ptrace.c 11.0 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9
/*
 * linux/kernel/ptrace.c
 *
 * (C) Copyright 1999 Linus Torvalds
 *
 * Common interfaces for "ptrace()" which we do not want
 * to continually duplicate across every architecture.
 */

10
#include <linux/capability.h>
L
Linus Torvalds 已提交
11 12 13 14 15 16 17 18 19
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/smp_lock.h>
#include <linux/ptrace.h>
#include <linux/security.h>
20
#include <linux/signal.h>
L
Linus Torvalds 已提交
21 22 23 24 25 26 27 28 29 30

#include <asm/pgtable.h>
#include <asm/uaccess.h>

/*
 * ptrace a task: make the debugger its new parent and
 * move it to the ptrace list.
 *
 * Must be called with the tasklist lock write-held.
 */
31
void __ptrace_link(struct task_struct *child, struct task_struct *new_parent)
L
Linus Torvalds 已提交
32
{
33
	BUG_ON(!list_empty(&child->ptrace_list));
L
Linus Torvalds 已提交
34 35 36
	if (child->parent == new_parent)
		return;
	list_add(&child->ptrace_list, &child->parent->ptrace_children);
37
	remove_parent(child);
L
Linus Torvalds 已提交
38
	child->parent = new_parent;
39
	add_parent(child);
L
Linus Torvalds 已提交
40 41 42 43 44 45 46 47 48
}
 
/*
 * Turn a tracing stop into a normal stop now, since with no tracer there
 * would be no way to wake it up with SIGCONT or SIGKILL.  If there was a
 * signal sent that would resume the child, but didn't because it was in
 * TASK_TRACED, resume it now.
 * Requires that irqs be disabled.
 */
49
void ptrace_untrace(struct task_struct *child)
L
Linus Torvalds 已提交
50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67
{
	spin_lock(&child->sighand->siglock);
	if (child->state == TASK_TRACED) {
		if (child->signal->flags & SIGNAL_STOP_STOPPED) {
			child->state = TASK_STOPPED;
		} else {
			signal_wake_up(child, 1);
		}
	}
	spin_unlock(&child->sighand->siglock);
}

/*
 * unptrace a task: move it back to its original parent and
 * remove it from the ptrace list.
 *
 * Must be called with the tasklist lock write-held.
 */
68
void __ptrace_unlink(struct task_struct *child)
L
Linus Torvalds 已提交
69
{
70 71
	BUG_ON(!child->ptrace);

L
Linus Torvalds 已提交
72 73 74
	child->ptrace = 0;
	if (!list_empty(&child->ptrace_list)) {
		list_del_init(&child->ptrace_list);
75
		remove_parent(child);
L
Linus Torvalds 已提交
76
		child->parent = child->real_parent;
77
		add_parent(child);
L
Linus Torvalds 已提交
78 79
	}

80 81
	if (child->state == TASK_TRACED)
		ptrace_untrace(child);
L
Linus Torvalds 已提交
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
}

/*
 * Check that we have indeed attached to the thing..
 */
int ptrace_check_attach(struct task_struct *child, int kill)
{
	int ret = -ESRCH;

	/*
	 * We take the read lock around doing both checks to close a
	 * possible race where someone else was tracing our child and
	 * detached between these two checks.  After this locked check,
	 * we are sure that this is our traced child and that can only
	 * be changed by us so it's not changing right after this.
	 */
	read_lock(&tasklist_lock);
	if ((child->ptrace & PT_PTRACED) && child->parent == current &&
	    (!(child->ptrace & PT_ATTACHED) || child->real_parent != current)
	    && child->signal != NULL) {
		ret = 0;
		spin_lock_irq(&child->sighand->siglock);
		if (child->state == TASK_STOPPED) {
			child->state = TASK_TRACED;
		} else if (child->state != TASK_TRACED && !kill) {
			ret = -ESRCH;
		}
		spin_unlock_irq(&child->sighand->siglock);
	}
	read_unlock(&tasklist_lock);

	if (!ret && !kill) {
		wait_task_inactive(child);
	}

	/* All systems go.. */
	return ret;
}

121 122
static int may_attach(struct task_struct *task)
{
123 124 125 126 127 128 129 130 131 132 133 134
	/* May we inspect the given task?
	 * This check is used both for attaching with ptrace
	 * and for allowing access to sensitive information in /proc.
	 *
	 * ptrace_attach denies several cases that /proc allows
	 * because setting up the necessary parent/child relationship
	 * or halting the specified task is impossible.
	 */
	int dumpable = 0;
	/* Don't let security modules deny introspection */
	if (task == current)
		return 0;
135 136 137 138 139 140 141 142
	if (((current->uid != task->euid) ||
	     (current->uid != task->suid) ||
	     (current->uid != task->uid) ||
	     (current->gid != task->egid) ||
	     (current->gid != task->sgid) ||
	     (current->gid != task->gid)) && !capable(CAP_SYS_PTRACE))
		return -EPERM;
	smp_rmb();
143 144 145
	if (task->mm)
		dumpable = task->mm->dumpable;
	if (!dumpable && !capable(CAP_SYS_PTRACE))
146 147 148 149 150 151 152 153 154 155 156 157 158 159
		return -EPERM;

	return security_ptrace(current, task);
}

int ptrace_may_attach(struct task_struct *task)
{
	int err;
	task_lock(task);
	err = may_attach(task);
	task_unlock(task);
	return !err;
}

L
Linus Torvalds 已提交
160 161 162
int ptrace_attach(struct task_struct *task)
{
	int retval;
163

L
Linus Torvalds 已提交
164 165
	retval = -EPERM;
	if (task->pid <= 1)
166
		goto out;
L
Linus Torvalds 已提交
167
	if (task->tgid == current->tgid)
168 169
		goto out;

170 171 172 173 174 175 176 177 178 179
repeat:
	/*
	 * Nasty, nasty.
	 *
	 * We want to hold both the task-lock and the
	 * tasklist_lock for writing at the same time.
	 * But that's against the rules (tasklist_lock
	 * is taken for reading by interrupts on other
	 * cpu's that may have task_lock).
	 */
180
	task_lock(task);
181 182 183 184 185 186 187 188 189
	local_irq_disable();
	if (!write_trylock(&tasklist_lock)) {
		local_irq_enable();
		task_unlock(task);
		do {
			cpu_relax();
		} while (!write_can_lock(&tasklist_lock));
		goto repeat;
	}
190

191 192
	if (!task->mm)
		goto bad;
L
Linus Torvalds 已提交
193 194 195
	/* the same process cannot be attached many times */
	if (task->ptrace & PT_PTRACED)
		goto bad;
196
	retval = may_attach(task);
L
Linus Torvalds 已提交
197 198 199 200 201 202 203 204 205 206 207 208 209 210
	if (retval)
		goto bad;

	/* Go */
	task->ptrace |= PT_PTRACED | ((task->real_parent != current)
				      ? PT_ATTACHED : 0);
	if (capable(CAP_SYS_PTRACE))
		task->ptrace |= PT_PTRACE_CAP;

	__ptrace_link(task, current);

	force_sig_specific(SIGSTOP, task);

bad:
211
	write_unlock_irq(&tasklist_lock);
L
Linus Torvalds 已提交
212
	task_unlock(task);
213
out:
L
Linus Torvalds 已提交
214 215 216
	return retval;
}

217
static inline void __ptrace_detach(struct task_struct *child, unsigned int data)
218 219 220 221 222 223 224 225 226
{
	child->exit_code = data;
	/* .. re-parent .. */
	__ptrace_unlink(child);
	/* .. and wake it up. */
	if (child->exit_state != EXIT_ZOMBIE)
		wake_up_process(child);
}

L
Linus Torvalds 已提交
227 228
int ptrace_detach(struct task_struct *child, unsigned int data)
{
229
	if (!valid_signal(data))
230
		return -EIO;
L
Linus Torvalds 已提交
231 232 233 234 235

	/* Architecture-specific hardware disable .. */
	ptrace_disable(child);

	write_lock_irq(&tasklist_lock);
236
	/* protect against de_thread()->release_task() */
237 238
	if (child->ptrace)
		__ptrace_detach(child, data);
L
Linus Torvalds 已提交
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
	write_unlock_irq(&tasklist_lock);

	return 0;
}

int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len)
{
	int copied = 0;

	while (len > 0) {
		char buf[128];
		int this_len, retval;

		this_len = (len > sizeof(buf)) ? sizeof(buf) : len;
		retval = access_process_vm(tsk, src, buf, this_len, 0);
		if (!retval) {
			if (copied)
				break;
			return -EIO;
		}
		if (copy_to_user(dst, buf, retval))
			return -EFAULT;
		copied += retval;
		src += retval;
		dst += retval;
		len -= retval;			
	}
	return copied;
}

int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len)
{
	int copied = 0;

	while (len > 0) {
		char buf[128];
		int this_len, retval;

		this_len = (len > sizeof(buf)) ? sizeof(buf) : len;
		if (copy_from_user(buf, src, this_len))
			return -EFAULT;
		retval = access_process_vm(tsk, dst, buf, this_len, 1);
		if (!retval) {
			if (copied)
				break;
			return -EIO;
		}
		copied += retval;
		src += retval;
		dst += retval;
		len -= retval;			
	}
	return copied;
}

static int ptrace_setoptions(struct task_struct *child, long data)
{
	child->ptrace &= ~PT_TRACE_MASK;

	if (data & PTRACE_O_TRACESYSGOOD)
		child->ptrace |= PT_TRACESYSGOOD;

	if (data & PTRACE_O_TRACEFORK)
		child->ptrace |= PT_TRACE_FORK;

	if (data & PTRACE_O_TRACEVFORK)
		child->ptrace |= PT_TRACE_VFORK;

	if (data & PTRACE_O_TRACECLONE)
		child->ptrace |= PT_TRACE_CLONE;

	if (data & PTRACE_O_TRACEEXEC)
		child->ptrace |= PT_TRACE_EXEC;

	if (data & PTRACE_O_TRACEVFORKDONE)
		child->ptrace |= PT_TRACE_VFORK_DONE;

	if (data & PTRACE_O_TRACEEXIT)
		child->ptrace |= PT_TRACE_EXIT;

	return (data & ~PTRACE_O_MASK) ? -EINVAL : 0;
}

static int ptrace_getsiginfo(struct task_struct *child, siginfo_t __user * data)
{
	siginfo_t lastinfo;
	int error = -ESRCH;

	read_lock(&tasklist_lock);
	if (likely(child->sighand != NULL)) {
		error = -EINVAL;
		spin_lock_irq(&child->sighand->siglock);
		if (likely(child->last_siginfo != NULL)) {
			lastinfo = *child->last_siginfo;
			error = 0;
		}
		spin_unlock_irq(&child->sighand->siglock);
	}
	read_unlock(&tasklist_lock);
	if (!error)
		return copy_siginfo_to_user(data, &lastinfo);
	return error;
}

static int ptrace_setsiginfo(struct task_struct *child, siginfo_t __user * data)
{
	siginfo_t newinfo;
	int error = -ESRCH;

	if (copy_from_user(&newinfo, data, sizeof (siginfo_t)))
		return -EFAULT;

	read_lock(&tasklist_lock);
	if (likely(child->sighand != NULL)) {
		error = -EINVAL;
		spin_lock_irq(&child->sighand->siglock);
		if (likely(child->last_siginfo != NULL)) {
			*child->last_siginfo = newinfo;
			error = 0;
		}
		spin_unlock_irq(&child->sighand->siglock);
	}
	read_unlock(&tasklist_lock);
	return error;
}

int ptrace_request(struct task_struct *child, long request,
		   long addr, long data)
{
	int ret = -EIO;

	switch (request) {
#ifdef PTRACE_OLDSETOPTIONS
	case PTRACE_OLDSETOPTIONS:
#endif
	case PTRACE_SETOPTIONS:
		ret = ptrace_setoptions(child, data);
		break;
	case PTRACE_GETEVENTMSG:
		ret = put_user(child->ptrace_message, (unsigned long __user *) data);
		break;
	case PTRACE_GETSIGINFO:
		ret = ptrace_getsiginfo(child, (siginfo_t __user *) data);
		break;
	case PTRACE_SETSIGINFO:
		ret = ptrace_setsiginfo(child, (siginfo_t __user *) data);
		break;
	default:
		break;
	}

	return ret;
}
392

393 394 395 396 397 398 399
/**
 * ptrace_traceme  --  helper for PTRACE_TRACEME
 *
 * Performs checks and sets PT_PTRACED.
 * Should be used by all ptrace implementations for PTRACE_TRACEME.
 */
int ptrace_traceme(void)
400
{
401
	int ret = -EPERM;
402 403

	/*
404 405
	 * Are we already being traced?
	 */
406 407 408 409 410 411 412 413 414 415 416
	task_lock(current);
	if (!(current->ptrace & PT_PTRACED)) {
		ret = security_ptrace(current->parent, current);
		/*
		 * Set the ptrace bit in the process ptrace flags.
		 */
		if (!ret)
			current->ptrace |= PT_PTRACED;
	}
	task_unlock(current);
	return ret;
417
}
418

419 420 421 422 423 424 425 426 427 428 429 430 431
/**
 * ptrace_get_task_struct  --  grab a task struct reference for ptrace
 * @pid:       process id to grab a task_struct reference of
 *
 * This function is a helper for ptrace implementations.  It checks
 * permissions and then grabs a task struct for use of the actual
 * ptrace implementation.
 *
 * Returns the task_struct for @pid or an ERR_PTR() on failure.
 */
struct task_struct *ptrace_get_task_struct(pid_t pid)
{
	struct task_struct *child;
432 433

	/*
434
	 * Tracing init is not allowed.
435 436
	 */
	if (pid == 1)
437
		return ERR_PTR(-EPERM);
438 439 440 441 442 443 444

	read_lock(&tasklist_lock);
	child = find_task_by_pid(pid);
	if (child)
		get_task_struct(child);
	read_unlock(&tasklist_lock);
	if (!child)
445 446
		return ERR_PTR(-ESRCH);
	return child;
447 448
}

449
#ifndef __ARCH_SYS_PTRACE
450 451 452 453 454 455 456 457 458
asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
{
	struct task_struct *child;
	long ret;

	/*
	 * This lock_kernel fixes a subtle race with suid exec
	 */
	lock_kernel();
459 460
	if (request == PTRACE_TRACEME) {
		ret = ptrace_traceme();
461
		goto out;
462 463 464 465 466 467 468
	}

	child = ptrace_get_task_struct(pid);
	if (IS_ERR(child)) {
		ret = PTR_ERR(child);
		goto out;
	}
469 470 471

	if (request == PTRACE_ATTACH) {
		ret = ptrace_attach(child);
472
		goto out_put_task_struct;
473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489
	}

	ret = ptrace_check_attach(child, request == PTRACE_KILL);
	if (ret < 0)
		goto out_put_task_struct;

	ret = arch_ptrace(child, request, addr, data);
	if (ret < 0)
		goto out_put_task_struct;

 out_put_task_struct:
	put_task_struct(child);
 out:
	unlock_kernel();
	return ret;
}
#endif /* __ARCH_SYS_PTRACE */