summaryrefslogtreecommitdiffstats
path: root/src/occ_405/amec/amec_health.c
blob: 0d99f20bad245730fe5d8cbd38a5eb5bda3fdfa0 (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
/* IBM_PROLOG_BEGIN_TAG                                                   */
/* This is an automatically generated prolog.                             */
/*                                                                        */
/* $Source: src/occ_405/amec/amec_health.c $                              */
/*                                                                        */
/* OpenPOWER OnChipController Project                                     */
/*                                                                        */
/* Contributors Listed Below - COPYRIGHT 2011,2019                        */
/* [+] International Business Machines Corp.                              */
/*                                                                        */
/*                                                                        */
/* Licensed under the Apache License, Version 2.0 (the "License");        */
/* you may not use this file except in compliance with the License.       */
/* You may obtain a copy of the License at                                */
/*                                                                        */
/*     http://www.apache.org/licenses/LICENSE-2.0                         */
/*                                                                        */
/* Unless required by applicable law or agreed to in writing, software    */
/* distributed under the License is distributed on an "AS IS" BASIS,      */
/* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or        */
/* implied. See the License for the specific language governing           */
/* permissions and limitations under the License.                         */
/*                                                                        */
/* IBM_PROLOG_END_TAG                                                     */

//*************************************************************************/
// Includes
//*************************************************************************/
#include "amec_health.h"
#include "amec_sys.h"
#include "amec_service_codes.h"
#include "occ_service_codes.h"
#include <centaur_data.h>
#include <proc_data.h>

//*************************************************************************/
// Externs
//*************************************************************************/
extern bool G_simics_environment;
extern bool G_log_gpe1_error;

//*************************************************************************/
// Defines/Enums
//*************************************************************************/

//*************************************************************************/
// Globals
//*************************************************************************/

// Have we already called out the dimm for overtemp (bitmap of dimms)?
dimm_sensor_flags_t G_dimm_overtemp_logged_bitmap = {{0}};

// Have we already called out the dimm for timeout (bitmap of dimms)?
dimm_sensor_flags_t G_dimm_timeout_logged_bitmap = {{0}};

// Are any dimms currently in the timedout state (bitmap of dimm)?
dimm_sensor_flags_t G_dimm_temp_expired_bitmap = {{0}};

// Have we already called out the centaur for timeout (bitmap of centaurs)?
uint16_t G_cent_timeout_logged_bitmap = 0;

// Have we already called out the centaur for overtemp (bitmap of centaurs)?
uint16_t G_cent_overtemp_logged_bitmap = 0;

// Are any mem controllers currently in the timedout state (bitmap of centaurs)?
uint16_t G_cent_temp_expired_bitmap = 0;

// Array to store the update tag of each core's temperature sensor
uint32_t G_core_temp_update_tag[MAX_NUM_CORES] = {0};

// Reading VRM Vdd temperature timedout?
bool G_vrm_vdd_temp_expired = false;

//*************************************************************************/
// Function Declarations
//*************************************************************************/

//*************************************************************************/
// Functions
//*************************************************************************/
uint64_t amec_mem_get_huid(uint8_t i_cent, uint8_t i_dimm)
{
    uint64_t l_huid;

    if(i_dimm == 0xff)
    {
        //we're being asked for a centaur huid
        l_huid = G_sysConfigData.centaur_huids[i_cent];
    }
    else
    {
        //we're being asked for a dimm huid
        l_huid = G_sysConfigData.dimm_huids[i_cent][i_dimm];
        if(l_huid == 0)
        {
            if (MEM_TYPE_CUMULUS == G_sysConfigData.mem_type)
            {
                //if we don't have a valid dimm huid, use the centaur huid.
                l_huid = G_sysConfigData.centaur_huids[i_cent];
            }
            else
            {
                // else NIMBUS huid of 0 indicates not present (should never get called)
                TRAC_ERR("amec_mem_get_huid: DIMM%04X did not have a HUID to call out!", (i_cent<<8)|i_dimm);
            }
        }
    }
    return l_huid;
}

//If i_dimm is 0xff it is assumed that the caller wishes to
//mark the centaur as being logged.  Otherwise, it is assumed
//that the dimm should be marked.
void amec_mem_mark_logged(uint8_t i_cent,
                          uint8_t i_dimm,
                          uint16_t* i_clog_bitmap,
                          uint8_t*  i_dlog_bitmap)
{
    if(i_dimm == 0xff)
    {
        //mark the centaur as being called out.
        *i_clog_bitmap |= CENTAUR0_PRESENT_MASK >> i_cent;
    }
    else
    {
        //mark the dimm as being called out.
        *i_dlog_bitmap |= DIMM_SENSOR0 >> i_dimm;
    }
}


/*
 * Function Specification
 *
 * Name: amec_health_check_dimm_temp
 *
 * Description: Check if DIMM temperature exceeds the error temperature
 *              as defined in thermal control thresholds
 *              (ERROR field for DIMM FRU Type)
 *
 * End Function Specification
 */
void amec_health_check_dimm_temp()
{
    uint16_t                    l_ot_error, l_max_temp;
    sensor_t                    *l_sensor;
    uint8_t                     l_dimm;
    uint8_t                     l_port;
    uint8_t                     l_max_port; // #ports in nimbus/#mem buf in cumulus/OCM
    uint8_t                     l_max_dimm_per_port; // per port in nimbus/per mem buf in cumulus/OCM
    uint32_t                    l_callouts_count = 0;
    uint8_t                     l_new_callouts;
    uint64_t                    l_huid;
    errlHndl_t                  l_err = NULL;

    if(G_sysConfigData.mem_type == MEM_TYPE_NIMBUS)
    {
        l_max_port = NUM_DIMM_PORTS;
        l_max_dimm_per_port = NUM_DIMMS_PER_I2CPORT;
    }
    else if(G_sysConfigData.mem_type == MEM_TYPE_OCM)
    {
        l_max_port = MAX_NUM_OCMBS;
        l_max_dimm_per_port = NUM_DIMMS_PER_OCMB;
    }
    else // MEM_TYPE_CUMULUS
    {
        l_max_port = MAX_NUM_CENTAURS;
        l_max_dimm_per_port = NUM_DIMMS_PER_CENTAUR;
    }

    // Check to see if any dimms have reached the error temperature that
    // haven't been called out already
    if( (G_dimm_overtemp_bitmap.dw[0] == G_dimm_overtemp_logged_bitmap.dw[0]) &&
        (G_dimm_overtemp_bitmap.dw[1] == G_dimm_overtemp_logged_bitmap.dw[1]) )
    {
        return;
    }

    l_ot_error = g_amec->thermaldimm.ot_error;
    l_sensor = getSensorByGsid(TEMPDIMMTHRM);
    l_max_temp = l_sensor->sample_max;

    //iterate over all dimms
    for(l_port = 0; l_port < l_max_port; l_port++)
    {
        //only callout a dimm if it hasn't been called out already
        l_new_callouts = G_dimm_overtemp_bitmap.bytes[l_port] ^
                         G_dimm_overtemp_logged_bitmap.bytes[l_port];

        //skip to next port if no new callouts for this one
        if (!l_new_callouts || (G_dimm_overtemp_bitmap.bytes[l_port] == 0))
        {
            continue;
        }

        // if the previous port had errors commit it so this port gets new error log
        if(l_err)
        {
           commitErrl(&l_err);
           l_callouts_count = 0;
        }

        //find the dimm(s) that need to be called out for this port
        for(l_dimm = 0; l_dimm < l_max_dimm_per_port; l_dimm++)
        {
            if (!(l_new_callouts & (DIMM_SENSOR0 >> l_dimm)))
            {
                continue;
            }

            fru_temp_t* l_fru;
            l_fru = &g_amec->proc[0].memctl[l_port].centaur.dimm_temps[l_dimm];
            amec_mem_mark_logged(l_port,
                                 l_dimm,
                                 &G_cent_overtemp_logged_bitmap,
                                 &G_dimm_overtemp_logged_bitmap.bytes[l_port]);
            TRAC_ERR("amec_health_check_dimm_temp: DIMM%04X being called out for overtemp - %dC",
                     (l_port<<8)|l_dimm, l_fru->cur_temp);

            // Create single elog with up to MAX_CALLOUTS for this port
            if(l_callouts_count < ERRL_MAX_CALLOUTS)
            {
                //If we don't have an error log for the callout, create one
                if(!l_err)
                {
                    TRAC_ERR("amec_health_check_dimm_temp: Creating log for port[%d] OT bitmap[0x%02X] logged bitmap[0x%02X]",
                             l_port,
                             G_dimm_overtemp_bitmap.bytes[l_port],
                             G_dimm_overtemp_logged_bitmap.bytes[l_port]);
                    /* @
                     * @errortype
                     * @moduleid    AMEC_HEALTH_CHECK_DIMM_TEMP
                     * @reasoncode  DIMM_ERROR_TEMP
                     * @userdata1   Maximum DIMM temperature
                     * @userdata2   DIMM temperature threshold
                     * @userdata4   OCC_NO_EXTENDED_RC
                     * @devdesc     Memory DIMM(s) exceeded maximum safe
                     *              temperature.
                     */
                    l_err = createErrl(AMEC_HEALTH_CHECK_DIMM_TEMP,    //modId
                                       DIMM_ERROR_TEMP,               //reasoncode
                                       OCC_NO_EXTENDED_RC,            //Extended reason code
                                       ERRL_SEV_PREDICTIVE,           //Severity
                                       NULL,                          //Trace Buf
                                       DEFAULT_TRACE_SIZE,            //Trace Size
                                       l_max_temp,                    //userdata1
                                       l_ot_error);                   //userdata2

                    // Callout the "over temperature" procedure
                    addCalloutToErrl(l_err,
                                     ERRL_CALLOUT_TYPE_COMPONENT_ID,
                                     ERRL_COMPONENT_ID_OVER_TEMPERATURE,
                                     ERRL_CALLOUT_PRIORITY_HIGH);
                    l_callouts_count = 1;
                }

                // Callout dimm
                l_huid = amec_mem_get_huid(l_port, l_dimm);
                addCalloutToErrl(l_err,
                                 ERRL_CALLOUT_TYPE_HUID,
                                 l_huid,
                                 ERRL_CALLOUT_PRIORITY_MED);

                l_callouts_count++;
            }
        }//iterate over dimms
    }//iterate over ports

    if(l_err)
    {
        commitErrl(&l_err);
    }

} // end amec_health_check_dimm_temp()


/*
 * Function Specification
 *
 * Name: amec_health_check_dimm_timeout
 *
 * Description: Check for centaur-dimm/rdimm-modules timeout condition
 *              as defined in thermal control thresholds
 *              (MAX_READ_TIMEOUT field for Centaur/DIMM FRU Type)
 *
 * End Function Specification
 */
void amec_health_check_dimm_timeout()
{
    static dimm_sensor_flags_t L_temp_update_bitmap_prev = {{0}};
    dimm_sensor_flags_t l_need_inc, l_need_clr, l_temp_update_bitmap;
    uint8_t l_dimm, l_port;
    fru_temp_t* l_fru;
    errlHndl_t  l_err = NULL;
    uint32_t    l_callouts_count = 0;
    uint64_t    l_huid;
    static bool L_ran_once = FALSE;

    do
    {
        //For every dimm sensor there are 3 cases to consider
        //
        //1) sensor is enabled and not updated (need to increment timer and check for timeout)
        //2) sensor is enabled and updated but wasn't updated on previous check (need to clear timer)
        //3) sensor is enabled and updated and was updated on previous check (do nothing)

        //Grab snapshot of G_dimm_temp_updated_bitmap and clear it
        l_temp_update_bitmap.dw[0] = G_dimm_temp_updated_bitmap.dw[0];
        l_temp_update_bitmap.dw[1] = G_dimm_temp_updated_bitmap.dw[1];
        G_dimm_temp_updated_bitmap.dw[0] = 0;
        G_dimm_temp_updated_bitmap.dw[1] = 0;

        //check if we need to increment any timers (haven't been updated in the last second)
        l_need_inc.dw[0] = G_dimm_enabled_sensors.dw[0] & ~l_temp_update_bitmap.dw[0];
        l_need_inc.dw[1] = G_dimm_enabled_sensors.dw[1] & ~l_temp_update_bitmap.dw[1];

        //check if we need to clear any timers (updated now but not updated previously)
        l_need_clr.dw[0] = l_temp_update_bitmap.dw[0] & ~L_temp_update_bitmap_prev.dw[0];
        l_need_clr.dw[1] = l_temp_update_bitmap.dw[1] & ~L_temp_update_bitmap_prev.dw[1];

        //save off the previous bitmap of updated sensors for next time
        L_temp_update_bitmap_prev.dw[0] = l_temp_update_bitmap.dw[0];
        L_temp_update_bitmap_prev.dw[1] = l_temp_update_bitmap.dw[1];

        //only go further if we actually have work to do here.
        if(!l_need_inc.dw[0] && !l_need_inc.dw[1] &&
           !l_need_clr.dw[0] && !l_need_clr.dw[1])
        {
            //nothing to do
            break;
        }

        uint8_t l_max_port; // #ports in nimbus/#mem buffs in cumulus/OCM
        uint8_t l_max_dimm_per_port; // per port in nimbus/per mem buff in cumulus/OCM
        if(G_sysConfigData.mem_type == MEM_TYPE_NIMBUS)
        {
            l_max_port = NUM_DIMM_PORTS;
            l_max_dimm_per_port = NUM_DIMMS_PER_I2CPORT;
        }
        else if(G_sysConfigData.mem_type == MEM_TYPE_OCM)
        {
            l_max_port = MAX_NUM_OCMBS;
            l_max_dimm_per_port = NUM_DIMMS_PER_OCMB;
        }
        else // MEM_TYPE_CUMULUS
        {
            l_max_port = MAX_NUM_CENTAURS;
            l_max_dimm_per_port = NUM_DIMMS_PER_CENTAUR;
        }
        //iterate across all ports incrementing dimm sensor timers as needed
        for(l_port = 0; l_port < l_max_port; l_port++)
        {
            //any dimm timers on this port need incrementing?
            if(!l_need_inc.bytes[l_port])
            {
                // All dimm sensors were updated for this port
                // Trace this fact and clear the expired byte for all DIMMs on this port
                if(G_dimm_temp_expired_bitmap.bytes[l_port])
                {
                    G_dimm_temp_expired_bitmap.bytes[l_port] = 0;
                    TRAC_INFO("All DIMM sensors for port %d have been updated", l_port);
                }
                continue;
            }

            //There's at least one dimm requiring an increment, find the dimm
            for(l_dimm = 0; l_dimm < l_max_dimm_per_port; l_dimm++)
            {
                //not this one, check if we need to clear the dimm timeout and go to the next one
                if(!(l_need_inc.bytes[l_port] & (DIMM_SENSOR0 >> l_dimm)))
                {
                    // Clear this one if needed
                    if(G_dimm_temp_expired_bitmap.bytes[l_port] & (DIMM_SENSOR0 >> l_dimm))
                    {
                        G_dimm_temp_expired_bitmap.bytes[l_port] &= ~(DIMM_SENSOR0 >> l_dimm);
                    }
                    continue;
                }

                //we found one.
                l_fru = &g_amec->proc[0].memctl[l_port].centaur.dimm_temps[l_dimm];

                //increment timer
                l_fru->sample_age++;

                //handle wrapping
                if(!l_fru->sample_age)
                {
                    l_fru->sample_age = -1;
                }

                // In Simics: the RTL timer is increased and a DIMM reading will not always
                // complete on each call.  (an error will still be logged if reading does not
                // meet the DIMM MAX_READ_TIMEOUT.)
                if((l_fru->sample_age == 1) && (!G_simics_environment))
                {
                    TRAC_INFO("No new DIMM temperature available for DIMM%04X (cur_temp[%d] flags[0x%02X])",
                              (l_port<<8)|l_dimm, l_fru->cur_temp, l_fru->flags);
                }

                //check if the temperature reading is still useable
                if(g_amec->thermaldimm.temp_timeout == 0xff ||
                   l_fru->sample_age < g_amec->thermaldimm.temp_timeout)
                {
                    continue;
                }

                //temperature has expired.  Notify control algorithms which DIMM
                if(!(G_dimm_temp_expired_bitmap.bytes[l_port] & (DIMM_SENSOR0 >> l_dimm)))
                {
                    G_dimm_temp_expired_bitmap.bytes[l_port] |= (DIMM_SENSOR0 >> l_dimm);
                    TRAC_ERR("Timed out reading DIMM%04X temperature sensor", (l_port<<8)|l_dimm);
                }

                //If we've already logged an error for this FRU go to the next one.
                if(G_dimm_timeout_logged_bitmap.bytes[l_port] & (DIMM_SENSOR0 >> l_dimm))
                {
                    continue;
                }

                // To prevent DIMMs from incorrectly being called out, don't log errors if there have
                // been timeouts with GPE1 tasks not finishing
                if(G_error_history[ERRH_GPE1_NOT_IDLE] > g_amec->thermaldimm.temp_timeout)
                {
                    TRAC_ERR("Timed out reading DIMM temperature due to GPE1 issues");
                    // give notification that GPE1 error should now be logged which will reset the OCC
                    G_log_gpe1_error = TRUE;
                    // no reason to check anymore since all DIMMs are collected from the same GPE
                    break;
                }

                TRAC_ERR("Timed out reading DIMM%04X temperature (cur_temp[%d] flags[0x%02X])",
                         (l_port<<8)|l_dimm, l_fru->cur_temp, l_fru->flags);

                //Mark DIMM as logged so we don't log it more than once
                amec_mem_mark_logged(l_port,
                                     l_dimm,
                                     &G_cent_timeout_logged_bitmap,
                                     &G_dimm_timeout_logged_bitmap.bytes[l_port]);

                // Create single elog with up to MAX_CALLOUTS
                if(l_callouts_count < ERRL_MAX_CALLOUTS)
                {
                    if(!l_err)
                    {
                        /* @
                         * @errortype
                         * @moduleid    AMEC_HEALTH_CHECK_DIMM_TIMEOUT
                         * @reasoncode  FRU_TEMP_TIMEOUT
                         * @userdata1   timeout value in seconds
                         * @userdata2   0
                         * @userdata4   ERC_AMEC_DIMM_TEMP_TIMEOUT
                         * @devdesc     Failed to read a memory DIMM temperature
                         *
                         */
                        l_err = createErrl(AMEC_HEALTH_CHECK_DIMM_TIMEOUT,    //modId
                                           FRU_TEMP_TIMEOUT,                  //reasoncode
                                           ERC_AMEC_DIMM_TEMP_TIMEOUT,        //Extended reason code
                                           ERRL_SEV_PREDICTIVE,               //Severity
                                           NULL,                              //Trace Buf
                                           DEFAULT_TRACE_SIZE,                //Trace Size
                                           g_amec->thermaldimm.temp_timeout,  //userdata1
                                           0);                                //userdata2
                    }

                    //Get the HUID for the DIMM and add callout
                    l_huid = amec_mem_get_huid(l_port, l_dimm);
                    addCalloutToErrl(l_err,
                                     ERRL_CALLOUT_TYPE_HUID,
                                     l_huid,
                                     ERRL_CALLOUT_PRIORITY_MED);

                    l_callouts_count++;
                }
            } //iterate over all dimms
            if(G_log_gpe1_error)
            {
                // Going to be resetting so no reason to check anymore ports
                break;
            }
        } //iterate over all ports

        if(l_err)
        {
            commitErrl(&l_err);
        }

        //skip clearing if no dimms need it
        if( (!l_need_clr.dw[0]) && (!l_need_clr.dw[1]) )
        {
            break;
        }

        //iterate across all centaurs/ports clearing dimm sensor timers as needed
        for(l_port = 0; l_port < l_max_port; l_port++)
        {

            if(!l_need_clr.bytes[l_port])
            {
                continue;
            }

            //iterate over all dimms
            for(l_dimm = 0; l_dimm < l_max_dimm_per_port; l_dimm++)
            {
                //not this one, go to next one
                if(!(l_need_clr.bytes[l_port] & (DIMM_SENSOR0 >> l_dimm)))
                {
                    continue;
                }

                //we found one.
                l_fru = &g_amec->proc[0].memctl[l_port].centaur.dimm_temps[l_dimm];

                //clear timer
                l_fru->sample_age = 0;

                // In Simics: the RTL timer is increased and a DIMM reading will not always
                // complete on each call.  Skip the "recovery" trace in Simics.
                if((L_ran_once) && (!G_simics_environment))
                {
                    TRAC_INFO("DIMM temperature collection has resumed for DIMM%04X temp[%d]",
                              (l_port<<8)|l_dimm, l_fru->cur_temp);
                }

            }//iterate over all dimms
        }//iterate over all centaurs/ports
    }while(0);
    L_ran_once = TRUE;

} // end amec_health_check_dimm_timeout()



/*
 * Function Specification
 *
 * Name: amec_health_check_cent_dimm_temp
 *
 * Description: Check if the centaur's dimm chips temperature exceeds the error
 *               temperature as defined in thermal control thresholds
 *              (ERROR field for Centaur FRU Type)
 *
 * End Function Specification
 */
void amec_health_check_cent_temp()
{
    /*------------------------------------------------------------------------*/
    /*  Local Variables                                                       */
    /*------------------------------------------------------------------------*/
    uint16_t                    l_ot_error, l_cur_temp, l_max_temp;
    sensor_t                    *l_sensor;
    uint32_t                    l_cent, l_max_mem_buf;
    uint32_t                    l_callouts_count = 0;
    uint16_t                    l_new_callouts;
    uint64_t                    l_huid;
    errlHndl_t                  l_err = NULL;

    /*------------------------------------------------------------------------*/
    /*  Code                                                                  */
    /*------------------------------------------------------------------------*/

    // Check to see if any centaurs have reached the error temperature that
    // haven't been called out already
    l_new_callouts = G_cent_overtemp_bitmap ^ G_cent_overtemp_logged_bitmap;
    if(!l_new_callouts)
    {
        return;
    }

    l_ot_error = g_amec->thermalcent.ot_error;
    l_sensor = getSensorByGsid(TEMPCENT);
    l_cur_temp = l_sensor->sample;
    l_max_temp = l_sensor->sample_max;
    TRAC_ERR("amec_health_check_cent_temp: Centaur reached error temp[%d]. current[%d], hist_max[%d], bitmap[0x%02X]",
             l_ot_error,
             l_cur_temp,
             l_max_temp,
             l_new_callouts);

    //find the centaur(s) that need to be called out
    if(G_sysConfigData.mem_type == MEM_TYPE_OCM)
    {
        l_max_mem_buf = MAX_NUM_OCMBS;
    }
    else // MEM_TYPE_CUMULUS
    {
        l_max_mem_buf = MAX_NUM_CENTAURS;
    }
    for(l_cent = 0; l_cent < l_max_mem_buf; l_cent++)
    {
        if(!(l_new_callouts & (CENTAUR0_PRESENT_MASK >> l_cent)))
        {
            continue;
        }

        l_huid = amec_mem_get_huid(l_cent, 0xff);

        amec_mem_mark_logged(l_cent,
                             0xff,
                             &G_cent_overtemp_logged_bitmap,
                             &G_dimm_overtemp_logged_bitmap.bytes[l_cent]);

        //If we don't have an error log for the callout, create one
        if(!l_err)
        {
            /* @
             * @errortype
             * @moduleid    AMEC_HEALTH_CHECK_CENT_TEMP
             * @reasoncode  CENT_ERROR_TEMP
             * @userdata1   Maximum centaur temperature
             * @userdata2   Centaur temperature threshold
             * @userdata4   OCC_NO_EXTENDED_RC
             * @devdesc     Centaur memory controller(s) exceeded maximum safe
             *              temperature.
             */
            l_err = createErrl(AMEC_HEALTH_CHECK_CENT_TEMP,    //modId
                               CENT_ERROR_TEMP,                //reasoncode
                               OCC_NO_EXTENDED_RC,             //Extended reason code
                               ERRL_SEV_PREDICTIVE,            //Severity
                               NULL,                           //Trace Buf
                               DEFAULT_TRACE_SIZE,             //Trace Size
                               l_max_temp,                     //userdata1
                               l_ot_error);                    //userdata2

            // Callout the "over temperature" procedure
            addCalloutToErrl(l_err,
                             ERRL_CALLOUT_TYPE_COMPONENT_ID,
                             ERRL_COMPONENT_ID_OVER_TEMPERATURE,
                             ERRL_CALLOUT_PRIORITY_HIGH);
            l_callouts_count = 1;
        }

        // Callout centaur
        addCalloutToErrl(l_err,
                         ERRL_CALLOUT_TYPE_HUID,
                         l_huid,
                         ERRL_CALLOUT_PRIORITY_MED);

        l_callouts_count++;

        //If we've reached the max # of callouts for an error log
        //commit the error log
        if(l_callouts_count == ERRL_MAX_CALLOUTS)
        {
            commitErrl(&l_err);
        }

    }//iterate over centaurs

    if(l_err)
    {
        commitErrl(&l_err);
    }
}

/*
 * Function Specification
 *
 * Name: amec_health_check_cent_timeout
 *
 * Description: Check for centaur timeout condition
 *              as defined in thermal control thresholds
 *              (MAX_READ_TIMEOUT field for Centaur FRU Type)
 *
 * End Function Specification
 */
void amec_health_check_cent_timeout()
{
    static uint16_t L_temp_update_bitmap_prev = 0;
    uint16_t l_need_inc, l_need_clr, l_temp_update_bitmap;
    uint16_t l_cent;
    fru_temp_t* l_fru;
    errlHndl_t  l_err = NULL;
    uint32_t    l_callouts_count = 0;
    uint64_t    l_huid;
    static bool L_ran_once = FALSE;

    do
    {
        //For every centaur sensor there are 3 cases to consider
        //
        //1) centaur is present and not updated (need to increment timer and check for timeout)
        //2) centaur is present and updated but wasn't updated on previous check (need to clear timer)
        //3) centaur is present and updated and was updated on previous check (do nothing)

        //Grab snapshot of G_cent_temp_update_bitmap and clear it
        l_temp_update_bitmap = G_cent_temp_updated_bitmap;
        G_cent_temp_updated_bitmap = 0;

        //check if we need to increment any timers
        l_need_inc = G_present_centaurs & ~l_temp_update_bitmap;

        //check if we need to clear any timers
        l_need_clr = l_temp_update_bitmap & ~L_temp_update_bitmap_prev;

        //only go further if we actually have work to do here.
        if(!l_need_inc && !l_need_clr)
        {
            //nothing to do
            break;
        }

        //save off the previous bitmap of updated sensors
        L_temp_update_bitmap_prev = l_temp_update_bitmap;

        //iterate across all centaurs incrementing timers as needed
        for(l_cent = 0; l_cent < MAX_NUM_CENTAURS; l_cent++)
        {
            //does this centaur timer need incrementing?
            if(!(l_need_inc & (CENTAUR0_PRESENT_MASK >> l_cent)))
            {
                //temperature was updated for this centaur. Clear the timeout bit for this centaur.
                if(G_cent_temp_expired_bitmap & (CENTAUR0_PRESENT_MASK >> l_cent))
                {
                    G_cent_temp_expired_bitmap &= ~(CENTAUR0_PRESENT_MASK >> l_cent);
                    TRAC_INFO("centaur %d temps have been updated", l_cent);
                }
                continue;
            }

            //This centaur requires an increment
            l_fru = &g_amec->proc[0].memctl[l_cent].centaur.centaur_hottest;

            //increment timer
            l_fru->sample_age++;

            //handle wrapping
            if(!l_fru->sample_age)
            {
                l_fru->sample_age = -1;
            }

            //info trace each transition to not having a new temperature
            if(l_fru->sample_age == 1)
            {
                TRAC_INFO("Failed to read centaur temperature on cent[%d] temp[%d] flags[0x%02X]",
                              l_cent, l_fru->cur_temp, l_fru->flags);
            }

            //check if the temperature reading is still useable
            if(g_amec->thermalcent.temp_timeout == 0xff ||
               l_fru->sample_age < g_amec->thermalcent.temp_timeout)
            {
                continue;
            }

            //temperature has expired.  Notify control algorithms which centaur.
            if(!(G_cent_temp_expired_bitmap & (CENTAUR0_PRESENT_MASK >> l_cent)))
            {
                G_cent_temp_expired_bitmap |= CENTAUR0_PRESENT_MASK >> l_cent;
                TRAC_ERR("Timed out reading centaur temperature sensor on cent %d",
                         l_cent);
            }

            //If we've already logged an error for this FRU go to the next one.
            if(G_cent_timeout_logged_bitmap & (CENTAUR0_PRESENT_MASK >> l_cent))
            {
                continue;
            }

            // To prevent Centaurs from incorrectly being called out, don't log errors if there have
            // been timeouts with GPE1 tasks not finishing
            if(G_error_history[ERRH_GPE1_NOT_IDLE] > g_amec->thermalcent.temp_timeout)
            {
                TRAC_ERR("Timed out reading centaur temperature due to GPE1 issues");
                // give notification that GPE1 error should now be logged which will reset the OCC
                G_log_gpe1_error = TRUE;
                // no reason to check anymore since all Centaurs are collected from the same GPE
                break;
            }

            TRAC_ERR("Timed out reading centaur temperature on cent[%d] temp[%d] flags[0x%02X]",
                     l_cent, l_fru->cur_temp, l_fru->flags);

            if(!l_err)
            {
                /* @
                 * @errortype
                 * @moduleid    AMEC_HEALTH_CHECK_CENT_TIMEOUT
                 * @reasoncode  FRU_TEMP_TIMEOUT
                 * @userdata1   timeout value in seconds
                 * @userdata2   0
                 * @userdata4   ERC_AMEC_CENT_TEMP_TIMEOUT
                 * @devdesc     Failed to read a centaur memory controller
                 *              temperature
                 *
                 */
                l_err = createErrl(AMEC_HEALTH_CHECK_CENT_TIMEOUT,    //modId
                                   FRU_TEMP_TIMEOUT,                  //reasoncode
                                   ERC_AMEC_CENT_TEMP_TIMEOUT,        //Extended reason code
                                   ERRL_SEV_PREDICTIVE,               //Severity
                                   NULL,                              //Trace Buf
                                   DEFAULT_TRACE_SIZE,                //Trace Size
                                   g_amec->thermalcent.temp_timeout,  //userdata1
                                   0);                                //userdata2

                l_callouts_count = 0;
            }

            //Get the HUID for the centaur
            l_huid = amec_mem_get_huid(l_cent, 0xff);

            // Callout centaur
            addCalloutToErrl(l_err,
                             ERRL_CALLOUT_TYPE_HUID,
                             l_huid,
                             ERRL_CALLOUT_PRIORITY_MED);

            l_callouts_count++;

            //If we've reached the max # of callouts for an error log
            //commit the error log
            if(l_callouts_count == ERRL_MAX_CALLOUTS)
            {
                commitErrl(&l_err);
            }

            //Mark centaur as logged so we don't log it more than once
            amec_mem_mark_logged(l_cent,
                                 0xff,
                                 &G_cent_timeout_logged_bitmap,
                                 &G_dimm_timeout_logged_bitmap.bytes[l_cent]);
        } //iterate over all centaurs

        if(l_err)
        {
            commitErrl(&l_err);
        }

        //skip clearing timers if no centaurs need it
        if(!l_need_clr)
        {
            break;
        }

        //iterate across all centaurs clearing timers as needed
        for(l_cent = 0; l_cent < MAX_NUM_CENTAURS; l_cent++)
        {
            //not this one, go to next one
            if(!(l_need_clr & (CENTAUR0_PRESENT_MASK >> l_cent)))
            {
                continue;
            }

            //we found one.
            l_fru = &g_amec->proc[0].memctl[l_cent].centaur.centaur_hottest;

            //clear timer
            l_fru->sample_age = 0;

            //info trace each time we recover
            if(L_ran_once)
            {
                TRAC_INFO("centaur temperature collection has resumed on cent[%d] temp[%d]",
                          l_cent, l_fru->cur_temp);
            }

        }//iterate over all centaurs
    }while(0);
    L_ran_once = TRUE;
}


// Function Specification
//
// Name:  amec_health_check_proc_temp
//
// Description: This function checks if the proc temperature has
// exceeded the error temperature as define in data format 0x13.
//
// End Function Specification
void amec_health_check_proc_temp()
{
    /*------------------------------------------------------------------------*/
    /*  Local Variables                                                       */
    /*------------------------------------------------------------------------*/
    uint16_t                    l_ot_error;
    static uint32_t             L_error_count = 0;
    static BOOLEAN              L_ot_error_logged = FALSE;
    sensor_t                    *l_sensor;
    errlHndl_t                  l_err = NULL;

    /*------------------------------------------------------------------------*/
    /*  Code                                                                  */
    /*------------------------------------------------------------------------*/
    do
    {
        // Get TEMPPROCTHRM sensor, which is hottest core temperature
        // in OCC processor
        l_sensor = getSensorByGsid(TEMPPROCTHRM);
        l_ot_error = g_amec->thermalproc.ot_error;

        // Check to see if we exceeded our error temperature
        if (l_sensor->sample > l_ot_error)
        {
            // Increment the error counter for this FRU
            L_error_count++;

            // Trace and log error the first time this occurs
            if (L_error_count == AMEC_HEALTH_ERROR_TIMER)
            {
                // Have we logged an OT error for this FRU already?
                if (L_ot_error_logged == TRUE)
                {
                    break;
                }

                L_ot_error_logged = TRUE;

                TRAC_ERR("amec_health_check_error_temp: processor has exceeded OT error! temp[%u] ot_error[%u]",
                         l_sensor->sample,
                         l_ot_error);

                // Log an OT error
                /* @
                 * @errortype
                 * @moduleid    AMEC_HEALTH_CHECK_PROC_TEMP
                 * @reasoncode  PROC_ERROR_TEMP
                 * @userdata1   0
                 * @userdata2   Fru peak temperature sensor
                 * @devdesc     Processor FRU has reached error temperature
                 *              threshold and is called out in this error log.
                 *
                 */
                l_err = createErrl(AMEC_HEALTH_CHECK_PROC_TEMP,
                                   PROC_ERROR_TEMP,
                                   ERC_AMEC_PROC_ERROR_OVER_TEMPERATURE,
                                   ERRL_SEV_PREDICTIVE,
                                   NULL,
                                   DEFAULT_TRACE_SIZE,
                                   0,
                                   l_sensor->sample_max);

                // Callout the Ambient procedure
                addCalloutToErrl(l_err,
                                 ERRL_CALLOUT_TYPE_COMPONENT_ID,
                                 ERRL_COMPONENT_ID_OVER_TEMPERATURE,
                                 ERRL_CALLOUT_PRIORITY_HIGH);

                // Callout to processor
                addCalloutToErrl(l_err,
                                 ERRL_CALLOUT_TYPE_HUID,
                                 G_sysConfigData.proc_huid,
                                 ERRL_CALLOUT_PRIORITY_MED);

                // Commit Error
                commitErrl(&l_err);
            }
        }
        else
        {
            // Trace that we have now dropped below the error threshold
            if (L_error_count >= AMEC_HEALTH_ERROR_TIMER)
            {
                TRAC_INFO("amec_health_check_proc_temp: We have dropped below error threshold for processors. error_count[%u]",
                          L_error_count);
            }

            // Reset the error counter for this FRU
            L_error_count = 0;
        }
    }while (0);

}

// Function Specification
//
// Name:  amec_health_check_proc_temp_timeout
//
// Description: This function checks if OCC has failed to read the processor
// temperature and if it has exceeded the maximum allowed number of retries.
//
// End Function Specification
void amec_health_check_proc_timeout()
{
    /*------------------------------------------------------------------------*/
    /*  Local Variables                                                       */
    /*------------------------------------------------------------------------*/
    errlHndl_t                  l_err = NULL;
    sensor_t                    *l_sensor = NULL;
    BOOLEAN                     l_core_fail_detected = FALSE;
    static uint32_t             L_read_fail_cnt = 0;
    uint8_t                     i = 0;
    uint8_t                     l_bad_core_index = 0;
    CoreData                    *l_core_data_ptr = NULL;

    /*------------------------------------------------------------------------*/
    /*  Code                                                                  */
    /*------------------------------------------------------------------------*/
    do
    {
        for(i=0; i<MAX_NUM_CORES; i++)
        {
            if(!CORE_PRESENT(i) || CORE_OFFLINE(i))
            {
                // If this core is not present, move on
                continue;
            }

            // Check if this core's temperature sensor has been updated
            l_sensor = AMECSENSOR_ARRAY_PTR(TEMPPROCTHRMC0,i);
            if (l_sensor->update_tag == G_core_temp_update_tag[i])
            {
                // If the update tag is not changing, then this core's
                // temperature sensor is not being updated.
                l_core_fail_detected = TRUE;
                l_bad_core_index = i;
            }

            // Take a snapshot of the update tag
            G_core_temp_update_tag[i] = l_sensor->update_tag;
        }

        // Have we found at least one core that has reading failures?
        if(!l_core_fail_detected)
        {
            // We were able to read all cores' temperature sensors so clear our
            // counter
            L_read_fail_cnt = 0;
        }
        else
        {
            // We've failed to read a core's temperature sensor so increment
            // our counter
            L_read_fail_cnt++;

            // Check if we have reached the maximum read time allowed
            if((L_read_fail_cnt == g_amec->thermalproc.temp_timeout) &&
               (g_amec->thermalproc.temp_timeout != 0xFF))
            {
                TRAC_ERR("Timed out reading processor temperature on core_index[%u]",
                         l_bad_core_index);

                // Get pointer to core data
                l_core_data_ptr = proc_get_bulk_core_data_ptr(l_bad_core_index);


                TRAC_ERR("Core Sensors[0x%04X%04X] Quad Sensor[0x%04X%04X]",
                         (uint16_t)(l_core_data_ptr->dts.core[0].result ),
                         (uint16_t)(l_core_data_ptr->dts.core[1].result ),
                         (uint16_t)(l_core_data_ptr->dts.cache[0].result),
                         (uint16_t)(l_core_data_ptr->dts.cache[1].result));

                /* @
                 * @errortype
                 * @moduleid    AMEC_HEALTH_CHECK_PROC_TIMEOUT
                 * @reasoncode  PROC_TEMP_TIMEOUT
                 * @userdata1   timeout value in seconds
                 * @userdata2   0
                 * @userdata4   OCC_NO_EXTENDED_RC
                 * @devdesc     Failed to read processor temperature.
                 *
                 */
                l_err = createErrl(AMEC_HEALTH_CHECK_PROC_TIMEOUT,    //modId
                                   PROC_TEMP_TIMEOUT,                 //reasoncode
                                   OCC_NO_EXTENDED_RC,                //Extended reason code
                                   ERRL_SEV_PREDICTIVE,               //Severity
                                   NULL,                              //Trace Buf
                                   DEFAULT_TRACE_SIZE,                //Trace Size
                                   g_amec->thermalproc.temp_timeout,  //userdata1
                                   0);                                //userdata2

                // Callout the processor
                addCalloutToErrl(l_err,
                                 ERRL_CALLOUT_TYPE_HUID,
                                 G_sysConfigData.proc_huid,
                                 ERRL_CALLOUT_PRIORITY_MED);

                // Commit error log and request reset
                REQUEST_RESET(l_err);
            }
        }
    }while(0);
}

// Function Specification
//
// Name:  amec_health_check_vrm_vdd_temp
//
// Description: This function checks if the VRM Vdd temperature has
// exceeded the error temperature sent in data format 0x13.
//
// End Function Specification
void amec_health_check_vrm_vdd_temp(const sensor_t *i_sensor)
{
    /*------------------------------------------------------------------------*/
    /*  Local Variables                                                       */
    /*------------------------------------------------------------------------*/
    uint16_t                    l_ot_error;
    static uint32_t             L_error_count = 0;
    static BOOLEAN              L_ot_error_logged = FALSE;
    errlHndl_t                  l_err = NULL;

    /*------------------------------------------------------------------------*/
    /*  Code                                                                  */
    /*------------------------------------------------------------------------*/
    do
    {
        l_ot_error = g_amec->thermalvdd.ot_error;

        // Check to see if we exceeded our error temperature
        if ((l_ot_error != 0) && (i_sensor->sample > l_ot_error))
        {
            // Increment the error counter for this FRU
            L_error_count++;

            // Trace and log error the first time this occurs
            if (L_error_count == AMEC_HEALTH_ERROR_TIMER)
            {
                // Have we logged an OT error for this FRU already?
                if (L_ot_error_logged == TRUE)
                {
                    break;
                }

                L_ot_error_logged = TRUE;

                TRAC_ERR("amec_health_check_vrm_vdd_temp: VRM vdd has exceeded OT error! temp[%u] ot_error[%u]",
                         i_sensor->sample,
                         l_ot_error);

                // Log an OT error
                /* @
                 * @errortype
                 * @moduleid    AMEC_HEALTH_CHECK_VRM_VDD_TEMP
                 * @reasoncode  VRM_VDD_ERROR_TEMP
                 * @userdata1   0
                 * @userdata2   Fru peak temperature sensor
                 * @devdesc     VRM Vdd has reached error temperature
                 *              threshold and is called out in this error log.
                 *
                 */
                l_err = createErrl(AMEC_HEALTH_CHECK_VRM_VDD_TEMP,
                                   VRM_VDD_ERROR_TEMP,
                                   ERC_AMEC_PROC_ERROR_OVER_TEMPERATURE,
                                   ERRL_SEV_PREDICTIVE,
                                   NULL,
                                   DEFAULT_TRACE_SIZE,
                                   0,
                                   i_sensor->sample_max);

                // Callout the Ambient procedure
                addCalloutToErrl(l_err,
                                 ERRL_CALLOUT_TYPE_COMPONENT_ID,
                                 ERRL_COMPONENT_ID_OVER_TEMPERATURE,
                                 ERRL_CALLOUT_PRIORITY_HIGH);

                // Callout VRM Vdd
                addCalloutToErrl(l_err,
                                 ERRL_CALLOUT_TYPE_HUID,
                                 G_sysConfigData.vrm_vdd_huid,
                                 ERRL_CALLOUT_PRIORITY_MED);

                // Commit Error
                commitErrl(&l_err);
            }
        }
        else
        {
            // Trace that we have now dropped below the error threshold
            if (L_error_count >= AMEC_HEALTH_ERROR_TIMER)
            {
                TRAC_INFO("amec_health_check_vrm_vdd_temp: VRM Vdd temp [%u] now below error temp [%u] after error_count [%u]",
                          i_sensor->sample, l_ot_error, L_error_count);
            }

            // Reset the error counter for this FRU
            L_error_count = 0;
        }
    }while (0);

}

// Function Specification
//
// Name:  amec_health_check_vrm_vdd_temp_timeout
//
// Description: This function checks if OCC has failed to read the VRM Vdd
// temperature and if it has exceeded the maximum allowed number of retries.
//
// End Function Specification
void amec_health_check_vrm_vdd_temp_timeout()
{
    /*------------------------------------------------------------------------*/
    /*  Local Variables                                                       */
    /*------------------------------------------------------------------------*/
    errlHndl_t                  l_err = NULL;
    uint32_t                    l_update_tag = 0;
    static uint32_t             L_read_fail_cnt = 0;
    static BOOLEAN              L_error_logged = FALSE;
    static uint32_t             L_vdd_temp_update_tag = 0;

    /*------------------------------------------------------------------------*/
    /*  Code                                                                  */
    /*------------------------------------------------------------------------*/

    // Check if VRM Vdd temperature sensor has been updated by checking the sensor update tag
    // If the update tag is not changing, then temperature sensor is not being updated.
    l_update_tag = AMECSENSOR_PTR(TEMPVDD)->update_tag;
    if (l_update_tag != L_vdd_temp_update_tag)
    {
        // We were able to read VRM Vdd temperature
        L_read_fail_cnt = 0;
        G_vrm_vdd_temp_expired = false;
        L_vdd_temp_update_tag = l_update_tag;
    }
    else
    {
        // Failed to read VRM Vdd temperature sensor
        L_read_fail_cnt++;

        // Check if we have reached the maximum read time allowed
        if((L_read_fail_cnt == g_amec->thermalvdd.temp_timeout) &&
           (g_amec->thermalvdd.temp_timeout != 0xFF))
        {
            //temperature has expired.  Notify control algorithms
            G_vrm_vdd_temp_expired = true;

            // Log error one time
            if (L_error_logged == FALSE)
            {
                L_error_logged = TRUE;

                TRAC_ERR("Timed out reading VRM Vdd temperature for timeout[%u]",
                          g_amec->thermalvdd.temp_timeout);

                /* @
                 * @errortype
                 * @moduleid    AMEC_HEALTH_CHECK_VRM_VDD_TIMEOUT
                 * @reasoncode  FRU_TEMP_TIMEOUT
                 * @userdata1   timeout value in seconds
                 * @userdata2   0
                 * @userdata4   ERC_AMEC_VRM_VDD_TEMP_TIMEOUT
                 * @devdesc     Failed to read VRM Vdd temperature.
                 *
                 */
                l_err = createErrl(AMEC_HEALTH_CHECK_VRM_VDD_TIMEOUT, //modId
                                   FRU_TEMP_TIMEOUT,                  //reasoncode
                                   ERC_AMEC_VRM_VDD_TEMP_TIMEOUT,     //Extended reason code
                                   ERRL_SEV_PREDICTIVE,               //Severity
                                   NULL,                              //Trace Buf
                                   DEFAULT_TRACE_SIZE,                //Trace Size
                                   g_amec->thermalvdd.temp_timeout,   //userdata1
                                   0);                                //userdata2

                // Callout the VRM
                addCalloutToErrl(l_err,
                                 ERRL_CALLOUT_TYPE_HUID,
                                 G_sysConfigData.vrm_vdd_huid,
                                 ERRL_CALLOUT_PRIORITY_MED);

                // Commit error log and request reset
                REQUEST_RESET(l_err);
            }
        } // if reached timeout
    } // else failed to read temp
}

/*----------------------------------------------------------------------------*/
/* End                                                                        */
/*----------------------------------------------------------------------------*/
OpenPOWER on IntegriCloud