ptrace.c 18.7 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
/* 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>
17
#include <linux/signal.h>
L
Linus Torvalds 已提交
18 19 20 21 22 23 24 25 26

#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>
27 28
#include <asm/prctl.h>
#include <asm/proto.h>
L
Linus Torvalds 已提交
29 30 31 32 33 34

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

35 36 37
/*
 * Determines which flags the user has access to [1 = access, 0 = no access].
 */
R
Roland McGrath 已提交
38 39 40 41 42 43 44
#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))

45 46 47 48 49 50 51 52 53 54
/*
 * 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

R
Roland McGrath 已提交
55
#define FLAG_MASK		FLAG_MASK_32
L
Linus Torvalds 已提交
56

R
Roland McGrath 已提交
57
static long *pt_regs_access(struct pt_regs *regs, unsigned long regno)
L
Linus Torvalds 已提交
58
{
59
	BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0);
60
	regno >>= 2;
R
Roland McGrath 已提交
61 62
	if (regno > FS)
		--regno;
63
	return &regs->bx + regno;
L
Linus Torvalds 已提交
64 65
}

66
static u16 get_segment_reg(struct task_struct *task, unsigned long offset)
L
Linus Torvalds 已提交
67
{
68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87
	/*
	 * 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.
	 */
88
	if (invalid_selector(value))
89 90 91 92 93 94 95
		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)
96 97 98 99 100
			/*
			 * The user-mode %gs is not affected by
			 * kernel entry, so we must update the CPU.
			 */
			loadsegment(gs, value);
L
Linus Torvalds 已提交
101
	}
102

L
Linus Torvalds 已提交
103 104 105
	return 0;
}

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
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;
		break;
#endif
	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;
		break;
#endif
	}

	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 */

242
static unsigned long get_flags(struct task_struct *task)
L
Linus Torvalds 已提交
243
{
244 245 246 247 248 249 250
	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;
L
Linus Torvalds 已提交
251 252 253 254

	return retval;
}

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
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);
288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310

#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
311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329
	}

	*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);
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

#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
361 362 363 364 365
	}

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

366 367 368 369 370 371 372
/*
 * 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)
{
373 374 375 376 377 378 379 380 381
	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;
382 383 384 385 386
}

static int ptrace_set_debugreg(struct task_struct *child,
			       int n, unsigned long data)
{
387 388
	int i;

389 390 391
	if (unlikely(n == 4 || n == 5))
		return -EIO;

392
	if (n < 4 && unlikely(data >= debugreg_addr_limit(child)))
393 394
		return -EIO;

395 396 397 398 399 400 401
	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:
402 403
		if ((data & ~0xffffffffUL) != 0)
			return -EIO;
404 405 406 407
		child->thread.debugreg6 = data;
		break;

	case 7:
408 409 410 411 412 413 414 415 416 417 418 419 420 421
		/*
		 * 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:
422
		 * - LENi == 0x10 (undefined), so mask |= 0x0f00.	[32-bit]
423 424 425 426 427 428 429 430 431 432 433 434 435 436 437
		 * - 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)
		 */
438 439 440 441 442
#ifdef CONFIG_X86_32
#define	DR7_MASK	0x5f54
#else
#define	DR7_MASK	0x5554
#endif
443 444
		data &= ~DR_CONTROL_RESERVED;
		for (i = 0; i < 4; i++)
445
			if ((DR7_MASK >> ((data >> (16 + 4*i)) & 0xf)) & 1)
446
				return -EIO;
447
		child->thread.debugreg7 = data;
448 449 450 451
		if (data)
			set_tsk_thread_flag(child, TIF_DEBUG);
		else
			clear_tsk_thread_flag(child, TIF_DEBUG);
452
		break;
453 454 455 456 457
	}

	return 0;
}

L
Linus Torvalds 已提交
458 459 460 461 462 463
/*
 * Called by kernel/ptrace.c when detaching..
 *
 * Make sure the single step bit is not set.
 */
void ptrace_disable(struct task_struct *child)
R
Roland McGrath 已提交
464
{
R
Roland McGrath 已提交
465
	user_disable_single_step(child);
466
	clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
L
Linus Torvalds 已提交
467 468
}

469
long arch_ptrace(struct task_struct *child, long request, long addr, long data)
L
Linus Torvalds 已提交
470 471 472 473 474 475 476
{
	struct user * dummy = NULL;
	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. */
R
Roland McGrath 已提交
477
	case PTRACE_PEEKTEXT: /* read word at location addr. */
A
Alexey Dobriyan 已提交
478 479
	case PTRACE_PEEKDATA:
		ret = generic_ptrace_peekdata(child, addr, data);
L
Linus Torvalds 已提交
480 481 482 483 484 485 486
		break;

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

		ret = -EIO;
R
Roland McGrath 已提交
487
		if ((addr & 3) || addr < 0 ||
L
Linus Torvalds 已提交
488 489 490 491 492 493 494 495 496 497
		    addr > sizeof(struct user) - 3)
			break;

		tmp = 0;  /* Default return condition */
		if(addr < FRAME_SIZE*sizeof(long))
			tmp = getreg(child, addr);
		if(addr >= (long) &dummy->u_debugreg[0] &&
		   addr <= (long) &dummy->u_debugreg[7]){
			addr -= (long) &dummy->u_debugreg[0];
			addr = addr >> 2;
498
			tmp = ptrace_get_debugreg(child, addr);
L
Linus Torvalds 已提交
499 500 501 502 503 504 505 506
		}
		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:
A
Alexey Dobriyan 已提交
507
		ret = generic_ptrace_pokedata(child, addr, data);
L
Linus Torvalds 已提交
508 509 510 511
		break;

	case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
		ret = -EIO;
R
Roland McGrath 已提交
512
		if ((addr & 3) || addr < 0 ||
L
Linus Torvalds 已提交
513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529
		    addr > sizeof(struct user) - 3)
			break;

		if (addr < FRAME_SIZE*sizeof(long)) {
			ret = putreg(child, addr, data);
			break;
		}
		/* We need to be very careful here.  We implicitly
		   want to modify a portion of the task_struct, and we
		   have to be selective about what portions we allow someone
		   to modify. */

		  ret = -EIO;
		  if(addr >= (long) &dummy->u_debugreg[0] &&
		     addr <= (long) &dummy->u_debugreg[7]){
			  addr -= (long) &dummy->u_debugreg;
			  addr = addr >> 2;
530
			  ret = ptrace_set_debugreg(child, addr, data);
L
Linus Torvalds 已提交
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
		  }
		  break;

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

	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;
	}

	case PTRACE_GET_THREAD_AREA:
R
Roland McGrath 已提交
611 612 613 614
		if (addr < 0)
			return -EIO;
		ret = do_get_thread_area(child, addr,
					 (struct user_desc __user *) data);
L
Linus Torvalds 已提交
615 616 617
		break;

	case PTRACE_SET_THREAD_AREA:
R
Roland McGrath 已提交
618 619 620 621
		if (addr < 0)
			return -EIO;
		ret = do_set_thread_area(child, addr,
					 (struct user_desc __user *) data, 0);
L
Linus Torvalds 已提交
622 623 624 625 626 627
		break;

	default:
		ret = ptrace_request(child, request, addr, data);
		break;
	}
628

L
Linus Torvalds 已提交
629 630 631 632 633 634 635 636 637 638 639 640 641 642
	return ret;
}

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;

643 644
	/* User-mode ip? */
	info.si_addr = user_mode_vm(regs) ? (void __user *) regs->ip : NULL;
L
Linus Torvalds 已提交
645

S
Simon Arlott 已提交
646
	/* Send us the fake SIGTRAP */
L
Linus Torvalds 已提交
647 648 649 650 651 652 653
	force_sig_info(SIGTRAP, &info, tsk);
}

/* notification of system call entry/exit
 * - triggered by current->work.syscall_trace
 */
__attribute__((regparm(3)))
654
int do_syscall_trace(struct pt_regs *regs, int entryexit)
L
Linus Torvalds 已提交
655
{
656 657 658 659 660
	int is_sysemu = test_thread_flag(TIF_SYSCALL_EMU);
	/*
	 * With TIF_SYSCALL_EMU set we want to ignore TIF_SINGLESTEP for syscall
	 * interception
	 */
661
	int is_singlestep = !is_sysemu && test_thread_flag(TIF_SINGLESTEP);
662
	int ret = 0;
663

L
Linus Torvalds 已提交
664
	/* do the secure computing check first */
665
	if (!entryexit)
666
		secure_computing(regs->orig_ax);
L
Linus Torvalds 已提交
667

668 669
	if (unlikely(current->audit_context)) {
		if (entryexit)
670 671
			audit_syscall_exit(AUDITSC_RESULT(regs->ax),
						regs->ax);
672 673 674 675 676 677 678 679 680 681 682 683 684
		/* 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;
	}
L
Linus Torvalds 已提交
685 686

	if (!(current->ptrace & PT_PTRACED))
687
		goto out;
L
Linus Torvalds 已提交
688

689 690 691 692 693
	/* 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;
694

L
Linus Torvalds 已提交
695
	/* Fake a debug trap */
696
	if (is_singlestep)
L
Linus Torvalds 已提交
697 698
		send_sigtrap(current, regs, 0);

699
 	if (!test_thread_flag(TIF_SYSCALL_TRACE) && !is_sysemu)
700
		goto out;
L
Linus Torvalds 已提交
701 702 703

	/* the 0x80 provides a way for the tracing parent to distinguish
	   between a syscall stop and SIGTRAP delivery */
704
	/* Note that the debugger could change the result of test_thread_flag!*/
705
	ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD) ? 0x80:0));
L
Linus Torvalds 已提交
706 707 708 709 710 711 712 713 714 715

	/*
	 * 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;
	}
716
	ret = is_sysemu;
717
out:
718
	if (unlikely(current->audit_context) && !entryexit)
719 720
		audit_syscall_entry(AUDIT_ARCH_I386, regs->orig_ax,
				    regs->bx, regs->cx, regs->dx, regs->si);
721 722 723
	if (ret == 0)
		return 0;

724
	regs->orig_ax = -1; /* force skip of syscall restarting */
725
	if (unlikely(current->audit_context))
726
		audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax);
727
	return 1;
L
Linus Torvalds 已提交
728
}