exec.c 34.5 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 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
/*
 *  linux/fs/exec.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

/*
 * #!-checking implemented by tytso.
 */
/*
 * Demand-loading implemented 01.12.91 - no need to read anything but
 * the header into memory. The inode of the executable is put into
 * "current->executable", and page faults do the actual loading. Clean.
 *
 * Once more I can proudly say that linux stood up to being changed: it
 * was less than 2 hours work to get demand-loading completely implemented.
 *
 * Demand loading changed July 1993 by Eric Youngdale.   Use mmap instead,
 * current->executable is only used by the procfs.  This allows a dispatch
 * table to check for several different types  of binary formats.  We keep
 * trying until we recognize the file or we run out of supported binary
 * formats. 
 */

#include <linux/config.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/mman.h>
#include <linux/a.out.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/spinlock.h>
#include <linux/key.h>
#include <linux/personality.h>
#include <linux/binfmts.h>
#include <linux/swap.h>
#include <linux/utsname.h>
#include <linux/module.h>
#include <linux/namei.h>
#include <linux/proc_fs.h>
#include <linux/ptrace.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/rmap.h>
#include <linux/acct.h>
M
Matt Helsley 已提交
51
#include <linux/cn_proc.h>
L
Linus Torvalds 已提交
52 53 54 55 56 57 58 59 60 61

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

#ifdef CONFIG_KMOD
#include <linux/kmod.h>
#endif

int core_uses_pid;
char core_pattern[65] = "core";
A
Alan Cox 已提交
62 63 64
int suid_dumpable = 0;

EXPORT_SYMBOL(suid_dumpable);
L
Linus Torvalds 已提交
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
/* The maximal length of core_pattern is also specified in sysctl.c */

static struct linux_binfmt *formats;
static DEFINE_RWLOCK(binfmt_lock);

int register_binfmt(struct linux_binfmt * fmt)
{
	struct linux_binfmt ** tmp = &formats;

	if (!fmt)
		return -EINVAL;
	if (fmt->next)
		return -EBUSY;
	write_lock(&binfmt_lock);
	while (*tmp) {
		if (fmt == *tmp) {
			write_unlock(&binfmt_lock);
			return -EBUSY;
		}
		tmp = &(*tmp)->next;
	}
	fmt->next = formats;
	formats = fmt;
	write_unlock(&binfmt_lock);
	return 0;	
}

EXPORT_SYMBOL(register_binfmt);

int unregister_binfmt(struct linux_binfmt * fmt)
{
	struct linux_binfmt ** tmp = &formats;

	write_lock(&binfmt_lock);
	while (*tmp) {
		if (fmt == *tmp) {
			*tmp = fmt->next;
			write_unlock(&binfmt_lock);
			return 0;
		}
		tmp = &(*tmp)->next;
	}
	write_unlock(&binfmt_lock);
	return -EINVAL;
}

EXPORT_SYMBOL(unregister_binfmt);

static inline void put_binfmt(struct linux_binfmt * fmt)
{
	module_put(fmt->module);
}

/*
 * Note that a shared library must be both readable and executable due to
 * security reasons.
 *
 * Also note that we take the address to load from from the file itself.
 */
asmlinkage long sys_uselib(const char __user * library)
{
	struct file * file;
	struct nameidata nd;
	int error;

130
	error = __user_path_lookup_open(library, LOOKUP_FOLLOW, &nd, FMODE_READ);
L
Linus Torvalds 已提交
131 132 133 134 135 136 137 138 139 140 141
	if (error)
		goto out;

	error = -EINVAL;
	if (!S_ISREG(nd.dentry->d_inode->i_mode))
		goto exit;

	error = permission(nd.dentry->d_inode, MAY_READ | MAY_EXEC, &nd);
	if (error)
		goto exit;

142
	file = nameidata_to_filp(&nd, O_RDONLY);
L
Linus Torvalds 已提交
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
	error = PTR_ERR(file);
	if (IS_ERR(file))
		goto out;

	error = -ENOEXEC;
	if(file->f_op) {
		struct linux_binfmt * fmt;

		read_lock(&binfmt_lock);
		for (fmt = formats ; fmt ; fmt = fmt->next) {
			if (!fmt->load_shlib)
				continue;
			if (!try_module_get(fmt->module))
				continue;
			read_unlock(&binfmt_lock);
			error = fmt->load_shlib(file);
			read_lock(&binfmt_lock);
			put_binfmt(fmt);
			if (error != -ENOEXEC)
				break;
		}
		read_unlock(&binfmt_lock);
	}
	fput(file);
out:
  	return error;
exit:
170
	release_open_intent(&nd);
L
Linus Torvalds 已提交
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
	path_release(&nd);
	goto out;
}

/*
 * count() counts the number of strings in array ARGV.
 */
static int count(char __user * __user * argv, int max)
{
	int i = 0;

	if (argv != NULL) {
		for (;;) {
			char __user * p;

			if (get_user(p, argv))
				return -EFAULT;
			if (!p)
				break;
			argv++;
			if(++i > max)
				return -E2BIG;
			cond_resched();
		}
	}
	return i;
}

/*
 * 'copy_strings()' copies argument/environment strings from user
 * memory to free pages in kernel mem. These are in a format ready
 * to be put directly into the top of new user memory.
 */
A
Adrian Bunk 已提交
204 205
static int copy_strings(int argc, char __user * __user * argv,
			struct linux_binprm *bprm)
L
Linus Torvalds 已提交
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
{
	struct page *kmapped_page = NULL;
	char *kaddr = NULL;
	int ret;

	while (argc-- > 0) {
		char __user *str;
		int len;
		unsigned long pos;

		if (get_user(str, argv+argc) ||
				!(len = strnlen_user(str, bprm->p))) {
			ret = -EFAULT;
			goto out;
		}

		if (bprm->p < len)  {
			ret = -E2BIG;
			goto out;
		}

		bprm->p -= len;
		/* XXX: add architecture specific overflow check here. */
		pos = bprm->p;

		while (len > 0) {
			int i, new, err;
			int offset, bytes_to_copy;
			struct page *page;

			offset = pos % PAGE_SIZE;
			i = pos/PAGE_SIZE;
			page = bprm->page[i];
			new = 0;
			if (!page) {
				page = alloc_page(GFP_HIGHUSER);
				bprm->page[i] = page;
				if (!page) {
					ret = -ENOMEM;
					goto out;
				}
				new = 1;
			}

			if (page != kmapped_page) {
				if (kmapped_page)
					kunmap(kmapped_page);
				kmapped_page = page;
				kaddr = kmap(kmapped_page);
			}
			if (new && offset)
				memset(kaddr, 0, offset);
			bytes_to_copy = PAGE_SIZE - offset;
			if (bytes_to_copy > len) {
				bytes_to_copy = len;
				if (new)
					memset(kaddr+offset+len, 0,
						PAGE_SIZE-offset-len);
			}
			err = copy_from_user(kaddr+offset, str, bytes_to_copy);
			if (err) {
				ret = -EFAULT;
				goto out;
			}

			pos += bytes_to_copy;
			str += bytes_to_copy;
			len -= bytes_to_copy;
		}
	}
	ret = 0;
out:
	if (kmapped_page)
		kunmap(kmapped_page);
	return ret;
}

/*
 * Like copy_strings, but get argv and its values from kernel memory.
 */
int copy_strings_kernel(int argc,char ** argv, struct linux_binprm *bprm)
{
	int r;
	mm_segment_t oldfs = get_fs();
	set_fs(KERNEL_DS);
	r = copy_strings(argc, (char __user * __user *)argv, bprm);
	set_fs(oldfs);
	return r;
}

EXPORT_SYMBOL(copy_strings_kernel);

#ifdef CONFIG_MMU
/*
 * This routine is used to map in a page into an address space: needed by
 * execve() for the initial stack and environment pages.
 *
 * vma->vm_mm->mmap_sem is held for writing.
 */
void install_arg_page(struct vm_area_struct *vma,
			struct page *page, unsigned long address)
{
	struct mm_struct *mm = vma->vm_mm;
	pgd_t * pgd;
	pud_t * pud;
	pmd_t * pmd;
	pte_t * pte;
H
Hugh Dickins 已提交
313
	spinlock_t *ptl;
L
Linus Torvalds 已提交
314 315

	if (unlikely(anon_vma_prepare(vma)))
H
Hugh Dickins 已提交
316
		goto out;
L
Linus Torvalds 已提交
317 318 319 320 321 322 323 324 325

	flush_dcache_page(page);
	pgd = pgd_offset(mm, address);
	pud = pud_alloc(mm, pgd, address);
	if (!pud)
		goto out;
	pmd = pmd_alloc(mm, pud, address);
	if (!pmd)
		goto out;
H
Hugh Dickins 已提交
326
	pte = pte_alloc_map_lock(mm, pmd, address, &ptl);
L
Linus Torvalds 已提交
327 328 329
	if (!pte)
		goto out;
	if (!pte_none(*pte)) {
H
Hugh Dickins 已提交
330
		pte_unmap_unlock(pte, ptl);
L
Linus Torvalds 已提交
331 332
		goto out;
	}
333
	inc_mm_counter(mm, anon_rss);
L
Linus Torvalds 已提交
334 335 336 337
	lru_cache_add_active(page);
	set_pte_at(mm, address, pte, pte_mkdirty(pte_mkwrite(mk_pte(
					page, vma->vm_page_prot))));
	page_add_anon_rmap(page, vma, address);
H
Hugh Dickins 已提交
338
	pte_unmap_unlock(pte, ptl);
L
Linus Torvalds 已提交
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

	/* no need for flush_tlb */
	return;
out:
	__free_page(page);
	force_sig(SIGKILL, current);
}

#define EXTRA_STACK_VM_PAGES	20	/* random */

int setup_arg_pages(struct linux_binprm *bprm,
		    unsigned long stack_top,
		    int executable_stack)
{
	unsigned long stack_base;
	struct vm_area_struct *mpnt;
	struct mm_struct *mm = current->mm;
	int i, ret;
	long arg_size;

#ifdef CONFIG_STACK_GROWSUP
	/* Move the argument and environment strings to the bottom of the
	 * stack space.
	 */
	int offset, j;
	char *to, *from;

	/* Start by shifting all the pages down */
	i = 0;
	for (j = 0; j < MAX_ARG_PAGES; j++) {
		struct page *page = bprm->page[j];
		if (!page)
			continue;
		bprm->page[i++] = page;
	}

	/* Now move them within their pages */
	offset = bprm->p % PAGE_SIZE;
	to = kmap(bprm->page[0]);
	for (j = 1; j < i; j++) {
		memmove(to, to + offset, PAGE_SIZE - offset);
		from = kmap(bprm->page[j]);
		memcpy(to + PAGE_SIZE - offset, from, offset);
		kunmap(bprm->page[j - 1]);
		to = from;
	}
	memmove(to, to + offset, PAGE_SIZE - offset);
	kunmap(bprm->page[j - 1]);

	/* Limit stack size to 1GB */
	stack_base = current->signal->rlim[RLIMIT_STACK].rlim_max;
	if (stack_base > (1 << 30))
		stack_base = 1 << 30;
	stack_base = PAGE_ALIGN(stack_top - stack_base);

	/* Adjust bprm->p to point to the end of the strings. */
	bprm->p = stack_base + PAGE_SIZE * i - offset;

	mm->arg_start = stack_base;
	arg_size = i << PAGE_SHIFT;

	/* zero pages that were copied above */
	while (i < MAX_ARG_PAGES)
		bprm->page[i++] = NULL;
#else
	stack_base = arch_align_stack(stack_top - MAX_ARG_PAGES*PAGE_SIZE);
	stack_base = PAGE_ALIGN(stack_base);
	bprm->p += stack_base;
	mm->arg_start = bprm->p;
	arg_size = stack_top - (PAGE_MASK & (unsigned long) mm->arg_start);
#endif

	arg_size += EXTRA_STACK_VM_PAGES * PAGE_SIZE;

	if (bprm->loader)
		bprm->loader += stack_base;
	bprm->exec += stack_base;

	mpnt = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
	if (!mpnt)
		return -ENOMEM;

	memset(mpnt, 0, sizeof(*mpnt));

	down_write(&mm->mmap_sem);
	{
		mpnt->vm_mm = mm;
#ifdef CONFIG_STACK_GROWSUP
		mpnt->vm_start = stack_base;
		mpnt->vm_end = stack_base + arg_size;
#else
		mpnt->vm_end = stack_top;
		mpnt->vm_start = mpnt->vm_end - arg_size;
#endif
		/* Adjust stack execute permissions; explicitly enable
		 * for EXSTACK_ENABLE_X, disable for EXSTACK_DISABLE_X
		 * and leave alone (arch default) otherwise. */
		if (unlikely(executable_stack == EXSTACK_ENABLE_X))
			mpnt->vm_flags = VM_STACK_FLAGS |  VM_EXEC;
		else if (executable_stack == EXSTACK_DISABLE_X)
			mpnt->vm_flags = VM_STACK_FLAGS & ~VM_EXEC;
		else
			mpnt->vm_flags = VM_STACK_FLAGS;
		mpnt->vm_flags |= mm->def_flags;
		mpnt->vm_page_prot = protection_map[mpnt->vm_flags & 0x7];
		if ((ret = insert_vm_struct(mm, mpnt))) {
			up_write(&mm->mmap_sem);
			kmem_cache_free(vm_area_cachep, mpnt);
			return ret;
		}
		mm->stack_vm = mm->total_vm = vma_pages(mpnt);
	}

	for (i = 0 ; i < MAX_ARG_PAGES ; i++) {
		struct page *page = bprm->page[i];
		if (page) {
			bprm->page[i] = NULL;
			install_arg_page(mpnt, page, stack_base);
		}
		stack_base += PAGE_SIZE;
	}
	up_write(&mm->mmap_sem);
	
	return 0;
}

EXPORT_SYMBOL(setup_arg_pages);

#define free_arg_pages(bprm) do { } while (0)

#else

static inline void free_arg_pages(struct linux_binprm *bprm)
{
	int i;

	for (i = 0; i < MAX_ARG_PAGES; i++) {
		if (bprm->page[i])
			__free_page(bprm->page[i]);
		bprm->page[i] = NULL;
	}
}

#endif /* CONFIG_MMU */

struct file *open_exec(const char *name)
{
	struct nameidata nd;
	int err;
	struct file *file;

490
	err = path_lookup_open(name, LOOKUP_FOLLOW, &nd, FMODE_READ);
L
Linus Torvalds 已提交
491 492 493 494 495 496 497 498 499 500 501 502
	file = ERR_PTR(err);

	if (!err) {
		struct inode *inode = nd.dentry->d_inode;
		file = ERR_PTR(-EACCES);
		if (!(nd.mnt->mnt_flags & MNT_NOEXEC) &&
		    S_ISREG(inode->i_mode)) {
			int err = permission(inode, MAY_EXEC, &nd);
			if (!err && !(inode->i_mode & 0111))
				err = -EACCES;
			file = ERR_PTR(err);
			if (!err) {
503
				file = nameidata_to_filp(&nd, O_RDONLY);
L
Linus Torvalds 已提交
504 505 506 507 508 509 510 511 512 513 514
				if (!IS_ERR(file)) {
					err = deny_write_access(file);
					if (err) {
						fput(file);
						file = ERR_PTR(err);
					}
				}
out:
				return file;
			}
		}
515
		release_open_intent(&nd);
L
Linus Torvalds 已提交
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
		path_release(&nd);
	}
	goto out;
}

EXPORT_SYMBOL(open_exec);

int kernel_read(struct file *file, unsigned long offset,
	char *addr, unsigned long count)
{
	mm_segment_t old_fs;
	loff_t pos = offset;
	int result;

	old_fs = get_fs();
	set_fs(get_ds());
	/* The cast to a user pointer is valid due to the set_fs() */
	result = vfs_read(file, (void __user *)addr, count, &pos);
	set_fs(old_fs);
	return result;
}

EXPORT_SYMBOL(kernel_read);

static int exec_mmap(struct mm_struct *mm)
{
	struct task_struct *tsk;
	struct mm_struct * old_mm, *active_mm;

	/* Notify parent that we're no longer interested in the old VM */
	tsk = current;
	old_mm = current->mm;
	mm_release(tsk, old_mm);

	if (old_mm) {
		/*
		 * Make sure that if there is a core dump in progress
		 * for the old mm, we get out and die instead of going
		 * through with the exec.  We must hold mmap_sem around
		 * checking core_waiters and changing tsk->mm.  The
		 * core-inducing thread will increment core_waiters for
		 * each thread whose ->mm == old_mm.
		 */
		down_read(&old_mm->mmap_sem);
		if (unlikely(old_mm->core_waiters)) {
			up_read(&old_mm->mmap_sem);
			return -EINTR;
		}
	}
	task_lock(tsk);
	active_mm = tsk->active_mm;
	tsk->mm = mm;
	tsk->active_mm = mm;
	activate_mm(active_mm, mm);
	task_unlock(tsk);
	arch_pick_mmap_layout(mm);
	if (old_mm) {
		up_read(&old_mm->mmap_sem);
		if (active_mm != old_mm) BUG();
		mmput(old_mm);
		return 0;
	}
	mmdrop(active_mm);
	return 0;
}

/*
 * This function makes sure the current process has its own signal table,
 * so that flush_signal_handlers can later reset the handlers without
 * disturbing other processes.  (Other processes might share the signal
 * table via the CLONE_SIGHAND option to clone().)
 */
static inline int de_thread(struct task_struct *tsk)
{
	struct signal_struct *sig = tsk->signal;
	struct sighand_struct *newsighand, *oldsighand = tsk->sighand;
	spinlock_t *lock = &oldsighand->siglock;
	int count;

	/*
	 * If we don't share sighandlers, then we aren't sharing anything
	 * and we can just re-use it all.
	 */
	if (atomic_read(&oldsighand->count) <= 1) {
		BUG_ON(atomic_read(&sig->count) != 1);
		exit_itimers(sig);
		return 0;
	}

	newsighand = kmem_cache_alloc(sighand_cachep, GFP_KERNEL);
	if (!newsighand)
		return -ENOMEM;

	if (thread_group_empty(current))
		goto no_thread_group;

	/*
	 * Kill all other threads in the thread group.
	 * We must hold tasklist_lock to call zap_other_threads.
	 */
	read_lock(&tasklist_lock);
	spin_lock_irq(lock);
	if (sig->flags & SIGNAL_GROUP_EXIT) {
		/*
		 * Another group action in progress, just
		 * return so that the signal is processed.
		 */
		spin_unlock_irq(lock);
		read_unlock(&tasklist_lock);
		kmem_cache_free(sighand_cachep, newsighand);
		return -EAGAIN;
	}
	zap_other_threads(current);
	read_unlock(&tasklist_lock);

	/*
	 * Account for the thread group leader hanging around:
	 */
O
Oleg Nesterov 已提交
634 635 636
	count = 1;
	if (!thread_group_leader(current)) {
		count = 2;
637 638 639 640 641 642 643 644
		/*
		 * The SIGALRM timer survives the exec, but needs to point
		 * at us as the new group leader now.  We have a race with
		 * a timer firing now getting the old leader, so we need to
		 * synchronize with any firing (by calling del_timer_sync)
		 * before we can safely let the old group leader die.
		 */
		sig->real_timer.data = (unsigned long)current;
645
		spin_unlock_irq(lock);
646 647
		if (del_timer_sync(&sig->real_timer))
			add_timer(&sig->real_timer);
648
		spin_lock_irq(lock);
649
	}
L
Linus Torvalds 已提交
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
	while (atomic_read(&sig->count) > count) {
		sig->group_exit_task = current;
		sig->notify_count = count;
		__set_current_state(TASK_UNINTERRUPTIBLE);
		spin_unlock_irq(lock);
		schedule();
		spin_lock_irq(lock);
	}
	sig->group_exit_task = NULL;
	sig->notify_count = 0;
	spin_unlock_irq(lock);

	/*
	 * At this point all other threads have exited, all we have to
	 * do is to wait for the thread group leader to become inactive,
	 * and to assume its PID:
	 */
	if (!thread_group_leader(current)) {
		struct task_struct *leader = current->group_leader, *parent;
		struct dentry *proc_dentry1, *proc_dentry2;
		unsigned long exit_state, ptrace;

		/*
		 * Wait for the thread group leader to be a zombie.
		 * It should already be zombie at this point, most
		 * of the time.
		 */
		while (leader->exit_state != EXIT_ZOMBIE)
			yield();

		spin_lock(&leader->proc_lock);
		spin_lock(&current->proc_lock);
		proc_dentry1 = proc_pid_unhash(current);
		proc_dentry2 = proc_pid_unhash(leader);
		write_lock_irq(&tasklist_lock);

L
Linus Torvalds 已提交
686 687
		BUG_ON(leader->tgid != current->tgid);
		BUG_ON(current->pid == current->tgid);
L
Linus Torvalds 已提交
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
		/*
		 * An exec() starts a new thread group with the
		 * TGID of the previous thread group. Rehash the
		 * two threads with a switched PID, and release
		 * the former thread group leader:
		 */
		ptrace = leader->ptrace;
		parent = leader->parent;
		if (unlikely(ptrace) && unlikely(parent == current)) {
			/*
			 * Joker was ptracing his own group leader,
			 * and now he wants to be his own parent!
			 * We can't have that.
			 */
			ptrace = 0;
		}

		ptrace_unlink(current);
		ptrace_unlink(leader);
		remove_parent(current);
		remove_parent(leader);

		switch_exec_pids(leader, current);

		current->parent = current->real_parent = leader->real_parent;
		leader->parent = leader->real_parent = child_reaper;
		current->group_leader = current;
		leader->group_leader = leader;

		add_parent(current, current->parent);
		add_parent(leader, leader->parent);
		if (ptrace) {
			current->ptrace = ptrace;
			__ptrace_link(current, parent);
		}

		list_del(&current->tasks);
		list_add_tail(&current->tasks, &init_task.tasks);
		current->exit_signal = SIGCHLD;
		exit_state = leader->exit_state;

		write_unlock_irq(&tasklist_lock);
		spin_unlock(&leader->proc_lock);
		spin_unlock(&current->proc_lock);
		proc_pid_flush(proc_dentry1);
		proc_pid_flush(proc_dentry2);

L
Linus Torvalds 已提交
735
		BUG_ON(exit_state != EXIT_ZOMBIE);
L
Linus Torvalds 已提交
736 737 738 739
		release_task(leader);
        }

	/*
740 741
	 * There may be one thread left which is just exiting,
	 * but it's safe to stop telling the group to kill themselves.
L
Linus Torvalds 已提交
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
	 */
	sig->flags = 0;

no_thread_group:
	BUG_ON(atomic_read(&sig->count) != 1);
	exit_itimers(sig);

	if (atomic_read(&oldsighand->count) == 1) {
		/*
		 * Now that we nuked the rest of the thread group,
		 * it turns out we are not sharing sighand any more either.
		 * So we can just keep it.
		 */
		kmem_cache_free(sighand_cachep, newsighand);
	} else {
		/*
		 * Move our state over to newsighand and switch it in.
		 */
		spin_lock_init(&newsighand->siglock);
		atomic_set(&newsighand->count, 1);
		memcpy(newsighand->action, oldsighand->action,
		       sizeof(newsighand->action));

		write_lock_irq(&tasklist_lock);
		spin_lock(&oldsighand->siglock);
		spin_lock(&newsighand->siglock);

		current->sighand = newsighand;
		recalc_sigpending();

		spin_unlock(&newsighand->siglock);
		spin_unlock(&oldsighand->siglock);
		write_unlock_irq(&tasklist_lock);

		if (atomic_dec_and_test(&oldsighand->count))
			kmem_cache_free(sighand_cachep, oldsighand);
	}

L
Linus Torvalds 已提交
780
	BUG_ON(!thread_group_leader(current));
L
Linus Torvalds 已提交
781 782 783 784 785 786 787 788 789 790 791
	return 0;
}
	
/*
 * These functions flushes out all traces of the currently running executable
 * so that a new one can be started
 */

static inline void flush_old_files(struct files_struct * files)
{
	long j = -1;
792
	struct fdtable *fdt;
L
Linus Torvalds 已提交
793 794 795 796 797 798 799

	spin_lock(&files->file_lock);
	for (;;) {
		unsigned long set, i;

		j++;
		i = j * __NFDBITS;
800 801
		fdt = files_fdtable(files);
		if (i >= fdt->max_fds || i >= fdt->max_fdset)
L
Linus Torvalds 已提交
802
			break;
803
		set = fdt->close_on_exec->fds_bits[j];
L
Linus Torvalds 已提交
804 805
		if (!set)
			continue;
806
		fdt->close_on_exec->fds_bits[j] = 0;
L
Linus Torvalds 已提交
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
		spin_unlock(&files->file_lock);
		for ( ; set ; i++,set >>= 1) {
			if (set & 1) {
				sys_close(i);
			}
		}
		spin_lock(&files->file_lock);

	}
	spin_unlock(&files->file_lock);
}

void get_task_comm(char *buf, struct task_struct *tsk)
{
	/* buf must be at least sizeof(tsk->comm) in size */
	task_lock(tsk);
	strncpy(buf, tsk->comm, sizeof(tsk->comm));
	task_unlock(tsk);
}

void set_task_comm(struct task_struct *tsk, char *buf)
{
	task_lock(tsk);
	strlcpy(tsk->comm, buf, sizeof(tsk->comm));
	task_unlock(tsk);
}

int flush_old_exec(struct linux_binprm * bprm)
{
	char * name;
	int i, ch, retval;
	struct files_struct *files;
	char tcomm[sizeof(current->comm)];

	/*
	 * Make sure we have a private signal table and that
	 * we are unassociated from the previous thread group.
	 */
	retval = de_thread(current);
	if (retval)
		goto out;

	/*
	 * Make sure we have private file handles. Ask the
	 * fork helper to do the work for us and the exit
	 * helper to do the cleanup of the old one.
	 */
	files = current->files;		/* refcounted so safe to hold */
	retval = unshare_files();
	if (retval)
		goto out;
	/*
	 * Release all of the old mmap stuff
	 */
	retval = exec_mmap(bprm->mm);
	if (retval)
		goto mmap_failed;

	bprm->mm = NULL;		/* We're using it now */

	/* This is the point of no return */
	steal_locks(files);
	put_files_struct(files);

	current->sas_ss_sp = current->sas_ss_size = 0;

	if (current->euid == current->uid && current->egid == current->gid)
		current->mm->dumpable = 1;
A
Alan Cox 已提交
875 876 877
	else
		current->mm->dumpable = suid_dumpable;

L
Linus Torvalds 已提交
878
	name = bprm->filename;
879 880

	/* Copies the binary name from after last slash */
L
Linus Torvalds 已提交
881 882
	for (i=0; (ch = *(name++)) != '\0';) {
		if (ch == '/')
883
			i = 0; /* overwrite what we wrote */
L
Linus Torvalds 已提交
884 885 886 887 888 889 890 891 892 893 894 895 896 897
		else
			if (i < (sizeof(tcomm) - 1))
				tcomm[i++] = ch;
	}
	tcomm[i] = '\0';
	set_task_comm(current, tcomm);

	current->flags &= ~PF_RANDOMIZE;
	flush_thread();

	if (bprm->e_uid != current->euid || bprm->e_gid != current->egid || 
	    permission(bprm->file->f_dentry->d_inode,MAY_READ, NULL) ||
	    (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP)) {
		suid_keys(current);
A
Alan Cox 已提交
898
		current->mm->dumpable = suid_dumpable;
L
Linus Torvalds 已提交
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 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099
	}

	/* An exec changes our domain. We are no longer part of the thread
	   group */

	current->self_exec_id++;
			
	flush_signal_handlers(current, 0);
	flush_old_files(current->files);

	return 0;

mmap_failed:
	put_files_struct(current->files);
	current->files = files;
out:
	return retval;
}

EXPORT_SYMBOL(flush_old_exec);

/* 
 * Fill the binprm structure from the inode. 
 * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes
 */
int prepare_binprm(struct linux_binprm *bprm)
{
	int mode;
	struct inode * inode = bprm->file->f_dentry->d_inode;
	int retval;

	mode = inode->i_mode;
	/*
	 * Check execute perms again - if the caller has CAP_DAC_OVERRIDE,
	 * generic_permission lets a non-executable through
	 */
	if (!(mode & 0111))	/* with at least _one_ execute bit set */
		return -EACCES;
	if (bprm->file->f_op == NULL)
		return -EACCES;

	bprm->e_uid = current->euid;
	bprm->e_gid = current->egid;

	if(!(bprm->file->f_vfsmnt->mnt_flags & MNT_NOSUID)) {
		/* Set-uid? */
		if (mode & S_ISUID) {
			current->personality &= ~PER_CLEAR_ON_SETID;
			bprm->e_uid = inode->i_uid;
		}

		/* Set-gid? */
		/*
		 * If setgid is set but no group execute bit then this
		 * is a candidate for mandatory locking, not a setgid
		 * executable.
		 */
		if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
			current->personality &= ~PER_CLEAR_ON_SETID;
			bprm->e_gid = inode->i_gid;
		}
	}

	/* fill in binprm security blob */
	retval = security_bprm_set(bprm);
	if (retval)
		return retval;

	memset(bprm->buf,0,BINPRM_BUF_SIZE);
	return kernel_read(bprm->file,0,bprm->buf,BINPRM_BUF_SIZE);
}

EXPORT_SYMBOL(prepare_binprm);

static inline int unsafe_exec(struct task_struct *p)
{
	int unsafe = 0;
	if (p->ptrace & PT_PTRACED) {
		if (p->ptrace & PT_PTRACE_CAP)
			unsafe |= LSM_UNSAFE_PTRACE_CAP;
		else
			unsafe |= LSM_UNSAFE_PTRACE;
	}
	if (atomic_read(&p->fs->count) > 1 ||
	    atomic_read(&p->files->count) > 1 ||
	    atomic_read(&p->sighand->count) > 1)
		unsafe |= LSM_UNSAFE_SHARE;

	return unsafe;
}

void compute_creds(struct linux_binprm *bprm)
{
	int unsafe;

	if (bprm->e_uid != current->uid)
		suid_keys(current);
	exec_keys(current);

	task_lock(current);
	unsafe = unsafe_exec(current);
	security_bprm_apply_creds(bprm, unsafe);
	task_unlock(current);
	security_bprm_post_apply_creds(bprm);
}

EXPORT_SYMBOL(compute_creds);

void remove_arg_zero(struct linux_binprm *bprm)
{
	if (bprm->argc) {
		unsigned long offset;
		char * kaddr;
		struct page *page;

		offset = bprm->p % PAGE_SIZE;
		goto inside;

		while (bprm->p++, *(kaddr+offset++)) {
			if (offset != PAGE_SIZE)
				continue;
			offset = 0;
			kunmap_atomic(kaddr, KM_USER0);
inside:
			page = bprm->page[bprm->p/PAGE_SIZE];
			kaddr = kmap_atomic(page, KM_USER0);
		}
		kunmap_atomic(kaddr, KM_USER0);
		bprm->argc--;
	}
}

EXPORT_SYMBOL(remove_arg_zero);

/*
 * cycle the list of binary formats handler, until one recognizes the image
 */
int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
{
	int try,retval;
	struct linux_binfmt *fmt;
#ifdef __alpha__
	/* handle /sbin/loader.. */
	{
	    struct exec * eh = (struct exec *) bprm->buf;

	    if (!bprm->loader && eh->fh.f_magic == 0x183 &&
		(eh->fh.f_flags & 0x3000) == 0x3000)
	    {
		struct file * file;
		unsigned long loader;

		allow_write_access(bprm->file);
		fput(bprm->file);
		bprm->file = NULL;

	        loader = PAGE_SIZE*MAX_ARG_PAGES-sizeof(void *);

		file = open_exec("/sbin/loader");
		retval = PTR_ERR(file);
		if (IS_ERR(file))
			return retval;

		/* Remember if the application is TASO.  */
		bprm->sh_bang = eh->ah.entry < 0x100000000UL;

		bprm->file = file;
		bprm->loader = loader;
		retval = prepare_binprm(bprm);
		if (retval<0)
			return retval;
		/* should call search_binary_handler recursively here,
		   but it does not matter */
	    }
	}
#endif
	retval = security_bprm_check(bprm);
	if (retval)
		return retval;

	/* kernel module loader fixup */
	/* so we don't try to load run modprobe in kernel space. */
	set_fs(USER_DS);
	retval = -ENOENT;
	for (try=0; try<2; try++) {
		read_lock(&binfmt_lock);
		for (fmt = formats ; fmt ; fmt = fmt->next) {
			int (*fn)(struct linux_binprm *, struct pt_regs *) = fmt->load_binary;
			if (!fn)
				continue;
			if (!try_module_get(fmt->module))
				continue;
			read_unlock(&binfmt_lock);
			retval = fn(bprm, regs);
			if (retval >= 0) {
				put_binfmt(fmt);
				allow_write_access(bprm->file);
				if (bprm->file)
					fput(bprm->file);
				bprm->file = NULL;
				current->did_exec = 1;
M
Matt Helsley 已提交
1100
				proc_exec_connector(current);
L
Linus Torvalds 已提交
1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421
				return retval;
			}
			read_lock(&binfmt_lock);
			put_binfmt(fmt);
			if (retval != -ENOEXEC || bprm->mm == NULL)
				break;
			if (!bprm->file) {
				read_unlock(&binfmt_lock);
				return retval;
			}
		}
		read_unlock(&binfmt_lock);
		if (retval != -ENOEXEC || bprm->mm == NULL) {
			break;
#ifdef CONFIG_KMOD
		}else{
#define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e))
			if (printable(bprm->buf[0]) &&
			    printable(bprm->buf[1]) &&
			    printable(bprm->buf[2]) &&
			    printable(bprm->buf[3]))
				break; /* -ENOEXEC */
			request_module("binfmt-%04x", *(unsigned short *)(&bprm->buf[2]));
#endif
		}
	}
	return retval;
}

EXPORT_SYMBOL(search_binary_handler);

/*
 * sys_execve() executes a new program.
 */
int do_execve(char * filename,
	char __user *__user *argv,
	char __user *__user *envp,
	struct pt_regs * regs)
{
	struct linux_binprm *bprm;
	struct file *file;
	int retval;
	int i;

	retval = -ENOMEM;
	bprm = kmalloc(sizeof(*bprm), GFP_KERNEL);
	if (!bprm)
		goto out_ret;
	memset(bprm, 0, sizeof(*bprm));

	file = open_exec(filename);
	retval = PTR_ERR(file);
	if (IS_ERR(file))
		goto out_kfree;

	sched_exec();

	bprm->p = PAGE_SIZE*MAX_ARG_PAGES-sizeof(void *);

	bprm->file = file;
	bprm->filename = filename;
	bprm->interp = filename;
	bprm->mm = mm_alloc();
	retval = -ENOMEM;
	if (!bprm->mm)
		goto out_file;

	retval = init_new_context(current, bprm->mm);
	if (retval < 0)
		goto out_mm;

	bprm->argc = count(argv, bprm->p / sizeof(void *));
	if ((retval = bprm->argc) < 0)
		goto out_mm;

	bprm->envc = count(envp, bprm->p / sizeof(void *));
	if ((retval = bprm->envc) < 0)
		goto out_mm;

	retval = security_bprm_alloc(bprm);
	if (retval)
		goto out;

	retval = prepare_binprm(bprm);
	if (retval < 0)
		goto out;

	retval = copy_strings_kernel(1, &bprm->filename, bprm);
	if (retval < 0)
		goto out;

	bprm->exec = bprm->p;
	retval = copy_strings(bprm->envc, envp, bprm);
	if (retval < 0)
		goto out;

	retval = copy_strings(bprm->argc, argv, bprm);
	if (retval < 0)
		goto out;

	retval = search_binary_handler(bprm,regs);
	if (retval >= 0) {
		free_arg_pages(bprm);

		/* execve success */
		security_bprm_free(bprm);
		acct_update_integrals(current);
		kfree(bprm);
		return retval;
	}

out:
	/* Something went wrong, return the inode and free the argument pages*/
	for (i = 0 ; i < MAX_ARG_PAGES ; i++) {
		struct page * page = bprm->page[i];
		if (page)
			__free_page(page);
	}

	if (bprm->security)
		security_bprm_free(bprm);

out_mm:
	if (bprm->mm)
		mmdrop(bprm->mm);

out_file:
	if (bprm->file) {
		allow_write_access(bprm->file);
		fput(bprm->file);
	}

out_kfree:
	kfree(bprm);

out_ret:
	return retval;
}

int set_binfmt(struct linux_binfmt *new)
{
	struct linux_binfmt *old = current->binfmt;

	if (new) {
		if (!try_module_get(new->module))
			return -1;
	}
	current->binfmt = new;
	if (old)
		module_put(old->module);
	return 0;
}

EXPORT_SYMBOL(set_binfmt);

#define CORENAME_MAX_SIZE 64

/* format_corename will inspect the pattern parameter, and output a
 * name into corename, which must have space for at least
 * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator.
 */
static void format_corename(char *corename, const char *pattern, long signr)
{
	const char *pat_ptr = pattern;
	char *out_ptr = corename;
	char *const out_end = corename + CORENAME_MAX_SIZE;
	int rc;
	int pid_in_pattern = 0;

	/* Repeat as long as we have more pattern to process and more output
	   space */
	while (*pat_ptr) {
		if (*pat_ptr != '%') {
			if (out_ptr == out_end)
				goto out;
			*out_ptr++ = *pat_ptr++;
		} else {
			switch (*++pat_ptr) {
			case 0:
				goto out;
			/* Double percent, output one percent */
			case '%':
				if (out_ptr == out_end)
					goto out;
				*out_ptr++ = '%';
				break;
			/* pid */
			case 'p':
				pid_in_pattern = 1;
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%d", current->tgid);
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			/* uid */
			case 'u':
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%d", current->uid);
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			/* gid */
			case 'g':
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%d", current->gid);
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			/* signal that caused the coredump */
			case 's':
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%ld", signr);
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			/* UNIX time of coredump */
			case 't': {
				struct timeval tv;
				do_gettimeofday(&tv);
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%lu", tv.tv_sec);
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			}
			/* hostname */
			case 'h':
				down_read(&uts_sem);
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%s", system_utsname.nodename);
				up_read(&uts_sem);
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			/* executable */
			case 'e':
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%s", current->comm);
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			default:
				break;
			}
			++pat_ptr;
		}
	}
	/* Backward compatibility with core_uses_pid:
	 *
	 * If core_pattern does not include a %p (as is the default)
	 * and core_uses_pid is set, then .%pid will be appended to
	 * the filename */
	if (!pid_in_pattern
            && (core_uses_pid || atomic_read(&current->mm->mm_users) != 1)) {
		rc = snprintf(out_ptr, out_end - out_ptr,
			      ".%d", current->tgid);
		if (rc > out_end - out_ptr)
			goto out;
		out_ptr += rc;
	}
      out:
	*out_ptr = 0;
}

static void zap_threads (struct mm_struct *mm)
{
	struct task_struct *g, *p;
	struct task_struct *tsk = current;
	struct completion *vfork_done = tsk->vfork_done;
	int traced = 0;

	/*
	 * Make sure nobody is waiting for us to release the VM,
	 * otherwise we can deadlock when we wait on each other
	 */
	if (vfork_done) {
		tsk->vfork_done = NULL;
		complete(vfork_done);
	}

	read_lock(&tasklist_lock);
	do_each_thread(g,p)
		if (mm == p->mm && p != tsk) {
			force_sig_specific(SIGKILL, p);
			mm->core_waiters++;
			if (unlikely(p->ptrace) &&
			    unlikely(p->parent->mm == mm))
				traced = 1;
		}
	while_each_thread(g,p);

	read_unlock(&tasklist_lock);

	if (unlikely(traced)) {
		/*
		 * We are zapping a thread and the thread it ptraces.
		 * If the tracee went into a ptrace stop for exit tracing,
		 * we could deadlock since the tracer is waiting for this
		 * coredump to finish.  Detach them so they can both die.
		 */
		write_lock_irq(&tasklist_lock);
		do_each_thread(g,p) {
			if (mm == p->mm && p != tsk &&
			    p->ptrace && p->parent->mm == mm) {
				__ptrace_unlink(p);
			}
		} while_each_thread(g,p);
		write_unlock_irq(&tasklist_lock);
	}
}

static void coredump_wait(struct mm_struct *mm)
{
	DECLARE_COMPLETION(startup_done);
O
Oleg Nesterov 已提交
1422
	int core_waiters;
L
Linus Torvalds 已提交
1423 1424 1425 1426

	mm->core_startup_done = &startup_done;

	zap_threads(mm);
O
Oleg Nesterov 已提交
1427 1428 1429 1430
	core_waiters = mm->core_waiters;
	up_write(&mm->mmap_sem);

	if (core_waiters)
L
Linus Torvalds 已提交
1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442
		wait_for_completion(&startup_done);
	BUG_ON(mm->core_waiters);
}

int do_coredump(long signr, int exit_code, struct pt_regs * regs)
{
	char corename[CORENAME_MAX_SIZE + 1];
	struct mm_struct *mm = current->mm;
	struct linux_binfmt * binfmt;
	struct inode * inode;
	struct file * file;
	int retval = 0;
A
Alan Cox 已提交
1443 1444
	int fsuid = current->fsuid;
	int flag = 0;
L
Linus Torvalds 已提交
1445 1446 1447 1448 1449 1450 1451 1452 1453

	binfmt = current->binfmt;
	if (!binfmt || !binfmt->core_dump)
		goto fail;
	down_write(&mm->mmap_sem);
	if (!mm->dumpable) {
		up_write(&mm->mmap_sem);
		goto fail;
	}
A
Alan Cox 已提交
1454 1455 1456 1457 1458 1459 1460 1461 1462 1463

	/*
	 *	We cannot trust fsuid as being the "true" uid of the
	 *	process nor do we know its entire history. We only know it
	 *	was tainted so we dump it as root in mode 2.
	 */
	if (mm->dumpable == 2) {	/* Setuid core dump mode */
		flag = O_EXCL;		/* Stop rewrite attacks */
		current->fsuid = 0;	/* Dump root private */
	}
L
Linus Torvalds 已提交
1464
	mm->dumpable = 0;
1465 1466

	retval = -EAGAIN;
L
Linus Torvalds 已提交
1467
	spin_lock_irq(&current->sighand->siglock);
1468 1469 1470 1471 1472
	if (!(current->signal->flags & SIGNAL_GROUP_EXIT)) {
		current->signal->flags = SIGNAL_GROUP_EXIT;
		current->signal->group_exit_code = exit_code;
		retval = 0;
	}
L
Linus Torvalds 已提交
1473
	spin_unlock_irq(&current->sighand->siglock);
1474 1475 1476 1477 1478 1479
	if (retval) {
		up_write(&mm->mmap_sem);
		goto fail;
	}

	init_completion(&mm->core_done);
L
Linus Torvalds 已提交
1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498
	coredump_wait(mm);

	/*
	 * Clear any false indication of pending signals that might
	 * be seen by the filesystem code called to write the core file.
	 */
	current->signal->group_stop_count = 0;
	clear_thread_flag(TIF_SIGPENDING);

	if (current->signal->rlim[RLIMIT_CORE].rlim_cur < binfmt->min_coredump)
		goto fail_unlock;

	/*
	 * lock_kernel() because format_corename() is controlled by sysctl, which
	 * uses lock_kernel()
	 */
 	lock_kernel();
	format_corename(corename, core_pattern, signr);
	unlock_kernel();
A
Alan Cox 已提交
1499
	file = filp_open(corename, O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag, 0600);
L
Linus Torvalds 已提交
1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523
	if (IS_ERR(file))
		goto fail_unlock;
	inode = file->f_dentry->d_inode;
	if (inode->i_nlink > 1)
		goto close_fail;	/* multiple links - don't dump */
	if (d_unhashed(file->f_dentry))
		goto close_fail;

	if (!S_ISREG(inode->i_mode))
		goto close_fail;
	if (!file->f_op)
		goto close_fail;
	if (!file->f_op->write)
		goto close_fail;
	if (do_truncate(file->f_dentry, 0) != 0)
		goto close_fail;

	retval = binfmt->core_dump(signr, regs, file);

	if (retval)
		current->signal->group_exit_code |= 0x80;
close_fail:
	filp_close(file, NULL);
fail_unlock:
A
Alan Cox 已提交
1524
	current->fsuid = fsuid;
L
Linus Torvalds 已提交
1525 1526 1527 1528
	complete_all(&mm->core_done);
fail:
	return retval;
}