aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/net/ethernet/mellanox/mlxsw/core_env.c
blob: 6dd4ae2f45f41eb30022046507873f7eb6f73290 (plain) (blame)
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
// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */

#include <linux/kernel.h>
#include <linux/err.h>
#include <linux/ethtool.h>
#include <linux/sfp.h>
#include <linux/mutex.h>

#include "core.h"
#include "core_env.h"
#include "item.h"
#include "reg.h"

struct mlxsw_env_module_info {
	u64 module_overheat_counter;
	bool is_overheat;
	int num_ports_mapped;
	int num_ports_up;
	enum ethtool_module_power_mode_policy power_mode_policy;
};

struct mlxsw_env {
	struct mlxsw_core *core;
	u8 module_count;
	struct mutex module_info_lock; /* Protects 'module_info'. */
	struct mlxsw_env_module_info module_info[];
};

static int mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id,
					  bool *qsfp, bool *cmis)
{
	char mcia_pl[MLXSW_REG_MCIA_LEN];
	char *eeprom_tmp;
	u8 ident;
	int err;

	mlxsw_reg_mcia_pack(mcia_pl, id, 0, MLXSW_REG_MCIA_PAGE0_LO_OFF, 0, 1,
			    MLXSW_REG_MCIA_I2C_ADDR_LOW);
	err = mlxsw_reg_query(core, MLXSW_REG(mcia), mcia_pl);
	if (err)
		return err;
	eeprom_tmp = mlxsw_reg_mcia_eeprom_data(mcia_pl);
	ident = eeprom_tmp[0];
	*cmis = false;
	switch (ident) {
	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_SFP:
		*qsfp = false;
		break;
	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP:
	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS:
	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28:
		*qsfp = true;
		break;
	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_DD:
		*qsfp = true;
		*cmis = true;
		break;
	default:
		return -EINVAL;
	}

	return 0;
}

static int
mlxsw_env_query_module_eeprom(struct mlxsw_core *mlxsw_core, int module,
			      u16 offset, u16 size, void *data,
			      bool qsfp, unsigned int *p_read_size)
{
	char mcia_pl[MLXSW_REG_MCIA_LEN];
	char *eeprom_tmp;
	u16 i2c_addr;
	u8 page = 0;
	int status;
	int err;

	/* MCIA register accepts buffer size <= 48. Page of size 128 should be
	 * read by chunks of size 48, 48, 32. Align the size of the last chunk
	 * to avoid reading after the end of the page.
	 */
	size = min_t(u16, size, MLXSW_REG_MCIA_EEPROM_SIZE);

	if (offset < MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH &&
	    offset + size > MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH)
		/* Cross pages read, read until offset 256 in low page */
		size = MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH - offset;

	i2c_addr = MLXSW_REG_MCIA_I2C_ADDR_LOW;
	if (offset >= MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH) {
		if (qsfp) {
			/* When reading upper pages 1, 2 and 3 the offset
			 * starts at 128. Please refer to "QSFP+ Memory Map"
			 * figure in SFF-8436 specification and to "CMIS Module
			 * Memory Map" figure in CMIS specification for
			 * graphical depiction.
			 */
			page = MLXSW_REG_MCIA_PAGE_GET(offset);
			offset -= MLXSW_REG_MCIA_EEPROM_UP_PAGE_LENGTH * page;
			if (offset + size > MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH)
				size = MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH - offset;
		} else {
			/* When reading upper pages 1, 2 and 3 the offset
			 * starts at 0 and I2C high address is used. Please refer
			 * refer to "Memory Organization" figure in SFF-8472
			 * specification for graphical depiction.
			 */
			i2c_addr = MLXSW_REG_MCIA_I2C_ADDR_HIGH;
			offset -= MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH;
		}
	}

	mlxsw_reg_mcia_pack(mcia_pl, module, 0, page, offset, size, i2c_addr);

	err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mcia), mcia_pl);
	if (err)
		return err;

	status = mlxsw_reg_mcia_status_get(mcia_pl);
	if (status)
		return -EIO;

	eeprom_tmp = mlxsw_reg_mcia_eeprom_data(mcia_pl);
	memcpy(data, eeprom_tmp, size);
	*p_read_size = size;

	return 0;
}

int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module,
					 int off, int *temp)
{
	unsigned int module_temp, module_crit, module_emerg;
	union {
		u8 buf[MLXSW_REG_MCIA_TH_ITEM_SIZE];
		u16 temp;
	} temp_thresh;
	char mcia_pl[MLXSW_REG_MCIA_LEN] = {0};
	char mtmp_pl[MLXSW_REG_MTMP_LEN];
	char *eeprom_tmp;
	bool qsfp, cmis;
	int page;
	int err;

	mlxsw_reg_mtmp_pack(mtmp_pl, MLXSW_REG_MTMP_MODULE_INDEX_MIN + module,
			    false, false);
	err = mlxsw_reg_query(core, MLXSW_REG(mtmp), mtmp_pl);
	if (err)
		return err;
	mlxsw_reg_mtmp_unpack(mtmp_pl, &module_temp, NULL, &module_crit,
			      &module_emerg, NULL);
	if (!module_temp) {
		*temp = 0;
		return 0;
	}

	/* Validate if threshold reading is available through MTMP register,
	 * otherwise fallback to read through MCIA.
	 */
	if (module_emerg) {
		*temp = off == SFP_TEMP_HIGH_WARN ? module_crit : module_emerg;
		return 0;
	}

	/* Read Free Side Device Temperature Thresholds from page 03h
	 * (MSB at lower byte address).
	 * Bytes:
	 * 128-129 - Temp High Alarm (SFP_TEMP_HIGH_ALARM);
	 * 130-131 - Temp Low Alarm (SFP_TEMP_LOW_ALARM);
	 * 132-133 - Temp High Warning (SFP_TEMP_HIGH_WARN);
	 * 134-135 - Temp Low Warning (SFP_TEMP_LOW_WARN);
	 */

	/* Validate module identifier value. */
	err = mlxsw_env_validate_cable_ident(core, module, &qsfp, &cmis);
	if (err)
		return err;

	if (qsfp) {
		/* For QSFP/CMIS module-defined thresholds are located in page
		 * 02h, otherwise in page 03h.
		 */
		if (cmis)
			page = MLXSW_REG_MCIA_TH_PAGE_CMIS_NUM;
		else
			page = MLXSW_REG_MCIA_TH_PAGE_NUM;
		mlxsw_reg_mcia_pack(mcia_pl, module, 0, page,
				    MLXSW_REG_MCIA_TH_PAGE_OFF + off,
				    MLXSW_REG_MCIA_TH_ITEM_SIZE,
				    MLXSW_REG_MCIA_I2C_ADDR_LOW);
	} else {
		mlxsw_reg_mcia_pack(mcia_pl, module, 0,
				    MLXSW_REG_MCIA_PAGE0_LO,
				    off, MLXSW_REG_MCIA_TH_ITEM_SIZE,
				    MLXSW_REG_MCIA_I2C_ADDR_HIGH);
	}

	err = mlxsw_reg_query(core, MLXSW_REG(mcia), mcia_pl);
	if (err)
		return err;

	eeprom_tmp = mlxsw_reg_mcia_eeprom_data(mcia_pl);
	memcpy(temp_thresh.buf, eeprom_tmp, MLXSW_REG_MCIA_TH_ITEM_SIZE);
	*temp = temp_thresh.temp * 1000;

	return 0;
}

int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module,
			      struct ethtool_modinfo *modinfo)
{
	u8 module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_SIZE];
	u16 offset = MLXSW_REG_MCIA_EEPROM_MODULE_INFO_SIZE;
	u8 module_rev_id, module_id, diag_mon;
	unsigned int read_size;
	int err;

	err = mlxsw_env_query_module_eeprom(mlxsw_core, module, 0, offset,
					    module_info, false, &read_size);
	if (err)
		return err;

	if (read_size < offset)
		return -EIO;

	module_rev_id = module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID];
	module_id = module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID];

	switch (module_id) {
	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP:
		modinfo->type       = ETH_MODULE_SFF_8436;
		modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN;
		break;
	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS:
	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28:
		if (module_id == MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28 ||
		    module_rev_id >=
		    MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID_8636) {
			modinfo->type       = ETH_MODULE_SFF_8636;
			modinfo->eeprom_len = ETH_MODULE_SFF_8636_MAX_LEN;
		} else {
			modinfo->type       = ETH_MODULE_SFF_8436;
			modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN;
		}
		break;
	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_SFP:
		/* Verify if transceiver provides diagnostic monitoring page */
		err = mlxsw_env_query_module_eeprom(mlxsw_core, module,
						    SFP_DIAGMON, 1, &diag_mon,
						    false, &read_size);
		if (err)
			return err;

		if (read_size < 1)
			return -EIO;

		modinfo->type       = ETH_MODULE_SFF_8472;
		if (diag_mon)
			modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
		else
			modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN / 2;
		break;
	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_DD:
		/* Use SFF_8636 as base type. ethtool should recognize specific
		 * type through the identifier value.
		 */
		modinfo->type       = ETH_MODULE_SFF_8636;
		/* Verify if module EEPROM is a flat memory. In case of flat
		 * memory only page 00h (0-255 bytes) can be read. Otherwise
		 * upper pages 01h and 02h can also be read. Upper pages 10h
		 * and 11h are currently not supported by the driver.
		 */
		if (module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_TYPE_ID] &
		    MLXSW_REG_MCIA_EEPROM_CMIS_FLAT_MEMORY)
			modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN;
		else
			modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
		break;
	default:
		return -EINVAL;
	}

	return 0;
}
EXPORT_SYMBOL(mlxsw_env_get_module_info);

int mlxsw_env_get_module_eeprom(struct net_device *netdev,
				struct mlxsw_core *mlxsw_core, int module,
				struct ethtool_eeprom *ee, u8 *data)
{
	int offset = ee->offset;
	unsigned int read_size;
	bool qsfp, cmis;
	int i = 0;
	int err;

	if (!ee->len)
		return -EINVAL;

	memset(data, 0, ee->len);
	/* Validate module identifier value. */
	err = mlxsw_env_validate_cable_ident(mlxsw_core, module, &qsfp, &cmis);
	if (err)
		return err;

	while (i < ee->len) {
		err = mlxsw_env_query_module_eeprom(mlxsw_core, module, offset,
						    ee->len - i, data + i,
						    qsfp, &read_size);
		if (err) {
			netdev_err(netdev, "Eeprom query failed\n");
			return err;
		}

		i += read_size;
		offset += read_size;
	}

	return 0;
}
EXPORT_SYMBOL(mlxsw_env_get_module_eeprom);

static int mlxsw_env_mcia_status_process(const char *mcia_pl,
					 struct netlink_ext_ack *extack)
{
	u8 status = mlxsw_reg_mcia_status_get(mcia_pl);

	switch (status) {
	case MLXSW_REG_MCIA_STATUS_GOOD:
		return 0;
	case MLXSW_REG_MCIA_STATUS_NO_EEPROM_MODULE:
		NL_SET_ERR_MSG_MOD(extack, "No response from module's EEPROM");
		return -EIO;
	case MLXSW_REG_MCIA_STATUS_MODULE_NOT_SUPPORTED:
		NL_SET_ERR_MSG_MOD(extack, "Module type not supported by the device");
		return -EOPNOTSUPP;
	case MLXSW_REG_MCIA_STATUS_MODULE_NOT_CONNECTED:
		NL_SET_ERR_MSG_MOD(extack, "No module present indication");
		return -EIO;
	case MLXSW_REG_MCIA_STATUS_I2C_ERROR:
		NL_SET_ERR_MSG_MOD(extack, "Error occurred while trying to access module's EEPROM using I2C");
		return -EIO;
	case MLXSW_REG_MCIA_STATUS_MODULE_DISABLED:
		NL_SET_ERR_MSG_MOD(extack, "Module is disabled");
		return -EIO;
	default:
		NL_SET_ERR_MSG_MOD(extack, "Unknown error");
		return -EIO;
	}
}

int
mlxsw_env_get_module_eeprom_by_page(struct mlxsw_core *mlxsw_core, u8 module,
				    const struct ethtool_module_eeprom *page,
				    struct netlink_ext_ack *extack)
{
	u32 bytes_read = 0;
	u16 device_addr;

	/* Offset cannot be larger than 2 * ETH_MODULE_EEPROM_PAGE_LEN */
	device_addr = page->offset;

	while (bytes_read < page->length) {
		char mcia_pl[MLXSW_REG_MCIA_LEN];
		char *eeprom_tmp;
		u8 size;
		int err;

		size = min_t(u8, page->length - bytes_read,
			     MLXSW_REG_MCIA_EEPROM_SIZE);

		mlxsw_reg_mcia_pack(mcia_pl, module, 0, page->page,
				    device_addr + bytes_read, size,
				    page->i2c_address);
		mlxsw_reg_mcia_bank_number_set(mcia_pl, page->bank);

		err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mcia), mcia_pl);
		if (err) {
			NL_SET_ERR_MSG_MOD(extack, "Failed to access module's EEPROM");
			return err;
		}

		err = mlxsw_env_mcia_status_process(mcia_pl, extack);
		if (err)
			return err;

		eeprom_tmp = mlxsw_reg_mcia_eeprom_data(mcia_pl);
		memcpy(page->data + bytes_read, eeprom_tmp, size);
		bytes_read += size;
	}

	return bytes_read;
}
EXPORT_SYMBOL(mlxsw_env_get_module_eeprom_by_page);

static int mlxsw_env_module_reset(struct mlxsw_core *mlxsw_core, u8 module)
{
	char pmaos_pl[MLXSW_REG_PMAOS_LEN];

	mlxsw_reg_pmaos_pack(pmaos_pl, module);
	mlxsw_reg_pmaos_rst_set(pmaos_pl, true);

	return mlxsw_reg_write(mlxsw_core, MLXSW_REG(pmaos), pmaos_pl);
}

int mlxsw_env_reset_module(struct net_device *netdev,
			   struct mlxsw_core *mlxsw_core, u8 module, u32 *flags)
{
	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
	u32 req = *flags;
	int err;

	if (!(req & ETH_RESET_PHY) &&
	    !(req & (ETH_RESET_PHY << ETH_RESET_SHARED_SHIFT)))
		return 0;

	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
		return -EINVAL;

	mutex_lock(&mlxsw_env->module_info_lock);

	if (mlxsw_env->module_info[module].num_ports_up) {
		netdev_err(netdev, "Cannot reset module when ports using it are administratively up\n");
		err = -EINVAL;
		goto out;
	}

	if (mlxsw_env->module_info[module].num_ports_mapped > 1 &&
	    !(req & (ETH_RESET_PHY << ETH_RESET_SHARED_SHIFT))) {
		netdev_err(netdev, "Cannot reset module without \"phy-shared\" flag when shared by multiple ports\n");
		err = -EINVAL;
		goto out;
	}

	err = mlxsw_env_module_reset(mlxsw_core, module);
	if (err) {
		netdev_err(netdev, "Failed to reset module\n");
		goto out;
	}

	*flags &= ~(ETH_RESET_PHY | (ETH_RESET_PHY << ETH_RESET_SHARED_SHIFT));

out:
	mutex_unlock(&mlxsw_env->module_info_lock);
	return err;
}
EXPORT_SYMBOL(mlxsw_env_reset_module);

int
mlxsw_env_get_module_power_mode(struct mlxsw_core *mlxsw_core, u8 module,
				struct ethtool_module_power_mode_params *params,
				struct netlink_ext_ack *extack)
{
	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
	char mcion_pl[MLXSW_REG_MCION_LEN];
	u32 status_bits;
	int err;

	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
		return -EINVAL;

	mutex_lock(&mlxsw_env->module_info_lock);

	params->policy = mlxsw_env->module_info[module].power_mode_policy;

	mlxsw_reg_mcion_pack(mcion_pl, module);
	err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mcion), mcion_pl);
	if (err) {
		NL_SET_ERR_MSG_MOD(extack, "Failed to retrieve module's power mode");
		goto out;
	}

	status_bits = mlxsw_reg_mcion_module_status_bits_get(mcion_pl);
	if (!(status_bits & MLXSW_REG_MCION_MODULE_STATUS_BITS_PRESENT_MASK))
		goto out;

	if (status_bits & MLXSW_REG_MCION_MODULE_STATUS_BITS_LOW_POWER_MASK)
		params->mode = ETHTOOL_MODULE_POWER_MODE_LOW;
	else
		params->mode = ETHTOOL_MODULE_POWER_MODE_HIGH;

out:
	mutex_unlock(&mlxsw_env->module_info_lock);
	return err;
}
EXPORT_SYMBOL(mlxsw_env_get_module_power_mode);

static int mlxsw_env_module_enable_set(struct mlxsw_core *mlxsw_core,
				       u8 module, bool enable)
{
	enum mlxsw_reg_pmaos_admin_status admin_status;
	char pmaos_pl[MLXSW_REG_PMAOS_LEN];

	mlxsw_reg_pmaos_pack(pmaos_pl, module);
	admin_status = enable ? MLXSW_REG_PMAOS_ADMIN_STATUS_ENABLED :
				MLXSW_REG_PMAOS_ADMIN_STATUS_DISABLED;
	mlxsw_reg_pmaos_admin_status_set(pmaos_pl, admin_status);
	mlxsw_reg_pmaos_ase_set(pmaos_pl, true);

	return mlxsw_reg_write(mlxsw_core, MLXSW_REG(pmaos), pmaos_pl);
}

static int mlxsw_env_module_low_power_set(struct mlxsw_core *mlxsw_core,
					  u8 module, bool low_power)
{
	u16 eeprom_override_mask, eeprom_override;
	char pmmp_pl[MLXSW_REG_PMMP_LEN];

	mlxsw_reg_pmmp_pack(pmmp_pl, module);
	mlxsw_reg_pmmp_sticky_set(pmmp_pl, true);
	/* Mask all the bits except low power mode. */
	eeprom_override_mask = ~MLXSW_REG_PMMP_EEPROM_OVERRIDE_LOW_POWER_MASK;
	mlxsw_reg_pmmp_eeprom_override_mask_set(pmmp_pl, eeprom_override_mask);
	eeprom_override = low_power ? MLXSW_REG_PMMP_EEPROM_OVERRIDE_LOW_POWER_MASK :
				      0;
	mlxsw_reg_pmmp_eeprom_override_set(pmmp_pl, eeprom_override);

	return mlxsw_reg_write(mlxsw_core, MLXSW_REG(pmmp), pmmp_pl);
}

static int __mlxsw_env_set_module_power_mode(struct mlxsw_core *mlxsw_core,
					     u8 module, bool low_power,
					     struct netlink_ext_ack *extack)
{
	int err;

	err = mlxsw_env_module_enable_set(mlxsw_core, module, false);
	if (err) {
		NL_SET_ERR_MSG_MOD(extack, "Failed to disable module");
		return err;
	}

	err = mlxsw_env_module_low_power_set(mlxsw_core, module, low_power);
	if (err) {
		NL_SET_ERR_MSG_MOD(extack, "Failed to set module's power mode");
		goto err_module_low_power_set;
	}

	err = mlxsw_env_module_enable_set(mlxsw_core, module, true);
	if (err) {
		NL_SET_ERR_MSG_MOD(extack, "Failed to enable module");
		goto err_module_enable_set;
	}

	return 0;

err_module_enable_set:
	mlxsw_env_module_low_power_set(mlxsw_core, module, !low_power);
err_module_low_power_set:
	mlxsw_env_module_enable_set(mlxsw_core, module, true);
	return err;
}

int
mlxsw_env_set_module_power_mode(struct mlxsw_core *mlxsw_core, u8 module,
				enum ethtool_module_power_mode_policy policy,
				struct netlink_ext_ack *extack)
{
	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
	bool low_power;
	int err = 0;

	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
		return -EINVAL;

	if (policy != ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH &&
	    policy != ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO) {
		NL_SET_ERR_MSG_MOD(extack, "Unsupported power mode policy");
		return -EOPNOTSUPP;
	}

	mutex_lock(&mlxsw_env->module_info_lock);

	if (mlxsw_env->module_info[module].power_mode_policy == policy)
		goto out;

	/* If any ports are up, we are already in high power mode. */
	if (mlxsw_env->module_info[module].num_ports_up)
		goto out_set_policy;

	low_power = policy == ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO;
	err = __mlxsw_env_set_module_power_mode(mlxsw_core, module, low_power,
						extack);
	if (err)
		goto out;

out_set_policy:
	mlxsw_env->module_info[module].power_mode_policy = policy;
out:
	mutex_unlock(&mlxsw_env->module_info_lock);
	return err;
}
EXPORT_SYMBOL(mlxsw_env_set_module_power_mode);

static int mlxsw_env_module_has_temp_sensor(struct mlxsw_core *mlxsw_core,
					    u8 module,
					    bool *p_has_temp_sensor)
{
	char mtbr_pl[MLXSW_REG_MTBR_LEN];
	u16 temp;
	int err;

	mlxsw_reg_mtbr_pack(mtbr_pl, MLXSW_REG_MTBR_BASE_MODULE_INDEX + module,
			    1);
	err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mtbr), mtbr_pl);
	if (err)
		return err;

	mlxsw_reg_mtbr_temp_unpack(mtbr_pl, 0, &temp, NULL);

	switch (temp) {
	case MLXSW_REG_MTBR_BAD_SENS_INFO:
	case MLXSW_REG_MTBR_NO_CONN:
	case MLXSW_REG_MTBR_NO_TEMP_SENS:
	case MLXSW_REG_MTBR_INDEX_NA:
		*p_has_temp_sensor = false;
		break;
	default:
		*p_has_temp_sensor = temp ? true : false;
	}
	return 0;
}

static int mlxsw_env_temp_event_set(struct mlxsw_core *mlxsw_core,
				    u16 sensor_index, bool enable)
{
	char mtmp_pl[MLXSW_REG_MTMP_LEN] = {0};
	enum mlxsw_reg_mtmp_tee tee;
	int err, threshold_hi;

	mlxsw_reg_mtmp_sensor_index_set(mtmp_pl, sensor_index);
	err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mtmp), mtmp_pl);
	if (err)
		return err;

	if (enable) {
		err = mlxsw_env_module_temp_thresholds_get(mlxsw_core,
							   sensor_index -
							   MLXSW_REG_MTMP_MODULE_INDEX_MIN,
							   SFP_TEMP_HIGH_WARN,
							   &threshold_hi);
		/* In case it is not possible to query the module's threshold,
		 * use the default value.
		 */
		if (err)
			threshold_hi = MLXSW_REG_MTMP_THRESH_HI;
		else
			/* mlxsw_env_module_temp_thresholds_get() multiplies
			 * Celsius degrees by 1000 whereas MTMP expects
			 * temperature in 0.125 Celsius degrees units.
			 * Convert threshold_hi to correct units.
			 */
			threshold_hi = threshold_hi / 1000 * 8;

		mlxsw_reg_mtmp_temperature_threshold_hi_set(mtmp_pl, threshold_hi);
		mlxsw_reg_mtmp_temperature_threshold_lo_set(mtmp_pl, threshold_hi -
							    MLXSW_REG_MTMP_HYSTERESIS_TEMP);
	}
	tee = enable ? MLXSW_REG_MTMP_TEE_GENERATE_EVENT : MLXSW_REG_MTMP_TEE_NO_EVENT;
	mlxsw_reg_mtmp_tee_set(mtmp_pl, tee);
	return mlxsw_reg_write(mlxsw_core, MLXSW_REG(mtmp), mtmp_pl);
}

static int mlxsw_env_module_temp_event_enable(struct mlxsw_core *mlxsw_core,
					      u8 module_count)
{
	int i, err, sensor_index;
	bool has_temp_sensor;

	for (i = 0; i < module_count; i++) {
		err = mlxsw_env_module_has_temp_sensor(mlxsw_core, i,
						       &has_temp_sensor);
		if (err)
			return err;

		if (!has_temp_sensor)
			continue;

		sensor_index = i + MLXSW_REG_MTMP_MODULE_INDEX_MIN;
		err = mlxsw_env_temp_event_set(mlxsw_core, sensor_index, true);
		if (err)
			return err;
	}

	return 0;
}

struct mlxsw_env_module_temp_warn_event {
	struct mlxsw_env *mlxsw_env;
	char mtwe_pl[MLXSW_REG_MTWE_LEN];
	struct work_struct work;
};

static void mlxsw_env_mtwe_event_work(struct work_struct *work)
{
	struct mlxsw_env_module_temp_warn_event *event;
	struct mlxsw_env *mlxsw_env;
	int i, sensor_warning;
	bool is_overheat;

	event = container_of(work, struct mlxsw_env_module_temp_warn_event,
			     work);
	mlxsw_env = event->mlxsw_env;

	for (i = 0; i < mlxsw_env->module_count; i++) {
		/* 64-127 of sensor_index are mapped to the port modules
		 * sequentially (module 0 is mapped to sensor_index 64,
		 * module 1 to sensor_index 65 and so on)
		 */
		sensor_warning =
			mlxsw_reg_mtwe_sensor_warning_get(event->mtwe_pl,
							  i + MLXSW_REG_MTMP_MODULE_INDEX_MIN);
		mutex_lock(&mlxsw_env->module_info_lock);
		is_overheat =
			mlxsw_env->module_info[i].is_overheat;

		if ((is_overheat && sensor_warning) ||
		    (!is_overheat && !sensor_warning)) {
			/* Current state is "warning" and MTWE still reports
			 * warning OR current state in "no warning" and MTWE
			 * does not report warning.
			 */
			mutex_unlock(&mlxsw_env->module_info_lock);
			continue;
		} else if (is_overheat && !sensor_warning) {
			/* MTWE reports "no warning", turn is_overheat off.
			 */
			mlxsw_env->module_info[i].is_overheat = false;
			mutex_unlock(&mlxsw_env->module_info_lock);
		} else {
			/* Current state is "no warning" and MTWE reports
			 * "warning", increase the counter and turn is_overheat
			 * on.
			 */
			mlxsw_env->module_info[i].is_overheat = true;
			mlxsw_env->module_info[i].module_overheat_counter++;
			mutex_unlock(&mlxsw_env->module_info_lock);
		}
	}

	kfree(event);
}

static void
mlxsw_env_mtwe_listener_func(const struct mlxsw_reg_info *reg, char *mtwe_pl,
			     void *priv)
{
	struct mlxsw_env_module_temp_warn_event *event;
	struct mlxsw_env *mlxsw_env = priv;

	event = kmalloc(sizeof(*event), GFP_ATOMIC);
	if (!event)
		return;

	event->mlxsw_env = mlxsw_env;
	memcpy(event->mtwe_pl, mtwe_pl, MLXSW_REG_MTWE_LEN);
	INIT_WORK(&event->work, mlxsw_env_mtwe_event_work);
	mlxsw_core_schedule_work(&event->work);
}

static const struct mlxsw_listener mlxsw_env_temp_warn_listener =
	MLXSW_EVENTL(mlxsw_env_mtwe_listener_func, MTWE, MTWE);

static int mlxsw_env_temp_warn_event_register(struct mlxsw_core *mlxsw_core)
{
	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);

	if (!mlxsw_core_temp_warn_enabled(mlxsw_core))
		return 0;

	return mlxsw_core_trap_register(mlxsw_core,
					&mlxsw_env_temp_warn_listener,
					mlxsw_env);
}

static void mlxsw_env_temp_warn_event_unregister(struct mlxsw_env *mlxsw_env)
{
	if (!mlxsw_core_temp_warn_enabled(mlxsw_env->core))
		return;

	mlxsw_core_trap_unregister(mlxsw_env->core,
				   &mlxsw_env_temp_warn_listener, mlxsw_env);
}

struct mlxsw_env_module_plug_unplug_event {
	struct mlxsw_env *mlxsw_env;
	u8 module;
	struct work_struct work;
};

static void mlxsw_env_pmpe_event_work(struct work_struct *work)
{
	struct mlxsw_env_module_plug_unplug_event *event;
	struct mlxsw_env *mlxsw_env;
	bool has_temp_sensor;
	u16 sensor_index;
	int err;

	event = container_of(work, struct mlxsw_env_module_plug_unplug_event,
			     work);
	mlxsw_env = event->mlxsw_env;

	mutex_lock(&mlxsw_env->module_info_lock);
	mlxsw_env->module_info[event->module].is_overheat = false;
	mutex_unlock(&mlxsw_env->module_info_lock);

	err = mlxsw_env_module_has_temp_sensor(mlxsw_env->core, event->module,
					       &has_temp_sensor);
	/* Do not disable events on modules without sensors or faulty sensors
	 * because FW returns errors.
	 */
	if (err)
		goto out;

	if (!has_temp_sensor)
		goto out;

	sensor_index = event->module + MLXSW_REG_MTMP_MODULE_INDEX_MIN;
	mlxsw_env_temp_event_set(mlxsw_env->core, sensor_index, true);

out:
	kfree(event);
}

static void
mlxsw_env_pmpe_listener_func(const struct mlxsw_reg_info *reg, char *pmpe_pl,
			     void *priv)
{
	struct mlxsw_env_module_plug_unplug_event *event;
	enum mlxsw_reg_pmpe_module_status module_status;
	u8 module = mlxsw_reg_pmpe_module_get(pmpe_pl);
	struct mlxsw_env *mlxsw_env = priv;

	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
		return;

	module_status = mlxsw_reg_pmpe_module_status_get(pmpe_pl);
	if (module_status != MLXSW_REG_PMPE_MODULE_STATUS_PLUGGED_ENABLED)
		return;

	event = kmalloc(sizeof(*event), GFP_ATOMIC);
	if (!event)
		return;

	event->mlxsw_env = mlxsw_env;
	event->module = module;
	INIT_WORK(&event->work, mlxsw_env_pmpe_event_work);
	mlxsw_core_schedule_work(&event->work);
}

static const struct mlxsw_listener mlxsw_env_module_plug_listener =
	MLXSW_EVENTL(mlxsw_env_pmpe_listener_func, PMPE, PMPE);

static int
mlxsw_env_module_plug_event_register(struct mlxsw_core *mlxsw_core)
{
	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);

	if (!mlxsw_core_temp_warn_enabled(mlxsw_core))
		return 0;

	return mlxsw_core_trap_register(mlxsw_core,
					&mlxsw_env_module_plug_listener,
					mlxsw_env);
}

static void
mlxsw_env_module_plug_event_unregister(struct mlxsw_env *mlxsw_env)
{
	if (!mlxsw_core_temp_warn_enabled(mlxsw_env->core))
		return;

	mlxsw_core_trap_unregister(mlxsw_env->core,
				   &mlxsw_env_module_plug_listener,
				   mlxsw_env);
}

static int
mlxsw_env_module_oper_state_event_enable(struct mlxsw_core *mlxsw_core,
					 u8 module_count)
{
	int i, err;

	for (i = 0; i < module_count; i++) {
		char pmaos_pl[MLXSW_REG_PMAOS_LEN];

		mlxsw_reg_pmaos_pack(pmaos_pl, i);
		mlxsw_reg_pmaos_e_set(pmaos_pl,
				      MLXSW_REG_PMAOS_E_GENERATE_EVENT);
		mlxsw_reg_pmaos_ee_set(pmaos_pl, true);
		err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(pmaos), pmaos_pl);
		if (err)
			return err;
	}
	return 0;
}

int
mlxsw_env_module_overheat_counter_get(struct mlxsw_core *mlxsw_core, u8 module,
				      u64 *p_counter)
{
	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);

	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
		return -EINVAL;

	mutex_lock(&mlxsw_env->module_info_lock);
	*p_counter = mlxsw_env->module_info[module].module_overheat_counter;
	mutex_unlock(&mlxsw_env->module_info_lock);

	return 0;
}
EXPORT_SYMBOL(mlxsw_env_module_overheat_counter_get);

void mlxsw_env_module_port_map(struct mlxsw_core *mlxsw_core, u8 module)
{
	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);

	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
		return;

	mutex_lock(&mlxsw_env->module_info_lock);
	mlxsw_env->module_info[module].num_ports_mapped++;
	mutex_unlock(&mlxsw_env->module_info_lock);
}
EXPORT_SYMBOL(mlxsw_env_module_port_map);

void mlxsw_env_module_port_unmap(struct mlxsw_core *mlxsw_core, u8 module)
{
	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);

	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
		return;

	mutex_lock(&mlxsw_env->module_info_lock);
	mlxsw_env->module_info[module].num_ports_mapped--;
	mutex_unlock(&mlxsw_env->module_info_lock);
}
EXPORT_SYMBOL(mlxsw_env_module_port_unmap);

int mlxsw_env_module_port_up(struct mlxsw_core *mlxsw_core, u8 module)
{
	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
	int err = 0;

	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
		return -EINVAL;

	mutex_lock(&mlxsw_env->module_info_lock);

	if (mlxsw_env->module_info[module].power_mode_policy !=
	    ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO)
		goto out_inc;

	if (mlxsw_env->module_info[module].num_ports_up != 0)
		goto out_inc;

	/* Transition to high power mode following first port using the module
	 * being put administratively up.
	 */
	err = __mlxsw_env_set_module_power_mode(mlxsw_core, module, false,
						NULL);
	if (err)
		goto out_unlock;

out_inc:
	mlxsw_env->module_info[module].num_ports_up++;
out_unlock:
	mutex_unlock(&mlxsw_env->module_info_lock);
	return err;
}
EXPORT_SYMBOL(mlxsw_env_module_port_up);

void mlxsw_env_module_port_down(struct mlxsw_core *mlxsw_core, u8 module)
{
	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);

	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
		return;

	mutex_lock(&mlxsw_env->module_info_lock);

	mlxsw_env->module_info[module].num_ports_up--;

	if (mlxsw_env->module_info[module].power_mode_policy !=
	    ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO)
		goto out_unlock;

	if (mlxsw_env->module_info[module].num_ports_up != 0)
		goto out_unlock;

	/* Transition to low power mode following last port using the module
	 * being put administratively down.
	 */
	__mlxsw_env_set_module_power_mode(mlxsw_core, module, true, NULL);

out_unlock:
	mutex_unlock(&mlxsw_env->module_info_lock);
}
EXPORT_SYMBOL(mlxsw_env_module_port_down);

int mlxsw_env_init(struct mlxsw_core *mlxsw_core, struct mlxsw_env **p_env)
{
	char mgpir_pl[MLXSW_REG_MGPIR_LEN];
	struct mlxsw_env *env;
	u8 module_count;
	int i, err;

	mlxsw_reg_mgpir_pack(mgpir_pl);
	err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mgpir), mgpir_pl);
	if (err)
		return err;

	mlxsw_reg_mgpir_unpack(mgpir_pl, NULL, NULL, NULL, &module_count);

	env = kzalloc(struct_size(env, module_info, module_count), GFP_KERNEL);
	if (!env)
		return -ENOMEM;

	/* Firmware defaults to high power mode policy where modules are
	 * transitioned to high power mode following plug-in.
	 */
	for (i = 0; i < module_count; i++)
		env->module_info[i].power_mode_policy =
			ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH;

	mutex_init(&env->module_info_lock);
	env->core = mlxsw_core;
	env->module_count = module_count;
	*p_env = env;

	err = mlxsw_env_temp_warn_event_register(mlxsw_core);
	if (err)
		goto err_temp_warn_event_register;

	err = mlxsw_env_module_plug_event_register(mlxsw_core);
	if (err)
		goto err_module_plug_event_register;

	err = mlxsw_env_module_oper_state_event_enable(mlxsw_core,
						       env->module_count);
	if (err)
		goto err_oper_state_event_enable;

	err = mlxsw_env_module_temp_event_enable(mlxsw_core, env->module_count);
	if (err)
		goto err_temp_event_enable;

	return 0;

err_temp_event_enable:
err_oper_state_event_enable:
	mlxsw_env_module_plug_event_unregister(env);
err_module_plug_event_register:
	mlxsw_env_temp_warn_event_unregister(env);
err_temp_warn_event_register:
	mutex_destroy(&env->module_info_lock);
	kfree(env);
	return err;
}

void mlxsw_env_fini(struct mlxsw_env *env)
{
	mlxsw_env_module_plug_event_unregister(env);
	/* Make sure there is no more event work scheduled. */
	mlxsw_core_flush_owq();
	mlxsw_env_temp_warn_event_unregister(env);
	mutex_destroy(&env->module_info_lock);
	kfree(env);
}