summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/entry_64.S
blob: db13655c3a2aff4a4475a9adf6ce1cb5b3639220 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
/*
 *  linux/arch/x86_64/entry.S
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *  Copyright (C) 2000, 2001, 2002  Andi Kleen SuSE Labs
 *  Copyright (C) 2000  Pavel Machek <pavel@suse.cz>
 */

/*
 * entry.S contains the system-call and fault low-level handling routines.
 *
 * Some of this is documented in Documentation/x86/entry_64.txt
 *
 * NOTE: This code handles signal-recognition, which happens every time
 * after an interrupt and after each system call.
 *
 * Normal syscalls and interrupts don't save a full stack frame, this is
 * only done for syscall tracing, signals or fork/exec et.al.
 *
 * A note on terminology:
 * - top of stack: Architecture defined interrupt frame from SS to RIP
 * at the top of the kernel process stack.
 * - partial stack frame: partially saved registers up to R11.
 * - full stack frame: Like partial stack frame, but all register saved.
 *
 * Some macro usage:
 * - CFI macros are used to generate dwarf2 unwind information for better
 * backtraces. They don't change any code.
 * - SAVE_ALL/RESTORE_ALL - Save/restore all registers
 * - SAVE_ARGS/RESTORE_ARGS - Save/restore registers that C functions modify.
 * There are unfortunately lots of special cases where some registers
 * not touched. The macro is a big mess that should be cleaned up.
 * - SAVE_REST/RESTORE_REST - Handle the registers not saved by SAVE_ARGS.
 * Gives a full stack frame.
 * - ENTRY/END Define functions in the symbol table.
 * - FIXUP_TOP_OF_STACK/RESTORE_TOP_OF_STACK - Fix up the hardware stack
 * frame that is otherwise undefined after a SYSCALL
 * - TRACE_IRQ_* - Trace hard interrupt state for lock debugging.
 * - idtentry - Define exception entry points.
 */

#include <linux/linkage.h>
#include <asm/segment.h>
#include <asm/cache.h>
#include <asm/errno.h>
#include <asm/dwarf2.h>
#include <asm/calling.h>
#include <asm/asm-offsets.h>
#include <asm/msr.h>
#include <asm/unistd.h>
#include <asm/thread_info.h>
#include <asm/hw_irq.h>
#include <asm/page_types.h>
#include <asm/irqflags.h>
#include <asm/paravirt.h>
#include <asm/percpu.h>
#include <asm/asm.h>
#include <asm/context_tracking.h>
#include <asm/smap.h>
#include <asm/pgtable_types.h>
#include <linux/err.h>

/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
#include <linux/elf-em.h>
#define AUDIT_ARCH_X86_64	(EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
#define __AUDIT_ARCH_64BIT 0x80000000
#define __AUDIT_ARCH_LE	   0x40000000

	.code64
	.section .entry.text, "ax"


#ifndef CONFIG_PREEMPT
#define retint_kernel retint_restore_args
#endif

#ifdef CONFIG_PARAVIRT
ENTRY(native_usergs_sysret64)
	swapgs
	sysretq
ENDPROC(native_usergs_sysret64)
#endif /* CONFIG_PARAVIRT */


.macro TRACE_IRQS_IRETQ offset=ARGOFFSET
#ifdef CONFIG_TRACE_IRQFLAGS
	bt   $9,EFLAGS-\offset(%rsp)	/* interrupts off? */
	jnc  1f
	TRACE_IRQS_ON
1:
#endif
.endm

/*
 * When dynamic function tracer is enabled it will add a breakpoint
 * to all locations that it is about to modify, sync CPUs, update
 * all the code, sync CPUs, then remove the breakpoints. In this time
 * if lockdep is enabled, it might jump back into the debug handler
 * outside the updating of the IST protection. (TRACE_IRQS_ON/OFF).
 *
 * We need to change the IDT table before calling TRACE_IRQS_ON/OFF to
 * make sure the stack pointer does not get reset back to the top
 * of the debug stack, and instead just reuses the current stack.
 */
#if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_TRACE_IRQFLAGS)

.macro TRACE_IRQS_OFF_DEBUG
	call debug_stack_set_zero
	TRACE_IRQS_OFF
	call debug_stack_reset
.endm

.macro TRACE_IRQS_ON_DEBUG
	call debug_stack_set_zero
	TRACE_IRQS_ON
	call debug_stack_reset
.endm

.macro TRACE_IRQS_IRETQ_DEBUG offset=ARGOFFSET
	bt   $9,EFLAGS-\offset(%rsp)	/* interrupts off? */
	jnc  1f
	TRACE_IRQS_ON_DEBUG
1:
.endm

#else
# define TRACE_IRQS_OFF_DEBUG		TRACE_IRQS_OFF
# define TRACE_IRQS_ON_DEBUG		TRACE_IRQS_ON
# define TRACE_IRQS_IRETQ_DEBUG		TRACE_IRQS_IRETQ
#endif

/*
 * C code is not supposed to know about undefined top of stack. Every time
 * a C function with an pt_regs argument is called from the SYSCALL based
 * fast path FIXUP_TOP_OF_STACK is needed.
 * RESTORE_TOP_OF_STACK syncs the syscall state after any possible ptregs
 * manipulation.
 */

	/* %rsp:at FRAMEEND */
	.macro FIXUP_TOP_OF_STACK tmp offset=0
	movq PER_CPU_VAR(old_rsp),\tmp
	movq \tmp,RSP+\offset(%rsp)
	movq $__USER_DS,SS+\offset(%rsp)
	movq $__USER_CS,CS+\offset(%rsp)
	movq RIP+\offset(%rsp),\tmp  /* get rip */
	movq \tmp,RCX+\offset(%rsp)  /* copy it to rcx as sysret would do */
	movq R11+\offset(%rsp),\tmp  /* get eflags */
	movq \tmp,EFLAGS+\offset(%rsp)
	.endm

	.macro RESTORE_TOP_OF_STACK tmp offset=0
	movq RSP+\offset(%rsp),\tmp
	movq \tmp,PER_CPU_VAR(old_rsp)
	movq EFLAGS+\offset(%rsp),\tmp
	movq \tmp,R11+\offset(%rsp)
	.endm

/*
 * initial frame state for interrupts (and exceptions without error code)
 */
	.macro EMPTY_FRAME start=1 offset=0
	.if \start
	CFI_STARTPROC simple
	CFI_SIGNAL_FRAME
	CFI_DEF_CFA rsp,8+\offset
	.else
	CFI_DEF_CFA_OFFSET 8+\offset
	.endif
	.endm

/*
 * initial frame state for interrupts (and exceptions without error code)
 */
	.macro INTR_FRAME start=1 offset=0
	EMPTY_FRAME \start, SS+8+\offset-RIP
	/*CFI_REL_OFFSET ss, SS+\offset-RIP*/
	CFI_REL_OFFSET rsp, RSP+\offset-RIP
	/*CFI_REL_OFFSET rflags, EFLAGS+\offset-RIP*/
	/*CFI_REL_OFFSET cs, CS+\offset-RIP*/
	CFI_REL_OFFSET rip, RIP+\offset-RIP
	.endm

/*
 * initial frame state for exceptions with error code (and interrupts
 * with vector already pushed)
 */
	.macro XCPT_FRAME start=1 offset=0
	INTR_FRAME \start, RIP+\offset-ORIG_RAX
	.endm

/*
 * frame that enables calling into C.
 */
	.macro PARTIAL_FRAME start=1 offset=0
	XCPT_FRAME \start, ORIG_RAX+\offset-ARGOFFSET
	CFI_REL_OFFSET rdi, RDI+\offset-ARGOFFSET
	CFI_REL_OFFSET rsi, RSI+\offset-ARGOFFSET
	CFI_REL_OFFSET rdx, RDX+\offset-ARGOFFSET
	CFI_REL_OFFSET rcx, RCX+\offset-ARGOFFSET
	CFI_REL_OFFSET rax, RAX+\offset-ARGOFFSET
	CFI_REL_OFFSET r8, R8+\offset-ARGOFFSET
	CFI_REL_OFFSET r9, R9+\offset-ARGOFFSET
	CFI_REL_OFFSET r10, R10+\offset-ARGOFFSET
	CFI_REL_OFFSET r11, R11+\offset-ARGOFFSET
	.endm

/*
 * frame that enables passing a complete pt_regs to a C function.
 */
	.macro DEFAULT_FRAME start=1 offset=0
	PARTIAL_FRAME \start, R11+\offset-R15
	CFI_REL_OFFSET rbx, RBX+\offset
	CFI_REL_OFFSET rbp, RBP+\offset
	CFI_REL_OFFSET r12, R12+\offset
	CFI_REL_OFFSET r13, R13+\offset
	CFI_REL_OFFSET r14, R14+\offset
	CFI_REL_OFFSET r15, R15+\offset
	.endm

ENTRY(save_paranoid)
	XCPT_FRAME 1 RDI+8
	cld
	movq %rdi, RDI+8(%rsp)
	movq %rsi, RSI+8(%rsp)
	movq_cfi rdx, RDX+8
	movq_cfi rcx, RCX+8
	movq_cfi rax, RAX+8
	movq %r8, R8+8(%rsp)
	movq %r9, R9+8(%rsp)
	movq %r10, R10+8(%rsp)
	movq %r11, R11+8(%rsp)
	movq_cfi rbx, RBX+8
	movq %rbp, RBP+8(%rsp)
	movq %r12, R12+8(%rsp)
	movq %r13, R13+8(%rsp)
	movq %r14, R14+8(%rsp)
	movq %r15, R15+8(%rsp)
	movl $1,%ebx
	movl $MSR_GS_BASE,%ecx
	rdmsr
	testl %edx,%edx
	js 1f	/* negative -> in kernel */
	SWAPGS
	xorl %ebx,%ebx
1:	ret
	CFI_ENDPROC
END(save_paranoid)

/*
 * A newly forked process directly context switches into this address.
 *
 * rdi: prev task we switched from
 */
ENTRY(ret_from_fork)
	DEFAULT_FRAME

	LOCK ; btr $TIF_FORK,TI_flags(%r8)

	pushq_cfi $0x0002
	popfq_cfi				# reset kernel eflags

	call schedule_tail			# rdi: 'prev' task parameter

	GET_THREAD_INFO(%rcx)

	RESTORE_REST

	testl $3, CS-ARGOFFSET(%rsp)		# from kernel_thread?
	jz   1f

	testl $_TIF_IA32, TI_flags(%rcx)	# 32-bit compat task needs IRET
	jnz  int_ret_from_sys_call

	RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET
	jmp ret_from_sys_call			# go to the SYSRET fastpath

1:
	subq $REST_SKIP, %rsp	# leave space for volatiles
	CFI_ADJUST_CFA_OFFSET	REST_SKIP
	movq %rbp, %rdi
	call *%rbx
	movl $0, RAX(%rsp)
	RESTORE_REST
	jmp int_ret_from_sys_call
	CFI_ENDPROC
END(ret_from_fork)

/*
 * System call entry. Up to 6 arguments in registers are supported.
 *
 * SYSCALL does not save anything on the stack and does not change the
 * stack pointer.  However, it does mask the flags register for us, so
 * CLD and CLAC are not needed.
 */

/*
 * Register setup:
 * rax  system call number
 * rdi  arg0
 * rcx  return address for syscall/sysret, C arg3
 * rsi  arg1
 * rdx  arg2
 * r10  arg3 	(--> moved to rcx for C)
 * r8   arg4
 * r9   arg5
 * r11  eflags for syscall/sysret, temporary for C
 * r12-r15,rbp,rbx saved by C code, not touched.
 *
 * Interrupts are off on entry.
 * Only called from user space.
 *
 * XXX	if we had a free scratch register we could save the RSP into the stack frame
 *      and report it properly in ps. Unfortunately we haven't.
 *
 * When user can change the frames always force IRET. That is because
 * it deals with uncanonical addresses better. SYSRET has trouble
 * with them due to bugs in both AMD and Intel CPUs.
 */

ENTRY(system_call)
	CFI_STARTPROC	simple
	CFI_SIGNAL_FRAME
	CFI_DEF_CFA	rsp,KERNEL_STACK_OFFSET
	CFI_REGISTER	rip,rcx
	/*CFI_REGISTER	rflags,r11*/
	SWAPGS_UNSAFE_STACK
	/*
	 * A hypervisor implementation might want to use a label
	 * after the swapgs, so that it can do the swapgs
	 * for the guest and jump here on syscall.
	 */
GLOBAL(system_call_after_swapgs)

	movq	%rsp,PER_CPU_VAR(old_rsp)
	movq	PER_CPU_VAR(kernel_stack),%rsp
	/*
	 * No need to follow this irqs off/on section - it's straight
	 * and short:
	 */
	ENABLE_INTERRUPTS(CLBR_NONE)
	SAVE_ARGS 8, 0, rax_enosys=1
	movq_cfi rax,(ORIG_RAX-ARGOFFSET)
	movq  %rcx,RIP-ARGOFFSET(%rsp)
	CFI_REL_OFFSET rip,RIP-ARGOFFSET
	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
	jnz tracesys
system_call_fastpath:
#if __SYSCALL_MASK == ~0
	cmpq $__NR_syscall_max,%rax
#else
	andl $__SYSCALL_MASK,%eax
	cmpl $__NR_syscall_max,%eax
#endif
	ja ret_from_sys_call  /* and return regs->ax */
	movq %r10,%rcx
	call *sys_call_table(,%rax,8)  # XXX:	 rip relative
	movq %rax,RAX-ARGOFFSET(%rsp)
/*
 * Syscall return path ending with SYSRET (fast path)
 * Has incomplete stack frame and undefined top of stack.
 */
ret_from_sys_call:
	testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
	jnz int_ret_from_sys_call_fixup	/* Go the the slow path */

	LOCKDEP_SYS_EXIT
	DISABLE_INTERRUPTS(CLBR_NONE)
	TRACE_IRQS_OFF
	CFI_REMEMBER_STATE
	/*
	 * sysretq will re-enable interrupts:
	 */
	TRACE_IRQS_ON
	movq RIP-ARGOFFSET(%rsp),%rcx
	CFI_REGISTER	rip,rcx
	RESTORE_ARGS 1,-ARG_SKIP,0
	/*CFI_REGISTER	rflags,r11*/
	movq	PER_CPU_VAR(old_rsp), %rsp
	USERGS_SYSRET64

	CFI_RESTORE_STATE

int_ret_from_sys_call_fixup:
	FIXUP_TOP_OF_STACK %r11, -ARGOFFSET
	jmp int_ret_from_sys_call

	/* Do syscall tracing */
tracesys:
	leaq -REST_SKIP(%rsp), %rdi
	movq $AUDIT_ARCH_X86_64, %rsi
	call syscall_trace_enter_phase1
	test %rax, %rax
	jnz tracesys_phase2		/* if needed, run the slow path */
	LOAD_ARGS 0			/* else restore clobbered regs */
	jmp system_call_fastpath	/*      and return to the fast path */

tracesys_phase2:
	SAVE_REST
	FIXUP_TOP_OF_STACK %rdi
	movq %rsp, %rdi
	movq $AUDIT_ARCH_X86_64, %rsi
	movq %rax,%rdx
	call syscall_trace_enter_phase2

	/*
	 * Reload arg registers from stack in case ptrace changed them.
	 * We don't reload %rax because syscall_trace_entry_phase2() returned
	 * the value it wants us to use in the table lookup.
	 */
	LOAD_ARGS ARGOFFSET, 1
	RESTORE_REST
#if __SYSCALL_MASK == ~0
	cmpq $__NR_syscall_max,%rax
#else
	andl $__SYSCALL_MASK,%eax
	cmpl $__NR_syscall_max,%eax
#endif
	ja   int_ret_from_sys_call	/* RAX(%rsp) is already set */
	movq %r10,%rcx	/* fixup for C */
	call *sys_call_table(,%rax,8)
	movq %rax,RAX-ARGOFFSET(%rsp)
	/* Use IRET because user could have changed frame */

/*
 * Syscall return path ending with IRET.
 * Has correct top of stack, but partial stack frame.
 */
GLOBAL(int_ret_from_sys_call)
	DISABLE_INTERRUPTS(CLBR_NONE)
	TRACE_IRQS_OFF
	movl $_TIF_ALLWORK_MASK,%edi
	/* edi:	mask to check */
GLOBAL(int_with_check)
	LOCKDEP_SYS_EXIT_IRQ
	GET_THREAD_INFO(%rcx)
	movl TI_flags(%rcx),%edx
	andl %edi,%edx
	jnz   int_careful
	andl    $~TS_COMPAT,TI_status(%rcx)
	jmp   retint_swapgs

	/* Either reschedule or signal or syscall exit tracking needed. */
	/* First do a reschedule test. */
	/* edx:	work, edi: workmask */
int_careful:
	bt $TIF_NEED_RESCHED,%edx
	jnc  int_very_careful
	TRACE_IRQS_ON
	ENABLE_INTERRUPTS(CLBR_NONE)
	pushq_cfi %rdi
	SCHEDULE_USER
	popq_cfi %rdi
	DISABLE_INTERRUPTS(CLBR_NONE)
	TRACE_IRQS_OFF
	jmp int_with_check

	/* handle signals and tracing -- both require a full stack frame */
int_very_careful:
	TRACE_IRQS_ON
	ENABLE_INTERRUPTS(CLBR_NONE)
int_check_syscall_exit_work:
	SAVE_REST
	/* Check for syscall exit trace */
	testl $_TIF_WORK_SYSCALL_EXIT,%edx
	jz int_signal
	pushq_cfi %rdi
	leaq 8(%rsp),%rdi	# &ptregs -> arg1
	call syscall_trace_leave
	popq_cfi %rdi
	andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi
	jmp int_restore_rest

int_signal:
	testl $_TIF_DO_NOTIFY_MASK,%edx
	jz 1f
	movq %rsp,%rdi		# &ptregs -> arg1
	xorl %esi,%esi		# oldset -> arg2
	call do_notify_resume
1:	movl $_TIF_WORK_MASK,%edi
int_restore_rest:
	RESTORE_REST
	DISABLE_INTERRUPTS(CLBR_NONE)
	TRACE_IRQS_OFF
	jmp int_with_check
	CFI_ENDPROC
END(system_call)

	.macro FORK_LIKE func
ENTRY(stub_\func)
	CFI_STARTPROC
	popq	%r11			/* save return address */
	PARTIAL_FRAME 0
	SAVE_REST
	pushq	%r11			/* put it back on stack */
	FIXUP_TOP_OF_STACK %r11, 8
	DEFAULT_FRAME 0 8		/* offset 8: return address */
	call sys_\func
	RESTORE_TOP_OF_STACK %r11, 8
	ret $REST_SKIP		/* pop extended registers */
	CFI_ENDPROC
END(stub_\func)
	.endm

	.macro FIXED_FRAME label,func
ENTRY(\label)
	CFI_STARTPROC
	PARTIAL_FRAME 0 8		/* offset 8: return address */
	FIXUP_TOP_OF_STACK %r11, 8-ARGOFFSET
	call \func
	RESTORE_TOP_OF_STACK %r11, 8-ARGOFFSET
	ret
	CFI_ENDPROC
END(\label)
	.endm

	FORK_LIKE  clone
	FORK_LIKE  fork
	FORK_LIKE  vfork
	FIXED_FRAME stub_iopl, sys_iopl

ENTRY(stub_execve)
	CFI_STARTPROC
	addq $8, %rsp
	PARTIAL_FRAME 0
	SAVE_REST
	FIXUP_TOP_OF_STACK %r11
	call sys_execve
	movq %rax,RAX(%rsp)
	RESTORE_REST
	jmp int_ret_from_sys_call
	CFI_ENDPROC
END(stub_execve)

ENTRY(stub_execveat)
	CFI_STARTPROC
	addq $8, %rsp
	PARTIAL_FRAME 0
	SAVE_REST
	FIXUP_TOP_OF_STACK %r11
	call sys_execveat
	RESTORE_TOP_OF_STACK %r11
	movq %rax,RAX(%rsp)
	RESTORE_REST
	jmp int_ret_from_sys_call
	CFI_ENDPROC
END(stub_execveat)

/*
 * sigreturn is special because it needs to restore all registers on return.
 * This cannot be done with SYSRET, so use the IRET return path instead.
 */
ENTRY(stub_rt_sigreturn)
	CFI_STARTPROC
	addq $8, %rsp
	PARTIAL_FRAME 0
	SAVE_REST
	FIXUP_TOP_OF_STACK %r11
	call sys_rt_sigreturn
	movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer
	RESTORE_REST
	jmp int_ret_from_sys_call
	CFI_ENDPROC
END(stub_rt_sigreturn)

#ifdef CONFIG_X86_X32_ABI
ENTRY(stub_x32_rt_sigreturn)
	CFI_STARTPROC
	addq $8, %rsp
	PARTIAL_FRAME 0
	SAVE_REST
	FIXUP_TOP_OF_STACK %r11
	call sys32_x32_rt_sigreturn
	movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer
	RESTORE_REST
	jmp int_ret_from_sys_call
	CFI_ENDPROC
END(stub_x32_rt_sigreturn)

ENTRY(stub_x32_execve)
	CFI_STARTPROC
	addq $8, %rsp
	PARTIAL_FRAME 0
	SAVE_REST
	FIXUP_TOP_OF_STACK %r11
	call compat_sys_execve
	RESTORE_TOP_OF_STACK %r11
	movq %rax,RAX(%rsp)
	RESTORE_REST
	jmp int_ret_from_sys_call
	CFI_ENDPROC
END(stub_x32_execve)

ENTRY(stub_x32_execveat)
	CFI_STARTPROC
	addq $8, %rsp
	PARTIAL_FRAME 0
	SAVE_REST
	FIXUP_TOP_OF_STACK %r11
	call compat_sys_execveat
	RESTORE_TOP_OF_STACK %r11
	movq %rax,RAX(%rsp)
	RESTORE_REST
	jmp int_ret_from_sys_call
	CFI_ENDPROC
END(stub_x32_execveat)

#endif

/*
 * Build the entry stubs and pointer table with some assembler magic.
 * We pack 7 stubs into a single 32-byte chunk, which will fit in a
 * single cache line on all modern x86 implementations.
 */
	.section .init.rodata,"a"
ENTRY(interrupt)
	.section .entry.text
	.p2align 5
	.p2align CONFIG_X86_L1_CACHE_SHIFT
ENTRY(irq_entries_start)
	INTR_FRAME
vector=FIRST_EXTERNAL_VECTOR
.rept (FIRST_SYSTEM_VECTOR-FIRST_EXTERNAL_VECTOR+6)/7
	.balign 32
  .rept	7
    .if vector < FIRST_SYSTEM_VECTOR
      .if vector <> FIRST_EXTERNAL_VECTOR
	CFI_ADJUST_CFA_OFFSET -8
      .endif
1:	pushq_cfi $(~vector+0x80)	/* Note: always in signed byte range */
      .if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6
	jmp 2f
      .endif
      .previous
	.quad 1b
      .section .entry.text
vector=vector+1
    .endif
  .endr
2:	jmp common_interrupt
.endr
	CFI_ENDPROC
END(irq_entries_start)

.previous
END(interrupt)
.previous

/*
 * Interrupt entry/exit.
 *
 * Interrupt entry points save only callee clobbered registers in fast path.
 *
 * Entry runs with interrupts off.
 */

/* 0(%rsp): ~(interrupt number) */
	.macro interrupt func
	/* reserve pt_regs for scratch regs and rbp */
	subq $ORIG_RAX-RBP, %rsp
	CFI_ADJUST_CFA_OFFSET ORIG_RAX-RBP
	cld
	/* start from rbp in pt_regs and jump over */
	movq_cfi rdi, (RDI-RBP)
	movq_cfi rsi, (RSI-RBP)
	movq_cfi rdx, (RDX-RBP)
	movq_cfi rcx, (RCX-RBP)
	movq_cfi rax, (RAX-RBP)
	movq_cfi  r8,  (R8-RBP)
	movq_cfi  r9,  (R9-RBP)
	movq_cfi r10, (R10-RBP)
	movq_cfi r11, (R11-RBP)

	/* Save rbp so that we can unwind from get_irq_regs() */
	movq_cfi rbp, 0

	/* Save previous stack value */
	movq %rsp, %rsi

	leaq -RBP(%rsp),%rdi	/* arg1 for handler */
	testl $3, CS-RBP(%rsi)
	je 1f
	SWAPGS
	/*
	 * irq_count is used to check if a CPU is already on an interrupt stack
	 * or not. While this is essentially redundant with preempt_count it is
	 * a little cheaper to use a separate counter in the PDA (short of
	 * moving irq_enter into assembly, which would be too much work)
	 */
1:	incl PER_CPU_VAR(irq_count)
	cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
	CFI_DEF_CFA_REGISTER	rsi

	/* Store previous stack value */
	pushq %rsi
	CFI_ESCAPE	0x0f /* DW_CFA_def_cfa_expression */, 6, \
			0x77 /* DW_OP_breg7 */, 0, \
			0x06 /* DW_OP_deref */, \
			0x08 /* DW_OP_const1u */, SS+8-RBP, \
			0x22 /* DW_OP_plus */
	/* We entered an interrupt context - irqs are off: */
	TRACE_IRQS_OFF

	call \func
	.endm

	/*
	 * The interrupt stubs push (~vector+0x80) onto the stack and
	 * then jump to common_interrupt.
	 */
	.p2align CONFIG_X86_L1_CACHE_SHIFT
common_interrupt:
	XCPT_FRAME
	ASM_CLAC
	addq $-0x80,(%rsp)		/* Adjust vector to [-256,-1] range */
	interrupt do_IRQ
	/* 0(%rsp): old_rsp-ARGOFFSET */
ret_from_intr:
	DISABLE_INTERRUPTS(CLBR_NONE)
	TRACE_IRQS_OFF
	decl PER_CPU_VAR(irq_count)

	/* Restore saved previous stack */
	popq %rsi
	CFI_DEF_CFA rsi,SS+8-RBP	/* reg/off reset after def_cfa_expr */
	leaq ARGOFFSET-RBP(%rsi), %rsp
	CFI_DEF_CFA_REGISTER	rsp
	CFI_ADJUST_CFA_OFFSET	RBP-ARGOFFSET

exit_intr:
	GET_THREAD_INFO(%rcx)
	testl $3,CS-ARGOFFSET(%rsp)
	je retint_kernel

	/* Interrupt came from user space */
	/*
	 * Has a correct top of stack, but a partial stack frame
	 * %rcx: thread info. Interrupts off.
	 */
retint_with_reschedule:
	movl $_TIF_WORK_MASK,%edi
retint_check:
	LOCKDEP_SYS_EXIT_IRQ
	movl TI_flags(%rcx),%edx
	andl %edi,%edx
	CFI_REMEMBER_STATE
	jnz  retint_careful

retint_swapgs:		/* return to user-space */
	/*
	 * The iretq could re-enable interrupts:
	 */
	DISABLE_INTERRUPTS(CLBR_ANY)
	TRACE_IRQS_IRETQ

	/*
	 * Try to use SYSRET instead of IRET if we're returning to
	 * a completely clean 64-bit userspace context.
	 */
	movq (RCX-R11)(%rsp), %rcx
	cmpq %rcx,(RIP-R11)(%rsp)		/* RCX == RIP */
	jne opportunistic_sysret_failed

	/*
	 * On Intel CPUs, sysret with non-canonical RCX/RIP will #GP
	 * in kernel space.  This essentially lets the user take over
	 * the kernel, since userspace controls RSP.  It's not worth
	 * testing for canonicalness exactly -- this check detects any
	 * of the 17 high bits set, which is true for non-canonical
	 * or kernel addresses.  (This will pessimize vsyscall=native.
	 * Big deal.)
	 *
	 * If virtual addresses ever become wider, this will need
	 * to be updated to remain correct on both old and new CPUs.
	 */
	.ifne __VIRTUAL_MASK_SHIFT - 47
	.error "virtual address width changed -- sysret checks need update"
	.endif
	shr $__VIRTUAL_MASK_SHIFT, %rcx
	jnz opportunistic_sysret_failed

	cmpq $__USER_CS,(CS-R11)(%rsp)		/* CS must match SYSRET */
	jne opportunistic_sysret_failed

	movq (R11-ARGOFFSET)(%rsp), %r11
	cmpq %r11,(EFLAGS-ARGOFFSET)(%rsp)	/* R11 == RFLAGS */
	jne opportunistic_sysret_failed

	testq $X86_EFLAGS_RF,%r11		/* sysret can't restore RF */
	jnz opportunistic_sysret_failed

	/* nothing to check for RSP */

	cmpq $__USER_DS,(SS-ARGOFFSET)(%rsp)	/* SS must match SYSRET */
	jne opportunistic_sysret_failed

	/*
	 * We win!  This label is here just for ease of understanding
	 * perf profiles.  Nothing jumps here.
	 */
irq_return_via_sysret:
	CFI_REMEMBER_STATE
	RESTORE_ARGS 1,8,1
	movq (RSP-RIP)(%rsp),%rsp
	USERGS_SYSRET64
	CFI_RESTORE_STATE

opportunistic_sysret_failed:
	SWAPGS
	jmp restore_args

retint_restore_args:	/* return to kernel space */
	DISABLE_INTERRUPTS(CLBR_ANY)
	/*
	 * The iretq could re-enable interrupts:
	 */
	TRACE_IRQS_IRETQ
restore_args:
	RESTORE_ARGS 1,8,1

irq_return:
	INTERRUPT_RETURN

ENTRY(native_iret)
	/*
	 * Are we returning to a stack segment from the LDT?  Note: in
	 * 64-bit mode SS:RSP on the exception stack is always valid.
	 */
#ifdef CONFIG_X86_ESPFIX64
	testb $4,(SS-RIP)(%rsp)
	jnz native_irq_return_ldt
#endif

.global native_irq_return_iret
native_irq_return_iret:
	/*
	 * This may fault.  Non-paranoid faults on return to userspace are
	 * handled by fixup_bad_iret.  These include #SS, #GP, and #NP.
	 * Double-faults due to espfix64 are handled in do_double_fault.
	 * Other faults here are fatal.
	 */
	iretq

#ifdef CONFIG_X86_ESPFIX64
native_irq_return_ldt:
	pushq_cfi %rax
	pushq_cfi %rdi
	SWAPGS
	movq PER_CPU_VAR(espfix_waddr),%rdi
	movq %rax,(0*8)(%rdi)	/* RAX */
	movq (2*8)(%rsp),%rax	/* RIP */
	movq %rax,(1*8)(%rdi)
	movq (3*8)(%rsp),%rax	/* CS */
	movq %rax,(2*8)(%rdi)
	movq (4*8)(%rsp),%rax	/* RFLAGS */
	movq %rax,(3*8)(%rdi)
	movq (6*8)(%rsp),%rax	/* SS */
	movq %rax,(5*8)(%rdi)
	movq (5*8)(%rsp),%rax	/* RSP */
	movq %rax,(4*8)(%rdi)
	andl $0xffff0000,%eax
	popq_cfi %rdi
	orq PER_CPU_VAR(espfix_stack),%rax
	SWAPGS
	movq %rax,%rsp
	popq_cfi %rax
	jmp native_irq_return_iret
#endif

	/* edi: workmask, edx: work */
retint_careful:
	CFI_RESTORE_STATE
	bt    $TIF_NEED_RESCHED,%edx
	jnc   retint_signal
	TRACE_IRQS_ON
	ENABLE_INTERRUPTS(CLBR_NONE)
	pushq_cfi %rdi
	SCHEDULE_USER
	popq_cfi %rdi
	GET_THREAD_INFO(%rcx)
	DISABLE_INTERRUPTS(CLBR_NONE)
	TRACE_IRQS_OFF
	jmp retint_check

retint_signal:
	testl $_TIF_DO_NOTIFY_MASK,%edx
	jz    retint_swapgs
	TRACE_IRQS_ON
	ENABLE_INTERRUPTS(CLBR_NONE)
	SAVE_REST
	movq $-1,ORIG_RAX(%rsp)
	xorl %esi,%esi		# oldset
	movq %rsp,%rdi		# &pt_regs
	call do_notify_resume
	RESTORE_REST
	DISABLE_INTERRUPTS(CLBR_NONE)
	TRACE_IRQS_OFF
	GET_THREAD_INFO(%rcx)
	jmp retint_with_reschedule

#ifdef CONFIG_PREEMPT
	/* Returning to kernel space. Check if we need preemption */
	/* rcx:	 threadinfo. interrupts off. */
ENTRY(retint_kernel)
	cmpl $0,PER_CPU_VAR(__preempt_count)
	jnz  retint_restore_args
	bt   $9,EFLAGS-ARGOFFSET(%rsp)	/* interrupts off? */
	jnc  retint_restore_args
	call preempt_schedule_irq
	jmp exit_intr
#endif
	CFI_ENDPROC
END(common_interrupt)

/*
 * APIC interrupts.
 */
.macro apicinterrupt3 num sym do_sym
ENTRY(\sym)
	INTR_FRAME
	ASM_CLAC
	pushq_cfi $~(\num)
.Lcommon_\sym:
	interrupt \do_sym
	jmp ret_from_intr
	CFI_ENDPROC
END(\sym)
.endm

#ifdef CONFIG_TRACING
#define trace(sym) trace_##sym
#define smp_trace(sym) smp_trace_##sym

.macro trace_apicinterrupt num sym
apicinterrupt3 \num trace(\sym) smp_trace(\sym)
.endm
#else
.macro trace_apicinterrupt num sym do_sym
.endm
#endif

.macro apicinterrupt num sym do_sym
apicinterrupt3 \num \sym \do_sym
trace_apicinterrupt \num \sym
.endm

#ifdef CONFIG_SMP
apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR \
	irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt
apicinterrupt3 REBOOT_VECTOR \
	reboot_interrupt smp_reboot_interrupt
#endif

#ifdef CONFIG_X86_UV
apicinterrupt3 UV_BAU_MESSAGE \
	uv_bau_message_intr1 uv_bau_message_interrupt
#endif
apicinterrupt LOCAL_TIMER_VECTOR \
	apic_timer_interrupt smp_apic_timer_interrupt
apicinterrupt X86_PLATFORM_IPI_VECTOR \
	x86_platform_ipi smp_x86_platform_ipi

#ifdef CONFIG_HAVE_KVM
apicinterrupt3 POSTED_INTR_VECTOR \
	kvm_posted_intr_ipi smp_kvm_posted_intr_ipi
#endif

#ifdef CONFIG_X86_MCE_THRESHOLD
apicinterrupt THRESHOLD_APIC_VECTOR \
	threshold_interrupt smp_threshold_interrupt
#endif

#ifdef CONFIG_X86_THERMAL_VECTOR
apicinterrupt THERMAL_APIC_VECTOR \
	thermal_interrupt smp_thermal_interrupt
#endif

#ifdef CONFIG_SMP
apicinterrupt CALL_FUNCTION_SINGLE_VECTOR \
	call_function_single_interrupt smp_call_function_single_interrupt
apicinterrupt CALL_FUNCTION_VECTOR \
	call_function_interrupt smp_call_function_interrupt
apicinterrupt RESCHEDULE_VECTOR \
	reschedule_interrupt smp_reschedule_interrupt
#endif

apicinterrupt ERROR_APIC_VECTOR \
	error_interrupt smp_error_interrupt
apicinterrupt SPURIOUS_APIC_VECTOR \
	spurious_interrupt smp_spurious_interrupt

#ifdef CONFIG_IRQ_WORK
apicinterrupt IRQ_WORK_VECTOR \
	irq_work_interrupt smp_irq_work_interrupt
#endif

/*
 * Exception entry points.
 */
#define INIT_TSS_IST(x) PER_CPU_VAR(init_tss) + (TSS_ist + ((x) - 1) * 8)

.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
ENTRY(\sym)
	/* Sanity check */
	.if \shift_ist != -1 && \paranoid == 0
	.error "using shift_ist requires paranoid=1"
	.endif

	.if \has_error_code
	XCPT_FRAME
	.else
	INTR_FRAME
	.endif

	ASM_CLAC
	PARAVIRT_ADJUST_EXCEPTION_FRAME

	.ifeq \has_error_code
	pushq_cfi $-1			/* ORIG_RAX: no syscall to restart */
	.endif

	subq $ORIG_RAX-R15, %rsp
	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15

	.if \paranoid
	.if \paranoid == 1
	CFI_REMEMBER_STATE
	testl $3, CS(%rsp)		/* If coming from userspace, switch */
	jnz 1f				/* stacks. */
	.endif
	call save_paranoid
	.else
	call error_entry
	.endif

	DEFAULT_FRAME 0

	.if \paranoid
	.if \shift_ist != -1
	TRACE_IRQS_OFF_DEBUG		/* reload IDT in case of recursion */
	.else
	TRACE_IRQS_OFF
	.endif
	.endif

	movq %rsp,%rdi			/* pt_regs pointer */

	.if \has_error_code
	movq ORIG_RAX(%rsp),%rsi	/* get error code */
	movq $-1,ORIG_RAX(%rsp)		/* no syscall to restart */
	.else
	xorl %esi,%esi			/* no error code */
	.endif

	.if \shift_ist != -1
	subq $EXCEPTION_STKSZ, INIT_TSS_IST(\shift_ist)
	.endif

	call \do_sym

	.if \shift_ist != -1
	addq $EXCEPTION_STKSZ, INIT_TSS_IST(\shift_ist)
	.endif

	.if \paranoid
	jmp paranoid_exit		/* %ebx: no swapgs flag */
	.else
	jmp error_exit			/* %ebx: no swapgs flag */
	.endif

	.if \paranoid == 1
	CFI_RESTORE_STATE
	/*
	 * Paranoid entry from userspace.  Switch stacks and treat it
	 * as a normal entry.  This means that paranoid handlers
	 * run in real process context if user_mode(regs).
	 */
1:
	call error_entry

	DEFAULT_FRAME 0

	movq %rsp,%rdi			/* pt_regs pointer */
	call sync_regs
	movq %rax,%rsp			/* switch stack */

	movq %rsp,%rdi			/* pt_regs pointer */

	.if \has_error_code
	movq ORIG_RAX(%rsp),%rsi	/* get error code */
	movq $-1,ORIG_RAX(%rsp)		/* no syscall to restart */
	.else
	xorl %esi,%esi			/* no error code */
	.endif

	call \do_sym

	jmp error_exit			/* %ebx: no swapgs flag */
	.endif

	CFI_ENDPROC
END(\sym)
.endm

#ifdef CONFIG_TRACING
.macro trace_idtentry sym do_sym has_error_code:req
idtentry trace(\sym) trace(\do_sym) has_error_code=\has_error_code
idtentry \sym \do_sym has_error_code=\has_error_code
.endm
#else
.macro trace_idtentry sym do_sym has_error_code:req
idtentry \sym \do_sym has_error_code=\has_error_code
.endm
#endif

idtentry divide_error do_divide_error has_error_code=0
idtentry overflow do_overflow has_error_code=0
idtentry bounds do_bounds has_error_code=0
idtentry invalid_op do_invalid_op has_error_code=0
idtentry device_not_available do_device_not_available has_error_code=0
idtentry double_fault do_double_fault has_error_code=1 paranoid=2
idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0
idtentry invalid_TSS do_invalid_TSS has_error_code=1
idtentry segment_not_present do_segment_not_present has_error_code=1
idtentry spurious_interrupt_bug do_spurious_interrupt_bug has_error_code=0
idtentry coprocessor_error do_coprocessor_error has_error_code=0
idtentry alignment_check do_alignment_check has_error_code=1
idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0


	/* Reload gs selector with exception handling */
	/* edi:  new selector */
ENTRY(native_load_gs_index)
	CFI_STARTPROC
	pushfq_cfi
	DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
	SWAPGS
gs_change:
	movl %edi,%gs
2:	mfence		/* workaround */
	SWAPGS
	popfq_cfi
	ret
	CFI_ENDPROC
END(native_load_gs_index)

	_ASM_EXTABLE(gs_change,bad_gs)
	.section .fixup,"ax"
	/* running with kernelgs */
bad_gs:
	SWAPGS			/* switch back to user gs */
	xorl %eax,%eax
	movl %eax,%gs
	jmp  2b
	.previous

/* Call softirq on interrupt stack. Interrupts are off. */
ENTRY(do_softirq_own_stack)
	CFI_STARTPROC
	pushq_cfi %rbp
	CFI_REL_OFFSET rbp,0
	mov  %rsp,%rbp
	CFI_DEF_CFA_REGISTER rbp
	incl PER_CPU_VAR(irq_count)
	cmove PER_CPU_VAR(irq_stack_ptr),%rsp
	push  %rbp			# backlink for old unwinder
	call __do_softirq
	leaveq
	CFI_RESTORE		rbp
	CFI_DEF_CFA_REGISTER	rsp
	CFI_ADJUST_CFA_OFFSET   -8
	decl PER_CPU_VAR(irq_count)
	ret
	CFI_ENDPROC
END(do_softirq_own_stack)

#ifdef CONFIG_XEN
idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0

/*
 * A note on the "critical region" in our callback handler.
 * We want to avoid stacking callback handlers due to events occurring
 * during handling of the last event. To do this, we keep events disabled
 * until we've done all processing. HOWEVER, we must enable events before
 * popping the stack frame (can't be done atomically) and so it would still
 * be possible to get enough handler activations to overflow the stack.
 * Although unlikely, bugs of that kind are hard to track down, so we'd
 * like to avoid the possibility.
 * So, on entry to the handler we detect whether we interrupted an
 * existing activation in its critical region -- if so, we pop the current
 * activation and restart the handler using the previous one.
 */
ENTRY(xen_do_hypervisor_callback)   # do_hypervisor_callback(struct *pt_regs)
	CFI_STARTPROC
/*
 * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will
 * see the correct pointer to the pt_regs
 */
	movq %rdi, %rsp            # we don't return, adjust the stack frame
	CFI_ENDPROC
	DEFAULT_FRAME
11:	incl PER_CPU_VAR(irq_count)
	movq %rsp,%rbp
	CFI_DEF_CFA_REGISTER rbp
	cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
	pushq %rbp			# backlink for old unwinder
	call xen_evtchn_do_upcall
	popq %rsp
	CFI_DEF_CFA_REGISTER rsp
	decl PER_CPU_VAR(irq_count)
	jmp  error_exit
	CFI_ENDPROC
END(xen_do_hypervisor_callback)

/*
 * Hypervisor uses this for application faults while it executes.
 * We get here for two reasons:
 *  1. Fault while reloading DS, ES, FS or GS
 *  2. Fault while executing IRET
 * Category 1 we do not need to fix up as Xen has already reloaded all segment
 * registers that could be reloaded and zeroed the others.
 * Category 2 we fix up by killing the current process. We cannot use the
 * normal Linux return path in this case because if we use the IRET hypercall
 * to pop the stack frame we end up in an infinite loop of failsafe callbacks.
 * We distinguish between categories by comparing each saved segment register
 * with its current contents: any discrepancy means we in category 1.
 */
ENTRY(xen_failsafe_callback)
	INTR_FRAME 1 (6*8)
	/*CFI_REL_OFFSET gs,GS*/
	/*CFI_REL_OFFSET fs,FS*/
	/*CFI_REL_OFFSET es,ES*/
	/*CFI_REL_OFFSET ds,DS*/
	CFI_REL_OFFSET r11,8
	CFI_REL_OFFSET rcx,0
	movw %ds,%cx
	cmpw %cx,0x10(%rsp)
	CFI_REMEMBER_STATE
	jne 1f
	movw %es,%cx
	cmpw %cx,0x18(%rsp)
	jne 1f
	movw %fs,%cx
	cmpw %cx,0x20(%rsp)
	jne 1f
	movw %gs,%cx
	cmpw %cx,0x28(%rsp)
	jne 1f
	/* All segments match their saved values => Category 2 (Bad IRET). */
	movq (%rsp),%rcx
	CFI_RESTORE rcx
	movq 8(%rsp),%r11
	CFI_RESTORE r11
	addq $0x30,%rsp
	CFI_ADJUST_CFA_OFFSET -0x30
	pushq_cfi $0	/* RIP */
	pushq_cfi %r11
	pushq_cfi %rcx
	jmp general_protection
	CFI_RESTORE_STATE
1:	/* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */
	movq (%rsp),%rcx
	CFI_RESTORE rcx
	movq 8(%rsp),%r11
	CFI_RESTORE r11
	addq $0x30,%rsp
	CFI_ADJUST_CFA_OFFSET -0x30
	pushq_cfi $-1 /* orig_ax = -1 => not a system call */
	SAVE_ALL
	jmp error_exit
	CFI_ENDPROC
END(xen_failsafe_callback)

apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
	xen_hvm_callback_vector xen_evtchn_do_upcall

#endif /* CONFIG_XEN */

#if IS_ENABLED(CONFIG_HYPERV)
apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
	hyperv_callback_vector hyperv_vector_handler
#endif /* CONFIG_HYPERV */

idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
idtentry stack_segment do_stack_segment has_error_code=1
#ifdef CONFIG_XEN
idtentry xen_debug do_debug has_error_code=0
idtentry xen_int3 do_int3 has_error_code=0
idtentry xen_stack_segment do_stack_segment has_error_code=1
#endif
idtentry general_protection do_general_protection has_error_code=1
trace_idtentry page_fault do_page_fault has_error_code=1
#ifdef CONFIG_KVM_GUEST
idtentry async_page_fault do_async_page_fault has_error_code=1
#endif
#ifdef CONFIG_X86_MCE
idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip)
#endif

	/*
	 * "Paranoid" exit path from exception stack.  This is invoked
	 * only on return from non-NMI IST interrupts that came
	 * from kernel space.
	 *
	 * We may be returning to very strange contexts (e.g. very early
	 * in syscall entry), so checking for preemption here would
	 * be complicated.  Fortunately, we there's no good reason
	 * to try to handle preemption here.
	 */

	/* ebx:	no swapgs flag */
ENTRY(paranoid_exit)
	DEFAULT_FRAME
	DISABLE_INTERRUPTS(CLBR_NONE)
	TRACE_IRQS_OFF_DEBUG
	testl %ebx,%ebx				/* swapgs needed? */
	jnz paranoid_restore
	TRACE_IRQS_IRETQ 0
	SWAPGS_UNSAFE_STACK
	RESTORE_ALL 8
	INTERRUPT_RETURN
paranoid_restore:
	TRACE_IRQS_IRETQ_DEBUG 0
	RESTORE_ALL 8
	INTERRUPT_RETURN
	CFI_ENDPROC
END(paranoid_exit)

/*
 * Exception entry point. This expects an error code/orig_rax on the stack.
 * returns in "no swapgs flag" in %ebx.
 */
ENTRY(error_entry)
	XCPT_FRAME
	CFI_ADJUST_CFA_OFFSET 15*8
	/* oldrax contains error code */
	cld
	movq %rdi, RDI+8(%rsp)
	movq %rsi, RSI+8(%rsp)
	movq %rdx, RDX+8(%rsp)
	movq %rcx, RCX+8(%rsp)
	movq %rax, RAX+8(%rsp)
	movq  %r8,  R8+8(%rsp)
	movq  %r9,  R9+8(%rsp)
	movq %r10, R10+8(%rsp)
	movq %r11, R11+8(%rsp)
	movq_cfi rbx, RBX+8
	movq %rbp, RBP+8(%rsp)
	movq %r12, R12+8(%rsp)
	movq %r13, R13+8(%rsp)
	movq %r14, R14+8(%rsp)
	movq %r15, R15+8(%rsp)
	xorl %ebx,%ebx
	testl $3,CS+8(%rsp)
	je error_kernelspace
error_swapgs:
	SWAPGS
error_sti:
	TRACE_IRQS_OFF
	ret

/*
 * There are two places in the kernel that can potentially fault with
 * usergs. Handle them here.  B stepping K8s sometimes report a
 * truncated RIP for IRET exceptions returning to compat mode. Check
 * for these here too.
 */
error_kernelspace:
	CFI_REL_OFFSET rcx, RCX+8
	incl %ebx
	leaq native_irq_return_iret(%rip),%rcx
	cmpq %rcx,RIP+8(%rsp)
	je error_bad_iret
	movl %ecx,%eax	/* zero extend */
	cmpq %rax,RIP+8(%rsp)
	je bstep_iret
	cmpq $gs_change,RIP+8(%rsp)
	je error_swapgs
	jmp error_sti

bstep_iret:
	/* Fix truncated RIP */
	movq %rcx,RIP+8(%rsp)
	/* fall through */

error_bad_iret:
	SWAPGS
	mov %rsp,%rdi
	call fixup_bad_iret
	mov %rax,%rsp
	decl %ebx	/* Return to usergs */
	jmp error_sti
	CFI_ENDPROC
END(error_entry)


/* ebx:	no swapgs flag (1: don't need swapgs, 0: need it) */
ENTRY(error_exit)
	DEFAULT_FRAME
	movl %ebx,%eax
	RESTORE_REST
	DISABLE_INTERRUPTS(CLBR_NONE)
	TRACE_IRQS_OFF
	GET_THREAD_INFO(%rcx)
	testl %eax,%eax
	jne retint_kernel
	LOCKDEP_SYS_EXIT_IRQ
	movl TI_flags(%rcx),%edx
	movl $_TIF_WORK_MASK,%edi
	andl %edi,%edx
	jnz retint_careful
	jmp retint_swapgs
	CFI_ENDPROC
END(error_exit)

/*
 * Test if a given stack is an NMI stack or not.
 */
	.macro test_in_nmi reg stack nmi_ret normal_ret
	cmpq %\reg, \stack
	ja \normal_ret
	subq $EXCEPTION_STKSZ, %\reg
	cmpq %\reg, \stack
	jb \normal_ret
	jmp \nmi_ret
	.endm

	/* runs on exception stack */
ENTRY(nmi)
	INTR_FRAME
	PARAVIRT_ADJUST_EXCEPTION_FRAME
	/*
	 * We allow breakpoints in NMIs. If a breakpoint occurs, then
	 * the iretq it performs will take us out of NMI context.
	 * This means that we can have nested NMIs where the next
	 * NMI is using the top of the stack of the previous NMI. We
	 * can't let it execute because the nested NMI will corrupt the
	 * stack of the previous NMI. NMI handlers are not re-entrant
	 * anyway.
	 *
	 * To handle this case we do the following:
	 *  Check the a special location on the stack that contains
	 *  a variable that is set when NMIs are executing.
	 *  The interrupted task's stack is also checked to see if it
	 *  is an NMI stack.
	 *  If the variable is not set and the stack is not the NMI
	 *  stack then:
	 *    o Set the special variable on the stack
	 *    o Copy the interrupt frame into a "saved" location on the stack
	 *    o Copy the interrupt frame into a "copy" location on the stack
	 *    o Continue processing the NMI
	 *  If the variable is set or the previous stack is the NMI stack:
	 *    o Modify the "copy" location to jump to the repeate_nmi
	 *    o return back to the first NMI
	 *
	 * Now on exit of the first NMI, we first clear the stack variable
	 * The NMI stack will tell any nested NMIs at that point that it is
	 * nested. Then we pop the stack normally with iret, and if there was
	 * a nested NMI that updated the copy interrupt stack frame, a
	 * jump will be made to the repeat_nmi code that will handle the second
	 * NMI.
	 */

	/* Use %rdx as out temp variable throughout */
	pushq_cfi %rdx
	CFI_REL_OFFSET rdx, 0

	/*
	 * If %cs was not the kernel segment, then the NMI triggered in user
	 * space, which means it is definitely not nested.
	 */
	cmpl $__KERNEL_CS, 16(%rsp)
	jne first_nmi

	/*
	 * Check the special variable on the stack to see if NMIs are
	 * executing.
	 */
	cmpl $1, -8(%rsp)
	je nested_nmi

	/*
	 * Now test if the previous stack was an NMI stack.
	 * We need the double check. We check the NMI stack to satisfy the
	 * race when the first NMI clears the variable before returning.
	 * We check the variable because the first NMI could be in a
	 * breakpoint routine using a breakpoint stack.
	 */
	lea 6*8(%rsp), %rdx
	test_in_nmi rdx, 4*8(%rsp), nested_nmi, first_nmi
	CFI_REMEMBER_STATE

nested_nmi:
	/*
	 * Do nothing if we interrupted the fixup in repeat_nmi.
	 * It's about to repeat the NMI handler, so we are fine
	 * with ignoring this one.
	 */
	movq $repeat_nmi, %rdx
	cmpq 8(%rsp), %rdx
	ja 1f
	movq $end_repeat_nmi, %rdx
	cmpq 8(%rsp), %rdx
	ja nested_nmi_out

1:
	/* Set up the interrupted NMIs stack to jump to repeat_nmi */
	leaq -1*8(%rsp), %rdx
	movq %rdx, %rsp
	CFI_ADJUST_CFA_OFFSET 1*8
	leaq -10*8(%rsp), %rdx
	pushq_cfi $__KERNEL_DS
	pushq_cfi %rdx
	pushfq_cfi
	pushq_cfi $__KERNEL_CS
	pushq_cfi $repeat_nmi

	/* Put stack back */
	addq $(6*8), %rsp
	CFI_ADJUST_CFA_OFFSET -6*8

nested_nmi_out:
	popq_cfi %rdx
	CFI_RESTORE rdx

	/* No need to check faults here */
	INTERRUPT_RETURN

	CFI_RESTORE_STATE
first_nmi:
	/*
	 * Because nested NMIs will use the pushed location that we
	 * stored in rdx, we must keep that space available.
	 * Here's what our stack frame will look like:
	 * +-------------------------+
	 * | original SS             |
	 * | original Return RSP     |
	 * | original RFLAGS         |
	 * | original CS             |
	 * | original RIP            |
	 * +-------------------------+
	 * | temp storage for rdx    |
	 * +-------------------------+
	 * | NMI executing variable  |
	 * +-------------------------+
	 * | copied SS               |
	 * | copied Return RSP       |
	 * | copied RFLAGS           |
	 * | copied CS               |
	 * | copied RIP              |
	 * +-------------------------+
	 * | Saved SS                |
	 * | Saved Return RSP        |
	 * | Saved RFLAGS            |
	 * | Saved CS                |
	 * | Saved RIP               |
	 * +-------------------------+
	 * | pt_regs                 |
	 * +-------------------------+
	 *
	 * The saved stack frame is used to fix up the copied stack frame
	 * that a nested NMI may change to make the interrupted NMI iret jump
	 * to the repeat_nmi. The original stack frame and the temp storage
	 * is also used by nested NMIs and can not be trusted on exit.
	 */
	/* Do not pop rdx, nested NMIs will corrupt that part of the stack */
	movq (%rsp), %rdx
	CFI_RESTORE rdx

	/* Set the NMI executing variable on the stack. */
	pushq_cfi $1

	/*
	 * Leave room for the "copied" frame
	 */
	subq $(5*8), %rsp
	CFI_ADJUST_CFA_OFFSET 5*8

	/* Copy the stack frame to the Saved frame */
	.rept 5
	pushq_cfi 11*8(%rsp)
	.endr
	CFI_DEF_CFA_OFFSET SS+8-RIP

	/* Everything up to here is safe from nested NMIs */

	/*
	 * If there was a nested NMI, the first NMI's iret will return
	 * here. But NMIs are still enabled and we can take another
	 * nested NMI. The nested NMI checks the interrupted RIP to see
	 * if it is between repeat_nmi and end_repeat_nmi, and if so
	 * it will just return, as we are about to repeat an NMI anyway.
	 * This makes it safe to copy to the stack frame that a nested
	 * NMI will update.
	 */
repeat_nmi:
	/*
	 * Update the stack variable to say we are still in NMI (the update
	 * is benign for the non-repeat case, where 1 was pushed just above
	 * to this very stack slot).
	 */
	movq $1, 10*8(%rsp)

	/* Make another copy, this one may be modified by nested NMIs */
	addq $(10*8), %rsp
	CFI_ADJUST_CFA_OFFSET -10*8
	.rept 5
	pushq_cfi -6*8(%rsp)
	.endr
	subq $(5*8), %rsp
	CFI_DEF_CFA_OFFSET SS+8-RIP
end_repeat_nmi:

	/*
	 * Everything below this point can be preempted by a nested
	 * NMI if the first NMI took an exception and reset our iret stack
	 * so that we repeat another NMI.
	 */
	pushq_cfi $-1		/* ORIG_RAX: no syscall to restart */
	subq $ORIG_RAX-R15, %rsp
	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
	/*
	 * Use save_paranoid to handle SWAPGS, but no need to use paranoid_exit
	 * as we should not be calling schedule in NMI context.
	 * Even with normal interrupts enabled. An NMI should not be
	 * setting NEED_RESCHED or anything that normal interrupts and
	 * exceptions might do.
	 */
	call save_paranoid
	DEFAULT_FRAME 0

	/*
	 * Save off the CR2 register. If we take a page fault in the NMI then
	 * it could corrupt the CR2 value. If the NMI preempts a page fault
	 * handler before it was able to read the CR2 register, and then the
	 * NMI itself takes a page fault, the page fault that was preempted
	 * will read the information from the NMI page fault and not the
	 * origin fault. Save it off and restore it if it changes.
	 * Use the r12 callee-saved register.
	 */
	movq %cr2, %r12

	/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
	movq %rsp,%rdi
	movq $-1,%rsi
	call do_nmi

	/* Did the NMI take a page fault? Restore cr2 if it did */
	movq %cr2, %rcx
	cmpq %rcx, %r12
	je 1f
	movq %r12, %cr2
1:
	
	testl %ebx,%ebx				/* swapgs needed? */
	jnz nmi_restore
nmi_swapgs:
	SWAPGS_UNSAFE_STACK
nmi_restore:
	/* Pop the extra iret frame at once */
	RESTORE_ALL 6*8

	/* Clear the NMI executing stack variable */
	movq $0, 5*8(%rsp)
	jmp irq_return
	CFI_ENDPROC
END(nmi)

ENTRY(ignore_sysret)
	CFI_STARTPROC
	mov $-ENOSYS,%eax
	sysret
	CFI_ENDPROC
END(ignore_sysret)

OpenPOWER on IntegriCloud