summaryrefslogtreecommitdiffstats
path: root/arch/x86_64/kernel/ptrace.c
blob: c7011675007d4a44f50ec31db3b5f7ceb57e5663 (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
/* ptrace.c */
/* By Ross Biro 1/23/92 */
/*
 * Pentium III FXSR, SSE support
 *	Gareth Hughes <gareth@valinux.com>, May 2000
 * 
 * x86-64 port 2000-2002 Andi Kleen
 */

#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/smp_lock.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 <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/proto.h>
#include <asm/ia32.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 0x44dd5UL

/* set's the trap flag. */
#define TRAP_FLAG 0x100UL

/*
 * eflags and offset of eflags on child stack..
 */
#define EFLAGS offsetof(struct pt_regs, eflags)
#define EFL_OFFSET ((int)(EFLAGS-sizeof(struct pt_regs)))

/*
 * this routine will get a word off of the processes privileged stack. 
 * the offset is how far from the base addr as stored in the TSS.  
 * this routine assumes that all the privileged stacks are in our
 * data space.
 */   
static inline unsigned long get_stack_long(struct task_struct *task, int offset)
{
	unsigned char *stack;

	stack = (unsigned char *)task->thread.rsp0;
	stack += offset;
	return (*((unsigned long *)stack));
}

static inline struct pt_regs *get_child_regs(struct task_struct *task)
{
	struct pt_regs *regs = (void *)task->thread.rsp0;
	return regs - 1;
}

/*
 * this routine will put a word on the processes privileged stack. 
 * the offset is how far from the base addr as stored in the TSS.  
 * this routine assumes that all the privileged stacks are in our
 * data space.
 */
static inline long put_stack_long(struct task_struct *task, int offset,
	unsigned long data)
{
	unsigned char * stack;

	stack = (unsigned char *) task->thread.rsp0;
	stack += offset;
	*(unsigned long *) stack = data;
	return 0;
}

#define LDT_SEGMENT 4

unsigned long convert_rip_to_linear(struct task_struct *child, struct pt_regs *regs)
{
	unsigned long addr, seg;

	addr = regs->rip;
	seg = regs->cs & 0xffff;

	/*
	 * We'll assume that the code segments in the GDT
	 * are all zero-based. That is largely true: the
	 * TLS segments are used for data, and the PNPBIOS
	 * and APM bios ones we just ignore here.
	 */
	if (seg & LDT_SEGMENT) {
		u32 *desc;
		unsigned long base;

		down(&child->mm->context.sem);
		desc = child->mm->context.ldt + (seg & ~7);
		base = (desc[0] >> 16) | ((desc[1] & 0xff) << 16) | (desc[1] & 0xff000000);

		/* 16-bit code segment? */
		if (!((desc[1] >> 22) & 1))
			addr &= 0xffff;
		addr += base;
		up(&child->mm->context.sem);
	}
	return addr;
}

static int is_at_popf(struct task_struct *child, struct pt_regs *regs)
{
	int i, copied;
	unsigned char opcode[16];
	unsigned long addr = convert_rip_to_linear(child, regs);

	copied = access_process_vm(child, addr, opcode, sizeof(opcode), 0);
	for (i = 0; i < copied; i++) {
		switch (opcode[i]) {
		/* popf */
		case 0x9d:
			return 1;

			/* CHECKME: 64 65 */

		/* opcode and address size prefixes */
		case 0x66: case 0x67:
			continue;
		/* irrelevant prefixes (segment overrides and repeats) */
		case 0x26: case 0x2e:
		case 0x36: case 0x3e:
		case 0x64: case 0x65:
		case 0xf0: case 0xf2: case 0xf3:
			continue;

		/* REX prefixes */
		case 0x40 ... 0x4f:
			continue;

			/* CHECKME: f0, f2, f3 */

		/*
		 * pushf: NOTE! We should probably not let
		 * the user see the TF bit being set. But
		 * it's more pain than it's worth to avoid
		 * it, and a debugger could emulate this
		 * all in user space if it _really_ cares.
		 */
		case 0x9c:
		default:
			return 0;
		}
	}
	return 0;
}

static void set_singlestep(struct task_struct *child)
{
	struct pt_regs *regs = get_child_regs(child);

	/*
	 * Always set TIF_SINGLESTEP - this guarantees that
	 * we single-step system calls etc..  This will also
	 * cause us to set TF when returning to user mode.
	 */
	set_tsk_thread_flag(child, TIF_SINGLESTEP);

	/*
	 * If TF was already set, don't do anything else
	 */
	if (regs->eflags & TRAP_FLAG)
		return;

	/* Set TF on the kernel stack.. */
	regs->eflags |= TRAP_FLAG;

	/*
	 * ..but if TF is changed by the instruction we will trace,
	 * don't mark it as being "us" that set it, so that we
	 * won't clear it by hand later.
	 *
	 * AK: this is not enough, LAHF and IRET can change TF in user space too.
	 */
	if (is_at_popf(child, regs))
		return;

	child->ptrace |= PT_DTRACE;
}

static void clear_singlestep(struct task_struct *child)
{
	/* Always clear TIF_SINGLESTEP... */
	clear_tsk_thread_flag(child, TIF_SINGLESTEP);

	/* But touch TF only if it was set by us.. */
	if (child->ptrace & PT_DTRACE) {
		struct pt_regs *regs = get_child_regs(child);
		regs->eflags &= ~TRAP_FLAG;
		child->ptrace &= ~PT_DTRACE;
	}
}

/*
 * Called by kernel/ptrace.c when detaching..
 *
 * Make sure the single step bit is not set.
 */
void ptrace_disable(struct task_struct *child)
{ 
	clear_singlestep(child);
}

static int putreg(struct task_struct *child,
	unsigned long regno, unsigned long value)
{
	unsigned long tmp; 
	
	/* Some code in the 64bit emulation may not be 64bit clean.
	   Don't take any chances. */
	if (test_tsk_thread_flag(child, TIF_IA32))
		value &= 0xffffffff;
	switch (regno) {
		case offsetof(struct user_regs_struct,fs):
			if (value && (value & 3) != 3)
				return -EIO;
			child->thread.fsindex = value & 0xffff; 
			return 0;
		case offsetof(struct user_regs_struct,gs):
			if (value && (value & 3) != 3)
				return -EIO;
			child->thread.gsindex = value & 0xffff;
			return 0;
		case offsetof(struct user_regs_struct,ds):
			if (value && (value & 3) != 3)
				return -EIO;
			child->thread.ds = value & 0xffff;
			return 0;
		case offsetof(struct user_regs_struct,es): 
			if (value && (value & 3) != 3)
				return -EIO;
			child->thread.es = value & 0xffff;
			return 0;
		case offsetof(struct user_regs_struct,ss):
			if ((value & 3) != 3)
				return -EIO;
			value &= 0xffff;
			return 0;
		case offsetof(struct user_regs_struct,fs_base):
			if (!((value >> 48) == 0 || (value >> 48) == 0xffff))
				return -EIO; 
			child->thread.fs = value;
			return 0;
		case offsetof(struct user_regs_struct,gs_base):
			if (!((value >> 48) == 0 || (value >> 48) == 0xffff))
				return -EIO; 
			child->thread.gs = value;
			return 0;
		case offsetof(struct user_regs_struct, eflags):
			value &= FLAG_MASK;
			tmp = get_stack_long(child, EFL_OFFSET); 
			tmp &= ~FLAG_MASK; 
			value |= tmp;
			break;
		case offsetof(struct user_regs_struct,cs): 
			if ((value & 3) != 3)
				return -EIO;
			value &= 0xffff;
			break;
	}
	put_stack_long(child, regno - sizeof(struct pt_regs), value);
	return 0;
}

static unsigned long getreg(struct task_struct *child, unsigned long regno)
{
	unsigned long val;
	switch (regno) {
		case offsetof(struct user_regs_struct, fs):
			return child->thread.fsindex;
		case offsetof(struct user_regs_struct, gs):
			return child->thread.gsindex;
		case offsetof(struct user_regs_struct, ds):
			return child->thread.ds;
		case offsetof(struct user_regs_struct, es):
			return child->thread.es; 
		case offsetof(struct user_regs_struct, fs_base):
			return child->thread.fs;
		case offsetof(struct user_regs_struct, gs_base):
			return child->thread.gs;
		default:
			regno = regno - sizeof(struct pt_regs);
			val = get_stack_long(child, regno);
			if (test_tsk_thread_flag(child, TIF_IA32))
				val &= 0xffffffff;
			return val;
	}

}

asmlinkage long sys_ptrace(long request, long pid, unsigned long addr, long data)
{
	struct task_struct *child;
	long i, ret;
	unsigned ui;

	/* This lock_kernel fixes a subtle race with suid exec */
	lock_kernel();
	ret = -EPERM;
	if (request == PTRACE_TRACEME) {
		/* are we already being traced? */
		if (current->ptrace & PT_PTRACED)
			goto out;
		ret = security_ptrace(current->parent, current);
		if (ret)
			goto out;
		/* set the ptrace bit in the process flags. */
		current->ptrace |= PT_PTRACED;
		ret = 0;
		goto out;
	}
	ret = -ESRCH;
	read_lock(&tasklist_lock);
	child = find_task_by_pid(pid);
	if (child)
		get_task_struct(child);
	read_unlock(&tasklist_lock);
	if (!child)
		goto out;

	ret = -EPERM;
	if (pid == 1)		/* you may not mess with init */
		goto out_tsk;

	if (request == PTRACE_ATTACH) {
		ret = ptrace_attach(child);
		goto out_tsk;
	}
	ret = ptrace_check_attach(child, request == PTRACE_KILL); 
	if (ret < 0) 
		goto out_tsk;

	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: {
		unsigned long tmp;
		int copied;

		copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
		ret = -EIO;
		if (copied != sizeof(tmp))
			break;
		ret = put_user(tmp,(unsigned long __user *) data);
		break;
	}

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

		ret = -EIO;
		if ((addr & 7) ||
		    addr > sizeof(struct user) - 7)
			break;

		switch (addr) { 
		case 0 ... sizeof(struct user_regs_struct):
			tmp = getreg(child, addr);
			break;
		case offsetof(struct user, u_debugreg[0]):
			tmp = child->thread.debugreg0;
			break;
		case offsetof(struct user, u_debugreg[1]):
			tmp = child->thread.debugreg1;
			break;
		case offsetof(struct user, u_debugreg[2]):
			tmp = child->thread.debugreg2;
			break;
		case offsetof(struct user, u_debugreg[3]):
			tmp = child->thread.debugreg3;
			break;
		case offsetof(struct user, u_debugreg[6]):
			tmp = child->thread.debugreg6;
			break;
		case offsetof(struct user, u_debugreg[7]):
			tmp = child->thread.debugreg7;
			break;
		default:
			tmp = 0;
			break;
		}
		ret = put_user(tmp,(unsigned long __user *) data);
		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 = 0;
		if (access_process_vm(child, addr, &data, sizeof(data), 1) == sizeof(data))
			break;
		ret = -EIO;
		break;

	case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
		ret = -EIO;
		if ((addr & 7) ||
		    addr > sizeof(struct user) - 7)
			break;

		switch (addr) { 
		case 0 ... sizeof(struct user_regs_struct): 
			ret = putreg(child, addr, data);
			break;
		/* Disallows to set a breakpoint into the vsyscall */
		case offsetof(struct user, u_debugreg[0]):
			if (data >= TASK_SIZE-7) break;
			child->thread.debugreg0 = data;
			ret = 0;
			break;
		case offsetof(struct user, u_debugreg[1]):
			if (data >= TASK_SIZE-7) break;
			child->thread.debugreg1 = data;
			ret = 0;
			break;
		case offsetof(struct user, u_debugreg[2]):
			if (data >= TASK_SIZE-7) break;
			child->thread.debugreg2 = data;
			ret = 0;
			break;
		case offsetof(struct user, u_debugreg[3]):
			if (data >= TASK_SIZE-7) break;
			child->thread.debugreg3 = data;
			ret = 0;
			break;
		case offsetof(struct user, u_debugreg[6]):
				  if (data >> 32)
				break; 
			child->thread.debugreg6 = data;
			ret = 0;
			break;
		case offsetof(struct user, u_debugreg[7]):
			/* See arch/i386/kernel/ptrace.c for an explanation of
			 * this awkward check.*/
				  data &= ~DR_CONTROL_RESERVED;
				  for(i=0; i<4; i++)
					  if ((0x5454 >> ((data >> (16 + 4*i)) & 0xf)) & 1)
					break;
			if (i == 4) {
				child->thread.debugreg7 = data;
			  ret = 0;
		  }
		  break;
		}
		break;
	case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */
	case PTRACE_CONT:    /* restart after signal. */

		ret = -EIO;
		if ((unsigned long) data > _NSIG)
			break;
		if (request == PTRACE_SYSCALL)
			set_tsk_thread_flag(child,TIF_SYSCALL_TRACE);
		else
			clear_tsk_thread_flag(child,TIF_SYSCALL_TRACE);
		clear_tsk_thread_flag(child, TIF_SINGLESTEP);
		child->exit_code = data;
		/* make sure the single step bit is not set. */
		clear_singlestep(child);
		wake_up_process(child);
		ret = 0;
		break;

#ifdef CONFIG_IA32_EMULATION
		/* This makes only sense with 32bit programs. Allow a
		   64bit debugger to fully examine them too. Better
		   don't use it against 64bit processes, use
		   PTRACE_ARCH_PRCTL instead. */
	case PTRACE_SET_THREAD_AREA: {
		struct user_desc __user *p;
		int old; 
		p = (struct user_desc __user *)data;
		get_user(old,  &p->entry_number); 
		put_user(addr, &p->entry_number);
		ret = do_set_thread_area(&child->thread, p);
		put_user(old,  &p->entry_number); 
		break;
	case PTRACE_GET_THREAD_AREA:
		p = (struct user_desc __user *)data;
		get_user(old,  &p->entry_number); 
		put_user(addr, &p->entry_number);
		ret = do_get_thread_area(&child->thread, p);
		put_user(old,  &p->entry_number); 
		break;
	} 
#endif
		/* 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;

/*
 * make the child exit.  Best I can do is send it a sigkill. 
 * perhaps it should be put in the status that it wants to 
 * exit.
 */
	case PTRACE_KILL:
		ret = 0;
		if (child->exit_state == EXIT_ZOMBIE)	/* already dead */
			break;
		clear_tsk_thread_flag(child, TIF_SINGLESTEP);
		child->exit_code = SIGKILL;
		/* make sure the single step bit is not set. */
		clear_singlestep(child);
		wake_up_process(child);
		break;

	case PTRACE_SINGLESTEP:    /* set the trap flag. */
		ret = -EIO;
		if ((unsigned long) data > _NSIG)
			break;
		clear_tsk_thread_flag(child,TIF_SYSCALL_TRACE);
		set_singlestep(child);
		child->exit_code = data;
		/* give it a chance to run. */
		wake_up_process(child);
		ret = 0;
		break;

	case PTRACE_DETACH:
		/* detach a process that was attached. */
		ret = ptrace_detach(child, data);
		break;

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

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

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

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

	default:
		ret = ptrace_request(child, request, addr, data);
		break;
	}
out_tsk:
	put_task_struct(child);
out:
	unlock_kernel();
	return ret;
}

static void syscall_trace(struct pt_regs *regs)
{

#if 0
	printk("trace %s rip %lx rsp %lx rax %d origrax %d caller %lx tiflags %x ptrace %x\n",
	       current->comm,
	       regs->rip, regs->rsp, regs->rax, regs->orig_rax, __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_rax);

	if (unlikely(current->audit_context))
		audit_syscall_entry(current, regs->orig_rax,
				    regs->rdi, regs->rsi,
				    regs->rdx, regs->r10);

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

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

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