-
Notifications
You must be signed in to change notification settings - Fork 54.4k
/
entry_64.S
1554 lines (1365 loc) · 43 KB
/
entry_64.S
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/* SPDX-License-Identifier: GPL-2.0 */
/*
* 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 <[email protected]>
*
* entry.S contains the system-call and fault low-level handling routines.
*
* Some of this is documented in Documentation/arch/x86/entry_64.rst
*
* 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:
* - SYM_FUNC_START/END:Define functions in the symbol table.
* - idtentry: Define exception entry points.
*/
#include <linux/export.h>
#include <linux/linkage.h>
#include <asm/segment.h>
#include <asm/cache.h>
#include <asm/errno.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 <asm/frame.h>
#include <asm/trapnr.h>
#include <asm/nospec-branch.h>
#include <asm/fsgsbase.h>
#include <linux/err.h>
#include "calling.h"
.code64
.section .entry.text, "ax"
/*
* 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.
*/
SYM_CODE_START(entry_SYSCALL_64)
UNWIND_HINT_ENTRY
ENDBR
swapgs
/* tss.sp2 is scratch space. */
movq %rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
movq PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
SYM_INNER_LABEL(entry_SYSCALL_64_safe_stack, SYM_L_GLOBAL)
ANNOTATE_NOENDBR
/* Construct struct pt_regs on stack */
pushq $__USER_DS /* pt_regs->ss */
pushq PER_CPU_VAR(cpu_tss_rw + TSS_sp2) /* pt_regs->sp */
pushq %r11 /* pt_regs->flags */
pushq $__USER_CS /* pt_regs->cs */
pushq %rcx /* pt_regs->ip */
SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
pushq %rax /* pt_regs->orig_ax */
PUSH_AND_CLEAR_REGS rax=$-ENOSYS
/* IRQs are off. */
movq %rsp, %rdi
/* Sign extend the lower 32bit as syscall numbers are treated as int */
movslq %eax, %rsi
/* clobbers %rax, make sure it is after saving the syscall nr */
IBRS_ENTER
UNTRAIN_RET
CLEAR_BRANCH_HISTORY
call do_syscall_64 /* returns with IRQs disabled */
/*
* Try to use SYSRET instead of IRET if we're returning to
* a completely clean 64-bit userspace context. If we're not,
* go to the slow exit path.
* In the Xen PV case we must use iret anyway.
*/
ALTERNATIVE "testb %al, %al; jz swapgs_restore_regs_and_return_to_usermode", \
"jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
/*
* We win! This label is here just for ease of understanding
* perf profiles. Nothing jumps here.
*/
syscall_return_via_sysret:
IBRS_EXIT
POP_REGS pop_rdi=0
/*
* Now all regs are restored except RSP and RDI.
* Save old stack pointer and switch to trampoline stack.
*/
movq %rsp, %rdi
movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
UNWIND_HINT_END_OF_STACK
pushq RSP-RDI(%rdi) /* RSP */
pushq (%rdi) /* RDI */
/*
* We are on the trampoline stack. All regs except RDI are live.
* We can do future final exit work right here.
*/
STACKLEAK_ERASE_NOCLOBBER
SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
popq %rdi
popq %rsp
SYM_INNER_LABEL(entry_SYSRETQ_unsafe_stack, SYM_L_GLOBAL)
ANNOTATE_NOENDBR
swapgs
CLEAR_CPU_BUFFERS
sysretq
SYM_INNER_LABEL(entry_SYSRETQ_end, SYM_L_GLOBAL)
ANNOTATE_NOENDBR
int3
SYM_CODE_END(entry_SYSCALL_64)
/*
* %rdi: prev task
* %rsi: next task
*/
.pushsection .text, "ax"
SYM_FUNC_START(__switch_to_asm)
/*
* Save callee-saved registers
* This must match the order in inactive_task_frame
*/
pushq %rbp
pushq %rbx
pushq %r12
pushq %r13
pushq %r14
pushq %r15
/* switch stack */
movq %rsp, TASK_threadsp(%rdi)
movq TASK_threadsp(%rsi), %rsp
#ifdef CONFIG_STACKPROTECTOR
movq TASK_stack_canary(%rsi), %rbx
movq %rbx, PER_CPU_VAR(fixed_percpu_data + FIXED_stack_canary)
#endif
/*
* When switching from a shallower to a deeper call stack
* the RSB may either underflow or use entries populated
* with userspace addresses. On CPUs where those concerns
* exist, overwrite the RSB with entries which capture
* speculative execution to prevent attack.
*/
FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
/* restore callee-saved registers */
popq %r15
popq %r14
popq %r13
popq %r12
popq %rbx
popq %rbp
jmp __switch_to
SYM_FUNC_END(__switch_to_asm)
.popsection
/*
* A newly forked process directly context switches into this address.
*
* rax: prev task we switched from
* rbx: kernel thread func (NULL for user thread)
* r12: kernel thread arg
*/
.pushsection .text, "ax"
SYM_CODE_START(ret_from_fork_asm)
/*
* This is the start of the kernel stack; even through there's a
* register set at the top, the regset isn't necessarily coherent
* (consider kthreads) and one cannot unwind further.
*
* This ensures stack unwinds of kernel threads terminate in a known
* good state.
*/
UNWIND_HINT_END_OF_STACK
ANNOTATE_NOENDBR // copy_thread
CALL_DEPTH_ACCOUNT
movq %rax, %rdi /* prev */
movq %rsp, %rsi /* regs */
movq %rbx, %rdx /* fn */
movq %r12, %rcx /* fn_arg */
call ret_from_fork
/*
* Set the stack state to what is expected for the target function
* -- at this point the register set should be a valid user set
* and unwind should work normally.
*/
UNWIND_HINT_REGS
#ifdef CONFIG_X86_FRED
ALTERNATIVE "jmp swapgs_restore_regs_and_return_to_usermode", \
"jmp asm_fred_exit_user", X86_FEATURE_FRED
#else
jmp swapgs_restore_regs_and_return_to_usermode
#endif
SYM_CODE_END(ret_from_fork_asm)
.popsection
.macro DEBUG_ENTRY_ASSERT_IRQS_OFF
#ifdef CONFIG_DEBUG_ENTRY
pushq %rax
SAVE_FLAGS
testl $X86_EFLAGS_IF, %eax
jz .Lokay_\@
ud2
.Lokay_\@:
popq %rax
#endif
.endm
SYM_CODE_START(xen_error_entry)
ANNOTATE_NOENDBR
UNWIND_HINT_FUNC
PUSH_AND_CLEAR_REGS save_ret=1
ENCODE_FRAME_POINTER 8
UNTRAIN_RET_FROM_CALL
RET
SYM_CODE_END(xen_error_entry)
/**
* idtentry_body - Macro to emit code calling the C function
* @cfunc: C function to be called
* @has_error_code: Hardware pushed error code on stack
*/
.macro idtentry_body cfunc has_error_code:req
/*
* Call error_entry() and switch to the task stack if from userspace.
*
* When in XENPV, it is already in the task stack, and it can't fault
* for native_iret() nor native_load_gs_index() since XENPV uses its
* own pvops for IRET and load_gs_index(). And it doesn't need to
* switch the CR3. So it can skip invoking error_entry().
*/
ALTERNATIVE "call error_entry; movq %rax, %rsp", \
"call xen_error_entry", X86_FEATURE_XENPV
ENCODE_FRAME_POINTER
UNWIND_HINT_REGS
movq %rsp, %rdi /* pt_regs pointer into 1st argument*/
.if \has_error_code == 1
movq ORIG_RAX(%rsp), %rsi /* get error code into 2nd argument*/
movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */
.endif
call \cfunc
/* For some configurations \cfunc ends up being a noreturn. */
REACHABLE
jmp error_return
.endm
/**
* idtentry - Macro to generate entry stubs for simple IDT entries
* @vector: Vector number
* @asmsym: ASM symbol for the entry point
* @cfunc: C function to be called
* @has_error_code: Hardware pushed error code on stack
*
* The macro emits code to set up the kernel context for straight forward
* and simple IDT entries. No IST stack, no paranoid entry checks.
*/
.macro idtentry vector asmsym cfunc has_error_code:req
SYM_CODE_START(\asmsym)
.if \vector == X86_TRAP_BP
/* #BP advances %rip to the next instruction */
UNWIND_HINT_IRET_ENTRY offset=\has_error_code*8 signal=0
.else
UNWIND_HINT_IRET_ENTRY offset=\has_error_code*8
.endif
ENDBR
ASM_CLAC
cld
.if \has_error_code == 0
pushq $-1 /* ORIG_RAX: no syscall to restart */
.endif
.if \vector == X86_TRAP_BP
/*
* If coming from kernel space, create a 6-word gap to allow the
* int3 handler to emulate a call instruction.
*/
testb $3, CS-ORIG_RAX(%rsp)
jnz .Lfrom_usermode_no_gap_\@
.rept 6
pushq 5*8(%rsp)
.endr
UNWIND_HINT_IRET_REGS offset=8
.Lfrom_usermode_no_gap_\@:
.endif
idtentry_body \cfunc \has_error_code
_ASM_NOKPROBE(\asmsym)
SYM_CODE_END(\asmsym)
.endm
/*
* Interrupt entry/exit.
*
+ The interrupt stubs push (vector) onto the stack, which is the error_code
* position of idtentry exceptions, and jump to one of the two idtentry points
* (common/spurious).
*
* common_interrupt is a hotpath, align it to a cache line
*/
.macro idtentry_irq vector cfunc
.p2align CONFIG_X86_L1_CACHE_SHIFT
idtentry \vector asm_\cfunc \cfunc has_error_code=1
.endm
/**
* idtentry_mce_db - Macro to generate entry stubs for #MC and #DB
* @vector: Vector number
* @asmsym: ASM symbol for the entry point
* @cfunc: C function to be called
*
* The macro emits code to set up the kernel context for #MC and #DB
*
* If the entry comes from user space it uses the normal entry path
* including the return to user space work and preemption checks on
* exit.
*
* If hits in kernel mode then it needs to go through the paranoid
* entry as the exception can hit any random state. No preemption
* check on exit to keep the paranoid path simple.
*/
.macro idtentry_mce_db vector asmsym cfunc
SYM_CODE_START(\asmsym)
UNWIND_HINT_IRET_ENTRY
ENDBR
ASM_CLAC
cld
pushq $-1 /* ORIG_RAX: no syscall to restart */
/*
* If the entry is from userspace, switch stacks and treat it as
* a normal entry.
*/
testb $3, CS-ORIG_RAX(%rsp)
jnz .Lfrom_usermode_switch_stack_\@
/* paranoid_entry returns GS information for paranoid_exit in EBX. */
call paranoid_entry
UNWIND_HINT_REGS
movq %rsp, %rdi /* pt_regs pointer */
call \cfunc
jmp paranoid_exit
/* Switch to the regular task stack and use the noist entry point */
.Lfrom_usermode_switch_stack_\@:
idtentry_body noist_\cfunc, has_error_code=0
_ASM_NOKPROBE(\asmsym)
SYM_CODE_END(\asmsym)
.endm
#ifdef CONFIG_AMD_MEM_ENCRYPT
/**
* idtentry_vc - Macro to generate entry stub for #VC
* @vector: Vector number
* @asmsym: ASM symbol for the entry point
* @cfunc: C function to be called
*
* The macro emits code to set up the kernel context for #VC. The #VC handler
* runs on an IST stack and needs to be able to cause nested #VC exceptions.
*
* To make this work the #VC entry code tries its best to pretend it doesn't use
* an IST stack by switching to the task stack if coming from user-space (which
* includes early SYSCALL entry path) or back to the stack in the IRET frame if
* entered from kernel-mode.
*
* If entered from kernel-mode the return stack is validated first, and if it is
* not safe to use (e.g. because it points to the entry stack) the #VC handler
* will switch to a fall-back stack (VC2) and call a special handler function.
*
* The macro is only used for one vector, but it is planned to be extended in
* the future for the #HV exception.
*/
.macro idtentry_vc vector asmsym cfunc
SYM_CODE_START(\asmsym)
UNWIND_HINT_IRET_ENTRY
ENDBR
ASM_CLAC
cld
/*
* If the entry is from userspace, switch stacks and treat it as
* a normal entry.
*/
testb $3, CS-ORIG_RAX(%rsp)
jnz .Lfrom_usermode_switch_stack_\@
/*
* paranoid_entry returns SWAPGS flag for paranoid_exit in EBX.
* EBX == 0 -> SWAPGS, EBX == 1 -> no SWAPGS
*/
call paranoid_entry
UNWIND_HINT_REGS
/*
* Switch off the IST stack to make it free for nested exceptions. The
* vc_switch_off_ist() function will switch back to the interrupted
* stack if it is safe to do so. If not it switches to the VC fall-back
* stack.
*/
movq %rsp, %rdi /* pt_regs pointer */
call vc_switch_off_ist
movq %rax, %rsp /* Switch to new stack */
ENCODE_FRAME_POINTER
UNWIND_HINT_REGS
/* Update pt_regs */
movq ORIG_RAX(%rsp), %rsi /* get error code into 2nd argument*/
movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */
movq %rsp, %rdi /* pt_regs pointer */
call kernel_\cfunc
/*
* No need to switch back to the IST stack. The current stack is either
* identical to the stack in the IRET frame or the VC fall-back stack,
* so it is definitely mapped even with PTI enabled.
*/
jmp paranoid_exit
/* Switch to the regular task stack */
.Lfrom_usermode_switch_stack_\@:
idtentry_body user_\cfunc, has_error_code=1
_ASM_NOKPROBE(\asmsym)
SYM_CODE_END(\asmsym)
.endm
#endif
/*
* Double fault entry. Straight paranoid. No checks from which context
* this comes because for the espfix induced #DF this would do the wrong
* thing.
*/
.macro idtentry_df vector asmsym cfunc
SYM_CODE_START(\asmsym)
UNWIND_HINT_IRET_ENTRY offset=8
ENDBR
ASM_CLAC
cld
/* paranoid_entry returns GS information for paranoid_exit in EBX. */
call paranoid_entry
UNWIND_HINT_REGS
movq %rsp, %rdi /* pt_regs pointer into first argument */
movq ORIG_RAX(%rsp), %rsi /* get error code into 2nd argument*/
movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */
call \cfunc
/* For some configurations \cfunc ends up being a noreturn. */
REACHABLE
jmp paranoid_exit
_ASM_NOKPROBE(\asmsym)
SYM_CODE_END(\asmsym)
.endm
/*
* Include the defines which emit the idt entries which are shared
* shared between 32 and 64 bit and emit the __irqentry_text_* markers
* so the stacktrace boundary checks work.
*/
__ALIGN
.globl __irqentry_text_start
__irqentry_text_start:
#include <asm/idtentry.h>
__ALIGN
.globl __irqentry_text_end
__irqentry_text_end:
ANNOTATE_NOENDBR
SYM_CODE_START_LOCAL(common_interrupt_return)
SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
IBRS_EXIT
#ifdef CONFIG_XEN_PV
ALTERNATIVE "", "jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
#endif
#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
ALTERNATIVE "", "jmp .Lpti_restore_regs_and_return_to_usermode", X86_FEATURE_PTI
#endif
STACKLEAK_ERASE
POP_REGS
add $8, %rsp /* orig_ax */
UNWIND_HINT_IRET_REGS
.Lswapgs_and_iret:
swapgs
CLEAR_CPU_BUFFERS
/* Assert that the IRET frame indicates user mode. */
testb $3, 8(%rsp)
jnz .Lnative_iret
ud2
#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
.Lpti_restore_regs_and_return_to_usermode:
POP_REGS pop_rdi=0
/*
* The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS.
* Save old stack pointer and switch to trampoline stack.
*/
movq %rsp, %rdi
movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
UNWIND_HINT_END_OF_STACK
/* Copy the IRET frame to the trampoline stack. */
pushq 6*8(%rdi) /* SS */
pushq 5*8(%rdi) /* RSP */
pushq 4*8(%rdi) /* EFLAGS */
pushq 3*8(%rdi) /* CS */
pushq 2*8(%rdi) /* RIP */
/* Push user RDI on the trampoline stack. */
pushq (%rdi)
/*
* We are on the trampoline stack. All regs except RDI are live.
* We can do future final exit work right here.
*/
STACKLEAK_ERASE_NOCLOBBER
push %rax
SWITCH_TO_USER_CR3 scratch_reg=%rdi scratch_reg2=%rax
pop %rax
/* Restore RDI. */
popq %rdi
jmp .Lswapgs_and_iret
#endif
SYM_INNER_LABEL(restore_regs_and_return_to_kernel, SYM_L_GLOBAL)
#ifdef CONFIG_DEBUG_ENTRY
/* Assert that pt_regs indicates kernel mode. */
testb $3, CS(%rsp)
jz 1f
ud2
1:
#endif
POP_REGS
addq $8, %rsp /* skip regs->orig_ax */
/*
* ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
* when returning from IPI handler.
*/
#ifdef CONFIG_XEN_PV
SYM_INNER_LABEL(early_xen_iret_patch, SYM_L_GLOBAL)
ANNOTATE_NOENDBR
.byte 0xe9
.long .Lnative_iret - (. + 4)
#endif
.Lnative_iret:
UNWIND_HINT_IRET_REGS
/*
* 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
SYM_INNER_LABEL(native_irq_return_iret, SYM_L_GLOBAL)
ANNOTATE_NOENDBR // exc_double_fault
/*
* 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 exc_double_fault.
* Other faults here are fatal.
*/
iretq
#ifdef CONFIG_X86_ESPFIX64
native_irq_return_ldt:
/*
* We are running with user GSBASE. All GPRs contain their user
* values. We have a percpu ESPFIX stack that is eight slots
* long (see ESPFIX_STACK_SIZE). espfix_waddr points to the bottom
* of the ESPFIX stack.
*
* We clobber RAX and RDI in this code. We stash RDI on the
* normal stack and RAX on the ESPFIX stack.
*
* The ESPFIX stack layout we set up looks like this:
*
* --- top of ESPFIX stack ---
* SS
* RSP
* RFLAGS
* CS
* RIP <-- RSP points here when we're done
* RAX <-- espfix_waddr points here
* --- bottom of ESPFIX stack ---
*/
pushq %rdi /* Stash user RDI */
swapgs /* to kernel GS */
SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi /* to kernel CR3 */
movq PER_CPU_VAR(espfix_waddr), %rdi
movq %rax, (0*8)(%rdi) /* user RAX */
movq (1*8)(%rsp), %rax /* user RIP */
movq %rax, (1*8)(%rdi)
movq (2*8)(%rsp), %rax /* user CS */
movq %rax, (2*8)(%rdi)
movq (3*8)(%rsp), %rax /* user RFLAGS */
movq %rax, (3*8)(%rdi)
movq (5*8)(%rsp), %rax /* user SS */
movq %rax, (5*8)(%rdi)
movq (4*8)(%rsp), %rax /* user RSP */
movq %rax, (4*8)(%rdi)
/* Now RAX == RSP. */
andl $0xffff0000, %eax /* RAX = (RSP & 0xffff0000) */
/*
* espfix_stack[31:16] == 0. The page tables are set up such that
* (espfix_stack | (X & 0xffff0000)) points to a read-only alias of
* espfix_waddr for any X. That is, there are 65536 RO aliases of
* the same page. Set up RSP so that RSP[31:16] contains the
* respective 16 bits of the /userspace/ RSP and RSP nonetheless
* still points to an RO alias of the ESPFIX stack.
*/
orq PER_CPU_VAR(espfix_stack), %rax
SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
swapgs /* to user GS */
popq %rdi /* Restore user RDI */
movq %rax, %rsp
UNWIND_HINT_IRET_REGS offset=8
/*
* At this point, we cannot write to the stack any more, but we can
* still read.
*/
popq %rax /* Restore user RAX */
CLEAR_CPU_BUFFERS
/*
* RSP now points to an ordinary IRET frame, except that the page
* is read-only and RSP[31:16] are preloaded with the userspace
* values. We can now IRET back to userspace.
*/
jmp native_irq_return_iret
#endif
SYM_CODE_END(common_interrupt_return)
_ASM_NOKPROBE(common_interrupt_return)
/*
* Reload gs selector with exception handling
* di: new selector
*
* Is in entry.text as it shouldn't be instrumented.
*/
SYM_FUNC_START(asm_load_gs_index)
FRAME_BEGIN
swapgs
.Lgs_change:
ANNOTATE_NOENDBR // error_entry
movl %edi, %gs
2: ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE
swapgs
FRAME_END
RET
/* running with kernelgs */
.Lbad_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
_ASM_EXTABLE(.Lgs_change, .Lbad_gs)
SYM_FUNC_END(asm_load_gs_index)
EXPORT_SYMBOL(asm_load_gs_index)
#ifdef CONFIG_XEN_PV
/*
* 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.
*
* C calling convention: exc_xen_hypervisor_callback(struct *pt_regs)
*/
__FUNC_ALIGN
SYM_CODE_START_LOCAL_NOALIGN(exc_xen_hypervisor_callback)
/*
* Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will
* see the correct pointer to the pt_regs
*/
UNWIND_HINT_FUNC
movq %rdi, %rsp /* we don't return, adjust the stack frame */
UNWIND_HINT_REGS
call xen_pv_evtchn_do_upcall
jmp error_return
SYM_CODE_END(exc_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 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.
*/
__FUNC_ALIGN
SYM_CODE_START_NOALIGN(xen_failsafe_callback)
UNWIND_HINT_UNDEFINED
ENDBR
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 */
UNWIND_HINT_IRET_REGS offset=8
jmp asm_exc_general_protection
1: /* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */
movq (%rsp), %rcx
movq 8(%rsp), %r11
addq $0x30, %rsp
UNWIND_HINT_IRET_REGS
pushq $-1 /* orig_ax = -1 => not a system call */
PUSH_AND_CLEAR_REGS
ENCODE_FRAME_POINTER
jmp error_return
SYM_CODE_END(xen_failsafe_callback)
#endif /* CONFIG_XEN_PV */
/*
* Save all registers in pt_regs. Return GSBASE related information
* in EBX depending on the availability of the FSGSBASE instructions:
*
* FSGSBASE R/EBX
* N 0 -> SWAPGS on exit
* 1 -> no SWAPGS on exit
*
* Y GSBASE value at entry, must be restored in paranoid_exit
*
* R14 - old CR3
* R15 - old SPEC_CTRL
*/
SYM_CODE_START(paranoid_entry)
ANNOTATE_NOENDBR
UNWIND_HINT_FUNC
PUSH_AND_CLEAR_REGS save_ret=1
ENCODE_FRAME_POINTER 8
/*
* Always stash CR3 in %r14. This value will be restored,
* verbatim, at exit. Needed if paranoid_entry interrupted
* another entry that already switched to the user CR3 value
* but has not yet returned to userspace.
*
* This is also why CS (stashed in the "iret frame" by the
* hardware at entry) can not be used: this may be a return
* to kernel code, but with a user CR3 value.
*
* Switching CR3 does not depend on kernel GSBASE so it can
* be done before switching to the kernel GSBASE. This is
* required for FSGSBASE because the kernel GSBASE has to
* be retrieved from a kernel internal table.
*/
SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14
/*
* Handling GSBASE depends on the availability of FSGSBASE.
*
* Without FSGSBASE the kernel enforces that negative GSBASE
* values indicate kernel GSBASE. With FSGSBASE no assumptions
* can be made about the GSBASE value when entering from user
* space.
*/
ALTERNATIVE "jmp .Lparanoid_entry_checkgs", "", X86_FEATURE_FSGSBASE
/*
* Read the current GSBASE and store it in %rbx unconditionally,
* retrieve and set the current CPUs kernel GSBASE. The stored value
* has to be restored in paranoid_exit unconditionally.
*
* The unconditional write to GS base below ensures that no subsequent
* loads based on a mispredicted GS base can happen, therefore no LFENCE
* is needed here.
*/
SAVE_AND_SET_GSBASE scratch_reg=%rax save_reg=%rbx
jmp .Lparanoid_gsbase_done
.Lparanoid_entry_checkgs:
/* EBX = 1 -> kernel GSBASE active, no restore required */
movl $1, %ebx
/*
* The kernel-enforced convention is a negative GSBASE indicates
* a kernel value. No SWAPGS needed on entry and exit.
*/
movl $MSR_GS_BASE, %ecx
rdmsr
testl %edx, %edx
js .Lparanoid_kernel_gsbase
/* EBX = 0 -> SWAPGS required on exit */
xorl %ebx, %ebx
swapgs
.Lparanoid_kernel_gsbase:
FENCE_SWAPGS_KERNEL_ENTRY
.Lparanoid_gsbase_done:
/*
* Once we have CR3 and %GS setup save and set SPEC_CTRL. Just like
* CR3 above, keep the old value in a callee saved register.
*/
IBRS_ENTER save_reg=%r15
UNTRAIN_RET_FROM_CALL
RET
SYM_CODE_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, there's no good reason to try
* to handle preemption here.
*
* R/EBX contains the GSBASE related information depending on the
* availability of the FSGSBASE instructions:
*
* FSGSBASE R/EBX
* N 0 -> SWAPGS on exit
* 1 -> no SWAPGS on exit
*
* Y User space GSBASE, must be restored unconditionally
*
* R14 - old CR3
* R15 - old SPEC_CTRL
*/
SYM_CODE_START_LOCAL(paranoid_exit)
UNWIND_HINT_REGS
/*
* Must restore IBRS state before both CR3 and %GS since we need access
* to the per-CPU x86_spec_ctrl_shadow variable.
*/
IBRS_EXIT save_reg=%r15
/*
* The order of operations is important. PARANOID_RESTORE_CR3 requires
* kernel GSBASE.
*
* NB to anyone to try to optimize this code: this code does
* not execute at all for exceptions from user mode. Those
* exceptions go through error_return instead.
*/
PARANOID_RESTORE_CR3 scratch_reg=%rax save_reg=%r14
/* Handle the three GSBASE cases */
ALTERNATIVE "jmp .Lparanoid_exit_checkgs", "", X86_FEATURE_FSGSBASE
/* With FSGSBASE enabled, unconditionally restore GSBASE */
wrgsbase %rbx
jmp restore_regs_and_return_to_kernel
.Lparanoid_exit_checkgs:
/* On non-FSGSBASE systems, conditionally do SWAPGS */
testl %ebx, %ebx
jnz restore_regs_and_return_to_kernel
/* We are returning to a context with user GSBASE */
swapgs
jmp restore_regs_and_return_to_kernel
SYM_CODE_END(paranoid_exit)
/*