aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/scsi/libata-eh.c
blob: 1e9e73d1348599076f17a919e86a49f6be82ac2b (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
/*
 *  libata-eh.c - libata error handling
 *
 *  Maintained by:  Jeff Garzik <jgarzik@pobox.com>
 *    		    Please ALWAYS copy linux-ide@vger.kernel.org
 *		    on emails.
 *
 *  Copyright 2006 Tejun Heo <htejun@gmail.com>
 *
 *
 *  This program is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU General Public License as
 *  published by the Free Software Foundation; either version 2, or
 *  (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 *  General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program; see the file COPYING.  If not, write to
 *  the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139,
 *  USA.
 *
 *
 *  libata documentation is available via 'make {ps|pdf}docs',
 *  as Documentation/DocBook/libata.*
 *
 *  Hardware documentation available from http://www.t13.org/ and
 *  http://www.sata-io.org/
 *
 */

#include <linux/config.h>
#include <linux/kernel.h>
#include <scsi/scsi.h>
#include <scsi/scsi_host.h>
#include <scsi/scsi_eh.h>
#include <scsi/scsi_device.h>
#include <scsi/scsi_cmnd.h>
#include "scsi_transport_api.h"

#include <linux/libata.h>

#include "libata.h"

static void __ata_port_freeze(struct ata_port *ap);
static void ata_eh_finish(struct ata_port *ap);

static void ata_ering_record(struct ata_ering *ering, int is_io,
			     unsigned int err_mask)
{
	struct ata_ering_entry *ent;

	WARN_ON(!err_mask);

	ering->cursor++;
	ering->cursor %= ATA_ERING_SIZE;

	ent = &ering->ring[ering->cursor];
	ent->is_io = is_io;
	ent->err_mask = err_mask;
	ent->timestamp = get_jiffies_64();
}

static struct ata_ering_entry * ata_ering_top(struct ata_ering *ering)
{
	struct ata_ering_entry *ent = &ering->ring[ering->cursor];
	if (!ent->err_mask)
		return NULL;
	return ent;
}

static int ata_ering_map(struct ata_ering *ering,
			 int (*map_fn)(struct ata_ering_entry *, void *),
			 void *arg)
{
	int idx, rc = 0;
	struct ata_ering_entry *ent;

	idx = ering->cursor;
	do {
		ent = &ering->ring[idx];
		if (!ent->err_mask)
			break;
		rc = map_fn(ent, arg);
		if (rc)
			break;
		idx = (idx - 1 + ATA_ERING_SIZE) % ATA_ERING_SIZE;
	} while (idx != ering->cursor);

	return rc;
}

static unsigned int ata_eh_dev_action(struct ata_device *dev)
{
	struct ata_eh_context *ehc = &dev->ap->eh_context;

	return ehc->i.action | ehc->i.dev_action[dev->devno];
}

static void ata_eh_clear_action(struct ata_device *dev,
				struct ata_eh_info *ehi, unsigned int action)
{
	int i;

	if (!dev) {
		ehi->action &= ~action;
		for (i = 0; i < ATA_MAX_DEVICES; i++)
			ehi->dev_action[i] &= ~action;
	} else {
		/* doesn't make sense for port-wide EH actions */
		WARN_ON(!(action & ATA_EH_PERDEV_MASK));

		/* break ehi->action into ehi->dev_action */
		if (ehi->action & action) {
			for (i = 0; i < ATA_MAX_DEVICES; i++)
				ehi->dev_action[i] |= ehi->action & action;
			ehi->action &= ~action;
		}

		/* turn off the specified per-dev action */
		ehi->dev_action[dev->devno] &= ~action;
	}
}

/**
 *	ata_scsi_timed_out - SCSI layer time out callback
 *	@cmd: timed out SCSI command
 *
 *	Handles SCSI layer timeout.  We race with normal completion of
 *	the qc for @cmd.  If the qc is already gone, we lose and let
 *	the scsi command finish (EH_HANDLED).  Otherwise, the qc has
 *	timed out and EH should be invoked.  Prevent ata_qc_complete()
 *	from finishing it by setting EH_SCHEDULED and return
 *	EH_NOT_HANDLED.
 *
 *	TODO: kill this function once old EH is gone.
 *
 *	LOCKING:
 *	Called from timer context
 *
 *	RETURNS:
 *	EH_HANDLED or EH_NOT_HANDLED
 */
enum scsi_eh_timer_return ata_scsi_timed_out(struct scsi_cmnd *cmd)
{
	struct Scsi_Host *host = cmd->device->host;
	struct ata_port *ap = ata_shost_to_port(host);
	unsigned long flags;
	struct ata_queued_cmd *qc;
	enum scsi_eh_timer_return ret;

	DPRINTK("ENTER\n");

	if (ap->ops->error_handler) {
		ret = EH_NOT_HANDLED;
		goto out;
	}

	ret = EH_HANDLED;
	spin_lock_irqsave(ap->lock, flags);
	qc = ata_qc_from_tag(ap, ap->active_tag);
	if (qc) {
		WARN_ON(qc->scsicmd != cmd);
		qc->flags |= ATA_QCFLAG_EH_SCHEDULED;
		qc->err_mask |= AC_ERR_TIMEOUT;
		ret = EH_NOT_HANDLED;
	}
	spin_unlock_irqrestore(ap->lock, flags);

 out:
	DPRINTK("EXIT, ret=%d\n", ret);
	return ret;
}

/**
 *	ata_scsi_error - SCSI layer error handler callback
 *	@host: SCSI host on which error occurred
 *
 *	Handles SCSI-layer-thrown error events.
 *
 *	LOCKING:
 *	Inherited from SCSI layer (none, can sleep)
 *
 *	RETURNS:
 *	Zero.
 */
void ata_scsi_error(struct Scsi_Host *host)
{
	struct ata_port *ap = ata_shost_to_port(host);
	int i, repeat_cnt = ATA_EH_MAX_REPEAT;
	unsigned long flags;

	DPRINTK("ENTER\n");

	/* synchronize with port task */
	ata_port_flush_task(ap);

	/* synchronize with host_set lock and sort out timeouts */

	/* For new EH, all qcs are finished in one of three ways -
	 * normal completion, error completion, and SCSI timeout.
	 * Both cmpletions can race against SCSI timeout.  When normal
	 * completion wins, the qc never reaches EH.  When error
	 * completion wins, the qc has ATA_QCFLAG_FAILED set.
	 *
	 * When SCSI timeout wins, things are a bit more complex.
	 * Normal or error completion can occur after the timeout but
	 * before this point.  In such cases, both types of
	 * completions are honored.  A scmd is determined to have
	 * timed out iff its associated qc is active and not failed.
	 */
	if (ap->ops->error_handler) {
		struct scsi_cmnd *scmd, *tmp;
		int nr_timedout = 0;

		spin_lock_irqsave(ap->lock, flags);

		list_for_each_entry_safe(scmd, tmp, &host->eh_cmd_q, eh_entry) {
			struct ata_queued_cmd *qc;

			for (i = 0; i < ATA_MAX_QUEUE; i++) {
				qc = __ata_qc_from_tag(ap, i);
				if (qc->flags & ATA_QCFLAG_ACTIVE &&
				    qc->scsicmd == scmd)
					break;
			}

			if (i < ATA_MAX_QUEUE) {
				/* the scmd has an associated qc */
				if (!(qc->flags & ATA_QCFLAG_FAILED)) {
					/* which hasn't failed yet, timeout */
					qc->err_mask |= AC_ERR_TIMEOUT;
					qc->flags |= ATA_QCFLAG_FAILED;
					nr_timedout++;
				}
			} else {
				/* Normal completion occurred after
				 * SCSI timeout but before this point.
				 * Successfully complete it.
				 */
				scmd->retries = scmd->allowed;
				scsi_eh_finish_cmd(scmd, &ap->eh_done_q);
			}
		}

		/* If we have timed out qcs.  They belong to EH from
		 * this point but the state of the controller is
		 * unknown.  Freeze the port to make sure the IRQ
		 * handler doesn't diddle with those qcs.  This must
		 * be done atomically w.r.t. setting QCFLAG_FAILED.
		 */
		if (nr_timedout)
			__ata_port_freeze(ap);

		spin_unlock_irqrestore(ap->lock, flags);
	} else
		spin_unlock_wait(ap->lock);

 repeat:
	/* invoke error handler */
	if (ap->ops->error_handler) {
		/* fetch & clear EH info */
		spin_lock_irqsave(ap->lock, flags);

		memset(&ap->eh_context, 0, sizeof(ap->eh_context));
		ap->eh_context.i = ap->eh_info;
		memset(&ap->eh_info, 0, sizeof(ap->eh_info));

		ap->pflags |= ATA_PFLAG_EH_IN_PROGRESS;
		ap->pflags &= ~ATA_PFLAG_EH_PENDING;

		spin_unlock_irqrestore(ap->lock, flags);

		/* invoke EH.  if unloading, just finish failed qcs */
		if (!(ap->pflags & ATA_PFLAG_UNLOADING))
			ap->ops->error_handler(ap);
		else
			ata_eh_finish(ap);

		/* Exception might have happend after ->error_handler
		 * recovered the port but before this point.  Repeat
		 * EH in such case.
		 */
		spin_lock_irqsave(ap->lock, flags);

		if (ap->pflags & ATA_PFLAG_EH_PENDING) {
			if (--repeat_cnt) {
				ata_port_printk(ap, KERN_INFO,
					"EH pending after completion, "
					"repeating EH (cnt=%d)\n", repeat_cnt);
				spin_unlock_irqrestore(ap->lock, flags);
				goto repeat;
			}
			ata_port_printk(ap, KERN_ERR, "EH pending after %d "
					"tries, giving up\n", ATA_EH_MAX_REPEAT);
		}

		/* this run is complete, make sure EH info is clear */
		memset(&ap->eh_info, 0, sizeof(ap->eh_info));

		/* Clear host_eh_scheduled while holding ap->lock such
		 * that if exception occurs after this point but
		 * before EH completion, SCSI midlayer will
		 * re-initiate EH.
		 */
		host->host_eh_scheduled = 0;

		spin_unlock_irqrestore(ap->lock, flags);
	} else {
		WARN_ON(ata_qc_from_tag(ap, ap->active_tag) == NULL);
		ap->ops->eng_timeout(ap);
	}

	/* finish or retry handled scmd's and clean up */
	WARN_ON(host->host_failed || !list_empty(&host->eh_cmd_q));

	scsi_eh_flush_done_q(&ap->eh_done_q);

	/* clean up */
	spin_lock_irqsave(ap->lock, flags);

	if (ap->pflags & ATA_PFLAG_LOADING)
		ap->pflags &= ~ATA_PFLAG_LOADING;
	else if (ap->pflags & ATA_PFLAG_SCSI_HOTPLUG)
		queue_work(ata_aux_wq, &ap->hotplug_task);

	if (ap->pflags & ATA_PFLAG_RECOVERED)
		ata_port_printk(ap, KERN_INFO, "EH complete\n");

	ap->pflags &= ~(ATA_PFLAG_SCSI_HOTPLUG | ATA_PFLAG_RECOVERED);

	/* tell wait_eh that we're done */
	ap->pflags &= ~ATA_PFLAG_EH_IN_PROGRESS;
	wake_up_all(&ap->eh_wait_q);

	spin_unlock_irqrestore(ap->lock, flags);

	DPRINTK("EXIT\n");
}

/**
 *	ata_port_wait_eh - Wait for the currently pending EH to complete
 *	@ap: Port to wait EH for
 *
 *	Wait until the currently pending EH is complete.
 *
 *	LOCKING:
 *	Kernel thread context (may sleep).
 */
void ata_port_wait_eh(struct ata_port *ap)
{
	unsigned long flags;
	DEFINE_WAIT(wait);

 retry:
	spin_lock_irqsave(ap->lock, flags);

	while (ap->pflags & (ATA_PFLAG_EH_PENDING | ATA_PFLAG_EH_IN_PROGRESS)) {
		prepare_to_wait(&ap->eh_wait_q, &wait, TASK_UNINTERRUPTIBLE);
		spin_unlock_irqrestore(ap->lock, flags);
		schedule();
		spin_lock_irqsave(ap->lock, flags);
	}
	finish_wait(&ap->eh_wait_q, &wait);

	spin_unlock_irqrestore(ap->lock, flags);

	/* make sure SCSI EH is complete */
	if (scsi_host_in_recovery(ap->host)) {
		msleep(10);
		goto retry;
	}
}

/**
 *	ata_qc_timeout - Handle timeout of queued command
 *	@qc: Command that timed out
 *
 *	Some part of the kernel (currently, only the SCSI layer)
 *	has noticed that the active command on port @ap has not
 *	completed after a specified length of time.  Handle this
 *	condition by disabling DMA (if necessary) and completing
 *	transactions, with error if necessary.
 *
 *	This also handles the case of the "lost interrupt", where
 *	for some reason (possibly hardware bug, possibly driver bug)
 *	an interrupt was not delivered to the driver, even though the
 *	transaction completed successfully.
 *
 *	TODO: kill this function once old EH is gone.
 *
 *	LOCKING:
 *	Inherited from SCSI layer (none, can sleep)
 */
static void ata_qc_timeout(struct ata_queued_cmd *qc)
{
	struct ata_port *ap = qc->ap;
	u8 host_stat = 0, drv_stat;
	unsigned long flags;

	DPRINTK("ENTER\n");

	ap->hsm_task_state = HSM_ST_IDLE;

	spin_lock_irqsave(ap->lock, flags);

	switch (qc->tf.protocol) {

	case ATA_PROT_DMA:
	case ATA_PROT_ATAPI_DMA:
		host_stat = ap->ops->bmdma_status(ap);

		/* before we do anything else, clear DMA-Start bit */
		ap->ops->bmdma_stop(qc);

		/* fall through */

	default:
		ata_altstatus(ap);
		drv_stat = ata_chk_status(ap);

		/* ack bmdma irq events */
		ap->ops->irq_clear(ap);

		ata_dev_printk(qc->dev, KERN_ERR, "command 0x%x timeout, "
			       "stat 0x%x host_stat 0x%x\n",
			       qc->tf.command, drv_stat, host_stat);

		/* complete taskfile transaction */
		qc->err_mask |= AC_ERR_TIMEOUT;
		break;
	}

	spin_unlock_irqrestore(ap->lock, flags);

	ata_eh_qc_complete(qc);

	DPRINTK("EXIT\n");
}

/**
 *	ata_eng_timeout - Handle timeout of queued command
 *	@ap: Port on which timed-out command is active
 *
 *	Some part of the kernel (currently, only the SCSI layer)
 *	has noticed that the active command on port @ap has not
 *	completed after a specified length of time.  Handle this
 *	condition by disabling DMA (if necessary) and completing
 *	transactions, with error if necessary.
 *
 *	This also handles the case of the "lost interrupt", where
 *	for some reason (possibly hardware bug, possibly driver bug)
 *	an interrupt was not delivered to the driver, even though the
 *	transaction completed successfully.
 *
 *	TODO: kill this function once old EH is gone.
 *
 *	LOCKING:
 *	Inherited from SCSI layer (none, can sleep)
 */
void ata_eng_timeout(struct ata_port *ap)
{
	DPRINTK("ENTER\n");

	ata_qc_timeout(ata_qc_from_tag(ap, ap->active_tag));

	DPRINTK("EXIT\n");
}

/**
 *	ata_qc_schedule_eh - schedule qc for error handling
 *	@qc: command to schedule error handling for
 *
 *	Schedule error handling for @qc.  EH will kick in as soon as
 *	other commands are drained.
 *
 *	LOCKING:
 *	spin_lock_irqsave(host_set lock)
 */
void ata_qc_schedule_eh(struct ata_queued_cmd *qc)
{
	struct ata_port *ap = qc->ap;

	WARN_ON(!ap->ops->error_handler);

	qc->flags |= ATA_QCFLAG_FAILED;
	qc->ap->pflags |= ATA_PFLAG_EH_PENDING;

	/* The following will fail if timeout has already expired.
	 * ata_scsi_error() takes care of such scmds on EH entry.
	 * Note that ATA_QCFLAG_FAILED is unconditionally set after
	 * this function completes.
	 */
	scsi_req_abort_cmd(qc->scsicmd);
}

/**
 *	ata_port_schedule_eh - schedule error handling without a qc
 *	@ap: ATA port to schedule EH for
 *
 *	Schedule error handling for @ap.  EH will kick in as soon as
 *	all commands are drained.
 *
 *	LOCKING:
 *	spin_lock_irqsave(host_set lock)
 */
void ata_port_schedule_eh(struct ata_port *ap)
{
	WARN_ON(!ap->ops->error_handler);

	ap->pflags |= ATA_PFLAG_EH_PENDING;
	scsi_schedule_eh(ap->host);

	DPRINTK("port EH scheduled\n");
}

/**
 *	ata_port_abort - abort all qc's on the port
 *	@ap: ATA port to abort qc's for
 *
 *	Abort all active qc's of @ap and schedule EH.
 *
 *	LOCKING:
 *	spin_lock_irqsave(host_set lock)
 *
 *	RETURNS:
 *	Number of aborted qc's.
 */
int ata_port_abort(struct ata_port *ap)
{
	int tag, nr_aborted = 0;

	WARN_ON(!ap->ops->error_handler);

	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
		struct ata_queued_cmd *qc = ata_qc_from_tag(ap, tag);

		if (qc) {
			qc->flags |= ATA_QCFLAG_FAILED;
			ata_qc_complete(qc);
			nr_aborted++;
		}
	}

	if (!nr_aborted)
		ata_port_schedule_eh(ap);

	return nr_aborted;
}

/**
 *	__ata_port_freeze - freeze port
 *	@ap: ATA port to freeze
 *
 *	This function is called when HSM violation or some other
 *	condition disrupts normal operation of the port.  Frozen port
 *	is not allowed to perform any operation until the port is
 *	thawed, which usually follows a successful reset.
 *
 *	ap->ops->freeze() callback can be used for freezing the port
 *	hardware-wise (e.g. mask interrupt and stop DMA engine).  If a
 *	port cannot be frozen hardware-wise, the interrupt handler
 *	must ack and clear interrupts unconditionally while the port
 *	is frozen.
 *
 *	LOCKING:
 *	spin_lock_irqsave(host_set lock)
 */
static void __ata_port_freeze(struct ata_port *ap)
{
	WARN_ON(!ap->ops->error_handler);

	if (ap->ops->freeze)
		ap->ops->freeze(ap);

	ap->pflags |= ATA_PFLAG_FROZEN;

	DPRINTK("ata%u port frozen\n", ap->id);
}

/**
 *	ata_port_freeze - abort & freeze port
 *	@ap: ATA port to freeze
 *
 *	Abort and freeze @ap.
 *
 *	LOCKING:
 *	spin_lock_irqsave(host_set lock)
 *
 *	RETURNS:
 *	Number of aborted commands.
 */
int ata_port_freeze(struct ata_port *ap)
{
	int nr_aborted;

	WARN_ON(!ap->ops->error_handler);

	nr_aborted = ata_port_abort(ap);
	__ata_port_freeze(ap);

	return nr_aborted;
}

/**
 *	ata_eh_freeze_port - EH helper to freeze port
 *	@ap: ATA port to freeze
 *
 *	Freeze @ap.
 *
 *	LOCKING:
 *	None.
 */
void ata_eh_freeze_port(struct ata_port *ap)
{
	unsigned long flags;

	if (!ap->ops->error_handler)
		return;

	spin_lock_irqsave(ap->lock, flags);
	__ata_port_freeze(ap);
	spin_unlock_irqrestore(ap->lock, flags);
}

/**
 *	ata_port_thaw_port - EH helper to thaw port
 *	@ap: ATA port to thaw
 *
 *	Thaw frozen port @ap.
 *
 *	LOCKING:
 *	None.
 */
void ata_eh_thaw_port(struct ata_port *ap)
{
	unsigned long flags;

	if (!ap->ops->error_handler)
		return;

	spin_lock_irqsave(ap->lock, flags);

	ap->pflags &= ~ATA_PFLAG_FROZEN;

	if (ap->ops->thaw)
		ap->ops->thaw(ap);

	spin_unlock_irqrestore(ap->lock, flags);

	DPRINTK("ata%u port thawed\n", ap->id);
}

static void ata_eh_scsidone(struct scsi_cmnd *scmd)
{
	/* nada */
}

static void __ata_eh_qc_complete(struct ata_queued_cmd *qc)
{
	struct ata_port *ap = qc->ap;
	struct scsi_cmnd *scmd = qc->scsicmd;
	unsigned long flags;

	spin_lock_irqsave(ap->lock, flags);
	qc->scsidone = ata_eh_scsidone;
	__ata_qc_complete(qc);
	WARN_ON(ata_tag_valid(qc->tag));
	spin_unlock_irqrestore(ap->lock, flags);

	scsi_eh_finish_cmd(scmd, &ap->eh_done_q);
}

/**
 *	ata_eh_qc_complete - Complete an active ATA command from EH
 *	@qc: Command to complete
 *
 *	Indicate to the mid and upper layers that an ATA command has
 *	completed.  To be used from EH.
 */
void ata_eh_qc_complete(struct ata_queued_cmd *qc)
{
	struct scsi_cmnd *scmd = qc->scsicmd;
	scmd->retries = scmd->allowed;
	__ata_eh_qc_complete(qc);
}

/**
 *	ata_eh_qc_retry - Tell midlayer to retry an ATA command after EH
 *	@qc: Command to retry
 *
 *	Indicate to the mid and upper layers that an ATA command
 *	should be retried.  To be used from EH.
 *
 *	SCSI midlayer limits the number of retries to scmd->allowed.
 *	scmd->retries is decremented for commands which get retried
 *	due to unrelated failures (qc->err_mask is zero).
 */
void ata_eh_qc_retry(struct ata_queued_cmd *qc)
{
	struct scsi_cmnd *scmd = qc->scsicmd;
	if (!qc->err_mask && scmd->retries)
		scmd->retries--;
	__ata_eh_qc_complete(qc);
}

/**
 *	ata_eh_detach_dev - detach ATA device
 *	@dev: ATA device to detach
 *
 *	Detach @dev.
 *
 *	LOCKING:
 *	None.
 */
static void ata_eh_detach_dev(struct ata_device *dev)
{
	struct ata_port *ap = dev->ap;
	unsigned long flags;

	ata_dev_disable(dev);

	spin_lock_irqsave(ap->lock, flags);

	dev->flags &= ~ATA_DFLAG_DETACH;

	if (ata_scsi_offline_dev(dev)) {
		dev->flags |= ATA_DFLAG_DETACHED;
		ap->pflags |= ATA_PFLAG_SCSI_HOTPLUG;
	}

	/* clear per-dev EH actions */
	ata_eh_clear_action(dev, &ap->eh_info, ATA_EH_PERDEV_MASK);
	ata_eh_clear_action(dev, &ap->eh_context.i, ATA_EH_PERDEV_MASK);

	spin_unlock_irqrestore(ap->lock, flags);
}

/**
 *	ata_eh_about_to_do - about to perform eh_action
 *	@ap: target ATA port
 *	@dev: target ATA dev for per-dev action (can be NULL)
 *	@action: action about to be performed
 *
 *	Called just before performing EH actions to clear related bits
 *	in @ap->eh_info such that eh actions are not unnecessarily
 *	repeated.
 *
 *	LOCKING:
 *	None.
 */
static void ata_eh_about_to_do(struct ata_port *ap, struct ata_device *dev,
			       unsigned int action)
{
	unsigned long flags;

	spin_lock_irqsave(ap->lock, flags);

	ata_eh_clear_action(dev, &ap->eh_info, action);

	if (!(ap->eh_context.i.flags & ATA_EHI_QUIET))
		ap->pflags |= ATA_PFLAG_RECOVERED;

	spin_unlock_irqrestore(ap->lock, flags);
}

/**
 *	ata_eh_done - EH action complete
 *	@ap: target ATA port
 *	@dev: target ATA dev for per-dev action (can be NULL)
 *	@action: action just completed
 *
 *	Called right after performing EH actions to clear related bits
 *	in @ap->eh_context.
 *
 *	LOCKING:
 *	None.
 */
static void ata_eh_done(struct ata_port *ap, struct ata_device *dev,
			unsigned int action)
{
	ata_eh_clear_action(dev, &ap->eh_context.i, action);
}

/**
 *	ata_err_string - convert err_mask to descriptive string
 *	@err_mask: error mask to convert to string
 *
 *	Convert @err_mask to descriptive string.  Errors are
 *	prioritized according to severity and only the most severe
 *	error is reported.
 *
 *	LOCKING:
 *	None.
 *
 *	RETURNS:
 *	Descriptive string for @err_mask
 */
static const char * ata_err_string(unsigned int err_mask)
{
	if (err_mask & AC_ERR_HOST_BUS)
		return "host bus error";
	if (err_mask & AC_ERR_ATA_BUS)
		return "ATA bus error";
	if (err_mask & AC_ERR_TIMEOUT)
		return "timeout";
	if (err_mask & AC_ERR_HSM)
		return "HSM violation";
	if (err_mask & AC_ERR_SYSTEM)
		return "internal error";
	if (err_mask & AC_ERR_MEDIA)
		return "media error";
	if (err_mask & AC_ERR_INVALID)
		return "invalid argument";
	if (err_mask & AC_ERR_DEV)
		return "device error";
	return "unknown error";
}

/**
 *	ata_read_log_page - read a specific log page
 *	@dev: target device
 *	@page: page to read
 *	@buf: buffer to store read page
 *	@sectors: number of sectors to read
 *
 *	Read log page using READ_LOG_EXT command.
 *
 *	LOCKING:
 *	Kernel thread context (may sleep).
 *
 *	RETURNS:
 *	0 on success, AC_ERR_* mask otherwise.
 */
static unsigned int ata_read_log_page(struct ata_device *dev,
				      u8 page, void *buf, unsigned int sectors)
{
	struct ata_taskfile tf;
	unsigned int err_mask;

	DPRINTK("read log page - page %d\n", page);

	ata_tf_init(dev, &tf);
	tf.command = ATA_CMD_READ_LOG_EXT;
	tf.lbal = page;
	tf.nsect = sectors;
	tf.hob_nsect = sectors >> 8;
	tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_LBA48 | ATA_TFLAG_DEVICE;
	tf.protocol = ATA_PROT_PIO;

	err_mask = ata_exec_internal(dev, &tf, NULL, DMA_FROM_DEVICE,
				     buf, sectors * ATA_SECT_SIZE);

	DPRINTK("EXIT, err_mask=%x\n", err_mask);
	return err_mask;
}

/**
 *	ata_eh_read_log_10h - Read log page 10h for NCQ error details
 *	@dev: Device to read log page 10h from
 *	@tag: Resulting tag of the failed command
 *	@tf: Resulting taskfile registers of the failed command
 *
 *	Read log page 10h to obtain NCQ error details and clear error
 *	condition.
 *
 *	LOCKING:
 *	Kernel thread context (may sleep).
 *
 *	RETURNS:
 *	0 on success, -errno otherwise.
 */
static int ata_eh_read_log_10h(struct ata_device *dev,
			       int *tag, struct ata_taskfile *tf)
{
	u8 *buf = dev->ap->sector_buf;
	unsigned int err_mask;
	u8 csum;
	int i;

	err_mask = ata_read_log_page(dev, ATA_LOG_SATA_NCQ, buf, 1);
	if (err_mask)
		return -EIO;

	csum = 0;
	for (i = 0; i < ATA_SECT_SIZE; i++)
		csum += buf[i];
	if (csum)
		ata_dev_printk(dev, KERN_WARNING,
			       "invalid checksum 0x%x on log page 10h\n", csum);

	if (buf[0] & 0x80)
		return -ENOENT;

	*tag = buf[0] & 0x1f;

	tf->command = buf[2];
	tf->feature = buf[3];
	tf->lbal = buf[4];
	tf->lbam = buf[5];
	tf->lbah = buf[6];
	tf->device = buf[7];
	tf->hob_lbal = buf[8];
	tf->hob_lbam = buf[9];
	tf->hob_lbah = buf[10];
	tf->nsect = buf[12];
	tf->hob_nsect = buf[13];

	return 0;
}

/**
 *	atapi_eh_request_sense - perform ATAPI REQUEST_SENSE
 *	@dev: device to perform REQUEST_SENSE to
 *	@sense_buf: result sense data buffer (SCSI_SENSE_BUFFERSIZE bytes long)
 *
 *	Perform ATAPI REQUEST_SENSE after the device reported CHECK
 *	SENSE.  This function is EH helper.
 *
 *	LOCKING:
 *	Kernel thread context (may sleep).
 *
 *	RETURNS:
 *	0 on success, AC_ERR_* mask on failure
 */
static unsigned int atapi_eh_request_sense(struct ata_device *dev,
					   unsigned char *sense_buf)
{
	struct ata_port *ap = dev->ap;
	struct ata_taskfile tf;
	u8 cdb[ATAPI_CDB_LEN];

	DPRINTK("ATAPI request sense\n");

	ata_tf_init(dev, &tf);

	/* FIXME: is this needed? */
	memset(sense_buf, 0, SCSI_SENSE_BUFFERSIZE);

	/* XXX: why tf_read here? */
	ap->ops->tf_read(ap, &tf);

	/* fill these in, for the case where they are -not- overwritten */
	sense_buf[0] = 0x70;
	sense_buf[2] = tf.feature >> 4;

	memset(cdb, 0, ATAPI_CDB_LEN);
	cdb[0] = REQUEST_SENSE;
	cdb[4] = SCSI_SENSE_BUFFERSIZE;

	tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE;
	tf.command = ATA_CMD_PACKET;

	/* is it pointless to prefer PIO for "safety reasons"? */
	if (ap->flags & ATA_FLAG_PIO_DMA) {
		tf.protocol = ATA_PROT_ATAPI_DMA;
		tf.feature |= ATAPI_PKT_DMA;
	} else {
		tf.protocol = ATA_PROT_ATAPI;
		tf.lbam = (8 * 1024) & 0xff;
		tf.lbah = (8 * 1024) >> 8;
	}

	return ata_exec_internal(dev, &tf, cdb, DMA_FROM_DEVICE,
				 sense_buf, SCSI_SENSE_BUFFERSIZE);
}

/**
 *	ata_eh_analyze_serror - analyze SError for a failed port
 *	@ap: ATA port to analyze SError for
 *
 *	Analyze SError if available and further determine cause of
 *	failure.
 *
 *	LOCKING:
 *	None.
 */
static void ata_eh_analyze_serror(struct ata_port *ap)
{
	struct ata_eh_context *ehc = &ap->eh_context;
	u32 serror = ehc->i.serror;
	unsigned int err_mask = 0, action = 0;

	if (serror & SERR_PERSISTENT) {
		err_mask |= AC_ERR_ATA_BUS;
		action |= ATA_EH_HARDRESET;
	}
	if (serror &
	    (SERR_DATA_RECOVERED | SERR_COMM_RECOVERED | SERR_DATA)) {
		err_mask |= AC_ERR_ATA_BUS;
		action |= ATA_EH_SOFTRESET;
	}
	if (serror & SERR_PROTOCOL) {
		err_mask |= AC_ERR_HSM;
		action |= ATA_EH_SOFTRESET;
	}
	if (serror & SERR_INTERNAL) {
		err_mask |= AC_ERR_SYSTEM;
		action |= ATA_EH_SOFTRESET;
	}
	if (serror & (SERR_PHYRDY_CHG | SERR_DEV_XCHG))
		ata_ehi_hotplugged(&ehc->i);

	ehc->i.err_mask |= err_mask;
	ehc->i.action |= action;
}

/**
 *	ata_eh_analyze_ncq_error - analyze NCQ error
 *	@ap: ATA port to analyze NCQ error for
 *
 *	Read log page 10h, determine the offending qc and acquire
 *	error status TF.  For NCQ device errors, all LLDDs have to do
 *	is setting AC_ERR_DEV in ehi->err_mask.  This function takes
 *	care of the rest.
 *
 *	LOCKING:
 *	Kernel thread context (may sleep).
 */
static void ata_eh_analyze_ncq_error(struct ata_port *ap)
{
	struct ata_eh_context *ehc = &ap->eh_context;
	struct ata_device *dev = ap->device;
	struct ata_queued_cmd *qc;
	struct ata_taskfile tf;
	int tag, rc;

	/* if frozen, we can't do much */
	if (ap->pflags & ATA_PFLAG_FROZEN)
		return;

	/* is it NCQ device error? */
	if (!ap->sactive || !(ehc->i.err_mask & AC_ERR_DEV))
		return;

	/* has LLDD analyzed already? */
	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
		qc = __ata_qc_from_tag(ap, tag);

		if (!(qc->flags & ATA_QCFLAG_FAILED))
			continue;

		if (qc->err_mask)
			return;
	}

	/* okay, this error is ours */
	rc = ata_eh_read_log_10h(dev, &tag, &tf);
	if (rc) {
		ata_port_printk(ap, KERN_ERR, "failed to read log page 10h "
				"(errno=%d)\n", rc);
		return;
	}

	if (!(ap->sactive & (1 << tag))) {
		ata_port_printk(ap, KERN_ERR, "log page 10h reported "
				"inactive tag %d\n", tag);
		return;
	}

	/* we've got the perpetrator, condemn it */
	qc = __ata_qc_from_tag(ap, tag);
	memcpy(&qc->result_tf, &tf, sizeof(tf));
	qc->err_mask |= AC_ERR_DEV;
	ehc->i.err_mask &= ~AC_ERR_DEV;
}

/**
 *	ata_eh_analyze_tf - analyze taskfile of a failed qc
 *	@qc: qc to analyze
 *	@tf: Taskfile registers to analyze
 *
 *	Analyze taskfile of @qc and further determine cause of
 *	failure.  This function also requests ATAPI sense data if
 *	avaliable.
 *
 *	LOCKING:
 *	Kernel thread context (may sleep).
 *
 *	RETURNS:
 *	Determined recovery action
 */
static unsigned int ata_eh_analyze_tf(struct ata_queued_cmd *qc,
				      const struct ata_taskfile *tf)
{
	unsigned int tmp, action = 0;
	u8 stat = tf->command, err = tf->feature;

	if ((stat & (ATA_BUSY | ATA_DRQ | ATA_DRDY)) != ATA_DRDY) {
		qc->err_mask |= AC_ERR_HSM;
		return ATA_EH_SOFTRESET;
	}

	if (!(qc->err_mask & AC_ERR_DEV))
		return 0;

	switch (qc->dev->class) {
	case ATA_DEV_ATA:
		if (err & ATA_ICRC)
			qc->err_mask |= AC_ERR_ATA_BUS;
		if (err & ATA_UNC)
			qc->err_mask |= AC_ERR_MEDIA;
		if (err & ATA_IDNF)
			qc->err_mask |= AC_ERR_INVALID;
		break;

	case ATA_DEV_ATAPI:
		tmp = atapi_eh_request_sense(qc->dev,
					     qc->scsicmd->sense_buffer);
		if (!tmp) {
			/* ATA_QCFLAG_SENSE_VALID is used to tell
			 * atapi_qc_complete() that sense data is
			 * already valid.
			 *
			 * TODO: interpret sense data and set
			 * appropriate err_mask.
			 */
			qc->flags |= ATA_QCFLAG_SENSE_VALID;
		} else
			qc->err_mask |= tmp;
	}

	if (qc->err_mask & (AC_ERR_HSM | AC_ERR_TIMEOUT | AC_ERR_ATA_BUS))
		action |= ATA_EH_SOFTRESET;

	return action;
}

static int ata_eh_categorize_ering_entry(struct ata_ering_entry *ent)
{
	if (ent->err_mask & (AC_ERR_ATA_BUS | AC_ERR_TIMEOUT))
		return 1;

	if (ent->is_io) {
		if (ent->err_mask & AC_ERR_HSM)
			return 1;
		if ((ent->err_mask &
		     (AC_ERR_DEV|AC_ERR_MEDIA|AC_ERR_INVALID)) == AC_ERR_DEV)
			return 2;
	}

	return 0;
}

struct speed_down_needed_arg {
	u64 since;
	int nr_errors[3];
};

static int speed_down_needed_cb(struct ata_ering_entry *ent, void *void_arg)
{
	struct speed_down_needed_arg *arg = void_arg;

	if (ent->timestamp < arg->since)
		return -1;

	arg->nr_errors[ata_eh_categorize_ering_entry(ent)]++;
	return 0;
}

/**
 *	ata_eh_speed_down_needed - Determine wheter speed down is necessary
 *	@dev: Device of interest
 *
 *	This function examines error ring of @dev and determines
 *	whether speed down is necessary.  Speed down is necessary if
 *	there have been more than 3 of Cat-1 errors or 10 of Cat-2
 *	errors during last 15 minutes.
 *
 *	Cat-1 errors are ATA_BUS, TIMEOUT for any command and HSM
 *	violation for known supported commands.
 *
 *	Cat-2 errors are unclassified DEV error for known supported
 *	command.
 *
 *	LOCKING:
 *	Inherited from caller.
 *
 *	RETURNS:
 *	1 if speed down is necessary, 0 otherwise
 */
static int ata_eh_speed_down_needed(struct ata_device *dev)
{
	const u64 interval = 15LLU * 60 * HZ;
	static const int err_limits[3] = { -1, 3, 10 };
	struct speed_down_needed_arg arg;
	struct ata_ering_entry *ent;
	int err_cat;
	u64 j64;

	ent = ata_ering_top(&dev->ering);
	if (!ent)
		return 0;

	err_cat = ata_eh_categorize_ering_entry(ent);
	if (err_cat == 0)
		return 0;

	memset(&arg, 0, sizeof(arg));

	j64 = get_jiffies_64();
	if (j64 >= interval)
		arg.since = j64 - interval;
	else
		arg.since = 0;

	ata_ering_map(&dev->ering, speed_down_needed_cb, &arg);

	return arg.nr_errors[err_cat] > err_limits[err_cat];
}

/**
 *	ata_eh_speed_down - record error and speed down if necessary
 *	@dev: Failed device
 *	@is_io: Did the device fail during normal IO?
 *	@err_mask: err_mask of the error
 *
 *	Record error and examine error history to determine whether
 *	adjusting transmission speed is necessary.  It also sets
 *	transmission limits appropriately if such adjustment is
 *	necessary.
 *
 *	LOCKING:
 *	Kernel thread context (may sleep).
 *
 *	RETURNS:
 *	0 on success, -errno otherwise
 */
static int ata_eh_speed_down(struct ata_device *dev, int is_io,
			     unsigned int err_mask)
{
	if (!err_mask)
		return 0;

	/* record error and determine whether speed down is necessary */
	ata_ering_record(&dev->ering, is_io, err_mask);

	if (!ata_eh_speed_down_needed(dev))
		return 0;

	/* speed down SATA link speed if possible */
	if (sata_down_spd_limit(dev->ap) == 0)
		return ATA_EH_HARDRESET;

	/* lower transfer mode */
	if (ata_down_xfermask_limit(dev, 0) == 0)
		return ATA_EH_SOFTRESET;

	ata_dev_printk(dev, KERN_ERR,
		       "speed down requested but no transfer mode left\n");
	return 0;
}

/**
 *	ata_eh_autopsy - analyze error and determine recovery action
 *	@ap: ATA port to perform autopsy on
 *
 *	Analyze why @ap failed and determine which recovery action is
 *	needed.  This function also sets more detailed AC_ERR_* values
 *	and fills sense data for ATAPI CHECK SENSE.
 *
 *	LOCKING:
 *	Kernel thread context (may sleep).
 */
static void ata_eh_autopsy(struct ata_port *ap)
{
	struct ata_eh_context *ehc = &ap->eh_context;
	unsigned int action = ehc->i.action;
	struct ata_device *failed_dev = NULL;
	unsigned int all_err_mask = 0;
	int tag, is_io = 0;
	u32 serror;
	int rc;

	DPRINTK("ENTER\n");

	if (ehc->i.flags & ATA_EHI_NO_AUTOPSY)
		return;

	/* obtain and analyze SError */
	rc = sata_scr_read(ap, SCR_ERROR, &serror);
	if (rc == 0) {
		ehc->i.serror |= serror;
		ata_eh_analyze_serror(ap);
	} else if (rc != -EOPNOTSUPP)
		action |= ATA_EH_HARDRESET;

	/* analyze NCQ failure */
	ata_eh_analyze_ncq_error(ap);

	/* any real error trumps AC_ERR_OTHER */
	if (ehc->i.err_mask & ~AC_ERR_OTHER)
		ehc->i.err_mask &= ~AC_ERR_OTHER;

	all_err_mask |= ehc->i.err_mask;

	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
		struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag);

		if (!(qc->flags & ATA_QCFLAG_FAILED))
			continue;

		/* inherit upper level err_mask */
		qc->err_mask |= ehc->i.err_mask;

		/* analyze TF */
		action |= ata_eh_analyze_tf(qc, &qc->result_tf);

		/* DEV errors are probably spurious in case of ATA_BUS error */
		if (qc->err_mask & AC_ERR_ATA_BUS)
			qc->err_mask &= ~(AC_ERR_DEV | AC_ERR_MEDIA |
					  AC_ERR_INVALID);

		/* any real error trumps unknown error */
		if (qc->err_mask & ~AC_ERR_OTHER)
			qc->err_mask &= ~AC_ERR_OTHER;

		/* SENSE_VALID trumps dev/unknown error and revalidation */
		if (qc->flags & ATA_QCFLAG_SENSE_VALID) {
			qc->err_mask &= ~(AC_ERR_DEV | AC_ERR_OTHER);
			action &= ~ATA_EH_REVALIDATE;
		}

		/* accumulate error info */
		failed_dev = qc->dev;
		all_err_mask |= qc->err_mask;
		if (qc->flags & ATA_QCFLAG_IO)
			is_io = 1;
	}

	/* enforce default EH actions */
	if (ap->pflags & ATA_PFLAG_FROZEN ||
	    all_err_mask & (AC_ERR_HSM | AC_ERR_TIMEOUT))
		action |= ATA_EH_SOFTRESET;
	else if (all_err_mask)
		action |= ATA_EH_REVALIDATE;

	/* if we have offending qcs and the associated failed device */
	if (failed_dev) {
		/* speed down */
		action |= ata_eh_speed_down(failed_dev, is_io, all_err_mask);

		/* perform per-dev EH action only on the offending device */
		ehc->i.dev_action[failed_dev->devno] |=
			action & ATA_EH_PERDEV_MASK;
		action &= ~ATA_EH_PERDEV_MASK;
	}

	/* record autopsy result */
	ehc->i.dev = failed_dev;
	ehc->i.action |= action;

	DPRINTK("EXIT\n");
}

/**
 *	ata_eh_report - report error handling to user
 *	@ap: ATA port EH is going on
 *
 *	Report EH to user.
 *
 *	LOCKING:
 *	None.
 */
static void ata_eh_report(struct ata_port *ap)
{
	struct ata_eh_context *ehc = &ap->eh_context;
	const char *frozen, *desc;
	int tag, nr_failed = 0;

	desc = NULL;
	if (ehc->i.desc[0] != '\0')
		desc = ehc->i.desc;

	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
		struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag);

		if (!(qc->flags & ATA_QCFLAG_FAILED))
			continue;
		if (qc->flags & ATA_QCFLAG_SENSE_VALID && !qc->err_mask)
			continue;

		nr_failed++;
	}

	if (!nr_failed && !ehc->i.err_mask)
		return;

	frozen = "";
	if (ap->pflags & ATA_PFLAG_FROZEN)
		frozen = " frozen";

	if (ehc->i.dev) {
		ata_dev_printk(ehc->i.dev, KERN_ERR, "exception Emask 0x%x "
			       "SAct 0x%x SErr 0x%x action 0x%x%s\n",
			       ehc->i.err_mask, ap->sactive, ehc->i.serror,
			       ehc->i.action, frozen);
		if (desc)
			ata_dev_printk(ehc->i.dev, KERN_ERR, "(%s)\n", desc);
	} else {
		ata_port_printk(ap, KERN_ERR, "exception Emask 0x%x "
				"SAct 0x%x SErr 0x%x action 0x%x%s\n",
				ehc->i.err_mask, ap->sactive, ehc->i.serror,
				ehc->i.action, frozen);
		if (desc)
			ata_port_printk(ap, KERN_ERR, "(%s)\n", desc);
	}

	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
		struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag);

		if (!(qc->flags & ATA_QCFLAG_FAILED) || !qc->err_mask)
			continue;

		ata_dev_printk(qc->dev, KERN_ERR, "tag %d cmd 0x%x "
			       "Emask 0x%x stat 0x%x err 0x%x (%s)\n",
			       qc->tag, qc->tf.command, qc->err_mask,
			       qc->result_tf.command, qc->result_tf.feature,
			       ata_err_string(qc->err_mask));
	}
}

static int ata_do_reset(struct ata_port *ap, ata_reset_fn_t reset,
			unsigned int *classes)
{
	int i, rc;

	for (i = 0; i < ATA_MAX_DEVICES; i++)
		classes[i] = ATA_DEV_UNKNOWN;

	rc = reset(ap, classes);
	if (rc)
		return rc;

	/* If any class isn't ATA_DEV_UNKNOWN, consider classification
	 * is complete and convert all ATA_DEV_UNKNOWN to
	 * ATA_DEV_NONE.
	 */
	for (i = 0; i < ATA_MAX_DEVICES; i++)
		if (classes[i] != ATA_DEV_UNKNOWN)
			break;

	if (i < ATA_MAX_DEVICES)
		for (i = 0; i < ATA_MAX_DEVICES; i++)
			if (classes[i] == ATA_DEV_UNKNOWN)
				classes[i] = ATA_DEV_NONE;

	return 0;
}

static int ata_eh_followup_srst_needed(int rc, int classify,
				       const unsigned int *classes)
{
	if (rc == -EAGAIN)
		return 1;
	if (rc != 0)
		return 0;
	if (classify && classes[0] == ATA_DEV_UNKNOWN)
		return 1;
	return 0;
}

static int ata_eh_reset(struct ata_port *ap, int classify,
			ata_prereset_fn_t prereset, ata_reset_fn_t softreset,
			ata_reset_fn_t hardreset, ata_postreset_fn_t postreset)
{
	struct ata_eh_context *ehc = &ap->eh_context;
	unsigned int *classes = ehc->classes;
	int tries = ATA_EH_RESET_TRIES;
	int verbose = !(ehc->i.flags & ATA_EHI_QUIET);
	unsigned int action;
	ata_reset_fn_t reset;
	int i, did_followup_srst, rc;

	/* Determine which reset to use and record in ehc->i.action.
	 * prereset() may examine and modify it.
	 */
	action = ehc->i.action;
	ehc->i.action &= ~ATA_EH_RESET_MASK;
	if (softreset && (!hardreset || (!sata_set_spd_needed(ap) &&
					 !(action & ATA_EH_HARDRESET))))
		ehc->i.action |= ATA_EH_SOFTRESET;
	else
		ehc->i.action |= ATA_EH_HARDRESET;

	if (prereset) {
		rc = prereset(ap);
		if (rc) {
			ata_port_printk(ap, KERN_ERR,
					"prereset failed (errno=%d)\n", rc);
			return rc;
		}
	}

	/* prereset() might have modified ehc->i.action */
	if (ehc->i.action & ATA_EH_HARDRESET)
		reset = hardreset;
	else if (ehc->i.action & ATA_EH_SOFTRESET)
		reset = softreset;
	else {
		/* prereset told us not to reset, bang classes and return */
		for (i = 0; i < ATA_MAX_DEVICES; i++)
			classes[i] = ATA_DEV_NONE;
		return 0;
	}

	/* did prereset() screw up?  if so, fix up to avoid oopsing */
	if (!reset) {
		ata_port_printk(ap, KERN_ERR, "BUG: prereset() requested "
				"invalid reset type\n");
		if (softreset)
			reset = softreset;
		else
			reset = hardreset;
	}

 retry:
	/* shut up during boot probing */
	if (verbose)
		ata_port_printk(ap, KERN_INFO, "%s resetting port\n",
				reset == softreset ? "soft" : "hard");

	/* reset */
	ata_eh_about_to_do(ap, NULL, ATA_EH_RESET_MASK);
	ehc->i.flags |= ATA_EHI_DID_RESET;

	rc = ata_do_reset(ap, reset, classes);

	did_followup_srst = 0;
	if (reset == hardreset &&
	    ata_eh_followup_srst_needed(rc, classify, classes)) {
		/* okay, let's do follow-up softreset */
		did_followup_srst = 1;
		reset = softreset;

		if (!reset) {
			ata_port_printk(ap, KERN_ERR,
					"follow-up softreset required "
					"but no softreset avaliable\n");
			return -EINVAL;
		}

		ata_eh_about_to_do(ap, NULL, ATA_EH_RESET_MASK);
		rc = ata_do_reset(ap, reset, classes);

		if (rc == 0 && classify &&
		    classes[0] == ATA_DEV_UNKNOWN) {
			ata_port_printk(ap, KERN_ERR,
					"classification failed\n");
			return -EINVAL;
		}
	}

	if (rc && --tries) {
		const char *type;

		if (reset == softreset) {
			if (did_followup_srst)
				type = "follow-up soft";
			else
				type = "soft";
		} else
			type = "hard";

		ata_port_printk(ap, KERN_WARNING,
				"%sreset failed, retrying in 5 secs\n", type);
		ssleep(5);

		if (reset == hardreset)
			sata_down_spd_limit(ap);
		if (hardreset)
			reset = hardreset;
		goto retry;
	}

	if (rc == 0) {
		/* After the reset, the device state is PIO 0 and the
		 * controller state is undefined.  Record the mode.
		 */
		for (i = 0; i < ATA_MAX_DEVICES; i++)
			ap->device[i].pio_mode = XFER_PIO_0;

		if (postreset)
			postreset(ap, classes);

		/* reset successful, schedule revalidation */
		ata_eh_done(ap, NULL, ATA_EH_RESET_MASK);
		ehc->i.action |= ATA_EH_REVALIDATE;
	}

	return rc;
}

static int ata_eh_revalidate_and_attach(struct ata_port *ap,
					struct ata_device **r_failed_dev)
{
	struct ata_eh_context *ehc = &ap->eh_context;
	struct ata_device *dev;
	unsigned long flags;
	int i, rc = 0;

	DPRINTK("ENTER\n");

	for (i = 0; i < ATA_MAX_DEVICES; i++) {
		unsigned int action;

		dev = &ap->device[i];
		action = ata_eh_dev_action(dev);

		if (action & ATA_EH_REVALIDATE && ata_dev_enabled(dev)) {
			if (ata_port_offline(ap)) {
				rc = -EIO;
				break;
			}

			ata_eh_about_to_do(ap, dev, ATA_EH_REVALIDATE);
			rc = ata_dev_revalidate(dev,
					ehc->i.flags & ATA_EHI_DID_RESET);
			if (rc)
				break;

			ata_eh_done(ap, dev, ATA_EH_REVALIDATE);

			/* schedule the scsi_rescan_device() here */
			queue_work(ata_aux_wq, &(ap->scsi_rescan_task));
		} else if (dev->class == ATA_DEV_UNKNOWN &&
			   ehc->tries[dev->devno] &&
			   ata_class_enabled(ehc->classes[dev->devno])) {
			dev->class = ehc->classes[dev->devno];

			rc = ata_dev_read_id(dev, &dev->class, 1, dev->id);
			if (rc == 0)
				rc = ata_dev_configure(dev, 1);

			if (rc) {
				dev->class = ATA_DEV_UNKNOWN;
				break;
			}

			spin_lock_irqsave(ap->lock, flags);
			ap->pflags |= ATA_PFLAG_SCSI_HOTPLUG;
			spin_unlock_irqrestore(ap->lock, flags);
		}
	}

	if (rc)
		*r_failed_dev = dev;

	DPRINTK("EXIT\n");
	return rc;
}

static int ata_port_nr_enabled(struct ata_port *ap)
{
	int i, cnt = 0;

	for (i = 0; i < ATA_MAX_DEVICES; i++)
		if (ata_dev_enabled(&ap->device[i]))
			cnt++;
	return cnt;
}

static int ata_port_nr_vacant(struct ata_port *ap)
{
	int i, cnt = 0;

	for (i = 0; i < ATA_MAX_DEVICES; i++)
		if (ap->device[i].class == ATA_DEV_UNKNOWN)
			cnt++;
	return cnt;
}

static int ata_eh_skip_recovery(struct ata_port *ap)
{
	struct ata_eh_context *ehc = &ap->eh_context;
	int i;

	if (ap->pflags & ATA_PFLAG_FROZEN || ata_port_nr_enabled(ap))
		return 0;

	/* skip if class codes for all vacant slots are ATA_DEV_NONE */
	for (i = 0; i < ATA_MAX_DEVICES; i++) {
		struct ata_device *dev = &ap->device[i];

		if (dev->class == ATA_DEV_UNKNOWN &&
		    ehc->classes[dev->devno] != ATA_DEV_NONE)
			return 0;
	}

	return 1;
}

/**
 *	ata_eh_recover - recover host port after error
 *	@ap: host port to recover
 *	@prereset: prereset method (can be NULL)
 *	@softreset: softreset method (can be NULL)
 *	@hardreset: hardreset method (can be NULL)
 *	@postreset: postreset method (can be NULL)
 *
 *	This is the alpha and omega, eum and yang, heart and soul of
 *	libata exception handling.  On entry, actions required to
 *	recover the port and hotplug requests are recorded in
 *	eh_context.  This function executes all the operations with
 *	appropriate retrials and fallbacks to resurrect failed
 *	devices, detach goners and greet newcomers.
 *
 *	LOCKING:
 *	Kernel thread context (may sleep).
 *
 *	RETURNS:
 *	0 on success, -errno on failure.
 */
static int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
			  ata_reset_fn_t softreset, ata_reset_fn_t hardreset,
			  ata_postreset_fn_t postreset)
{
	struct ata_eh_context *ehc = &ap->eh_context;
	struct ata_device *dev;
	int down_xfermask, i, rc;

	DPRINTK("ENTER\n");

	/* prep for recovery */
	for (i = 0; i < ATA_MAX_DEVICES; i++) {
		dev = &ap->device[i];

		ehc->tries[dev->devno] = ATA_EH_DEV_TRIES;

		/* process hotplug request */
		if (dev->flags & ATA_DFLAG_DETACH)
			ata_eh_detach_dev(dev);

		if (!ata_dev_enabled(dev) &&
		    ((ehc->i.probe_mask & (1 << dev->devno)) &&
		     !(ehc->did_probe_mask & (1 << dev->devno)))) {
			ata_eh_detach_dev(dev);
			ata_dev_init(dev);
			ehc->did_probe_mask |= (1 << dev->devno);
			ehc->i.action |= ATA_EH_SOFTRESET;
		}
	}

 retry:
	down_xfermask = 0;
	rc = 0;

	/* if UNLOADING, finish immediately */
	if (ap->pflags & ATA_PFLAG_UNLOADING)
		goto out;

	/* skip EH if possible. */
	if (ata_eh_skip_recovery(ap))
		ehc->i.action = 0;

	for (i = 0; i < ATA_MAX_DEVICES; i++)
		ehc->classes[i] = ATA_DEV_UNKNOWN;

	/* reset */
	if (ehc->i.action & ATA_EH_RESET_MASK) {
		ata_eh_freeze_port(ap);

		rc = ata_eh_reset(ap, ata_port_nr_vacant(ap), prereset,
				  softreset, hardreset, postreset);
		if (rc) {
			ata_port_printk(ap, KERN_ERR,
					"reset failed, giving up\n");
			goto out;
		}

		ata_eh_thaw_port(ap);
	}

	/* revalidate existing devices and attach new ones */
	rc = ata_eh_revalidate_and_attach(ap, &dev);
	if (rc)
		goto dev_fail;

	/* configure transfer mode if the port has been reset */
	if (ehc->i.flags & ATA_EHI_DID_RESET) {
		rc = ata_set_mode(ap, &dev);
		if (rc) {
			down_xfermask = 1;
			goto dev_fail;
		}
	}

	goto out;

 dev_fail:
	switch (rc) {
	case -ENODEV:
		/* device missing, schedule probing */
		ehc->i.probe_mask |= (1 << dev->devno);
	case -EINVAL:
		ehc->tries[dev->devno] = 0;
		break;
	case -EIO:
		sata_down_spd_limit(ap);
	default:
		ehc->tries[dev->devno]--;
		if (down_xfermask &&
		    ata_down_xfermask_limit(dev, ehc->tries[dev->devno] == 1))
			ehc->tries[dev->devno] = 0;
	}

	if (ata_dev_enabled(dev) && !ehc->tries[dev->devno]) {
		/* disable device if it has used up all its chances */
		ata_dev_disable(dev);

		/* detach if offline */
		if (ata_port_offline(ap))
			ata_eh_detach_dev(dev);

		/* probe if requested */
		if ((ehc->i.probe_mask & (1 << dev->devno)) &&
		    !(ehc->did_probe_mask & (1 << dev->devno))) {
			ata_eh_detach_dev(dev);
			ata_dev_init(dev);

			ehc->tries[dev->devno] = ATA_EH_DEV_TRIES;
			ehc->did_probe_mask |= (1 << dev->devno);
			ehc->i.action |= ATA_EH_SOFTRESET;
		}
	} else {
		/* soft didn't work?  be haaaaard */
		if (ehc->i.flags & ATA_EHI_DID_RESET)
			ehc->i.action |= ATA_EH_HARDRESET;
		else
			ehc->i.action |= ATA_EH_SOFTRESET;
	}

	if (ata_port_nr_enabled(ap)) {
		ata_port_printk(ap, KERN_WARNING, "failed to recover some "
				"devices, retrying in 5 secs\n");
		ssleep(5);
	} else {
		/* no device left, repeat fast */
		msleep(500);
	}

	goto retry;

 out:
	if (rc) {
		for (i = 0; i < ATA_MAX_DEVICES; i++)
			ata_dev_disable(&ap->device[i]);
	}

	DPRINTK("EXIT, rc=%d\n", rc);
	return rc;
}

/**
 *	ata_eh_finish - finish up EH
 *	@ap: host port to finish EH for
 *
 *	Recovery is complete.  Clean up EH states and retry or finish
 *	failed qcs.
 *
 *	LOCKING:
 *	None.
 */
static void ata_eh_finish(struct ata_port *ap)
{
	int tag;

	/* retry or finish qcs */
	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
		struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag);

		if (!(qc->flags & ATA_QCFLAG_FAILED))
			continue;

		if (qc->err_mask) {
			/* FIXME: Once EH migration is complete,
			 * generate sense data in this function,
			 * considering both err_mask and tf.
			 */
			if (qc->err_mask & AC_ERR_INVALID)
				ata_eh_qc_complete(qc);
			else
				ata_eh_qc_retry(qc);
		} else {
			if (qc->flags & ATA_QCFLAG_SENSE_VALID) {
				ata_eh_qc_complete(qc);
			} else {
				/* feed zero TF to sense generation */
				memset(&qc->result_tf, 0, sizeof(qc->result_tf));
				ata_eh_qc_retry(qc);
			}
		}
	}
}

/**
 *	ata_do_eh - do standard error handling
 *	@ap: host port to handle error for
 *	@prereset: prereset method (can be NULL)
 *	@softreset: softreset method (can be NULL)
 *	@hardreset: hardreset method (can be NULL)
 *	@postreset: postreset method (can be NULL)
 *
 *	Perform standard error handling sequence.
 *
 *	LOCKING:
 *	Kernel thread context (may sleep).
 */
void ata_do_eh(struct ata_port *ap, ata_prereset_fn_t prereset,
	       ata_reset_fn_t softreset, ata_reset_fn_t hardreset,
	       ata_postreset_fn_t postreset)
{
	ata_eh_autopsy(ap);
	ata_eh_report(ap);
	ata_eh_recover(ap, prereset, softreset, hardreset, postreset);
	ata_eh_finish(ap);
}

Privacy Policy