aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kernel/entry_32.S
blob: 0ac73de925d1dccdbf11e8b9fda6ead8c552a9ce (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
/*
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

/*
 * entry.S contains the system-call and fault low-level handling routines.
 * This also contains the timer-interrupt handler, as well as all interrupts
 * and faults that can result in a task-switch.
 *
 * NOTE: This code handles signal-recognition, which happens every time
 * after a timer-interrupt and after each system call.
 *
 * I changed all the .align's to 4 (16 byte alignment), as that's faster
 * on a 486.
 *
 * Stack layout in 'syscall_exit':
 * 	ptrace needs to have all regs on the stack.
 *	if the order here is changed, it needs to be
 *	updated in fork.c:copy_process, signal.c:do_signal,
 *	ptrace.c and ptrace.h
 *
 *	 0(%esp) - %ebx
 *	 4(%esp) - %ecx
 *	 8(%esp) - %edx
 *       C(%esp) - %esi
 *	10(%esp) - %edi
 *	14(%esp) - %ebp
 *	18(%esp) - %eax
 *	1C(%esp) - %ds
 *	20(%esp) - %es
 *	24(%esp) - %fs
 *	28(%esp) - %gs		saved iff !CONFIG_X86_32_LAZY_GS
 *	2C(%esp) - orig_eax
 *	30(%esp) - %eip
 *	34(%esp) - %cs
 *	38(%esp) - %eflags
 *	3C(%esp) - %oldesp
 *	40(%esp) - %oldss
 *
 * "current" is in register %ebx during any slow entries.
 */

#include <linux/linkage.h>
#include <linux/err.h>
#include <asm/thread_info.h>
#include <asm/irqflags.h>
#include <asm/errno.h>
#include <asm/segment.h>
#include <asm/smp.h>
#include <asm/page_types.h>
#include <asm/percpu.h>
#include <asm/processor-flags.h>
#include <asm/ftrace.h>
#include <asm/irq_vectors.h>
#include <asm/cpufeature.h>
#include <asm/alternative-asm.h>
#include <asm/asm.h>
#include <asm/smap.h>

/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
#include <linux/elf-em.h>
#define AUDIT_ARCH_I386		(EM_386|__AUDIT_ARCH_LE)
#define __AUDIT_ARCH_LE	   0x40000000

#ifndef CONFIG_AUDITSYSCALL
#define sysenter_audit	syscall_trace_entry
#define sysexit_audit	syscall_exit_work
#endif

	.section .entry.text, "ax"

/*
 * We use macros for low-level operations which need to be overridden
 * for paravirtualization.  The following will never clobber any registers:
 *   INTERRUPT_RETURN (aka. "iret")
 *   GET_CR0_INTO_EAX (aka. "movl %cr0, %eax")
 *   ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit").
 *
 * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must
 * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY).
 * Allowing a register to be clobbered can shrink the paravirt replacement
 * enough to patch inline, increasing performance.
 */

#ifdef CONFIG_PREEMPT
#define preempt_stop(clobbers)	DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
#else
#define preempt_stop(clobbers)
#define resume_kernel		restore_all
#endif

.macro TRACE_IRQS_IRET
#ifdef CONFIG_TRACE_IRQFLAGS
	testl $X86_EFLAGS_IF,PT_EFLAGS(%esp)     # interrupts off?
	jz 1f
	TRACE_IRQS_ON
1:
#endif
.endm

/*
 * User gs save/restore
 *
 * %gs is used for userland TLS and kernel only uses it for stack
 * canary which is required to be at %gs:20 by gcc.  Read the comment
 * at the top of stackprotector.h for more info.
 *
 * Local labels 98 and 99 are used.
 */
#ifdef CONFIG_X86_32_LAZY_GS

 /* unfortunately push/pop can't be no-op */
.macro PUSH_GS
	pushl $0
.endm
.macro POP_GS pop=0
	addl $(4 + \pop), %esp
.endm
.macro POP_GS_EX
.endm

 /* all the rest are no-op */
.macro PTGS_TO_GS
.endm
.macro PTGS_TO_GS_EX
.endm
.macro GS_TO_REG reg
.endm
.macro REG_TO_PTGS reg
.endm
.macro SET_KERNEL_GS reg
.endm

#else	/* CONFIG_X86_32_LAZY_GS */

.macro PUSH_GS
	pushl %gs
.endm

.macro POP_GS pop=0
98:	popl %gs
  .if \pop <> 0
	add $\pop, %esp
  .endif
.endm
.macro POP_GS_EX
.pushsection .fixup, "ax"
99:	movl $0, (%esp)
	jmp 98b
.popsection
	_ASM_EXTABLE(98b,99b)
.endm

.macro PTGS_TO_GS
98:	mov PT_GS(%esp), %gs
.endm
.macro PTGS_TO_GS_EX
.pushsection .fixup, "ax"
99:	movl $0, PT_GS(%esp)
	jmp 98b
.popsection
	_ASM_EXTABLE(98b,99b)
.endm

.macro GS_TO_REG reg
	movl %gs, \reg
.endm
.macro REG_TO_PTGS reg
	movl \reg, PT_GS(%esp)
.endm
.macro SET_KERNEL_GS reg
	movl $(__KERNEL_STACK_CANARY), \reg
	movl \reg, %gs
.endm

#endif	/* CONFIG_X86_32_LAZY_GS */

.macro SAVE_ALL
	cld
	PUSH_GS
	pushl %fs
	pushl %es
	pushl %ds
	pushl %eax
	pushl %ebp
	pushl %edi
	pushl %esi
	pushl %edx
	pushl %ecx
	pushl %ebx
	movl $(__USER_DS), %edx
	movl %edx, %ds
	movl %edx, %es
	movl $(__KERNEL_PERCPU), %edx
	movl %edx, %fs
	SET_KERNEL_GS %edx
.endm

.macro RESTORE_INT_REGS
	popl %ebx
	popl %ecx
	popl %edx
	popl %esi
	popl %edi
	popl %ebp
	popl %eax
.endm

.macro RESTORE_REGS pop=0
	RESTORE_INT_REGS
1:	popl %ds
2:	popl %es
3:	popl %fs
	POP_GS \pop
.pushsection .fixup, "ax"
4:	movl $0, (%esp)
	jmp 1b
5:	movl $0, (%esp)
	jmp 2b
6:	movl $0, (%esp)
	jmp 3b
.popsection
	_ASM_EXTABLE(1b,4b)
	_ASM_EXTABLE(2b,5b)
	_ASM_EXTABLE(3b,6b)
	POP_GS_EX
.endm

ENTRY(ret_from_fork)
	pushl %eax
	call schedule_tail
	GET_THREAD_INFO(%ebp)
	popl %eax
	pushl $0x0202		# Reset kernel eflags
	popfl
	jmp syscall_exit
END(ret_from_fork)

ENTRY(ret_from_kernel_thread)
	pushl %eax
	call schedule_tail
	GET_THREAD_INFO(%ebp)
	popl %eax
	pushl $0x0202		# Reset kernel eflags
	popfl
	movl PT_EBP(%esp),%eax
	call *PT_EBX(%esp)
	movl $0,PT_EAX(%esp)
	jmp syscall_exit
ENDPROC(ret_from_kernel_thread)

/*
 * Return to user mode is not as complex as all this looks,
 * but we want the default path for a system call return to
 * go as quickly as possible which is why some of this is
 * less clear than it otherwise should be.
 */

	# userspace resumption stub bypassing syscall exit tracing
	ALIGN
ret_from_exception:
	preempt_stop(CLBR_ANY)
ret_from_intr:
	GET_THREAD_INFO(%ebp)
#ifdef CONFIG_VM86
	movl PT_EFLAGS(%esp), %eax	# mix EFLAGS and CS
	movb PT_CS(%esp), %al
	andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax
#else
	/*
	 * We can be coming here from child spawned by kernel_thread().
	 */
	movl PT_CS(%esp), %eax
	andl $SEGMENT_RPL_MASK, %eax
#endif
	cmpl $USER_RPL, %eax
	jb resume_kernel		# not returning to v8086 or userspace

ENTRY(resume_userspace)
	LOCKDEP_SYS_EXIT
 	DISABLE_INTERRUPTS(CLBR_ANY)	# make sure we don't miss an interrupt
					# setting need_resched or sigpending
					# between sampling and the iret
	TRACE_IRQS_OFF
	movl TI_flags(%ebp), %ecx
	andl $_TIF_WORK_MASK, %ecx	# is there any work to be done on
					# int/exception return?
	jne work_pending
	jmp restore_all
END(ret_from_exception)

#ifdef CONFIG_PREEMPT
ENTRY(resume_kernel)
	DISABLE_INTERRUPTS(CLBR_ANY)
need_resched:
	cmpl $0,PER_CPU_VAR(__preempt_count)
	jnz restore_all
	testl $X86_EFLAGS_IF,PT_EFLAGS(%esp)	# interrupts off (exception path) ?
	jz restore_all
	call preempt_schedule_irq
	jmp need_resched
END(resume_kernel)
#endif

/* SYSENTER_RETURN points to after the "sysenter" instruction in
   the vsyscall page.  See vsyscall-sysentry.S, which defines the symbol.  */

	# sysenter call handler stub
ENTRY(ia32_sysenter_target)
	movl TSS_sysenter_sp0(%esp),%esp
sysenter_past_esp:
	/*
	 * Interrupts are disabled here, but we can't trace it until
	 * enough kernel state to call TRACE_IRQS_OFF can be called - but
	 * we immediately enable interrupts at that point anyway.
	 */
	pushl $__USER_DS
	pushl %ebp
	pushfl
	orl $X86_EFLAGS_IF, (%esp)
	pushl $__USER_CS
	/*
	 * Push current_thread_info()->sysenter_return to the stack.
	 * A tiny bit of offset fixup is necessary: TI_sysenter_return
	 * is relative to thread_info, which is at the bottom of the
	 * kernel stack page.  4*4 means the 4 words pushed above;
	 * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack;
	 * and THREAD_SIZE takes us to the bottom.
	 */
	pushl ((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp)

	pushl %eax
	SAVE_ALL
	ENABLE_INTERRUPTS(CLBR_NONE)

/*
 * Load the potential sixth argument from user stack.
 * Careful about security.
 */
	cmpl $__PAGE_OFFSET-3,%ebp
	jae syscall_fault
	ASM_STAC
1:	movl (%ebp),%ebp
	ASM_CLAC
	movl %ebp,PT_EBP(%esp)
	_ASM_EXTABLE(1b,syscall_fault)

	GET_THREAD_INFO(%ebp)

	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp)
	jnz sysenter_audit
sysenter_do_call:
	cmpl $(NR_syscalls), %eax
	jae sysenter_badsys
	call *sys_call_table(,%eax,4)
sysenter_after_call:
	movl %eax,PT_EAX(%esp)
	LOCKDEP_SYS_EXIT
	DISABLE_INTERRUPTS(CLBR_ANY)
	TRACE_IRQS_OFF
	movl TI_flags(%ebp), %ecx
	testl $_TIF_ALLWORK_MASK, %ecx
	jnz sysexit_audit
sysenter_exit:
/* if something modifies registers it must also disable sysexit */
	movl PT_EIP(%esp), %edx
	movl PT_OLDESP(%esp), %ecx
	xorl %ebp,%ebp
	TRACE_IRQS_ON
1:	mov  PT_FS(%esp), %fs
	PTGS_TO_GS
	ENABLE_INTERRUPTS_SYSEXIT

#ifdef CONFIG_AUDITSYSCALL
sysenter_audit:
	testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp)
	jnz syscall_trace_entry
	/* movl PT_EAX(%esp), %eax	already set, syscall number: 1st arg to audit */
	movl PT_EBX(%esp), %edx		/* ebx/a0: 2nd arg to audit */
	/* movl PT_ECX(%esp), %ecx	already set, a1: 3nd arg to audit */
	pushl PT_ESI(%esp)		/* a3: 5th arg */
	pushl PT_EDX+4(%esp)	/* a2: 4th arg */
	call __audit_syscall_entry
	popl %ecx /* get that remapped edx off the stack */
	popl %ecx /* get that remapped esi off the stack */
	movl PT_EAX(%esp),%eax		/* reload syscall number */
	jmp sysenter_do_call

sysexit_audit:
	testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
	jnz syscall_exit_work
	TRACE_IRQS_ON
	ENABLE_INTERRUPTS(CLBR_ANY)
	movl %eax,%edx		/* second arg, syscall return value */
	cmpl $-MAX_ERRNO,%eax	/* is it an error ? */
	setbe %al		/* 1 if so, 0 if not */
	movzbl %al,%eax		/* zero-extend that */
	call __audit_syscall_exit
	DISABLE_INTERRUPTS(CLBR_ANY)
	TRACE_IRQS_OFF
	movl TI_flags(%ebp), %ecx
	testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
	jnz syscall_exit_work
	movl PT_EAX(%esp),%eax	/* reload syscall return value */
	jmp sysenter_exit
#endif

.pushsection .fixup,"ax"
2:	movl $0,PT_FS(%esp)
	jmp 1b
.popsection
	_ASM_EXTABLE(1b,2b)
	PTGS_TO_GS_EX
ENDPROC(ia32_sysenter_target)

	# system call handler stub
ENTRY(system_call)
	ASM_CLAC
	pushl %eax			# save orig_eax
	SAVE_ALL
	GET_THREAD_INFO(%ebp)
					# system call tracing in operation / emulation
	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp)
	jnz syscall_trace_entry
	cmpl $(NR_syscalls), %eax
	jae syscall_badsys
syscall_call:
	call *sys_call_table(,%eax,4)
syscall_after_call:
	movl %eax,PT_EAX(%esp)		# store the return value
syscall_exit:
	LOCKDEP_SYS_EXIT
	DISABLE_INTERRUPTS(CLBR_ANY)	# make sure we don't miss an interrupt
					# setting need_resched or sigpending
					# between sampling and the iret
	TRACE_IRQS_OFF
	movl TI_flags(%ebp), %ecx
	testl $_TIF_ALLWORK_MASK, %ecx	# current->work
	jnz syscall_exit_work

restore_all:
	TRACE_IRQS_IRET
restore_all_notrace:
#ifdef CONFIG_X86_ESPFIX32
	movl PT_EFLAGS(%esp), %eax	# mix EFLAGS, SS and CS
	# Warning: PT_OLDSS(%esp) contains the wrong/random values if we
	# are returning to the kernel.
	# See comments in process.c:copy_thread() for details.
	movb PT_OLDSS(%esp), %ah
	movb PT_CS(%esp), %al
	andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
	cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
	je ldt_ss			# returning to user-space with LDT SS
#endif
restore_nocheck:
	RESTORE_REGS 4			# skip orig_eax/error_code
irq_return:
	INTERRUPT_RETURN
.section .fixup,"ax"
ENTRY(iret_exc)
	pushl $0			# no error code
	pushl $do_iret_error
	jmp error_code
.previous
	_ASM_EXTABLE(irq_return,iret_exc)

#ifdef CONFIG_X86_ESPFIX32
ldt_ss:
#ifdef CONFIG_PARAVIRT
	/*
	 * The kernel can't run on a non-flat stack if paravirt mode
	 * is active.  Rather than try to fixup the high bits of
	 * ESP, bypass this code entirely.  This may break DOSemu
	 * and/or Wine support in a paravirt VM, although the option
	 * is still available to implement the setting of the high
	 * 16-bits in the INTERRUPT_RETURN paravirt-op.
	 */
	cmpl $0, pv_info+PARAVIRT_enabled
	jne restore_nocheck
#endif

/*
 * Setup and switch to ESPFIX stack
 *
 * We're returning to userspace with a 16 bit stack. The CPU will not
 * restore the high word of ESP for us on executing iret... This is an
 * "official" bug of all the x86-compatible CPUs, which we can work
 * around to make dosemu and wine happy. We do this by preloading the
 * high word of ESP with the high word of the userspace ESP while
 * compensating for the offset by changing to the ESPFIX segment with
 * a base address that matches for the difference.
 */
#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
	mov %esp, %edx			/* load kernel esp */
	mov PT_OLDESP(%esp), %eax	/* load userspace esp */
	mov %dx, %ax			/* eax: new kernel esp */
	sub %eax, %edx			/* offset (low word is 0) */
	shr $16, %edx
	mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */
	mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */
	pushl $__ESPFIX_SS
	pushl %eax			/* new kernel esp */
	/* Disable interrupts, but do not irqtrace this section: we
	 * will soon execute iret and the tracer was already set to
	 * the irqstate after the iret */
	DISABLE_INTERRUPTS(CLBR_EAX)
	lss (%esp), %esp		/* switch to espfix segment */
	jmp restore_nocheck
#endif
ENDPROC(system_call)

	# perform work that needs to be done immediately before resumption
	ALIGN
work_pending:
	testb $_TIF_NEED_RESCHED, %cl
	jz work_notifysig
work_resched:
	call schedule
	LOCKDEP_SYS_EXIT
	DISABLE_INTERRUPTS(CLBR_ANY)	# make sure we don't miss an interrupt
					# setting need_resched or sigpending
					# between sampling and the iret
	TRACE_IRQS_OFF
	movl TI_flags(%ebp), %ecx
	andl $_TIF_WORK_MASK, %ecx	# is there any work to be done other
					# than syscall tracing?
	jz restore_all
	testb $_TIF_NEED_RESCHED, %cl
	jnz work_resched

work_notifysig:				# deal with pending signals and
					# notify-resume requests
#ifdef CONFIG_VM86
	testl $X86_EFLAGS_VM, PT_EFLAGS(%esp)
	movl %esp, %eax
	jnz work_notifysig_v86		# returning to kernel-space or
					# vm86-space
1:
#else
	movl %esp, %eax
#endif
	TRACE_IRQS_ON
	ENABLE_INTERRUPTS(CLBR_NONE)
	movb PT_CS(%esp), %bl
	andb $SEGMENT_RPL_MASK, %bl
	cmpb $USER_RPL, %bl
	jb resume_kernel
	xorl %edx, %edx
	call do_notify_resume
	jmp resume_userspace

#ifdef CONFIG_VM86
	ALIGN
work_notifysig_v86:
	pushl %ecx			# save ti_flags for do_notify_resume
	call save_v86_state		# %eax contains pt_regs pointer
	popl %ecx
	movl %eax, %esp
	jmp 1b
#endif
END(work_pending)

	# perform syscall exit tracing
	ALIGN
syscall_trace_entry:
	movl $-ENOSYS,PT_EAX(%esp)
	movl %esp, %eax
	call syscall_trace_enter
	/* What it returned is what we'll actually use.  */
	cmpl $(NR_syscalls), %eax
	jnae syscall_call
	jmp syscall_exit
END(syscall_trace_entry)

	# perform syscall exit tracing
	ALIGN
syscall_exit_work:
	testl $_TIF_WORK_SYSCALL_EXIT, %ecx
	jz work_pending
	TRACE_IRQS_ON
	ENABLE_INTERRUPTS(CLBR_ANY)	# could let syscall_trace_leave() call
					# schedule() instead
	movl %esp, %eax
	call syscall_trace_leave
	jmp resume_userspace
END(syscall_exit_work)

syscall_fault:
	ASM_CLAC
	GET_THREAD_INFO(%ebp)
	movl $-EFAULT,PT_EAX(%esp)
	jmp resume_userspace
END(syscall_fault)

syscall_badsys:
	movl $-ENOSYS,%eax
	jmp syscall_after_call
END(syscall_badsys)

sysenter_badsys:
	movl $-ENOSYS,%eax
	jmp sysenter_after_call
END(sysenter_badsys)

.macro FIXUP_ESPFIX_STACK
/*
 * Switch back for ESPFIX stack to the normal zerobased stack
 *
 * We can't call C functions using the ESPFIX stack. This code reads
 * the high word of the segment base from the GDT and swiches to the
 * normal stack and adjusts ESP with the matching offset.
 */
#ifdef CONFIG_X86_ESPFIX32
	/* fixup the stack */
	mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
	mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
	shl $16, %eax
	addl %esp, %eax			/* the adjusted stack pointer */
	pushl $__KERNEL_DS
	pushl %eax
	lss (%esp), %esp		/* switch to the normal stack segment */
#endif
.endm
.macro UNWIND_ESPFIX_STACK
#ifdef CONFIG_X86_ESPFIX32
	movl %ss, %eax
	/* see if on espfix stack */
	cmpw $__ESPFIX_SS, %ax
	jne 27f
	movl $__KERNEL_DS, %eax
	movl %eax, %ds
	movl %eax, %es
	/* switch to normal stack */
	FIXUP_ESPFIX_STACK
27:
#endif
.endm

/*
 * 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)
	pushl $(~vector+0x80)	/* Note: always in signed byte range */
    vector=vector+1
	jmp	common_interrupt
	.align	8
    .endr
END(irq_entries_start)

/*
 * the CPU automatically disables interrupts when executing an IRQ vector,
 * so IRQ-flags tracing has to follow that:
 */
	.p2align CONFIG_X86_L1_CACHE_SHIFT
common_interrupt:
	ASM_CLAC
	addl $-0x80,(%esp)	/* Adjust vector into the [-256,-1] range */
	SAVE_ALL
	TRACE_IRQS_OFF
	movl %esp,%eax
	call do_IRQ
	jmp ret_from_intr
ENDPROC(common_interrupt)

#define BUILD_INTERRUPT3(name, nr, fn)	\
ENTRY(name)				\
	ASM_CLAC;			\
	pushl $~(nr);		\
	SAVE_ALL;			\
	TRACE_IRQS_OFF			\
	movl %esp,%eax;			\
	call fn;			\
	jmp ret_from_intr;		\
ENDPROC(name)


#ifdef CONFIG_TRACING
#define TRACE_BUILD_INTERRUPT(name, nr)		\
	BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name)
#else
#define TRACE_BUILD_INTERRUPT(name, nr)
#endif

#define BUILD_INTERRUPT(name, nr) \
	BUILD_INTERRUPT3(name, nr, smp_##name); \
	TRACE_BUILD_INTERRUPT(name, nr)

/* The include is where all of the SMP etc. interrupts come from */
#include <asm/entry_arch.h>

ENTRY(coprocessor_error)
	ASM_CLAC
	pushl $0
	pushl $do_coprocessor_error
	jmp error_code
END(coprocessor_error)

ENTRY(simd_coprocessor_error)
	ASM_CLAC
	pushl $0
#ifdef CONFIG_X86_INVD_BUG
	/* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */
	ALTERNATIVE "pushl $do_general_protection",	\
		    "pushl $do_simd_coprocessor_error", \
		    X86_FEATURE_XMM
#else
	pushl $do_simd_coprocessor_error
#endif
	jmp error_code
END(simd_coprocessor_error)

ENTRY(device_not_available)
	ASM_CLAC
	pushl $-1			# mark this as an int
	pushl $do_device_not_available
	jmp error_code
END(device_not_available)

#ifdef CONFIG_PARAVIRT
ENTRY(native_iret)
	iret
	_ASM_EXTABLE(native_iret, iret_exc)
END(native_iret)

ENTRY(native_irq_enable_sysexit)
	sti
	sysexit
END(native_irq_enable_sysexit)
#endif

ENTRY(overflow)
	ASM_CLAC
	pushl $0
	pushl $do_overflow
	jmp error_code
END(overflow)

ENTRY(bounds)
	ASM_CLAC
	pushl $0
	pushl $do_bounds
	jmp error_code
END(bounds)

ENTRY(invalid_op)
	ASM_CLAC
	pushl $0
	pushl $do_invalid_op
	jmp error_code
END(invalid_op)

ENTRY(coprocessor_segment_overrun)
	ASM_CLAC
	pushl $0
	pushl $do_coprocessor_segment_overrun
	jmp error_code
END(coprocessor_segment_overrun)

ENTRY(invalid_TSS)
	ASM_CLAC
	pushl $do_invalid_TSS
	jmp error_code
END(invalid_TSS)

ENTRY(segment_not_present)
	ASM_CLAC
	pushl $do_segment_not_present
	jmp error_code
END(segment_not_present)

ENTRY(stack_segment)
	ASM_CLAC
	pushl $do_stack_segment
	jmp error_code
END(stack_segment)

ENTRY(alignment_check)
	ASM_CLAC
	pushl $do_alignment_check
	jmp error_code
END(alignment_check)

ENTRY(divide_error)
	ASM_CLAC
	pushl $0			# no error code
	pushl $do_divide_error
	jmp error_code
END(divide_error)

#ifdef CONFIG_X86_MCE
ENTRY(machine_check)
	ASM_CLAC
	pushl $0
	pushl machine_check_vector
	jmp error_code
END(machine_check)
#endif

ENTRY(spurious_interrupt_bug)
	ASM_CLAC
	pushl $0
	pushl $do_spurious_interrupt_bug
	jmp error_code
END(spurious_interrupt_bug)

#ifdef CONFIG_XEN
/* Xen doesn't set %esp to be precisely what the normal sysenter
   entrypoint expects, so fix it up before using the normal path. */
ENTRY(xen_sysenter_target)
	addl $5*4, %esp		/* remove xen-provided frame */
	jmp sysenter_past_esp

ENTRY(xen_hypervisor_callback)
	pushl $-1 /* orig_ax = -1 => not a system call */
	SAVE_ALL
	TRACE_IRQS_OFF

	/* Check to see if we got the event in the critical
	   region in xen_iret_direct, after we've reenabled
	   events and checked for pending events.  This simulates
	   iret instruction's behaviour where it delivers a
	   pending interrupt when enabling interrupts. */
	movl PT_EIP(%esp),%eax
	cmpl $xen_iret_start_crit,%eax
	jb   1f
	cmpl $xen_iret_end_crit,%eax
	jae  1f

	jmp  xen_iret_crit_fixup

ENTRY(xen_do_upcall)
1:	mov %esp, %eax
	call xen_evtchn_do_upcall
#ifndef CONFIG_PREEMPT
	call xen_maybe_preempt_hcall
#endif
	jmp  ret_from_intr
ENDPROC(xen_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 fix up by reattempting the load, and zeroing the segment
# register if the load fails.
# Category 2 we fix up by jumping to do_iret_error. 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 maintaining a status value in EAX.
ENTRY(xen_failsafe_callback)
	pushl %eax
	movl $1,%eax
1:	mov 4(%esp),%ds
2:	mov 8(%esp),%es
3:	mov 12(%esp),%fs
4:	mov 16(%esp),%gs
	/* EAX == 0 => Category 1 (Bad segment)
	   EAX != 0 => Category 2 (Bad IRET) */
	testl %eax,%eax
	popl %eax
	lea 16(%esp),%esp
	jz 5f
	jmp iret_exc
5:	pushl $-1 /* orig_ax = -1 => not a system call */
	SAVE_ALL
	jmp ret_from_exception

.section .fixup,"ax"
6:	xorl %eax,%eax
	movl %eax,4(%esp)
	jmp 1b
7:	xorl %eax,%eax
	movl %eax,8(%esp)
	jmp 2b
8:	xorl %eax,%eax
	movl %eax,12(%esp)
	jmp 3b
9:	xorl %eax,%eax
	movl %eax,16(%esp)
	jmp 4b
.previous
	_ASM_EXTABLE(1b,6b)
	_ASM_EXTABLE(2b,7b)
	_ASM_EXTABLE(3b,8b)
	_ASM_EXTABLE(4b,9b)
ENDPROC(xen_failsafe_callback)

BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
		xen_evtchn_do_upcall)

#endif	/* CONFIG_XEN */

#if IS_ENABLED(CONFIG_HYPERV)

BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
	hyperv_vector_handler)

#endif /* CONFIG_HYPERV */

#ifdef CONFIG_FUNCTION_TRACER
#ifdef CONFIG_DYNAMIC_FTRACE

ENTRY(mcount)
	ret
END(mcount)

ENTRY(ftrace_caller)
	pushl %eax
	pushl %ecx
	pushl %edx
	pushl $0	/* Pass NULL as regs pointer */
	movl 4*4(%esp), %eax
	movl 0x4(%ebp), %edx
	movl function_trace_op, %ecx
	subl $MCOUNT_INSN_SIZE, %eax

.globl ftrace_call
ftrace_call:
	call ftrace_stub

	addl $4,%esp	/* skip NULL pointer */
	popl %edx
	popl %ecx
	popl %eax
ftrace_ret:
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
.globl ftrace_graph_call
ftrace_graph_call:
	jmp ftrace_stub
#endif

.globl ftrace_stub
ftrace_stub:
	ret
END(ftrace_caller)

ENTRY(ftrace_regs_caller)
	pushf	/* push flags before compare (in cs location) */

	/*
	 * i386 does not save SS and ESP when coming from kernel.
	 * Instead, to get sp, &regs->sp is used (see ptrace.h).
	 * Unfortunately, that means eflags must be at the same location
	 * as the current return ip is. We move the return ip into the
	 * ip location, and move flags into the return ip location.
	 */
	pushl 4(%esp)	/* save return ip into ip slot */

	pushl $0	/* Load 0 into orig_ax */
	pushl %gs
	pushl %fs
	pushl %es
	pushl %ds
	pushl %eax
	pushl %ebp
	pushl %edi
	pushl %esi
	pushl %edx
	pushl %ecx
	pushl %ebx

	movl 13*4(%esp), %eax	/* Get the saved flags */
	movl %eax, 14*4(%esp)	/* Move saved flags into regs->flags location */
				/* clobbering return ip */
	movl $__KERNEL_CS,13*4(%esp)

	movl 12*4(%esp), %eax	/* Load ip (1st parameter) */
	subl $MCOUNT_INSN_SIZE, %eax	/* Adjust ip */
	movl 0x4(%ebp), %edx	/* Load parent ip (2nd parameter) */
	movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
	pushl %esp		/* Save pt_regs as 4th parameter */

GLOBAL(ftrace_regs_call)
	call ftrace_stub

	addl $4, %esp		/* Skip pt_regs */
	movl 14*4(%esp), %eax	/* Move flags back into cs */
	movl %eax, 13*4(%esp)	/* Needed to keep addl from modifying flags */
	movl 12*4(%esp), %eax	/* Get return ip from regs->ip */
	movl %eax, 14*4(%esp)	/* Put return ip back for ret */

	popl %ebx
	popl %ecx
	popl %edx
	popl %esi
	popl %edi
	popl %ebp
	popl %eax
	popl %ds
	popl %es
	popl %fs
	popl %gs
	addl $8, %esp		/* Skip orig_ax and ip */
	popf			/* Pop flags at end (no addl to corrupt flags) */
	jmp ftrace_ret

	popf
	jmp  ftrace_stub
#else /* ! CONFIG_DYNAMIC_FTRACE */

ENTRY(mcount)
	cmpl $__PAGE_OFFSET, %esp
	jb ftrace_stub		/* Paging not enabled yet? */

	cmpl $ftrace_stub, ftrace_trace_function
	jnz trace
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
	cmpl $ftrace_stub, ftrace_graph_return
	jnz ftrace_graph_caller

	cmpl $ftrace_graph_entry_stub, ftrace_graph_entry
	jnz ftrace_graph_caller
#endif
.globl ftrace_stub
ftrace_stub:
	ret

	/* taken from glibc */
trace:
	pushl %eax
	pushl %ecx
	pushl %edx
	movl 0xc(%esp), %eax
	movl 0x4(%ebp), %edx
	subl $MCOUNT_INSN_SIZE, %eax

	call *ftrace_trace_function

	popl %edx
	popl %ecx
	popl %eax
	jmp ftrace_stub
END(mcount)
#endif /* CONFIG_DYNAMIC_FTRACE */
#endif /* CONFIG_FUNCTION_TRACER */

#ifdef CONFIG_FUNCTION_GRAPH_TRACER
ENTRY(ftrace_graph_caller)
	pushl %eax
	pushl %ecx
	pushl %edx
	movl 0xc(%esp), %eax
	lea 0x4(%ebp), %edx
	movl (%ebp), %ecx
	subl $MCOUNT_INSN_SIZE, %eax
	call prepare_ftrace_return
	popl %edx
	popl %ecx
	popl %eax
	ret
END(ftrace_graph_caller)

.globl return_to_handler
return_to_handler:
	pushl %eax
	pushl %edx
	movl %ebp, %eax
	call ftrace_return_to_handler
	movl %eax, %ecx
	popl %edx
	popl %eax
	jmp *%ecx
#endif

#ifdef CONFIG_TRACING
ENTRY(trace_page_fault)
	ASM_CLAC
	pushl $trace_do_page_fault
	jmp error_code
END(trace_page_fault)
#endif

ENTRY(page_fault)
	ASM_CLAC
	pushl $do_page_fault
	ALIGN
error_code:
	/* the function address is in %gs's slot on the stack */
	pushl %fs
	pushl %es
	pushl %ds
	pushl %eax
	pushl %ebp
	pushl %edi
	pushl %esi
	pushl %edx
	pushl %ecx
	pushl %ebx
	cld
	movl $(__KERNEL_PERCPU), %ecx
	movl %ecx, %fs
	UNWIND_ESPFIX_STACK
	GS_TO_REG %ecx
	movl PT_GS(%esp), %edi		# get the function address
	movl PT_ORIG_EAX(%esp), %edx	# get the error code
	movl $-1, PT_ORIG_EAX(%esp)	# no syscall to restart
	REG_TO_PTGS %ecx
	SET_KERNEL_GS %ecx
	movl $(__USER_DS), %ecx
	movl %ecx, %ds
	movl %ecx, %es
	TRACE_IRQS_OFF
	movl %esp,%eax			# pt_regs pointer
	call *%edi
	jmp ret_from_exception
END(page_fault)

/*
 * Debug traps and NMI can happen at the one SYSENTER instruction
 * that sets up the real kernel stack. Check here, since we can't
 * allow the wrong stack to be used.
 *
 * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have
 * already pushed 3 words if it hits on the sysenter instruction:
 * eflags, cs and eip.
 *
 * We just load the right stack, and push the three (known) values
 * by hand onto the new stack - while updating the return eip past
 * the instruction that would have done it for sysenter.
 */
.macro FIX_STACK offset ok label
	cmpw $__KERNEL_CS, 4(%esp)
	jne \ok
\label:
	movl TSS_sysenter_sp0 + \offset(%esp), %esp
	pushfl
	pushl $__KERNEL_CS
	pushl $sysenter_past_esp
.endm

ENTRY(debug)
	ASM_CLAC
	cmpl $ia32_sysenter_target,(%esp)
	jne debug_stack_correct
	FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn
debug_stack_correct:
	pushl $-1			# mark this as an int
	SAVE_ALL
	TRACE_IRQS_OFF
	xorl %edx,%edx			# error code 0
	movl %esp,%eax			# pt_regs pointer
	call do_debug
	jmp ret_from_exception
END(debug)

/*
 * NMI is doubly nasty. It can happen _while_ we're handling
 * a debug fault, and the debug fault hasn't yet been able to
 * clear up the stack. So we first check whether we got  an
 * NMI on the sysenter entry path, but after that we need to
 * check whether we got an NMI on the debug path where the debug
 * fault happened on the sysenter path.
 */
ENTRY(nmi)
	ASM_CLAC
#ifdef CONFIG_X86_ESPFIX32
	pushl %eax
	movl %ss, %eax
	cmpw $__ESPFIX_SS, %ax
	popl %eax
	je nmi_espfix_stack
#endif
	cmpl $ia32_sysenter_target,(%esp)
	je nmi_stack_fixup
	pushl %eax
	movl %esp,%eax
	/* Do not access memory above the end of our stack page,
	 * it might not exist.
	 */
	andl $(THREAD_SIZE-1),%eax
	cmpl $(THREAD_SIZE-20),%eax
	popl %eax
	jae nmi_stack_correct
	cmpl $ia32_sysenter_target,12(%esp)
	je nmi_debug_stack_check
nmi_stack_correct:
	pushl %eax
	SAVE_ALL
	xorl %edx,%edx		# zero error code
	movl %esp,%eax		# pt_regs pointer
	call do_nmi
	jmp restore_all_notrace

nmi_stack_fixup:
	FIX_STACK 12, nmi_stack_correct, 1
	jmp nmi_stack_correct

nmi_debug_stack_check:
	cmpw $__KERNEL_CS,16(%esp)
	jne nmi_stack_correct
	cmpl $debug,(%esp)
	jb nmi_stack_correct
	cmpl $debug_esp_fix_insn,(%esp)
	ja nmi_stack_correct
	FIX_STACK 24, nmi_stack_correct, 1
	jmp nmi_stack_correct

#ifdef CONFIG_X86_ESPFIX32
nmi_espfix_stack:
	/*
	 * create the pointer to lss back
	 */
	pushl %ss
	pushl %esp
	addl $4, (%esp)
	/* copy the iret frame of 12 bytes */
	.rept 3
	pushl 16(%esp)
	.endr
	pushl %eax
	SAVE_ALL
	FIXUP_ESPFIX_STACK		# %eax == %esp
	xorl %edx,%edx			# zero error code
	call do_nmi
	RESTORE_REGS
	lss 12+4(%esp), %esp		# back to espfix stack
	jmp irq_return
#endif
END(nmi)

ENTRY(int3)
	ASM_CLAC
	pushl $-1			# mark this as an int
	SAVE_ALL
	TRACE_IRQS_OFF
	xorl %edx,%edx		# zero error code
	movl %esp,%eax		# pt_regs pointer
	call do_int3
	jmp ret_from_exception
END(int3)

ENTRY(general_protection)
	pushl $do_general_protection
	jmp error_code
END(general_protection)

#ifdef CONFIG_KVM_GUEST
ENTRY(async_page_fault)
	ASM_CLAC
	pushl $do_async_page_fault
	jmp error_code
END(async_page_fault)
#endif