-
Notifications
You must be signed in to change notification settings - Fork 0
/
asm_ppc64x.s
1228 lines (1093 loc) · 27.9 KB
/
asm_ppc64x.s
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
// Copyright 2014 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// +build ppc64 ppc64le
#include "go_asm.h"
#include "go_tls.h"
#include "funcdata.h"
#include "textflag.h"
TEXT runtime·rt0_go(SB),NOSPLIT,$0
// R1 = stack; R3 = argc; R4 = argv; R13 = C TLS base pointer
// initialize essential registers
BL runtime·reginit(SB)
SUB $24, R1
MOVW R3, 8(R1) // argc
MOVD R4, 16(R1) // argv
// create istack out of the given (operating system) stack.
// _cgo_init may update stackguard.
MOVD $runtime·g0(SB), g
MOVD $(-64*1024), R31
ADD R31, R1, R3
MOVD R3, g_stackguard0(g)
MOVD R3, g_stackguard1(g)
MOVD R3, (g_stack+stack_lo)(g)
MOVD R1, (g_stack+stack_hi)(g)
// if there is a _cgo_init, call it using the gcc ABI.
MOVD _cgo_init(SB), R12
CMP R0, R12
BEQ nocgo
MOVD R12, CTR // r12 = "global function entry point"
MOVD R13, R5 // arg 2: TLS base pointer
MOVD $setg_gcc<>(SB), R4 // arg 1: setg
MOVD g, R3 // arg 0: G
// C functions expect 32 bytes of space on caller stack frame
// and a 16-byte aligned R1
MOVD R1, R14 // save current stack
SUB $32, R1 // reserve 32 bytes
RLDCR $0, R1, $~15, R1 // 16-byte align
BL (CTR) // may clobber R0, R3-R12
MOVD R14, R1 // restore stack
XOR R0, R0 // fix R0
nocgo:
// update stackguard after _cgo_init
MOVD (g_stack+stack_lo)(g), R3
ADD $const__StackGuard, R3
MOVD R3, g_stackguard0(g)
MOVD R3, g_stackguard1(g)
// set the per-goroutine and per-mach "registers"
MOVD $runtime·m0(SB), R3
// save m->g0 = g0
MOVD g, m_g0(R3)
// save m0 to g0->m
MOVD R3, g_m(g)
BL runtime·check(SB)
// args are already prepared
BL runtime·args(SB)
BL runtime·osinit(SB)
BL runtime·schedinit(SB)
// create a new goroutine to start program
MOVD $runtime·mainPC(SB), R3 // entry
MOVDU R3, -8(R1)
MOVDU R0, -8(R1)
MOVDU R0, -8(R1)
BL runtime·newproc(SB)
ADD $24, R1
// start this M
BL runtime·mstart(SB)
MOVD R0, 1(R0)
RET
DATA runtime·mainPC+0(SB)/8,$runtime·main(SB)
GLOBL runtime·mainPC(SB),RODATA,$8
TEXT runtime·breakpoint(SB),NOSPLIT,$-8-0
MOVD R0, 2(R0) // TODO: TD
RET
TEXT runtime·asminit(SB),NOSPLIT,$-8-0
RET
TEXT _cgo_reginit(SB),NOSPLIT,$-8-0
// crosscall_ppc64 and crosscall2 need to reginit, but can't
// get at the 'runtime.reginit' symbol.
BR runtime·reginit(SB)
TEXT runtime·reginit(SB),NOSPLIT,$-8-0
// set R0 to zero, it's expected by the toolchain
XOR R0, R0
// initialize essential FP registers
FMOVD $4503601774854144.0, F27
FMOVD $0.5, F29
FSUB F29, F29, F28
FADD F29, F29, F30
FADD F30, F30, F31
RET
/*
* go-routine
*/
// void gosave(Gobuf*)
// save state in Gobuf; setjmp
TEXT runtime·gosave(SB), NOSPLIT, $-8-8
MOVD buf+0(FP), R3
MOVD R1, gobuf_sp(R3)
MOVD LR, R31
MOVD R31, gobuf_pc(R3)
MOVD g, gobuf_g(R3)
MOVD R0, gobuf_lr(R3)
MOVD R0, gobuf_ret(R3)
MOVD R0, gobuf_ctxt(R3)
RET
// void gogo(Gobuf*)
// restore state from Gobuf; longjmp
TEXT runtime·gogo(SB), NOSPLIT, $-8-8
MOVD buf+0(FP), R5
MOVD gobuf_g(R5), g // make sure g is not nil
BL runtime·save_g(SB)
MOVD 0(g), R4
MOVD gobuf_sp(R5), R1
MOVD gobuf_lr(R5), R31
MOVD R31, LR
MOVD gobuf_ret(R5), R3
MOVD gobuf_ctxt(R5), R11
MOVD R0, gobuf_sp(R5)
MOVD R0, gobuf_ret(R5)
MOVD R0, gobuf_lr(R5)
MOVD R0, gobuf_ctxt(R5)
CMP R0, R0 // set condition codes for == test, needed by stack split
MOVD gobuf_pc(R5), R31
MOVD R31, CTR
BR (CTR)
// void mcall(fn func(*g))
// Switch to m->g0's stack, call fn(g).
// Fn must never return. It should gogo(&g->sched)
// to keep running g.
TEXT runtime·mcall(SB), NOSPLIT, $-8-8
// Save caller state in g->sched
MOVD R1, (g_sched+gobuf_sp)(g)
MOVD LR, R31
MOVD R31, (g_sched+gobuf_pc)(g)
MOVD R0, (g_sched+gobuf_lr)(g)
MOVD g, (g_sched+gobuf_g)(g)
// Switch to m->g0 & its stack, call fn.
MOVD g, R3
MOVD g_m(g), R8
MOVD m_g0(R8), g
BL runtime·save_g(SB)
CMP g, R3
BNE 2(PC)
BR runtime·badmcall(SB)
MOVD fn+0(FP), R11 // context
MOVD 0(R11), R4 // code pointer
MOVD R4, CTR
MOVD (g_sched+gobuf_sp)(g), R1 // sp = m->g0->sched.sp
MOVDU R3, -8(R1)
MOVDU R0, -8(R1)
BL (CTR)
BR runtime·badmcall2(SB)
// systemstack_switch is a dummy routine that systemstack leaves at the bottom
// of the G stack. We need to distinguish the routine that
// lives at the bottom of the G stack from the one that lives
// at the top of the system stack because the one at the top of
// the system stack terminates the stack walk (see topofstack()).
TEXT runtime·systemstack_switch(SB), NOSPLIT, $0-0
UNDEF
BL (LR) // make sure this function is not leaf
RET
// func systemstack(fn func())
TEXT runtime·systemstack(SB), NOSPLIT, $0-8
MOVD fn+0(FP), R3 // R3 = fn
MOVD R3, R11 // context
MOVD g_m(g), R4 // R4 = m
MOVD m_gsignal(R4), R5 // R5 = gsignal
CMP g, R5
BEQ noswitch
MOVD m_g0(R4), R5 // R5 = g0
CMP g, R5
BEQ noswitch
MOVD m_curg(R4), R6
CMP g, R6
BEQ switch
// Bad: g is not gsignal, not g0, not curg. What is it?
// Hide call from linker nosplit analysis.
MOVD $runtime·badsystemstack(SB), R3
MOVD R3, CTR
BL (CTR)
switch:
// save our state in g->sched. Pretend to
// be systemstack_switch if the G stack is scanned.
MOVD $runtime·systemstack_switch(SB), R6
ADD $8, R6 // get past prologue
MOVD R6, (g_sched+gobuf_pc)(g)
MOVD R1, (g_sched+gobuf_sp)(g)
MOVD R0, (g_sched+gobuf_lr)(g)
MOVD g, (g_sched+gobuf_g)(g)
// switch to g0
MOVD R5, g
BL runtime·save_g(SB)
MOVD (g_sched+gobuf_sp)(g), R3
// make it look like mstart called systemstack on g0, to stop traceback
SUB $8, R3
MOVD $runtime·mstart(SB), R4
MOVD R4, 0(R3)
MOVD R3, R1
// call target function
MOVD 0(R11), R3 // code pointer
MOVD R3, CTR
BL (CTR)
// switch back to g
MOVD g_m(g), R3
MOVD m_curg(R3), g
BL runtime·save_g(SB)
MOVD (g_sched+gobuf_sp)(g), R1
MOVD R0, (g_sched+gobuf_sp)(g)
RET
noswitch:
// already on m stack, just call directly
MOVD 0(R11), R3 // code pointer
MOVD R3, CTR
BL (CTR)
RET
/*
* support for morestack
*/
// Called during function prolog when more stack is needed.
// Caller has already loaded:
// R3: framesize, R4: argsize, R5: LR
//
// The traceback routines see morestack on a g0 as being
// the top of a stack (for example, morestack calling newstack
// calling the scheduler calling newm calling gc), so we must
// record an argument size. For that purpose, it has no arguments.
TEXT runtime·morestack(SB),NOSPLIT,$-8-0
// Cannot grow scheduler stack (m->g0).
MOVD g_m(g), R7
MOVD m_g0(R7), R8
CMP g, R8
BNE 2(PC)
BL runtime·abort(SB)
// Cannot grow signal stack (m->gsignal).
MOVD m_gsignal(R7), R8
CMP g, R8
BNE 2(PC)
BL runtime·abort(SB)
// Called from f.
// Set g->sched to context in f.
MOVD R11, (g_sched+gobuf_ctxt)(g)
MOVD R1, (g_sched+gobuf_sp)(g)
MOVD LR, R8
MOVD R8, (g_sched+gobuf_pc)(g)
MOVD R5, (g_sched+gobuf_lr)(g)
// Called from f.
// Set m->morebuf to f's caller.
MOVD R5, (m_morebuf+gobuf_pc)(R7) // f's caller's PC
MOVD R1, (m_morebuf+gobuf_sp)(R7) // f's caller's SP
MOVD g, (m_morebuf+gobuf_g)(R7)
// Call newstack on m->g0's stack.
MOVD m_g0(R7), g
BL runtime·save_g(SB)
MOVD (g_sched+gobuf_sp)(g), R1
BL runtime·newstack(SB)
// Not reached, but make sure the return PC from the call to newstack
// is still in this function, and not the beginning of the next.
UNDEF
TEXT runtime·morestack_noctxt(SB),NOSPLIT,$-8-0
MOVD R0, R11
BR runtime·morestack(SB)
TEXT runtime·stackBarrier(SB),NOSPLIT,$0
// We came here via a RET to an overwritten LR.
// R3 may be live. Other registers are available.
// Get the original return PC, g.stkbar[g.stkbarPos].savedLRVal.
MOVD (g_stkbar+slice_array)(g), R4
MOVD g_stkbarPos(g), R5
MOVD $stkbar__size, R6
MULLD R5, R6
ADD R4, R6
MOVD stkbar_savedLRVal(R6), R6
// Record that this stack barrier was hit.
ADD $1, R5
MOVD R5, g_stkbarPos(g)
// Jump to the original return PC.
MOVD R6, CTR
BR (CTR)
// reflectcall: call a function with the given argument list
// func call(argtype *_type, f *FuncVal, arg *byte, argsize, retoffset uint32).
// we don't have variable-sized frames, so we use a small number
// of constant-sized-frame functions to encode a few bits of size in the pc.
// Caution: ugly multiline assembly macros in your future!
#define DISPATCH(NAME,MAXSIZE) \
MOVD $MAXSIZE, R31; \
CMP R3, R31; \
BGT 4(PC); \
MOVD $NAME(SB), R31; \
MOVD R31, CTR; \
BR (CTR)
// Note: can't just "BR NAME(SB)" - bad inlining results.
TEXT reflect·call(SB), NOSPLIT, $0-0
BR ·reflectcall(SB)
TEXT ·reflectcall(SB), NOSPLIT, $-8-32
MOVWZ argsize+24(FP), R3
// NOTE(rsc): No call16, because CALLFN needs four words
// of argument space to invoke callwritebarrier.
DISPATCH(runtime·call32, 32)
DISPATCH(runtime·call64, 64)
DISPATCH(runtime·call128, 128)
DISPATCH(runtime·call256, 256)
DISPATCH(runtime·call512, 512)
DISPATCH(runtime·call1024, 1024)
DISPATCH(runtime·call2048, 2048)
DISPATCH(runtime·call4096, 4096)
DISPATCH(runtime·call8192, 8192)
DISPATCH(runtime·call16384, 16384)
DISPATCH(runtime·call32768, 32768)
DISPATCH(runtime·call65536, 65536)
DISPATCH(runtime·call131072, 131072)
DISPATCH(runtime·call262144, 262144)
DISPATCH(runtime·call524288, 524288)
DISPATCH(runtime·call1048576, 1048576)
DISPATCH(runtime·call2097152, 2097152)
DISPATCH(runtime·call4194304, 4194304)
DISPATCH(runtime·call8388608, 8388608)
DISPATCH(runtime·call16777216, 16777216)
DISPATCH(runtime·call33554432, 33554432)
DISPATCH(runtime·call67108864, 67108864)
DISPATCH(runtime·call134217728, 134217728)
DISPATCH(runtime·call268435456, 268435456)
DISPATCH(runtime·call536870912, 536870912)
DISPATCH(runtime·call1073741824, 1073741824)
MOVD $runtime·badreflectcall(SB), R31
MOVD R31, CTR
BR (CTR)
#define CALLFN(NAME,MAXSIZE) \
TEXT NAME(SB), WRAPPER, $MAXSIZE-24; \
NO_LOCAL_POINTERS; \
/* copy arguments to stack */ \
MOVD arg+16(FP), R3; \
MOVWZ argsize+24(FP), R4; \
MOVD R1, R5; \
ADD $(8-1), R5; \
SUB $1, R3; \
ADD R5, R4; \
CMP R5, R4; \
BEQ 4(PC); \
MOVBZU 1(R3), R6; \
MOVBZU R6, 1(R5); \
BR -4(PC); \
/* call function */ \
MOVD f+8(FP), R11; \
MOVD (R11), R31; \
MOVD R31, CTR; \
PCDATA $PCDATA_StackMapIndex, $0; \
BL (CTR); \
/* copy return values back */ \
MOVD arg+16(FP), R3; \
MOVWZ n+24(FP), R4; \
MOVWZ retoffset+28(FP), R6; \
MOVD R1, R5; \
ADD R6, R5; \
ADD R6, R3; \
SUB R6, R4; \
ADD $(8-1), R5; \
SUB $1, R3; \
ADD R5, R4; \
loop: \
CMP R5, R4; \
BEQ end; \
MOVBZU 1(R5), R6; \
MOVBZU R6, 1(R3); \
BR loop; \
end: \
/* execute write barrier updates */ \
MOVD argtype+0(FP), R7; \
MOVD arg+16(FP), R3; \
MOVWZ n+24(FP), R4; \
MOVWZ retoffset+28(FP), R6; \
MOVD R7, 8(R1); \
MOVD R3, 16(R1); \
MOVD R4, 24(R1); \
MOVD R6, 32(R1); \
BL runtime·callwritebarrier(SB); \
RET
CALLFN(·call16, 16)
CALLFN(·call32, 32)
CALLFN(·call64, 64)
CALLFN(·call128, 128)
CALLFN(·call256, 256)
CALLFN(·call512, 512)
CALLFN(·call1024, 1024)
CALLFN(·call2048, 2048)
CALLFN(·call4096, 4096)
CALLFN(·call8192, 8192)
CALLFN(·call16384, 16384)
CALLFN(·call32768, 32768)
CALLFN(·call65536, 65536)
CALLFN(·call131072, 131072)
CALLFN(·call262144, 262144)
CALLFN(·call524288, 524288)
CALLFN(·call1048576, 1048576)
CALLFN(·call2097152, 2097152)
CALLFN(·call4194304, 4194304)
CALLFN(·call8388608, 8388608)
CALLFN(·call16777216, 16777216)
CALLFN(·call33554432, 33554432)
CALLFN(·call67108864, 67108864)
CALLFN(·call134217728, 134217728)
CALLFN(·call268435456, 268435456)
CALLFN(·call536870912, 536870912)
CALLFN(·call1073741824, 1073741824)
// bool cas(uint32 *ptr, uint32 old, uint32 new)
// Atomically:
// if(*val == old){
// *val = new;
// return 1;
// } else
// return 0;
TEXT runtime·cas(SB), NOSPLIT, $0-17
MOVD ptr+0(FP), R3
MOVWZ old+8(FP), R4
MOVWZ new+12(FP), R5
cas_again:
SYNC
LWAR (R3), R6
CMPW R6, R4
BNE cas_fail
STWCCC R5, (R3)
BNE cas_again
MOVD $1, R3
SYNC
ISYNC
MOVB R3, ret+16(FP)
RET
cas_fail:
MOVD $0, R3
BR -5(PC)
// bool runtime·cas64(uint64 *ptr, uint64 old, uint64 new)
// Atomically:
// if(*val == *old){
// *val = new;
// return 1;
// } else {
// return 0;
// }
TEXT runtime·cas64(SB), NOSPLIT, $0-25
MOVD ptr+0(FP), R3
MOVD old+8(FP), R4
MOVD new+16(FP), R5
cas64_again:
SYNC
LDAR (R3), R6
CMP R6, R4
BNE cas64_fail
STDCCC R5, (R3)
BNE cas64_again
MOVD $1, R3
SYNC
ISYNC
MOVB R3, ret+24(FP)
RET
cas64_fail:
MOVD $0, R3
BR -5(PC)
TEXT runtime·casuintptr(SB), NOSPLIT, $0-25
BR runtime·cas64(SB)
TEXT runtime·atomicloaduintptr(SB), NOSPLIT, $-8-16
BR runtime·atomicload64(SB)
TEXT runtime·atomicloaduint(SB), NOSPLIT, $-8-16
BR runtime·atomicload64(SB)
TEXT runtime·atomicstoreuintptr(SB), NOSPLIT, $0-16
BR runtime·atomicstore64(SB)
// bool casp(void **val, void *old, void *new)
// Atomically:
// if(*val == old){
// *val = new;
// return 1;
// } else
// return 0;
TEXT runtime·casp1(SB), NOSPLIT, $0-25
BR runtime·cas64(SB)
// uint32 xadd(uint32 volatile *ptr, int32 delta)
// Atomically:
// *val += delta;
// return *val;
TEXT runtime·xadd(SB), NOSPLIT, $0-20
MOVD ptr+0(FP), R4
MOVW delta+8(FP), R5
SYNC
LWAR (R4), R3
ADD R5, R3
STWCCC R3, (R4)
BNE -4(PC)
SYNC
ISYNC
MOVW R3, ret+16(FP)
RET
TEXT runtime·xadd64(SB), NOSPLIT, $0-24
MOVD ptr+0(FP), R4
MOVD delta+8(FP), R5
SYNC
LDAR (R4), R3
ADD R5, R3
STDCCC R3, (R4)
BNE -4(PC)
SYNC
ISYNC
MOVD R3, ret+16(FP)
RET
TEXT runtime·xchg(SB), NOSPLIT, $0-20
MOVD ptr+0(FP), R4
MOVW new+8(FP), R5
SYNC
LWAR (R4), R3
STWCCC R5, (R4)
BNE -3(PC)
SYNC
ISYNC
MOVW R3, ret+16(FP)
RET
TEXT runtime·xchg64(SB), NOSPLIT, $0-24
MOVD ptr+0(FP), R4
MOVD new+8(FP), R5
SYNC
LDAR (R4), R3
STDCCC R5, (R4)
BNE -3(PC)
SYNC
ISYNC
MOVD R3, ret+16(FP)
RET
TEXT runtime·xchguintptr(SB), NOSPLIT, $0-24
BR runtime·xchg64(SB)
TEXT runtime·procyield(SB),NOSPLIT,$0-0
RET
TEXT runtime·atomicstorep1(SB), NOSPLIT, $0-16
BR runtime·atomicstore64(SB)
TEXT runtime·atomicstore(SB), NOSPLIT, $0-12
MOVD ptr+0(FP), R3
MOVW val+8(FP), R4
SYNC
MOVW R4, 0(R3)
RET
TEXT runtime·atomicstore64(SB), NOSPLIT, $0-16
MOVD ptr+0(FP), R3
MOVD val+8(FP), R4
SYNC
MOVD R4, 0(R3)
RET
// void runtime·atomicor8(byte volatile*, byte);
TEXT runtime·atomicor8(SB), NOSPLIT, $0-9
MOVD ptr+0(FP), R3
MOVBZ val+8(FP), R4
// Align ptr down to 4 bytes so we can use 32-bit load/store.
// R5 = (R3 << 0) & ~3
RLDCR $0, R3, $~3, R5
// Compute val shift.
#ifdef GOARCH_ppc64
// Big endian. ptr = ptr ^ 3
XOR $3, R3
#endif
// R6 = ((ptr & 3) * 8) = (ptr << 3) & (3*8)
RLDC $3, R3, $(3*8), R6
// Shift val for aligned ptr. R4 = val << R6
SLD R6, R4, R4
again:
SYNC
LWAR (R5), R6
OR R4, R6
STWCCC R6, (R5)
BNE again
SYNC
ISYNC
RET
// void runtime·atomicand8(byte volatile*, byte);
TEXT runtime·atomicand8(SB), NOSPLIT, $0-9
MOVD ptr+0(FP), R3
MOVBZ val+8(FP), R4
// Align ptr down to 4 bytes so we can use 32-bit load/store.
// R5 = (R3 << 0) & ~3
RLDCR $0, R3, $~3, R5
// Compute val shift.
#ifdef GOARCH_ppc64
// Big endian. ptr = ptr ^ 3
XOR $3, R3
#endif
// R6 = ((ptr & 3) * 8) = (ptr << 3) & (3*8)
RLDC $3, R3, $(3*8), R6
// Shift val for aligned ptr. R4 = val << R6 | ^(0xFF << R6)
MOVD $0xFF, R7
SLD R6, R4
SLD R6, R7
XOR $-1, R7
OR R7, R4
again:
SYNC
LWAR (R5), R6
AND R4, R6
STWCCC R6, (R5)
BNE again
SYNC
ISYNC
RET
// void jmpdefer(fv, sp);
// called from deferreturn.
// 1. grab stored LR for caller
// 2. sub 4 bytes to get back to BL deferreturn
// 3. BR to fn
TEXT runtime·jmpdefer(SB), NOSPLIT, $-8-16
MOVD 0(R1), R31
SUB $4, R31
MOVD R31, LR
MOVD fv+0(FP), R11
MOVD argp+8(FP), R1
SUB $8, R1
MOVD 0(R11), R3
MOVD R3, CTR
BR (CTR)
// Save state of caller into g->sched. Smashes R31.
TEXT gosave<>(SB),NOSPLIT,$-8
MOVD LR, R31
MOVD R31, (g_sched+gobuf_pc)(g)
MOVD R1, (g_sched+gobuf_sp)(g)
MOVD R0, (g_sched+gobuf_lr)(g)
MOVD R0, (g_sched+gobuf_ret)(g)
MOVD R0, (g_sched+gobuf_ctxt)(g)
RET
// func asmcgocall(fn, arg unsafe.Pointer) int32
// Call fn(arg) on the scheduler stack,
// aligned appropriately for the gcc ABI.
// See cgocall.go for more details.
TEXT ·asmcgocall(SB),NOSPLIT,$0-20
MOVD fn+0(FP), R3
MOVD arg+8(FP), R4
MOVD R1, R2 // save original stack pointer
MOVD g, R5
// Figure out if we need to switch to m->g0 stack.
// We get called to create new OS threads too, and those
// come in on the m->g0 stack already.
MOVD g_m(g), R6
MOVD m_g0(R6), R6
CMP R6, g
BEQ g0
BL gosave<>(SB)
MOVD R6, g
BL runtime·save_g(SB)
MOVD (g_sched+gobuf_sp)(g), R1
// Now on a scheduling stack (a pthread-created stack).
g0:
// Save room for two of our pointers, plus 32 bytes of callee
// save area that lives on the caller stack.
SUB $48, R1
RLDCR $0, R1, $~15, R1 // 16-byte alignment for gcc ABI
MOVD R5, 40(R1) // save old g on stack
MOVD (g_stack+stack_hi)(R5), R5
SUB R2, R5
MOVD R5, 32(R1) // save depth in old g stack (can't just save SP, as stack might be copied during a callback)
MOVD R0, 0(R1) // clear back chain pointer (TODO can we give it real back trace information?)
// This is a "global call", so put the global entry point in r12
MOVD R3, R12
MOVD R12, CTR
MOVD R4, R3 // arg in r3
BL (CTR)
// C code can clobber R0, so set it back to 0. F27-F31 are
// callee save, so we don't need to recover those.
XOR R0, R0
// Restore g, stack pointer. R3 is errno, so don't touch it
MOVD 40(R1), g
BL runtime·save_g(SB)
MOVD (g_stack+stack_hi)(g), R5
MOVD 32(R1), R6
SUB R6, R5
MOVD R5, R1
MOVW R3, ret+16(FP)
RET
// cgocallback(void (*fn)(void*), void *frame, uintptr framesize)
// Turn the fn into a Go func (by taking its address) and call
// cgocallback_gofunc.
TEXT runtime·cgocallback(SB),NOSPLIT,$24-24
MOVD $fn+0(FP), R3
MOVD R3, 8(R1)
MOVD frame+8(FP), R3
MOVD R3, 16(R1)
MOVD framesize+16(FP), R3
MOVD R3, 24(R1)
MOVD $runtime·cgocallback_gofunc(SB), R3
MOVD R3, CTR
BL (CTR)
RET
// cgocallback_gofunc(FuncVal*, void *frame, uintptr framesize)
// See cgocall.go for more details.
TEXT ·cgocallback_gofunc(SB),NOSPLIT,$16-24
NO_LOCAL_POINTERS
// Load m and g from thread-local storage.
MOVB runtime·iscgo(SB), R3
CMP R3, $0
BEQ nocgo
BL runtime·load_g(SB)
nocgo:
// If g is nil, Go did not create the current thread.
// Call needm to obtain one for temporary use.
// In this case, we're running on the thread stack, so there's
// lots of space, but the linker doesn't know. Hide the call from
// the linker analysis by using an indirect call.
CMP g, $0
BNE havem
MOVD g, savedm-8(SP) // g is zero, so is m.
MOVD $runtime·needm(SB), R3
MOVD R3, CTR
BL (CTR)
// Set m->sched.sp = SP, so that if a panic happens
// during the function we are about to execute, it will
// have a valid SP to run on the g0 stack.
// The next few lines (after the havem label)
// will save this SP onto the stack and then write
// the same SP back to m->sched.sp. That seems redundant,
// but if an unrecovered panic happens, unwindm will
// restore the g->sched.sp from the stack location
// and then systemstack will try to use it. If we don't set it here,
// that restored SP will be uninitialized (typically 0) and
// will not be usable.
MOVD g_m(g), R3
MOVD m_g0(R3), R3
MOVD R1, (g_sched+gobuf_sp)(R3)
havem:
MOVD g_m(g), R8
MOVD R8, savedm-8(SP)
// Now there's a valid m, and we're running on its m->g0.
// Save current m->g0->sched.sp on stack and then set it to SP.
// Save current sp in m->g0->sched.sp in preparation for
// switch back to m->curg stack.
// NOTE: unwindm knows that the saved g->sched.sp is at 8(R1) aka savedsp-16(SP).
MOVD m_g0(R8), R3
MOVD (g_sched+gobuf_sp)(R3), R4
MOVD R4, savedsp-16(SP)
MOVD R1, (g_sched+gobuf_sp)(R3)
// Switch to m->curg stack and call runtime.cgocallbackg.
// Because we are taking over the execution of m->curg
// but *not* resuming what had been running, we need to
// save that information (m->curg->sched) so we can restore it.
// We can restore m->curg->sched.sp easily, because calling
// runtime.cgocallbackg leaves SP unchanged upon return.
// To save m->curg->sched.pc, we push it onto the stack.
// This has the added benefit that it looks to the traceback
// routine like cgocallbackg is going to return to that
// PC (because the frame we allocate below has the same
// size as cgocallback_gofunc's frame declared above)
// so that the traceback will seamlessly trace back into
// the earlier calls.
//
// In the new goroutine, -16(SP) and -8(SP) are unused.
MOVD m_curg(R8), g
BL runtime·save_g(SB)
MOVD (g_sched+gobuf_sp)(g), R4 // prepare stack as R4
MOVD (g_sched+gobuf_pc)(g), R5
MOVD R5, -24(R4)
MOVD $-24(R4), R1
BL runtime·cgocallbackg(SB)
// Restore g->sched (== m->curg->sched) from saved values.
MOVD 0(R1), R5
MOVD R5, (g_sched+gobuf_pc)(g)
MOVD $24(R1), R4
MOVD R4, (g_sched+gobuf_sp)(g)
// Switch back to m->g0's stack and restore m->g0->sched.sp.
// (Unlike m->curg, the g0 goroutine never uses sched.pc,
// so we do not have to restore it.)
MOVD g_m(g), R8
MOVD m_g0(R8), g
BL runtime·save_g(SB)
MOVD (g_sched+gobuf_sp)(g), R1
MOVD savedsp-16(SP), R4
MOVD R4, (g_sched+gobuf_sp)(g)
// If the m on entry was nil, we called needm above to borrow an m
// for the duration of the call. Since the call is over, return it with dropm.
MOVD savedm-8(SP), R6
CMP R6, $0
BNE droppedm
MOVD $runtime·dropm(SB), R3
MOVD R3, CTR
BL (CTR)
droppedm:
// Done!
RET
// void setg(G*); set g. for use by needm.
TEXT runtime·setg(SB), NOSPLIT, $0-8
MOVD gg+0(FP), g
// This only happens if iscgo, so jump straight to save_g
BL runtime·save_g(SB)
RET
// void setg_gcc(G*); set g in C TLS.
// Must obey the gcc calling convention.
TEXT setg_gcc<>(SB),NOSPLIT,$-8-0
// The standard prologue clobbers R31, which is callee-save in
// the C ABI, so we have to use $-8-0 and save LR ourselves.
MOVD LR, R4
// Also save g and R31, since they're callee-save in C ABI
MOVD R31, R5
MOVD g, R6
MOVD R3, g
BL runtime·save_g(SB)
MOVD R6, g
MOVD R5, R31
MOVD R4, LR
RET
TEXT runtime·getcallerpc(SB),NOSPLIT,$8-16
MOVD 16(R1), R3 // LR saved by caller
MOVD runtime·stackBarrierPC(SB), R4
CMP R3, R4
BNE nobar
// Get original return PC.
BL runtime·nextBarrierPC(SB)
MOVD 8(R1), R3
nobar:
MOVD R3, ret+8(FP)
RET
TEXT runtime·setcallerpc(SB),NOSPLIT,$8-16
MOVD pc+8(FP), R3
MOVD 16(R1), R4
MOVD runtime·stackBarrierPC(SB), R5
CMP R4, R5
BEQ setbar
MOVD R3, 16(R1) // set LR in caller
RET
setbar:
// Set the stack barrier return PC.
MOVD R3, 8(R1)
BL runtime·setNextBarrierPC(SB)
RET
TEXT runtime·getcallersp(SB),NOSPLIT,$0-16
MOVD argp+0(FP), R3
SUB $8, R3
MOVD R3, ret+8(FP)
RET
TEXT runtime·abort(SB),NOSPLIT,$-8-0
MOVW (R0), R0
UNDEF
#define TBRL 268
#define TBRU 269 /* Time base Upper/Lower */
// int64 runtime·cputicks(void)
TEXT runtime·cputicks(SB),NOSPLIT,$0-8
MOVW SPR(TBRU), R4
MOVW SPR(TBRL), R3
MOVW SPR(TBRU), R5
CMPW R4, R5
BNE -4(PC)
SLD $32, R5
OR R5, R3
MOVD R3, ret+0(FP)
RET
// memhash_varlen(p unsafe.Pointer, h seed) uintptr
// redirects to memhash(p, h, size) using the size
// stored in the closure.
TEXT runtime·memhash_varlen(SB),NOSPLIT,$40-24
GO_ARGS
NO_LOCAL_POINTERS
MOVD p+0(FP), R3
MOVD h+8(FP), R4
MOVD 8(R11), R5
MOVD R3, 8(R1)
MOVD R4, 16(R1)
MOVD R5, 24(R1)
BL runtime·memhash(SB)
MOVD 32(R1), R3
MOVD R3, ret+16(FP)
RET
// AES hashing not implemented for ppc64
TEXT runtime·aeshash(SB),NOSPLIT,$-8-0
MOVW (R0), R1
TEXT runtime·aeshash32(SB),NOSPLIT,$-8-0
MOVW (R0), R1
TEXT runtime·aeshash64(SB),NOSPLIT,$-8-0
MOVW (R0), R1
TEXT runtime·aeshashstr(SB),NOSPLIT,$-8-0
MOVW (R0), R1
TEXT runtime·memeq(SB),NOSPLIT,$-8-25
MOVD a+0(FP), R3
MOVD b+8(FP), R4
MOVD size+16(FP), R5
SUB $1, R3
SUB $1, R4
ADD R3, R5, R8
loop:
CMP R3, R8
BNE test
MOVD $1, R3
MOVB R3, ret+24(FP)
RET
test:
MOVBZU 1(R3), R6
MOVBZU 1(R4), R7
CMP R6, R7
BEQ loop
MOVB R0, ret+24(FP)
RET
// memequal_varlen(a, b unsafe.Pointer) bool
TEXT runtime·memequal_varlen(SB),NOSPLIT,$40-17
MOVD a+0(FP), R3
MOVD b+8(FP), R4
CMP R3, R4
BEQ eq
MOVD 8(R11), R5 // compiler stores size at offset 8 in the closure
MOVD R3, 8(R1)
MOVD R4, 16(R1)