summaryrefslogtreecommitdiff
path: root/drivers/hwtracing/intel_th/msu.c
blob: 255f8f41c8ff7d2f71b8dfbbf1240be180420184 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
// SPDX-License-Identifier: GPL-2.0
/*
 * Intel(R) Trace Hub Memory Storage Unit
 *
 * Copyright (C) 2014-2015 Intel Corporation.
 */

#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt

#include <linux/types.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/uaccess.h>
#include <linux/sizes.h>
#include <linux/printk.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/io.h>
#include <linux/workqueue.h>
#include <linux/dma-mapping.h>

#ifdef CONFIG_X86
#include <asm/set_memory.h>
#endif

#include <linux/intel_th.h>
#include "intel_th.h"
#include "msu.h"

#define msc_dev(x) (&(x)->thdev->dev)

/*
 * Lockout state transitions:
 *   READY -> INUSE -+-> LOCKED -+-> READY -> etc.
 *                   \-----------/
 * WIN_READY:	window can be used by HW
 * WIN_INUSE:	window is in use
 * WIN_LOCKED:	window is filled up and is being processed by the buffer
 * handling code
 *
 * All state transitions happen automatically, except for the LOCKED->READY,
 * which needs to be signalled by the buffer code by calling
 * intel_th_msc_window_unlock().
 *
 * When the interrupt handler has to switch to the next window, it checks
 * whether it's READY, and if it is, it performs the switch and tracing
 * continues. If it's LOCKED, it stops the trace.
 */
enum lockout_state {
	WIN_READY = 0,
	WIN_INUSE,
	WIN_LOCKED
};

/**
 * struct msc_window - multiblock mode window descriptor
 * @entry:	window list linkage (msc::win_list)
 * @pgoff:	page offset into the buffer that this window starts at
 * @lockout:	lockout state, see comment below
 * @lo_lock:	lockout state serialization
 * @nr_blocks:	number of blocks (pages) in this window
 * @nr_segs:	number of segments in this window (<= @nr_blocks)
 * @_sgt:	array of block descriptors
 * @sgt:	array of block descriptors
 */
struct msc_window {
	struct list_head	entry;
	unsigned long		pgoff;
	enum lockout_state	lockout;
	spinlock_t		lo_lock;
	unsigned int		nr_blocks;
	unsigned int		nr_segs;
	struct msc		*msc;
	struct sg_table		_sgt;
	struct sg_table		*sgt;
};

/**
 * struct msc_iter - iterator for msc buffer
 * @entry:		msc::iter_list linkage
 * @msc:		pointer to the MSC device
 * @start_win:		oldest window
 * @win:		current window
 * @offset:		current logical offset into the buffer
 * @start_block:	oldest block in the window
 * @block:		block number in the window
 * @block_off:		offset into current block
 * @wrap_count:		block wrapping handling
 * @eof:		end of buffer reached
 */
struct msc_iter {
	struct list_head	entry;
	struct msc		*msc;
	struct msc_window	*start_win;
	struct msc_window	*win;
	unsigned long		offset;
	struct scatterlist	*start_block;
	struct scatterlist	*block;
	unsigned int		block_off;
	unsigned int		wrap_count;
	unsigned int		eof;
};

/**
 * struct msc - MSC device representation
 * @reg_base:		register window base address
 * @thdev:		intel_th_device pointer
 * @mbuf:		MSU buffer, if assigned
 * @mbuf_priv		MSU buffer's private data, if @mbuf
 * @win_list:		list of windows in multiblock mode
 * @single_sgt:		single mode buffer
 * @cur_win:		current window
 * @nr_pages:		total number of pages allocated for this buffer
 * @single_sz:		amount of data in single mode
 * @single_wrap:	single mode wrap occurred
 * @base:		buffer's base pointer
 * @base_addr:		buffer's base address
 * @user_count:		number of users of the buffer
 * @mmap_count:		number of mappings
 * @buf_mutex:		mutex to serialize access to buffer-related bits

 * @enabled:		MSC is enabled
 * @wrap:		wrapping is enabled
 * @mode:		MSC operating mode
 * @burst_len:		write burst length
 * @index:		number of this MSC in the MSU
 */
struct msc {
	void __iomem		*reg_base;
	void __iomem		*msu_base;
	struct intel_th_device	*thdev;

	const struct msu_buffer	*mbuf;
	void			*mbuf_priv;

	struct work_struct	work;
	struct list_head	win_list;
	struct sg_table		single_sgt;
	struct msc_window	*cur_win;
	unsigned long		nr_pages;
	unsigned long		single_sz;
	unsigned int		single_wrap : 1;
	void			*base;
	dma_addr_t		base_addr;
	u32			orig_addr;
	u32			orig_sz;

	/* <0: no buffer, 0: no users, >0: active users */
	atomic_t		user_count;

	atomic_t		mmap_count;
	struct mutex		buf_mutex;

	struct list_head	iter_list;

	/* config */
	unsigned int		enabled : 1,
				wrap	: 1,
				do_irq	: 1;
	unsigned int		mode;
	unsigned int		burst_len;
	unsigned int		index;
};

static LIST_HEAD(msu_buffer_list);
static DEFINE_MUTEX(msu_buffer_mutex);

/**
 * struct msu_buffer_entry - internal MSU buffer bookkeeping
 * @entry:	link to msu_buffer_list
 * @mbuf:	MSU buffer object
 * @owner:	module that provides this MSU buffer
 */
struct msu_buffer_entry {
	struct list_head	entry;
	const struct msu_buffer	*mbuf;
	struct module		*owner;
};

static struct msu_buffer_entry *__msu_buffer_entry_find(const char *name)
{
	struct msu_buffer_entry *mbe;

	lockdep_assert_held(&msu_buffer_mutex);

	list_for_each_entry(mbe, &msu_buffer_list, entry) {
		if (!strcmp(mbe->mbuf->name, name))
			return mbe;
	}

	return NULL;
}

static const struct msu_buffer *
msu_buffer_get(const char *name)
{
	struct msu_buffer_entry *mbe;

	mutex_lock(&msu_buffer_mutex);
	mbe = __msu_buffer_entry_find(name);
	if (mbe && !try_module_get(mbe->owner))
		mbe = NULL;
	mutex_unlock(&msu_buffer_mutex);

	return mbe ? mbe->mbuf : NULL;
}

static void msu_buffer_put(const struct msu_buffer *mbuf)
{
	struct msu_buffer_entry *mbe;

	mutex_lock(&msu_buffer_mutex);
	mbe = __msu_buffer_entry_find(mbuf->name);
	if (mbe)
		module_put(mbe->owner);
	mutex_unlock(&msu_buffer_mutex);
}

int intel_th_msu_buffer_register(const struct msu_buffer *mbuf,
				 struct module *owner)
{
	struct msu_buffer_entry *mbe;
	int ret = 0;

	mbe = kzalloc(sizeof(*mbe), GFP_KERNEL);
	if (!mbe)
		return -ENOMEM;

	mutex_lock(&msu_buffer_mutex);
	if (__msu_buffer_entry_find(mbuf->name)) {
		ret = -EEXIST;
		kfree(mbe);
		goto unlock;
	}

	mbe->mbuf = mbuf;
	mbe->owner = owner;
	list_add_tail(&mbe->entry, &msu_buffer_list);
unlock:
	mutex_unlock(&msu_buffer_mutex);

	return ret;
}
EXPORT_SYMBOL_GPL(intel_th_msu_buffer_register);

void intel_th_msu_buffer_unregister(const struct msu_buffer *mbuf)
{
	struct msu_buffer_entry *mbe;

	mutex_lock(&msu_buffer_mutex);
	mbe = __msu_buffer_entry_find(mbuf->name);
	if (mbe) {
		list_del(&mbe->entry);
		kfree(mbe);
	}
	mutex_unlock(&msu_buffer_mutex);
}
EXPORT_SYMBOL_GPL(intel_th_msu_buffer_unregister);

static inline bool msc_block_is_empty(struct msc_block_desc *bdesc)
{
	/* header hasn't been written */
	if (!bdesc->valid_dw)
		return true;

	/* valid_dw includes the header */
	if (!msc_data_sz(bdesc))
		return true;

	return false;
}

static inline struct scatterlist *msc_win_base_sg(struct msc_window *win)
{
	return win->sgt->sgl;
}

static inline struct msc_block_desc *msc_win_base(struct msc_window *win)
{
	return sg_virt(msc_win_base_sg(win));
}

static inline dma_addr_t msc_win_base_dma(struct msc_window *win)
{
	return sg_dma_address(msc_win_base_sg(win));
}

static inline unsigned long
msc_win_base_pfn(struct msc_window *win)
{
	return PFN_DOWN(msc_win_base_dma(win));
}

/**
 * msc_is_last_win() - check if a window is the last one for a given MSC
 * @win:	window
 * Return:	true if @win is the last window in MSC's multiblock buffer
 */
static inline bool msc_is_last_win(struct msc_window *win)
{
	return win->entry.next == &win->msc->win_list;
}

/**
 * msc_next_window() - return next window in the multiblock buffer
 * @win:	current window
 *
 * Return:	window following the current one
 */
static struct msc_window *msc_next_window(struct msc_window *win)
{
	if (msc_is_last_win(win))
		return list_first_entry(&win->msc->win_list, struct msc_window,
					entry);

	return list_next_entry(win, entry);
}

static size_t msc_win_total_sz(struct msc_window *win)
{
	struct scatterlist *sg;
	unsigned int blk;
	size_t size = 0;

	for_each_sg(win->sgt->sgl, sg, win->nr_segs, blk) {
		struct msc_block_desc *bdesc = sg_virt(sg);

		if (msc_block_wrapped(bdesc))
			return (size_t)win->nr_blocks << PAGE_SHIFT;

		size += msc_total_sz(bdesc);
		if (msc_block_last_written(bdesc))
			break;
	}

	return size;
}

/**
 * msc_find_window() - find a window matching a given sg_table
 * @msc:	MSC device
 * @sgt:	SG table of the window
 * @nonempty:	skip over empty windows
 *
 * Return:	MSC window structure pointer or NULL if the window
 *		could not be found.
 */
static struct msc_window *
msc_find_window(struct msc *msc, struct sg_table *sgt, bool nonempty)
{
	struct msc_window *win;
	unsigned int found = 0;

	if (list_empty(&msc->win_list))
		return NULL;

	/*
	 * we might need a radix tree for this, depending on how
	 * many windows a typical user would allocate; ideally it's
	 * something like 2, in which case we're good
	 */
	list_for_each_entry(win, &msc->win_list, entry) {
		if (win->sgt == sgt)
			found++;

		/* skip the empty ones */
		if (nonempty && msc_block_is_empty(msc_win_base(win)))
			continue;

		if (found)
			return win;
	}

	return NULL;
}

/**
 * msc_oldest_window() - locate the window with oldest data
 * @msc:	MSC device
 *
 * This should only be used in multiblock mode. Caller should hold the
 * msc::user_count reference.
 *
 * Return:	the oldest window with valid data
 */
static struct msc_window *msc_oldest_window(struct msc *msc)
{
	struct msc_window *win;

	if (list_empty(&msc->win_list))
		return NULL;

	win = msc_find_window(msc, msc_next_window(msc->cur_win)->sgt, true);
	if (win)
		return win;

	return list_first_entry(&msc->win_list, struct msc_window, entry);
}

/**
 * msc_win_oldest_sg() - locate the oldest block in a given window
 * @win:	window to look at
 *
 * Return:	index of the block with the oldest data
 */
static struct scatterlist *msc_win_oldest_sg(struct msc_window *win)
{
	unsigned int blk;
	struct scatterlist *sg;
	struct msc_block_desc *bdesc = msc_win_base(win);

	/* without wrapping, first block is the oldest */
	if (!msc_block_wrapped(bdesc))
		return msc_win_base_sg(win);

	/*
	 * with wrapping, last written block contains both the newest and the
	 * oldest data for this window.
	 */
	for_each_sg(win->sgt->sgl, sg, win->nr_segs, blk) {
		struct msc_block_desc *bdesc = sg_virt(sg);

		if (msc_block_last_written(bdesc))
			return sg;
	}

	return msc_win_base_sg(win);
}

static struct msc_block_desc *msc_iter_bdesc(struct msc_iter *iter)
{
	return sg_virt(iter->block);
}

static struct msc_iter *msc_iter_install(struct msc *msc)
{
	struct msc_iter *iter;

	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
	if (!iter)
		return ERR_PTR(-ENOMEM);

	mutex_lock(&msc->buf_mutex);

	/*
	 * Reading and tracing are mutually exclusive; if msc is
	 * enabled, open() will fail; otherwise existing readers
	 * will prevent enabling the msc and the rest of fops don't
	 * need to worry about it.
	 */
	if (msc->enabled) {
		kfree(iter);
		iter = ERR_PTR(-EBUSY);
		goto unlock;
	}

	iter->msc = msc;

	list_add_tail(&iter->entry, &msc->iter_list);
unlock:
	mutex_unlock(&msc->buf_mutex);

	return iter;
}

static void msc_iter_remove(struct msc_iter *iter, struct msc *msc)
{
	mutex_lock(&msc->buf_mutex);
	list_del(&iter->entry);
	mutex_unlock(&msc->buf_mutex);

	kfree(iter);
}

static void msc_iter_block_start(struct msc_iter *iter)
{
	if (iter->start_block)
		return;

	iter->start_block = msc_win_oldest_sg(iter->win);
	iter->block = iter->start_block;
	iter->wrap_count = 0;

	/*
	 * start with the block with oldest data; if data has wrapped
	 * in this window, it should be in this block
	 */
	if (msc_block_wrapped(msc_iter_bdesc(iter)))
		iter->wrap_count = 2;

}

static int msc_iter_win_start(struct msc_iter *iter, struct msc *msc)
{
	/* already started, nothing to do */
	if (iter->start_win)
		return 0;

	iter->start_win = msc_oldest_window(msc);
	if (!iter->start_win)
		return -EINVAL;

	iter->win = iter->start_win;
	iter->start_block = NULL;

	msc_iter_block_start(iter);

	return 0;
}

static int msc_iter_win_advance(struct msc_iter *iter)
{
	iter->win = msc_next_window(iter->win);
	iter->start_block = NULL;

	if (iter->win == iter->start_win) {
		iter->eof++;
		return 1;
	}

	msc_iter_block_start(iter);

	return 0;
}

static int msc_iter_block_advance(struct msc_iter *iter)
{
	iter->block_off = 0;

	/* wrapping */
	if (iter->wrap_count && iter->block == iter->start_block) {
		iter->wrap_count--;
		if (!iter->wrap_count)
			/* copied newest data from the wrapped block */
			return msc_iter_win_advance(iter);
	}

	/* no wrapping, check for last written block */
	if (!iter->wrap_count && msc_block_last_written(msc_iter_bdesc(iter)))
		/* copied newest data for the window */
		return msc_iter_win_advance(iter);

	/* block advance */
	if (sg_is_last(iter->block))
		iter->block = msc_win_base_sg(iter->win);
	else
		iter->block = sg_next(iter->block);

	/* no wrapping, sanity check in case there is no last written block */
	if (!iter->wrap_count && iter->block == iter->start_block)
		return msc_iter_win_advance(iter);

	return 0;
}

/**
 * msc_buffer_iterate() - go through multiblock buffer's data
 * @iter:	iterator structure
 * @size:	amount of data to scan
 * @data:	callback's private data
 * @fn:		iterator callback
 *
 * This will start at the window which will be written to next (containing
 * the oldest data) and work its way to the current window, calling @fn
 * for each chunk of data as it goes.
 *
 * Caller should have msc::user_count reference to make sure the buffer
 * doesn't disappear from under us.
 *
 * Return:	amount of data actually scanned.
 */
static ssize_t
msc_buffer_iterate(struct msc_iter *iter, size_t size, void *data,
		   unsigned long (*fn)(void *, void *, size_t))
{
	struct msc *msc = iter->msc;
	size_t len = size;
	unsigned int advance;

	if (iter->eof)
		return 0;

	/* start with the oldest window */
	if (msc_iter_win_start(iter, msc))
		return 0;

	do {
		unsigned long data_bytes = msc_data_sz(msc_iter_bdesc(iter));
		void *src = (void *)msc_iter_bdesc(iter) + MSC_BDESC;
		size_t tocopy = data_bytes, copied = 0;
		size_t remaining = 0;

		advance = 1;

		/*
		 * If block wrapping happened, we need to visit the last block
		 * twice, because it contains both the oldest and the newest
		 * data in this window.
		 *
		 * First time (wrap_count==2), in the very beginning, to collect
		 * the oldest data, which is in the range
		 * (data_bytes..DATA_IN_PAGE).
		 *
		 * Second time (wrap_count==1), it's just like any other block,
		 * containing data in the range of [MSC_BDESC..data_bytes].
		 */
		if (iter->block == iter->start_block && iter->wrap_count == 2) {
			tocopy = DATA_IN_PAGE - data_bytes;
			src += data_bytes;
		}

		if (!tocopy)
			goto next_block;

		tocopy -= iter->block_off;
		src += iter->block_off;

		if (len < tocopy) {
			tocopy = len;
			advance = 0;
		}

		remaining = fn(data, src, tocopy);

		if (remaining)
			advance = 0;

		copied = tocopy - remaining;
		len -= copied;
		iter->block_off += copied;
		iter->offset += copied;

		if (!advance)
			break;

next_block:
		if (msc_iter_block_advance(iter))
			break;

	} while (len);

	return size - len;
}

/**
 * msc_buffer_clear_hw_header() - clear hw header for multiblock
 * @msc:	MSC device
 */
static void msc_buffer_clear_hw_header(struct msc *msc)
{
	struct msc_window *win;
	struct scatterlist *sg;

	list_for_each_entry(win, &msc->win_list, entry) {
		unsigned int blk;
		size_t hw_sz = sizeof(struct msc_block_desc) -
			offsetof(struct msc_block_desc, hw_tag);

		for_each_sg(win->sgt->sgl, sg, win->nr_segs, blk) {
			struct msc_block_desc *bdesc = sg_virt(sg);

			memset(&bdesc->hw_tag, 0, hw_sz);
		}
	}
}

static int intel_th_msu_init(struct msc *msc)
{
	u32 mintctl, msusts;

	if (!msc->do_irq)
		return 0;

	if (!msc->mbuf)
		return 0;

	mintctl = ioread32(msc->msu_base + REG_MSU_MINTCTL);
	mintctl |= msc->index ? M1BLIE : M0BLIE;
	iowrite32(mintctl, msc->msu_base + REG_MSU_MINTCTL);
	if (mintctl != ioread32(msc->msu_base + REG_MSU_MINTCTL)) {
		dev_info(msc_dev(msc), "MINTCTL ignores writes: no usable interrupts\n");
		msc->do_irq = 0;
		return 0;
	}

	msusts = ioread32(msc->msu_base + REG_MSU_MSUSTS);
	iowrite32(msusts, msc->msu_base + REG_MSU_MSUSTS);

	return 0;
}

static void intel_th_msu_deinit(struct msc *msc)
{
	u32 mintctl;

	if (!msc->do_irq)
		return;

	mintctl = ioread32(msc->msu_base + REG_MSU_MINTCTL);
	mintctl &= msc->index ? ~M1BLIE : ~M0BLIE;
	iowrite32(mintctl, msc->msu_base + REG_MSU_MINTCTL);
}

static int msc_win_set_lockout(struct msc_window *win,
			       enum lockout_state expect,
			       enum lockout_state new)
{
	enum lockout_state old;
	unsigned long flags;
	int ret = 0;

	if (!win->msc->mbuf)
		return 0;

	spin_lock_irqsave(&win->lo_lock, flags);
	old = win->lockout;

	if (old != expect) {
		ret = -EINVAL;
		goto unlock;
	}

	win->lockout = new;

	if (old == expect && new == WIN_LOCKED)
		atomic_inc(&win->msc->user_count);
	else if (old == expect && old == WIN_LOCKED)
		atomic_dec(&win->msc->user_count);

unlock:
	spin_unlock_irqrestore(&win->lo_lock, flags);

	if (ret) {
		if (expect == WIN_READY && old == WIN_LOCKED)
			return -EBUSY;

		/* from intel_th_msc_window_unlock(), don't warn if not locked */
		if (expect == WIN_LOCKED && old == new)
			return 0;

		dev_warn_ratelimited(msc_dev(win->msc),
				     "expected lockout state %d, got %d\n",
				     expect, old);
	}

	return ret;
}
/**
 * msc_configure() - set up MSC hardware
 * @msc:	the MSC device to configure
 *
 * Program storage mode, wrapping, burst length and trace buffer address
 * into a given MSC. Then, enable tracing and set msc::enabled.
 * The latter is serialized on msc::buf_mutex, so make sure to hold it.
 */
static int msc_configure(struct msc *msc)
{
	u32 reg;

	lockdep_assert_held(&msc->buf_mutex);

	if (msc->mode > MSC_MODE_MULTI)
		return -EINVAL;

	if (msc->mode == MSC_MODE_MULTI) {
		if (msc_win_set_lockout(msc->cur_win, WIN_READY, WIN_INUSE))
			return -EBUSY;

		msc_buffer_clear_hw_header(msc);
	}

	msc->orig_addr = ioread32(msc->reg_base + REG_MSU_MSC0BAR);
	msc->orig_sz   = ioread32(msc->reg_base + REG_MSU_MSC0SIZE);

	reg = msc->base_addr >> PAGE_SHIFT;
	iowrite32(reg, msc->reg_base + REG_MSU_MSC0BAR);

	if (msc->mode == MSC_MODE_SINGLE) {
		reg = msc->nr_pages;
		iowrite32(reg, msc->reg_base + REG_MSU_MSC0SIZE);
	}

	reg = ioread32(msc->reg_base + REG_MSU_MSC0CTL);
	reg &= ~(MSC_MODE | MSC_WRAPEN | MSC_EN | MSC_RD_HDR_OVRD);

	reg |= MSC_EN;
	reg |= msc->mode << __ffs(MSC_MODE);
	reg |= msc->burst_len << __ffs(MSC_LEN);

	if (msc->wrap)
		reg |= MSC_WRAPEN;

	iowrite32(reg, msc->reg_base + REG_MSU_MSC0CTL);

	intel_th_msu_init(msc);

	msc->thdev->output.multiblock = msc->mode == MSC_MODE_MULTI;
	intel_th_trace_enable(msc->thdev);
	msc->enabled = 1;

	if (msc->mbuf && msc->mbuf->activate)
		msc->mbuf->activate(msc->mbuf_priv);

	return 0;
}

/**
 * msc_disable() - disable MSC hardware
 * @msc:	MSC device to disable
 *
 * If @msc is enabled, disable tracing on the switch and then disable MSC
 * storage. Caller must hold msc::buf_mutex.
 */
static void msc_disable(struct msc *msc)
{
	struct msc_window *win = msc->cur_win;
	u32 reg;

	lockdep_assert_held(&msc->buf_mutex);

	if (msc->mode == MSC_MODE_MULTI)
		msc_win_set_lockout(win, WIN_INUSE, WIN_LOCKED);

	if (msc->mbuf && msc->mbuf->deactivate)
		msc->mbuf->deactivate(msc->mbuf_priv);
	intel_th_msu_deinit(msc);
	intel_th_trace_disable(msc->thdev);

	if (msc->mode == MSC_MODE_SINGLE) {
		reg = ioread32(msc->reg_base + REG_MSU_MSC0STS);
		msc->single_wrap = !!(reg & MSCSTS_WRAPSTAT);

		reg = ioread32(msc->reg_base + REG_MSU_MSC0MWP);
		msc->single_sz = reg & ((msc->nr_pages << PAGE_SHIFT) - 1);
		dev_dbg(msc_dev(msc), "MSCnMWP: %08x/%08lx, wrap: %d\n",
			reg, msc->single_sz, msc->single_wrap);
	}

	reg = ioread32(msc->reg_base + REG_MSU_MSC0CTL);
	reg &= ~MSC_EN;
	iowrite32(reg, msc->reg_base + REG_MSU_MSC0CTL);

	if (msc->mbuf && msc->mbuf->ready)
		msc->mbuf->ready(msc->mbuf_priv, win->sgt,
				 msc_win_total_sz(win));

	msc->enabled = 0;

	iowrite32(msc->orig_addr, msc->reg_base + REG_MSU_MSC0BAR);
	iowrite32(msc->orig_sz, msc->reg_base + REG_MSU_MSC0SIZE);

	dev_dbg(msc_dev(msc), "MSCnNWSA: %08x\n",
		ioread32(msc->reg_base + REG_MSU_MSC0NWSA));

	reg = ioread32(msc->reg_base + REG_MSU_MSC0STS);
	dev_dbg(msc_dev(msc), "MSCnSTS: %08x\n", reg);

	reg = ioread32(msc->reg_base + REG_MSU_MSUSTS);
	reg &= msc->index ? MSUSTS_MSC1BLAST : MSUSTS_MSC0BLAST;
	iowrite32(reg, msc->reg_base + REG_MSU_MSUSTS);
}

static int intel_th_msc_activate(struct intel_th_device *thdev)
{
	struct msc *msc = dev_get_drvdata(&thdev->dev);
	int ret = -EBUSY;

	if (!atomic_inc_unless_negative(&msc->user_count))
		return -ENODEV;

	mutex_lock(&msc->buf_mutex);

	/* if there are readers, refuse */
	if (list_empty(&msc->iter_list))
		ret = msc_configure(msc);

	mutex_unlock(&msc->buf_mutex);

	if (ret)
		atomic_dec(&msc->user_count);

	return ret;
}

static void intel_th_msc_deactivate(struct intel_th_device *thdev)
{
	struct msc *msc = dev_get_drvdata(&thdev->dev);

	mutex_lock(&msc->buf_mutex);
	if (msc->enabled) {
		msc_disable(msc);
		atomic_dec(&msc->user_count);
	}
	mutex_unlock(&msc->buf_mutex);
}

/**
 * msc_buffer_contig_alloc() - allocate a contiguous buffer for SINGLE mode
 * @msc:	MSC device
 * @size:	allocation size in bytes
 *
 * This modifies msc::base, which requires msc::buf_mutex to serialize, so the
 * caller is expected to hold it.
 *
 * Return:	0 on success, -errno otherwise.
 */
static int msc_buffer_contig_alloc(struct msc *msc, unsigned long size)
{
	unsigned long nr_pages = size >> PAGE_SHIFT;
	unsigned int order = get_order(size);
	struct page *page;
	int ret;

	if (!size)
		return 0;

	ret = sg_alloc_table(&msc->single_sgt, 1, GFP_KERNEL);
	if (ret)
		goto err_out;

	ret = -ENOMEM;
	page = alloc_pages(GFP_KERNEL | __GFP_ZERO | GFP_DMA32, order);
	if (!page)
		goto err_free_sgt;

	split_page(page, order);
	sg_set_buf(msc->single_sgt.sgl, page_address(page), size);

	ret = dma_map_sg(msc_dev(msc)->parent->parent, msc->single_sgt.sgl, 1,
			 DMA_FROM_DEVICE);
	if (ret < 0)
		goto err_free_pages;

	msc->nr_pages = nr_pages;
	msc->base = page_address(page);
	msc->base_addr = sg_dma_address(msc->single_sgt.sgl);

	return 0;

err_free_pages:
	__free_pages(page, order);

err_free_sgt:
	sg_free_table(&msc->single_sgt);

err_out:
	return ret;
}

/**
 * msc_buffer_contig_free() - free a contiguous buffer
 * @msc:	MSC configured in SINGLE mode
 */
static void msc_buffer_contig_free(struct msc *msc)
{
	unsigned long off;

	dma_unmap_sg(msc_dev(msc)->parent->parent, msc->single_sgt.sgl,
		     1, DMA_FROM_DEVICE);
	sg_free_table(&msc->single_sgt);

	for (off = 0; off < msc->nr_pages << PAGE_SHIFT; off += PAGE_SIZE) {
		struct page *page = virt_to_page(msc->base + off);

		page->mapping = NULL;
		__free_page(page);
	}

	msc->nr_pages = 0;
}

/**
 * msc_buffer_contig_get_page() - find a page at a given offset
 * @msc:	MSC configured in SINGLE mode
 * @pgoff:	page offset
 *
 * Return:	page, if @pgoff is within the range, NULL otherwise.
 */
static struct page *msc_buffer_contig_get_page(struct msc *msc,
					       unsigned long pgoff)
{
	if (pgoff >= msc->nr_pages)
		return NULL;

	return virt_to_page(msc->base + (pgoff << PAGE_SHIFT));
}

static int __msc_buffer_win_alloc(struct msc_window *win,
				  unsigned int nr_segs)
{
	struct scatterlist *sg_ptr;
	void *block;
	int i, ret;

	ret = sg_alloc_table(win->sgt, nr_segs, GFP_KERNEL);
	if (ret)
		return -ENOMEM;

	for_each_sg(win->sgt->sgl, sg_ptr, nr_segs, i) {
		block = dma_alloc_coherent(msc_dev(win->msc)->parent->parent,
					  PAGE_SIZE, &sg_dma_address(sg_ptr),
					  GFP_KERNEL);
		if (!block)
			goto err_nomem;

		sg_set_buf(sg_ptr, block, PAGE_SIZE);
	}

	return nr_segs;

err_nomem:
	for_each_sg(win->sgt->sgl, sg_ptr, i, ret)
		dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE,
				  sg_virt(sg_ptr), sg_dma_address(sg_ptr));

	sg_free_table(win->sgt);

	return -ENOMEM;
}

#ifdef CONFIG_X86
static void msc_buffer_set_uc(struct msc_window *win, unsigned int nr_segs)
{
	struct scatterlist *sg_ptr;
	int i;

	for_each_sg(win->sgt->sgl, sg_ptr, nr_segs, i) {
		/* Set the page as uncached */
		set_memory_uc((unsigned long)sg_virt(sg_ptr),
			      PFN_DOWN(sg_ptr->length));
	}
}

static void msc_buffer_set_wb(struct msc_window *win)
{
	struct scatterlist *sg_ptr;
	int i;

	for_each_sg(win->sgt->sgl, sg_ptr, win->nr_segs, i) {
		/* Reset the page to write-back */
		set_memory_wb((unsigned long)sg_virt(sg_ptr),
			      PFN_DOWN(sg_ptr->length));
	}
}
#else /* !X86 */
static inline void
msc_buffer_set_uc(struct msc_window *win, unsigned int nr_segs) {}
static inline void msc_buffer_set_wb(struct msc_window *win) {}
#endif /* CONFIG_X86 */

/**
 * msc_buffer_win_alloc() - alloc a window for a multiblock mode
 * @msc:	MSC device
 * @nr_blocks:	number of pages in this window
 *
 * This modifies msc::win_list and msc::base, which requires msc::buf_mutex
 * to serialize, so the caller is expected to hold it.
 *
 * Return:	0 on success, -errno otherwise.
 */
static int msc_buffer_win_alloc(struct msc *msc, unsigned int nr_blocks)
{
	struct msc_window *win;
	int ret = -ENOMEM;

	if (!nr_blocks)
		return 0;

	win = kzalloc(sizeof(*win), GFP_KERNEL);
	if (!win)
		return -ENOMEM;

	win->msc = msc;
	win->sgt = &win->_sgt;
	win->lockout = WIN_READY;
	spin_lock_init(&win->lo_lock);

	if (!list_empty(&msc->win_list)) {
		struct msc_window *prev = list_last_entry(&msc->win_list,
							  struct msc_window,
							  entry);

		win->pgoff = prev->pgoff + prev->nr_blocks;
	}

	if (msc->mbuf && msc->mbuf->alloc_window)
		ret = msc->mbuf->alloc_window(msc->mbuf_priv, &win->sgt,
					      nr_blocks << PAGE_SHIFT);
	else
		ret = __msc_buffer_win_alloc(win, nr_blocks);

	if (ret <= 0)
		goto err_nomem;

	msc_buffer_set_uc(win, ret);

	win->nr_segs = ret;
	win->nr_blocks = nr_blocks;

	if (list_empty(&msc->win_list)) {
		msc->base = msc_win_base(win);
		msc->base_addr = msc_win_base_dma(win);
		msc->cur_win = win;
	}

	list_add_tail(&win->entry, &msc->win_list);
	msc->nr_pages += nr_blocks;

	return 0;

err_nomem:
	kfree(win);

	return ret;
}

static void __msc_buffer_win_free(struct msc *msc, struct msc_window *win)
{
	struct scatterlist *sg;
	int i;

	for_each_sg(win->sgt->sgl, sg, win->nr_segs, i) {
		struct page *page = sg_page(sg);

		page->mapping = NULL;
		dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE,
				  sg_virt(sg), sg_dma_address(sg));
	}
	sg_free_table(win->sgt);
}

/**
 * msc_buffer_win_free() - free a window from MSC's window list
 * @msc:	MSC device
 * @win:	window to free
 *
 * This modifies msc::win_list and msc::base, which requires msc::buf_mutex
 * to serialize, so the caller is expected to hold it.
 */
static void msc_buffer_win_free(struct msc *msc, struct msc_window *win)
{
	msc->nr_pages -= win->nr_blocks;

	list_del(&win->entry);
	if (list_empty(&msc->win_list)) {
		msc->base = NULL;
		msc->base_addr = 0;
	}

	msc_buffer_set_wb(win);

	if (msc->mbuf && msc->mbuf->free_window)
		msc->mbuf->free_window(msc->mbuf_priv, win->sgt);
	else
		__msc_buffer_win_free(msc, win);

	kfree(win);
}

/**
 * msc_buffer_relink() - set up block descriptors for multiblock mode
 * @msc:	MSC device
 *
 * This traverses msc::win_list, which requires msc::buf_mutex to serialize,
 * so the caller is expected to hold it.
 */
static void msc_buffer_relink(struct msc *msc)
{
	struct msc_window *win, *next_win;

	/* call with msc::mutex locked */
	list_for_each_entry(win, &msc->win_list, entry) {
		struct scatterlist *sg;
		unsigned int blk;
		u32 sw_tag = 0;

		/*
		 * Last window's next_win should point to the first window
		 * and MSC_SW_TAG_LASTWIN should be set.
		 */
		if (msc_is_last_win(win)) {
			sw_tag |= MSC_SW_TAG_LASTWIN;
			next_win = list_first_entry(&msc->win_list,
						    struct msc_window, entry);
		} else {
			next_win = list_next_entry(win, entry);
		}

		for_each_sg(win->sgt->sgl, sg, win->nr_segs, blk) {
			struct msc_block_desc *bdesc = sg_virt(sg);

			memset(bdesc, 0, sizeof(*bdesc));

			bdesc->next_win = msc_win_base_pfn(next_win);

			/*
			 * Similarly to last window, last block should point
			 * to the first one.
			 */
			if (blk == win->nr_segs - 1) {
				sw_tag |= MSC_SW_TAG_LASTBLK;
				bdesc->next_blk = msc_win_base_pfn(win);
			} else {
				dma_addr_t addr = sg_dma_address(sg_next(sg));

				bdesc->next_blk = PFN_DOWN(addr);
			}

			bdesc->sw_tag = sw_tag;
			bdesc->block_sz = sg->length / 64;
		}
	}

	/*
	 * Make the above writes globally visible before tracing is
	 * enabled to make sure hardware sees them coherently.
	 */
	wmb();
}

static void msc_buffer_multi_free(struct msc *msc)
{
	struct msc_window *win, *iter;

	list_for_each_entry_safe(win, iter, &msc->win_list, entry)
		msc_buffer_win_free(msc, win);
}

static int msc_buffer_multi_alloc(struct msc *msc, unsigned long *nr_pages,
				  unsigned int nr_wins)
{
	int ret, i;

	for (i = 0; i < nr_wins; i++) {
		ret = msc_buffer_win_alloc(msc, nr_pages[i]);
		if (ret) {
			msc_buffer_multi_free(msc);
			return ret;
		}
	}

	msc_buffer_relink(msc);

	return 0;
}

/**
 * msc_buffer_free() - free buffers for MSC
 * @msc:	MSC device
 *
 * Free MSC's storage buffers.
 *
 * This modifies msc::win_list and msc::base, which requires msc::buf_mutex to
 * serialize, so the caller is expected to hold it.
 */
static void msc_buffer_free(struct msc *msc)
{
	if (msc->mode == MSC_MODE_SINGLE)
		msc_buffer_contig_free(msc);
	else if (msc->mode == MSC_MODE_MULTI)
		msc_buffer_multi_free(msc);
}

/**
 * msc_buffer_alloc() - allocate a buffer for MSC
 * @msc:	MSC device
 * @size:	allocation size in bytes
 *
 * Allocate a storage buffer for MSC, depending on the msc::mode, it will be
 * either done via msc_buffer_contig_alloc() for SINGLE operation mode or
 * msc_buffer_win_alloc() for multiblock operation. The latter allocates one
 * window per invocation, so in multiblock mode this can be called multiple
 * times for the same MSC to allocate multiple windows.
 *
 * This modifies msc::win_list and msc::base, which requires msc::buf_mutex
 * to serialize, so the caller is expected to hold it.
 *
 * Return:	0 on success, -errno otherwise.
 */
static int msc_buffer_alloc(struct msc *msc, unsigned long *nr_pages,
			    unsigned int nr_wins)
{
	int ret;

	/* -1: buffer not allocated */
	if (atomic_read(&msc->user_count) != -1)
		return -EBUSY;

	if (msc->mode == MSC_MODE_SINGLE) {
		if (nr_wins != 1)
			return -EINVAL;

		ret = msc_buffer_contig_alloc(msc, nr_pages[0] << PAGE_SHIFT);
	} else if (msc->mode == MSC_MODE_MULTI) {
		ret = msc_buffer_multi_alloc(msc, nr_pages, nr_wins);
	} else {
		ret = -EINVAL;
	}

	if (!ret) {
		/* allocation should be visible before the counter goes to 0 */
		smp_mb__before_atomic();

		if (WARN_ON_ONCE(atomic_cmpxchg(&msc->user_count, -1, 0) != -1))
			return -EINVAL;
	}

	return ret;
}

/**
 * msc_buffer_unlocked_free_unless_used() - free a buffer unless it's in use
 * @msc:	MSC device
 *
 * This will free MSC buffer unless it is in use or there is no allocated
 * buffer.
 * Caller needs to hold msc::buf_mutex.
 *
 * Return:	0 on successful deallocation or if there was no buffer to
 *		deallocate, -EBUSY if there are active users.
 */
static int msc_buffer_unlocked_free_unless_used(struct msc *msc)
{
	int count, ret = 0;

	count = atomic_cmpxchg(&msc->user_count, 0, -1);

	/* > 0: buffer is allocated and has users */
	if (count > 0)
		ret = -EBUSY;
	/* 0: buffer is allocated, no users */
	else if (!count)
		msc_buffer_free(msc);
	/* < 0: no buffer, nothing to do */

	return ret;
}

/**
 * msc_buffer_free_unless_used() - free a buffer unless it's in use
 * @msc:	MSC device
 *
 * This is a locked version of msc_buffer_unlocked_free_unless_used().
 */
static int msc_buffer_free_unless_used(struct msc *msc)
{
	int ret;

	mutex_lock(&msc->buf_mutex);
	ret = msc_buffer_unlocked_free_unless_used(msc);
	mutex_unlock(&msc->buf_mutex);

	return ret;
}

/**
 * msc_buffer_get_page() - get MSC buffer page at a given offset
 * @msc:	MSC device
 * @pgoff:	page offset into the storage buffer
 *
 * This traverses msc::win_list, so holding msc::buf_mutex is expected from
 * the caller.
 *
 * Return:	page if @pgoff corresponds to a valid buffer page or NULL.
 */
static struct page *msc_buffer_get_page(struct msc *msc, unsigned long pgoff)
{
	struct msc_window *win;
	struct scatterlist *sg;
	unsigned int blk;

	if (msc->mode == MSC_MODE_SINGLE)
		return msc_buffer_contig_get_page(msc, pgoff);

	list_for_each_entry(win, &msc->win_list, entry)
		if (pgoff >= win->pgoff && pgoff < win->pgoff + win->nr_blocks)
			goto found;

	return NULL;

found:
	pgoff -= win->pgoff;

	for_each_sg(win->sgt->sgl, sg, win->nr_segs, blk) {
		struct page *page = sg_page(sg);
		size_t pgsz = PFN_DOWN(sg->length);

		if (pgoff < pgsz)
			return page + pgoff;

		pgoff -= pgsz;
	}

	return NULL;
}

/**
 * struct msc_win_to_user_struct - data for copy_to_user() callback
 * @buf:	userspace buffer to copy data to
 * @offset:	running offset
 */
struct msc_win_to_user_struct {
	char __user	*buf;
	unsigned long	offset;
};

/**
 * msc_win_to_user() - iterator for msc_buffer_iterate() to copy data to user
 * @data:	callback's private data
 * @src:	source buffer
 * @len:	amount of data to copy from the source buffer
 */
static unsigned long msc_win_to_user(void *data, void *src, size_t len)
{
	struct msc_win_to_user_struct *u = data;
	unsigned long ret;

	ret = copy_to_user(u->buf + u->offset, src, len);
	u->offset += len - ret;

	return ret;
}


/*
 * file operations' callbacks
 */

static int intel_th_msc_open(struct inode *inode, struct file *file)
{
	struct intel_th_device *thdev = file->private_data;
	struct msc *msc = dev_get_drvdata(&thdev->dev);
	struct msc_iter *iter;

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

	iter = msc_iter_install(msc);
	if (IS_ERR(iter))
		return PTR_ERR(iter);

	file->private_data = iter;

	return nonseekable_open(inode, file);
}

static int intel_th_msc_release(struct inode *inode, struct file *file)
{
	struct msc_iter *iter = file->private_data;
	struct msc *msc = iter->msc;

	msc_iter_remove(iter, msc);

	return 0;
}

static ssize_t
msc_single_to_user(struct msc *msc, char __user *buf, loff_t off, size_t len)
{
	unsigned long size = msc->nr_pages << PAGE_SHIFT, rem = len;
	unsigned long start = off, tocopy = 0;

	if (msc->single_wrap) {
		start += msc->single_sz;
		if (start < size) {
			tocopy = min(rem, size - start);
			if (copy_to_user(buf, msc->base + start, tocopy))
				return -EFAULT;

			buf += tocopy;
			rem -= tocopy;
			start += tocopy;
		}

		start &= size - 1;
		if (rem) {
			tocopy = min(rem, msc->single_sz - start);
			if (copy_to_user(buf, msc->base + start, tocopy))
				return -EFAULT;

			rem -= tocopy;
		}

		return len - rem;
	}

	if (copy_to_user(buf, msc->base + start, rem))
		return -EFAULT;

	return len;
}

static ssize_t intel_th_msc_read(struct file *file, char __user *buf,
				 size_t len, loff_t *ppos)
{
	struct msc_iter *iter = file->private_data;
	struct msc *msc = iter->msc;
	size_t size;
	loff_t off = *ppos;
	ssize_t ret = 0;

	if (!atomic_inc_unless_negative(&msc->user_count))
		return 0;

	if (msc->mode == MSC_MODE_SINGLE && !msc->single_wrap)
		size = msc->single_sz;
	else
		size = msc->nr_pages << PAGE_SHIFT;

	if (!size)
		goto put_count;

	if (off >= size)
		goto put_count;

	if (off + len >= size)
		len = size - off;

	if (msc->mode == MSC_MODE_SINGLE) {
		ret = msc_single_to_user(msc, buf, off, len);
		if (ret >= 0)
			*ppos += ret;
	} else if (msc->mode == MSC_MODE_MULTI) {
		struct msc_win_to_user_struct u = {
			.buf	= buf,
			.offset	= 0,
		};

		ret = msc_buffer_iterate(iter, len, &u, msc_win_to_user);
		if (ret >= 0)
			*ppos = iter->offset;
	} else {
		ret = -EINVAL;
	}

put_count:
	atomic_dec(&msc->user_count);

	return ret;
}

/*
 * vm operations callbacks (vm_ops)
 */

static void msc_mmap_open(struct vm_area_struct *vma)
{
	struct msc_iter *iter = vma->vm_file->private_data;
	struct msc *msc = iter->msc;

	atomic_inc(&msc->mmap_count);
}

static void msc_mmap_close(struct vm_area_struct *vma)
{
	struct msc_iter *iter = vma->vm_file->private_data;
	struct msc *msc = iter->msc;
	unsigned long pg;

	if (!atomic_dec_and_mutex_lock(&msc->mmap_count, &msc->buf_mutex))
		return;

	/* drop page _refcounts */
	for (pg = 0; pg < msc->nr_pages; pg++) {
		struct page *page = msc_buffer_get_page(msc, pg);

		if (WARN_ON_ONCE(!page))
			continue;

		if (page->mapping)
			page->mapping = NULL;
	}

	/* last mapping -- drop user_count */
	atomic_dec(&msc->user_count);
	mutex_unlock(&msc->buf_mutex);
}

static vm_fault_t msc_mmap_fault(struct vm_fault *vmf)
{
	struct msc_iter *iter = vmf->vma->vm_file->private_data;
	struct msc *msc = iter->msc;

	vmf->page = msc_buffer_get_page(msc, vmf->pgoff);
	if (!vmf->page)
		return VM_FAULT_SIGBUS;

	get_page(vmf->page);
	vmf->page->mapping = vmf->vma->vm_file->f_mapping;
	vmf->page->index = vmf->pgoff;

	return 0;
}

static const struct vm_operations_struct msc_mmap_ops = {
	.open	= msc_mmap_open,
	.close	= msc_mmap_close,
	.fault	= msc_mmap_fault,
};

static int intel_th_msc_mmap(struct file *file, struct vm_area_struct *vma)
{
	unsigned long size = vma->vm_end - vma->vm_start;
	struct msc_iter *iter = vma->vm_file->private_data;
	struct msc *msc = iter->msc;
	int ret = -EINVAL;

	if (!size || offset_in_page(size))
		return -EINVAL;

	if (vma->vm_pgoff)
		return -EINVAL;

	/* grab user_count once per mmap; drop in msc_mmap_close() */
	if (!atomic_inc_unless_negative(&msc->user_count))
		return -EINVAL;

	if (msc->mode != MSC_MODE_SINGLE &&
	    msc->mode != MSC_MODE_MULTI)
		goto out;

	if (size >> PAGE_SHIFT != msc->nr_pages)
		goto out;

	atomic_set(&msc->mmap_count, 1);
	ret = 0;

out:
	if (ret)
		atomic_dec(&msc->user_count);

	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
	vma->vm_flags |= VM_DONTEXPAND | VM_DONTCOPY;
	vma->vm_ops = &msc_mmap_ops;
	return ret;
}

static const struct file_operations intel_th_msc_fops = {
	.open		= intel_th_msc_open,
	.release	= intel_th_msc_release,
	.read		= intel_th_msc_read,
	.mmap		= intel_th_msc_mmap,
	.llseek		= no_llseek,
	.owner		= THIS_MODULE,
};

static void intel_th_msc_wait_empty(struct intel_th_device *thdev)
{
	struct msc *msc = dev_get_drvdata(&thdev->dev);
	unsigned long count;
	u32 reg;

	for (reg = 0, count = MSC_PLE_WAITLOOP_DEPTH;
	     count && !(reg & MSCSTS_PLE); count--) {
		reg = __raw_readl(msc->reg_base + REG_MSU_MSC0STS);
		cpu_relax();
	}

	if (!count)
		dev_dbg(msc_dev(msc), "timeout waiting for MSC0 PLE\n");
}

static int intel_th_msc_init(struct msc *msc)
{
	atomic_set(&msc->user_count, -1);

	msc->mode = MSC_MODE_MULTI;
	mutex_init(&msc->buf_mutex);
	INIT_LIST_HEAD(&msc->win_list);
	INIT_LIST_HEAD(&msc->iter_list);

	msc->burst_len =
		(ioread32(msc->reg_base + REG_MSU_MSC0CTL) & MSC_LEN) >>
		__ffs(MSC_LEN);

	return 0;
}

static int msc_win_switch(struct msc *msc)
{
	struct msc_window *first;

	if (list_empty(&msc->win_list))
		return -EINVAL;

	first = list_first_entry(&msc->win_list, struct msc_window, entry);

	if (msc_is_last_win(msc->cur_win))
		msc->cur_win = first;
	else
		msc->cur_win = list_next_entry(msc->cur_win, entry);

	msc->base = msc_win_base(msc->cur_win);
	msc->base_addr = msc_win_base_dma(msc->cur_win);

	intel_th_trace_switch(msc->thdev);

	return 0;
}

/**
 * intel_th_msc_window_unlock - put the window back in rotation
 * @dev:	MSC device to which this relates
 * @sgt:	buffer's sg_table for the window, does nothing if NULL
 */
void intel_th_msc_window_unlock(struct device *dev, struct sg_table *sgt)
{
	struct msc *msc = dev_get_drvdata(dev);
	struct msc_window *win;

	if (!sgt)
		return;

	win = msc_find_window(msc, sgt, false);
	if (!win)
		return;

	msc_win_set_lockout(win, WIN_LOCKED, WIN_READY);
}
EXPORT_SYMBOL_GPL(intel_th_msc_window_unlock);

static void msc_work(struct work_struct *work)
{
	struct msc *msc = container_of(work, struct msc, work);

	intel_th_msc_deactivate(msc->thdev);
}

static irqreturn_t intel_th_msc_interrupt(struct intel_th_device *thdev)
{
	struct msc *msc = dev_get_drvdata(&thdev->dev);
	u32 msusts = ioread32(msc->msu_base + REG_MSU_MSUSTS);
	u32 mask = msc->index ? MSUSTS_MSC1BLAST : MSUSTS_MSC0BLAST;
	struct msc_window *win, *next_win;

	if (!msc->do_irq || !msc->mbuf)
		return IRQ_NONE;

	msusts &= mask;

	if (!msusts)
		return msc->enabled ? IRQ_HANDLED : IRQ_NONE;

	iowrite32(msusts, msc->msu_base + REG_MSU_MSUSTS);

	if (!msc->enabled)
		return IRQ_NONE;

	/* grab the window before we do the switch */
	win = msc->cur_win;
	if (!win)
		return IRQ_HANDLED;
	next_win = msc_next_window(win);
	if (!next_win)
		return IRQ_HANDLED;

	/* next window: if READY, proceed, if LOCKED, stop the trace */
	if (msc_win_set_lockout(next_win, WIN_READY, WIN_INUSE)) {
		schedule_work(&msc->work);
		return IRQ_HANDLED;
	}

	/* current window: INUSE -> LOCKED */
	msc_win_set_lockout(win, WIN_INUSE, WIN_LOCKED);

	msc_win_switch(msc);

	if (msc->mbuf && msc->mbuf->ready)
		msc->mbuf->ready(msc->mbuf_priv, win->sgt,
				 msc_win_total_sz(win));

	return IRQ_HANDLED;
}

static const char * const msc_mode[] = {
	[MSC_MODE_SINGLE]	= "single",
	[MSC_MODE_MULTI]	= "multi",
	[MSC_MODE_EXI]		= "ExI",
	[MSC_MODE_DEBUG]	= "debug",
};

static ssize_t
wrap_show(struct device *dev, struct device_attribute *attr, char *buf)
{
	struct msc *msc = dev_get_drvdata(dev);

	return scnprintf(buf, PAGE_SIZE, "%d\n", msc->wrap);
}

static ssize_t
wrap_store(struct device *dev, struct device_attribute *attr, const char *buf,
	   size_t size)
{
	struct msc *msc = dev_get_drvdata(dev);
	unsigned long val;
	int ret;

	ret = kstrtoul(buf, 10, &val);
	if (ret)
		return ret;

	msc->wrap = !!val;

	return size;
}

static DEVICE_ATTR_RW(wrap);

static void msc_buffer_unassign(struct msc *msc)
{
	lockdep_assert_held(&msc->buf_mutex);

	if (!msc->mbuf)
		return;

	msc->mbuf->unassign(msc->mbuf_priv);
	msu_buffer_put(msc->mbuf);
	msc->mbuf_priv = NULL;
	msc->mbuf = NULL;
}

static ssize_t
mode_show(struct device *dev, struct device_attribute *attr, char *buf)
{
	struct msc *msc = dev_get_drvdata(dev);
	const char *mode = msc_mode[msc->mode];
	ssize_t ret;

	mutex_lock(&msc->buf_mutex);
	if (msc->mbuf)
		mode = msc->mbuf->name;
	ret = scnprintf(buf, PAGE_SIZE, "%s\n", mode);
	mutex_unlock(&msc->buf_mutex);

	return ret;
}

static ssize_t
mode_store(struct device *dev, struct device_attribute *attr, const char *buf,
	   size_t size)
{
	const struct msu_buffer *mbuf = NULL;
	struct msc *msc = dev_get_drvdata(dev);
	size_t len = size;
	char *cp, *mode;
	int i, ret;

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

	cp = memchr(buf, '\n', len);
	if (cp)
		len = cp - buf;

	mode = kstrndup(buf, len, GFP_KERNEL);
	if (!mode)
		return -ENOMEM;

	i = match_string(msc_mode, ARRAY_SIZE(msc_mode), mode);
	if (i >= 0) {
		kfree(mode);
		goto found;
	}

	/* Buffer sinks only work with a usable IRQ */
	if (!msc->do_irq) {
		kfree(mode);
		return -EINVAL;
	}

	mbuf = msu_buffer_get(mode);
	kfree(mode);
	if (mbuf)
		goto found;

	return -EINVAL;

found:
	mutex_lock(&msc->buf_mutex);
	ret = 0;

	/* Same buffer: do nothing */
	if (mbuf && mbuf == msc->mbuf) {
		/* put the extra reference we just got */
		msu_buffer_put(mbuf);
		goto unlock;
	}

	ret = msc_buffer_unlocked_free_unless_used(msc);
	if (ret)
		goto unlock;

	if (mbuf) {
		void *mbuf_priv = mbuf->assign(dev, &i);

		if (!mbuf_priv) {
			ret = -ENOMEM;
			goto unlock;
		}

		msc_buffer_unassign(msc);
		msc->mbuf_priv = mbuf_priv;
		msc->mbuf = mbuf;
	} else {
		msc_buffer_unassign(msc);
	}

	msc->mode = i;

unlock:
	if (ret && mbuf)
		msu_buffer_put(mbuf);
	mutex_unlock(&msc->buf_mutex);

	return ret ? ret : size;
}

static DEVICE_ATTR_RW(mode);

static ssize_t
nr_pages_show(struct device *dev, struct device_attribute *attr, char *buf)
{
	struct msc *msc = dev_get_drvdata(dev);
	struct msc_window *win;
	size_t count = 0;

	mutex_lock(&msc->buf_mutex);

	if (msc->mode == MSC_MODE_SINGLE)
		count = scnprintf(buf, PAGE_SIZE, "%ld\n", msc->nr_pages);
	else if (msc->mode == MSC_MODE_MULTI) {
		list_for_each_entry(win, &msc->win_list, entry) {
			count += scnprintf(buf + count, PAGE_SIZE - count,
					   "%d%c", win->nr_blocks,
					   msc_is_last_win(win) ? '\n' : ',');
		}
	} else {
		count = scnprintf(buf, PAGE_SIZE, "unsupported\n");
	}

	mutex_unlock(&msc->buf_mutex);

	return count;
}

static ssize_t
nr_pages_store(struct device *dev, struct device_attribute *attr,
	       const char *buf, size_t size)
{
	struct msc *msc = dev_get_drvdata(dev);
	unsigned long val, *win = NULL, *rewin;
	size_t len = size;
	const char *p = buf;
	char *end, *s;
	int ret, nr_wins = 0;

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

	ret = msc_buffer_free_unless_used(msc);
	if (ret)
		return ret;

	/* scan the comma-separated list of allocation sizes */
	end = memchr(buf, '\n', len);
	if (end)
		len = end - buf;

	do {
		end = memchr(p, ',', len);
		s = kstrndup(p, end ? end - p : len, GFP_KERNEL);
		if (!s) {
			ret = -ENOMEM;
			goto free_win;
		}

		ret = kstrtoul(s, 10, &val);
		kfree(s);

		if (ret || !val)
			goto free_win;

		if (nr_wins && msc->mode == MSC_MODE_SINGLE) {
			ret = -EINVAL;
			goto free_win;
		}

		nr_wins++;
		rewin = krealloc(win, sizeof(*win) * nr_wins, GFP_KERNEL);
		if (!rewin) {
			kfree(win);
			return -ENOMEM;
		}

		win = rewin;
		win[nr_wins - 1] = val;

		if (!end)
			break;

		/* consume the number and the following comma, hence +1 */
		len -= end - p + 1;
		p = end + 1;
	} while (len);

	mutex_lock(&msc->buf_mutex);
	ret = msc_buffer_alloc(msc, win, nr_wins);
	mutex_unlock(&msc->buf_mutex);

free_win:
	kfree(win);

	return ret ? ret : size;
}

static DEVICE_ATTR_RW(nr_pages);

static ssize_t
win_switch_store(struct device *dev, struct device_attribute *attr,
		 const char *buf, size_t size)
{
	struct msc *msc = dev_get_drvdata(dev);
	unsigned long val;
	int ret;

	ret = kstrtoul(buf, 10, &val);
	if (ret)
		return ret;

	if (val != 1)
		return -EINVAL;

	ret = -EINVAL;
	mutex_lock(&msc->buf_mutex);
	/*
	 * Window switch can only happen in the "multi" mode.
	 * If a external buffer is engaged, they have the full
	 * control over window switching.
	 */
	if (msc->mode == MSC_MODE_MULTI && !msc->mbuf)
		ret = msc_win_switch(msc);
	mutex_unlock(&msc->buf_mutex);

	return ret ? ret : size;
}

static DEVICE_ATTR_WO(win_switch);

static struct attribute *msc_output_attrs[] = {
	&dev_attr_wrap.attr,
	&dev_attr_mode.attr,
	&dev_attr_nr_pages.attr,
	&dev_attr_win_switch.attr,
	NULL,
};

static struct attribute_group msc_output_group = {
	.attrs	= msc_output_attrs,
};

static int intel_th_msc_probe(struct intel_th_device *thdev)
{
	struct device *dev = &thdev->dev;
	struct resource *res;
	struct msc *msc;
	void __iomem *base;
	int err;

	res = intel_th_device_get_resource(thdev, IORESOURCE_MEM, 0);
	if (!res)
		return -ENODEV;

	base = devm_ioremap(dev, res->start, resource_size(res));
	if (!base)
		return -ENOMEM;

	msc = devm_kzalloc(dev, sizeof(*msc), GFP_KERNEL);
	if (!msc)
		return -ENOMEM;

	res = intel_th_device_get_resource(thdev, IORESOURCE_IRQ, 1);
	if (!res)
		msc->do_irq = 1;

	msc->index = thdev->id;

	msc->thdev = thdev;
	msc->reg_base = base + msc->index * 0x100;
	msc->msu_base = base;

	INIT_WORK(&msc->work, msc_work);
	err = intel_th_msc_init(msc);
	if (err)
		return err;

	dev_set_drvdata(dev, msc);

	return 0;
}

static void intel_th_msc_remove(struct intel_th_device *thdev)
{
	struct msc *msc = dev_get_drvdata(&thdev->dev);
	int ret;

	intel_th_msc_deactivate(thdev);

	/*
	 * Buffers should not be used at this point except if the
	 * output character device is still open and the parent
	 * device gets detached from its bus, which is a FIXME.
	 */
	ret = msc_buffer_free_unless_used(msc);
	WARN_ON_ONCE(ret);
}

static struct intel_th_driver intel_th_msc_driver = {
	.probe	= intel_th_msc_probe,
	.remove	= intel_th_msc_remove,
	.irq		= intel_th_msc_interrupt,
	.wait_empty	= intel_th_msc_wait_empty,
	.activate	= intel_th_msc_activate,
	.deactivate	= intel_th_msc_deactivate,
	.fops	= &intel_th_msc_fops,
	.attr_group	= &msc_output_group,
	.driver	= {
		.name	= "msc",
		.owner	= THIS_MODULE,
	},
};

module_driver(intel_th_msc_driver,
	      intel_th_driver_register,
	      intel_th_driver_unregister);

MODULE_LICENSE("GPL v2");
MODULE_DESCRIPTION("Intel(R) Trace Hub Memory Storage Unit driver");
MODULE_AUTHOR("Alexander Shishkin <alexander.shishkin@linux.intel.com>");