forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
entry_64.S
1745 lines (1529 loc) · 49.4 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/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.
* - 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 <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/export.h>
#include <asm/frame.h>
#include <asm/nospec-branch.h>
#include <linux/err.h>
#include "calling.h"
.code64
.section .entry.text, "ax"
#ifdef CONFIG_PARAVIRT
SYM_CODE_START(native_usergs_sysret64)
UNWIND_HINT_EMPTY
swapgs
sysretq
SYM_CODE_END(native_usergs_sysret64)
#endif /* CONFIG_PARAVIRT */
.macro TRACE_IRQS_FLAGS flags:req
#ifdef CONFIG_TRACE_IRQFLAGS
btl $9, \flags /* interrupts off? */
jnc 1f
TRACE_IRQS_ON
1:
#endif
.endm
.macro TRACE_IRQS_IRETQ
TRACE_IRQS_FLAGS EFLAGS(%rsp)
.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
btl $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.
*/
SYM_CODE_START(entry_SYSCALL_64)
UNWIND_HINT_EMPTY
/*
* 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
/* 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(cpu_current_top_of_stack), %rsp
/* 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
TRACE_IRQS_OFF
/* IRQs are off. */
movq %rax, %rdi
movq %rsp, %rsi
call do_syscall_64 /* returns with IRQs disabled */
TRACE_IRQS_ON /* return enables interrupts */
/*
* 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.
*/
movq RCX(%rsp), %rcx
movq RIP(%rsp), %r11
cmpq %rcx, %r11 /* SYSRET requires RCX == RIP */
jne swapgs_restore_regs_and_return_to_usermode
/*
* 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.
*
* Change top bits to match most significant bit (47th or 56th bit
* depending on paging mode) in the address.
*/
#ifdef CONFIG_X86_5LEVEL
ALTERNATIVE "shl $(64 - 48), %rcx; sar $(64 - 48), %rcx", \
"shl $(64 - 57), %rcx; sar $(64 - 57), %rcx", X86_FEATURE_LA57
#else
shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
#endif
/* If this changed %rcx, it was not canonical */
cmpq %rcx, %r11
jne swapgs_restore_regs_and_return_to_usermode
cmpq $__USER_CS, CS(%rsp) /* CS must match SYSRET */
jne swapgs_restore_regs_and_return_to_usermode
movq R11(%rsp), %r11
cmpq %r11, EFLAGS(%rsp) /* R11 == RFLAGS */
jne swapgs_restore_regs_and_return_to_usermode
/*
* SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot
* restore RF properly. If the slowpath sets it for whatever reason, we
* need to restore it correctly.
*
* 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 swapgs_restore_regs_and_return_to_usermode
/* nothing to check for RSP */
cmpq $__USER_DS, SS(%rsp) /* SS must match SYSRET */
jne swapgs_restore_regs_and_return_to_usermode
/*
* 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) */
UNWIND_HINT_EMPTY
POP_REGS pop_rdi=0 skip_r11rcx=1
/*
* 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
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
USERGS_SYSRET64
SYM_CODE_END(entry_SYSCALL_64)
/*
* %rdi: prev task
* %rsi: next task
*/
SYM_CODE_START(__switch_to_asm)
UNWIND_HINT_FUNC
/*
* 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) + stack_canary_offset
#endif
#ifdef CONFIG_RETPOLINE
/*
* 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
#endif
/* restore callee-saved registers */
popq %r15
popq %r14
popq %r13
popq %r12
popq %rbx
popq %rbp
jmp __switch_to
SYM_CODE_END(__switch_to_asm)
/*
* 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
*/
SYM_CODE_START(ret_from_fork)
UNWIND_HINT_EMPTY
movq %rax, %rdi
call schedule_tail /* rdi: 'prev' task parameter */
testq %rbx, %rbx /* from kernel_thread? */
jnz 1f /* kernel threads are uncommon */
2:
UNWIND_HINT_REGS
movq %rsp, %rdi
call syscall_return_slowpath /* returns with IRQs disabled */
TRACE_IRQS_ON /* user mode is traced as IRQS on */
jmp swapgs_restore_regs_and_return_to_usermode
1:
/* kernel thread */
UNWIND_HINT_EMPTY
movq %r12, %rdi
CALL_NOSPEC %rbx
/*
* A kernel thread is allowed to return here after successfully
* calling do_execve(). Exit to userspace to complete the execve()
* syscall.
*/
movq $0, RAX(%rsp)
jmp 2b
SYM_CODE_END(ret_from_fork)
/*
* Build the entry stubs with some assembler magic.
* We pack 1 stub into every 8-byte block.
*/
.align 8
SYM_CODE_START(irq_entries_start)
vector=FIRST_EXTERNAL_VECTOR
.rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
UNWIND_HINT_IRET_REGS
pushq $(~vector+0x80) /* Note: always in signed byte range */
jmp common_interrupt
.align 8
vector=vector+1
.endr
SYM_CODE_END(irq_entries_start)
.align 8
SYM_CODE_START(spurious_entries_start)
vector=FIRST_SYSTEM_VECTOR
.rept (NR_VECTORS - FIRST_SYSTEM_VECTOR)
UNWIND_HINT_IRET_REGS
pushq $(~vector+0x80) /* Note: always in signed byte range */
jmp common_spurious
.align 8
vector=vector+1
.endr
SYM_CODE_END(spurious_entries_start)
.macro DEBUG_ENTRY_ASSERT_IRQS_OFF
#ifdef CONFIG_DEBUG_ENTRY
pushq %rax
SAVE_FLAGS(CLBR_RAX)
testl $X86_EFLAGS_IF, %eax
jz .Lokay_\@
ud2
.Lokay_\@:
popq %rax
#endif
.endm
/*
* Enters the IRQ stack if we're not already using it. NMI-safe. Clobbers
* flags and puts old RSP into old_rsp, and leaves all other GPRs alone.
* Requires kernel GSBASE.
*
* The invariant is that, if irq_count != -1, then the IRQ stack is in use.
*/
.macro ENTER_IRQ_STACK regs=1 old_rsp save_ret=0
DEBUG_ENTRY_ASSERT_IRQS_OFF
.if \save_ret
/*
* If save_ret is set, the original stack contains one additional
* entry -- the return address. Therefore, move the address one
* entry below %rsp to \old_rsp.
*/
leaq 8(%rsp), \old_rsp
.else
movq %rsp, \old_rsp
.endif
.if \regs
UNWIND_HINT_REGS base=\old_rsp
.endif
incl PER_CPU_VAR(irq_count)
jnz .Lirq_stack_push_old_rsp_\@
/*
* Right now, if we just incremented irq_count to zero, we've
* claimed the IRQ stack but we haven't switched to it yet.
*
* If anything is added that can interrupt us here without using IST,
* it must be *extremely* careful to limit its stack usage. This
* could include kprobes and a hypothetical future IST-less #DB
* handler.
*
* The OOPS unwinder relies on the word at the top of the IRQ
* stack linking back to the previous RSP for the entire time we're
* on the IRQ stack. For this to work reliably, we need to write
* it before we actually move ourselves to the IRQ stack.
*/
movq \old_rsp, PER_CPU_VAR(irq_stack_backing_store + IRQ_STACK_SIZE - 8)
movq PER_CPU_VAR(hardirq_stack_ptr), %rsp
#ifdef CONFIG_DEBUG_ENTRY
/*
* If the first movq above becomes wrong due to IRQ stack layout
* changes, the only way we'll notice is if we try to unwind right
* here. Assert that we set up the stack right to catch this type
* of bug quickly.
*/
cmpq -8(%rsp), \old_rsp
je .Lirq_stack_okay\@
ud2
.Lirq_stack_okay\@:
#endif
.Lirq_stack_push_old_rsp_\@:
pushq \old_rsp
.if \regs
UNWIND_HINT_REGS indirect=1
.endif
.if \save_ret
/*
* Push the return address to the stack. This return address can
* be found at the "real" original RSP, which was offset by 8 at
* the beginning of this macro.
*/
pushq -8(\old_rsp)
.endif
.endm
/*
* Undoes ENTER_IRQ_STACK.
*/
.macro LEAVE_IRQ_STACK regs=1
DEBUG_ENTRY_ASSERT_IRQS_OFF
/* We need to be off the IRQ stack before decrementing irq_count. */
popq %rsp
.if \regs
UNWIND_HINT_REGS
.endif
/*
* As in ENTER_IRQ_STACK, irq_count == 0, we are still claiming
* the irq stack but we're not on it.
*/
decl PER_CPU_VAR(irq_count)
.endm
/*
* Interrupt entry helper function.
*
* Entry runs with interrupts off. Stack layout at entry:
* +----------------------------------------------------+
* | regs->ss |
* | regs->rsp |
* | regs->eflags |
* | regs->cs |
* | regs->ip |
* +----------------------------------------------------+
* | regs->orig_ax = ~(interrupt number) |
* +----------------------------------------------------+
* | return address |
* +----------------------------------------------------+
*/
SYM_CODE_START(interrupt_entry)
UNWIND_HINT_FUNC
ASM_CLAC
cld
testb $3, CS-ORIG_RAX+8(%rsp)
jz 1f
SWAPGS
FENCE_SWAPGS_USER_ENTRY
/*
* Switch to the thread stack. The IRET frame and orig_ax are
* on the stack, as well as the return address. RDI..R12 are
* not (yet) on the stack and space has not (yet) been
* allocated for them.
*/
pushq %rdi
/* Need to switch before accessing the thread stack. */
SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
movq %rsp, %rdi
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
/*
* We have RDI, return address, and orig_ax on the stack on
* top of the IRET frame. That means offset=24
*/
UNWIND_HINT_IRET_REGS base=%rdi offset=24
pushq 7*8(%rdi) /* regs->ss */
pushq 6*8(%rdi) /* regs->rsp */
pushq 5*8(%rdi) /* regs->eflags */
pushq 4*8(%rdi) /* regs->cs */
pushq 3*8(%rdi) /* regs->ip */
pushq 2*8(%rdi) /* regs->orig_ax */
pushq 8(%rdi) /* return address */
UNWIND_HINT_FUNC
movq (%rdi), %rdi
jmp 2f
1:
FENCE_SWAPGS_KERNEL_ENTRY
2:
PUSH_AND_CLEAR_REGS save_ret=1
ENCODE_FRAME_POINTER 8
testb $3, CS+8(%rsp)
jz 1f
/*
* IRQ from user mode.
*
* 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 is 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:
ENTER_IRQ_STACK old_rsp=%rdi save_ret=1
/* We entered an interrupt context - irqs are off: */
TRACE_IRQS_OFF
ret
SYM_CODE_END(interrupt_entry)
_ASM_NOKPROBE(interrupt_entry)
/* Interrupt entry/exit. */
/*
* The interrupt stubs push (~vector+0x80) onto the stack and
* then jump to common_spurious/interrupt.
*/
SYM_CODE_START_LOCAL(common_spurious)
addq $-0x80, (%rsp) /* Adjust vector to [-256, -1] range */
call interrupt_entry
UNWIND_HINT_REGS indirect=1
call smp_spurious_interrupt /* rdi points to pt_regs */
jmp ret_from_intr
SYM_CODE_END(common_spurious)
_ASM_NOKPROBE(common_spurious)
/* common_interrupt is a hotpath. Align it */
.p2align CONFIG_X86_L1_CACHE_SHIFT
SYM_CODE_START_LOCAL(common_interrupt)
addq $-0x80, (%rsp) /* Adjust vector to [-256, -1] range */
call interrupt_entry
UNWIND_HINT_REGS indirect=1
call do_IRQ /* rdi points to pt_regs */
/* 0(%rsp): old RSP */
ret_from_intr:
DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
LEAVE_IRQ_STACK
testb $3, CS(%rsp)
jz retint_kernel
/* Interrupt came from user space */
.Lretint_user:
mov %rsp,%rdi
call prepare_exit_to_usermode
TRACE_IRQS_ON
SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
#ifdef CONFIG_DEBUG_ENTRY
/* Assert that pt_regs indicates user mode. */
testb $3, CS(%rsp)
jnz 1f
ud2
1:
#endif
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
/* 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
SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
/* Restore RDI. */
popq %rdi
SWAPGS
INTERRUPT_RETURN
/* Returning to kernel space */
retint_kernel:
#ifdef CONFIG_PREEMPTION
/* Interrupts are off */
/* Check if we need preemption */
btl $9, EFLAGS(%rsp) /* were interrupts off? */
jnc 1f
cmpl $0, PER_CPU_VAR(__preempt_count)
jnz 1f
call preempt_schedule_irq
1:
#endif
/*
* The iretq could re-enable interrupts:
*/
TRACE_IRQS_IRETQ
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.
*/
INTERRUPT_RETURN
SYM_INNER_LABEL_ALIGN(native_iret, SYM_L_GLOBAL)
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)
/*
* 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:
/*
* 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 */
/*
* 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)
_ASM_NOKPROBE(common_interrupt)
/*
* APIC interrupts.
*/
.macro apicinterrupt3 num sym do_sym
SYM_CODE_START(\sym)
UNWIND_HINT_IRET_REGS
pushq $~(\num)
.Lcommon_\sym:
call interrupt_entry
UNWIND_HINT_REGS indirect=1
call \do_sym /* rdi points to pt_regs */
jmp ret_from_intr
SYM_CODE_END(\sym)
_ASM_NOKPROBE(\sym)
.endm
/* Make sure APIC interrupt handlers end up in the irqentry section: */
#define PUSH_SECTION_IRQENTRY .pushsection .irqentry.text, "ax"
#define POP_SECTION_IRQENTRY .popsection
.macro apicinterrupt num sym do_sym
PUSH_SECTION_IRQENTRY
apicinterrupt3 \num \sym \do_sym
POP_SECTION_IRQENTRY
.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
apicinterrupt3 POSTED_INTR_NESTED_VECTOR kvm_posted_intr_nested_ipi smp_kvm_posted_intr_nested_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_rw) + (TSS_ist + (x) * 8)
.macro idtentry_part do_sym, has_error_code:req, read_cr2:req, paranoid:req, shift_ist=-1, ist_offset=0
.if \paranoid
call paranoid_entry
/* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */
.else
call error_entry
.endif
UNWIND_HINT_REGS
.if \read_cr2
/*
* Store CR2 early so subsequent faults cannot clobber it. Use R12 as
* intermediate storage as RDX can be clobbered in enter_from_user_mode().
* GET_CR2_INTO can clobber RAX.
*/
GET_CR2_INTO(%r12);
.endif
.if \shift_ist != -1
TRACE_IRQS_OFF_DEBUG /* reload IDT in case of recursion */
.else
TRACE_IRQS_OFF
.endif
.if \paranoid == 0
testb $3, CS(%rsp)
jz .Lfrom_kernel_no_context_tracking_\@
CALL_enter_from_user_mode
.Lfrom_kernel_no_context_tracking_\@:
.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 $\ist_offset, CPU_TSS_IST(\shift_ist)
.endif
.if \read_cr2
movq %r12, %rdx /* Move CR2 into 3rd argument */
.endif
call \do_sym
.if \shift_ist != -1
addq $\ist_offset, CPU_TSS_IST(\shift_ist)
.endif
.if \paranoid
/* this procedure expect "no swapgs" flag in ebx */
jmp paranoid_exit
.else
jmp error_exit
.endif
.endm
/**
* idtentry - Generate an IDT entry stub
* @sym: Name of the generated entry point
* @do_sym: C function to be called
* @has_error_code: True if this IDT vector has an error code on the stack
* @paranoid: non-zero means that this vector may be invoked from
* kernel mode with user GSBASE and/or user CR3.
* 2 is special -- see below.
* @shift_ist: Set to an IST index if entries from kernel mode should
* decrement the IST stack so that nested entries get a
* fresh stack. (This is for #DB, which has a nasty habit
* of recursing.)
* @create_gap: create a 6-word stack gap when coming from kernel mode.
* @read_cr2: load CR2 into the 3rd argument; done before calling any C code
*
* idtentry generates an IDT stub that sets up a usable kernel context,
* creates struct pt_regs, and calls @do_sym. The stub has the following
* special behaviors:
*
* On an entry from user mode, the stub switches from the trampoline or
* IST stack to the normal thread stack. On an exit to user mode, the
* normal exit-to-usermode path is invoked.
*
* On an exit to kernel mode, if @paranoid == 0, we check for preemption,
* whereas we omit the preemption check if @paranoid != 0. This is purely
* because the implementation is simpler this way. The kernel only needs
* to check for asynchronous kernel preemption when IRQ handlers return.
*
* If @paranoid == 0, then the stub will handle IRET faults by pretending
* that the fault came from user mode. It will handle gs_change faults by
* pretending that the fault happened with kernel GSBASE. Since this handling
* is omitted for @paranoid != 0, the #GP, #SS, and #NP stubs must have
* @paranoid == 0. This special handling will do the wrong thing for
* espfix-induced #DF on IRET, so #DF must not use @paranoid == 0.
*
* @paranoid == 2 is special: the stub will never switch stacks. This is for
* #DF: if the thread stack is somehow unusable, we'll still get a useful OOPS.
*/
.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ist_offset=0 create_gap=0 read_cr2=0
SYM_CODE_START(\sym)
UNWIND_HINT_IRET_REGS offset=\has_error_code*8
/* Sanity check */
.if \shift_ist != -1 && \paranoid != 1
.error "using shift_ist requires paranoid=1"
.endif
.if \create_gap && \paranoid
.error "using create_gap requires paranoid=0"
.endif
ASM_CLAC
.if \has_error_code == 0
pushq $-1 /* ORIG_RAX: no syscall to restart */
.endif
.if \paranoid == 1
testb $3, CS-ORIG_RAX(%rsp) /* If coming from userspace, switch stacks */
jnz .Lfrom_usermode_switch_stack_\@
.endif
.if \create_gap == 1
/*
* 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_\@