if (scsi_host_set_state(shost, SHOST_RECOVERY))
WARN_ON(scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY));
spin_unlock_irqrestore(shost->host_lock, flags);
}
/**
* scsi_eh_ready_devs - check device ready state and recover if not.
* @shost: host to be recovered.
* @work_q: &list_head for pending commands.
* @done_q: &list_head for processed commands.
*/
void scsi_eh_ready_devs(struct Scsi_Host *shost,
struct list_head *work_q,
struct list_head *done_q)
{
if (!scsi_eh_stu(shost, work_q, done_q))
if (!scsi_eh_bus_device_reset(shost, work_q, done_q))
if (!scsi_eh_target_reset(shost, work_q, done_q))
if (!scsi_eh_bus_reset(shost, work_q, done_q))
if (!scsi_eh_host_reset(shost, work_q, done_q))
scsi_eh_offline_sdevs(work_q,
done_q);
}
EXPORT_SYMBOL_GPL(scsi_eh_ready_devs);
/**
* scsi_eh_flush_done_q - finish processed commands or retry them.
* @done_q: list_head of processed commands.
*/
void scsi_eh_flush_done_q(struct list_head *done_q)
{
struct scsi_cmnd *scmd, *next;
list_for_each_entry_safe(scmd, next, done_q, eh_entry) {
list_del_init(&scmd->eh_entry);
if (scsi_device_online(scmd->device) &&
!scsi_noretry_cmd(scmd) && scsi_cmd_retry_allowed(scmd) &&
scsi_eh_should_retry_cmd(scmd)) {
SCSI_LOG_ERROR_RECOVERY(3,
scmd_printk(KERN_INFO, scmd,
"%s: flush retry cmd\n",
current->comm));
scsi_queue_insert(scmd, SCSI_MLQUEUE_EH_RETRY);
} else {
/*
* If just we got sense for the device (called
* scsi_eh_get_sense), scmd->result is already
* set, do not set DID_TIME_OUT.
*/
if (!scmd->result)
scmd->result |= (DID_TIME_OUT << 16);
SCSI_LOG_ERROR_RECOVERY(3,
scmd_printk(KERN_INFO, scmd,
"%s: flush finish cmd\n",
current->comm));
scsi_finish_command(scmd);
}
}
}
EXPORT_SYMBOL(scsi_eh_flush_done_q);
/**
* scsi_unjam_host - Attempt to fix a host which has a cmd that failed.
* @shost: Host to unjam.
*
* Notes:
* When we come in here, we *know* that all commands on the bus have
* either completed, failed or timed out. we also know that no further
* commands are being sent to the host, so things are relatively quiet
* and we have freedom to fiddle with things as we wish.
*
* This is only the *default* implementation. it is possible for
* individual drivers to supply their own version of this function, and
* if the maintainer wishes to do this, it is strongly suggested that
* this function be taken as a template and modified. this function
* was designed to correctly handle problems for about 95% of the
* different cases out there, and it should always provide at least a
* reasonable amount of error recovery.
*
* Any command marked 'failed' or 'timeout' must eventually have
* scsi_finish_cmd() called for it. we do all of the retry stuff
* here, so when we restart the host after we return it should have an
* empty queue.
*/
static void scsi_unjam_host(struct Scsi_Host *shost)
{
unsigned long flags;
LIST_HEAD(eh_work_q);
LIST_HEAD(eh_done_q);
spin_lock_irqsave(shost->host_lock, flags);
list_splice_init(&shost->eh_cmd_q, &eh_work_q);
spin_unlock_irqrestore(shost->host_lock, flags);
SCSI_LOG_ERROR_RECOVERY(1, scsi_eh_prt_fail_stats(shost, &eh_work_q));
if (!scsi_eh_get_sense(&eh_work_q, &eh_done_q))
scsi_eh_ready_devs(shost, &eh_work_q, &eh_done_q);
spin_lock_irqsave(shost->host_lock, flags);
if (shost->eh_deadline != -1)
shost->last_reset = 0;
spin_unlock_irqrestore(shost->host_lock, flags);
scsi_eh_flush_done_q(&eh_done_q);
}
/**
* scsi_error_handler - SCSI error handler thread
* @data: Host for which we are running.
*
* Notes:
* This is the main error handling loop. This is run as a kernel thread
* for every SCSI host and handles all error handling activity.
*/
int scsi_error_handler(void *data)
{
struct Scsi_Host *shost = data;
/*
* We use TASK_INTERRUPTIBLE so that the thread is not
* counted against the load average as a running process.
* We never actually get interrupted because kthread_run
* disables signal delivery for the created thread.
*/
while (true) {
/*
* The sequence in kthread_stop() sets the stop flag first
* then wakes the process. To avoid missed wakeups, the task
* should always be in a non running state before the stop
* flag is checked
*/
set_current_state(TASK_INTERRUPTIBLE);
if (kthread_should_stop())
break;
if ((shost->host_failed == 0 && shost->host_eh_scheduled == 0) ||
shost->host_failed != scsi_host_busy(shost)) {
SCSI_LOG_ERROR_RECOVERY(1,
shost_printk(KERN_INFO, shost,
"scsi_eh_%d: sleeping\n",
shost->host_no));
schedule();
continue;
}
__set_current_state(TASK_RUNNING);
SCSI_LOG_ERROR_RECOVERY(1,
shost_printk(KERN_INFO, shost,
"scsi_eh_%d: waking up %d/%d/%d\n",
shost->host_no, shost->host_eh_scheduled,
shost->host_failed,
scsi_host_busy(shost)));
/*
* We have a host that is failing for some reason. Figure out
* what we need to do to get it up and online again (if we can).
* If we fail, we end up taking the thing offline.
*/
if (!shost->eh_noresume && scsi_autopm_get_host(shost) != 0) {
SCSI_LOG_ERROR_RECOVERY(1,
shost_printk(KERN_ERR, shost,
"scsi_eh_%d: unable to autoresume\n",
shost->host_no));
continue;
}
if (shost->transportt->eh_strategy_handler)
shost->transportt->eh_strategy_handler(shost);
else
scsi_unjam_host(shost);
/* All scmds have been handled */
shost->host_failed = 0;
/*
* Note - if the above fails completely, the action is to take
* individual devices offline and flush the queue of any
* outstanding requests that may have been pending. When we
* restart, we restart any I/O to any other devices on the bus
* which are still online.
*/
scsi_restart_operations(shost);
if (!shost->eh_noresume)
scsi_autopm_put_host(shost);
}
__set_current_state(TASK_RUNNING);
SCSI_LOG_ERROR_RECOVERY(1,
shost_printk(KERN_INFO, shost,
"Error handler scsi_eh_%d exiting\n",
shost->host_no));
shost->ehandler = NULL;
return 0;
}
/*
* Function: scsi_report_bus_reset()
*
* Purpose: Utility function used by low-level drivers to report that
* they have observed a bus reset on the bus being handled.
*
* Arguments: shost - Host in question
* channel - channel on which reset was observed.
*
* Returns: Nothing
*
* Lock status: Host lock must be held.
*
* Notes: This only needs to be called if the reset is one which
* originates from an unknown location. Resets originated
* by the mid-level itself don't need to call this, but there
* should be no harm.
*
* The main purpose of this is to make sure that a CHECK_CONDITION
* is properly treated.
*/
void scsi_report_bus_reset(struct Scsi_Host *shost, int channel)
{
struct scsi_device *sdev;
__shost_for_each_device(sdev, shost) {
if (channel == sdev_channel(sdev))
__scsi_report_device_reset(sdev, NULL);
}
}
EXPORT_SYMBOL(scsi_report_bus_reset);
/*
* Function: scsi_report_device_reset()
*
* Purpose: Utility function used by low-level drivers to report that
* they have observed a device reset on the device being handled.
*
* Arguments: shost - Host in question
* channel - channel on which reset was observed
* target - target on which reset was observed
*
* Returns: Nothing
*
* Lock status: Host lock must be held
*
* Notes: This only needs to be called if the reset is one which
* originates from an unknown location. Resets originated
* by the mid-level itself don't need to call this, but there
* should be no harm.
*
* The main purpose of this is to make sure that a CHECK_CONDITION
* is properly treated.
*/
void scsi_report_device_reset(struct Scsi_Host *shost, int channel, int target)
{
struct scsi_device *sdev;
__shost_for_each_device(sdev, shost) {
if (channel == sdev_channel(sdev) &&
target == sdev_id(sdev))
__scsi_report_device_reset(sdev, NULL);
}
}
EXPORT_SYMBOL(scsi_report_device_reset);
/**
* scsi_ioctl_reset: explicitly reset a host/bus/target/device
* @dev: scsi_device to operate on
* @arg: reset type (see sg.h)
*/
int
scsi_ioctl_reset(struct scsi_device *dev, int __user *arg)
{
struct scsi_cmnd *scmd;
struct Scsi_Host *shost = dev->host;
struct request *rq;
unsigned long flags;
int error = 0, val;
enum scsi_disposition rtn;
if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO))
return -EACCES;
error = get_user(val, arg);
if (error)
return error;
if (scsi_autopm_get_host(shost) < 0)
return -EIO;
error = -EIO;
rq = kzalloc(sizeof(struct request) + sizeof(struct scsi_cmnd) +
shost->hostt->cmd_size, GFP_KERNEL);
if (!rq)
goto out_put_autopm_host;
blk_rq_init(NULL, rq);
scmd = (struct scsi_cmnd *)(rq + 1);
scsi_init_command(dev, scmd);
scmd->submitter = SUBMITTED_BY_SCSI_RESET_IOCTL;
memset(&scmd->sdb, 0, sizeof(scmd->sdb));
scmd->cmd_len = 0;
scmd->sc_data_direction = DMA_BIDIRECTIONAL;
spin_lock_irqsave(shost->host_lock, flags);
shost->tmf_in_progress = 1;
spin_unlock_irqrestore(shost->host_lock, flags);
switch (val & ~SG_SCSI_RESET_NO_ESCALATE) {
case SG_SCSI_RESET_NOTHING:
rtn = SUCCESS;
break;
case SG_SCSI_RESET_DEVICE:
rtn = scsi_try_bus_device_reset(scmd);
if (rtn == SUCCESS || (val & SG_SCSI_RESET_NO_ESCALATE))
break;
fallthrough;
case SG_SCSI_RESET_TARGET:
rtn = scsi_try_target_reset(scmd);
if (rtn == SUCCESS || (val & SG_SCSI_RESET_NO_ESCALATE))
break;
fallthrough;
case SG_SCSI_RESET_BUS:
rtn = scsi_try_bus_reset(scmd);
if (rtn == SUCCESS || (val & SG_SCSI_RESET_NO_ESCALATE))
break;
fallthrough;
case SG_SCSI_RESET_HOST:
rtn = scsi_try_host_reset(scmd);
if (rtn == SUCCESS)
break;
fallthrough;
default:
rtn = FAILED;
break;
}
error = (rtn == SUCCESS) ? 0 : -EIO;
spin_lock_irqsave(shost->host_lock, flags);
shost->tmf_in_progress = 0;
spin_unlock_irqrestore(shost->host_lock, flags);
/*
* be sure to wake up anyone who was sleeping or had their queue
* suspended while we performed the TMF.
*/
SCSI_LOG_ERROR_RECOVERY(3,
shost_printk(KERN_INFO, shost,
"waking up host to restart after TMF\n"));
wake_up(&shost->host_wait);
scsi_run_host_queues(shost);
kfree(rq);
out_put_autopm_host:
scsi_autopm_put_host(shost);
return error;
}
bool scsi_command_normalize_sense(const struct scsi_cmnd *cmd,
struct scsi_sense_hdr *sshdr)
{
return scsi_normalize_sense(cmd->sense_buffer,
SCSI_SENSE_BUFFERSIZE, sshdr);
}
EXPORT_SYMBOL(scsi_command_normalize_sense);
/**
* scsi_get_sense_info_fld - get information field from sense data (either fixed or descriptor format)
* @sense_buffer: byte array of sense data
* @sb_len: number of valid bytes in sense_buffer
* @info_out: pointer to 64 integer where 8 or 4 byte information
* field will be placed if found.
*
* Return value:
* true if information field found, false if not found.
*/
bool scsi_get_sense_info_fld(const u8 *sense_buffer, int sb_len,
u64 *info_out)
{
const u8 * ucp;
if (sb_len < 7)
return false;
switch (sense_buffer[0] & 0x7f) {
case 0x70:
case 0x71:
if (sense_buffer[0] & 0x80) {
*info_out = get_unaligned_be32(&sense_buffer[3]);
return true;
}
return false;
case 0x72:
case 0x73:
ucp = scsi_sense_desc_find(sense_buffer, sb_len,
0 /* info desc */);
if (ucp && (0xa == ucp[1])) {
*info_out = get_unaligned_be64(&ucp[4]);
return true;
}
return false;
default:
return false;
}
}
EXPORT_SYMBOL(scsi_get_sense_info_fld);
|