summaryrefslogtreecommitdiff
path: root/arch/x86/entry/entry_64.S
blob: 9ee0da1807edff462536e3628e1db217bb835cd8 (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
/*
 *  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
 *
 * A note on terminology:
 * - iret frame:	Architecture defined interrupt frame from SS to RIP
 *			at the top of the kernel process stack.
 *
 * Some macro usage:
 * - ENTRY/END:		Define functions in the symbol table.
 * - TRACE_IRQ_*:	Trace hardirq 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 "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/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"

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

.macro TRACE_IRQS_IRETQ
#ifdef CONFIG_TRACE_IRQFLAGS
	bt	$9, EFLAGS(%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
	bt	$9, EFLAGS(%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

/*
 * 64-bit SYSCALL instruction entry. Up to 6 arguments in registers.
 *
 * This is the only entry point used for 64-bit system calls.  The
 * hardware interface is reasonably well designed and the register to
 * argument mapping Linux uses fits well with the registers that are
 * available when SYSCALL is used.
 *
 * SYSCALL instructions can be found inlined in libc implementations as
 * well as some other programs and libraries.  There are also a handful
 * of SYSCALL instructions in the vDSO used, for example, as a
 * clock_gettimeofday fallback.
 *
 * 64-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
 * then loads new ss, cs, and rip from previously programmed MSRs.
 * rflags gets masked by a value from another MSR (so CLD and CLAC
 * are not needed). SYSCALL does not save anything on the stack
 * and does not change rsp.
 *
 * Registers on entry:
 * rax  system call number
 * rcx  return address
 * r11  saved rflags (note: r11 is callee-clobbered register in C ABI)
 * rdi  arg0
 * rsi  arg1
 * rdx  arg2
 * r10  arg3 (needs to be moved to rcx to conform to C ABI)
 * r8   arg4
 * r9   arg5
 * (note: r12-r15, rbp, rbx are callee-preserved in C ABI)
 *
 * Only called from user space.
 *
 * When user can change pt_regs->foo 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(entry_SYSCALL_64)
	/*
	 * Interrupts are off on entry.
	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
	 * it is too small to ever cause noticeable irq latency.
	 */
	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(entry_SYSCALL_64_after_swapgs)

	movq	%rsp, PER_CPU_VAR(rsp_scratch)
	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp

	TRACE_IRQS_OFF

	/* Construct struct pt_regs on stack */
	pushq	$__USER_DS			/* pt_regs->ss */
	pushq	PER_CPU_VAR(rsp_scratch)	/* pt_regs->sp */
	pushq	%r11				/* pt_regs->flags */
	pushq	$__USER_CS			/* pt_regs->cs */
	pushq	%rcx				/* pt_regs->ip */
	pushq	%rax				/* pt_regs->orig_ax */
	pushq	%rdi				/* pt_regs->di */
	pushq	%rsi				/* pt_regs->si */
	pushq	%rdx				/* pt_regs->dx */
	pushq	%rcx				/* pt_regs->cx */
	pushq	$-ENOSYS			/* pt_regs->ax */
	pushq	%r8				/* pt_regs->r8 */
	pushq	%r9				/* pt_regs->r9 */
	pushq	%r10				/* pt_regs->r10 */
	pushq	%r11				/* pt_regs->r11 */
	sub	$(6*8), %rsp			/* pt_regs->bp, bx, r12-15 not saved */

	/*
	 * If we need to do entry work or if we guess we'll need to do
	 * exit work, go straight to the slow path.
	 */
	testl	$_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
	jnz	entry_SYSCALL64_slow_path

entry_SYSCALL_64_fastpath:
	/*
	 * Easy case: enable interrupts and issue the syscall.  If the syscall
	 * needs pt_regs, we'll call a stub that disables interrupts again
	 * and jumps to the slow path.
	 */
	TRACE_IRQS_ON
	ENABLE_INTERRUPTS(CLBR_NONE)
#if __SYSCALL_MASK == ~0
	cmpq	$__NR_syscall_max, %rax
#else
	andl	$__SYSCALL_MASK, %eax
	cmpl	$__NR_syscall_max, %eax
#endif
	ja	1f				/* return -ENOSYS (already in pt_regs->ax) */
	movq	%r10, %rcx

	/*
	 * This call instruction is handled specially in stub_ptregs_64.
	 * It might end up jumping to the slow path.  If it jumps, RAX
	 * and all argument registers are clobbered.
	 */
	call	*sys_call_table(, %rax, 8)
.Lentry_SYSCALL_64_after_fastpath_call:

	movq	%rax, RAX(%rsp)
1:

	/*
	 * If we get here, then we know that pt_regs is clean for SYSRET64.
	 * If we see that no exit work is required (which we are required
	 * to check with IRQs off), then we can go straight to SYSRET64.
	 */
	DISABLE_INTERRUPTS(CLBR_NONE)
	TRACE_IRQS_OFF
	testl	$_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
	jnz	1f

	LOCKDEP_SYS_EXIT
	TRACE_IRQS_ON		/* user mode is traced as IRQs on */
	movq	RIP(%rsp), %rcx
	movq	EFLAGS(%rsp), %r11
	RESTORE_C_REGS_EXCEPT_RCX_R11
	movq	RSP(%rsp), %rsp
	USERGS_SYSRET64

1:
	/*
	 * The fast path looked good when we started, but something changed
	 * along the way and we need to switch to the slow path.  Calling
	 * raise(3) will trigger this, for example.  IRQs are off.
	 */
	TRACE_IRQS_ON
	ENABLE_INTERRUPTS(CLBR_NONE)
	SAVE_EXTRA_REGS
	movq	%rsp, %rdi
	call	syscall_return_slowpath	/* returns with IRQs disabled */
	jmp	return_from_SYSCALL_64

entry_SYSCALL64_slow_path:
	/* IRQs are off. */
	SAVE_EXTRA_REGS
	movq	%rsp, %rdi
	call	do_syscall_64		/* returns with IRQs disabled */

return_from_SYSCALL_64:
	RESTORE_EXTRA_REGS
	TRACE_IRQS_IRETQ		/* we're about to change IF */

	/*
	 * Try to use SYSRET instead of IRET if we're returning to
	 * a completely clean 64-bit userspace context.
	 */
	movq	RCX(%rsp), %rcx
	movq	RIP(%rsp), %r11
	cmpq	%rcx, %r11			/* 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.
	 *
	 * If width of "canonical tail" ever becomes variable, 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

	/* Change top 16 bits to be the sign-extension of 47th bit */
	shl	$(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
	sar	$(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx

	/* If this changed %rcx, it was not canonical */
	cmpq	%rcx, %r11
	jne	opportunistic_sysret_failed

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

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

	/*
	 * SYSRET can't restore RF.  SYSRET can restore TF, but unlike IRET,
	 * restoring TF results in a trap from userspace immediately after
	 * SYSRET.  This would cause an infinite loop whenever #DB happens
	 * with register state that satisfies the opportunistic SYSRET
	 * conditions.  For example, single-stepping this user code:
	 *
	 *           movq	$stuck_here, %rcx
	 *           pushfq
	 *           popq %r11
	 *   stuck_here:
	 *
	 * would never get past 'stuck_here'.
	 */
	testq	$(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
	jnz	opportunistic_sysret_failed

	/* nothing to check for RSP */

	cmpq	$__USER_DS, SS(%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.
	 */
syscall_return_via_sysret:
	/* rcx and r11 are already restored (see code above) */
	RESTORE_C_REGS_EXCEPT_RCX_R11
	movq	RSP(%rsp), %rsp
	USERGS_SYSRET64

opportunistic_sysret_failed:
	SWAPGS
	jmp	restore_c_regs_and_iret
END(entry_SYSCALL_64)

ENTRY(stub_ptregs_64)
	/*
	 * Syscalls marked as needing ptregs land here.
	 * If we are on the fast path, we need to save the extra regs,
	 * which we achieve by trying again on the slow path.  If we are on
	 * the slow path, the extra regs are already saved.
	 *
	 * RAX stores a pointer to the C function implementing the syscall.
	 * IRQs are on.
	 */
	cmpq	$.Lentry_SYSCALL_64_after_fastpath_call, (%rsp)
	jne	1f

	/*
	 * Called from fast path -- disable IRQs again, pop return address
	 * and jump to slow path
	 */
	DISABLE_INTERRUPTS(CLBR_NONE)
	TRACE_IRQS_OFF
	popq	%rax
	jmp	entry_SYSCALL64_slow_path

1:
	/* Called from C */
	jmp	*%rax				/* called from C */
END(stub_ptregs_64)

.macro ptregs_stub func
ENTRY(ptregs_\func)
	leaq	\func(%rip), %rax
	jmp	stub_ptregs_64
END(ptregs_\func)
.endm

/* Instantiate ptregs_stub for each ptregs-using syscall */
#define __SYSCALL_64_QUAL_(sym)
#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_stub sym
#define __SYSCALL_64(nr, sym, qual) __SYSCALL_64_QUAL_##qual(sym)
#include <asm/syscalls_64.h>

/*
 * A newly forked process directly context switches into this address.
 *
 * rdi: prev task we switched from
 */
ENTRY(ret_from_fork)
	LOCK ; btr $TIF_FORK, TI_flags(%r8)

	call	schedule_tail			/* rdi: 'prev' task parameter */

	testb	$3, CS(%rsp)			/* from kernel_thread? */
	jnz	1f

	/*
	 * We came from kernel_thread.  This code path is quite twisted, and
	 * someone should clean it up.
	 *
	 * copy_thread_tls stashes the function pointer in RBX and the
	 * parameter to be passed in RBP.  The called function is permitted
	 * to call do_execve and thereby jump to user mode.
	 */
	movq	RBP(%rsp), %rdi
	call	*RBX(%rsp)
	movl	$0, RAX(%rsp)

	/*
	 * Fall through as though we're exiting a syscall.  This makes a
	 * twisted sort of sense if we just called do_execve.
	 */

1:
	movq	%rsp, %rdi
	call	syscall_return_slowpath	/* returns with IRQs disabled */
	TRACE_IRQS_ON			/* user mode is traced as IRQS on */
	SWAPGS
	jmp	restore_regs_and_iret
END(ret_from_fork)

/*
 * Build the entry stubs with some assembler magic.
 * We pack 1 stub into every 8-byte block.
 */
	.align 8
ENTRY(irq_entries_start)
    vector=FIRST_EXTERNAL_VECTOR
    .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
	pushq	$(~vector+0x80)			/* Note: always in signed byte range */
    vector=vector+1
	jmp	common_interrupt
	.align	8
    .endr
END(irq_entries_start)

/*
 * 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
	cld
	ALLOC_PT_GPREGS_ON_STACK
	SAVE_C_REGS
	SAVE_EXTRA_REGS

	testb	$3, CS(%rsp)
	jz	1f

	/*
	 * IRQ from user mode.  Switch to kernel gsbase and inform context
	 * tracking that we're in kernel mode.
	 */
	SWAPGS

	/*
	 * We need to tell lockdep that IRQs are off.  We can't do this until
	 * we fix gsbase, and we should do it before enter_from_user_mode
	 * (which can take locks).  Since TRACE_IRQS_OFF idempotent,
	 * the simplest way to handle it is to just call it twice if
	 * we enter from user mode.  There's no reason to optimize this since
	 * TRACE_IRQS_OFF is a no-op if lockdep is off.
	 */
	TRACE_IRQS_OFF

	CALL_enter_from_user_mode

1:
	/*
	 * Save previous stack pointer, optionally switch to interrupt stack.
	 * 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)
	 */
	movq	%rsp, %rdi
	incl	PER_CPU_VAR(irq_count)
	cmovzq	PER_CPU_VAR(irq_stack_ptr), %rsp
	pushq	%rdi
	/* We entered an interrupt context - irqs are off: */
	TRACE_IRQS_OFF

	call	\func	/* rdi points to pt_regs */
	.endm

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

	/* Restore saved previous stack */
	popq	%rsp

	testb	$3, CS(%rsp)
	jz	retint_kernel

	/* Interrupt came from user space */
GLOBAL(retint_user)
	mov	%rsp,%rdi
	call	prepare_exit_to_usermode
	TRACE_IRQS_IRETQ
	SWAPGS
	jmp	restore_regs_and_iret

/* Returning to kernel space */
retint_kernel:
#ifdef CONFIG_PREEMPT
	/* Interrupts are off */
	/* Check if we need preemption */
	bt	$9, EFLAGS(%rsp)		/* were interrupts off? */
	jnc	1f
0:	cmpl	$0, PER_CPU_VAR(__preempt_count)
	jnz	1f
	call	preempt_schedule_irq
	jmp	0b
1:
#endif
	/*
	 * The iretq could re-enable interrupts:
	 */
	TRACE_IRQS_IRETQ

/*
 * At this label, code paths which return to kernel and to user,
 * which come from interrupts/exception and from syscalls, merge.
 */
GLOBAL(restore_regs_and_iret)
	RESTORE_EXTRA_REGS
restore_c_regs_and_iret:
	RESTORE_C_REGS
	REMOVE_PT_GPREGS_FROM_STACK 8
	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	%rax
	pushq	%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	%rdi
	orq	PER_CPU_VAR(espfix_stack), %rax
	SWAPGS
	movq	%rax, %rsp
	popq	%rax
	jmp	native_irq_return_iret
#endif
END(common_interrupt)

/*
 * APIC interrupts.
 */
.macro apicinterrupt3 num sym do_sym
ENTRY(\sym)
	ASM_CLAC
	pushq	$~(\num)
.Lcommon_\sym:
	interrupt \do_sym
	jmp	ret_from_intr
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
apicinterrupt3 POSTED_INTR_WAKEUP_VECTOR	kvm_posted_intr_wakeup_ipi	smp_kvm_posted_intr_wakeup_ipi
#endif

#ifdef CONFIG_X86_MCE_THRESHOLD
apicinterrupt THRESHOLD_APIC_VECTOR		threshold_interrupt		smp_threshold_interrupt
#endif

#ifdef CONFIG_X86_MCE_AMD
apicinterrupt DEFERRED_ERROR_VECTOR		deferred_error_interrupt	smp_deferred_error_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 CPU_TSS_IST(x) PER_CPU_VAR(cpu_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

	ASM_CLAC
	PARAVIRT_ADJUST_EXCEPTION_FRAME

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

	ALLOC_PT_GPREGS_ON_STACK

	.if \paranoid
	.if \paranoid == 1
	testb	$3, CS(%rsp)			/* If coming from userspace, switch stacks */
	jnz	1f
	.endif
	call	paranoid_entry
	.else
	call	error_entry
	.endif
	/* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */

	.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, CPU_TSS_IST(\shift_ist)
	.endif

	call	\do_sym

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

	/* these procedures expect "no swapgs" flag in ebx */
	.if \paranoid
	jmp	paranoid_exit
	.else
	jmp	error_exit
	.endif

	.if \paranoid == 1
	/*
	 * 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


	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
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)
	pushfq
	DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
	SWAPGS
.Lgs_change:
	movl	%edi, %gs
2:	ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE
	SWAPGS
	popfq
	ret
END(native_load_gs_index)

	_ASM_EXTABLE(.Lgs_change, bad_gs)
	.section .fixup, "ax"
	/* running with kernelgs */
bad_gs:
	SWAPGS					/* switch back to user gs */
.macro ZAP_GS
	/* This can't be a string because the preprocessor needs to see it. */
	movl $__USER_DS, %eax
	movl %eax, %gs
.endm
	ALTERNATIVE "", "ZAP_GS", X86_BUG_NULL_SEG
	xorl	%eax, %eax
	movl	%eax, %gs
	jmp	2b
	.previous

/* Call softirq on interrupt stack. Interrupts are off. */
ENTRY(do_softirq_own_stack)
	pushq	%rbp
	mov	%rsp, %rbp
	incl	PER_CPU_VAR(irq_count)
	cmove	PER_CPU_VAR(irq_stack_ptr), %rsp
	push	%rbp				/* frame pointer backlink */
	call	__do_softirq
	leaveq
	decl	PER_CPU_VAR(irq_count)
	ret
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) */

/*
 * 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 */
11:	incl	PER_CPU_VAR(irq_count)
	movq	%rsp, %rbp
	cmovzq	PER_CPU_VAR(irq_stack_ptr), %rsp
	pushq	%rbp				/* frame pointer backlink */
	call	xen_evtchn_do_upcall
	popq	%rsp
	decl	PER_CPU_VAR(irq_count)
#ifndef CONFIG_PREEMPT
	call	xen_maybe_preempt_hcall
#endif
	jmp	error_exit
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)
	movl	%ds, %ecx
	cmpw	%cx, 0x10(%rsp)
	jne	1f
	movl	%es, %ecx
	cmpw	%cx, 0x18(%rsp)
	jne	1f
	movl	%fs, %ecx
	cmpw	%cx, 0x20(%rsp)
	jne	1f
	movl	%gs, %ecx
	cmpw	%cx, 0x28(%rsp)
	jne	1f
	/* All segments match their saved values => Category 2 (Bad IRET). */
	movq	(%rsp), %rcx
	movq	8(%rsp), %r11
	addq	$0x30, %rsp
	pushq	$0				/* RIP */
	pushq	%r11
	pushq	%rcx
	jmp	general_protection
1:	/* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */
	movq	(%rsp), %rcx
	movq	8(%rsp), %r11
	addq	$0x30, %rsp
	pushq	$-1 /* orig_ax = -1 => not a system call */
	ALLOC_PT_GPREGS_ON_STACK
	SAVE_C_REGS
	SAVE_EXTRA_REGS
	jmp	error_exit
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

/*
 * Save all registers in pt_regs, and switch gs if needed.
 * Use slow, but surefire "are we in kernel?" check.
 * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
 */
ENTRY(paranoid_entry)
	cld
	SAVE_C_REGS 8
	SAVE_EXTRA_REGS 8
	movl	$1, %ebx
	movl	$MSR_GS_BASE, %ecx
	rdmsr
	testl	%edx, %edx
	js	1f				/* negative -> in kernel */
	SWAPGS
	xorl	%ebx, %ebx
1:	ret
END(paranoid_entry)

/*
 * "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.
 *
 * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it)
 */
ENTRY(paranoid_exit)
	DISABLE_INTERRUPTS(CLBR_NONE)
	TRACE_IRQS_OFF_DEBUG
	testl	%ebx, %ebx			/* swapgs needed? */
	jnz	paranoid_exit_no_swapgs
	TRACE_IRQS_IRETQ
	SWAPGS_UNSAFE_STACK
	jmp	paranoid_exit_restore
paranoid_exit_no_swapgs:
	TRACE_IRQS_IRETQ_DEBUG
paranoid_exit_restore:
	RESTORE_EXTRA_REGS
	RESTORE_C_REGS
	REMOVE_PT_GPREGS_FROM_STACK 8
	INTERRUPT_RETURN
END(paranoid_exit)

/*
 * Save all registers in pt_regs, and switch gs if needed.
 * Return: EBX=0: came from user mode; EBX=1: otherwise
 */
ENTRY(error_entry)
	cld
	SAVE_C_REGS 8
	SAVE_EXTRA_REGS 8
	xorl	%ebx, %ebx
	testb	$3, CS+8(%rsp)
	jz	.Lerror_kernelspace

.Lerror_entry_from_usermode_swapgs:
	/*
	 * We entered from user mode or we're pretending to have entered
	 * from user mode due to an IRET fault.
	 */
	SWAPGS

.Lerror_entry_from_usermode_after_swapgs:
	/*
	 * We need to tell lockdep that IRQs are off.  We can't do this until
	 * we fix gsbase, and we should do it before enter_from_user_mode
	 * (which can take locks).
	 */
	TRACE_IRQS_OFF
	CALL_enter_from_user_mode
	ret

.Lerror_entry_done:
	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.
	 */
.Lerror_kernelspace:
	incl	%ebx
	leaq	native_irq_return_iret(%rip), %rcx
	cmpq	%rcx, RIP+8(%rsp)
	je	.Lerror_bad_iret
	movl	%ecx, %eax			/* zero extend */
	cmpq	%rax, RIP+8(%rsp)
	je	.Lbstep_iret
	cmpq	$.Lgs_change, RIP+8(%rsp)
	jne	.Lerror_entry_done

	/*
	 * hack: .Lgs_change can fail with user gsbase.  If this happens, fix up
	 * gsbase and proceed.  We'll fix up the exception and land in
	 * .Lgs_change's error handler with kernel gsbase.
	 */
	jmp	.Lerror_entry_from_usermode_swapgs

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

.Lerror_bad_iret:
	/*
	 * We came from an IRET to user mode, so we have user gsbase.
	 * Switch to kernel gsbase:
	 */
	SWAPGS

	/*
	 * Pretend that the exception came from user mode: set up pt_regs
	 * as if we faulted immediately after IRET and clear EBX so that
	 * error_exit knows that we will be returning to user mode.
	 */
	mov	%rsp, %rdi
	call	fixup_bad_iret
	mov	%rax, %rsp
	decl	%ebx
	jmp	.Lerror_entry_from_usermode_after_swapgs
END(error_entry)


/*
 * On entry, EBS is a "return to kernel mode" flag:
 *   1: already in kernel mode, don't need SWAPGS
 *   0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode
 */
ENTRY(error_exit)
	movl	%ebx, %eax
	DISABLE_INTERRUPTS(CLBR_NONE)
	TRACE_IRQS_OFF
	testl	%eax, %eax
	jnz	retint_kernel
	jmp	retint_user
END(error_exit)

/* Runs on exception stack */
ENTRY(nmi)
	/*
	 * Fix up the exception frame if we're on Xen.
	 * PARAVIRT_ADJUST_EXCEPTION_FRAME is guaranteed to push at most
	 * one value to the stack on native, so it may clobber the rdx
	 * scratch slot, but it won't clobber any of the important
	 * slots past it.
	 *
	 * Xen is a different story, because the Xen frame itself overlaps
	 * the "NMI executing" variable.
	 */
	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 an "outermost" location on the
	 *      stack
	 *    o Copy the interrupt frame into an "iret" 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 "iret" location to jump to the repeat_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.
	 *
	 * However, espfix prevents us from directly returning to userspace
	 * with a single IRET instruction.  Similarly, IRET to user mode
	 * can fault.  We therefore handle NMIs from user space like
	 * other IST entries.
	 */

	/* Use %rdx as our temp variable throughout */
	pushq	%rdx

	testb	$3, CS-RIP+8(%rsp)
	jz	.Lnmi_from_kernel

	/*
	 * NMI from user mode.  We need to run on the thread stack, but we
	 * can't go through the normal entry paths: NMIs are masked, and
	 * we don't want to enable interrupts, because then we'll end
	 * up in an awkward situation in which IRQs are on but NMIs
	 * are off.
	 *
	 * We also must not push anything to the stack before switching
	 * stacks lest we corrupt the "NMI executing" variable.
	 */

	SWAPGS_UNSAFE_STACK
	cld
	movq	%rsp, %rdx
	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
	pushq	5*8(%rdx)	/* pt_regs->ss */
	pushq	4*8(%rdx)	/* pt_regs->rsp */
	pushq	3*8(%rdx)	/* pt_regs->flags */
	pushq	2*8(%rdx)	/* pt_regs->cs */
	pushq	1*8(%rdx)	/* pt_regs->rip */
	pushq   $-1		/* pt_regs->orig_ax */
	pushq   %rdi		/* pt_regs->di */
	pushq   %rsi		/* pt_regs->si */
	pushq   (%rdx)		/* pt_regs->dx */
	pushq   %rcx		/* pt_regs->cx */
	pushq   %rax		/* pt_regs->ax */
	pushq   %r8		/* pt_regs->r8 */
	pushq   %r9		/* pt_regs->r9 */
	pushq   %r10		/* pt_regs->r10 */
	pushq   %r11		/* pt_regs->r11 */
	pushq	%rbx		/* pt_regs->rbx */
	pushq	%rbp		/* pt_regs->rbp */
	pushq	%r12		/* pt_regs->r12 */
	pushq	%r13		/* pt_regs->r13 */
	pushq	%r14		/* pt_regs->r14 */
	pushq	%r15		/* pt_regs->r15 */

	/*
	 * At this point we no longer need to worry about stack damage
	 * due to nesting -- we're on the normal thread stack and we're
	 * done with the NMI stack.
	 */

	movq	%rsp, %rdi
	movq	$-1, %rsi
	call	do_nmi

	/*
	 * Return back to user mode.  We must *not* do the normal exit
	 * work, because we don't want to enable interrupts.  Fortunately,
	 * do_nmi doesn't modify pt_regs.
	 */
	SWAPGS
	jmp	restore_c_regs_and_iret

.Lnmi_from_kernel:
	/*
	 * 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                                |
	 * +---------------------------------------------------------+
	 * | iret SS          } Copied from "outermost" frame        |
	 * | iret Return RSP  } on each loop iteration; overwritten  |
	 * | iret RFLAGS      } by a nested NMI to force another     |
	 * | iret CS          } iteration if needed.                 |
	 * | iret RIP         }                                      |
	 * +---------------------------------------------------------+
	 * | outermost SS          } initialized in first_nmi;       |
	 * | outermost Return RSP  } will not be changed before      |
	 * | outermost RFLAGS      } NMI processing is done.         |
	 * | outermost CS          } Copied to "iret" frame on each  |
	 * | outermost RIP         } iteration.                      |
	 * +---------------------------------------------------------+
	 * | pt_regs                                                 |
	 * +---------------------------------------------------------+
	 *
	 * The "original" frame is used by hardware.  Before re-enabling
	 * NMIs, we need to be done with it, and we need to leave enough
	 * space for the asm code here.
	 *
	 * We return by executing IRET while RSP points to the "iret" frame.
	 * That will either return for real or it will loop back into NMI
	 * processing.
	 *
	 * The "outermost" frame is copied to the "iret" frame on each
	 * iteration of the loop, so each iteration starts with the "iret"
	 * frame pointing to the final return target.
	 */

	/*
	 * Determine whether we're a nested NMI.
	 *
	 * If we interrupted kernel code between repeat_nmi and
	 * end_repeat_nmi, then we are a nested NMI.  We must not
	 * modify the "iret" frame because it's being written by
	 * the outer NMI.  That's okay; the outer NMI handler is
	 * about to about to call do_nmi anyway, so we can just
	 * resume the outer NMI.
	 */

	movq	$repeat_nmi, %rdx
	cmpq	8(%rsp), %rdx
	ja	1f
	movq	$end_repeat_nmi, %rdx
	cmpq	8(%rsp), %rdx
	ja	nested_nmi_out
1:

	/*
	 * Now check "NMI executing".  If it's set, then we're nested.
	 * This will not detect if we interrupted an outer NMI just
	 * before IRET.
	 */
	cmpl	$1, -8(%rsp)
	je	nested_nmi

	/*
	 * Now test if the previous stack was an NMI stack.  This covers
	 * the case where we interrupt an outer NMI after it clears
	 * "NMI executing" but before IRET.  We need to be careful, though:
	 * there is one case in which RSP could point to the NMI stack
	 * despite there being no NMI active: naughty userspace controls
	 * RSP at the very beginning of the SYSCALL targets.  We can
	 * pull a fast one on naughty userspace, though: we program
	 * SYSCALL to mask DF, so userspace cannot cause DF to be set
	 * if it controls the kernel's RSP.  We set DF before we clear
	 * "NMI executing".
	 */
	lea	6*8(%rsp), %rdx
	/* Compare the NMI stack (rdx) with the stack we came from (4*8(%rsp)) */
	cmpq	%rdx, 4*8(%rsp)
	/* If the stack pointer is above the NMI stack, this is a normal NMI */
	ja	first_nmi

	subq	$EXCEPTION_STKSZ, %rdx
	cmpq	%rdx, 4*8(%rsp)
	/* If it is below the NMI stack, it is a normal NMI */
	jb	first_nmi

	/* Ah, it is within the NMI stack. */

	testb	$(X86_EFLAGS_DF >> 8), (3*8 + 1)(%rsp)
	jz	first_nmi	/* RSP was user controlled. */

	/* This is a nested NMI. */

nested_nmi:
	/*
	 * Modify the "iret" frame to point to repeat_nmi, forcing another
	 * iteration of NMI handling.
	 */
	subq	$8, %rsp
	leaq	-10*8(%rsp), %rdx
	pushq	$__KERNEL_DS
	pushq	%rdx
	pushfq
	pushq	$__KERNEL_CS
	pushq	$repeat_nmi

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

nested_nmi_out:
	popq	%rdx

	/* We are returning to kernel mode, so this cannot result in a fault. */
	INTERRUPT_RETURN

first_nmi:
	/* Restore rdx. */
	movq	(%rsp), %rdx

	/* Make room for "NMI executing". */
	pushq	$0

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

	/* Copy the "original" frame to the "outermost" frame */
	.rept 5
	pushq	11*8(%rsp)
	.endr

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

#ifdef CONFIG_DEBUG_ENTRY
	/*
	 * For ease of testing, unmask NMIs right away.  Disabled by
	 * default because IRET is very expensive.
	 */
	pushq	$0		/* SS */
	pushq	%rsp		/* RSP (minus 8 because of the previous push) */
	addq	$8, (%rsp)	/* Fix up RSP */
	pushfq			/* RFLAGS */
	pushq	$__KERNEL_CS	/* CS */
	pushq	$1f		/* RIP */
	INTERRUPT_RETURN	/* continues at repeat_nmi below */
1:
#endif

repeat_nmi:
	/*
	 * 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.
	 *
	 * RSP is pointing to "outermost RIP".  gsbase is unknown, but, if
	 * we're repeating an NMI, gsbase has the same value that it had on
	 * the first iteration.  paranoid_entry will load the kernel
	 * gsbase if needed before we call do_nmi.  "NMI executing"
	 * is zero.
	 */
	movq	$1, 10*8(%rsp)		/* Set "NMI executing". */

	/*
	 * Copy the "outermost" frame to the "iret" frame.  NMIs that nest
	 * here must not modify the "iret" frame while we're writing to
	 * it or it will end up containing garbage.
	 */
	addq	$(10*8), %rsp
	.rept 5
	pushq	-6*8(%rsp)
	.endr
	subq	$(5*8), %rsp
end_repeat_nmi:

	/*
	 * Everything below this point can be preempted by a nested NMI.
	 * If this happens, then the inner NMI will change the "iret"
	 * frame to point back to repeat_nmi.
	 */
	pushq	$-1				/* ORIG_RAX: no syscall to restart */
	ALLOC_PT_GPREGS_ON_STACK

	/*
	 * Use paranoid_entry 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	paranoid_entry

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

	testl	%ebx, %ebx			/* swapgs needed? */
	jnz	nmi_restore
nmi_swapgs:
	SWAPGS_UNSAFE_STACK
nmi_restore:
	RESTORE_EXTRA_REGS
	RESTORE_C_REGS

	/* Point RSP at the "iret" frame. */
	REMOVE_PT_GPREGS_FROM_STACK 6*8

	/*
	 * Clear "NMI executing".  Set DF first so that we can easily
	 * distinguish the remaining code between here and IRET from
	 * the SYSCALL entry and exit paths.  On a native kernel, we
	 * could just inspect RIP, but, on paravirt kernels,
	 * INTERRUPT_RETURN can translate into a jump into a
	 * hypercall page.
	 */
	std
	movq	$0, 5*8(%rsp)		/* clear "NMI executing" */

	/*
	 * INTERRUPT_RETURN reads the "iret" frame and exits the NMI
	 * stack in a single instruction.  We are returning to kernel
	 * mode, so this cannot result in a fault.
	 */
	INTERRUPT_RETURN
END(nmi)

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