forked from hrydgard/ppsspp
-
Notifications
You must be signed in to change notification settings - Fork 0
/
GPUCommon.cpp
1585 lines (1359 loc) · 44.4 KB
/
GPUCommon.cpp
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
#include <algorithm>
#include <type_traits>
#include "base/mutex.h"
#include "base/timeutil.h"
#include "Common/ColorConv.h"
#include "GPU/GeDisasm.h"
#include "GPU/GPU.h"
#include "GPU/GPUCommon.h"
#include "GPU/GPUState.h"
#include "ChunkFile.h"
#include "Core/Config.h"
#include "Core/CoreTiming.h"
#include "Core/MemMap.h"
#include "Core/Host.h"
#include "Core/Reporting.h"
#include "Core/HLE/HLE.h"
#include "Core/HLE/sceKernelMemory.h"
#include "Core/HLE/sceKernelInterrupt.h"
#include "Core/HLE/sceKernelThread.h"
#include "Core/HLE/sceGe.h"
#include "Core/Debugger/Breakpoints.h"
#include "Core/MemMapHelpers.h"
#include "GPU/Common/FramebufferCommon.h"
#include "GPU/Common/TextureCacheCommon.h"
GPUCommon::GPUCommon() :
dumpNextFrame_(false),
dumpThisFrame_(false),
framebufferManager_(nullptr),
resized_(false)
{
// This assert failed on GCC x86 32-bit (but not MSVC 32-bit!) before adding the
// "padding" field at the end. This is important for save state compatibility.
// The compiler was not rounding the struct size up to an 8 byte boundary, which
// you'd expect due to the int64 field, but the Linux ABI apparently does not require that.
static_assert(sizeof(DisplayList) == 456, "Bad DisplayList size");
Reinitialize();
SetupColorConv();
SetThreadEnabled(g_Config.bSeparateCPUThread);
gstate.Reset();
gstate_c.Reset();
gpuStats.Reset();
}
GPUCommon::~GPUCommon() {
delete framebufferManager_;
}
void GPUCommon::BeginHostFrame() {
ReapplyGfxState();
}
void GPUCommon::EndHostFrame() {
}
void GPUCommon::InitClear() {
ScheduleEvent(GPU_EVENT_INIT_CLEAR);
}
void GPUCommon::CopyDisplayToOutput() {
ScheduleEvent(GPU_EVENT_COPY_DISPLAY_TO_OUTPUT);
}
void GPUCommon::Reinitialize() {
easy_guard guard(listLock);
memset(dls, 0, sizeof(dls));
for (int i = 0; i < DisplayListMaxCount; ++i) {
dls[i].state = PSP_GE_DL_STATE_NONE;
dls[i].waitTicks = 0;
}
nextListID = 0;
currentList = NULL;
isbreak = false;
drawCompleteTicks = 0;
busyTicks = 0;
timeSpentStepping_ = 0.0;
interruptsEnabled_ = true;
UpdateTickEstimate(0);
ScheduleEvent(GPU_EVENT_REINITIALIZE);
}
void GPUCommon::PopDLQueue() {
easy_guard guard(listLock);
if(!dlQueue.empty()) {
dlQueue.pop_front();
if(!dlQueue.empty()) {
bool running = currentList->state == PSP_GE_DL_STATE_RUNNING;
currentList = &dls[dlQueue.front()];
if (running)
currentList->state = PSP_GE_DL_STATE_RUNNING;
} else {
currentList = NULL;
}
}
}
bool GPUCommon::BusyDrawing() {
u32 state = DrawSync(1);
if (state == PSP_GE_LIST_DRAWING || state == PSP_GE_LIST_STALLING) {
lock_guard guard(listLock);
if (currentList && currentList->state != PSP_GE_DL_STATE_PAUSED) {
return true;
}
}
return false;
}
void GPUCommon::Resized() {
resized_ = true;
framebufferManager_->Resized();
}
u32 GPUCommon::DrawSync(int mode) {
if (ThreadEnabled()) {
// Sync first, because the CPU is usually faster than the emulated GPU.
SyncThread();
}
easy_guard guard(listLock);
if (mode < 0 || mode > 1)
return SCE_KERNEL_ERROR_INVALID_MODE;
if (mode == 0) {
if (!__KernelIsDispatchEnabled()) {
return SCE_KERNEL_ERROR_CAN_NOT_WAIT;
}
if (__IsInInterrupt()) {
return SCE_KERNEL_ERROR_ILLEGAL_CONTEXT;
}
if (drawCompleteTicks > CoreTiming::GetTicks()) {
__GeWaitCurrentThread(GPU_SYNC_DRAW, 1, "GeDrawSync");
} else {
for (int i = 0; i < DisplayListMaxCount; ++i) {
if (dls[i].state == PSP_GE_DL_STATE_COMPLETED) {
dls[i].state = PSP_GE_DL_STATE_NONE;
}
}
}
return 0;
}
// If there's no current list, it must be complete.
DisplayList *top = NULL;
for (auto it = dlQueue.begin(), end = dlQueue.end(); it != end; ++it) {
if (dls[*it].state != PSP_GE_DL_STATE_COMPLETED) {
top = &dls[*it];
break;
}
}
if (!top || top->state == PSP_GE_DL_STATE_COMPLETED)
return PSP_GE_LIST_COMPLETED;
if (currentList->pc == currentList->stall)
return PSP_GE_LIST_STALLING;
return PSP_GE_LIST_DRAWING;
}
void GPUCommon::CheckDrawSync() {
easy_guard guard(listLock);
if (dlQueue.empty()) {
for (int i = 0; i < DisplayListMaxCount; ++i)
dls[i].state = PSP_GE_DL_STATE_NONE;
}
}
int GPUCommon::ListSync(int listid, int mode) {
if (ThreadEnabled()) {
// Sync first, because the CPU is usually faster than the emulated GPU.
SyncThread();
}
easy_guard guard(listLock);
if (listid < 0 || listid >= DisplayListMaxCount)
return SCE_KERNEL_ERROR_INVALID_ID;
if (mode < 0 || mode > 1)
return SCE_KERNEL_ERROR_INVALID_MODE;
DisplayList& dl = dls[listid];
if (mode == 1) {
switch (dl.state) {
case PSP_GE_DL_STATE_QUEUED:
if (dl.interrupted)
return PSP_GE_LIST_PAUSED;
return PSP_GE_LIST_QUEUED;
case PSP_GE_DL_STATE_RUNNING:
if (dl.pc == dl.stall)
return PSP_GE_LIST_STALLING;
return PSP_GE_LIST_DRAWING;
case PSP_GE_DL_STATE_COMPLETED:
return PSP_GE_LIST_COMPLETED;
case PSP_GE_DL_STATE_PAUSED:
return PSP_GE_LIST_PAUSED;
default:
return SCE_KERNEL_ERROR_INVALID_ID;
}
}
if (!__KernelIsDispatchEnabled()) {
return SCE_KERNEL_ERROR_CAN_NOT_WAIT;
}
if (__IsInInterrupt()) {
return SCE_KERNEL_ERROR_ILLEGAL_CONTEXT;
}
if (dl.waitTicks > CoreTiming::GetTicks()) {
__GeWaitCurrentThread(GPU_SYNC_LIST, listid, "GeListSync");
}
return PSP_GE_LIST_COMPLETED;
}
int GPUCommon::GetStack(int index, u32 stackPtr) {
easy_guard guard(listLock);
if (currentList == NULL) {
// Seems like it doesn't return an error code?
return 0;
}
if (currentList->stackptr <= index) {
return SCE_KERNEL_ERROR_INVALID_INDEX;
}
if (index >= 0) {
auto stack = PSPPointer<u32>::Create(stackPtr);
if (stack.IsValid()) {
auto entry = currentList->stack[index];
// Not really sure what most of these values are.
stack[0] = 0;
stack[1] = entry.pc + 4;
stack[2] = entry.offsetAddr;
stack[7] = entry.baseAddr;
}
}
return currentList->stackptr;
}
u32 GPUCommon::EnqueueList(u32 listpc, u32 stall, int subIntrBase, PSPPointer<PspGeListArgs> args, bool head) {
easy_guard guard(listLock);
// TODO Check the stack values in missing arg and ajust the stack depth
// Check alignment
// TODO Check the context and stack alignement too
if (((listpc | stall) & 3) != 0)
return SCE_KERNEL_ERROR_INVALID_POINTER;
int id = -1;
u64 currentTicks = CoreTiming::GetTicks();
u32_le stackAddr = args.IsValid() ? args->stackAddr : 0;
// Check compatibility
if (sceKernelGetCompiledSdkVersion() > 0x01FFFFFF) {
//numStacks = 0;
//stack = NULL;
for (int i = 0; i < DisplayListMaxCount; ++i) {
if (dls[i].state != PSP_GE_DL_STATE_NONE && dls[i].state != PSP_GE_DL_STATE_COMPLETED) {
// Logically, if the CPU has not interrupted yet, it hasn't seen the latest pc either.
// Exit enqueues right after an END, which fails without ignoring pendingInterrupt lists.
if (dls[i].pc == listpc && !dls[i].pendingInterrupt) {
ERROR_LOG(G3D, "sceGeListEnqueue: can't enqueue, list address %08X already used", listpc);
return 0x80000021;
} else if (stackAddr != 0 && dls[i].stackAddr == stackAddr && !dls[i].pendingInterrupt) {
ERROR_LOG(G3D, "sceGeListEnqueue: can't enqueue, stack address %08X already used", stackAddr);
return 0x80000021;
}
}
}
}
// TODO Check if list stack dls[i].stack already used then return 0x80000021 as above
for (int i = 0; i < DisplayListMaxCount; ++i) {
int possibleID = (i + nextListID) % DisplayListMaxCount;
auto possibleList = dls[possibleID];
if (possibleList.pendingInterrupt) {
continue;
}
if (possibleList.state == PSP_GE_DL_STATE_NONE) {
id = possibleID;
break;
}
if (possibleList.state == PSP_GE_DL_STATE_COMPLETED && possibleList.waitTicks < currentTicks) {
id = possibleID;
}
}
if (id < 0) {
ERROR_LOG_REPORT(G3D, "No DL ID available to enqueue");
for (auto it = dlQueue.begin(); it != dlQueue.end(); ++it) {
DisplayList &dl = dls[*it];
DEBUG_LOG(G3D, "DisplayList %d status %d pc %08x stall %08x", *it, dl.state, dl.pc, dl.stall);
}
return SCE_KERNEL_ERROR_OUT_OF_MEMORY;
}
nextListID = id + 1;
DisplayList &dl = dls[id];
dl.id = id;
dl.startpc = listpc & 0x0FFFFFFF;
dl.pc = listpc & 0x0FFFFFFF;
dl.stall = stall & 0x0FFFFFFF;
dl.subIntrBase = std::max(subIntrBase, -1);
dl.stackptr = 0;
dl.signal = PSP_GE_SIGNAL_NONE;
dl.interrupted = false;
dl.waitTicks = (u64)-1;
dl.interruptsEnabled = interruptsEnabled_;
dl.started = false;
dl.offsetAddr = 0;
dl.bboxResult = false;
dl.stackAddr = stackAddr;
if (args.IsValid() && args->context.IsValid())
dl.context = args->context;
else
dl.context = 0;
if (head) {
if (currentList) {
if (currentList->state != PSP_GE_DL_STATE_PAUSED)
return SCE_KERNEL_ERROR_INVALID_VALUE;
currentList->state = PSP_GE_DL_STATE_QUEUED;
}
dl.state = PSP_GE_DL_STATE_PAUSED;
currentList = &dl;
dlQueue.push_front(id);
} else if (currentList) {
dl.state = PSP_GE_DL_STATE_QUEUED;
dlQueue.push_back(id);
} else {
dl.state = PSP_GE_DL_STATE_RUNNING;
currentList = &dl;
dlQueue.push_front(id);
drawCompleteTicks = (u64)-1;
// TODO save context when starting the list if param is set
guard.unlock();
ProcessDLQueue();
}
return id;
}
u32 GPUCommon::DequeueList(int listid) {
easy_guard guard(listLock);
if (listid < 0 || listid >= DisplayListMaxCount || dls[listid].state == PSP_GE_DL_STATE_NONE)
return SCE_KERNEL_ERROR_INVALID_ID;
auto &dl = dls[listid];
if (dl.started)
return SCE_KERNEL_ERROR_BUSY;
dl.state = PSP_GE_DL_STATE_NONE;
if (listid == dlQueue.front())
PopDLQueue();
else
dlQueue.remove(listid);
dl.waitTicks = 0;
__GeTriggerWait(GPU_SYNC_LIST, listid);
CheckDrawSync();
return 0;
}
u32 GPUCommon::UpdateStall(int listid, u32 newstall) {
easy_guard guard(listLock);
if (listid < 0 || listid >= DisplayListMaxCount || dls[listid].state == PSP_GE_DL_STATE_NONE)
return SCE_KERNEL_ERROR_INVALID_ID;
auto &dl = dls[listid];
if (dl.state == PSP_GE_DL_STATE_COMPLETED)
return SCE_KERNEL_ERROR_ALREADY;
dl.stall = newstall & 0x0FFFFFFF;
guard.unlock();
ProcessDLQueue();
return 0;
}
u32 GPUCommon::Continue() {
easy_guard guard(listLock);
if (!currentList)
return 0;
if (currentList->state == PSP_GE_DL_STATE_PAUSED)
{
if (!isbreak)
{
// TODO: Supposedly this returns SCE_KERNEL_ERROR_BUSY in some case, previously it had
// currentList->signal == PSP_GE_SIGNAL_HANDLER_PAUSE, but it doesn't reproduce.
currentList->state = PSP_GE_DL_STATE_RUNNING;
currentList->signal = PSP_GE_SIGNAL_NONE;
// TODO Restore context of DL is necessary
// TODO Restore BASE
// We have a list now, so it's not complete.
drawCompleteTicks = (u64)-1;
}
else
currentList->state = PSP_GE_DL_STATE_QUEUED;
}
else if (currentList->state == PSP_GE_DL_STATE_RUNNING)
{
if (sceKernelGetCompiledSdkVersion() >= 0x02000000)
return 0x80000020;
return -1;
}
else
{
if (sceKernelGetCompiledSdkVersion() >= 0x02000000)
return 0x80000004;
return -1;
}
guard.unlock();
ProcessDLQueue();
return 0;
}
u32 GPUCommon::Break(int mode) {
easy_guard guard(listLock);
if (mode < 0 || mode > 1)
return SCE_KERNEL_ERROR_INVALID_MODE;
if (!currentList)
return SCE_KERNEL_ERROR_ALREADY;
if (mode == 1)
{
// Clear the queue
dlQueue.clear();
for (int i = 0; i < DisplayListMaxCount; ++i)
{
dls[i].state = PSP_GE_DL_STATE_NONE;
dls[i].signal = PSP_GE_SIGNAL_NONE;
}
nextListID = 0;
currentList = NULL;
return 0;
}
if (currentList->state == PSP_GE_DL_STATE_NONE || currentList->state == PSP_GE_DL_STATE_COMPLETED)
{
if (sceKernelGetCompiledSdkVersion() >= 0x02000000)
return 0x80000004;
return -1;
}
if (currentList->state == PSP_GE_DL_STATE_PAUSED)
{
if (sceKernelGetCompiledSdkVersion() > 0x02000010)
{
if (currentList->signal == PSP_GE_SIGNAL_HANDLER_PAUSE)
{
ERROR_LOG_REPORT(G3D, "sceGeBreak: can't break signal-pausing list");
}
else
return SCE_KERNEL_ERROR_ALREADY;
}
return SCE_KERNEL_ERROR_BUSY;
}
if (currentList->state == PSP_GE_DL_STATE_QUEUED)
{
currentList->state = PSP_GE_DL_STATE_PAUSED;
return currentList->id;
}
// TODO Save BASE
// TODO Adjust pc to be just before SIGNAL/END
// TODO: Is this right?
if (currentList->signal == PSP_GE_SIGNAL_SYNC)
currentList->pc += 8;
currentList->interrupted = true;
currentList->state = PSP_GE_DL_STATE_PAUSED;
currentList->signal = PSP_GE_SIGNAL_HANDLER_SUSPEND;
isbreak = true;
return currentList->id;
}
void GPUCommon::NotifySteppingEnter() {
if (g_Config.bShowDebugStats) {
time_update();
timeSteppingStarted_ = time_now_d();
}
}
void GPUCommon::NotifySteppingExit() {
if (g_Config.bShowDebugStats) {
if (timeSteppingStarted_ <= 0.0) {
ERROR_LOG(G3D, "Mismatched stepping enter/exit.");
}
time_update();
timeSpentStepping_ += time_now_d() - timeSteppingStarted_;
timeSteppingStarted_ = 0.0;
}
}
bool GPUCommon::InterpretList(DisplayList &list) {
// Initialized to avoid a race condition with bShowDebugStats changing.
double start = 0.0;
if (g_Config.bShowDebugStats) {
time_update();
start = time_now_d();
}
easy_guard guard(listLock);
if (list.state == PSP_GE_DL_STATE_PAUSED)
return false;
currentList = &list;
if (!list.started && list.context.IsValid()) {
gstate.Save(list.context);
}
list.started = true;
gstate_c.offsetAddr = list.offsetAddr;
if (!Memory::IsValidAddress(list.pc)) {
ERROR_LOG_REPORT(G3D, "DL PC = %08x WTF!!!!", list.pc);
return true;
}
cycleLastPC = list.pc;
cyclesExecuted += 60;
downcount = list.stall == 0 ? 0x0FFFFFFF : (list.stall - list.pc) / 4;
list.state = PSP_GE_DL_STATE_RUNNING;
list.interrupted = false;
gpuState = list.pc == list.stall ? GPUSTATE_STALL : GPUSTATE_RUNNING;
guard.unlock();
const bool useDebugger = host->GPUDebuggingActive();
const bool useFastRunLoop = !dumpThisFrame_ && !useDebugger;
while (gpuState == GPUSTATE_RUNNING) {
{
easy_guard innerGuard(listLock);
if (list.pc == list.stall) {
gpuState = GPUSTATE_STALL;
downcount = 0;
}
}
if (useFastRunLoop) {
FastRunLoop(list);
} else {
SlowRunLoop(list);
}
{
easy_guard innerGuard(listLock);
downcount = list.stall == 0 ? 0x0FFFFFFF : (list.stall - list.pc) / 4;
if (gpuState == GPUSTATE_STALL && list.stall != list.pc) {
// Unstalled.
gpuState = GPUSTATE_RUNNING;
}
}
}
FinishDeferred();
// We haven't run the op at list.pc, so it shouldn't count.
if (cycleLastPC != list.pc) {
UpdatePC(list.pc - 4, list.pc);
}
list.offsetAddr = gstate_c.offsetAddr;
if (g_Config.bShowDebugStats) {
time_update();
double total = time_now_d() - start - timeSpentStepping_;
hleSetSteppingTime(timeSpentStepping_);
timeSpentStepping_ = 0.0;
gpuStats.msProcessingDisplayLists += total;
}
return gpuState == GPUSTATE_DONE || gpuState == GPUSTATE_ERROR;
}
void GPUCommon::SlowRunLoop(DisplayList &list)
{
const bool dumpThisFrame = dumpThisFrame_;
while (downcount > 0)
{
host->GPUNotifyCommand(list.pc);
u32 op = Memory::ReadUnchecked_U32(list.pc);
u32 cmd = op >> 24;
u32 diff = op ^ gstate.cmdmem[cmd];
PreExecuteOp(op, diff);
if (dumpThisFrame) {
char temp[256];
u32 prev;
if (Memory::IsValidAddress(list.pc - 4)) {
prev = Memory::ReadUnchecked_U32(list.pc - 4);
} else {
prev = 0;
}
GeDisassembleOp(list.pc, op, prev, temp, 256);
NOTICE_LOG(G3D, "%08x: %s", op, temp);
}
gstate.cmdmem[cmd] = op;
ExecuteOp(op, diff);
list.pc += 4;
--downcount;
}
}
// The newPC parameter is used for jumps, we don't count cycles between.
void GPUCommon::UpdatePC(u32 currentPC, u32 newPC) {
// Rough estimate, 2 CPU ticks (it's double the clock rate) per GPU instruction.
u32 executed = (currentPC - cycleLastPC) / 4;
cyclesExecuted += 2 * executed;
cycleLastPC = newPC;
if (g_Config.bShowDebugStats) {
gpuStats.otherGPUCycles += 2 * executed;
gpuStats.gpuCommandsAtCallLevel[std::min(currentList->stackptr, 3)] += executed;
}
// Exit the runloop and recalculate things. This happens a lot in some games.
easy_guard innerGuard(listLock);
if (currentList)
downcount = currentList->stall == 0 ? 0x0FFFFFFF : (currentList->stall - newPC) / 4;
else
downcount = 0;
}
void GPUCommon::ReapplyGfxState() {
if (IsOnSeparateCPUThread()) {
ScheduleEvent(GPU_EVENT_REAPPLY_GFX_STATE);
} else {
ReapplyGfxStateInternal();
}
}
void GPUCommon::ReapplyGfxStateInternal() {
// The commands are embedded in the command memory so we can just reexecute the words. Convenient.
// To be safe we pass 0xFFFFFFFF as the diff.
for (int i = GE_CMD_VERTEXTYPE; i < GE_CMD_BONEMATRIXNUMBER; i++) {
if (i != GE_CMD_ORIGIN && i != GE_CMD_OFFSETADDR) {
ExecuteOp(gstate.cmdmem[i], 0xFFFFFFFF);
}
}
// Can't write to bonematrixnumber here
for (int i = GE_CMD_MORPHWEIGHT0; i <= GE_CMD_PATCHFACING; i++) {
ExecuteOp(gstate.cmdmem[i], 0xFFFFFFFF);
}
// There are a few here in the middle that we shouldn't execute...
for (int i = GE_CMD_VIEWPORTXSCALE; i < GE_CMD_TRANSFERSTART; i++) {
ExecuteOp(gstate.cmdmem[i], 0xFFFFFFFF);
}
// Let's just skip the transfer size stuff, it's just values.
}
inline void GPUCommon::UpdateState(GPURunState state) {
gpuState = state;
if (state != GPUSTATE_RUNNING)
downcount = 0;
}
void GPUCommon::ProcessEvent(GPUEvent ev) {
switch (ev.type) {
case GPU_EVENT_PROCESS_QUEUE:
ProcessDLQueueInternal();
break;
case GPU_EVENT_REAPPLY_GFX_STATE:
ReapplyGfxStateInternal();
break;
case GPU_EVENT_INIT_CLEAR:
InitClearInternal();
break;
case GPU_EVENT_BEGIN_FRAME:
BeginFrameInternal();
break;
case GPU_EVENT_COPY_DISPLAY_TO_OUTPUT:
CopyDisplayToOutputInternal();
break;
case GPU_EVENT_INVALIDATE_CACHE:
InvalidateCacheInternal(ev.invalidate_cache.addr, ev.invalidate_cache.size, ev.invalidate_cache.type);
break;
case GPU_EVENT_FB_MEMCPY:
PerformMemoryCopyInternal(ev.fb_memcpy.dst, ev.fb_memcpy.src, ev.fb_memcpy.size);
break;
case GPU_EVENT_FB_MEMSET:
PerformMemorySetInternal(ev.fb_memset.dst, ev.fb_memset.v, ev.fb_memset.size);
break;
case GPU_EVENT_FB_STENCIL_UPLOAD:
PerformStencilUploadInternal(ev.fb_stencil_upload.dst, ev.fb_stencil_upload.size);
break;
default:
ERROR_LOG_REPORT(G3D, "Unexpected GPU event type: %d", (int)ev);
break;
}
}
int GPUCommon::GetNextListIndex() {
easy_guard guard(listLock);
auto iter = dlQueue.begin();
if (iter != dlQueue.end()) {
return *iter;
} else {
return -1;
}
}
bool GPUCommon::ProcessDLQueue() {
ScheduleEvent(GPU_EVENT_PROCESS_QUEUE);
return true;
}
void GPUCommon::ProcessDLQueueInternal() {
startingTicks = CoreTiming::GetTicks();
cyclesExecuted = 0;
UpdateTickEstimate(std::max(busyTicks, startingTicks + cyclesExecuted));
// Game might've written new texture data.
gstate_c.textureChanged = TEXCHANGE_UPDATED;
// Seems to be correct behaviour to process the list anyway?
if (startingTicks < busyTicks) {
DEBUG_LOG(G3D, "Can't execute a list yet, still busy for %lld ticks", busyTicks - startingTicks);
//return;
}
for (int listIndex = GetNextListIndex(); listIndex != -1; listIndex = GetNextListIndex()) {
DisplayList &l = dls[listIndex];
DEBUG_LOG(G3D, "Starting DL execution at %08x - stall = %08x", l.pc, l.stall);
if (!InterpretList(l)) {
return;
} else {
easy_guard guard(listLock);
// Some other list could've taken the spot while we dilly-dallied around.
if (l.state != PSP_GE_DL_STATE_QUEUED) {
// At the end, we can remove it from the queue and continue.
dlQueue.erase(std::remove(dlQueue.begin(), dlQueue.end(), listIndex), dlQueue.end());
}
UpdateTickEstimate(std::max(busyTicks, startingTicks + cyclesExecuted));
}
}
easy_guard guard(listLock);
currentList = NULL;
drawCompleteTicks = startingTicks + cyclesExecuted;
busyTicks = std::max(busyTicks, drawCompleteTicks);
__GeTriggerSync(GPU_SYNC_DRAW, 1, drawCompleteTicks);
// Since the event is in CoreTiming, we're in sync. Just set 0 now.
UpdateTickEstimate(0);
}
void GPUCommon::PreExecuteOp(u32 op, u32 diff) {
// Nothing to do
}
void GPUCommon::Execute_OffsetAddr(u32 op, u32 diff) {
gstate_c.offsetAddr = op << 8;
}
void GPUCommon::Execute_Origin(u32 op, u32 diff) {
easy_guard guard(listLock);
gstate_c.offsetAddr = currentList->pc;
}
void GPUCommon::Execute_Jump(u32 op, u32 diff) {
easy_guard guard(listLock);
const u32 target = gstate_c.getRelativeAddress(op & 0x00FFFFFC);
if (Memory::IsValidAddress(target)) {
UpdatePC(currentList->pc, target - 4);
currentList->pc = target - 4; // pc will be increased after we return, counteract that
} else {
ERROR_LOG_REPORT(G3D, "JUMP to illegal address %08x - ignoring! data=%06x", target, op & 0x00FFFFFF);
}
}
void GPUCommon::Execute_BJump(u32 op, u32 diff) {
if (!currentList->bboxResult) {
// bounding box jump.
easy_guard guard(listLock);
const u32 target = gstate_c.getRelativeAddress(op & 0x00FFFFFC);
if (Memory::IsValidAddress(target)) {
UpdatePC(currentList->pc, target - 4);
currentList->pc = target - 4; // pc will be increased after we return, counteract that
} else {
ERROR_LOG_REPORT(G3D, "BJUMP to illegal address %08x - ignoring! data=%06x", target, op & 0x00FFFFFF);
}
}
}
void GPUCommon::Execute_Call(u32 op, u32 diff) {
easy_guard guard(listLock);
// Saint Seiya needs correct support for relative calls.
const u32 retval = currentList->pc + 4;
const u32 target = gstate_c.getRelativeAddress(op & 0x00FFFFFC);
if (!Memory::IsValidAddress(target)) {
ERROR_LOG_REPORT(G3D, "CALL to illegal address %08x - ignoring! data=%06x", target, op & 0x00FFFFFF);
return;
}
// Bone matrix optimization - many games will CALL a bone matrix (!).
if ((Memory::ReadUnchecked_U32(target) >> 24) == GE_CMD_BONEMATRIXDATA) {
// Check for the end
if ((Memory::ReadUnchecked_U32(target + 11 * 4) >> 24) == GE_CMD_BONEMATRIXDATA &&
(Memory::ReadUnchecked_U32(target + 12 * 4) >> 24) == GE_CMD_RET) {
// Yep, pretty sure this is a bone matrix call.
FastLoadBoneMatrix(target);
return;
}
}
if (currentList->stackptr == ARRAY_SIZE(currentList->stack)) {
ERROR_LOG_REPORT(G3D, "CALL: Stack full!");
} else {
auto &stackEntry = currentList->stack[currentList->stackptr++];
stackEntry.pc = retval;
stackEntry.offsetAddr = gstate_c.offsetAddr;
// The base address is NOT saved/restored for a regular call.
UpdatePC(currentList->pc, target - 4);
currentList->pc = target - 4; // pc will be increased after we return, counteract that
}
}
void GPUCommon::Execute_Ret(u32 op, u32 diff) {
easy_guard guard(listLock);
if (currentList->stackptr == 0) {
DEBUG_LOG_REPORT(G3D, "RET: Stack empty!");
} else {
auto &stackEntry = currentList->stack[--currentList->stackptr];
gstate_c.offsetAddr = stackEntry.offsetAddr;
// We always clear the top (uncached/etc.) bits
const u32 target = stackEntry.pc & 0x0FFFFFFF;
UpdatePC(currentList->pc, target - 4);
currentList->pc = target - 4;
if (!Memory::IsValidAddress(currentList->pc)) {
ERROR_LOG_REPORT(G3D, "Invalid DL PC %08x on return", currentList->pc);
UpdateState(GPUSTATE_ERROR);
}
}
}
void GPUCommon::Execute_End(u32 op, u32 diff) {
easy_guard guard(listLock);
const u32 prev = Memory::ReadUnchecked_U32(currentList->pc - 4);
UpdatePC(currentList->pc);
// Count in a few extra cycles on END.
cyclesExecuted += 60;
switch (prev >> 24) {
case GE_CMD_SIGNAL:
{
// TODO: see http://code.google.com/p/jpcsp/source/detail?r=2935#
SignalBehavior behaviour = static_cast<SignalBehavior>((prev >> 16) & 0xFF);
const int signal = prev & 0xFFFF;
const int enddata = op & 0xFFFF;
bool trigger = true;
currentList->subIntrToken = signal;
switch (behaviour) {
case PSP_GE_SIGNAL_HANDLER_SUSPEND:
// Suspend the list, and call the signal handler. When it's done, resume.
// Before sdkver 0x02000010, listsync should return paused.
if (sceKernelGetCompiledSdkVersion() <= 0x02000010)
currentList->state = PSP_GE_DL_STATE_PAUSED;
currentList->signal = behaviour;
DEBUG_LOG(G3D, "Signal with wait. signal/end: %04x %04x", signal, enddata);
break;
case PSP_GE_SIGNAL_HANDLER_CONTINUE:
// Resume the list right away, then call the handler.
currentList->signal = behaviour;
DEBUG_LOG(G3D, "Signal without wait. signal/end: %04x %04x", signal, enddata);
break;
case PSP_GE_SIGNAL_HANDLER_PAUSE:
// Pause the list instead of ending at the next FINISH.
// Call the handler with the PAUSE signal value at that FINISH.
// Technically, this ought to trigger an interrupt, but it won't do anything.
// But right now, signal is always reset by interrupts, so that causes pause to not work.
trigger = false;
currentList->signal = behaviour;
DEBUG_LOG(G3D, "Signal with Pause. signal/end: %04x %04x", signal, enddata);
break;
case PSP_GE_SIGNAL_SYNC:
// Acts as a memory barrier, never calls any user code.
// Technically, this ought to trigger an interrupt, but it won't do anything.
// Triggering here can cause incorrect rescheduling, which breaks 3rd Birthday.
// However, this is likely a bug in how GE signal interrupts are handled.
trigger = false;
currentList->signal = behaviour;
DEBUG_LOG(G3D, "Signal with Sync. signal/end: %04x %04x", signal, enddata);
break;
case PSP_GE_SIGNAL_JUMP:
{
trigger = false;
currentList->signal = behaviour;
// pc will be increased after we return, counteract that.
u32 target = ((signal << 16) | enddata) - 4;
if (!Memory::IsValidAddress(target)) {
ERROR_LOG_REPORT(G3D, "Signal with Jump: bad address. signal/end: %04x %04x", signal, enddata);
} else {
UpdatePC(currentList->pc, target);
currentList->pc = target;
DEBUG_LOG(G3D, "Signal with Jump. signal/end: %04x %04x", signal, enddata);
}
}
break;
case PSP_GE_SIGNAL_CALL:
{
trigger = false;
currentList->signal = behaviour;
// pc will be increased after we return, counteract that.
u32 target = ((signal << 16) | enddata) - 4;
if (currentList->stackptr == ARRAY_SIZE(currentList->stack)) {
ERROR_LOG_REPORT(G3D, "Signal with Call: stack full. signal/end: %04x %04x", signal, enddata);
} else if (!Memory::IsValidAddress(target)) {
ERROR_LOG_REPORT(G3D, "Signal with Call: bad address. signal/end: %04x %04x", signal, enddata);
} else {
// TODO: This might save/restore other state...
auto &stackEntry = currentList->stack[currentList->stackptr++];
stackEntry.pc = currentList->pc;
stackEntry.offsetAddr = gstate_c.offsetAddr;
stackEntry.baseAddr = gstate.base;
UpdatePC(currentList->pc, target);
currentList->pc = target;
DEBUG_LOG(G3D, "Signal with Call. signal/end: %04x %04x", signal, enddata);
}
}
break;
case PSP_GE_SIGNAL_RET:
{
trigger = false;
currentList->signal = behaviour;
if (currentList->stackptr == 0) {
ERROR_LOG_REPORT(G3D, "Signal with Return: stack empty. signal/end: %04x %04x", signal, enddata);
} else {
// TODO: This might save/restore other state...
auto &stackEntry = currentList->stack[--currentList->stackptr];
gstate_c.offsetAddr = stackEntry.offsetAddr;
gstate.base = stackEntry.baseAddr;
UpdatePC(currentList->pc, stackEntry.pc);
currentList->pc = stackEntry.pc;
DEBUG_LOG(G3D, "Signal with Return. signal/end: %04x %04x", signal, enddata);
}
}
break;
default:
ERROR_LOG_REPORT(G3D, "UNKNOWN Signal UNIMPLEMENTED %i ! signal/end: %04x %04x", behaviour, signal, enddata);
break;
}
// TODO: Technically, jump/call/ret should generate an interrupt, but before the pc change maybe?
if (currentList->interruptsEnabled && trigger) {
if (__GeTriggerInterrupt(currentList->id, currentList->pc, startingTicks + cyclesExecuted)) {
currentList->pendingInterrupt = true;
UpdateState(GPUSTATE_INTERRUPT);
}
}
}
break;
case GE_CMD_FINISH:
switch (currentList->signal) {
case PSP_GE_SIGNAL_HANDLER_PAUSE:
currentList->state = PSP_GE_DL_STATE_PAUSED;