aboutsummaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/sfc/ptp.c
blob: 3dd39dcfe36b92f3221119171b1e0c26729d85e8 (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
/****************************************************************************
 * Driver for Solarflare network controllers and boards
 * Copyright 2011-2013 Solarflare Communications Inc.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 as published
 * by the Free Software Foundation, incorporated herein by reference.
 */

/* Theory of operation:
 *
 * PTP support is assisted by firmware running on the MC, which provides
 * the hardware timestamping capabilities.  Both transmitted and received
 * PTP event packets are queued onto internal queues for subsequent processing;
 * this is because the MC operations are relatively long and would block
 * block NAPI/interrupt operation.
 *
 * Receive event processing:
 *	The event contains the packet's UUID and sequence number, together
 *	with the hardware timestamp.  The PTP receive packet queue is searched
 *	for this UUID/sequence number and, if found, put on a pending queue.
 *	Packets not matching are delivered without timestamps (MCDI events will
 *	always arrive after the actual packet).
 *	It is important for the operation of the PTP protocol that the ordering
 *	of packets between the event and general port is maintained.
 *
 * Work queue processing:
 *	If work waiting, synchronise host/hardware time
 *
 *	Transmit: send packet through MC, which returns the transmission time
 *	that is converted to an appropriate timestamp.
 *
 *	Receive: the packet's reception time is converted to an appropriate
 *	timestamp.
 */
#include <linux/ip.h>
#include <linux/udp.h>
#include <linux/time.h>
#include <linux/ktime.h>
#include <linux/module.h>
#include <linux/net_tstamp.h>
#include <linux/pps_kernel.h>
#include <linux/ptp_clock_kernel.h>
#include "net_driver.h"
#include "efx.h"
#include "mcdi.h"
#include "mcdi_pcol.h"
#include "io.h"
#include "farch_regs.h"
#include "nic.h"

/* Maximum number of events expected to make up a PTP event */
#define	MAX_EVENT_FRAGS			3

/* Maximum delay, ms, to begin synchronisation */
#define	MAX_SYNCHRONISE_WAIT_MS		2

/* How long, at most, to spend synchronising */
#define	SYNCHRONISE_PERIOD_NS		250000

/* How often to update the shared memory time */
#define	SYNCHRONISATION_GRANULARITY_NS	200

/* Minimum permitted length of a (corrected) synchronisation time */
#define	MIN_SYNCHRONISATION_NS		120

/* Maximum permitted length of a (corrected) synchronisation time */
#define	MAX_SYNCHRONISATION_NS		1000

/* How many (MC) receive events that can be queued */
#define	MAX_RECEIVE_EVENTS		8

/* Length of (modified) moving average. */
#define	AVERAGE_LENGTH			16

/* How long an unmatched event or packet can be held */
#define PKT_EVENT_LIFETIME_MS		10

/* Offsets into PTP packet for identification.  These offsets are from the
 * start of the IP header, not the MAC header.  Note that neither PTP V1 nor
 * PTP V2 permit the use of IPV4 options.
 */
#define PTP_DPORT_OFFSET	22

#define PTP_V1_VERSION_LENGTH	2
#define PTP_V1_VERSION_OFFSET	28

#define PTP_V1_UUID_LENGTH	6
#define PTP_V1_UUID_OFFSET	50

#define PTP_V1_SEQUENCE_LENGTH	2
#define PTP_V1_SEQUENCE_OFFSET	58

/* The minimum length of a PTP V1 packet for offsets, etc. to be valid:
 * includes IP header.
 */
#define	PTP_V1_MIN_LENGTH	64

#define PTP_V2_VERSION_LENGTH	1
#define PTP_V2_VERSION_OFFSET	29

#define PTP_V2_UUID_LENGTH	8
#define PTP_V2_UUID_OFFSET	48

/* Although PTP V2 UUIDs are comprised a ClockIdentity (8) and PortNumber (2),
 * the MC only captures the last six bytes of the clock identity. These values
 * reflect those, not the ones used in the standard.  The standard permits
 * mapping of V1 UUIDs to V2 UUIDs with these same values.
 */
#define PTP_V2_MC_UUID_LENGTH	6
#define PTP_V2_MC_UUID_OFFSET	50

#define PTP_V2_SEQUENCE_LENGTH	2
#define PTP_V2_SEQUENCE_OFFSET	58

/* The minimum length of a PTP V2 packet for offsets, etc. to be valid:
 * includes IP header.
 */
#define	PTP_V2_MIN_LENGTH	63

#define	PTP_MIN_LENGTH		63

#define PTP_ADDRESS		0xe0000181	/* 224.0.1.129 */
#define PTP_EVENT_PORT		319
#define PTP_GENERAL_PORT	320

/* Annoyingly the format of the version numbers are different between
 * versions 1 and 2 so it isn't possible to simply look for 1 or 2.
 */
#define	PTP_VERSION_V1		1

#define	PTP_VERSION_V2		2
#define	PTP_VERSION_V2_MASK	0x0f

enum ptp_packet_state {
	PTP_PACKET_STATE_UNMATCHED = 0,
	PTP_PACKET_STATE_MATCHED,
	PTP_PACKET_STATE_TIMED_OUT,
	PTP_PACKET_STATE_MATCH_UNWANTED
};

/* NIC synchronised with single word of time only comprising
 * partial seconds and full nanoseconds: 10^9 ~ 2^30 so 2 bits for seconds.
 */
#define	MC_NANOSECOND_BITS	30
#define	MC_NANOSECOND_MASK	((1 << MC_NANOSECOND_BITS) - 1)
#define	MC_SECOND_MASK		((1 << (32 - MC_NANOSECOND_BITS)) - 1)

/* Maximum parts-per-billion adjustment that is acceptable */
#define MAX_PPB			1000000

/* Number of bits required to hold the above */
#define	MAX_PPB_BITS		20

/* Number of extra bits allowed when calculating fractional ns.
 * EXTRA_BITS + MC_CMD_PTP_IN_ADJUST_BITS + MAX_PPB_BITS should
 * be less than 63.
 */
#define	PPB_EXTRA_BITS		2

/* Precalculate scale word to avoid long long division at runtime */
#define	PPB_SCALE_WORD	((1LL << (PPB_EXTRA_BITS + MC_CMD_PTP_IN_ADJUST_BITS +\
			MAX_PPB_BITS)) / 1000000000LL)

#define PTP_SYNC_ATTEMPTS	4

/**
 * struct efx_ptp_match - Matching structure, stored in sk_buff's cb area.
 * @words: UUID and (partial) sequence number
 * @expiry: Time after which the packet should be delivered irrespective of
 *            event arrival.
 * @state: The state of the packet - whether it is ready for processing or
 *         whether that is of no interest.
 */
struct efx_ptp_match {
	u32 words[DIV_ROUND_UP(PTP_V1_UUID_LENGTH, 4)];
	unsigned long expiry;
	enum ptp_packet_state state;
};

/**
 * struct efx_ptp_event_rx - A PTP receive event (from MC)
 * @seq0: First part of (PTP) UUID
 * @seq1: Second part of (PTP) UUID and sequence number
 * @hwtimestamp: Event timestamp
 */
struct efx_ptp_event_rx {
	struct list_head link;
	u32 seq0;
	u32 seq1;
	ktime_t hwtimestamp;
	unsigned long expiry;
};

/**
 * struct efx_ptp_timeset - Synchronisation between host and MC
 * @host_start: Host time immediately before hardware timestamp taken
 * @seconds: Hardware timestamp, seconds
 * @nanoseconds: Hardware timestamp, nanoseconds
 * @host_end: Host time immediately after hardware timestamp taken
 * @waitns: Number of nanoseconds between hardware timestamp being read and
 *          host end time being seen
 * @window: Difference of host_end and host_start
 * @valid: Whether this timeset is valid
 */
struct efx_ptp_timeset {
	u32 host_start;
	u32 seconds;
	u32 nanoseconds;
	u32 host_end;
	u32 waitns;
	u32 window;	/* Derived: end - start, allowing for wrap */
};

/**
 * struct efx_ptp_data - Precision Time Protocol (PTP) state
 * @channel: The PTP channel
 * @rxq: Receive queue (awaiting timestamps)
 * @txq: Transmit queue
 * @evt_list: List of MC receive events awaiting packets
 * @evt_free_list: List of free events
 * @evt_lock: Lock for manipulating evt_list and evt_free_list
 * @evt_overflow: Boolean indicating that event list has overflowed
 * @rx_evts: Instantiated events (on evt_list and evt_free_list)
 * @workwq: Work queue for processing pending PTP operations
 * @work: Work task
 * @reset_required: A serious error has occurred and the PTP task needs to be
 *                  reset (disable, enable).
 * @rxfilter_event: Receive filter when operating
 * @rxfilter_general: Receive filter when operating
 * @config: Current timestamp configuration
 * @enabled: PTP operation enabled
 * @mode: Mode in which PTP operating (PTP version)
 * @evt_frags: Partly assembled PTP events
 * @evt_frag_idx: Current fragment number
 * @evt_code: Last event code
 * @start: Address at which MC indicates ready for synchronisation
 * @host_time_pps: Host time at last PPS
 * @last_sync_ns: Last number of nanoseconds between readings when synchronising
 * @base_sync_ns: Number of nanoseconds for last synchronisation.
 * @base_sync_valid: Whether base_sync_time is valid.
 * @current_adjfreq: Current ppb adjustment.
 * @phc_clock: Pointer to registered phc device
 * @phc_clock_info: Registration structure for phc device
 * @pps_work: pps work task for handling pps events
 * @pps_workwq: pps work queue
 * @nic_ts_enabled: Flag indicating if NIC generated TS events are handled
 * @txbuf: Buffer for use when transmitting (PTP) packets to MC (avoids
 *         allocations in main data path).
 * @debug_ptp_dir: PTP debugfs directory
 * @missed_rx_sync: Number of packets received without syncrhonisation.
 * @good_syncs: Number of successful synchronisations.
 * @no_time_syncs: Number of synchronisations with no good times.
 * @bad_sync_durations: Number of synchronisations with bad durations.
 * @bad_syncs: Number of failed synchronisations.
 * @last_sync_time: Number of nanoseconds for last synchronisation.
 * @sync_timeouts: Number of synchronisation timeouts
 * @fast_syncs: Number of synchronisations requiring short delay
 * @min_sync_delta: Minimum time between event and synchronisation
 * @max_sync_delta: Maximum time between event and synchronisation
 * @average_sync_delta: Average time between event and synchronisation.
 *                      Modified moving average.
 * @last_sync_delta: Last time between event and synchronisation
 * @mc_stats: Context value for MC statistics
 * @timeset: Last set of synchronisation statistics.
 */
struct efx_ptp_data {
	struct efx_channel *channel;
	struct sk_buff_head rxq;
	struct sk_buff_head txq;
	struct list_head evt_list;
	struct list_head evt_free_list;
	spinlock_t evt_lock;
	bool evt_overflow;
	struct efx_ptp_event_rx rx_evts[MAX_RECEIVE_EVENTS];
	struct workqueue_struct *workwq;
	struct work_struct work;
	bool reset_required;
	u32 rxfilter_event;
	u32 rxfilter_general;
	bool rxfilter_installed;
	struct hwtstamp_config config;
	bool enabled;
	unsigned int mode;
	efx_qword_t evt_frags[MAX_EVENT_FRAGS];
	int evt_frag_idx;
	int evt_code;
	struct efx_buffer start;
	struct pps_event_time host_time_pps;
	unsigned last_sync_ns;
	unsigned base_sync_ns;
	bool base_sync_valid;
	s64 current_adjfreq;
	struct ptp_clock *phc_clock;
	struct ptp_clock_info phc_clock_info;
	struct work_struct pps_work;
	struct workqueue_struct *pps_workwq;
	bool nic_ts_enabled;
	MCDI_DECLARE_BUF(txbuf, MC_CMD_PTP_IN_TRANSMIT_LENMAX);
	struct efx_ptp_timeset
	timeset[MC_CMD_PTP_OUT_SYNCHRONIZE_TIMESET_MAXNUM];
};

static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta);
static int efx_phc_adjtime(struct ptp_clock_info *ptp, s64 delta);
static int efx_phc_gettime(struct ptp_clock_info *ptp, struct timespec *ts);
static int efx_phc_settime(struct ptp_clock_info *ptp,
			   const struct timespec *e_ts);
static int efx_phc_enable(struct ptp_clock_info *ptp,
			  struct ptp_clock_request *request, int on);

/* Enable MCDI PTP support. */
static int efx_ptp_enable(struct efx_nic *efx)
{
	MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_ENABLE_LEN);

	MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_ENABLE);
	MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);
	MCDI_SET_DWORD(inbuf, PTP_IN_ENABLE_QUEUE,
		       efx->ptp_data->channel->channel);
	MCDI_SET_DWORD(inbuf, PTP_IN_ENABLE_MODE, efx->ptp_data->mode);

	return efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
			    NULL, 0, NULL);
}

/* Disable MCDI PTP support.
 *
 * Note that this function should never rely on the presence of ptp_data -
 * may be called before that exists.
 */
static int efx_ptp_disable(struct efx_nic *efx)
{
	MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_DISABLE_LEN);

	MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_DISABLE);
	MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);
	return efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
			    NULL, 0, NULL);
}

static void efx_ptp_deliver_rx_queue(struct sk_buff_head *q)
{
	struct sk_buff *skb;

	while ((skb = skb_dequeue(q))) {
		local_bh_disable();
		netif_receive_skb(skb);
		local_bh_enable();
	}
}

static void efx_ptp_handle_no_channel(struct efx_nic *efx)
{
	netif_err(efx, drv, efx->net_dev,
		  "ERROR: PTP requires MSI-X and 1 additional interrupt"
		  "vector. PTP disabled\n");
}

/* Repeatedly send the host time to the MC which will capture the hardware
 * time.
 */
static void efx_ptp_send_times(struct efx_nic *efx,
			       struct pps_event_time *last_time)
{
	struct pps_event_time now;
	struct timespec limit;
	struct efx_ptp_data *ptp = efx->ptp_data;
	struct timespec start;
	int *mc_running = ptp->start.addr;

	pps_get_ts(&now);
	start = now.ts_real;
	limit = now.ts_real;
	timespec_add_ns(&limit, SYNCHRONISE_PERIOD_NS);

	/* Write host time for specified period or until MC is done */
	while ((timespec_compare(&now.ts_real, &limit) < 0) &&
	       ACCESS_ONCE(*mc_running)) {
		struct timespec update_time;
		unsigned int host_time;

		/* Don't update continuously to avoid saturating the PCIe bus */
		update_time = now.ts_real;
		timespec_add_ns(&update_time, SYNCHRONISATION_GRANULARITY_NS);
		do {
			pps_get_ts(&now);
		} while ((timespec_compare(&now.ts_real, &update_time) < 0) &&
			 ACCESS_ONCE(*mc_running));

		/* Synchronise NIC with single word of time only */
		host_time = (now.ts_real.tv_sec << MC_NANOSECOND_BITS |
			     now.ts_real.tv_nsec);
		/* Update host time in NIC memory */
		efx->type->ptp_write_host_time(efx, host_time);
	}
	*last_time = now;
}

/* Read a timeset from the MC's results and partial process. */
static void efx_ptp_read_timeset(MCDI_DECLARE_STRUCT_PTR(data),
				 struct efx_ptp_timeset *timeset)
{
	unsigned start_ns, end_ns;

	timeset->host_start = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_HOSTSTART);
	timeset->seconds = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_SECONDS);
	timeset->nanoseconds = MCDI_DWORD(data,
					 PTP_OUT_SYNCHRONIZE_NANOSECONDS);
	timeset->host_end = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_HOSTEND),
	timeset->waitns = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_WAITNS);

	/* Ignore seconds */
	start_ns = timeset->host_start & MC_NANOSECOND_MASK;
	end_ns = timeset->host_end & MC_NANOSECOND_MASK;
	/* Allow for rollover */
	if (end_ns < start_ns)
		end_ns += NSEC_PER_SEC;
	/* Determine duration of operation */
	timeset->window = end_ns - start_ns;
}

/* Process times received from MC.
 *
 * Extract times from returned results, and establish the minimum value
 * seen.  The minimum value represents the "best" possible time and events
 * too much greater than this are rejected - the machine is, perhaps, too
 * busy. A number of readings are taken so that, hopefully, at least one good
 * synchronisation will be seen in the results.
 */
static int
efx_ptp_process_times(struct efx_nic *efx, MCDI_DECLARE_STRUCT_PTR(synch_buf),
		      size_t response_length,
		      const struct pps_event_time *last_time)
{
	unsigned number_readings =
		MCDI_VAR_ARRAY_LEN(response_length,
				   PTP_OUT_SYNCHRONIZE_TIMESET);
	unsigned i;
	unsigned total;
	unsigned ngood = 0;
	unsigned last_good = 0;
	struct efx_ptp_data *ptp = efx->ptp_data;
	u32 last_sec;
	u32 start_sec;
	struct timespec delta;

	if (number_readings == 0)
		return -EAGAIN;

	/* Read the set of results and increment stats for any results that
	 * appera to be erroneous.
	 */
	for (i = 0; i < number_readings; i++) {
		efx_ptp_read_timeset(
			MCDI_ARRAY_STRUCT_PTR(synch_buf,
					      PTP_OUT_SYNCHRONIZE_TIMESET, i),
			&ptp->timeset[i]);
	}

	/* Find the last good host-MC synchronization result. The MC times
	 * when it finishes reading the host time so the corrected window time
	 * should be fairly constant for a given platform.
	 */
	total = 0;
	for (i = 0; i < number_readings; i++)
		if (ptp->timeset[i].window > ptp->timeset[i].waitns) {
			unsigned win;

			win = ptp->timeset[i].window - ptp->timeset[i].waitns;
			if (win >= MIN_SYNCHRONISATION_NS &&
			    win < MAX_SYNCHRONISATION_NS) {
				total += ptp->timeset[i].window;
				ngood++;
				last_good = i;
			}
		}

	if (ngood == 0) {
		netif_warn(efx, drv, efx->net_dev,
			   "PTP no suitable synchronisations %dns\n",
			   ptp->base_sync_ns);
		return -EAGAIN;
	}

	/* Average minimum this synchronisation */
	ptp->last_sync_ns = DIV_ROUND_UP(total, ngood);
	if (!ptp->base_sync_valid || (ptp->last_sync_ns < ptp->base_sync_ns)) {
		ptp->base_sync_valid = true;
		ptp->base_sync_ns = ptp->last_sync_ns;
	}

	/* Calculate delay from actual PPS to last_time */
	delta.tv_nsec =
		ptp->timeset[last_good].nanoseconds +
		last_time->ts_real.tv_nsec -
		(ptp->timeset[last_good].host_start & MC_NANOSECOND_MASK);

	/* It is possible that the seconds rolled over between taking
	 * the start reading and the last value written by the host.  The
	 * timescales are such that a gap of more than one second is never
	 * expected.
	 */
	start_sec = ptp->timeset[last_good].host_start >> MC_NANOSECOND_BITS;
	last_sec = last_time->ts_real.tv_sec & MC_SECOND_MASK;
	if (start_sec != last_sec) {
		if (((start_sec + 1) & MC_SECOND_MASK) != last_sec) {
			netif_warn(efx, hw, efx->net_dev,
				   "PTP bad synchronisation seconds\n");
			return -EAGAIN;
		} else {
			delta.tv_sec = 1;
		}
	} else {
		delta.tv_sec = 0;
	}

	ptp->host_time_pps = *last_time;
	pps_sub_ts(&ptp->host_time_pps, delta);

	return 0;
}

/* Synchronize times between the host and the MC */
static int efx_ptp_synchronize(struct efx_nic *efx, unsigned int num_readings)
{
	struct efx_ptp_data *ptp = efx->ptp_data;
	MCDI_DECLARE_BUF(synch_buf, MC_CMD_PTP_OUT_SYNCHRONIZE_LENMAX);
	size_t response_length;
	int rc;
	unsigned long timeout;
	struct pps_event_time last_time = {};
	unsigned int loops = 0;
	int *start = ptp->start.addr;

	MCDI_SET_DWORD(synch_buf, PTP_IN_OP, MC_CMD_PTP_OP_SYNCHRONIZE);
	MCDI_SET_DWORD(synch_buf, PTP_IN_PERIPH_ID, 0);
	MCDI_SET_DWORD(synch_buf, PTP_IN_SYNCHRONIZE_NUMTIMESETS,
		       num_readings);
	MCDI_SET_QWORD(synch_buf, PTP_IN_SYNCHRONIZE_START_ADDR,
		       ptp->start.dma_addr);

	/* Clear flag that signals MC ready */
	ACCESS_ONCE(*start) = 0;
	rc = efx_mcdi_rpc_start(efx, MC_CMD_PTP, synch_buf,
				MC_CMD_PTP_IN_SYNCHRONIZE_LEN);
	EFX_BUG_ON_PARANOID(rc);

	/* Wait for start from MCDI (or timeout) */
	timeout = jiffies + msecs_to_jiffies(MAX_SYNCHRONISE_WAIT_MS);
	while (!ACCESS_ONCE(*start) && (time_before(jiffies, timeout))) {
		udelay(20);	/* Usually start MCDI execution quickly */
		loops++;
	}

	if (ACCESS_ONCE(*start))
		efx_ptp_send_times(efx, &last_time);

	/* Collect results */
	rc = efx_mcdi_rpc_finish(efx, MC_CMD_PTP,
				 MC_CMD_PTP_IN_SYNCHRONIZE_LEN,
				 synch_buf, sizeof(synch_buf),
				 &response_length);
	if (rc == 0)
		rc = efx_ptp_process_times(efx, synch_buf, response_length,
					   &last_time);

	return rc;
}

/* Transmit a PTP packet, via the MCDI interface, to the wire. */
static int efx_ptp_xmit_skb(struct efx_nic *efx, struct sk_buff *skb)
{
	struct efx_ptp_data *ptp_data = efx->ptp_data;
	struct skb_shared_hwtstamps timestamps;
	int rc = -EIO;
	MCDI_DECLARE_BUF(txtime, MC_CMD_PTP_OUT_TRANSMIT_LEN);
	size_t len;

	MCDI_SET_DWORD(ptp_data->txbuf, PTP_IN_OP, MC_CMD_PTP_OP_TRANSMIT);
	MCDI_SET_DWORD(ptp_data->txbuf, PTP_IN_PERIPH_ID, 0);
	MCDI_SET_DWORD(ptp_data->txbuf, PTP_IN_TRANSMIT_LENGTH, skb->len);
	if (skb_shinfo(skb)->nr_frags != 0) {
		rc = skb_linearize(skb);
		if (rc != 0)
			goto fail;
	}

	if (skb->ip_summed == CHECKSUM_PARTIAL) {
		rc = skb_checksum_help(skb);
		if (rc != 0)
			goto fail;
	}
	skb_copy_from_linear_data(skb,
				  MCDI_PTR(ptp_data->txbuf,
					   PTP_IN_TRANSMIT_PACKET),
				  skb->len);
	rc = efx_mcdi_rpc(efx, MC_CMD_PTP,
			  ptp_data->txbuf, MC_CMD_PTP_IN_TRANSMIT_LEN(skb->len),
			  txtime, sizeof(txtime), &len);
	if (rc != 0)
		goto fail;

	memset(&timestamps, 0, sizeof(timestamps));
	timestamps.hwtstamp = ktime_set(
		MCDI_DWORD(txtime, PTP_OUT_TRANSMIT_SECONDS),
		MCDI_DWORD(txtime, PTP_OUT_TRANSMIT_NANOSECONDS));

	skb_tstamp_tx(skb, &timestamps);

	rc = 0;

fail:
	dev_kfree_skb(skb);

	return rc;
}

static void efx_ptp_drop_time_expired_events(struct efx_nic *efx)
{
	struct efx_ptp_data *ptp = efx->ptp_data;
	struct list_head *cursor;
	struct list_head *next;

	/* Drop time-expired events */
	spin_lock_bh(&ptp->evt_lock);
	if (!list_empty(&ptp->evt_list)) {
		list_for_each_safe(cursor, next, &ptp->evt_list) {
			struct efx_ptp_event_rx *evt;

			evt = list_entry(cursor, struct efx_ptp_event_rx,
					 link);
			if (time_after(jiffies, evt->expiry)) {
				list_move(&evt->link, &ptp->evt_free_list);
				netif_warn(efx, hw, efx->net_dev,
					   "PTP rx event dropped\n");
			}
		}
	}
	/* If the event overflow flag is set and the event list is now empty
	 * clear the flag to re-enable the overflow warning message.
	 */
	if (ptp->evt_overflow && list_empty(&ptp->evt_list))
		ptp->evt_overflow = false;
	spin_unlock_bh(&ptp->evt_lock);
}

static enum ptp_packet_state efx_ptp_match_rx(struct efx_nic *efx,
					      struct sk_buff *skb)
{
	struct efx_ptp_data *ptp = efx->ptp_data;
	bool evts_waiting;
	struct list_head *cursor;
	struct list_head *next;
	struct efx_ptp_match *match;
	enum ptp_packet_state rc = PTP_PACKET_STATE_UNMATCHED;

	spin_lock_bh(&ptp->evt_lock);
	evts_waiting = !list_empty(&ptp->evt_list);
	spin_unlock_bh(&ptp->evt_lock);

	if (!evts_waiting)
		return PTP_PACKET_STATE_UNMATCHED;

	match = (struct efx_ptp_match *)skb->cb;
	/* Look for a matching timestamp in the event queue */
	spin_lock_bh(&ptp->evt_lock);
	list_for_each_safe(cursor, next, &ptp->evt_list) {
		struct efx_ptp_event_rx *evt;

		evt = list_entry(cursor, struct efx_ptp_event_rx, link);
		if ((evt->seq0 == match->words[0]) &&
		    (evt->seq1 == match->words[1])) {
			struct skb_shared_hwtstamps *timestamps;

			/* Match - add in hardware timestamp */
			timestamps = skb_hwtstamps(skb);
			timestamps->hwtstamp = evt->hwtimestamp;

			match->state = PTP_PACKET_STATE_MATCHED;
			rc = PTP_PACKET_STATE_MATCHED;
			list_move(&evt->link, &ptp->evt_free_list);
			break;
		}
	}
	/* If the event overflow flag is set and the event list is now empty
	 * clear the flag to re-enable the overflow warning message.
	 */
	if (ptp->evt_overflow && list_empty(&ptp->evt_list))
		ptp->evt_overflow = false;
	spin_unlock_bh(&ptp->evt_lock);

	return rc;
}

/* Process any queued receive events and corresponding packets
 *
 * q is returned with all the packets that are ready for delivery.
 * true is returned if at least one of those packets requires
 * synchronisation.
 */
static bool efx_ptp_process_events(struct efx_nic *efx, struct sk_buff_head *q)
{
	struct efx_ptp_data *ptp = efx->ptp_data;
	bool rc = false;
	struct sk_buff *skb;

	while ((skb = skb_dequeue(&ptp->rxq))) {
		struct efx_ptp_match *match;

		match = (struct efx_ptp_match *)skb->cb;
		if (match->state == PTP_PACKET_STATE_MATCH_UNWANTED) {
			__skb_queue_tail(q, skb);
		} else if (efx_ptp_match_rx(efx, skb) ==
			   PTP_PACKET_STATE_MATCHED) {
			rc = true;
			__skb_queue_tail(q, skb);
		} else if (time_after(jiffies, match->expiry)) {
			match->state = PTP_PACKET_STATE_TIMED_OUT;
			if (net_ratelimit())
				netif_warn(efx, rx_err, efx->net_dev,
					   "PTP packet - no timestamp seen\n");
			__skb_queue_tail(q, skb);
		} else {
			/* Replace unprocessed entry and stop */
			skb_queue_head(&ptp->rxq, skb);
			break;
		}
	}

	return rc;
}

/* Complete processing of a received packet */
static inline void efx_ptp_process_rx(struct efx_nic *efx, struct sk_buff *skb)
{
	local_bh_disable();
	netif_receive_skb(skb);
	local_bh_enable();
}

static int efx_ptp_start(struct efx_nic *efx)
{
	struct efx_ptp_data *ptp = efx->ptp_data;
	struct efx_filter_spec rxfilter;
	int rc;

	ptp->reset_required = false;

	/* Must filter on both event and general ports to ensure
	 * that there is no packet re-ordering.
	 */
	efx_filter_init_rx(&rxfilter, EFX_FILTER_PRI_REQUIRED, 0,
			   efx_rx_queue_index(
				   efx_channel_get_rx_queue(ptp->channel)));
	rc = efx_filter_set_ipv4_local(&rxfilter, IPPROTO_UDP,
				       htonl(PTP_ADDRESS),
				       htons(PTP_EVENT_PORT));
	if (rc != 0)
		return rc;

	rc = efx_filter_insert_filter(efx, &rxfilter, true);
	if (rc < 0)
		return rc;
	ptp->rxfilter_event = rc;

	efx_filter_init_rx(&rxfilter, EFX_FILTER_PRI_REQUIRED, 0,
			   efx_rx_queue_index(
				   efx_channel_get_rx_queue(ptp->channel)));
	rc = efx_filter_set_ipv4_local(&rxfilter, IPPROTO_UDP,
				       htonl(PTP_ADDRESS),
				       htons(PTP_GENERAL_PORT));
	if (rc != 0)
		goto fail;

	rc = efx_filter_insert_filter(efx, &rxfilter, true);
	if (rc < 0)
		goto fail;
	ptp->rxfilter_general = rc;

	rc = efx_ptp_enable(efx);
	if (rc != 0)
		goto fail2;

	ptp->evt_frag_idx = 0;
	ptp->current_adjfreq = 0;
	ptp->rxfilter_installed = true;

	return 0;

fail2:
	efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED,
				  ptp->rxfilter_general);
fail:
	efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED,
				  ptp->rxfilter_event);

	return rc;
}

static int efx_ptp_stop(struct efx_nic *efx)
{
	struct efx_ptp_data *ptp = efx->ptp_data;
	struct list_head *cursor;
	struct list_head *next;
	int rc;

	if (ptp == NULL)
		return 0;

	rc = efx_ptp_disable(efx);

	if (ptp->rxfilter_installed) {
		efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED,
					  ptp->rxfilter_general);
		efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED,
					  ptp->rxfilter_event);
		ptp->rxfilter_installed = false;
	}

	/* Make sure RX packets are really delivered */
	efx_ptp_deliver_rx_queue(&efx->ptp_data->rxq);
	skb_queue_purge(&efx->ptp_data->txq);

	/* Drop any pending receive events */
	spin_lock_bh(&efx->ptp_data->evt_lock);
	list_for_each_safe(cursor, next, &efx->ptp_data->evt_list) {
		list_move(cursor, &efx->ptp_data->evt_free_list);
	}
	ptp->evt_overflow = false;
	spin_unlock_bh(&efx->ptp_data->evt_lock);

	return rc;
}

static int efx_ptp_restart(struct efx_nic *efx)
{
	if (efx->ptp_data && efx->ptp_data->enabled)
		return efx_ptp_start(efx);
	return 0;
}

static void efx_ptp_pps_worker(struct work_struct *work)
{
	struct efx_ptp_data *ptp =
		container_of(work, struct efx_ptp_data, pps_work);
	struct efx_nic *efx = ptp->channel->efx;
	struct ptp_clock_event ptp_evt;

	if (efx_ptp_synchronize(efx, PTP_SYNC_ATTEMPTS))
		return;

	ptp_evt.type = PTP_CLOCK_PPSUSR;
	ptp_evt.pps_times = ptp->host_time_pps;
	ptp_clock_event(ptp->phc_clock, &ptp_evt);
}

/* Process any pending transmissions and timestamp any received packets.
 */
static void efx_ptp_worker(struct work_struct *work)
{
	struct efx_ptp_data *ptp_data =
		container_of(work, struct efx_ptp_data, work);
	struct efx_nic *efx = ptp_data->channel->efx;
	struct sk_buff *skb;
	struct sk_buff_head tempq;

	if (ptp_data->reset_required) {
		efx_ptp_stop(efx);
		efx_ptp_start(efx);
		return;
	}

	efx_ptp_drop_time_expired_events(efx);

	__skb_queue_head_init(&tempq);
	if (efx_ptp_process_events(efx, &tempq) ||
	    !skb_queue_empty(&ptp_data->txq)) {

		while ((skb = skb_dequeue(&ptp_data->txq)))
			efx_ptp_xmit_skb(efx, skb);
	}

	while ((skb = __skb_dequeue(&tempq)))
		efx_ptp_process_rx(efx, skb);
}

/* Initialise PTP channel and state.
 *
 * Setting core_index to zero causes the queue to be initialised and doesn't
 * overlap with 'rxq0' because ptp.c doesn't use skb_record_rx_queue.
 */
static int efx_ptp_probe_channel(struct efx_channel *channel)
{
	struct efx_nic *efx = channel->efx;
	struct efx_ptp_data *ptp;
	int rc = 0;
	unsigned int pos;

	channel->irq_moderation = 0;
	channel->rx_queue.core_index = 0;

	ptp = kzalloc(sizeof(struct efx_ptp_data), GFP_KERNEL);
	efx->ptp_data = ptp;
	if (!efx->ptp_data)
		return -ENOMEM;

	rc = efx_nic_alloc_buffer(efx, &ptp->start, sizeof(int), GFP_KERNEL);
	if (rc != 0)
		goto fail1;

	ptp->channel = channel;
	skb_queue_head_init(&ptp->rxq);
	skb_queue_head_init(&ptp->txq);
	ptp->workwq = create_singlethread_workqueue("sfc_ptp");
	if (!ptp->workwq) {
		rc = -ENOMEM;
		goto fail2;
	}

	INIT_WORK(&ptp->work, efx_ptp_worker);
	ptp->config.flags = 0;
	ptp->config.tx_type = HWTSTAMP_TX_OFF;
	ptp->config.rx_filter = HWTSTAMP_FILTER_NONE;
	INIT_LIST_HEAD(&ptp->evt_list);
	INIT_LIST_HEAD(&ptp->evt_free_list);
	spin_lock_init(&ptp->evt_lock);
	for (pos = 0; pos < MAX_RECEIVE_EVENTS; pos++)
		list_add(&ptp->rx_evts[pos].link, &ptp->evt_free_list);
	ptp->evt_overflow = false;

	ptp->phc_clock_info.owner = THIS_MODULE;
	snprintf(ptp->phc_clock_info.name,
		 sizeof(ptp->phc_clock_info.name),
		 "%pm", efx->net_dev->perm_addr);
	ptp->phc_clock_info.max_adj = MAX_PPB;
	ptp->phc_clock_info.n_alarm = 0;
	ptp->phc_clock_info.n_ext_ts = 0;
	ptp->phc_clock_info.n_per_out = 0;
	ptp->phc_clock_info.pps = 1;
	ptp->phc_clock_info.adjfreq = efx_phc_adjfreq;
	ptp->phc_clock_info.adjtime = efx_phc_adjtime;
	ptp->phc_clock_info.gettime = efx_phc_gettime;
	ptp->phc_clock_info.settime = efx_phc_settime;
	ptp->phc_clock_info.enable = efx_phc_enable;

	ptp->phc_clock = ptp_clock_register(&ptp->phc_clock_info,
					    &efx->pci_dev->dev);
	if (IS_ERR(ptp->phc_clock)) {
		rc = PTR_ERR(ptp->phc_clock);
		goto fail3;
	}

	INIT_WORK(&ptp->pps_work, efx_ptp_pps_worker);
	ptp->pps_workwq = create_singlethread_workqueue("sfc_pps");
	if (!ptp->pps_workwq) {
		rc = -ENOMEM;
		goto fail4;
	}
	ptp->nic_ts_enabled = false;

	return 0;
fail4:
	ptp_clock_unregister(efx->ptp_data->phc_clock);

fail3:
	destroy_workqueue(efx->ptp_data->workwq);

fail2:
	efx_nic_free_buffer(efx, &ptp->start);

fail1:
	kfree(efx->ptp_data);
	efx->ptp_data = NULL;

	return rc;
}

static void efx_ptp_remove_channel(struct efx_channel *channel)
{
	struct efx_nic *efx = channel->efx;

	if (!efx->ptp_data)
		return;

	(void)efx_ptp_disable(channel->efx);

	cancel_work_sync(&efx->ptp_data->work);
	cancel_work_sync(&efx->ptp_data->pps_work);

	skb_queue_purge(&efx->ptp_data->rxq);
	skb_queue_purge(&efx->ptp_data->txq);

	ptp_clock_unregister(efx->ptp_data->phc_clock);

	destroy_workqueue(efx->ptp_data->workwq);
	destroy_workqueue(efx->ptp_data->pps_workwq);

	efx_nic_free_buffer(efx, &efx->ptp_data->start);
	kfree(efx->ptp_data);
}

static void efx_ptp_get_channel_name(struct efx_channel *channel,
				     char *buf, size_t len)
{
	snprintf(buf, len, "%s-ptp", channel->efx->name);
}

/* Determine whether this packet should be processed by the PTP module
 * or transmitted conventionally.
 */
bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb)
{
	return efx->ptp_data &&
		efx->ptp_data->enabled &&
		skb->len >= PTP_MIN_LENGTH &&
		skb->len <= MC_CMD_PTP_IN_TRANSMIT_PACKET_MAXNUM &&
		likely(skb->protocol == htons(ETH_P_IP)) &&
		skb_transport_header_was_set(skb) &&
		skb_network_header_len(skb) >= sizeof(struct iphdr) &&
		ip_hdr(skb)->protocol == IPPROTO_UDP &&
		skb_headlen(skb) >=
		skb_transport_offset(skb) + sizeof(struct udphdr) &&
		udp_hdr(skb)->dest == htons(PTP_EVENT_PORT);
}

/* Receive a PTP packet.  Packets are queued until the arrival of
 * the receive timestamp from the MC - this will probably occur after the
 * packet arrival because of the processing in the MC.
 */
static bool efx_ptp_rx(struct efx_channel *channel, struct sk_buff *skb)
{
	struct efx_nic *efx = channel->efx;
	struct efx_ptp_data *ptp = efx->ptp_data;
	struct efx_ptp_match *match = (struct efx_ptp_match *)skb->cb;
	u8 *match_data_012, *match_data_345;
	unsigned int version;

	match->expiry = jiffies + msecs_to_jiffies(PKT_EVENT_LIFETIME_MS);

	/* Correct version? */
	if (ptp->mode == MC_CMD_PTP_MODE_V1) {
		if (!pskb_may_pull(skb, PTP_V1_MIN_LENGTH)) {
			return false;
		}
		version = ntohs(*(__be16 *)&skb->data[PTP_V1_VERSION_OFFSET]);
		if (version != PTP_VERSION_V1) {
			return false;
		}

		/* PTP V1 uses all six bytes of the UUID to match the packet
		 * to the timestamp
		 */
		match_data_012 = skb->data + PTP_V1_UUID_OFFSET;
		match_data_345 = skb->data + PTP_V1_UUID_OFFSET + 3;
	} else {
		if (!pskb_may_pull(skb, PTP_V2_MIN_LENGTH)) {
			return false;
		}
		version = skb->data[PTP_V2_VERSION_OFFSET];
		if ((version & PTP_VERSION_V2_MASK) != PTP_VERSION_V2) {
			return false;
		}

		/* The original V2 implementation uses bytes 2-7 of
		 * the UUID to match the packet to the timestamp. This
		 * discards two of the bytes of the MAC address used
		 * to create the UUID (SF bug 33070).  The PTP V2
		 * enhanced mode fixes this issue and uses bytes 0-2
		 * and byte 5-7 of the UUID.
		 */
		match_data_345 = skb->data + PTP_V2_UUID_OFFSET + 5;
		if (ptp->mode == MC_CMD_PTP_MODE_V2) {
			match_data_012 = skb->data + PTP_V2_UUID_OFFSET + 2;
		} else {
			match_data_012 = skb->data + PTP_V2_UUID_OFFSET + 0;
			BUG_ON(ptp->mode != MC_CMD_PTP_MODE_V2_ENHANCED);
		}
	}

	/* Does this packet require timestamping? */
	if (ntohs(*(__be16 *)&skb->data[PTP_DPORT_OFFSET]) == PTP_EVENT_PORT) {
		struct skb_shared_hwtstamps *timestamps;

		match->state = PTP_PACKET_STATE_UNMATCHED;

		/* Clear all timestamps held: filled in later */
		timestamps = skb_hwtstamps(skb);
		memset(timestamps, 0, sizeof(*timestamps));

		/* We expect the sequence number to be in the same position in
		 * the packet for PTP V1 and V2
		 */
		BUILD_BUG_ON(PTP_V1_SEQUENCE_OFFSET != PTP_V2_SEQUENCE_OFFSET);
		BUILD_BUG_ON(PTP_V1_SEQUENCE_LENGTH != PTP_V2_SEQUENCE_LENGTH);

		/* Extract UUID/Sequence information */
		match->words[0] = (match_data_012[0]         |
				   (match_data_012[1] << 8)  |
				   (match_data_012[2] << 16) |
				   (match_data_345[0] << 24));
		match->words[1] = (match_data_345[1]         |
				   (match_data_345[2] << 8)  |
				   (skb->data[PTP_V1_SEQUENCE_OFFSET +
					      PTP_V1_SEQUENCE_LENGTH - 1] <<
				    16));
	} else {
		match->state = PTP_PACKET_STATE_MATCH_UNWANTED;
	}

	skb_queue_tail(&ptp->rxq, skb);
	queue_work(ptp->workwq, &ptp->work);

	return true;
}

/* Transmit a PTP packet.  This has to be transmitted by the MC
 * itself, through an MCDI call.  MCDI calls aren't permitted
 * in the transmit path so defer the actual transmission to a suitable worker.
 */
int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb)
{
	struct efx_ptp_data *ptp = efx->ptp_data;

	skb_queue_tail(&ptp->txq, skb);

	if ((udp_hdr(skb)->dest == htons(PTP_EVENT_PORT)) &&
	    (skb->len <= MC_CMD_PTP_IN_TRANSMIT_PACKET_MAXNUM))
		efx_xmit_hwtstamp_pending(skb);
	queue_work(ptp->workwq, &ptp->work);

	return NETDEV_TX_OK;
}

static int efx_ptp_change_mode(struct efx_nic *efx, bool enable_wanted,
			       unsigned int new_mode)
{
	if ((enable_wanted != efx->ptp_data->enabled) ||
	    (enable_wanted && (efx->ptp_data->mode != new_mode))) {
		int rc = 0;

		if (enable_wanted) {
			/* Change of mode requires disable */
			if (efx->ptp_data->enabled &&
			    (efx->ptp_data->mode != new_mode)) {
				efx->ptp_data->enabled = false;
				rc = efx_ptp_stop(efx);
				if (rc != 0)
					return rc;
			}

			/* Set new operating mode and establish
			 * baseline synchronisation, which must
			 * succeed.
			 */
			efx->ptp_data->mode = new_mode;
			if (netif_running(efx->net_dev))
				rc = efx_ptp_start(efx);
			if (rc == 0) {
				rc = efx_ptp_synchronize(efx,
							 PTP_SYNC_ATTEMPTS * 2);
				if (rc != 0)
					efx_ptp_stop(efx);
			}
		} else {
			rc = efx_ptp_stop(efx);
		}

		if (rc != 0)
			return rc;

		efx->ptp_data->enabled = enable_wanted;
	}

	return 0;
}

static int efx_ptp_ts_init(struct efx_nic *efx, struct hwtstamp_config *init)
{
	bool enable_wanted = false;
	unsigned int new_mode;
	int rc;

	if (init->flags)
		return -EINVAL;

	if ((init->tx_type != HWTSTAMP_TX_OFF) &&
	    (init->tx_type != HWTSTAMP_TX_ON))
		return -ERANGE;

	new_mode = efx->ptp_data->mode;
	/* Determine whether any PTP HW operations are required */
	switch (init->rx_filter) {
	case HWTSTAMP_FILTER_NONE:
		break;
	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
		init->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
		new_mode = MC_CMD_PTP_MODE_V1;
		enable_wanted = true;
		break;
	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
	/* Although these three are accepted only IPV4 packets will be
	 * timestamped
	 */
		init->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
		new_mode = MC_CMD_PTP_MODE_V2_ENHANCED;
		enable_wanted = true;
		break;
	case HWTSTAMP_FILTER_PTP_V2_EVENT:
	case HWTSTAMP_FILTER_PTP_V2_SYNC:
	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
		/* Non-IP + IPv6 timestamping not supported */
		return -ERANGE;
		break;
	default:
		return -ERANGE;
	}

	if (init->tx_type != HWTSTAMP_TX_OFF)
		enable_wanted = true;

	/* Old versions of the firmware do not support the improved
	 * UUID filtering option (SF bug 33070).  If the firmware does
	 * not accept the enhanced mode, fall back to the standard PTP
	 * v2 UUID filtering.
	 */
	rc = efx_ptp_change_mode(efx, enable_wanted, new_mode);
	if ((rc != 0) && (new_mode == MC_CMD_PTP_MODE_V2_ENHANCED))
		rc = efx_ptp_change_mode(efx, enable_wanted, MC_CMD_PTP_MODE_V2);
	if (rc != 0)
		return rc;

	efx->ptp_data->config = *init;

	return 0;
}

void efx_ptp_get_ts_info(struct efx_nic *efx, struct ethtool_ts_info *ts_info)
{
	struct efx_ptp_data *ptp = efx->ptp_data;

	if (!ptp)
		return;

	ts_info->so_timestamping |= (SOF_TIMESTAMPING_TX_HARDWARE |
				     SOF_TIMESTAMPING_RX_HARDWARE |
				     SOF_TIMESTAMPING_RAW_HARDWARE);
	ts_info->phc_index = ptp_clock_index(ptp->phc_clock);
	ts_info->tx_types = 1 << HWTSTAMP_TX_OFF | 1 << HWTSTAMP_TX_ON;
	ts_info->rx_filters = (1 << HWTSTAMP_FILTER_NONE |
			       1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT |
			       1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC |
			       1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ |
			       1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT |
			       1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC |
			       1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ);
}

int efx_ptp_ioctl(struct efx_nic *efx, struct ifreq *ifr, int cmd)
{
	struct hwtstamp_config config;
	int rc;

	/* Not a PTP enabled port */
	if (!efx->ptp_data)
		return -EOPNOTSUPP;

	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
		return -EFAULT;

	rc = efx_ptp_ts_init(efx, &config);
	if (rc != 0)
		return rc;

	return copy_to_user(ifr->ifr_data, &config, sizeof(config))
		? -EFAULT : 0;
}

static void ptp_event_failure(struct efx_nic *efx, int expected_frag_len)
{
	struct efx_ptp_data *ptp = efx->ptp_data;

	netif_err(efx, hw, efx->net_dev,
		"PTP unexpected event length: got %d expected %d\n",
		ptp->evt_frag_idx, expected_frag_len);
	ptp->reset_required = true;
	queue_work(ptp->workwq, &ptp->work);
}

/* Process a completed receive event.  Put it on the event queue and
 * start worker thread.  This is required because event and their
 * correspoding packets may come in either order.
 */
static void ptp_event_rx(struct efx_nic *efx, struct efx_ptp_data *ptp)
{
	struct efx_ptp_event_rx *evt = NULL;

	if (ptp->evt_frag_idx != 3) {
		ptp_event_failure(efx, 3);
		return;
	}

	spin_lock_bh(&ptp->evt_lock);
	if (!list_empty(&ptp->evt_free_list)) {
		evt = list_first_entry(&ptp->evt_free_list,
				       struct efx_ptp_event_rx, link);
		list_del(&evt->link);

		evt->seq0 = EFX_QWORD_FIELD(ptp->evt_frags[2], MCDI_EVENT_DATA);
		evt->seq1 = (EFX_QWORD_FIELD(ptp->evt_frags[2],
					     MCDI_EVENT_SRC)        |
			     (EFX_QWORD_FIELD(ptp->evt_frags[1],
					      MCDI_EVENT_SRC) << 8) |
			     (EFX_QWORD_FIELD(ptp->evt_frags[0],
					      MCDI_EVENT_SRC) << 16));
		evt->hwtimestamp = ktime_set(
			EFX_QWORD_FIELD(ptp->evt_frags[0], MCDI_EVENT_DATA),
			EFX_QWORD_FIELD(ptp->evt_frags[1], MCDI_EVENT_DATA));
		evt->expiry = jiffies + msecs_to_jiffies(PKT_EVENT_LIFETIME_MS);
		list_add_tail(&evt->link, &ptp->evt_list);

		queue_work(ptp->workwq, &ptp->work);
	} else if (!ptp->evt_overflow) {
		/* Log a warning message and set the event overflow flag.
		 * The message won't be logged again until the event queue
		 * becomes empty.
		 */
		netif_err(efx, rx_err, efx->net_dev, "PTP event queue overflow\n");
		ptp->evt_overflow = true;
	}
	spin_unlock_bh(&ptp->evt_lock);
}

static void ptp_event_fault(struct efx_nic *efx, struct efx_ptp_data *ptp)
{
	int code = EFX_QWORD_FIELD(ptp->evt_frags[0], MCDI_EVENT_DATA);
	if (ptp->evt_frag_idx != 1) {
		ptp_event_failure(efx, 1);
		return;
	}

	netif_err(efx, hw, efx->net_dev, "PTP error %d\n", code);
}

static void ptp_event_pps(struct efx_nic *efx, struct efx_ptp_data *ptp)
{
	if (ptp->nic_ts_enabled)
		queue_work(ptp->pps_workwq, &ptp->pps_work);
}

void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev)
{
	struct efx_ptp_data *ptp = efx->ptp_data;
	int code = EFX_QWORD_FIELD(*ev, MCDI_EVENT_CODE);

	if (!ptp->enabled)
		return;

	if (ptp->evt_frag_idx == 0) {
		ptp->evt_code = code;
	} else if (ptp->evt_code != code) {
		netif_err(efx, hw, efx->net_dev,
			  "PTP out of sequence event %d\n", code);
		ptp->evt_frag_idx = 0;
	}

	ptp->evt_frags[ptp->evt_frag_idx++] = *ev;
	if (!MCDI_EVENT_FIELD(*ev, CONT)) {
		/* Process resulting event */
		switch (code) {
		case MCDI_EVENT_CODE_PTP_RX:
			ptp_event_rx(efx, ptp);
			break;
		case MCDI_EVENT_CODE_PTP_FAULT:
			ptp_event_fault(efx, ptp);
			break;
		case MCDI_EVENT_CODE_PTP_PPS:
			ptp_event_pps(efx, ptp);
			break;
		default:
			netif_err(efx, hw, efx->net_dev,
				  "PTP unknown event %d\n", code);
			break;
		}
		ptp->evt_frag_idx = 0;
	} else if (MAX_EVENT_FRAGS == ptp->evt_frag_idx) {
		netif_err(efx, hw, efx->net_dev,
			  "PTP too many event fragments\n");
		ptp->evt_frag_idx = 0;
	}
}

static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta)
{
	struct efx_ptp_data *ptp_data = container_of(ptp,
						     struct efx_ptp_data,
						     phc_clock_info);
	struct efx_nic *efx = ptp_data->channel->efx;
	MCDI_DECLARE_BUF(inadj, MC_CMD_PTP_IN_ADJUST_LEN);
	s64 adjustment_ns;
	int rc;

	if (delta > MAX_PPB)
		delta = MAX_PPB;
	else if (delta < -MAX_PPB)
		delta = -MAX_PPB;

	/* Convert ppb to fixed point ns. */
	adjustment_ns = (((s64)delta * PPB_SCALE_WORD) >>
			 (PPB_EXTRA_BITS + MAX_PPB_BITS));

	MCDI_SET_DWORD(inadj, PTP_IN_OP, MC_CMD_PTP_OP_ADJUST);
	MCDI_SET_DWORD(inadj, PTP_IN_PERIPH_ID, 0);
	MCDI_SET_QWORD(inadj, PTP_IN_ADJUST_FREQ, adjustment_ns);
	MCDI_SET_DWORD(inadj, PTP_IN_ADJUST_SECONDS, 0);
	MCDI_SET_DWORD(inadj, PTP_IN_ADJUST_NANOSECONDS, 0);
	rc = efx_mcdi_rpc(efx, MC_CMD_PTP, inadj, sizeof(inadj),
			  NULL, 0, NULL);
	if (rc != 0)
		return rc;

	ptp_data->current_adjfreq = adjustment_ns;
	return 0;
}

static int efx_phc_adjtime(struct ptp_clock_info *ptp, s64 delta)
{
	struct efx_ptp_data *ptp_data = container_of(ptp,
						     struct efx_ptp_data,
						     phc_clock_info);
	struct efx_nic *efx = ptp_data->channel->efx;
	struct timespec delta_ts = ns_to_timespec(delta);
	MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_ADJUST_LEN);

	MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_ADJUST);
	MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);
	MCDI_SET_QWORD(inbuf, PTP_IN_ADJUST_FREQ, ptp_data->current_adjfreq);
	MCDI_SET_DWORD(inbuf, PTP_IN_ADJUST_SECONDS, (u32)delta_ts.tv_sec);
	MCDI_SET_DWORD(inbuf, PTP_IN_ADJUST_NANOSECONDS, (u32)delta_ts.tv_nsec);
	return efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
			    NULL, 0, NULL);
}

static int efx_phc_gettime(struct ptp_clock_info *ptp, struct timespec *ts)
{
	struct efx_ptp_data *ptp_data = container_of(ptp,
						     struct efx_ptp_data,
						     phc_clock_info);
	struct efx_nic *efx = ptp_data->channel->efx;
	MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_READ_NIC_TIME_LEN);
	MCDI_DECLARE_BUF(outbuf, MC_CMD_PTP_OUT_READ_NIC_TIME_LEN);
	int rc;

	MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_READ_NIC_TIME);
	MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);

	rc = efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
			  outbuf, sizeof(outbuf), NULL);
	if (rc != 0)
		return rc;

	ts->tv_sec = MCDI_DWORD(outbuf, PTP_OUT_READ_NIC_TIME_SECONDS);
	ts->tv_nsec = MCDI_DWORD(outbuf, PTP_OUT_READ_NIC_TIME_NANOSECONDS);
	return 0;
}

static int efx_phc_settime(struct ptp_clock_info *ptp,
			   const struct timespec *e_ts)
{
	/* Get the current NIC time, efx_phc_gettime.
	 * Subtract from the desired time to get the offset
	 * call efx_phc_adjtime with the offset
	 */
	int rc;
	struct timespec time_now;
	struct timespec delta;

	rc = efx_phc_gettime(ptp, &time_now);
	if (rc != 0)
		return rc;

	delta = timespec_sub(*e_ts, time_now);

	rc = efx_phc_adjtime(ptp, timespec_to_ns(&delta));
	if (rc != 0)
		return rc;

	return 0;
}

static int efx_phc_enable(struct ptp_clock_info *ptp,
			  struct ptp_clock_request *request,
			  int enable)
{
	struct efx_ptp_data *ptp_data = container_of(ptp,
						     struct efx_ptp_data,
						     phc_clock_info);
	if (request->type != PTP_CLK_REQ_PPS)
		return -EOPNOTSUPP;

	ptp_data->nic_ts_enabled = !!enable;
	return 0;
}

static const struct efx_channel_type efx_ptp_channel_type = {
	.handle_no_channel	= efx_ptp_handle_no_channel,
	.pre_probe		= efx_ptp_probe_channel,
	.post_remove		= efx_ptp_remove_channel,
	.get_name		= efx_ptp_get_channel_name,
	/* no copy operation; there is no need to reallocate this channel */
	.receive_skb		= efx_ptp_rx,
	.keep_eventq		= false,
};

void efx_ptp_probe(struct efx_nic *efx)
{
	/* Check whether PTP is implemented on this NIC.  The DISABLE
	 * operation will succeed if and only if it is implemented.
	 */
	if (efx_ptp_disable(efx) == 0)
		efx->extra_channel_type[EFX_EXTRA_CHANNEL_PTP] =
			&efx_ptp_channel_type;
}

void efx_ptp_start_datapath(struct efx_nic *efx)
{
	if (efx_ptp_restart(efx))
		netif_err(efx, drv, efx->net_dev, "Failed to restart PTP.\n");
}

void efx_ptp_stop_datapath(struct efx_nic *efx)
{
	efx_ptp_stop(efx);
}