summaryrefslogtreecommitdiff
path: root/src/cpu/simple/timing.cc
blob: b5450cf5fe76c98e5c0f79ba6555c77d778f1cdf (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
/*
 * Copyright 2014 Google, Inc.
 * Copyright (c) 2010-2013,2015,2017 ARM Limited
 * All rights reserved
 *
 * The license below extends only to copyright in the software and shall
 * not be construed as granting a license to any other intellectual
 * property including but not limited to intellectual property relating
 * to a hardware implementation of the functionality of the software
 * licensed hereunder.  You may use the software subject to the license
 * terms below provided that you ensure that this notice is replicated
 * unmodified and in its entirety in all distributions of the software,
 * modified or unmodified, in source code or in binary form.
 *
 * Copyright (c) 2002-2005 The Regents of The University of Michigan
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are
 * met: redistributions of source code must retain the above copyright
 * notice, this list of conditions and the following disclaimer;
 * redistributions in binary form must reproduce the above copyright
 * notice, this list of conditions and the following disclaimer in the
 * documentation and/or other materials provided with the distribution;
 * neither the name of the copyright holders nor the names of its
 * contributors may be used to endorse or promote products derived from
 * this software without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 *
 * Authors: Steve Reinhardt
 */

#include "cpu/simple/timing.hh"

#include "arch/locked_mem.hh"
#include "arch/mmapped_ipr.hh"
#include "arch/utility.hh"
#include "config/the_isa.hh"
#include "cpu/exetrace.hh"
#include "debug/Config.hh"
#include "debug/Drain.hh"
#include "debug/ExecFaulting.hh"
#include "debug/Mwait.hh"
#include "debug/SimpleCPU.hh"
#include "mem/packet.hh"
#include "mem/packet_access.hh"
#include "params/TimingSimpleCPU.hh"
#include "sim/faults.hh"
#include "sim/full_system.hh"
#include "sim/system.hh"

using namespace std;
using namespace TheISA;

void
TimingSimpleCPU::init()
{
    BaseSimpleCPU::init();
}

void
TimingSimpleCPU::TimingCPUPort::TickEvent::schedule(PacketPtr _pkt, Tick t)
{
    pkt = _pkt;
    cpu->schedule(this, t);
}

TimingSimpleCPU::TimingSimpleCPU(TimingSimpleCPUParams *p)
    : BaseSimpleCPU(p), fetchTranslation(this), icachePort(this),
      dcachePort(this), ifetch_pkt(NULL), dcache_pkt(NULL), previousCycle(0),
      fetchEvent([this]{ fetch(); }, name())
{
    _status = Idle;
}



TimingSimpleCPU::~TimingSimpleCPU()
{
}

DrainState
TimingSimpleCPU::drain()
{
    // Deschedule any power gating event (if any)
    deschedulePowerGatingEvent();

    if (switchedOut())
        return DrainState::Drained;

    if (_status == Idle ||
        (_status == BaseSimpleCPU::Running && isDrained())) {
        DPRINTF(Drain, "No need to drain.\n");
        activeThreads.clear();
        return DrainState::Drained;
    } else {
        DPRINTF(Drain, "Requesting drain.\n");

        // The fetch event can become descheduled if a drain didn't
        // succeed on the first attempt. We need to reschedule it if
        // the CPU is waiting for a microcode routine to complete.
        if (_status == BaseSimpleCPU::Running && !fetchEvent.scheduled())
            schedule(fetchEvent, clockEdge());

        return DrainState::Draining;
    }
}

void
TimingSimpleCPU::drainResume()
{
    assert(!fetchEvent.scheduled());
    if (switchedOut())
        return;

    DPRINTF(SimpleCPU, "Resume\n");
    verifyMemoryMode();

    assert(!threadContexts.empty());

    _status = BaseSimpleCPU::Idle;

    for (ThreadID tid = 0; tid < numThreads; tid++) {
        if (threadInfo[tid]->thread->status() == ThreadContext::Active) {
            threadInfo[tid]->notIdleFraction = 1;

            activeThreads.push_back(tid);

            _status = BaseSimpleCPU::Running;

            // Fetch if any threads active
            if (!fetchEvent.scheduled()) {
                schedule(fetchEvent, nextCycle());
            }
        } else {
            threadInfo[tid]->notIdleFraction = 0;
        }
    }

    // Reschedule any power gating event (if any)
    schedulePowerGatingEvent();

    system->totalNumInsts = 0;
}

bool
TimingSimpleCPU::tryCompleteDrain()
{
    if (drainState() != DrainState::Draining)
        return false;

    DPRINTF(Drain, "tryCompleteDrain.\n");
    if (!isDrained())
        return false;

    DPRINTF(Drain, "CPU done draining, processing drain event\n");
    signalDrainDone();

    return true;
}

void
TimingSimpleCPU::switchOut()
{
    SimpleExecContext& t_info = *threadInfo[curThread];
    M5_VAR_USED SimpleThread* thread = t_info.thread;

    BaseSimpleCPU::switchOut();

    assert(!fetchEvent.scheduled());
    assert(_status == BaseSimpleCPU::Running || _status == Idle);
    assert(!t_info.stayAtPC);
    assert(thread->microPC() == 0);

    updateCycleCounts();
    updateCycleCounters(BaseCPU::CPU_STATE_ON);
}


void
TimingSimpleCPU::takeOverFrom(BaseCPU *oldCPU)
{
    BaseSimpleCPU::takeOverFrom(oldCPU);

    previousCycle = curCycle();
}

void
TimingSimpleCPU::verifyMemoryMode() const
{
    if (!system->isTimingMode()) {
        fatal("The timing CPU requires the memory system to be in "
              "'timing' mode.\n");
    }
}

void
TimingSimpleCPU::activateContext(ThreadID thread_num)
{
    DPRINTF(SimpleCPU, "ActivateContext %d\n", thread_num);

    assert(thread_num < numThreads);

    threadInfo[thread_num]->notIdleFraction = 1;
    if (_status == BaseSimpleCPU::Idle)
        _status = BaseSimpleCPU::Running;

    // kick things off by initiating the fetch of the next instruction
    if (!fetchEvent.scheduled())
        schedule(fetchEvent, clockEdge(Cycles(0)));

    if (std::find(activeThreads.begin(), activeThreads.end(), thread_num)
         == activeThreads.end()) {
        activeThreads.push_back(thread_num);
    }

    BaseCPU::activateContext(thread_num);
}


void
TimingSimpleCPU::suspendContext(ThreadID thread_num)
{
    DPRINTF(SimpleCPU, "SuspendContext %d\n", thread_num);

    assert(thread_num < numThreads);
    activeThreads.remove(thread_num);

    if (_status == Idle)
        return;

    assert(_status == BaseSimpleCPU::Running);

    threadInfo[thread_num]->notIdleFraction = 0;

    if (activeThreads.empty()) {
        _status = Idle;

        if (fetchEvent.scheduled()) {
            deschedule(fetchEvent);
        }
    }

    BaseCPU::suspendContext(thread_num);
}

bool
TimingSimpleCPU::handleReadPacket(PacketPtr pkt)
{
    SimpleExecContext &t_info = *threadInfo[curThread];
    SimpleThread* thread = t_info.thread;

    const RequestPtr &req = pkt->req;

    // We're about the issues a locked load, so tell the monitor
    // to start caring about this address
    if (pkt->isRead() && pkt->req->isLLSC()) {
        TheISA::handleLockedRead(thread, pkt->req);
    }
    if (req->isMmappedIpr()) {
        Cycles delay = TheISA::handleIprRead(thread->getTC(), pkt);
        new IprEvent(pkt, this, clockEdge(delay));
        _status = DcacheWaitResponse;
        dcache_pkt = NULL;
    } else if (!dcachePort.sendTimingReq(pkt)) {
        _status = DcacheRetry;
        dcache_pkt = pkt;
    } else {
        _status = DcacheWaitResponse;
        // memory system takes ownership of packet
        dcache_pkt = NULL;
    }
    return dcache_pkt == NULL;
}

void
TimingSimpleCPU::sendData(const RequestPtr &req, uint8_t *data, uint64_t *res,
                          bool read)
{
    SimpleExecContext &t_info = *threadInfo[curThread];
    SimpleThread* thread = t_info.thread;

    PacketPtr pkt = buildPacket(req, read);
    pkt->dataDynamic<uint8_t>(data);
    if (req->getFlags().isSet(Request::NO_ACCESS)) {
        assert(!dcache_pkt);
        pkt->makeResponse();
        completeDataAccess(pkt);
    } else if (read) {
        handleReadPacket(pkt);
    } else {
        bool do_access = true;  // flag to suppress cache access

        if (req->isLLSC()) {
            do_access = TheISA::handleLockedWrite(thread, req, dcachePort.cacheBlockMask);
        } else if (req->isCondSwap()) {
            assert(res);
            req->setExtraData(*res);
        }

        if (do_access) {
            dcache_pkt = pkt;
            handleWritePacket();
            threadSnoop(pkt, curThread);
        } else {
            _status = DcacheWaitResponse;
            completeDataAccess(pkt);
        }
    }
}

void
TimingSimpleCPU::sendSplitData(const RequestPtr &req1, const RequestPtr &req2,
                               const RequestPtr &req, uint8_t *data, bool read)
{
    PacketPtr pkt1, pkt2;
    buildSplitPacket(pkt1, pkt2, req1, req2, req, data, read);
    if (req->getFlags().isSet(Request::NO_ACCESS)) {
        assert(!dcache_pkt);
        pkt1->makeResponse();
        completeDataAccess(pkt1);
    } else if (read) {
        SplitFragmentSenderState * send_state =
            dynamic_cast<SplitFragmentSenderState *>(pkt1->senderState);
        if (handleReadPacket(pkt1)) {
            send_state->clearFromParent();
            send_state = dynamic_cast<SplitFragmentSenderState *>(
                    pkt2->senderState);
            if (handleReadPacket(pkt2)) {
                send_state->clearFromParent();
            }
        }
    } else {
        dcache_pkt = pkt1;
        SplitFragmentSenderState * send_state =
            dynamic_cast<SplitFragmentSenderState *>(pkt1->senderState);
        if (handleWritePacket()) {
            send_state->clearFromParent();
            dcache_pkt = pkt2;
            send_state = dynamic_cast<SplitFragmentSenderState *>(
                    pkt2->senderState);
            if (handleWritePacket()) {
                send_state->clearFromParent();
            }
        }
    }
}

void
TimingSimpleCPU::translationFault(const Fault &fault)
{
    // fault may be NoFault in cases where a fault is suppressed,
    // for instance prefetches.
    updateCycleCounts();
    updateCycleCounters(BaseCPU::CPU_STATE_ON);

    if (traceData) {
        // Since there was a fault, we shouldn't trace this instruction.
        delete traceData;
        traceData = NULL;
    }

    postExecute();

    advanceInst(fault);
}

PacketPtr
TimingSimpleCPU::buildPacket(const RequestPtr &req, bool read)
{
    return read ? Packet::createRead(req) : Packet::createWrite(req);
}

void
TimingSimpleCPU::buildSplitPacket(PacketPtr &pkt1, PacketPtr &pkt2,
        const RequestPtr &req1, const RequestPtr &req2, const RequestPtr &req,
        uint8_t *data, bool read)
{
    pkt1 = pkt2 = NULL;

    assert(!req1->isMmappedIpr() && !req2->isMmappedIpr());

    if (req->getFlags().isSet(Request::NO_ACCESS)) {
        pkt1 = buildPacket(req, read);
        return;
    }

    pkt1 = buildPacket(req1, read);
    pkt2 = buildPacket(req2, read);

    PacketPtr pkt = new Packet(req, pkt1->cmd.responseCommand());

    pkt->dataDynamic<uint8_t>(data);
    pkt1->dataStatic<uint8_t>(data);
    pkt2->dataStatic<uint8_t>(data + req1->getSize());

    SplitMainSenderState * main_send_state = new SplitMainSenderState;
    pkt->senderState = main_send_state;
    main_send_state->fragments[0] = pkt1;
    main_send_state->fragments[1] = pkt2;
    main_send_state->outstanding = 2;
    pkt1->senderState = new SplitFragmentSenderState(pkt, 0);
    pkt2->senderState = new SplitFragmentSenderState(pkt, 1);
}

Fault
TimingSimpleCPU::readMem(Addr addr, uint8_t *data,
                         unsigned size, Request::Flags flags)
{
    panic("readMem() is for atomic accesses, and should "
          "never be called on TimingSimpleCPU.\n");
}

Fault
TimingSimpleCPU::initiateMemRead(Addr addr, unsigned size,
                                 Request::Flags flags)
{
    SimpleExecContext &t_info = *threadInfo[curThread];
    SimpleThread* thread = t_info.thread;

    Fault fault;
    const int asid = 0;
    const Addr pc = thread->instAddr();
    unsigned block_size = cacheLineSize();
    BaseTLB::Mode mode = BaseTLB::Read;

    if (traceData)
        traceData->setMem(addr, size, flags);

    RequestPtr req = std::make_shared<Request>(
        asid, addr, size, flags, dataMasterId(), pc,
        thread->contextId());

    req->taskId(taskId());

    Addr split_addr = roundDown(addr + size - 1, block_size);
    assert(split_addr <= addr || split_addr - addr < block_size);

    _status = DTBWaitResponse;
    if (split_addr > addr) {
        RequestPtr req1, req2;
        assert(!req->isLLSC() && !req->isSwap());
        req->splitOnVaddr(split_addr, req1, req2);

        WholeTranslationState *state =
            new WholeTranslationState(req, req1, req2, new uint8_t[size],
                                      NULL, mode);
        DataTranslation<TimingSimpleCPU *> *trans1 =
            new DataTranslation<TimingSimpleCPU *>(this, state, 0);
        DataTranslation<TimingSimpleCPU *> *trans2 =
            new DataTranslation<TimingSimpleCPU *>(this, state, 1);

        thread->dtb->translateTiming(req1, thread->getTC(), trans1, mode);
        thread->dtb->translateTiming(req2, thread->getTC(), trans2, mode);
    } else {
        WholeTranslationState *state =
            new WholeTranslationState(req, new uint8_t[size], NULL, mode);
        DataTranslation<TimingSimpleCPU *> *translation
            = new DataTranslation<TimingSimpleCPU *>(this, state);
        thread->dtb->translateTiming(req, thread->getTC(), translation, mode);
    }

    return NoFault;
}

bool
TimingSimpleCPU::handleWritePacket()
{
    SimpleExecContext &t_info = *threadInfo[curThread];
    SimpleThread* thread = t_info.thread;

    const RequestPtr &req = dcache_pkt->req;
    if (req->isMmappedIpr()) {
        Cycles delay = TheISA::handleIprWrite(thread->getTC(), dcache_pkt);
        new IprEvent(dcache_pkt, this, clockEdge(delay));
        _status = DcacheWaitResponse;
        dcache_pkt = NULL;
    } else if (!dcachePort.sendTimingReq(dcache_pkt)) {
        _status = DcacheRetry;
    } else {
        _status = DcacheWaitResponse;
        // memory system takes ownership of packet
        dcache_pkt = NULL;
    }
    return dcache_pkt == NULL;
}

Fault
TimingSimpleCPU::writeMem(uint8_t *data, unsigned size,
                          Addr addr, Request::Flags flags, uint64_t *res)
{
    SimpleExecContext &t_info = *threadInfo[curThread];
    SimpleThread* thread = t_info.thread;

    uint8_t *newData = new uint8_t[size];
    const int asid = 0;
    const Addr pc = thread->instAddr();
    unsigned block_size = cacheLineSize();
    BaseTLB::Mode mode = BaseTLB::Write;

    if (data == NULL) {
        assert(flags & Request::STORE_NO_DATA);
        // This must be a cache block cleaning request
        memset(newData, 0, size);
    } else {
        memcpy(newData, data, size);
    }

    if (traceData)
        traceData->setMem(addr, size, flags);

    RequestPtr req = std::make_shared<Request>(
        asid, addr, size, flags, dataMasterId(), pc,
        thread->contextId());

    req->taskId(taskId());

    Addr split_addr = roundDown(addr + size - 1, block_size);
    assert(split_addr <= addr || split_addr - addr < block_size);

    _status = DTBWaitResponse;
    if (split_addr > addr) {
        RequestPtr req1, req2;
        assert(!req->isLLSC() && !req->isSwap());
        req->splitOnVaddr(split_addr, req1, req2);

        WholeTranslationState *state =
            new WholeTranslationState(req, req1, req2, newData, res, mode);
        DataTranslation<TimingSimpleCPU *> *trans1 =
            new DataTranslation<TimingSimpleCPU *>(this, state, 0);
        DataTranslation<TimingSimpleCPU *> *trans2 =
            new DataTranslation<TimingSimpleCPU *>(this, state, 1);

        thread->dtb->translateTiming(req1, thread->getTC(), trans1, mode);
        thread->dtb->translateTiming(req2, thread->getTC(), trans2, mode);
    } else {
        WholeTranslationState *state =
            new WholeTranslationState(req, newData, res, mode);
        DataTranslation<TimingSimpleCPU *> *translation =
            new DataTranslation<TimingSimpleCPU *>(this, state);
        thread->dtb->translateTiming(req, thread->getTC(), translation, mode);
    }

    // Translation faults will be returned via finishTranslation()
    return NoFault;
}

void
TimingSimpleCPU::threadSnoop(PacketPtr pkt, ThreadID sender)
{
    for (ThreadID tid = 0; tid < numThreads; tid++) {
        if (tid != sender) {
            if (getCpuAddrMonitor(tid)->doMonitor(pkt)) {
                wakeup(tid);
            }
            TheISA::handleLockedSnoop(threadInfo[tid]->thread, pkt,
                    dcachePort.cacheBlockMask);
        }
    }
}

void
TimingSimpleCPU::finishTranslation(WholeTranslationState *state)
{
    _status = BaseSimpleCPU::Running;

    if (state->getFault() != NoFault) {
        if (state->isPrefetch()) {
            state->setNoFault();
        }
        delete [] state->data;
        state->deleteReqs();
        translationFault(state->getFault());
    } else {
        if (!state->isSplit) {
            sendData(state->mainReq, state->data, state->res,
                     state->mode == BaseTLB::Read);
        } else {
            sendSplitData(state->sreqLow, state->sreqHigh, state->mainReq,
                          state->data, state->mode == BaseTLB::Read);
        }
    }

    delete state;
}


void
TimingSimpleCPU::fetch()
{
    // Change thread if multi-threaded
    swapActiveThread();

    SimpleExecContext &t_info = *threadInfo[curThread];
    SimpleThread* thread = t_info.thread;

    DPRINTF(SimpleCPU, "Fetch\n");

    if (!curStaticInst || !curStaticInst->isDelayedCommit()) {
        checkForInterrupts();
        checkPcEventQueue();
    }

    // We must have just got suspended by a PC event
    if (_status == Idle)
        return;

    TheISA::PCState pcState = thread->pcState();
    bool needToFetch = !isRomMicroPC(pcState.microPC()) &&
                       !curMacroStaticInst;

    if (needToFetch) {
        _status = BaseSimpleCPU::Running;
        RequestPtr ifetch_req = std::make_shared<Request>();
        ifetch_req->taskId(taskId());
        ifetch_req->setContext(thread->contextId());
        setupFetchRequest(ifetch_req);
        DPRINTF(SimpleCPU, "Translating address %#x\n", ifetch_req->getVaddr());
        thread->itb->translateTiming(ifetch_req, thread->getTC(),
                &fetchTranslation, BaseTLB::Execute);
    } else {
        _status = IcacheWaitResponse;
        completeIfetch(NULL);

        updateCycleCounts();
        updateCycleCounters(BaseCPU::CPU_STATE_ON);
    }
}


void
TimingSimpleCPU::sendFetch(const Fault &fault, const RequestPtr &req,
                           ThreadContext *tc)
{
    if (fault == NoFault) {
        DPRINTF(SimpleCPU, "Sending fetch for addr %#x(pa: %#x)\n",
                req->getVaddr(), req->getPaddr());
        ifetch_pkt = new Packet(req, MemCmd::ReadReq);
        ifetch_pkt->dataStatic(&inst);
        DPRINTF(SimpleCPU, " -- pkt addr: %#x\n", ifetch_pkt->getAddr());

        if (!icachePort.sendTimingReq(ifetch_pkt)) {
            // Need to wait for retry
            _status = IcacheRetry;
        } else {
            // Need to wait for cache to respond
            _status = IcacheWaitResponse;
            // ownership of packet transferred to memory system
            ifetch_pkt = NULL;
        }
    } else {
        DPRINTF(SimpleCPU, "Translation of addr %#x faulted\n", req->getVaddr());
        // fetch fault: advance directly to next instruction (fault handler)
        _status = BaseSimpleCPU::Running;
        advanceInst(fault);
    }

    updateCycleCounts();
    updateCycleCounters(BaseCPU::CPU_STATE_ON);
}


void
TimingSimpleCPU::advanceInst(const Fault &fault)
{
    SimpleExecContext &t_info = *threadInfo[curThread];

    if (_status == Faulting)
        return;

    if (fault != NoFault) {
        DPRINTF(SimpleCPU, "Fault occured. Handling the fault\n");

        advancePC(fault);

        // A syscall fault could suspend this CPU (e.g., futex_wait)
        // If the _status is not Idle, schedule an event to fetch the next
        // instruction after 'stall' ticks.
        // If the cpu has been suspended (i.e., _status == Idle), another
        // cpu will wake this cpu up later.
        if (_status != Idle) {
            DPRINTF(SimpleCPU, "Scheduling fetch event after the Fault\n");

            Tick stall = dynamic_pointer_cast<SyscallRetryFault>(fault) ?
                         clockEdge(syscallRetryLatency) : clockEdge();
            reschedule(fetchEvent, stall, true);
            _status = Faulting;
        }

        return;
    }

    if (!t_info.stayAtPC)
        advancePC(fault);

    if (tryCompleteDrain())
        return;

    if (_status == BaseSimpleCPU::Running) {
        // kick off fetch of next instruction... callback from icache
        // response will cause that instruction to be executed,
        // keeping the CPU running.
        fetch();
    }
}


void
TimingSimpleCPU::completeIfetch(PacketPtr pkt)
{
    SimpleExecContext& t_info = *threadInfo[curThread];

    DPRINTF(SimpleCPU, "Complete ICache Fetch for addr %#x\n", pkt ?
            pkt->getAddr() : 0);

    // received a response from the icache: execute the received
    // instruction
    assert(!pkt || !pkt->isError());
    assert(_status == IcacheWaitResponse);

    _status = BaseSimpleCPU::Running;

    updateCycleCounts();
    updateCycleCounters(BaseCPU::CPU_STATE_ON);

    if (pkt)
        pkt->req->setAccessLatency();


    preExecute();
    if (curStaticInst && curStaticInst->isMemRef()) {
        // load or store: just send to dcache
        Fault fault = curStaticInst->initiateAcc(&t_info, traceData);

        // If we're not running now the instruction will complete in a dcache
        // response callback or the instruction faulted and has started an
        // ifetch
        if (_status == BaseSimpleCPU::Running) {
            if (fault != NoFault && traceData) {
                // If there was a fault, we shouldn't trace this instruction.
                delete traceData;
                traceData = NULL;
            }

            postExecute();
            // @todo remove me after debugging with legion done
            if (curStaticInst && (!curStaticInst->isMicroop() ||
                        curStaticInst->isFirstMicroop()))
                instCnt++;
            advanceInst(fault);
        }
    } else if (curStaticInst) {
        // non-memory instruction: execute completely now
        Fault fault = curStaticInst->execute(&t_info, traceData);

        // keep an instruction count
        if (fault == NoFault)
            countInst();
        else if (traceData && !DTRACE(ExecFaulting)) {
            delete traceData;
            traceData = NULL;
        }

        postExecute();
        // @todo remove me after debugging with legion done
        if (curStaticInst && (!curStaticInst->isMicroop() ||
                curStaticInst->isFirstMicroop()))
            instCnt++;
        advanceInst(fault);
    } else {
        advanceInst(NoFault);
    }

    if (pkt) {
        delete pkt;
    }
}

void
TimingSimpleCPU::IcachePort::ITickEvent::process()
{
    cpu->completeIfetch(pkt);
}

bool
TimingSimpleCPU::IcachePort::recvTimingResp(PacketPtr pkt)
{
    DPRINTF(SimpleCPU, "Received fetch response %#x\n", pkt->getAddr());
    // we should only ever see one response per cycle since we only
    // issue a new request once this response is sunk
    assert(!tickEvent.scheduled());
    // delay processing of returned data until next CPU clock edge
    tickEvent.schedule(pkt, cpu->clockEdge());

    return true;
}

void
TimingSimpleCPU::IcachePort::recvReqRetry()
{
    // we shouldn't get a retry unless we have a packet that we're
    // waiting to transmit
    assert(cpu->ifetch_pkt != NULL);
    assert(cpu->_status == IcacheRetry);
    PacketPtr tmp = cpu->ifetch_pkt;
    if (sendTimingReq(tmp)) {
        cpu->_status = IcacheWaitResponse;
        cpu->ifetch_pkt = NULL;
    }
}

void
TimingSimpleCPU::completeDataAccess(PacketPtr pkt)
{
    // received a response from the dcache: complete the load or store
    // instruction
    assert(!pkt->isError());
    assert(_status == DcacheWaitResponse || _status == DTBWaitResponse ||
           pkt->req->getFlags().isSet(Request::NO_ACCESS));

    pkt->req->setAccessLatency();

    updateCycleCounts();
    updateCycleCounters(BaseCPU::CPU_STATE_ON);

    if (pkt->senderState) {
        SplitFragmentSenderState * send_state =
            dynamic_cast<SplitFragmentSenderState *>(pkt->senderState);
        assert(send_state);
        delete pkt;
        PacketPtr big_pkt = send_state->bigPkt;
        delete send_state;

        SplitMainSenderState * main_send_state =
            dynamic_cast<SplitMainSenderState *>(big_pkt->senderState);
        assert(main_send_state);
        // Record the fact that this packet is no longer outstanding.
        assert(main_send_state->outstanding != 0);
        main_send_state->outstanding--;

        if (main_send_state->outstanding) {
            return;
        } else {
            delete main_send_state;
            big_pkt->senderState = NULL;
            pkt = big_pkt;
        }
    }

    _status = BaseSimpleCPU::Running;

    Fault fault = curStaticInst->completeAcc(pkt, threadInfo[curThread],
                                             traceData);

    // keep an instruction count
    if (fault == NoFault)
        countInst();
    else if (traceData) {
        // If there was a fault, we shouldn't trace this instruction.
        delete traceData;
        traceData = NULL;
    }

    delete pkt;

    postExecute();

    advanceInst(fault);
}

void
TimingSimpleCPU::updateCycleCounts()
{
    const Cycles delta(curCycle() - previousCycle);

    numCycles += delta;

    previousCycle = curCycle();
}

void
TimingSimpleCPU::DcachePort::recvTimingSnoopReq(PacketPtr pkt)
{
    for (ThreadID tid = 0; tid < cpu->numThreads; tid++) {
        if (cpu->getCpuAddrMonitor(tid)->doMonitor(pkt)) {
            cpu->wakeup(tid);
        }
    }

    // Making it uniform across all CPUs:
    // The CPUs need to be woken up only on an invalidation packet (when using caches)
    // or on an incoming write packet (when not using caches)
    // It is not necessary to wake up the processor on all incoming packets
    if (pkt->isInvalidate() || pkt->isWrite()) {
        for (auto &t_info : cpu->threadInfo) {
            TheISA::handleLockedSnoop(t_info->thread, pkt, cacheBlockMask);
        }
    }
}

void
TimingSimpleCPU::DcachePort::recvFunctionalSnoop(PacketPtr pkt)
{
    for (ThreadID tid = 0; tid < cpu->numThreads; tid++) {
        if (cpu->getCpuAddrMonitor(tid)->doMonitor(pkt)) {
            cpu->wakeup(tid);
        }
    }
}

bool
TimingSimpleCPU::DcachePort::recvTimingResp(PacketPtr pkt)
{
    DPRINTF(SimpleCPU, "Received load/store response %#x\n", pkt->getAddr());

    // The timing CPU is not really ticked, instead it relies on the
    // memory system (fetch and load/store) to set the pace.
    if (!tickEvent.scheduled()) {
        // Delay processing of returned data until next CPU clock edge
        tickEvent.schedule(pkt, cpu->clockEdge());
        return true;
    } else {
        // In the case of a split transaction and a cache that is
        // faster than a CPU we could get two responses in the
        // same tick, delay the second one
        if (!retryRespEvent.scheduled())
            cpu->schedule(retryRespEvent, cpu->clockEdge(Cycles(1)));
        return false;
    }
}

void
TimingSimpleCPU::DcachePort::DTickEvent::process()
{
    cpu->completeDataAccess(pkt);
}

void
TimingSimpleCPU::DcachePort::recvReqRetry()
{
    // we shouldn't get a retry unless we have a packet that we're
    // waiting to transmit
    assert(cpu->dcache_pkt != NULL);
    assert(cpu->_status == DcacheRetry);
    PacketPtr tmp = cpu->dcache_pkt;
    if (tmp->senderState) {
        // This is a packet from a split access.
        SplitFragmentSenderState * send_state =
            dynamic_cast<SplitFragmentSenderState *>(tmp->senderState);
        assert(send_state);
        PacketPtr big_pkt = send_state->bigPkt;

        SplitMainSenderState * main_send_state =
            dynamic_cast<SplitMainSenderState *>(big_pkt->senderState);
        assert(main_send_state);

        if (sendTimingReq(tmp)) {
            // If we were able to send without retrying, record that fact
            // and try sending the other fragment.
            send_state->clearFromParent();
            int other_index = main_send_state->getPendingFragment();
            if (other_index > 0) {
                tmp = main_send_state->fragments[other_index];
                cpu->dcache_pkt = tmp;
                if ((big_pkt->isRead() && cpu->handleReadPacket(tmp)) ||
                        (big_pkt->isWrite() && cpu->handleWritePacket())) {
                    main_send_state->fragments[other_index] = NULL;
                }
            } else {
                cpu->_status = DcacheWaitResponse;
                // memory system takes ownership of packet
                cpu->dcache_pkt = NULL;
            }
        }
    } else if (sendTimingReq(tmp)) {
        cpu->_status = DcacheWaitResponse;
        // memory system takes ownership of packet
        cpu->dcache_pkt = NULL;
    }
}

TimingSimpleCPU::IprEvent::IprEvent(Packet *_pkt, TimingSimpleCPU *_cpu,
    Tick t)
    : pkt(_pkt), cpu(_cpu)
{
    cpu->schedule(this, t);
}

void
TimingSimpleCPU::IprEvent::process()
{
    cpu->completeDataAccess(pkt);
}

const char *
TimingSimpleCPU::IprEvent::description() const
{
    return "Timing Simple CPU Delay IPR event";
}


void
TimingSimpleCPU::printAddr(Addr a)
{
    dcachePort.printAddr(a);
}


////////////////////////////////////////////////////////////////////////
//
//  TimingSimpleCPU Simulation Object
//
TimingSimpleCPU *
TimingSimpleCPUParams::create()
{
    return new TimingSimpleCPU(this);
}