summaryrefslogtreecommitdiffstats
path: root/drivers/hwtracing/coresight/coresight-tmc-etr.c
blob: 66dc5f97a009804f739a1baf0bfa043395b4ea6f (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright(C) 2016 Linaro Limited. All rights reserved.
 * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
 */

#include <linux/atomic.h>
#include <linux/coresight.h>
#include <linux/dma-mapping.h>
#include <linux/iommu.h>
#include <linux/idr.h>
#include <linux/mutex.h>
#include <linux/refcount.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/vmalloc.h>
#include "coresight-catu.h"
#include "coresight-etm-perf.h"
#include "coresight-priv.h"
#include "coresight-tmc.h"

struct etr_flat_buf {
	struct device	*dev;
	dma_addr_t	daddr;
	void		*vaddr;
	size_t		size;
};

/*
 * etr_perf_buffer - Perf buffer used for ETR
 * @drvdata		- The ETR drvdaga this buffer has been allocated for.
 * @etr_buf		- Actual buffer used by the ETR
 * @pid			- The PID this etr_perf_buffer belongs to.
 * @snaphost		- Perf session mode
 * @nr_pages		- Number of pages in the ring buffer.
 * @pages		- Array of Pages in the ring buffer.
 */
struct etr_perf_buffer {
	struct tmc_drvdata	*drvdata;
	struct etr_buf		*etr_buf;
	pid_t			pid;
	bool			snapshot;
	int			nr_pages;
	void			**pages;
};

/* Convert the perf index to an offset within the ETR buffer */
#define PERF_IDX2OFF(idx, buf)		\
		((idx) % ((unsigned long)(buf)->nr_pages << PAGE_SHIFT))

/* Lower limit for ETR hardware buffer */
#define TMC_ETR_PERF_MIN_BUF_SIZE	SZ_1M

/*
 * The TMC ETR SG has a page size of 4K. The SG table contains pointers
 * to 4KB buffers. However, the OS may use a PAGE_SIZE different from
 * 4K (i.e, 16KB or 64KB). This implies that a single OS page could
 * contain more than one SG buffer and tables.
 *
 * A table entry has the following format:
 *
 * ---Bit31------------Bit4-------Bit1-----Bit0--
 * |     Address[39:12]    | SBZ |  Entry Type  |
 * ----------------------------------------------
 *
 * Address: Bits [39:12] of a physical page address. Bits [11:0] are
 *	    always zero.
 *
 * Entry type:
 *	b00 - Reserved.
 *	b01 - Last entry in the tables, points to 4K page buffer.
 *	b10 - Normal entry, points to 4K page buffer.
 *	b11 - Link. The address points to the base of next table.
 */

typedef u32 sgte_t;

#define ETR_SG_PAGE_SHIFT		12
#define ETR_SG_PAGE_SIZE		(1UL << ETR_SG_PAGE_SHIFT)
#define ETR_SG_PAGES_PER_SYSPAGE	(PAGE_SIZE / ETR_SG_PAGE_SIZE)
#define ETR_SG_PTRS_PER_PAGE		(ETR_SG_PAGE_SIZE / sizeof(sgte_t))
#define ETR_SG_PTRS_PER_SYSPAGE		(PAGE_SIZE / sizeof(sgte_t))

#define ETR_SG_ET_MASK			0x3
#define ETR_SG_ET_LAST			0x1
#define ETR_SG_ET_NORMAL		0x2
#define ETR_SG_ET_LINK			0x3

#define ETR_SG_ADDR_SHIFT		4

#define ETR_SG_ENTRY(addr, type) \
	(sgte_t)((((addr) >> ETR_SG_PAGE_SHIFT) << ETR_SG_ADDR_SHIFT) | \
		 (type & ETR_SG_ET_MASK))

#define ETR_SG_ADDR(entry) \
	(((dma_addr_t)(entry) >> ETR_SG_ADDR_SHIFT) << ETR_SG_PAGE_SHIFT)
#define ETR_SG_ET(entry)		((entry) & ETR_SG_ET_MASK)

/*
 * struct etr_sg_table : ETR SG Table
 * @sg_table:		Generic SG Table holding the data/table pages.
 * @hwaddr:		hwaddress used by the TMC, which is the base
 *			address of the table.
 */
struct etr_sg_table {
	struct tmc_sg_table	*sg_table;
	dma_addr_t		hwaddr;
};

/*
 * tmc_etr_sg_table_entries: Total number of table entries required to map
 * @nr_pages system pages.
 *
 * We need to map @nr_pages * ETR_SG_PAGES_PER_SYSPAGE data pages.
 * Each TMC page can map (ETR_SG_PTRS_PER_PAGE - 1) buffer pointers,
 * with the last entry pointing to another page of table entries.
 * If we spill over to a new page for mapping 1 entry, we could as
 * well replace the link entry of the previous page with the last entry.
 */
static inline unsigned long __attribute_const__
tmc_etr_sg_table_entries(int nr_pages)
{
	unsigned long nr_sgpages = nr_pages * ETR_SG_PAGES_PER_SYSPAGE;
	unsigned long nr_sglinks = nr_sgpages / (ETR_SG_PTRS_PER_PAGE - 1);
	/*
	 * If we spill over to a new page for 1 entry, we could as well
	 * make it the LAST entry in the previous page, skipping the Link
	 * address.
	 */
	if (nr_sglinks && (nr_sgpages % (ETR_SG_PTRS_PER_PAGE - 1) < 2))
		nr_sglinks--;
	return nr_sgpages + nr_sglinks;
}

/*
 * tmc_pages_get_offset:  Go through all the pages in the tmc_pages
 * and map the device address @addr to an offset within the virtual
 * contiguous buffer.
 */
static long
tmc_pages_get_offset(struct tmc_pages *tmc_pages, dma_addr_t addr)
{
	int i;
	dma_addr_t page_start;

	for (i = 0; i < tmc_pages->nr_pages; i++) {
		page_start = tmc_pages->daddrs[i];
		if (addr >= page_start && addr < (page_start + PAGE_SIZE))
			return i * PAGE_SIZE + (addr - page_start);
	}

	return -EINVAL;
}

/*
 * tmc_pages_free : Unmap and free the pages used by tmc_pages.
 * If the pages were not allocated in tmc_pages_alloc(), we would
 * simply drop the refcount.
 */
static void tmc_pages_free(struct tmc_pages *tmc_pages,
			   struct device *dev, enum dma_data_direction dir)
{
	int i;
	struct device *real_dev = dev->parent;

	for (i = 0; i < tmc_pages->nr_pages; i++) {
		if (tmc_pages->daddrs && tmc_pages->daddrs[i])
			dma_unmap_page(real_dev, tmc_pages->daddrs[i],
					 PAGE_SIZE, dir);
		if (tmc_pages->pages && tmc_pages->pages[i])
			__free_page(tmc_pages->pages[i]);
	}

	kfree(tmc_pages->pages);
	kfree(tmc_pages->daddrs);
	tmc_pages->pages = NULL;
	tmc_pages->daddrs = NULL;
	tmc_pages->nr_pages = 0;
}

/*
 * tmc_pages_alloc : Allocate and map pages for a given @tmc_pages.
 * If @pages is not NULL, the list of page virtual addresses are
 * used as the data pages. The pages are then dma_map'ed for @dev
 * with dma_direction @dir.
 *
 * Returns 0 upon success, else the error number.
 */
static int tmc_pages_alloc(struct tmc_pages *tmc_pages,
			   struct device *dev, int node,
			   enum dma_data_direction dir, void **pages)
{
	int i, nr_pages;
	dma_addr_t paddr;
	struct page *page;
	struct device *real_dev = dev->parent;

	nr_pages = tmc_pages->nr_pages;
	tmc_pages->daddrs = kcalloc(nr_pages, sizeof(*tmc_pages->daddrs),
					 GFP_KERNEL);
	if (!tmc_pages->daddrs)
		return -ENOMEM;
	tmc_pages->pages = kcalloc(nr_pages, sizeof(*tmc_pages->pages),
					 GFP_KERNEL);
	if (!tmc_pages->pages) {
		kfree(tmc_pages->daddrs);
		tmc_pages->daddrs = NULL;
		return -ENOMEM;
	}

	for (i = 0; i < nr_pages; i++) {
		if (pages && pages[i]) {
			page = virt_to_page(pages[i]);
			/* Hold a refcount on the page */
			get_page(page);
		} else {
			page = alloc_pages_node(node,
						GFP_KERNEL | __GFP_ZERO, 0);
			if (!page)
				goto err;
		}
		paddr = dma_map_page(real_dev, page, 0, PAGE_SIZE, dir);
		if (dma_mapping_error(real_dev, paddr))
			goto err;
		tmc_pages->daddrs[i] = paddr;
		tmc_pages->pages[i] = page;
	}
	return 0;
err:
	tmc_pages_free(tmc_pages, dev, dir);
	return -ENOMEM;
}

static inline long
tmc_sg_get_data_page_offset(struct tmc_sg_table *sg_table, dma_addr_t addr)
{
	return tmc_pages_get_offset(&sg_table->data_pages, addr);
}

static inline void tmc_free_table_pages(struct tmc_sg_table *sg_table)
{
	if (sg_table->table_vaddr)
		vunmap(sg_table->table_vaddr);
	tmc_pages_free(&sg_table->table_pages, sg_table->dev, DMA_TO_DEVICE);
}

static void tmc_free_data_pages(struct tmc_sg_table *sg_table)
{
	if (sg_table->data_vaddr)
		vunmap(sg_table->data_vaddr);
	tmc_pages_free(&sg_table->data_pages, sg_table->dev, DMA_FROM_DEVICE);
}

void tmc_free_sg_table(struct tmc_sg_table *sg_table)
{
	tmc_free_table_pages(sg_table);
	tmc_free_data_pages(sg_table);
}
EXPORT_SYMBOL_GPL(tmc_free_sg_table);

/*
 * Alloc pages for the table. Since this will be used by the device,
 * allocate the pages closer to the device (i.e, dev_to_node(dev)
 * rather than the CPU node).
 */
static int tmc_alloc_table_pages(struct tmc_sg_table *sg_table)
{
	int rc;
	struct tmc_pages *table_pages = &sg_table->table_pages;

	rc = tmc_pages_alloc(table_pages, sg_table->dev,
			     dev_to_node(sg_table->dev),
			     DMA_TO_DEVICE, NULL);
	if (rc)
		return rc;
	sg_table->table_vaddr = vmap(table_pages->pages,
				     table_pages->nr_pages,
				     VM_MAP,
				     PAGE_KERNEL);
	if (!sg_table->table_vaddr)
		rc = -ENOMEM;
	else
		sg_table->table_daddr = table_pages->daddrs[0];
	return rc;
}

static int tmc_alloc_data_pages(struct tmc_sg_table *sg_table, void **pages)
{
	int rc;

	/* Allocate data pages on the node requested by the caller */
	rc = tmc_pages_alloc(&sg_table->data_pages,
			     sg_table->dev, sg_table->node,
			     DMA_FROM_DEVICE, pages);
	if (!rc) {
		sg_table->data_vaddr = vmap(sg_table->data_pages.pages,
					    sg_table->data_pages.nr_pages,
					    VM_MAP,
					    PAGE_KERNEL);
		if (!sg_table->data_vaddr)
			rc = -ENOMEM;
	}
	return rc;
}

/*
 * tmc_alloc_sg_table: Allocate and setup dma pages for the TMC SG table
 * and data buffers. TMC writes to the data buffers and reads from the SG
 * Table pages.
 *
 * @dev		- Coresight device to which page should be DMA mapped.
 * @node	- Numa node for mem allocations
 * @nr_tpages	- Number of pages for the table entries.
 * @nr_dpages	- Number of pages for Data buffer.
 * @pages	- Optional list of virtual address of pages.
 */
struct tmc_sg_table *tmc_alloc_sg_table(struct device *dev,
					int node,
					int nr_tpages,
					int nr_dpages,
					void **pages)
{
	long rc;
	struct tmc_sg_table *sg_table;

	sg_table = kzalloc(sizeof(*sg_table), GFP_KERNEL);
	if (!sg_table)
		return ERR_PTR(-ENOMEM);
	sg_table->data_pages.nr_pages = nr_dpages;
	sg_table->table_pages.nr_pages = nr_tpages;
	sg_table->node = node;
	sg_table->dev = dev;

	rc  = tmc_alloc_data_pages(sg_table, pages);
	if (!rc)
		rc = tmc_alloc_table_pages(sg_table);
	if (rc) {
		tmc_free_sg_table(sg_table);
		kfree(sg_table);
		return ERR_PTR(rc);
	}

	return sg_table;
}
EXPORT_SYMBOL_GPL(tmc_alloc_sg_table);

/*
 * tmc_sg_table_sync_data_range: Sync the data buffer written
 * by the device from @offset upto a @size bytes.
 */
void tmc_sg_table_sync_data_range(struct tmc_sg_table *table,
				  u64 offset, u64 size)
{
	int i, index, start;
	int npages = DIV_ROUND_UP(size, PAGE_SIZE);
	struct device *real_dev = table->dev->parent;
	struct tmc_pages *data = &table->data_pages;

	start = offset >> PAGE_SHIFT;
	for (i = start; i < (start + npages); i++) {
		index = i % data->nr_pages;
		dma_sync_single_for_cpu(real_dev, data->daddrs[index],
					PAGE_SIZE, DMA_FROM_DEVICE);
	}
}
EXPORT_SYMBOL_GPL(tmc_sg_table_sync_data_range);

/* tmc_sg_sync_table: Sync the page table */
void tmc_sg_table_sync_table(struct tmc_sg_table *sg_table)
{
	int i;
	struct device *real_dev = sg_table->dev->parent;
	struct tmc_pages *table_pages = &sg_table->table_pages;

	for (i = 0; i < table_pages->nr_pages; i++)
		dma_sync_single_for_device(real_dev, table_pages->daddrs[i],
					   PAGE_SIZE, DMA_TO_DEVICE);
}
EXPORT_SYMBOL_GPL(tmc_sg_table_sync_table);

/*
 * tmc_sg_table_get_data: Get the buffer pointer for data @offset
 * in the SG buffer. The @bufpp is updated to point to the buffer.
 * Returns :
 *	the length of linear data available at @offset.
 *	or
 *	<= 0 if no data is available.
 */
ssize_t tmc_sg_table_get_data(struct tmc_sg_table *sg_table,
			      u64 offset, size_t len, char **bufpp)
{
	size_t size;
	int pg_idx = offset >> PAGE_SHIFT;
	int pg_offset = offset & (PAGE_SIZE - 1);
	struct tmc_pages *data_pages = &sg_table->data_pages;

	size = tmc_sg_table_buf_size(sg_table);
	if (offset >= size)
		return -EINVAL;

	/* Make sure we don't go beyond the end */
	len = (len < (size - offset)) ? len : size - offset;
	/* Respect the page boundaries */
	len = (len < (PAGE_SIZE - pg_offset)) ? len : (PAGE_SIZE - pg_offset);
	if (len > 0)
		*bufpp = page_address(data_pages->pages[pg_idx]) + pg_offset;
	return len;
}
EXPORT_SYMBOL_GPL(tmc_sg_table_get_data);

#ifdef ETR_SG_DEBUG
/* Map a dma address to virtual address */
static unsigned long
tmc_sg_daddr_to_vaddr(struct tmc_sg_table *sg_table,
		      dma_addr_t addr, bool table)
{
	long offset;
	unsigned long base;
	struct tmc_pages *tmc_pages;

	if (table) {
		tmc_pages = &sg_table->table_pages;
		base = (unsigned long)sg_table->table_vaddr;
	} else {
		tmc_pages = &sg_table->data_pages;
		base = (unsigned long)sg_table->data_vaddr;
	}

	offset = tmc_pages_get_offset(tmc_pages, addr);
	if (offset < 0)
		return 0;
	return base + offset;
}

/* Dump the given sg_table */
static void tmc_etr_sg_table_dump(struct etr_sg_table *etr_table)
{
	sgte_t *ptr;
	int i = 0;
	dma_addr_t addr;
	struct tmc_sg_table *sg_table = etr_table->sg_table;

	ptr = (sgte_t *)tmc_sg_daddr_to_vaddr(sg_table,
					      etr_table->hwaddr, true);
	while (ptr) {
		addr = ETR_SG_ADDR(*ptr);
		switch (ETR_SG_ET(*ptr)) {
		case ETR_SG_ET_NORMAL:
			dev_dbg(sg_table->dev,
				"%05d: %p\t:[N] 0x%llx\n", i, ptr, addr);
			ptr++;
			break;
		case ETR_SG_ET_LINK:
			dev_dbg(sg_table->dev,
				"%05d: *** %p\t:{L} 0x%llx ***\n",
				 i, ptr, addr);
			ptr = (sgte_t *)tmc_sg_daddr_to_vaddr(sg_table,
							      addr, true);
			break;
		case ETR_SG_ET_LAST:
			dev_dbg(sg_table->dev,
				"%05d: ### %p\t:[L] 0x%llx ###\n",
				 i, ptr, addr);
			return;
		default:
			dev_dbg(sg_table->dev,
				"%05d: xxx %p\t:[INVALID] 0x%llx xxx\n",
				 i, ptr, addr);
			return;
		}
		i++;
	}
	dev_dbg(sg_table->dev, "******* End of Table *****\n");
}
#else
static inline void tmc_etr_sg_table_dump(struct etr_sg_table *etr_table) {}
#endif

/*
 * Populate the SG Table page table entries from table/data
 * pages allocated. Each Data page has ETR_SG_PAGES_PER_SYSPAGE SG pages.
 * So does a Table page. So we keep track of indices of the tables
 * in each system page and move the pointers accordingly.
 */
#define INC_IDX_ROUND(idx, size) ((idx) = ((idx) + 1) % (size))
static void tmc_etr_sg_table_populate(struct etr_sg_table *etr_table)
{
	dma_addr_t paddr;
	int i, type, nr_entries;
	int tpidx = 0; /* index to the current system table_page */
	int sgtidx = 0;	/* index to the sg_table within the current syspage */
	int sgtentry = 0; /* the entry within the sg_table */
	int dpidx = 0; /* index to the current system data_page */
	int spidx = 0; /* index to the SG page within the current data page */
	sgte_t *ptr; /* pointer to the table entry to fill */
	struct tmc_sg_table *sg_table = etr_table->sg_table;
	dma_addr_t *table_daddrs = sg_table->table_pages.daddrs;
	dma_addr_t *data_daddrs = sg_table->data_pages.daddrs;

	nr_entries = tmc_etr_sg_table_entries(sg_table->data_pages.nr_pages);
	/*
	 * Use the contiguous virtual address of the table to update entries.
	 */
	ptr = sg_table->table_vaddr;
	/*
	 * Fill all the entries, except the last entry to avoid special
	 * checks within the loop.
	 */
	for (i = 0; i < nr_entries - 1; i++) {
		if (sgtentry == ETR_SG_PTRS_PER_PAGE - 1) {
			/*
			 * Last entry in a sg_table page is a link address to
			 * the next table page. If this sg_table is the last
			 * one in the system page, it links to the first
			 * sg_table in the next system page. Otherwise, it
			 * links to the next sg_table page within the system
			 * page.
			 */
			if (sgtidx == ETR_SG_PAGES_PER_SYSPAGE - 1) {
				paddr = table_daddrs[tpidx + 1];
			} else {
				paddr = table_daddrs[tpidx] +
					(ETR_SG_PAGE_SIZE * (sgtidx + 1));
			}
			type = ETR_SG_ET_LINK;
		} else {
			/*
			 * Update the indices to the data_pages to point to the
			 * next sg_page in the data buffer.
			 */
			type = ETR_SG_ET_NORMAL;
			paddr = data_daddrs[dpidx] + spidx * ETR_SG_PAGE_SIZE;
			if (!INC_IDX_ROUND(spidx, ETR_SG_PAGES_PER_SYSPAGE))
				dpidx++;
		}
		*ptr++ = ETR_SG_ENTRY(paddr, type);
		/*
		 * Move to the next table pointer, moving the table page index
		 * if necessary
		 */
		if (!INC_IDX_ROUND(sgtentry, ETR_SG_PTRS_PER_PAGE)) {
			if (!INC_IDX_ROUND(sgtidx, ETR_SG_PAGES_PER_SYSPAGE))
				tpidx++;
		}
	}

	/* Set up the last entry, which is always a data pointer */
	paddr = data_daddrs[dpidx] + spidx * ETR_SG_PAGE_SIZE;
	*ptr++ = ETR_SG_ENTRY(paddr, ETR_SG_ET_LAST);
}

/*
 * tmc_init_etr_sg_table: Allocate a TMC ETR SG table, data buffer of @size and
 * populate the table.
 *
 * @dev		- Device pointer for the TMC
 * @node	- NUMA node where the memory should be allocated
 * @size	- Total size of the data buffer
 * @pages	- Optional list of page virtual address
 */
static struct etr_sg_table *
tmc_init_etr_sg_table(struct device *dev, int node,
		      unsigned long size, void **pages)
{
	int nr_entries, nr_tpages;
	int nr_dpages = size >> PAGE_SHIFT;
	struct tmc_sg_table *sg_table;
	struct etr_sg_table *etr_table;

	etr_table = kzalloc(sizeof(*etr_table), GFP_KERNEL);
	if (!etr_table)
		return ERR_PTR(-ENOMEM);
	nr_entries = tmc_etr_sg_table_entries(nr_dpages);
	nr_tpages = DIV_ROUND_UP(nr_entries, ETR_SG_PTRS_PER_SYSPAGE);

	sg_table = tmc_alloc_sg_table(dev, node, nr_tpages, nr_dpages, pages);
	if (IS_ERR(sg_table)) {
		kfree(etr_table);
		return ERR_CAST(sg_table);
	}

	etr_table->sg_table = sg_table;
	/* TMC should use table base address for DBA */
	etr_table->hwaddr = sg_table->table_daddr;
	tmc_etr_sg_table_populate(etr_table);
	/* Sync the table pages for the HW */
	tmc_sg_table_sync_table(sg_table);
	tmc_etr_sg_table_dump(etr_table);

	return etr_table;
}

/*
 * tmc_etr_alloc_flat_buf: Allocate a contiguous DMA buffer.
 */
static int tmc_etr_alloc_flat_buf(struct tmc_drvdata *drvdata,
				  struct etr_buf *etr_buf, int node,
				  void **pages)
{
	struct etr_flat_buf *flat_buf;
	struct device *real_dev = drvdata->csdev->dev.parent;

	/* We cannot reuse existing pages for flat buf */
	if (pages)
		return -EINVAL;

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

	flat_buf->vaddr = dma_alloc_noncoherent(real_dev, etr_buf->size,
						&flat_buf->daddr,
						DMA_FROM_DEVICE, GFP_KERNEL);
	if (!flat_buf->vaddr) {
		kfree(flat_buf);
		return -ENOMEM;
	}

	flat_buf->size = etr_buf->size;
	flat_buf->dev = &drvdata->csdev->dev;
	etr_buf->hwaddr = flat_buf->daddr;
	etr_buf->mode = ETR_MODE_FLAT;
	etr_buf->private = flat_buf;
	return 0;
}

static void tmc_etr_free_flat_buf(struct etr_buf *etr_buf)
{
	struct etr_flat_buf *flat_buf = etr_buf->private;

	if (flat_buf && flat_buf->daddr) {
		struct device *real_dev = flat_buf->dev->parent;

		dma_free_noncoherent(real_dev, etr_buf->size,
				     flat_buf->vaddr, flat_buf->daddr,
				     DMA_FROM_DEVICE);
	}
	kfree(flat_buf);
}

static void tmc_etr_sync_flat_buf(struct etr_buf *etr_buf, u64 rrp, u64 rwp)
{
	struct etr_flat_buf *flat_buf = etr_buf->private;
	struct device *real_dev = flat_buf->dev->parent;

	/*
	 * Adjust the buffer to point to the beginning of the trace data
	 * and update the available trace data.
	 */
	etr_buf->offset = rrp - etr_buf->hwaddr;
	if (etr_buf->full)
		etr_buf->len = etr_buf->size;
	else
		etr_buf->len = rwp - rrp;

	/*
	 * The driver always starts tracing at the beginning of the buffer,
	 * the only reason why we would get a wrap around is when the buffer
	 * is full.  Sync the entire buffer in one go for this case.
	 */
	if (etr_buf->offset + etr_buf->len > etr_buf->size)
		dma_sync_single_for_cpu(real_dev, flat_buf->daddr,
					etr_buf->size, DMA_FROM_DEVICE);
	else
		dma_sync_single_for_cpu(real_dev,
					flat_buf->daddr + etr_buf->offset,
					etr_buf->len, DMA_FROM_DEVICE);
}

static ssize_t tmc_etr_get_data_flat_buf(struct etr_buf *etr_buf,
					 u64 offset, size_t len, char **bufpp)
{
	struct etr_flat_buf *flat_buf = etr_buf->private;

	*bufpp = (char *)flat_buf->vaddr + offset;
	/*
	 * tmc_etr_buf_get_data already adjusts the length to handle
	 * buffer wrapping around.
	 */
	return len;
}

static const struct etr_buf_operations etr_flat_buf_ops = {
	.alloc = tmc_etr_alloc_flat_buf,
	.free = tmc_etr_free_flat_buf,
	.sync = tmc_etr_sync_flat_buf,
	.get_data = tmc_etr_get_data_flat_buf,
};

/*
 * tmc_etr_alloc_sg_buf: Allocate an SG buf @etr_buf. Setup the parameters
 * appropriately.
 */
static int tmc_etr_alloc_sg_buf(struct tmc_drvdata *drvdata,
				struct etr_buf *etr_buf, int node,
				void **pages)
{
	struct etr_sg_table *etr_table;
	struct device *dev = &drvdata->csdev->dev;

	etr_table = tmc_init_etr_sg_table(dev, node,
					  etr_buf->size, pages);
	if (IS_ERR(etr_table))
		return -ENOMEM;
	etr_buf->hwaddr = etr_table->hwaddr;
	etr_buf->mode = ETR_MODE_ETR_SG;
	etr_buf->private = etr_table;
	return 0;
}

static void tmc_etr_free_sg_buf(struct etr_buf *etr_buf)
{
	struct etr_sg_table *etr_table = etr_buf->private;

	if (etr_table) {
		tmc_free_sg_table(etr_table->sg_table);
		kfree(etr_table);
	}
}

static ssize_t tmc_etr_get_data_sg_buf(struct etr_buf *etr_buf, u64 offset,
				       size_t len, char **bufpp)
{
	struct etr_sg_table *etr_table = etr_buf->private;

	return tmc_sg_table_get_data(etr_table->sg_table, offset, len, bufpp);
}

static void tmc_etr_sync_sg_buf(struct etr_buf *etr_buf, u64 rrp, u64 rwp)
{
	long r_offset, w_offset;
	struct etr_sg_table *etr_table = etr_buf->private;
	struct tmc_sg_table *table = etr_table->sg_table;

	/* Convert hw address to offset in the buffer */
	r_offset = tmc_sg_get_data_page_offset(table, rrp);
	if (r_offset < 0) {
		dev_warn(table->dev,
			 "Unable to map RRP %llx to offset\n", rrp);
		etr_buf->len = 0;
		return;
	}

	w_offset = tmc_sg_get_data_page_offset(table, rwp);
	if (w_offset < 0) {
		dev_warn(table->dev,
			 "Unable to map RWP %llx to offset\n", rwp);
		etr_buf->len = 0;
		return;
	}

	etr_buf->offset = r_offset;
	if (etr_buf->full)
		etr_buf->len = etr_buf->size;
	else
		etr_buf->len = ((w_offset < r_offset) ? etr_buf->size : 0) +
				w_offset - r_offset;
	tmc_sg_table_sync_data_range(table, r_offset, etr_buf->len);
}

static const struct etr_buf_operations etr_sg_buf_ops = {
	.alloc = tmc_etr_alloc_sg_buf,
	.free = tmc_etr_free_sg_buf,
	.sync = tmc_etr_sync_sg_buf,
	.get_data = tmc_etr_get_data_sg_buf,
};

/*
 * TMC ETR could be connected to a CATU device, which can provide address
 * translation service. This is represented by the Output port of the TMC
 * (ETR) connected to the input port of the CATU.
 *
 * Returns	: coresight_device ptr for the CATU device if a CATU is found.
 *		: NULL otherwise.
 */
struct coresight_device *
tmc_etr_get_catu_device(struct tmc_drvdata *drvdata)
{
	struct coresight_device *etr = drvdata->csdev;
	union coresight_dev_subtype catu_subtype = {
		.helper_subtype = CORESIGHT_DEV_SUBTYPE_HELPER_CATU
	};

	if (!IS_ENABLED(CONFIG_CORESIGHT_CATU))
		return NULL;

	return coresight_find_output_type(etr->pdata, CORESIGHT_DEV_TYPE_HELPER,
					  catu_subtype);
}
EXPORT_SYMBOL_GPL(tmc_etr_get_catu_device);

static const struct etr_buf_operations *etr_buf_ops[] = {
	[ETR_MODE_FLAT] = &etr_flat_buf_ops,
	[ETR_MODE_ETR_SG] = &etr_sg_buf_ops,
	[ETR_MODE_CATU] = NULL,
};

void tmc_etr_set_catu_ops(const struct etr_buf_operations *catu)
{
	etr_buf_ops[ETR_MODE_CATU] = catu;
}
EXPORT_SYMBOL_GPL(tmc_etr_set_catu_ops);

void tmc_etr_remove_catu_ops(void)
{
	etr_buf_ops[ETR_MODE_CATU] = NULL;
}
EXPORT_SYMBOL_GPL(tmc_etr_remove_catu_ops);

static inline int tmc_etr_mode_alloc_buf(int mode,
					 struct tmc_drvdata *drvdata,
					 struct etr_buf *etr_buf, int node,
					 void **pages)
{
	int rc = -EINVAL;

	switch (mode) {
	case ETR_MODE_FLAT:
	case ETR_MODE_ETR_SG:
	case ETR_MODE_CATU:
		if (etr_buf_ops[mode] && etr_buf_ops[mode]->alloc)
			rc = etr_buf_ops[mode]->alloc(drvdata, etr_buf,
						      node, pages);
		if (!rc)
			etr_buf->ops = etr_buf_ops[mode];
		return rc;
	default:
		return -EINVAL;
	}
}

/*
 * tmc_alloc_etr_buf: Allocate a buffer use by ETR.
 * @drvdata	: ETR device details.
 * @size	: size of the requested buffer.
 * @flags	: Required properties for the buffer.
 * @node	: Node for memory allocations.
 * @pages	: An optional list of pages.
 */
static struct etr_buf *tmc_alloc_etr_buf(struct tmc_drvdata *drvdata,
					 ssize_t size, int flags,
					 int node, void **pages)
{
	int rc = -ENOMEM;
	bool has_etr_sg, has_iommu;
	bool has_sg, has_catu;
	struct etr_buf *etr_buf;
	struct device *dev = &drvdata->csdev->dev;

	has_etr_sg = tmc_etr_has_cap(drvdata, TMC_ETR_SG);
	has_iommu = iommu_get_domain_for_dev(dev->parent);
	has_catu = !!tmc_etr_get_catu_device(drvdata);

	has_sg = has_catu || has_etr_sg;

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

	etr_buf->size = size;

	/*
	 * If we have to use an existing list of pages, we cannot reliably
	 * use a contiguous DMA memory (even if we have an IOMMU). Otherwise,
	 * we use the contiguous DMA memory if at least one of the following
	 * conditions is true:
	 *  a) The ETR cannot use Scatter-Gather.
	 *  b) we have a backing IOMMU
	 *  c) The requested memory size is smaller (< 1M).
	 *
	 * Fallback to available mechanisms.
	 *
	 */
	if (!pages &&
	    (!has_sg || has_iommu || size < SZ_1M))
		rc = tmc_etr_mode_alloc_buf(ETR_MODE_FLAT, drvdata,
					    etr_buf, node, pages);
	if (rc && has_etr_sg)
		rc = tmc_etr_mode_alloc_buf(ETR_MODE_ETR_SG, drvdata,
					    etr_buf, node, pages);
	if (rc && has_catu)
		rc = tmc_etr_mode_alloc_buf(ETR_MODE_CATU, drvdata,
					    etr_buf, node, pages);
	if (rc) {
		kfree(etr_buf);
		return ERR_PTR(rc);
	}

	refcount_set(&etr_buf->refcount, 1);
	dev_dbg(dev, "allocated buffer of size %ldKB in mode %d\n",
		(unsigned long)size >> 10, etr_buf->mode);
	return etr_buf;
}

static void tmc_free_etr_buf(struct etr_buf *etr_buf)
{
	WARN_ON(!etr_buf->ops || !etr_buf->ops->free);
	etr_buf->ops->free(etr_buf);
	kfree(etr_buf);
}

/*
 * tmc_etr_buf_get_data: Get the pointer the trace data at @offset
 * with a maximum of @len bytes.
 * Returns: The size of the linear data available @pos, with *bufpp
 * updated to point to the buffer.
 */
static ssize_t tmc_etr_buf_get_data(struct etr_buf *etr_buf,
				    u64 offset, size_t len, char **bufpp)
{
	/* Adjust the length to limit this transaction to end of buffer */
	len = (len < (etr_buf->size - offset)) ? len : etr_buf->size - offset;

	return etr_buf->ops->get_data(etr_buf, (u64)offset, len, bufpp);
}

static inline s64
tmc_etr_buf_insert_barrier_packet(struct etr_buf *etr_buf, u64 offset)
{
	ssize_t len;
	char *bufp;

	len = tmc_etr_buf_get_data(etr_buf, offset,
				   CORESIGHT_BARRIER_PKT_SIZE, &bufp);
	if (WARN_ON(len < 0 || len < CORESIGHT_BARRIER_PKT_SIZE))
		return -EINVAL;
	coresight_insert_barrier_packet(bufp);
	return offset + CORESIGHT_BARRIER_PKT_SIZE;
}

/*
 * tmc_sync_etr_buf: Sync the trace buffer availability with drvdata.
 * Makes sure the trace data is synced to the memory for consumption.
 * @etr_buf->offset will hold the offset to the beginning of the trace data
 * within the buffer, with @etr_buf->len bytes to consume.
 */
static void tmc_sync_etr_buf(struct tmc_drvdata *drvdata)
{
	struct etr_buf *etr_buf = drvdata->etr_buf;
	u64 rrp, rwp;
	u32 status;

	rrp = tmc_read_rrp(drvdata);
	rwp = tmc_read_rwp(drvdata);
	status = readl_relaxed(drvdata->base + TMC_STS);

	/*
	 * If there were memory errors in the session, truncate the
	 * buffer.
	 */
	if (WARN_ON_ONCE(status & TMC_STS_MEMERR)) {
		dev_dbg(&drvdata->csdev->dev,
			"tmc memory error detected, truncating buffer\n");
		etr_buf->len = 0;
		etr_buf->full = false;
		return;
	}

	etr_buf->full = !!(status & TMC_STS_FULL);

	WARN_ON(!etr_buf->ops || !etr_buf->ops->sync);

	etr_buf->ops->sync(etr_buf, rrp, rwp);
}

static int __tmc_etr_enable_hw(struct tmc_drvdata *drvdata)
{
	u32 axictl, sts;
	struct etr_buf *etr_buf = drvdata->etr_buf;
	int rc = 0;

	CS_UNLOCK(drvdata->base);

	/* Wait for TMCSReady bit to be set */
	rc = tmc_wait_for_tmcready(drvdata);
	if (rc) {
		dev_err(&drvdata->csdev->dev,
			"Failed to enable : TMC not ready\n");
		CS_LOCK(drvdata->base);
		return rc;
	}

	writel_relaxed(etr_buf->size / 4, drvdata->base + TMC_RSZ);
	writel_relaxed(TMC_MODE_CIRCULAR_BUFFER, drvdata->base + TMC_MODE);

	axictl = readl_relaxed(drvdata->base + TMC_AXICTL);
	axictl &= ~TMC_AXICTL_CLEAR_MASK;
	axictl |= TMC_AXICTL_PROT_CTL_B1;
	axictl |= TMC_AXICTL_WR_BURST(drvdata->max_burst_size);
	axictl |= TMC_AXICTL_AXCACHE_OS;

	if (tmc_etr_has_cap(drvdata, TMC_ETR_AXI_ARCACHE)) {
		axictl &= ~TMC_AXICTL_ARCACHE_MASK;
		axictl |= TMC_AXICTL_ARCACHE_OS;
	}

	if (etr_buf->mode == ETR_MODE_ETR_SG)
		axictl |= TMC_AXICTL_SCT_GAT_MODE;

	writel_relaxed(axictl, drvdata->base + TMC_AXICTL);
	tmc_write_dba(drvdata, etr_buf->hwaddr);
	/*
	 * If the TMC pointers must be programmed before the session,
	 * we have to set it properly (i.e, RRP/RWP to base address and
	 * STS to "not full").
	 */
	if (tmc_etr_has_cap(drvdata, TMC_ETR_SAVE_RESTORE)) {
		tmc_write_rrp(drvdata, etr_buf->hwaddr);
		tmc_write_rwp(drvdata, etr_buf->hwaddr);
		sts = readl_relaxed(drvdata->base + TMC_STS) & ~TMC_STS_FULL;
		writel_relaxed(sts, drvdata->base + TMC_STS);
	}

	writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI |
		       TMC_FFCR_FON_FLIN | TMC_FFCR_FON_TRIG_EVT |
		       TMC_FFCR_TRIGON_TRIGIN,
		       drvdata->base + TMC_FFCR);
	writel_relaxed(drvdata->trigger_cntr, drvdata->base + TMC_TRG);
	tmc_enable_hw(drvdata);

	CS_LOCK(drvdata->base);
	return rc;
}

static int tmc_etr_enable_hw(struct tmc_drvdata *drvdata,
			     struct etr_buf *etr_buf)
{
	int rc;

	/* Callers should provide an appropriate buffer for use */
	if (WARN_ON(!etr_buf))
		return -EINVAL;

	if ((etr_buf->mode == ETR_MODE_ETR_SG) &&
	    WARN_ON(!tmc_etr_has_cap(drvdata, TMC_ETR_SG)))
		return -EINVAL;

	if (WARN_ON(drvdata->etr_buf))
		return -EBUSY;

	rc = coresight_claim_device(drvdata->csdev);
	if (!rc) {
		drvdata->etr_buf = etr_buf;
		rc = __tmc_etr_enable_hw(drvdata);
		if (rc) {
			drvdata->etr_buf = NULL;
			coresight_disclaim_device(drvdata->csdev);
		}
	}

	return rc;
}

/*
 * Return the available trace data in the buffer (starts at etr_buf->offset,
 * limited by etr_buf->len) from @pos, with a maximum limit of @len,
 * also updating the @bufpp on where to find it. Since the trace data
 * starts at anywhere in the buffer, depending on the RRP, we adjust the
 * @len returned to handle buffer wrapping around.
 *
 * We are protected here by drvdata->reading != 0, which ensures the
 * sysfs_buf stays alive.
 */
ssize_t tmc_etr_get_sysfs_trace(struct tmc_drvdata *drvdata,
				loff_t pos, size_t len, char **bufpp)
{
	s64 offset;
	ssize_t actual = len;
	struct etr_buf *etr_buf = drvdata->sysfs_buf;

	if (pos + actual > etr_buf->len)
		actual = etr_buf->len - pos;
	if (actual <= 0)
		return actual;

	/* Compute the offset from which we read the data */
	offset = etr_buf->offset + pos;
	if (offset >= etr_buf->size)
		offset -= etr_buf->size;
	return tmc_etr_buf_get_data(etr_buf, offset, actual, bufpp);
}

static struct etr_buf *
tmc_etr_setup_sysfs_buf(struct tmc_drvdata *drvdata)
{
	return tmc_alloc_etr_buf(drvdata, drvdata->size,
				 0, cpu_to_node(0), NULL);
}

static void
tmc_etr_free_sysfs_buf(struct etr_buf *buf)
{
	if (buf)
		tmc_free_etr_buf(buf);
}

static void tmc_etr_sync_sysfs_buf(struct tmc_drvdata *drvdata)
{
	struct etr_buf *etr_buf = drvdata->etr_buf;

	if (WARN_ON(drvdata->sysfs_buf != etr_buf)) {
		tmc_etr_free_sysfs_buf(drvdata->sysfs_buf);
		drvdata->sysfs_buf = NULL;
	} else {
		tmc_sync_etr_buf(drvdata);
		/*
		 * Insert barrier packets at the beginning, if there was
		 * an overflow.
		 */
		if (etr_buf->full)
			tmc_etr_buf_insert_barrier_packet(etr_buf,
							  etr_buf->offset);
	}
}

static void __tmc_etr_disable_hw(struct tmc_drvdata *drvdata)
{
	CS_UNLOCK(drvdata->base);

	tmc_flush_and_stop(drvdata);
	/*
	 * When operating in sysFS mode the content of the buffer needs to be
	 * read before the TMC is disabled.
	 */
	if (drvdata->mode == CS_MODE_SYSFS)
		tmc_etr_sync_sysfs_buf(drvdata);

	tmc_disable_hw(drvdata);

	CS_LOCK(drvdata->base);

}

void tmc_etr_disable_hw(struct tmc_drvdata *drvdata)
{
	__tmc_etr_disable_hw(drvdata);
	coresight_disclaim_device(drvdata->csdev);
	/* Reset the ETR buf used by hardware */
	drvdata->etr_buf = NULL;
}

static struct etr_buf *tmc_etr_get_sysfs_buffer(struct coresight_device *csdev)
{
	int ret = 0;
	unsigned long flags;
	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
	struct etr_buf *sysfs_buf = NULL, *new_buf = NULL, *free_buf = NULL;

	/*
	 * If we are enabling the ETR from disabled state, we need to make
	 * sure we have a buffer with the right size. The etr_buf is not reset
	 * immediately after we stop the tracing in SYSFS mode as we wait for
	 * the user to collect the data. We may be able to reuse the existing
	 * buffer, provided the size matches. Any allocation has to be done
	 * with the lock released.
	 */
	spin_lock_irqsave(&drvdata->spinlock, flags);
	sysfs_buf = READ_ONCE(drvdata->sysfs_buf);
	if (!sysfs_buf || (sysfs_buf->size != drvdata->size)) {
		spin_unlock_irqrestore(&drvdata->spinlock, flags);

		/* Allocate memory with the locks released */
		free_buf = new_buf = tmc_etr_setup_sysfs_buf(drvdata);
		if (IS_ERR(new_buf))
			return new_buf;

		/* Let's try again */
		spin_lock_irqsave(&drvdata->spinlock, flags);
	}

	if (drvdata->reading || drvdata->mode == CS_MODE_PERF) {
		ret = -EBUSY;
		goto out;
	}

	/*
	 * In sysFS mode we can have multiple writers per sink.  Since this
	 * sink is already enabled no memory is needed and the HW need not be
	 * touched, even if the buffer size has changed.
	 */
	if (drvdata->mode == CS_MODE_SYSFS) {
		atomic_inc(&csdev->refcnt);
		goto out;
	}

	/*
	 * If we don't have a buffer or it doesn't match the requested size,
	 * use the buffer allocated above. Otherwise reuse the existing buffer.
	 */
	sysfs_buf = READ_ONCE(drvdata->sysfs_buf);
	if (!sysfs_buf || (new_buf && sysfs_buf->size != new_buf->size)) {
		free_buf = sysfs_buf;
		drvdata->sysfs_buf = new_buf;
	}

out:
	spin_unlock_irqrestore(&drvdata->spinlock, flags);

	/* Free memory outside the spinlock if need be */
	if (free_buf)
		tmc_etr_free_sysfs_buf(free_buf);
	return ret ? ERR_PTR(ret) : drvdata->sysfs_buf;
}

static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev)
{
	int ret;
	unsigned long flags;
	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
	struct etr_buf *sysfs_buf = tmc_etr_get_sysfs_buffer(csdev);

	if (IS_ERR(sysfs_buf))
		return PTR_ERR(sysfs_buf);

	spin_lock_irqsave(&drvdata->spinlock, flags);
	ret = tmc_etr_enable_hw(drvdata, sysfs_buf);
	if (!ret) {
		drvdata->mode = CS_MODE_SYSFS;
		atomic_inc(&csdev->refcnt);
	}

	spin_unlock_irqrestore(&drvdata->spinlock, flags);

	if (!ret)
		dev_dbg(&csdev->dev, "TMC-ETR enabled\n");

	return ret;
}

struct etr_buf *tmc_etr_get_buffer(struct coresight_device *csdev,
				   enum cs_mode mode, void *data)
{
	struct perf_output_handle *handle = data;
	struct etr_perf_buffer *etr_perf;

	switch (mode) {
	case CS_MODE_SYSFS:
		return tmc_etr_get_sysfs_buffer(csdev);
	case CS_MODE_PERF:
		etr_perf = etm_perf_sink_config(handle);
		if (WARN_ON(!etr_perf || !etr_perf->etr_buf))
			return ERR_PTR(-EINVAL);
		return etr_perf->etr_buf;
	default:
		return ERR_PTR(-EINVAL);
	}
}
EXPORT_SYMBOL_GPL(tmc_etr_get_buffer);

/*
 * alloc_etr_buf: Allocate ETR buffer for use by perf.
 * The size of the hardware buffer is dependent on the size configured
 * via sysfs and the perf ring buffer size. We prefer to allocate the
 * largest possible size, scaling down the size by half until it
 * reaches a minimum limit (1M), beyond which we give up.
 */
static struct etr_buf *
alloc_etr_buf(struct tmc_drvdata *drvdata, struct perf_event *event,
	      int nr_pages, void **pages, bool snapshot)
{
	int node;
	struct etr_buf *etr_buf;
	unsigned long size;

	node = (event->cpu == -1) ? NUMA_NO_NODE : cpu_to_node(event->cpu);
	/*
	 * Try to match the perf ring buffer size if it is larger
	 * than the size requested via sysfs.
	 */
	if ((nr_pages << PAGE_SHIFT) > drvdata->size) {
		etr_buf = tmc_alloc_etr_buf(drvdata, ((ssize_t)nr_pages << PAGE_SHIFT),
					    0, node, NULL);
		if (!IS_ERR(etr_buf))
			goto done;
	}

	/*
	 * Else switch to configured size for this ETR
	 * and scale down until we hit the minimum limit.
	 */
	size = drvdata->size;
	do {
		etr_buf = tmc_alloc_etr_buf(drvdata, size, 0, node, NULL);
		if (!IS_ERR(etr_buf))
			goto done;
		size /= 2;
	} while (size >= TMC_ETR_PERF_MIN_BUF_SIZE);

	return ERR_PTR(-ENOMEM);

done:
	return etr_buf;
}

static struct etr_buf *
get_perf_etr_buf_cpu_wide(struct tmc_drvdata *drvdata,
			  struct perf_event *event, int nr_pages,
			  void **pages, bool snapshot)
{
	int ret;
	pid_t pid = task_pid_nr(event->owner);
	struct etr_buf *etr_buf;

retry:
	/*
	 * An etr_perf_buffer is associated with an event and holds a reference
	 * to the AUX ring buffer that was created for that event.  In CPU-wide
	 * N:1 mode multiple events (one per CPU), each with its own AUX ring
	 * buffer, share a sink.  As such an etr_perf_buffer is created for each
	 * event but a single etr_buf associated with the ETR is shared between
	 * them.  The last event in a trace session will copy the content of the
	 * etr_buf to its AUX ring buffer.  Ring buffer associated to other
	 * events are simply not used an freed as events are destoyed.  We still
	 * need to allocate a ring buffer for each event since we don't know
	 * which event will be last.
	 */

	/*
	 * The first thing to do here is check if an etr_buf has already been
	 * allocated for this session.  If so it is shared with this event,
	 * otherwise it is created.
	 */
	mutex_lock(&drvdata->idr_mutex);
	etr_buf = idr_find(&drvdata->idr, pid);
	if (etr_buf) {
		refcount_inc(&etr_buf->refcount);
		mutex_unlock(&drvdata->idr_mutex);
		return etr_buf;
	}

	/* If we made it here no buffer has been allocated, do so now. */
	mutex_unlock(&drvdata->idr_mutex);

	etr_buf = alloc_etr_buf(drvdata, event, nr_pages, pages, snapshot);
	if (IS_ERR(etr_buf))
		return etr_buf;

	/* Now that we have a buffer, add it to the IDR. */
	mutex_lock(&drvdata->idr_mutex);
	ret = idr_alloc(&drvdata->idr, etr_buf, pid, pid + 1, GFP_KERNEL);
	mutex_unlock(&drvdata->idr_mutex);

	/* Another event with this session ID has allocated this buffer. */
	if (ret == -ENOSPC) {
		tmc_free_etr_buf(etr_buf);
		goto retry;
	}

	/* The IDR can't allocate room for a new session, abandon ship. */
	if (ret == -ENOMEM) {
		tmc_free_etr_buf(etr_buf);
		return ERR_PTR(ret);
	}


	return etr_buf;
}

static struct etr_buf *
get_perf_etr_buf_per_thread(struct tmc_drvdata *drvdata,
			    struct perf_event *event, int nr_pages,
			    void **pages, bool snapshot)
{
	/*
	 * In per-thread mode the etr_buf isn't shared, so just go ahead
	 * with memory allocation.
	 */
	return alloc_etr_buf(drvdata, event, nr_pages, pages, snapshot);
}

static struct etr_buf *
get_perf_etr_buf(struct tmc_drvdata *drvdata, struct perf_event *event,
		 int nr_pages, void **pages, bool snapshot)
{
	if (event->cpu == -1)
		return get_perf_etr_buf_per_thread(drvdata, event, nr_pages,
						   pages, snapshot);

	return get_perf_etr_buf_cpu_wide(drvdata, event, nr_pages,
					 pages, snapshot);
}

static struct etr_perf_buffer *
tmc_etr_setup_perf_buf(struct tmc_drvdata *drvdata, struct perf_event *event,
		       int nr_pages, void **pages, bool snapshot)
{
	int node;
	struct etr_buf *etr_buf;
	struct etr_perf_buffer *etr_perf;

	node = (event->cpu == -1) ? NUMA_NO_NODE : cpu_to_node(event->cpu);

	etr_perf = kzalloc_node(sizeof(*etr_perf), GFP_KERNEL, node);
	if (!etr_perf)
		return ERR_PTR(-ENOMEM);

	etr_buf = get_perf_etr_buf(drvdata, event, nr_pages, pages, snapshot);
	if (!IS_ERR(etr_buf))
		goto done;

	kfree(etr_perf);
	return ERR_PTR(-ENOMEM);

done:
	/*
	 * Keep a reference to the ETR this buffer has been allocated for
	 * in order to have access to the IDR in tmc_free_etr_buffer().
	 */
	etr_perf->drvdata = drvdata;
	etr_perf->etr_buf = etr_buf;

	return etr_perf;
}


static void *tmc_alloc_etr_buffer(struct coresight_device *csdev,
				  struct perf_event *event, void **pages,
				  int nr_pages, bool snapshot)
{
	struct etr_perf_buffer *etr_perf;
	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);

	etr_perf = tmc_etr_setup_perf_buf(drvdata, event,
					  nr_pages, pages, snapshot);
	if (IS_ERR(etr_perf)) {
		dev_dbg(&csdev->dev, "Unable to allocate ETR buffer\n");
		return NULL;
	}

	etr_perf->pid = task_pid_nr(event->owner);
	etr_perf->snapshot = snapshot;
	etr_perf->nr_pages = nr_pages;
	etr_perf->pages = pages;

	return etr_perf;
}

static void tmc_free_etr_buffer(void *config)
{
	struct etr_perf_buffer *etr_perf = config;
	struct tmc_drvdata *drvdata = etr_perf->drvdata;
	struct etr_buf *buf, *etr_buf = etr_perf->etr_buf;

	if (!etr_buf)
		goto free_etr_perf_buffer;

	mutex_lock(&drvdata->idr_mutex);
	/* If we are not the last one to use the buffer, don't touch it. */
	if (!refcount_dec_and_test(&etr_buf->refcount)) {
		mutex_unlock(&drvdata->idr_mutex);
		goto free_etr_perf_buffer;
	}

	/* We are the last one, remove from the IDR and free the buffer. */
	buf = idr_remove(&drvdata->idr, etr_perf->pid);
	mutex_unlock(&drvdata->idr_mutex);

	/*
	 * Something went very wrong if the buffer associated with this ID
	 * is not the same in the IDR.  Leak to avoid use after free.
	 */
	if (buf && WARN_ON(buf != etr_buf))
		goto free_etr_perf_buffer;

	tmc_free_etr_buf(etr_perf->etr_buf);

free_etr_perf_buffer:
	kfree(etr_perf);
}

/*
 * tmc_etr_sync_perf_buffer: Copy the actual trace data from the hardware
 * buffer to the perf ring buffer.
 */
static void tmc_etr_sync_perf_buffer(struct etr_perf_buffer *etr_perf,
				     unsigned long head,
				     unsigned long src_offset,
				     unsigned long to_copy)
{
	long bytes;
	long pg_idx, pg_offset;
	char **dst_pages, *src_buf;
	struct etr_buf *etr_buf = etr_perf->etr_buf;

	head = PERF_IDX2OFF(head, etr_perf);
	pg_idx = head >> PAGE_SHIFT;
	pg_offset = head & (PAGE_SIZE - 1);
	dst_pages = (char **)etr_perf->pages;

	while (to_copy > 0) {
		/*
		 * In one iteration, we can copy minimum of :
		 *  1) what is available in the source buffer,
		 *  2) what is available in the source buffer, before it
		 *     wraps around.
		 *  3) what is available in the destination page.
		 * in one iteration.
		 */
		if (src_offset >= etr_buf->size)
			src_offset -= etr_buf->size;
		bytes = tmc_etr_buf_get_data(etr_buf, src_offset, to_copy,
					     &src_buf);
		if (WARN_ON_ONCE(bytes <= 0))
			break;
		bytes = min(bytes, (long)(PAGE_SIZE - pg_offset));

		memcpy(dst_pages[pg_idx] + pg_offset, src_buf, bytes);

		to_copy -= bytes;

		/* Move destination pointers */
		pg_offset += bytes;
		if (pg_offset == PAGE_SIZE) {
			pg_offset = 0;
			if (++pg_idx == etr_perf->nr_pages)
				pg_idx = 0;
		}

		/* Move source pointers */
		src_offset += bytes;
	}
}

/*
 * tmc_update_etr_buffer : Update the perf ring buffer with the
 * available trace data. We use software double buffering at the moment.
 *
 * TODO: Add support for reusing the perf ring buffer.
 */
static unsigned long
tmc_update_etr_buffer(struct coresight_device *csdev,
		      struct perf_output_handle *handle,
		      void *config)
{
	bool lost = false;
	unsigned long flags, offset, size = 0;
	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
	struct etr_perf_buffer *etr_perf = config;
	struct etr_buf *etr_buf = etr_perf->etr_buf;

	spin_lock_irqsave(&drvdata->spinlock, flags);

	/* Don't do anything if another tracer is using this sink */
	if (atomic_read(&csdev->refcnt) != 1) {
		spin_unlock_irqrestore(&drvdata->spinlock, flags);
		goto out;
	}

	if (WARN_ON(drvdata->perf_buf != etr_buf)) {
		lost = true;
		spin_unlock_irqrestore(&drvdata->spinlock, flags);
		goto out;
	}

	CS_UNLOCK(drvdata->base);

	tmc_flush_and_stop(drvdata);
	tmc_sync_etr_buf(drvdata);

	CS_LOCK(drvdata->base);
	spin_unlock_irqrestore(&drvdata->spinlock, flags);

	lost = etr_buf->full;
	offset = etr_buf->offset;
	size = etr_buf->len;

	/*
	 * The ETR buffer may be bigger than the space available in the
	 * perf ring buffer (handle->size).  If so advance the offset so that we
	 * get the latest trace data.  In snapshot mode none of that matters
	 * since we are expected to clobber stale data in favour of the latest
	 * traces.
	 */
	if (!etr_perf->snapshot && size > handle->size) {
		u32 mask = tmc_get_memwidth_mask(drvdata);

		/*
		 * Make sure the new size is aligned in accordance with the
		 * requirement explained in function tmc_get_memwidth_mask().
		 */
		size = handle->size & mask;
		offset = etr_buf->offset + etr_buf->len - size;

		if (offset >= etr_buf->size)
			offset -= etr_buf->size;
		lost = true;
	}

	/* Insert barrier packets at the beginning, if there was an overflow */
	if (lost)
		tmc_etr_buf_insert_barrier_packet(etr_buf, offset);
	tmc_etr_sync_perf_buffer(etr_perf, handle->head, offset, size);

	/*
	 * In snapshot mode we simply increment the head by the number of byte
	 * that were written.  User space will figure out how many bytes to get
	 * from the AUX buffer based on the position of the head.
	 */
	if (etr_perf->snapshot)
		handle->head += size;

	/*
	 * Ensure that the AUX trace data is visible before the aux_head
	 * is updated via perf_aux_output_end(), as expected by the
	 * perf ring buffer.
	 */
	smp_wmb();

out:
	/*
	 * Don't set the TRUNCATED flag in snapshot mode because 1) the
	 * captured buffer is expected to be truncated and 2) a full buffer
	 * prevents the event from being re-enabled by the perf core,
	 * resulting in stale data being send to user space.
	 */
	if (!etr_perf->snapshot && lost)
		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
	return size;
}

static int tmc_enable_etr_sink_perf(struct coresight_device *csdev, void *data)
{
	int rc = 0;
	pid_t pid;
	unsigned long flags;
	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
	struct perf_output_handle *handle = data;
	struct etr_perf_buffer *etr_perf = etm_perf_sink_config(handle);

	spin_lock_irqsave(&drvdata->spinlock, flags);
	 /* Don't use this sink if it is already claimed by sysFS */
	if (drvdata->mode == CS_MODE_SYSFS) {
		rc = -EBUSY;
		goto unlock_out;
	}

	if (WARN_ON(!etr_perf || !etr_perf->etr_buf)) {
		rc = -EINVAL;
		goto unlock_out;
	}

	/* Get a handle on the pid of the process to monitor */
	pid = etr_perf->pid;

	/* Do not proceed if this device is associated with another session */
	if (drvdata->pid != -1 && drvdata->pid != pid) {
		rc = -EBUSY;
		goto unlock_out;
	}

	/*
	 * No HW configuration is needed if the sink is already in
	 * use for this session.
	 */
	if (drvdata->pid == pid) {
		atomic_inc(&csdev->refcnt);
		goto unlock_out;
	}

	rc = tmc_etr_enable_hw(drvdata, etr_perf->etr_buf);
	if (!rc) {
		/* Associate with monitored process. */
		drvdata->pid = pid;
		drvdata->mode = CS_MODE_PERF;
		drvdata->perf_buf = etr_perf->etr_buf;
		atomic_inc(&csdev->refcnt);
	}

unlock_out:
	spin_unlock_irqrestore(&drvdata->spinlock, flags);
	return rc;
}

static int tmc_enable_etr_sink(struct coresight_device *csdev,
			       enum cs_mode mode, void *data)
{
	switch (mode) {
	case CS_MODE_SYSFS:
		return tmc_enable_etr_sink_sysfs(csdev);
	case CS_MODE_PERF:
		return tmc_enable_etr_sink_perf(csdev, data);
	default:
		return -EINVAL;
	}
}

static int tmc_disable_etr_sink(struct coresight_device *csdev)
{
	unsigned long flags;
	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);

	spin_lock_irqsave(&drvdata->spinlock, flags);

	if (drvdata->reading) {
		spin_unlock_irqrestore(&drvdata->spinlock, flags);
		return -EBUSY;
	}

	if (atomic_dec_return(&csdev->refcnt)) {
		spin_unlock_irqrestore(&drvdata->spinlock, flags);
		return -EBUSY;
	}

	/* Complain if we (somehow) got out of sync */
	WARN_ON_ONCE(drvdata->mode == CS_MODE_DISABLED);
	tmc_etr_disable_hw(drvdata);
	/* Dissociate from monitored process. */
	drvdata->pid = -1;
	drvdata->mode = CS_MODE_DISABLED;
	/* Reset perf specific data */
	drvdata->perf_buf = NULL;

	spin_unlock_irqrestore(&drvdata->spinlock, flags);

	dev_dbg(&csdev->dev, "TMC-ETR disabled\n");
	return 0;
}

static const struct coresight_ops_sink tmc_etr_sink_ops = {
	.enable		= tmc_enable_etr_sink,
	.disable	= tmc_disable_etr_sink,
	.alloc_buffer	= tmc_alloc_etr_buffer,
	.update_buffer	= tmc_update_etr_buffer,
	.free_buffer	= tmc_free_etr_buffer,
};

const struct coresight_ops tmc_etr_cs_ops = {
	.sink_ops	= &tmc_etr_sink_ops,
};

int tmc_read_prepare_etr(struct tmc_drvdata *drvdata)
{
	int ret = 0;
	unsigned long flags;

	/* config types are set a boot time and never change */
	if (WARN_ON_ONCE(drvdata->config_type != TMC_CONFIG_TYPE_ETR))
		return -EINVAL;

	spin_lock_irqsave(&drvdata->spinlock, flags);
	if (drvdata->reading) {
		ret = -EBUSY;
		goto out;
	}

	/*
	 * We can safely allow reads even if the ETR is operating in PERF mode,
	 * since the sysfs session is captured in mode specific data.
	 * If drvdata::sysfs_data is NULL the trace data has been read already.
	 */
	if (!drvdata->sysfs_buf) {
		ret = -EINVAL;
		goto out;
	}

	/* Disable the TMC if we are trying to read from a running session. */
	if (drvdata->mode == CS_MODE_SYSFS)
		__tmc_etr_disable_hw(drvdata);

	drvdata->reading = true;
out:
	spin_unlock_irqrestore(&drvdata->spinlock, flags);

	return ret;
}

int tmc_read_unprepare_etr(struct tmc_drvdata *drvdata)
{
	unsigned long flags;
	struct etr_buf *sysfs_buf = NULL;

	/* config types are set a boot time and never change */
	if (WARN_ON_ONCE(drvdata->config_type != TMC_CONFIG_TYPE_ETR))
		return -EINVAL;

	spin_lock_irqsave(&drvdata->spinlock, flags);

	/* RE-enable the TMC if need be */
	if (drvdata->mode == CS_MODE_SYSFS) {
		/*
		 * The trace run will continue with the same allocated trace
		 * buffer. Since the tracer is still enabled drvdata::buf can't
		 * be NULL.
		 */
		__tmc_etr_enable_hw(drvdata);
	} else {
		/*
		 * The ETR is not tracing and the buffer was just read.
		 * As such prepare to free the trace buffer.
		 */
		sysfs_buf = drvdata->sysfs_buf;
		drvdata->sysfs_buf = NULL;
	}

	drvdata->reading = false;
	spin_unlock_irqrestore(&drvdata->spinlock, flags);

	/* Free allocated memory out side of the spinlock */
	if (sysfs_buf)
		tmc_etr_free_sysfs_buf(sysfs_buf);

	return 0;
}