aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kernel/ptrace.c
blob: d56aa18309f81fc38492d093373cdca42f6feced (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
/* By Ross Biro 1/23/92 */
/*
 * Pentium III FXSR, SSE support
 *	Gareth Hughes <gareth@valinux.com>, May 2000
 */

#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/errno.h>
#include <linux/ptrace.h>
#include <linux/user.h>
#include <linux/security.h>
#include <linux/audit.h>
#include <linux/seccomp.h>
#include <linux/signal.h>

#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/system.h>
#include <asm/processor.h>
#include <asm/i387.h>
#include <asm/debugreg.h>
#include <asm/ldt.h>
#include <asm/desc.h>
#include <asm/prctl.h>
#include <asm/proto.h>

/*
 * does not yet catch signals sent when the child dies.
 * in exit.c or in signal.c.
 */

/*
 * Determines which flags the user has access to [1 = access, 0 = no access].
 */
#define FLAG_MASK_32		((unsigned long)			\
				 (X86_EFLAGS_CF | X86_EFLAGS_PF |	\
				  X86_EFLAGS_AF | X86_EFLAGS_ZF |	\
				  X86_EFLAGS_SF | X86_EFLAGS_TF |	\
				  X86_EFLAGS_DF | X86_EFLAGS_OF |	\
				  X86_EFLAGS_RF | X86_EFLAGS_AC))

/*
 * Determines whether a value may be installed in a segment register.
 */
static inline bool invalid_selector(u16 value)
{
	return unlikely(value != 0 && (value & SEGMENT_RPL_MASK) != USER_RPL);
}

#ifdef CONFIG_X86_32

#define FLAG_MASK		FLAG_MASK_32

static long *pt_regs_access(struct pt_regs *regs, unsigned long regno)
{
	BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0);
	regno >>= 2;
	if (regno > FS)
		--regno;
	return &regs->bx + regno;
}

static u16 get_segment_reg(struct task_struct *task, unsigned long offset)
{
	/*
	 * Returning the value truncates it to 16 bits.
	 */
	unsigned int retval;
	if (offset != offsetof(struct user_regs_struct, gs))
		retval = *pt_regs_access(task_pt_regs(task), offset);
	else {
		retval = task->thread.gs;
		if (task == current)
			savesegment(gs, retval);
	}
	return retval;
}

static int set_segment_reg(struct task_struct *task,
			   unsigned long offset, u16 value)
{
	/*
	 * The value argument was already truncated to 16 bits.
	 */
	if (invalid_selector(value))
		return -EIO;

	if (offset != offsetof(struct user_regs_struct, gs))
		*pt_regs_access(task_pt_regs(task), offset) = value;
	else {
		task->thread.gs = value;
		if (task == current)
			/*
			 * The user-mode %gs is not affected by
			 * kernel entry, so we must update the CPU.
			 */
			loadsegment(gs, value);
	}

	return 0;
}

static unsigned long debugreg_addr_limit(struct task_struct *task)
{
	return TASK_SIZE - 3;
}

#else  /* CONFIG_X86_64 */

#define FLAG_MASK		(FLAG_MASK_32 | X86_EFLAGS_NT)

static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long offset)
{
	BUILD_BUG_ON(offsetof(struct pt_regs, r15) != 0);
	return &regs->r15 + (offset / sizeof(regs->r15));
}

static u16 get_segment_reg(struct task_struct *task, unsigned long offset)
{
	/*
	 * Returning the value truncates it to 16 bits.
	 */
	unsigned int seg;

	switch (offset) {
	case offsetof(struct user_regs_struct, fs):
		if (task == current) {
			/* Older gas can't assemble movq %?s,%r?? */
			asm("movl %%fs,%0" : "=r" (seg));
			return seg;
		}
		return task->thread.fsindex;
	case offsetof(struct user_regs_struct, gs):
		if (task == current) {
			asm("movl %%gs,%0" : "=r" (seg));
			return seg;
		}
		return task->thread.gsindex;
	case offsetof(struct user_regs_struct, ds):
		if (task == current) {
			asm("movl %%ds,%0" : "=r" (seg));
			return seg;
		}
		return task->thread.ds;
	case offsetof(struct user_regs_struct, es):
		if (task == current) {
			asm("movl %%es,%0" : "=r" (seg));
			return seg;
		}
		return task->thread.es;

	case offsetof(struct user_regs_struct, cs):
	case offsetof(struct user_regs_struct, ss):
		break;
	}
	return *pt_regs_access(task_pt_regs(task), offset);
}

static int set_segment_reg(struct task_struct *task,
			   unsigned long offset, u16 value)
{
	/*
	 * The value argument was already truncated to 16 bits.
	 */
	if (invalid_selector(value))
		return -EIO;

	switch (offset) {
	case offsetof(struct user_regs_struct,fs):
		/*
		 * If this is setting fs as for normal 64-bit use but
		 * setting fs_base has implicitly changed it, leave it.
		 */
		if ((value == FS_TLS_SEL && task->thread.fsindex == 0 &&
		     task->thread.fs != 0) ||
		    (value == 0 && task->thread.fsindex == FS_TLS_SEL &&
		     task->thread.fs == 0))
			break;
		task->thread.fsindex = value;
		if (task == current)
			loadsegment(fs, task->thread.fsindex);
		break;
	case offsetof(struct user_regs_struct,gs):
		/*
		 * If this is setting gs as for normal 64-bit use but
		 * setting gs_base has implicitly changed it, leave it.
		 */
		if ((value == GS_TLS_SEL && task->thread.gsindex == 0 &&
		     task->thread.gs != 0) ||
		    (value == 0 && task->thread.gsindex == GS_TLS_SEL &&
		     task->thread.gs == 0))
			break;
		task->thread.gsindex = value;
		if (task == current)
			load_gs_index(task->thread.gsindex);
		break;
	case offsetof(struct user_regs_struct,ds):
		task->thread.ds = value;
		if (task == current)
			loadsegment(ds, task->thread.ds);
		break;
	case offsetof(struct user_regs_struct,es):
		task->thread.es = value;
		if (task == current)
			loadsegment(es, task->thread.es);
		break;

		/*
		 * Can't actually change these in 64-bit mode.
		 */
	case offsetof(struct user_regs_struct,cs):
#ifdef CONFIG_IA32_EMULATION
		if (test_tsk_thread_flag(task, TIF_IA32))
			task_pt_regs(task)->cs = value;
#endif
		break;
	case offsetof(struct user_regs_struct,ss):
#ifdef CONFIG_IA32_EMULATION
		if (test_tsk_thread_flag(task, TIF_IA32))
			task_pt_regs(task)->ss = value;
#endif
		break;
	}

	return 0;
}

static unsigned long debugreg_addr_limit(struct task_struct *task)
{
#ifdef CONFIG_IA32_EMULATION
	if (test_tsk_thread_flag(task, TIF_IA32))
		return IA32_PAGE_OFFSET - 3;
#endif
	return TASK_SIZE64 - 7;
}

#endif	/* CONFIG_X86_32 */

static unsigned long get_flags(struct task_struct *task)
{
	unsigned long retval = task_pt_regs(task)->flags;

	/*
	 * If the debugger set TF, hide it from the readout.
	 */
	if (test_tsk_thread_flag(task, TIF_FORCED_TF))
		retval &= ~X86_EFLAGS_TF;

	return retval;
}

static int set_flags(struct task_struct *task, unsigned long value)
{
	struct pt_regs *regs = task_pt_regs(task);

	/*
	 * If the user value contains TF, mark that
	 * it was not "us" (the debugger) that set it.
	 * If not, make sure it stays set if we had.
	 */
	if (value & X86_EFLAGS_TF)
		clear_tsk_thread_flag(task, TIF_FORCED_TF);
	else if (test_tsk_thread_flag(task, TIF_FORCED_TF))
		value |= X86_EFLAGS_TF;

	regs->flags = (regs->flags & ~FLAG_MASK) | (value & FLAG_MASK);

	return 0;
}

static int putreg(struct task_struct *child,
		  unsigned long offset, unsigned long value)
{
	switch (offset) {
	case offsetof(struct user_regs_struct, cs):
	case offsetof(struct user_regs_struct, ds):
	case offsetof(struct user_regs_struct, es):
	case offsetof(struct user_regs_struct, fs):
	case offsetof(struct user_regs_struct, gs):
	case offsetof(struct user_regs_struct, ss):
		return set_segment_reg(child, offset, value);

	case offsetof(struct user_regs_struct, flags):
		return set_flags(child, value);

#ifdef CONFIG_X86_64
	case offsetof(struct user_regs_struct,fs_base):
		if (value >= TASK_SIZE_OF(child))
			return -EIO;
		/*
		 * When changing the segment base, use do_arch_prctl
		 * to set either thread.fs or thread.fsindex and the
		 * corresponding GDT slot.
		 */
		if (child->thread.fs != value)
			return do_arch_prctl(child, ARCH_SET_FS, value);
		return 0;
	case offsetof(struct user_regs_struct,gs_base):
		/*
		 * Exactly the same here as the %fs handling above.
		 */
		if (value >= TASK_SIZE_OF(child))
			return -EIO;
		if (child->thread.gs != value)
			return do_arch_prctl(child, ARCH_SET_GS, value);
		return 0;
#endif
	}

	*pt_regs_access(task_pt_regs(child), offset) = value;
	return 0;
}

static unsigned long getreg(struct task_struct *task, unsigned long offset)
{
	switch (offset) {
	case offsetof(struct user_regs_struct, cs):
	case offsetof(struct user_regs_struct, ds):
	case offsetof(struct user_regs_struct, es):
	case offsetof(struct user_regs_struct, fs):
	case offsetof(struct user_regs_struct, gs):
	case offsetof(struct user_regs_struct, ss):
		return get_segment_reg(task, offset);

	case offsetof(struct user_regs_struct, flags):
		return get_flags(task);

#ifdef CONFIG_X86_64
	case offsetof(struct user_regs_struct, fs_base): {
		/*
		 * do_arch_prctl may have used a GDT slot instead of
		 * the MSR.  To userland, it appears the same either
		 * way, except the %fs segment selector might not be 0.
		 */
		unsigned int seg = task->thread.fsindex;
		if (task->thread.fs != 0)
			return task->thread.fs;
		if (task == current)
			asm("movl %%fs,%0" : "=r" (seg));
		if (seg != FS_TLS_SEL)
			return 0;
		return get_desc_base(&task->thread.tls_array[FS_TLS]);
	}
	case offsetof(struct user_regs_struct, gs_base): {
		/*
		 * Exactly the same here as the %fs handling above.
		 */
		unsigned int seg = task->thread.gsindex;
		if (task->thread.gs != 0)
			return task->thread.gs;
		if (task == current)
			asm("movl %%gs,%0" : "=r" (seg));
		if (seg != GS_TLS_SEL)
			return 0;
		return get_desc_base(&task->thread.tls_array[GS_TLS]);
	}
#endif
	}

	return *pt_regs_access(task_pt_regs(task), offset);
}

/*
 * This function is trivial and will be inlined by the compiler.
 * Having it separates the implementation details of debug
 * registers from the interface details of ptrace.
 */
static unsigned long ptrace_get_debugreg(struct task_struct *child, int n)
{
	switch (n) {
	case 0:		return child->thread.debugreg0;
	case 1:		return child->thread.debugreg1;
	case 2:		return child->thread.debugreg2;
	case 3:		return child->thread.debugreg3;
	case 6:		return child->thread.debugreg6;
	case 7:		return child->thread.debugreg7;
	}
	return 0;
}

static int ptrace_set_debugreg(struct task_struct *child,
			       int n, unsigned long data)
{
	int i;

	if (unlikely(n == 4 || n == 5))
		return -EIO;

	if (n < 4 && unlikely(data >= debugreg_addr_limit(child)))
		return -EIO;

	switch (n) {
	case 0:		child->thread.debugreg0 = data; break;
	case 1:		child->thread.debugreg1 = data; break;
	case 2:		child->thread.debugreg2 = data; break;
	case 3:		child->thread.debugreg3 = data; break;

	case 6:
		if ((data & ~0xffffffffUL) != 0)
			return -EIO;
		child->thread.debugreg6 = data;
		break;

	case 7:
		/*
		 * Sanity-check data. Take one half-byte at once with
		 * check = (val >> (16 + 4*i)) & 0xf. It contains the
		 * R/Wi and LENi bits; bits 0 and 1 are R/Wi, and bits
		 * 2 and 3 are LENi. Given a list of invalid values,
		 * we do mask |= 1 << invalid_value, so that
		 * (mask >> check) & 1 is a correct test for invalid
		 * values.
		 *
		 * R/Wi contains the type of the breakpoint /
		 * watchpoint, LENi contains the length of the watched
		 * data in the watchpoint case.
		 *
		 * The invalid values are:
		 * - LENi == 0x10 (undefined), so mask |= 0x0f00.	[32-bit]
		 * - R/Wi == 0x10 (break on I/O reads or writes), so
		 *   mask |= 0x4444.
		 * - R/Wi == 0x00 && LENi != 0x00, so we have mask |=
		 *   0x1110.
		 *
		 * Finally, mask = 0x0f00 | 0x4444 | 0x1110 == 0x5f54.
		 *
		 * See the Intel Manual "System Programming Guide",
		 * 15.2.4
		 *
		 * Note that LENi == 0x10 is defined on x86_64 in long
		 * mode (i.e. even for 32-bit userspace software, but
		 * 64-bit kernel), so the x86_64 mask value is 0x5454.
		 * See the AMD manual no. 24593 (AMD64 System Programming)
		 */
#ifdef CONFIG_X86_32
#define	DR7_MASK	0x5f54
#else
#define	DR7_MASK	0x5554
#endif
		data &= ~DR_CONTROL_RESERVED;
		for (i = 0; i < 4; i++)
			if ((DR7_MASK >> ((data >> (16 + 4*i)) & 0xf)) & 1)
				return -EIO;
		child->thread.debugreg7 = data;
		if (data)
			set_tsk_thread_flag(child, TIF_DEBUG);
		else
			clear_tsk_thread_flag(child, TIF_DEBUG);
		break;
	}

	return 0;
}

/*
 * Called by kernel/ptrace.c when detaching..
 *
 * Make sure the single step bit is not set.
 */
void ptrace_disable(struct task_struct *child)
{
	user_disable_single_step(child);
#ifdef TIF_SYSCALL_EMU
	clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
#endif
}

long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
	int i, ret;
	unsigned long __user *datap = (unsigned long __user *)data;

	switch (request) {
	/* when I and D space are separate, these will need to be fixed. */
	case PTRACE_PEEKTEXT: /* read word at location addr. */
	case PTRACE_PEEKDATA:
		ret = generic_ptrace_peekdata(child, addr, data);
		break;

	/* read the word at location addr in the USER area. */
	case PTRACE_PEEKUSR: {
		unsigned long tmp;

		ret = -EIO;
		if ((addr & (sizeof(data) - 1)) || addr < 0 ||
		    addr >= sizeof(struct user))
			break;

		tmp = 0;  /* Default return condition */
		if (addr < sizeof(struct user_regs_struct))
			tmp = getreg(child, addr);
		else if (addr >= offsetof(struct user, u_debugreg[0]) &&
			 addr <= offsetof(struct user, u_debugreg[7])) {
			addr -= offsetof(struct user, u_debugreg[0]);
			tmp = ptrace_get_debugreg(child, addr / sizeof(data));
		}
		ret = put_user(tmp, datap);
		break;
	}

	/* when I and D space are separate, this will have to be fixed. */
	case PTRACE_POKETEXT: /* write the word at location addr. */
	case PTRACE_POKEDATA:
		ret = generic_ptrace_pokedata(child, addr, data);
		break;

	case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
		ret = -EIO;
		if ((addr & (sizeof(data) - 1)) || addr < 0 ||
		    addr >= sizeof(struct user))
			break;

		if (addr < sizeof(struct user_regs_struct))
			ret = putreg(child, addr, data);
		else if (addr >= offsetof(struct user, u_debugreg[0]) &&
			 addr <= offsetof(struct user, u_debugreg[7])) {
			addr -= offsetof(struct user, u_debugreg[0]);
			ret = ptrace_set_debugreg(child,
						  addr / sizeof(data), data);
		}
		break;

	case PTRACE_GETREGS: { /* Get all gp regs from the child. */
		if (!access_ok(VERIFY_WRITE, datap, sizeof(struct user_regs_struct))) {
			ret = -EIO;
			break;
		}
		for (i = 0; i < sizeof(struct user_regs_struct); i += sizeof(long)) {
			__put_user(getreg(child, i), datap);
			datap++;
		}
		ret = 0;
		break;
	}

	case PTRACE_SETREGS: { /* Set all gp regs in the child. */
		unsigned long tmp;
		if (!access_ok(VERIFY_READ, datap, sizeof(struct user_regs_struct))) {
			ret = -EIO;
			break;
		}
		for (i = 0; i < sizeof(struct user_regs_struct); i += sizeof(long)) {
			__get_user(tmp, datap);
			putreg(child, i, tmp);
			datap++;
		}
		ret = 0;
		break;
	}

	case PTRACE_GETFPREGS: { /* Get the child FPU state. */
		if (!access_ok(VERIFY_WRITE, datap,
			       sizeof(struct user_i387_struct))) {
			ret = -EIO;
			break;
		}
		ret = 0;
		if (!tsk_used_math(child))
			init_fpu(child);
		get_fpregs((struct user_i387_struct __user *)data, child);
		break;
	}

	case PTRACE_SETFPREGS: { /* Set the child FPU state. */
		if (!access_ok(VERIFY_READ, datap,
			       sizeof(struct user_i387_struct))) {
			ret = -EIO;
			break;
		}
		set_stopped_child_used_math(child);
		set_fpregs(child, (struct user_i387_struct __user *)data);
		ret = 0;
		break;
	}

#ifdef CONFIG_X86_32
	case PTRACE_GETFPXREGS: { /* Get the child extended FPU state. */
		if (!access_ok(VERIFY_WRITE, datap,
			       sizeof(struct user_fxsr_struct))) {
			ret = -EIO;
			break;
		}
		if (!tsk_used_math(child))
			init_fpu(child);
		ret = get_fpxregs((struct user_fxsr_struct __user *)data, child);
		break;
	}

	case PTRACE_SETFPXREGS: { /* Set the child extended FPU state. */
		if (!access_ok(VERIFY_READ, datap,
			       sizeof(struct user_fxsr_struct))) {
			ret = -EIO;
			break;
		}
		set_stopped_child_used_math(child);
		ret = set_fpxregs(child, (struct user_fxsr_struct __user *)data);
		break;
	}
#endif

#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
	case PTRACE_GET_THREAD_AREA:
		if (addr < 0)
			return -EIO;
		ret = do_get_thread_area(child, addr,
					 (struct user_desc __user *) data);
		break;

	case PTRACE_SET_THREAD_AREA:
		if (addr < 0)
			return -EIO;
		ret = do_set_thread_area(child, addr,
					 (struct user_desc __user *) data, 0);
		break;
#endif

#ifdef CONFIG_X86_64
		/* normal 64bit interface to access TLS data.
		   Works just like arch_prctl, except that the arguments
		   are reversed. */
	case PTRACE_ARCH_PRCTL:
		ret = do_arch_prctl(child, data, addr);
		break;
#endif

	default:
		ret = ptrace_request(child, request, addr, data);
		break;
	}

	return ret;
}

#ifdef CONFIG_IA32_EMULATION

#include <asm/user32.h>

#define R32(l,q)							\
	case offsetof(struct user32, regs.l):				\
		regs->q = value; break

#define SEG32(rs)							\
	case offsetof(struct user32, regs.rs):				\
		return set_segment_reg(child,				\
				       offsetof(struct user_regs_struct, rs), \
				       value);				\
		break

static int putreg32(struct task_struct *child, unsigned regno, u32 value)
{
	struct pt_regs *regs = task_pt_regs(child);

	switch (regno) {

	SEG32(cs);
	SEG32(ds);
	SEG32(es);
	SEG32(fs);
	SEG32(gs);
	SEG32(ss);

	R32(ebx, bx);
	R32(ecx, cx);
	R32(edx, dx);
	R32(edi, di);
	R32(esi, si);
	R32(ebp, bp);
	R32(eax, ax);
	R32(orig_eax, orig_ax);
	R32(eip, ip);
	R32(esp, sp);

	case offsetof(struct user32, regs.eflags):
		return set_flags(child, value);

	case offsetof(struct user32, u_debugreg[0]) ...
		offsetof(struct user32, u_debugreg[7]):
		regno -= offsetof(struct user32, u_debugreg[0]);
		return ptrace_set_debugreg(child, regno / 4, value);

	default:
		if (regno > sizeof(struct user32) || (regno & 3))
			return -EIO;

		/*
		 * Other dummy fields in the virtual user structure
		 * are ignored
		 */
		break;
	}
	return 0;
}

#undef R32
#undef SEG32

#define R32(l,q)							\
	case offsetof(struct user32, regs.l):				\
		*val = regs->q; break

#define SEG32(rs)							\
	case offsetof(struct user32, regs.rs):				\
		*val = get_segment_reg(child,				\
				       offsetof(struct user_regs_struct, rs)); \
		break

static int getreg32(struct task_struct *child, unsigned regno, u32 *val)
{
	struct pt_regs *regs = task_pt_regs(child);

	switch (regno) {

	SEG32(ds);
	SEG32(es);
	SEG32(fs);
	SEG32(gs);

	R32(cs, cs);
	R32(ss, ss);
	R32(ebx, bx);
	R32(ecx, cx);
	R32(edx, dx);
	R32(edi, di);
	R32(esi, si);
	R32(ebp, bp);
	R32(eax, ax);
	R32(orig_eax, orig_ax);
	R32(eip, ip);
	R32(esp, sp);

	case offsetof(struct user32, regs.eflags):
		*val = get_flags(child);
		break;

	case offsetof(struct user32, u_debugreg[0]) ...
		offsetof(struct user32, u_debugreg[7]):
		regno -= offsetof(struct user32, u_debugreg[0]);
		*val = ptrace_get_debugreg(child, regno / 4);
		break;

	default:
		if (regno > sizeof(struct user32) || (regno & 3))
			return -EIO;

		/*
		 * Other dummy fields in the virtual user structure
		 * are ignored
		 */
		*val = 0;
		break;
	}
	return 0;
}

#undef R32
#undef SEG32

#endif	/* CONFIG_IA32_EMULATION */

#ifdef CONFIG_X86_32

void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code)
{
	struct siginfo info;

	tsk->thread.trap_no = 1;
	tsk->thread.error_code = error_code;

	memset(&info, 0, sizeof(info));
	info.si_signo = SIGTRAP;
	info.si_code = TRAP_BRKPT;

	/* User-mode ip? */
	info.si_addr = user_mode_vm(regs) ? (void __user *) regs->ip : NULL;

	/* Send us the fake SIGTRAP */
	force_sig_info(SIGTRAP, &info, tsk);
}

/* notification of system call entry/exit
 * - triggered by current->work.syscall_trace
 */
__attribute__((regparm(3)))
int do_syscall_trace(struct pt_regs *regs, int entryexit)
{
	int is_sysemu = test_thread_flag(TIF_SYSCALL_EMU);
	/*
	 * With TIF_SYSCALL_EMU set we want to ignore TIF_SINGLESTEP for syscall
	 * interception
	 */
	int is_singlestep = !is_sysemu && test_thread_flag(TIF_SINGLESTEP);
	int ret = 0;

	/* do the secure computing check first */
	if (!entryexit)
		secure_computing(regs->orig_ax);

	if (unlikely(current->audit_context)) {
		if (entryexit)
			audit_syscall_exit(AUDITSC_RESULT(regs->ax),
						regs->ax);
		/* Debug traps, when using PTRACE_SINGLESTEP, must be sent only
		 * on the syscall exit path. Normally, when TIF_SYSCALL_AUDIT is
		 * not used, entry.S will call us only on syscall exit, not
		 * entry; so when TIF_SYSCALL_AUDIT is used we must avoid
		 * calling send_sigtrap() on syscall entry.
		 *
		 * Note that when PTRACE_SYSEMU_SINGLESTEP is used,
		 * is_singlestep is false, despite his name, so we will still do
		 * the correct thing.
		 */
		else if (is_singlestep)
			goto out;
	}

	if (!(current->ptrace & PT_PTRACED))
		goto out;

	/* If a process stops on the 1st tracepoint with SYSCALL_TRACE
	 * and then is resumed with SYSEMU_SINGLESTEP, it will come in
	 * here. We have to check this and return */
	if (is_sysemu && entryexit)
		return 0;

	/* Fake a debug trap */
	if (is_singlestep)
		send_sigtrap(current, regs, 0);

 	if (!test_thread_flag(TIF_SYSCALL_TRACE) && !is_sysemu)
		goto out;

	/* the 0x80 provides a way for the tracing parent to distinguish
	   between a syscall stop and SIGTRAP delivery */
	/* Note that the debugger could change the result of test_thread_flag!*/
	ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD) ? 0x80:0));

	/*
	 * this isn't the same as continuing with a signal, but it will do
	 * for normal use.  strace only continues with a signal if the
	 * stopping signal is not SIGTRAP.  -brl
	 */
	if (current->exit_code) {
		send_sig(current->exit_code, current, 1);
		current->exit_code = 0;
	}
	ret = is_sysemu;
out:
	if (unlikely(current->audit_context) && !entryexit)
		audit_syscall_entry(AUDIT_ARCH_I386, regs->orig_ax,
				    regs->bx, regs->cx, regs->dx, regs->si);
	if (ret == 0)
		return 0;

	regs->orig_ax = -1; /* force skip of syscall restarting */
	if (unlikely(current->audit_context))
		audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax);
	return 1;
}

#else  /* CONFIG_X86_64 */

static void syscall_trace(struct pt_regs *regs)
{

#if 0
	printk("trace %s ip %lx sp %lx ax %d origrax %d caller %lx tiflags %x ptrace %x\n",
	       current->comm,
	       regs->ip, regs->sp, regs->ax, regs->orig_ax, __builtin_return_address(0),
	       current_thread_info()->flags, current->ptrace);
#endif

	ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
				? 0x80 : 0));
	/*
	 * this isn't the same as continuing with a signal, but it will do
	 * for normal use.  strace only continues with a signal if the
	 * stopping signal is not SIGTRAP.  -brl
	 */
	if (current->exit_code) {
		send_sig(current->exit_code, current, 1);
		current->exit_code = 0;
	}
}

asmlinkage void syscall_trace_enter(struct pt_regs *regs)
{
	/* do the secure computing check first */
	secure_computing(regs->orig_ax);

	if (test_thread_flag(TIF_SYSCALL_TRACE)
	    && (current->ptrace & PT_PTRACED))
		syscall_trace(regs);

	if (unlikely(current->audit_context)) {
		if (test_thread_flag(TIF_IA32)) {
			audit_syscall_entry(AUDIT_ARCH_I386,
					    regs->orig_ax,
					    regs->bx, regs->cx,
					    regs->dx, regs->si);
		} else {
			audit_syscall_entry(AUDIT_ARCH_X86_64,
					    regs->orig_ax,
					    regs->di, regs->si,
					    regs->dx, regs->r10);
		}
	}
}

asmlinkage void syscall_trace_leave(struct pt_regs *regs)
{
	if (unlikely(current->audit_context))
		audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax);

	if ((test_thread_flag(TIF_SYSCALL_TRACE)
	     || test_thread_flag(TIF_SINGLESTEP))
	    && (current->ptrace & PT_PTRACED))
		syscall_trace(regs);
}

#endif	/* CONFIG_X86_32 */