summaryrefslogtreecommitdiffstats
path: root/drivers/thunderbolt/nhi.c
blob: d76e923fbc6a01fcc8ce93bb998d4231511ffa39 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Thunderbolt driver - NHI driver
 *
 * The NHI (native host interface) is the pci device that allows us to send and
 * receive frames from the thunderbolt bus.
 *
 * Copyright (c) 2014 Andreas Noever <andreas.noever@gmail.com>
 * Copyright (C) 2018, Intel Corporation
 */

#include <linux/pm_runtime.h>
#include <linux/slab.h>
#include <linux/errno.h>
#include <linux/pci.h>
#include <linux/dma-mapping.h>
#include <linux/interrupt.h>
#include <linux/iommu.h>
#include <linux/module.h>
#include <linux/delay.h>
#include <linux/property.h>
#include <linux/string_helpers.h>

#include "nhi.h"
#include "nhi_regs.h"
#include "tb.h"

#define RING_TYPE(ring) ((ring)->is_tx ? "TX ring" : "RX ring")

#define RING_FIRST_USABLE_HOPID	1
/*
 * Used with QUIRK_E2E to specify an unused HopID the Rx credits are
 * transferred.
 */
#define RING_E2E_RESERVED_HOPID	RING_FIRST_USABLE_HOPID
/*
 * Minimal number of vectors when we use MSI-X. Two for control channel
 * Rx/Tx and the rest four are for cross domain DMA paths.
 */
#define MSIX_MIN_VECS		6
#define MSIX_MAX_VECS		16

#define NHI_MAILBOX_TIMEOUT	500 /* ms */

/* Host interface quirks */
#define QUIRK_AUTO_CLEAR_INT	BIT(0)
#define QUIRK_E2E		BIT(1)

static int ring_interrupt_index(const struct tb_ring *ring)
{
	int bit = ring->hop;
	if (!ring->is_tx)
		bit += ring->nhi->hop_count;
	return bit;
}

/*
 * ring_interrupt_active() - activate/deactivate interrupts for a single ring
 *
 * ring->nhi->lock must be held.
 */
static void ring_interrupt_active(struct tb_ring *ring, bool active)
{
	int reg = REG_RING_INTERRUPT_BASE +
		  ring_interrupt_index(ring) / 32 * 4;
	int interrupt_bit = ring_interrupt_index(ring) & 31;
	int mask = 1 << interrupt_bit;
	u32 old, new;

	if (ring->irq > 0) {
		u32 step, shift, ivr, misc;
		void __iomem *ivr_base;
		int auto_clear_bit;
		int index;

		if (ring->is_tx)
			index = ring->hop;
		else
			index = ring->hop + ring->nhi->hop_count;

		/*
		 * Intel routers support a bit that isn't part of
		 * the USB4 spec to ask the hardware to clear
		 * interrupt status bits automatically since
		 * we already know which interrupt was triggered.
		 *
		 * Other routers explicitly disable auto-clear
		 * to prevent conditions that may occur where two
		 * MSIX interrupts are simultaneously active and
		 * reading the register clears both of them.
		 */
		misc = ioread32(ring->nhi->iobase + REG_DMA_MISC);
		if (ring->nhi->quirks & QUIRK_AUTO_CLEAR_INT)
			auto_clear_bit = REG_DMA_MISC_INT_AUTO_CLEAR;
		else
			auto_clear_bit = REG_DMA_MISC_DISABLE_AUTO_CLEAR;
		if (!(misc & auto_clear_bit))
			iowrite32(misc | auto_clear_bit,
				  ring->nhi->iobase + REG_DMA_MISC);

		ivr_base = ring->nhi->iobase + REG_INT_VEC_ALLOC_BASE;
		step = index / REG_INT_VEC_ALLOC_REGS * REG_INT_VEC_ALLOC_BITS;
		shift = index % REG_INT_VEC_ALLOC_REGS * REG_INT_VEC_ALLOC_BITS;
		ivr = ioread32(ivr_base + step);
		ivr &= ~(REG_INT_VEC_ALLOC_MASK << shift);
		if (active)
			ivr |= ring->vector << shift;
		iowrite32(ivr, ivr_base + step);
	}

	old = ioread32(ring->nhi->iobase + reg);
	if (active)
		new = old | mask;
	else
		new = old & ~mask;

	dev_dbg(&ring->nhi->pdev->dev,
		"%s interrupt at register %#x bit %d (%#x -> %#x)\n",
		active ? "enabling" : "disabling", reg, interrupt_bit, old, new);

	if (new == old)
		dev_WARN(&ring->nhi->pdev->dev,
					 "interrupt for %s %d is already %s\n",
					 RING_TYPE(ring), ring->hop,
					 active ? "enabled" : "disabled");
	iowrite32(new, ring->nhi->iobase + reg);
}

/*
 * nhi_disable_interrupts() - disable interrupts for all rings
 *
 * Use only during init and shutdown.
 */
static void nhi_disable_interrupts(struct tb_nhi *nhi)
{
	int i = 0;
	/* disable interrupts */
	for (i = 0; i < RING_INTERRUPT_REG_COUNT(nhi); i++)
		iowrite32(0, nhi->iobase + REG_RING_INTERRUPT_BASE + 4 * i);

	/* clear interrupt status bits */
	for (i = 0; i < RING_NOTIFY_REG_COUNT(nhi); i++)
		ioread32(nhi->iobase + REG_RING_NOTIFY_BASE + 4 * i);
}

/* ring helper methods */

static void __iomem *ring_desc_base(struct tb_ring *ring)
{
	void __iomem *io = ring->nhi->iobase;
	io += ring->is_tx ? REG_TX_RING_BASE : REG_RX_RING_BASE;
	io += ring->hop * 16;
	return io;
}

static void __iomem *ring_options_base(struct tb_ring *ring)
{
	void __iomem *io = ring->nhi->iobase;
	io += ring->is_tx ? REG_TX_OPTIONS_BASE : REG_RX_OPTIONS_BASE;
	io += ring->hop * 32;
	return io;
}

static void ring_iowrite_cons(struct tb_ring *ring, u16 cons)
{
	/*
	 * The other 16-bits in the register is read-only and writes to it
	 * are ignored by the hardware so we can save one ioread32() by
	 * filling the read-only bits with zeroes.
	 */
	iowrite32(cons, ring_desc_base(ring) + 8);
}

static void ring_iowrite_prod(struct tb_ring *ring, u16 prod)
{
	/* See ring_iowrite_cons() above for explanation */
	iowrite32(prod << 16, ring_desc_base(ring) + 8);
}

static void ring_iowrite32desc(struct tb_ring *ring, u32 value, u32 offset)
{
	iowrite32(value, ring_desc_base(ring) + offset);
}

static void ring_iowrite64desc(struct tb_ring *ring, u64 value, u32 offset)
{
	iowrite32(value, ring_desc_base(ring) + offset);
	iowrite32(value >> 32, ring_desc_base(ring) + offset + 4);
}

static void ring_iowrite32options(struct tb_ring *ring, u32 value, u32 offset)
{
	iowrite32(value, ring_options_base(ring) + offset);
}

static bool ring_full(struct tb_ring *ring)
{
	return ((ring->head + 1) % ring->size) == ring->tail;
}

static bool ring_empty(struct tb_ring *ring)
{
	return ring->head == ring->tail;
}

/*
 * ring_write_descriptors() - post frames from ring->queue to the controller
 *
 * ring->lock is held.
 */
static void ring_write_descriptors(struct tb_ring *ring)
{
	struct ring_frame *frame, *n;
	struct ring_desc *descriptor;
	list_for_each_entry_safe(frame, n, &ring->queue, list) {
		if (ring_full(ring))
			break;
		list_move_tail(&frame->list, &ring->in_flight);
		descriptor = &ring->descriptors[ring->head];
		descriptor->phys = frame->buffer_phy;
		descriptor->time = 0;
		descriptor->flags = RING_DESC_POSTED | RING_DESC_INTERRUPT;
		if (ring->is_tx) {
			descriptor->length = frame->size;
			descriptor->eof = frame->eof;
			descriptor->sof = frame->sof;
		}
		ring->head = (ring->head + 1) % ring->size;
		if (ring->is_tx)
			ring_iowrite_prod(ring, ring->head);
		else
			ring_iowrite_cons(ring, ring->head);
	}
}

/*
 * ring_work() - progress completed frames
 *
 * If the ring is shutting down then all frames are marked as canceled and
 * their callbacks are invoked.
 *
 * Otherwise we collect all completed frame from the ring buffer, write new
 * frame to the ring buffer and invoke the callbacks for the completed frames.
 */
static void ring_work(struct work_struct *work)
{
	struct tb_ring *ring = container_of(work, typeof(*ring), work);
	struct ring_frame *frame;
	bool canceled = false;
	unsigned long flags;
	LIST_HEAD(done);

	spin_lock_irqsave(&ring->lock, flags);

	if (!ring->running) {
		/*  Move all frames to done and mark them as canceled. */
		list_splice_tail_init(&ring->in_flight, &done);
		list_splice_tail_init(&ring->queue, &done);
		canceled = true;
		goto invoke_callback;
	}

	while (!ring_empty(ring)) {
		if (!(ring->descriptors[ring->tail].flags
				& RING_DESC_COMPLETED))
			break;
		frame = list_first_entry(&ring->in_flight, typeof(*frame),
					 list);
		list_move_tail(&frame->list, &done);
		if (!ring->is_tx) {
			frame->size = ring->descriptors[ring->tail].length;
			frame->eof = ring->descriptors[ring->tail].eof;
			frame->sof = ring->descriptors[ring->tail].sof;
			frame->flags = ring->descriptors[ring->tail].flags;
		}
		ring->tail = (ring->tail + 1) % ring->size;
	}
	ring_write_descriptors(ring);

invoke_callback:
	/* allow callbacks to schedule new work */
	spin_unlock_irqrestore(&ring->lock, flags);
	while (!list_empty(&done)) {
		frame = list_first_entry(&done, typeof(*frame), list);
		/*
		 * The callback may reenqueue or delete frame.
		 * Do not hold on to it.
		 */
		list_del_init(&frame->list);
		if (frame->callback)
			frame->callback(ring, frame, canceled);
	}
}

int __tb_ring_enqueue(struct tb_ring *ring, struct ring_frame *frame)
{
	unsigned long flags;
	int ret = 0;

	spin_lock_irqsave(&ring->lock, flags);
	if (ring->running) {
		list_add_tail(&frame->list, &ring->queue);
		ring_write_descriptors(ring);
	} else {
		ret = -ESHUTDOWN;
	}
	spin_unlock_irqrestore(&ring->lock, flags);
	return ret;
}
EXPORT_SYMBOL_GPL(__tb_ring_enqueue);

/**
 * tb_ring_poll() - Poll one completed frame from the ring
 * @ring: Ring to poll
 *
 * This function can be called when @start_poll callback of the @ring
 * has been called. It will read one completed frame from the ring and
 * return it to the caller. Returns %NULL if there is no more completed
 * frames.
 */
struct ring_frame *tb_ring_poll(struct tb_ring *ring)
{
	struct ring_frame *frame = NULL;
	unsigned long flags;

	spin_lock_irqsave(&ring->lock, flags);
	if (!ring->running)
		goto unlock;
	if (ring_empty(ring))
		goto unlock;

	if (ring->descriptors[ring->tail].flags & RING_DESC_COMPLETED) {
		frame = list_first_entry(&ring->in_flight, typeof(*frame),
					 list);
		list_del_init(&frame->list);

		if (!ring->is_tx) {
			frame->size = ring->descriptors[ring->tail].length;
			frame->eof = ring->descriptors[ring->tail].eof;
			frame->sof = ring->descriptors[ring->tail].sof;
			frame->flags = ring->descriptors[ring->tail].flags;
		}

		ring->tail = (ring->tail + 1) % ring->size;
	}

unlock:
	spin_unlock_irqrestore(&ring->lock, flags);
	return frame;
}
EXPORT_SYMBOL_GPL(tb_ring_poll);

static void __ring_interrupt_mask(struct tb_ring *ring, bool mask)
{
	int idx = ring_interrupt_index(ring);
	int reg = REG_RING_INTERRUPT_BASE + idx / 32 * 4;
	int bit = idx % 32;
	u32 val;

	val = ioread32(ring->nhi->iobase + reg);
	if (mask)
		val &= ~BIT(bit);
	else
		val |= BIT(bit);
	iowrite32(val, ring->nhi->iobase + reg);
}

/* Both @nhi->lock and @ring->lock should be held */
static void __ring_interrupt(struct tb_ring *ring)
{
	if (!ring->running)
		return;

	if (ring->start_poll) {
		__ring_interrupt_mask(ring, true);
		ring->start_poll(ring->poll_data);
	} else {
		schedule_work(&ring->work);
	}
}

/**
 * tb_ring_poll_complete() - Re-start interrupt for the ring
 * @ring: Ring to re-start the interrupt
 *
 * This will re-start (unmask) the ring interrupt once the user is done
 * with polling.
 */
void tb_ring_poll_complete(struct tb_ring *ring)
{
	unsigned long flags;

	spin_lock_irqsave(&ring->nhi->lock, flags);
	spin_lock(&ring->lock);
	if (ring->start_poll)
		__ring_interrupt_mask(ring, false);
	spin_unlock(&ring->lock);
	spin_unlock_irqrestore(&ring->nhi->lock, flags);
}
EXPORT_SYMBOL_GPL(tb_ring_poll_complete);

static void ring_clear_msix(const struct tb_ring *ring)
{
	int bit;

	if (ring->nhi->quirks & QUIRK_AUTO_CLEAR_INT)
		return;

	bit = ring_interrupt_index(ring) & 31;
	if (ring->is_tx)
		iowrite32(BIT(bit), ring->nhi->iobase + REG_RING_INT_CLEAR);
	else
		iowrite32(BIT(bit), ring->nhi->iobase + REG_RING_INT_CLEAR +
			  4 * (ring->nhi->hop_count / 32));
}

static irqreturn_t ring_msix(int irq, void *data)
{
	struct tb_ring *ring = data;

	spin_lock(&ring->nhi->lock);
	ring_clear_msix(ring);
	spin_lock(&ring->lock);
	__ring_interrupt(ring);
	spin_unlock(&ring->lock);
	spin_unlock(&ring->nhi->lock);

	return IRQ_HANDLED;
}

static int ring_request_msix(struct tb_ring *ring, bool no_suspend)
{
	struct tb_nhi *nhi = ring->nhi;
	unsigned long irqflags;
	int ret;

	if (!nhi->pdev->msix_enabled)
		return 0;

	ret = ida_simple_get(&nhi->msix_ida, 0, MSIX_MAX_VECS, GFP_KERNEL);
	if (ret < 0)
		return ret;

	ring->vector = ret;

	ret = pci_irq_vector(ring->nhi->pdev, ring->vector);
	if (ret < 0)
		goto err_ida_remove;

	ring->irq = ret;

	irqflags = no_suspend ? IRQF_NO_SUSPEND : 0;
	ret = request_irq(ring->irq, ring_msix, irqflags, "thunderbolt", ring);
	if (ret)
		goto err_ida_remove;

	return 0;

err_ida_remove:
	ida_simple_remove(&nhi->msix_ida, ring->vector);

	return ret;
}

static void ring_release_msix(struct tb_ring *ring)
{
	if (ring->irq <= 0)
		return;

	free_irq(ring->irq, ring);
	ida_simple_remove(&ring->nhi->msix_ida, ring->vector);
	ring->vector = 0;
	ring->irq = 0;
}

static int nhi_alloc_hop(struct tb_nhi *nhi, struct tb_ring *ring)
{
	unsigned int start_hop = RING_FIRST_USABLE_HOPID;
	int ret = 0;

	if (nhi->quirks & QUIRK_E2E) {
		start_hop = RING_FIRST_USABLE_HOPID + 1;
		if (ring->flags & RING_FLAG_E2E && !ring->is_tx) {
			dev_dbg(&nhi->pdev->dev, "quirking E2E TX HopID %u -> %u\n",
				ring->e2e_tx_hop, RING_E2E_RESERVED_HOPID);
			ring->e2e_tx_hop = RING_E2E_RESERVED_HOPID;
		}
	}

	spin_lock_irq(&nhi->lock);

	if (ring->hop < 0) {
		unsigned int i;

		/*
		 * Automatically allocate HopID from the non-reserved
		 * range 1 .. hop_count - 1.
		 */
		for (i = start_hop; i < nhi->hop_count; i++) {
			if (ring->is_tx) {
				if (!nhi->tx_rings[i]) {
					ring->hop = i;
					break;
				}
			} else {
				if (!nhi->rx_rings[i]) {
					ring->hop = i;
					break;
				}
			}
		}
	}

	if (ring->hop > 0 && ring->hop < start_hop) {
		dev_warn(&nhi->pdev->dev, "invalid hop: %d\n", ring->hop);
		ret = -EINVAL;
		goto err_unlock;
	}
	if (ring->hop < 0 || ring->hop >= nhi->hop_count) {
		dev_warn(&nhi->pdev->dev, "invalid hop: %d\n", ring->hop);
		ret = -EINVAL;
		goto err_unlock;
	}
	if (ring->is_tx && nhi->tx_rings[ring->hop]) {
		dev_warn(&nhi->pdev->dev, "TX hop %d already allocated\n",
			 ring->hop);
		ret = -EBUSY;
		goto err_unlock;
	}
	if (!ring->is_tx && nhi->rx_rings[ring->hop]) {
		dev_warn(&nhi->pdev->dev, "RX hop %d already allocated\n",
			 ring->hop);
		ret = -EBUSY;
		goto err_unlock;
	}

	if (ring->is_tx)
		nhi->tx_rings[ring->hop] = ring;
	else
		nhi->rx_rings[ring->hop] = ring;

err_unlock:
	spin_unlock_irq(&nhi->lock);

	return ret;
}

static struct tb_ring *tb_ring_alloc(struct tb_nhi *nhi, u32 hop, int size,
				     bool transmit, unsigned int flags,
				     int e2e_tx_hop, u16 sof_mask, u16 eof_mask,
				     void (*start_poll)(void *),
				     void *poll_data)
{
	struct tb_ring *ring = NULL;

	dev_dbg(&nhi->pdev->dev, "allocating %s ring %d of size %d\n",
		transmit ? "TX" : "RX", hop, size);

	ring = kzalloc(sizeof(*ring), GFP_KERNEL);
	if (!ring)
		return NULL;

	spin_lock_init(&ring->lock);
	INIT_LIST_HEAD(&ring->queue);
	INIT_LIST_HEAD(&ring->in_flight);
	INIT_WORK(&ring->work, ring_work);

	ring->nhi = nhi;
	ring->hop = hop;
	ring->is_tx = transmit;
	ring->size = size;
	ring->flags = flags;
	ring->e2e_tx_hop = e2e_tx_hop;
	ring->sof_mask = sof_mask;
	ring->eof_mask = eof_mask;
	ring->head = 0;
	ring->tail = 0;
	ring->running = false;
	ring->start_poll = start_poll;
	ring->poll_data = poll_data;

	ring->descriptors = dma_alloc_coherent(&ring->nhi->pdev->dev,
			size * sizeof(*ring->descriptors),
			&ring->descriptors_dma, GFP_KERNEL | __GFP_ZERO);
	if (!ring->descriptors)
		goto err_free_ring;

	if (ring_request_msix(ring, flags & RING_FLAG_NO_SUSPEND))
		goto err_free_descs;

	if (nhi_alloc_hop(nhi, ring))
		goto err_release_msix;

	return ring;

err_release_msix:
	ring_release_msix(ring);
err_free_descs:
	dma_free_coherent(&ring->nhi->pdev->dev,
			  ring->size * sizeof(*ring->descriptors),
			  ring->descriptors, ring->descriptors_dma);
err_free_ring:
	kfree(ring);

	return NULL;
}

/**
 * tb_ring_alloc_tx() - Allocate DMA ring for transmit
 * @nhi: Pointer to the NHI the ring is to be allocated
 * @hop: HopID (ring) to allocate
 * @size: Number of entries in the ring
 * @flags: Flags for the ring
 */
struct tb_ring *tb_ring_alloc_tx(struct tb_nhi *nhi, int hop, int size,
				 unsigned int flags)
{
	return tb_ring_alloc(nhi, hop, size, true, flags, 0, 0, 0, NULL, NULL);
}
EXPORT_SYMBOL_GPL(tb_ring_alloc_tx);

/**
 * tb_ring_alloc_rx() - Allocate DMA ring for receive
 * @nhi: Pointer to the NHI the ring is to be allocated
 * @hop: HopID (ring) to allocate. Pass %-1 for automatic allocation.
 * @size: Number of entries in the ring
 * @flags: Flags for the ring
 * @e2e_tx_hop: Transmit HopID when E2E is enabled in @flags
 * @sof_mask: Mask of PDF values that start a frame
 * @eof_mask: Mask of PDF values that end a frame
 * @start_poll: If not %NULL the ring will call this function when an
 *		interrupt is triggered and masked, instead of callback
 *		in each Rx frame.
 * @poll_data: Optional data passed to @start_poll
 */
struct tb_ring *tb_ring_alloc_rx(struct tb_nhi *nhi, int hop, int size,
				 unsigned int flags, int e2e_tx_hop,
				 u16 sof_mask, u16 eof_mask,
				 void (*start_poll)(void *), void *poll_data)
{
	return tb_ring_alloc(nhi, hop, size, false, flags, e2e_tx_hop, sof_mask, eof_mask,
			     start_poll, poll_data);
}
EXPORT_SYMBOL_GPL(tb_ring_alloc_rx);

/**
 * tb_ring_start() - enable a ring
 * @ring: Ring to start
 *
 * Must not be invoked in parallel with tb_ring_stop().
 */
void tb_ring_start(struct tb_ring *ring)
{
	u16 frame_size;
	u32 flags;

	spin_lock_irq(&ring->nhi->lock);
	spin_lock(&ring->lock);
	if (ring->nhi->going_away)
		goto err;
	if (ring->running) {
		dev_WARN(&ring->nhi->pdev->dev, "ring already started\n");
		goto err;
	}
	dev_dbg(&ring->nhi->pdev->dev, "starting %s %d\n",
		RING_TYPE(ring), ring->hop);

	if (ring->flags & RING_FLAG_FRAME) {
		/* Means 4096 */
		frame_size = 0;
		flags = RING_FLAG_ENABLE;
	} else {
		frame_size = TB_FRAME_SIZE;
		flags = RING_FLAG_ENABLE | RING_FLAG_RAW;
	}

	ring_iowrite64desc(ring, ring->descriptors_dma, 0);
	if (ring->is_tx) {
		ring_iowrite32desc(ring, ring->size, 12);
		ring_iowrite32options(ring, 0, 4); /* time releated ? */
		ring_iowrite32options(ring, flags, 0);
	} else {
		u32 sof_eof_mask = ring->sof_mask << 16 | ring->eof_mask;

		ring_iowrite32desc(ring, (frame_size << 16) | ring->size, 12);
		ring_iowrite32options(ring, sof_eof_mask, 4);
		ring_iowrite32options(ring, flags, 0);
	}

	/*
	 * Now that the ring valid bit is set we can configure E2E if
	 * enabled for the ring.
	 */
	if (ring->flags & RING_FLAG_E2E) {
		if (!ring->is_tx) {
			u32 hop;

			hop = ring->e2e_tx_hop << REG_RX_OPTIONS_E2E_HOP_SHIFT;
			hop &= REG_RX_OPTIONS_E2E_HOP_MASK;
			flags |= hop;

			dev_dbg(&ring->nhi->pdev->dev,
				"enabling E2E for %s %d with TX HopID %d\n",
				RING_TYPE(ring), ring->hop, ring->e2e_tx_hop);
		} else {
			dev_dbg(&ring->nhi->pdev->dev, "enabling E2E for %s %d\n",
				RING_TYPE(ring), ring->hop);
		}

		flags |= RING_FLAG_E2E_FLOW_CONTROL;
		ring_iowrite32options(ring, flags, 0);
	}

	ring_interrupt_active(ring, true);
	ring->running = true;
err:
	spin_unlock(&ring->lock);
	spin_unlock_irq(&ring->nhi->lock);
}
EXPORT_SYMBOL_GPL(tb_ring_start);

/**
 * tb_ring_stop() - shutdown a ring
 * @ring: Ring to stop
 *
 * Must not be invoked from a callback.
 *
 * This method will disable the ring. Further calls to
 * tb_ring_tx/tb_ring_rx will return -ESHUTDOWN until ring_stop has been
 * called.
 *
 * All enqueued frames will be canceled and their callbacks will be executed
 * with frame->canceled set to true (on the callback thread). This method
 * returns only after all callback invocations have finished.
 */
void tb_ring_stop(struct tb_ring *ring)
{
	spin_lock_irq(&ring->nhi->lock);
	spin_lock(&ring->lock);
	dev_dbg(&ring->nhi->pdev->dev, "stopping %s %d\n",
		RING_TYPE(ring), ring->hop);
	if (ring->nhi->going_away)
		goto err;
	if (!ring->running) {
		dev_WARN(&ring->nhi->pdev->dev, "%s %d already stopped\n",
			 RING_TYPE(ring), ring->hop);
		goto err;
	}
	ring_interrupt_active(ring, false);

	ring_iowrite32options(ring, 0, 0);
	ring_iowrite64desc(ring, 0, 0);
	ring_iowrite32desc(ring, 0, 8);
	ring_iowrite32desc(ring, 0, 12);
	ring->head = 0;
	ring->tail = 0;
	ring->running = false;

err:
	spin_unlock(&ring->lock);
	spin_unlock_irq(&ring->nhi->lock);

	/*
	 * schedule ring->work to invoke callbacks on all remaining frames.
	 */
	schedule_work(&ring->work);
	flush_work(&ring->work);
}
EXPORT_SYMBOL_GPL(tb_ring_stop);

/*
 * tb_ring_free() - free ring
 *
 * When this method returns all invocations of ring->callback will have
 * finished.
 *
 * Ring must be stopped.
 *
 * Must NOT be called from ring_frame->callback!
 */
void tb_ring_free(struct tb_ring *ring)
{
	spin_lock_irq(&ring->nhi->lock);
	/*
	 * Dissociate the ring from the NHI. This also ensures that
	 * nhi_interrupt_work cannot reschedule ring->work.
	 */
	if (ring->is_tx)
		ring->nhi->tx_rings[ring->hop] = NULL;
	else
		ring->nhi->rx_rings[ring->hop] = NULL;

	if (ring->running) {
		dev_WARN(&ring->nhi->pdev->dev, "%s %d still running\n",
			 RING_TYPE(ring), ring->hop);
	}
	spin_unlock_irq(&ring->nhi->lock);

	ring_release_msix(ring);

	dma_free_coherent(&ring->nhi->pdev->dev,
			  ring->size * sizeof(*ring->descriptors),
			  ring->descriptors, ring->descriptors_dma);

	ring->descriptors = NULL;
	ring->descriptors_dma = 0;


	dev_dbg(&ring->nhi->pdev->dev, "freeing %s %d\n", RING_TYPE(ring),
		ring->hop);

	/*
	 * ring->work can no longer be scheduled (it is scheduled only
	 * by nhi_interrupt_work, ring_stop and ring_msix). Wait for it
	 * to finish before freeing the ring.
	 */
	flush_work(&ring->work);
	kfree(ring);
}
EXPORT_SYMBOL_GPL(tb_ring_free);

/**
 * nhi_mailbox_cmd() - Send a command through NHI mailbox
 * @nhi: Pointer to the NHI structure
 * @cmd: Command to send
 * @data: Data to be send with the command
 *
 * Sends mailbox command to the firmware running on NHI. Returns %0 in
 * case of success and negative errno in case of failure.
 */
int nhi_mailbox_cmd(struct tb_nhi *nhi, enum nhi_mailbox_cmd cmd, u32 data)
{
	ktime_t timeout;
	u32 val;

	iowrite32(data, nhi->iobase + REG_INMAIL_DATA);

	val = ioread32(nhi->iobase + REG_INMAIL_CMD);
	val &= ~(REG_INMAIL_CMD_MASK | REG_INMAIL_ERROR);
	val |= REG_INMAIL_OP_REQUEST | cmd;
	iowrite32(val, nhi->iobase + REG_INMAIL_CMD);

	timeout = ktime_add_ms(ktime_get(), NHI_MAILBOX_TIMEOUT);
	do {
		val = ioread32(nhi->iobase + REG_INMAIL_CMD);
		if (!(val & REG_INMAIL_OP_REQUEST))
			break;
		usleep_range(10, 20);
	} while (ktime_before(ktime_get(), timeout));

	if (val & REG_INMAIL_OP_REQUEST)
		return -ETIMEDOUT;
	if (val & REG_INMAIL_ERROR)
		return -EIO;

	return 0;
}

/**
 * nhi_mailbox_mode() - Return current firmware operation mode
 * @nhi: Pointer to the NHI structure
 *
 * The function reads current firmware operation mode using NHI mailbox
 * registers and returns it to the caller.
 */
enum nhi_fw_mode nhi_mailbox_mode(struct tb_nhi *nhi)
{
	u32 val;

	val = ioread32(nhi->iobase + REG_OUTMAIL_CMD);
	val &= REG_OUTMAIL_CMD_OPMODE_MASK;
	val >>= REG_OUTMAIL_CMD_OPMODE_SHIFT;

	return (enum nhi_fw_mode)val;
}

static void nhi_interrupt_work(struct work_struct *work)
{
	struct tb_nhi *nhi = container_of(work, typeof(*nhi), interrupt_work);
	int value = 0; /* Suppress uninitialized usage warning. */
	int bit;
	int hop = -1;
	int type = 0; /* current interrupt type 0: TX, 1: RX, 2: RX overflow */
	struct tb_ring *ring;

	spin_lock_irq(&nhi->lock);

	/*
	 * Starting at REG_RING_NOTIFY_BASE there are three status bitfields
	 * (TX, RX, RX overflow). We iterate over the bits and read a new
	 * dwords as required. The registers are cleared on read.
	 */
	for (bit = 0; bit < 3 * nhi->hop_count; bit++) {
		if (bit % 32 == 0)
			value = ioread32(nhi->iobase
					 + REG_RING_NOTIFY_BASE
					 + 4 * (bit / 32));
		if (++hop == nhi->hop_count) {
			hop = 0;
			type++;
		}
		if ((value & (1 << (bit % 32))) == 0)
			continue;
		if (type == 2) {
			dev_warn(&nhi->pdev->dev,
				 "RX overflow for ring %d\n",
				 hop);
			continue;
		}
		if (type == 0)
			ring = nhi->tx_rings[hop];
		else
			ring = nhi->rx_rings[hop];
		if (ring == NULL) {
			dev_warn(&nhi->pdev->dev,
				 "got interrupt for inactive %s ring %d\n",
				 type ? "RX" : "TX",
				 hop);
			continue;
		}

		spin_lock(&ring->lock);
		__ring_interrupt(ring);
		spin_unlock(&ring->lock);
	}
	spin_unlock_irq(&nhi->lock);
}

static irqreturn_t nhi_msi(int irq, void *data)
{
	struct tb_nhi *nhi = data;
	schedule_work(&nhi->interrupt_work);
	return IRQ_HANDLED;
}

static int __nhi_suspend_noirq(struct device *dev, bool wakeup)
{
	struct pci_dev *pdev = to_pci_dev(dev);
	struct tb *tb = pci_get_drvdata(pdev);
	struct tb_nhi *nhi = tb->nhi;
	int ret;

	ret = tb_domain_suspend_noirq(tb);
	if (ret)
		return ret;

	if (nhi->ops && nhi->ops->suspend_noirq) {
		ret = nhi->ops->suspend_noirq(tb->nhi, wakeup);
		if (ret)
			return ret;
	}

	return 0;
}

static int nhi_suspend_noirq(struct device *dev)
{
	return __nhi_suspend_noirq(dev, device_may_wakeup(dev));
}

static int nhi_freeze_noirq(struct device *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev);
	struct tb *tb = pci_get_drvdata(pdev);

	return tb_domain_freeze_noirq(tb);
}

static int nhi_thaw_noirq(struct device *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev);
	struct tb *tb = pci_get_drvdata(pdev);

	return tb_domain_thaw_noirq(tb);
}

static bool nhi_wake_supported(struct pci_dev *pdev)
{
	u8 val;

	/*
	 * If power rails are sustainable for wakeup from S4 this
	 * property is set by the BIOS.
	 */
	if (device_property_read_u8(&pdev->dev, "WAKE_SUPPORTED", &val))
		return !!val;

	return true;
}

static int nhi_poweroff_noirq(struct device *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev);
	bool wakeup;

	wakeup = device_may_wakeup(dev) && nhi_wake_supported(pdev);
	return __nhi_suspend_noirq(dev, wakeup);
}

static void nhi_enable_int_throttling(struct tb_nhi *nhi)
{
	/* Throttling is specified in 256ns increments */
	u32 throttle = DIV_ROUND_UP(128 * NSEC_PER_USEC, 256);
	unsigned int i;

	/*
	 * Configure interrupt throttling for all vectors even if we
	 * only use few.
	 */
	for (i = 0; i < MSIX_MAX_VECS; i++) {
		u32 reg = REG_INT_THROTTLING_RATE + i * 4;
		iowrite32(throttle, nhi->iobase + reg);
	}
}

static int nhi_resume_noirq(struct device *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev);
	struct tb *tb = pci_get_drvdata(pdev);
	struct tb_nhi *nhi = tb->nhi;
	int ret;

	/*
	 * Check that the device is still there. It may be that the user
	 * unplugged last device which causes the host controller to go
	 * away on PCs.
	 */
	if (!pci_device_is_present(pdev)) {
		nhi->going_away = true;
	} else {
		if (nhi->ops && nhi->ops->resume_noirq) {
			ret = nhi->ops->resume_noirq(nhi);
			if (ret)
				return ret;
		}
		nhi_enable_int_throttling(tb->nhi);
	}

	return tb_domain_resume_noirq(tb);
}

static int nhi_suspend(struct device *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev);
	struct tb *tb = pci_get_drvdata(pdev);

	return tb_domain_suspend(tb);
}

static void nhi_complete(struct device *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev);
	struct tb *tb = pci_get_drvdata(pdev);

	/*
	 * If we were runtime suspended when system suspend started,
	 * schedule runtime resume now. It should bring the domain back
	 * to functional state.
	 */
	if (pm_runtime_suspended(&pdev->dev))
		pm_runtime_resume(&pdev->dev);
	else
		tb_domain_complete(tb);
}

static int nhi_runtime_suspend(struct device *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev);
	struct tb *tb = pci_get_drvdata(pdev);
	struct tb_nhi *nhi = tb->nhi;
	int ret;

	ret = tb_domain_runtime_suspend(tb);
	if (ret)
		return ret;

	if (nhi->ops && nhi->ops->runtime_suspend) {
		ret = nhi->ops->runtime_suspend(tb->nhi);
		if (ret)
			return ret;
	}
	return 0;
}

static int nhi_runtime_resume(struct device *dev)
{
	struct pci_dev *pdev = to_pci_dev(dev);
	struct tb *tb = pci_get_drvdata(pdev);
	struct tb_nhi *nhi = tb->nhi;
	int ret;

	if (nhi->ops && nhi->ops->runtime_resume) {
		ret = nhi->ops->runtime_resume(nhi);
		if (ret)
			return ret;
	}

	nhi_enable_int_throttling(nhi);
	return tb_domain_runtime_resume(tb);
}

static void nhi_shutdown(struct tb_nhi *nhi)
{
	int i;

	dev_dbg(&nhi->pdev->dev, "shutdown\n");

	for (i = 0; i < nhi->hop_count; i++) {
		if (nhi->tx_rings[i])
			dev_WARN(&nhi->pdev->dev,
				 "TX ring %d is still active\n", i);
		if (nhi->rx_rings[i])
			dev_WARN(&nhi->pdev->dev,
				 "RX ring %d is still active\n", i);
	}
	nhi_disable_interrupts(nhi);
	/*
	 * We have to release the irq before calling flush_work. Otherwise an
	 * already executing IRQ handler could call schedule_work again.
	 */
	if (!nhi->pdev->msix_enabled) {
		devm_free_irq(&nhi->pdev->dev, nhi->pdev->irq, nhi);
		flush_work(&nhi->interrupt_work);
	}
	ida_destroy(&nhi->msix_ida);

	if (nhi->ops && nhi->ops->shutdown)
		nhi->ops->shutdown(nhi);
}

static void nhi_check_quirks(struct tb_nhi *nhi)
{
	if (nhi->pdev->vendor == PCI_VENDOR_ID_INTEL) {
		/*
		 * Intel hardware supports auto clear of the interrupt
		 * status register right after interrupt is being
		 * issued.
		 */
		nhi->quirks |= QUIRK_AUTO_CLEAR_INT;

		switch (nhi->pdev->device) {
		case PCI_DEVICE_ID_INTEL_FALCON_RIDGE_2C_NHI:
		case PCI_DEVICE_ID_INTEL_FALCON_RIDGE_4C_NHI:
			/*
			 * Falcon Ridge controller needs the end-to-end
			 * flow control workaround to avoid losing Rx
			 * packets when RING_FLAG_E2E is set.
			 */
			nhi->quirks |= QUIRK_E2E;
			break;
		}
	}
}

static int nhi_check_iommu_pdev(struct pci_dev *pdev, void *data)
{
	if (!pdev->external_facing ||
	    !device_iommu_capable(&pdev->dev, IOMMU_CAP_PRE_BOOT_PROTECTION))
		return 0;
	*(bool *)data = true;
	return 1; /* Stop walking */
}

static void nhi_check_iommu(struct tb_nhi *nhi)
{
	struct pci_bus *bus = nhi->pdev->bus;
	bool port_ok = false;

	/*
	 * Ideally what we'd do here is grab every PCI device that
	 * represents a tunnelling adapter for this NHI and check their
	 * status directly, but unfortunately USB4 seems to make it
	 * obnoxiously difficult to reliably make any correlation.
	 *
	 * So for now we'll have to bodge it... Hoping that the system
	 * is at least sane enough that an adapter is in the same PCI
	 * segment as its NHI, if we can find *something* on that segment
	 * which meets the requirements for Kernel DMA Protection, we'll
	 * take that to imply that firmware is aware and has (hopefully)
	 * done the right thing in general. We need to know that the PCI
	 * layer has seen the ExternalFacingPort property which will then
	 * inform the IOMMU layer to enforce the complete "untrusted DMA"
	 * flow, but also that the IOMMU driver itself can be trusted not
	 * to have been subverted by a pre-boot DMA attack.
	 */
	while (bus->parent)
		bus = bus->parent;

	pci_walk_bus(bus, nhi_check_iommu_pdev, &port_ok);

	nhi->iommu_dma_protection = port_ok;
	dev_dbg(&nhi->pdev->dev, "IOMMU DMA protection is %s\n",
		str_enabled_disabled(port_ok));
}

static int nhi_init_msi(struct tb_nhi *nhi)
{
	struct pci_dev *pdev = nhi->pdev;
	struct device *dev = &pdev->dev;
	int res, irq, nvec;

	/* In case someone left them on. */
	nhi_disable_interrupts(nhi);

	nhi_enable_int_throttling(nhi);

	ida_init(&nhi->msix_ida);

	/*
	 * The NHI has 16 MSI-X vectors or a single MSI. We first try to
	 * get all MSI-X vectors and if we succeed, each ring will have
	 * one MSI-X. If for some reason that does not work out, we
	 * fallback to a single MSI.
	 */
	nvec = pci_alloc_irq_vectors(pdev, MSIX_MIN_VECS, MSIX_MAX_VECS,
				     PCI_IRQ_MSIX);
	if (nvec < 0) {
		nvec = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI);
		if (nvec < 0)
			return nvec;

		INIT_WORK(&nhi->interrupt_work, nhi_interrupt_work);

		irq = pci_irq_vector(nhi->pdev, 0);
		if (irq < 0)
			return irq;

		res = devm_request_irq(&pdev->dev, irq, nhi_msi,
				       IRQF_NO_SUSPEND, "thunderbolt", nhi);
		if (res)
			return dev_err_probe(dev, res, "request_irq failed, aborting\n");
	}

	return 0;
}

static bool nhi_imr_valid(struct pci_dev *pdev)
{
	u8 val;

	if (!device_property_read_u8(&pdev->dev, "IMR_VALID", &val))
		return !!val;

	return true;
}

static struct tb *nhi_select_cm(struct tb_nhi *nhi)
{
	struct tb *tb;

	/*
	 * USB4 case is simple. If we got control of any of the
	 * capabilities, we use software CM.
	 */
	if (tb_acpi_is_native())
		return tb_probe(nhi);

	/*
	 * Either firmware based CM is running (we did not get control
	 * from the firmware) or this is pre-USB4 PC so try first
	 * firmware CM and then fallback to software CM.
	 */
	tb = icm_probe(nhi);
	if (!tb)
		tb = tb_probe(nhi);

	return tb;
}

static int nhi_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
	struct device *dev = &pdev->dev;
	struct tb_nhi *nhi;
	struct tb *tb;
	int res;

	if (!nhi_imr_valid(pdev))
		return dev_err_probe(dev, -ENODEV, "firmware image not valid, aborting\n");

	res = pcim_enable_device(pdev);
	if (res)
		return dev_err_probe(dev, res, "cannot enable PCI device, aborting\n");

	res = pcim_iomap_regions(pdev, 1 << 0, "thunderbolt");
	if (res)
		return dev_err_probe(dev, res, "cannot obtain PCI resources, aborting\n");

	nhi = devm_kzalloc(&pdev->dev, sizeof(*nhi), GFP_KERNEL);
	if (!nhi)
		return -ENOMEM;

	nhi->pdev = pdev;
	nhi->ops = (const struct tb_nhi_ops *)id->driver_data;
	/* cannot fail - table is allocated in pcim_iomap_regions */
	nhi->iobase = pcim_iomap_table(pdev)[0];
	nhi->hop_count = ioread32(nhi->iobase + REG_HOP_COUNT) & 0x3ff;
	dev_dbg(dev, "total paths: %d\n", nhi->hop_count);

	nhi->tx_rings = devm_kcalloc(&pdev->dev, nhi->hop_count,
				     sizeof(*nhi->tx_rings), GFP_KERNEL);
	nhi->rx_rings = devm_kcalloc(&pdev->dev, nhi->hop_count,
				     sizeof(*nhi->rx_rings), GFP_KERNEL);
	if (!nhi->tx_rings || !nhi->rx_rings)
		return -ENOMEM;

	nhi_check_quirks(nhi);
	nhi_check_iommu(nhi);

	res = nhi_init_msi(nhi);
	if (res)
		return dev_err_probe(dev, res, "cannot enable MSI, aborting\n");

	spin_lock_init(&nhi->lock);

	res = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
	if (res)
		return dev_err_probe(dev, res, "failed to set DMA mask\n");

	pci_set_master(pdev);

	if (nhi->ops && nhi->ops->init) {
		res = nhi->ops->init(nhi);
		if (res)
			return res;
	}

	tb = nhi_select_cm(nhi);
	if (!tb)
		return dev_err_probe(dev, -ENODEV,
			"failed to determine connection manager, aborting\n");

	dev_dbg(dev, "NHI initialized, starting thunderbolt\n");

	res = tb_domain_add(tb);
	if (res) {
		/*
		 * At this point the RX/TX rings might already have been
		 * activated. Do a proper shutdown.
		 */
		tb_domain_put(tb);
		nhi_shutdown(nhi);
		return res;
	}
	pci_set_drvdata(pdev, tb);

	device_wakeup_enable(&pdev->dev);

	pm_runtime_allow(&pdev->dev);
	pm_runtime_set_autosuspend_delay(&pdev->dev, TB_AUTOSUSPEND_DELAY);
	pm_runtime_use_autosuspend(&pdev->dev);
	pm_runtime_put_autosuspend(&pdev->dev);

	return 0;
}

static void nhi_remove(struct pci_dev *pdev)
{
	struct tb *tb = pci_get_drvdata(pdev);
	struct tb_nhi *nhi = tb->nhi;

	pm_runtime_get_sync(&pdev->dev);
	pm_runtime_dont_use_autosuspend(&pdev->dev);
	pm_runtime_forbid(&pdev->dev);

	tb_domain_remove(tb);
	nhi_shutdown(nhi);
}

/*
 * The tunneled pci bridges are siblings of us. Use resume_noirq to reenable
 * the tunnels asap. A corresponding pci quirk blocks the downstream bridges
 * resume_noirq until we are done.
 */
static const struct dev_pm_ops nhi_pm_ops = {
	.suspend_noirq = nhi_suspend_noirq,
	.resume_noirq = nhi_resume_noirq,
	.freeze_noirq = nhi_freeze_noirq,  /*
					    * we just disable hotplug, the
					    * pci-tunnels stay alive.
					    */
	.thaw_noirq = nhi_thaw_noirq,
	.restore_noirq = nhi_resume_noirq,
	.suspend = nhi_suspend,
	.poweroff_noirq = nhi_poweroff_noirq,
	.poweroff = nhi_suspend,
	.complete = nhi_complete,
	.runtime_suspend = nhi_runtime_suspend,
	.runtime_resume = nhi_runtime_resume,
};

static struct pci_device_id nhi_ids[] = {
	/*
	 * We have to specify class, the TB bridges use the same device and
	 * vendor (sub)id on gen 1 and gen 2 controllers.
	 */
	{
		.class = PCI_CLASS_SYSTEM_OTHER << 8, .class_mask = ~0,
		.vendor = PCI_VENDOR_ID_INTEL,
		.device = PCI_DEVICE_ID_INTEL_LIGHT_RIDGE,
		.subvendor = 0x2222, .subdevice = 0x1111,
	},
	{
		.class = PCI_CLASS_SYSTEM_OTHER << 8, .class_mask = ~0,
		.vendor = PCI_VENDOR_ID_INTEL,
		.device = PCI_DEVICE_ID_INTEL_CACTUS_RIDGE_4C,
		.subvendor = 0x2222, .subdevice = 0x1111,
	},
	{
		.class = PCI_CLASS_SYSTEM_OTHER << 8, .class_mask = ~0,
		.vendor = PCI_VENDOR_ID_INTEL,
		.device = PCI_DEVICE_ID_INTEL_FALCON_RIDGE_2C_NHI,
		.subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID,
	},
	{
		.class = PCI_CLASS_SYSTEM_OTHER << 8, .class_mask = ~0,
		.vendor = PCI_VENDOR_ID_INTEL,
		.device = PCI_DEVICE_ID_INTEL_FALCON_RIDGE_4C_NHI,
		.subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID,
	},

	/* Thunderbolt 3 */
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_2C_NHI) },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_4C_NHI) },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_USBONLY_NHI) },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_LP_NHI) },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_LP_USBONLY_NHI) },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_C_2C_NHI) },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_C_4C_NHI) },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_C_USBONLY_NHI) },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TITAN_RIDGE_2C_NHI) },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TITAN_RIDGE_4C_NHI) },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ICL_NHI0),
	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ICL_NHI1),
	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
	/* Thunderbolt 4 */
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_NHI0),
	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_NHI1),
	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_H_NHI0),
	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_H_NHI1),
	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ADL_NHI0),
	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ADL_NHI1),
	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_RPL_NHI0),
	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_RPL_NHI1),
	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTL_M_NHI0),
	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTL_P_NHI0),
	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTL_P_NHI1),
	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },

	/* Any USB4 compliant host */
	{ PCI_DEVICE_CLASS(PCI_CLASS_SERIAL_USB_USB4, ~0) },

	{ 0,}
};

MODULE_DEVICE_TABLE(pci, nhi_ids);
MODULE_LICENSE("GPL");

static struct pci_driver nhi_driver = {
	.name = "thunderbolt",
	.id_table = nhi_ids,
	.probe = nhi_probe,
	.remove = nhi_remove,
	.shutdown = nhi_remove,
	.driver.pm = &nhi_pm_ops,
};

static int __init nhi_init(void)
{
	int ret;

	ret = tb_domain_init();
	if (ret)
		return ret;
	ret = pci_register_driver(&nhi_driver);
	if (ret)
		tb_domain_exit();
	return ret;
}

static void __exit nhi_unload(void)
{
	pci_unregister_driver(&nhi_driver);
	tb_domain_exit();
}

rootfs_initcall(nhi_init);
module_exit(nhi_unload);