exec.c 40.9 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
/*
 *  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/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>
32
#include <linux/string.h>
L
Linus Torvalds 已提交
33 34 35 36 37 38 39 40 41
#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>
42
#include <linux/pid_namespace.h>
L
Linus Torvalds 已提交
43 44 45 46 47 48 49 50
#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>
51
#include <linux/tsacct_kern.h>
M
Matt Helsley 已提交
52
#include <linux/cn_proc.h>
A
Al Viro 已提交
53
#include <linux/audit.h>
L
Linus Torvalds 已提交
54 55 56

#include <asm/uaccess.h>
#include <asm/mmu_context.h>
57
#include <asm/tlb.h>
L
Linus Torvalds 已提交
58 59 60 61 62 63

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

int core_uses_pid;
64
char core_pattern[CORENAME_MAX_SIZE] = "core";
A
Alan Cox 已提交
65 66
int suid_dumpable = 0;

L
Linus Torvalds 已提交
67 68
/* The maximal length of core_pattern is also specified in sysctl.c */

A
Alexey Dobriyan 已提交
69
static LIST_HEAD(formats);
L
Linus Torvalds 已提交
70 71 72 73 74 75 76
static DEFINE_RWLOCK(binfmt_lock);

int register_binfmt(struct linux_binfmt * fmt)
{
	if (!fmt)
		return -EINVAL;
	write_lock(&binfmt_lock);
A
Alexey Dobriyan 已提交
77
	list_add(&fmt->lh, &formats);
L
Linus Torvalds 已提交
78 79 80 81 82 83
	write_unlock(&binfmt_lock);
	return 0;	
}

EXPORT_SYMBOL(register_binfmt);

84
void unregister_binfmt(struct linux_binfmt * fmt)
L
Linus Torvalds 已提交
85 86
{
	write_lock(&binfmt_lock);
A
Alexey Dobriyan 已提交
87
	list_del(&fmt->lh);
L
Linus Torvalds 已提交
88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109
	write_unlock(&binfmt_lock);
}

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;

110
	error = __user_path_lookup_open(library, LOOKUP_FOLLOW, &nd, FMODE_READ|FMODE_EXEC);
L
Linus Torvalds 已提交
111 112 113 114 115 116 117
	if (error)
		goto out;

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

118
	error = vfs_permission(&nd, MAY_READ | MAY_EXEC);
L
Linus Torvalds 已提交
119 120 121
	if (error)
		goto exit;

122
	file = nameidata_to_filp(&nd, O_RDONLY);
L
Linus Torvalds 已提交
123 124 125 126 127 128 129 130 131
	error = PTR_ERR(file);
	if (IS_ERR(file))
		goto out;

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

		read_lock(&binfmt_lock);
A
Alexey Dobriyan 已提交
132
		list_for_each_entry(fmt, &formats, lh) {
L
Linus Torvalds 已提交
133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149
			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:
150
	release_open_intent(&nd);
L
Linus Torvalds 已提交
151 152 153 154
	path_release(&nd);
	goto out;
}

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
#ifdef CONFIG_MMU

static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
		int write)
{
	struct page *page;
	int ret;

#ifdef CONFIG_STACK_GROWSUP
	if (write) {
		ret = expand_stack_downwards(bprm->vma, pos);
		if (ret < 0)
			return NULL;
	}
#endif
	ret = get_user_pages(current, bprm->mm, pos,
			1, write, 1, &page, NULL);
	if (ret <= 0)
		return NULL;

	if (write) {
		struct rlimit *rlim = current->signal->rlim;
		unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start;

		/*
		 * Limit to 1/4-th the stack size for the argv+env strings.
		 * This ensures that:
		 *  - the remaining binfmt code will not run out of stack space,
		 *  - the program will have a reasonable amount of stack left
		 *    to work from.
		 */
		if (size > rlim[RLIMIT_STACK].rlim_cur / 4) {
			put_page(page);
			return NULL;
		}
	}

	return page;
}

static void put_arg_page(struct page *page)
{
	put_page(page);
}

static void free_arg_page(struct linux_binprm *bprm, int i)
{
}

static void free_arg_pages(struct linux_binprm *bprm)
{
}

static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos,
		struct page *page)
{
	flush_cache_page(bprm->vma, pos, page_to_pfn(page));
}

static int __bprm_mm_init(struct linux_binprm *bprm)
{
	int err = -ENOMEM;
	struct vm_area_struct *vma = NULL;
	struct mm_struct *mm = bprm->mm;

	bprm->vma = vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
	if (!vma)
		goto err;

	down_write(&mm->mmap_sem);
	vma->vm_mm = mm;

	/*
	 * Place the stack at the largest stack address the architecture
	 * supports. Later, we'll move this to an appropriate place. We don't
	 * use STACK_TOP because that can depend on attributes which aren't
	 * configured yet.
	 */
	vma->vm_end = STACK_TOP_MAX;
	vma->vm_start = vma->vm_end - PAGE_SIZE;

	vma->vm_flags = VM_STACK_FLAGS;
237
	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
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
	err = insert_vm_struct(mm, vma);
	if (err) {
		up_write(&mm->mmap_sem);
		goto err;
	}

	mm->stack_vm = mm->total_vm = 1;
	up_write(&mm->mmap_sem);

	bprm->p = vma->vm_end - sizeof(void *);

	return 0;

err:
	if (vma) {
		bprm->vma = NULL;
		kmem_cache_free(vm_area_cachep, vma);
	}

	return err;
}

static bool valid_arg_len(struct linux_binprm *bprm, long len)
{
	return len <= MAX_ARG_STRLEN;
}

#else

static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
		int write)
{
	struct page *page;

	page = bprm->page[pos / PAGE_SIZE];
	if (!page && write) {
		page = alloc_page(GFP_HIGHUSER|__GFP_ZERO);
		if (!page)
			return NULL;
		bprm->page[pos / PAGE_SIZE] = page;
	}

	return page;
}

static void put_arg_page(struct page *page)
{
}

static void free_arg_page(struct linux_binprm *bprm, int i)
{
	if (bprm->page[i]) {
		__free_page(bprm->page[i]);
		bprm->page[i] = NULL;
	}
}

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

	for (i = 0; i < MAX_ARG_PAGES; i++)
		free_arg_page(bprm, i);
}

static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos,
		struct page *page)
{
}

static int __bprm_mm_init(struct linux_binprm *bprm)
{
	bprm->p = PAGE_SIZE * MAX_ARG_PAGES - sizeof(void *);
	return 0;
}

static bool valid_arg_len(struct linux_binprm *bprm, long len)
{
	return len <= bprm->p;
}

#endif /* CONFIG_MMU */

/*
 * Create a new mm_struct and populate it with a temporary stack
 * vm_area_struct.  We don't have enough context at this point to set the stack
 * flags, permissions, and offset, so we use temporary values.  We'll update
 * them later in setup_arg_pages().
 */
int bprm_mm_init(struct linux_binprm *bprm)
{
	int err;
	struct mm_struct *mm = NULL;

	bprm->mm = mm = mm_alloc();
	err = -ENOMEM;
	if (!mm)
		goto err;

	err = init_new_context(current, mm);
	if (err)
		goto err;

	err = __bprm_mm_init(bprm);
	if (err)
		goto err;

	return 0;

err:
	if (mm) {
		bprm->mm = NULL;
		mmdrop(mm);
	}

	return err;
}

L
Linus Torvalds 已提交
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
/*
 * 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;
}

/*
381 382 383
 * 'copy_strings()' copies argument/environment strings from the old
 * processes's memory to the new process's stack.  The call to get_user_pages()
 * ensures the destination page is created and not swapped out.
L
Linus Torvalds 已提交
384
 */
A
Adrian Bunk 已提交
385 386
static int copy_strings(int argc, char __user * __user * argv,
			struct linux_binprm *bprm)
L
Linus Torvalds 已提交
387 388 389
{
	struct page *kmapped_page = NULL;
	char *kaddr = NULL;
390
	unsigned long kpos = 0;
L
Linus Torvalds 已提交
391 392 393 394 395 396 397 398
	int ret;

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

		if (get_user(str, argv+argc) ||
399
				!(len = strnlen_user(str, MAX_ARG_STRLEN))) {
L
Linus Torvalds 已提交
400 401 402 403
			ret = -EFAULT;
			goto out;
		}

404
		if (!valid_arg_len(bprm, len)) {
L
Linus Torvalds 已提交
405 406 407 408
			ret = -E2BIG;
			goto out;
		}

409
		/* We're going to work our way backwords. */
L
Linus Torvalds 已提交
410
		pos = bprm->p;
411 412
		str += len;
		bprm->p -= len;
L
Linus Torvalds 已提交
413 414 415 416 417

		while (len > 0) {
			int offset, bytes_to_copy;

			offset = pos % PAGE_SIZE;
418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433
			if (offset == 0)
				offset = PAGE_SIZE;

			bytes_to_copy = offset;
			if (bytes_to_copy > len)
				bytes_to_copy = len;

			offset -= bytes_to_copy;
			pos -= bytes_to_copy;
			str -= bytes_to_copy;
			len -= bytes_to_copy;

			if (!kmapped_page || kpos != (pos & PAGE_MASK)) {
				struct page *page;

				page = get_arg_page(bprm, pos, 1);
L
Linus Torvalds 已提交
434
				if (!page) {
435
					ret = -E2BIG;
L
Linus Torvalds 已提交
436 437 438
					goto out;
				}

439 440
				if (kmapped_page) {
					flush_kernel_dcache_page(kmapped_page);
L
Linus Torvalds 已提交
441
					kunmap(kmapped_page);
442 443
					put_arg_page(kmapped_page);
				}
L
Linus Torvalds 已提交
444 445
				kmapped_page = page;
				kaddr = kmap(kmapped_page);
446 447
				kpos = pos & PAGE_MASK;
				flush_arg_page(bprm, kpos, kmapped_page);
L
Linus Torvalds 已提交
448
			}
449
			if (copy_from_user(kaddr+offset, str, bytes_to_copy)) {
L
Linus Torvalds 已提交
450 451 452 453 454 455 456
				ret = -EFAULT;
				goto out;
			}
		}
	}
	ret = 0;
out:
457 458
	if (kmapped_page) {
		flush_kernel_dcache_page(kmapped_page);
L
Linus Torvalds 已提交
459
		kunmap(kmapped_page);
460 461
		put_arg_page(kmapped_page);
	}
L
Linus Torvalds 已提交
462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479
	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
480

L
Linus Torvalds 已提交
481
/*
482 483 484
 * During bprm_mm_init(), we create a temporary stack at STACK_TOP_MAX.  Once
 * the binfmt code determines where the new stack should reside, we shift it to
 * its final location.  The process proceeds as follows:
L
Linus Torvalds 已提交
485
 *
486 487 488 489 490 491
 * 1) Use shift to calculate the new vma endpoints.
 * 2) Extend vma to cover both the old and new ranges.  This ensures the
 *    arguments passed to subsequent functions are consistent.
 * 3) Move vma's page tables to the new range.
 * 4) Free up any cleared pgd range.
 * 5) Shrink the vma to cover only the new range.
L
Linus Torvalds 已提交
492
 */
493
static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
L
Linus Torvalds 已提交
494 495
{
	struct mm_struct *mm = vma->vm_mm;
496 497 498 499 500 501
	unsigned long old_start = vma->vm_start;
	unsigned long old_end = vma->vm_end;
	unsigned long length = old_end - old_start;
	unsigned long new_start = old_start - shift;
	unsigned long new_end = old_end - shift;
	struct mmu_gather *tlb;
L
Linus Torvalds 已提交
502

503
	BUG_ON(new_start > new_end);
L
Linus Torvalds 已提交
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
	/*
	 * ensure there are no vmas between where we want to go
	 * and where we are
	 */
	if (vma != find_vma(mm, new_start))
		return -EFAULT;

	/*
	 * cover the whole range: [new_start, old_end)
	 */
	vma_adjust(vma, new_start, old_end, vma->vm_pgoff, NULL);

	/*
	 * move the page tables downwards, on failure we rely on
	 * process cleanup to remove whatever mess we made.
	 */
	if (length != move_page_tables(vma, old_start,
				       vma, new_start, length))
		return -ENOMEM;

	lru_add_drain();
	tlb = tlb_gather_mmu(mm, 0);
	if (new_end > old_start) {
		/*
		 * when the old and new regions overlap clear from new_end.
		 */
		free_pgd_range(&tlb, new_end, old_end, new_end,
			vma->vm_next ? vma->vm_next->vm_start : 0);
	} else {
		/*
		 * otherwise, clean from old_start; this is done to not touch
		 * the address space in [new_end, old_start) some architectures
		 * have constraints on va-space that make this illegal (IA64) -
		 * for the others its just a little faster.
		 */
		free_pgd_range(&tlb, old_start, old_end, new_end,
			vma->vm_next ? vma->vm_next->vm_start : 0);
L
Linus Torvalds 已提交
542
	}
543 544 545 546 547 548 549 550
	tlb_finish_mmu(tlb, new_end, old_end);

	/*
	 * shrink the vma to just the new range.
	 */
	vma_adjust(vma, new_start, new_end, vma->vm_pgoff, NULL);

	return 0;
L
Linus Torvalds 已提交
551 552 553 554
}

#define EXTRA_STACK_VM_PAGES	20	/* random */

555 556 557 558
/*
 * Finalizes the stack vm_area_struct. The flags and permissions are updated,
 * the stack is optionally relocated, and some extra space is added.
 */
L
Linus Torvalds 已提交
559 560 561 562
int setup_arg_pages(struct linux_binprm *bprm,
		    unsigned long stack_top,
		    int executable_stack)
{
563 564
	unsigned long ret;
	unsigned long stack_shift;
L
Linus Torvalds 已提交
565
	struct mm_struct *mm = current->mm;
566 567 568 569
	struct vm_area_struct *vma = bprm->vma;
	struct vm_area_struct *prev = NULL;
	unsigned long vm_flags;
	unsigned long stack_base;
L
Linus Torvalds 已提交
570 571 572 573 574 575 576

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

577 578 579
	/* Make sure we didn't let the argument array grow too large. */
	if (vma->vm_end - vma->vm_start > stack_base)
		return -ENOMEM;
L
Linus Torvalds 已提交
580

581
	stack_base = PAGE_ALIGN(stack_top - stack_base);
L
Linus Torvalds 已提交
582

583 584 585
	stack_shift = vma->vm_start - stack_base;
	mm->arg_start = bprm->p - stack_shift;
	bprm->p = vma->vm_end - stack_shift;
L
Linus Torvalds 已提交
586
#else
587 588 589 590 591
	stack_top = arch_align_stack(stack_top);
	stack_top = PAGE_ALIGN(stack_top);
	stack_shift = vma->vm_end - stack_top;

	bprm->p -= stack_shift;
L
Linus Torvalds 已提交
592 593 594 595
	mm->arg_start = bprm->p;
#endif

	if (bprm->loader)
596 597
		bprm->loader -= stack_shift;
	bprm->exec -= stack_shift;
L
Linus Torvalds 已提交
598 599

	down_write(&mm->mmap_sem);
600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622
	vm_flags = vma->vm_flags;

	/*
	 * 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))
		vm_flags |= VM_EXEC;
	else if (executable_stack == EXSTACK_DISABLE_X)
		vm_flags &= ~VM_EXEC;
	vm_flags |= mm->def_flags;

	ret = mprotect_fixup(vma, &prev, vma->vm_start, vma->vm_end,
			vm_flags);
	if (ret)
		goto out_unlock;
	BUG_ON(prev != vma);

	/* Move stack pages down in memory. */
	if (stack_shift) {
		ret = shift_arg_pages(vma, stack_shift);
		if (ret) {
L
Linus Torvalds 已提交
623 624 625 626 627
			up_write(&mm->mmap_sem);
			return ret;
		}
	}

628 629 630 631 632 633 634 635 636 637
#ifdef CONFIG_STACK_GROWSUP
	stack_base = vma->vm_end + EXTRA_STACK_VM_PAGES * PAGE_SIZE;
#else
	stack_base = vma->vm_start - EXTRA_STACK_VM_PAGES * PAGE_SIZE;
#endif
	ret = expand_stack(vma, stack_base);
	if (ret)
		ret = -EFAULT;

out_unlock:
L
Linus Torvalds 已提交
638 639 640 641 642 643 644 645 646 647 648 649 650
	up_write(&mm->mmap_sem);
	return 0;
}
EXPORT_SYMBOL(setup_arg_pages);

#endif /* CONFIG_MMU */

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

651
	err = path_lookup_open(AT_FDCWD, name, LOOKUP_FOLLOW, &nd, FMODE_READ|FMODE_EXEC);
L
Linus Torvalds 已提交
652 653 654 655 656
	file = ERR_PTR(err);

	if (!err) {
		struct inode *inode = nd.dentry->d_inode;
		file = ERR_PTR(-EACCES);
657
		if (S_ISREG(inode->i_mode)) {
658
			int err = vfs_permission(&nd, MAY_EXEC);
L
Linus Torvalds 已提交
659 660
			file = ERR_PTR(err);
			if (!err) {
661
				file = nameidata_to_filp(&nd, O_RDONLY);
L
Linus Torvalds 已提交
662 663 664 665 666 667 668 669 670 671 672
				if (!IS_ERR(file)) {
					err = deny_write_access(file);
					if (err) {
						fput(file);
						file = ERR_PTR(err);
					}
				}
out:
				return file;
			}
		}
673
		release_open_intent(&nd);
L
Linus Torvalds 已提交
674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731
		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);
732
		BUG_ON(active_mm != old_mm);
L
Linus Torvalds 已提交
733 734 735 736 737 738 739 740 741 742 743 744 745
		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().)
 */
746
static int de_thread(struct task_struct *tsk)
L
Linus Torvalds 已提交
747 748
{
	struct signal_struct *sig = tsk->signal;
749
	struct sighand_struct *oldsighand = tsk->sighand;
L
Linus Torvalds 已提交
750
	spinlock_t *lock = &oldsighand->siglock;
751
	struct task_struct *leader = NULL;
L
Linus Torvalds 已提交
752 753
	int count;

754
	if (thread_group_empty(tsk))
L
Linus Torvalds 已提交
755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771
		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);
		return -EAGAIN;
	}
772 773 774 775 776 777

	/*
	 * child_reaper ignores SIGKILL, change it now.
	 * Reparenting needs write_lock on tasklist_lock,
	 * so it is safe to do it under read_lock.
	 */
778 779
	if (unlikely(tsk->group_leader == child_reaper(tsk)))
		tsk->nsproxy->pid_ns->child_reaper = tsk;
780

781
	zap_other_threads(tsk);
L
Linus Torvalds 已提交
782 783 784 785 786
	read_unlock(&tasklist_lock);

	/*
	 * Account for the thread group leader hanging around:
	 */
O
Oleg Nesterov 已提交
787
	count = 1;
788
	if (!thread_group_leader(tsk)) {
O
Oleg Nesterov 已提交
789
		count = 2;
790 791 792 793 794 795 796
		/*
		 * 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.
		 */
797
		sig->tsk = tsk;
798
		spin_unlock_irq(lock);
799 800
		if (hrtimer_cancel(&sig->real_timer))
			hrtimer_restart(&sig->real_timer);
801
		spin_lock_irq(lock);
802
	}
803 804 805

	sig->notify_count = count;
	sig->group_exit_task = tsk;
L
Linus Torvalds 已提交
806 807 808 809 810 811 812 813 814 815 816 817 818
	while (atomic_read(&sig->count) > count) {
		__set_current_state(TASK_UNINTERRUPTIBLE);
		spin_unlock_irq(lock);
		schedule();
		spin_lock_irq(lock);
	}
	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:
	 */
819 820
	if (!thread_group_leader(tsk)) {
		leader = tsk->group_leader;
821 822 823 824 825 826 827 828 829 830

		sig->notify_count = -1;
		for (;;) {
			write_lock_irq(&tasklist_lock);
			if (likely(leader->exit_state))
				break;
			__set_current_state(TASK_UNINTERRUPTIBLE);
			write_unlock_irq(&tasklist_lock);
			schedule();
		}
L
Linus Torvalds 已提交
831

832 833 834 835 836 837 838 839 840 841
		/*
		 * The only record we have of the real-time age of a
		 * process, regardless of execs it's done, is start_time.
		 * All the past CPU time is accumulated in signal_struct
		 * from sister threads now dead.  But in this non-leader
		 * exec, nothing survives from the original leader thread,
		 * whose birth marks the true age of this process now.
		 * When we take on its identity by switching to its PID, we
		 * also take its birthdate (always earlier than our own).
		 */
842
		tsk->start_time = leader->start_time;
843

844 845
		BUG_ON(leader->tgid != tsk->tgid);
		BUG_ON(tsk->pid == tsk->tgid);
L
Linus Torvalds 已提交
846 847 848 849 850 851
		/*
		 * 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:
		 */
852 853

		/* Become a process group leader with the old leader's pid.
854 855
		 * The old leader becomes a thread of the this thread group.
		 * Note: The old leader also uses this pid until release_task
856 857
		 *       is called.  Odd but simple and correct.
		 */
858 859
		detach_pid(tsk, PIDTYPE_PID);
		tsk->pid = leader->pid;
860
		attach_pid(tsk, PIDTYPE_PID,  find_pid(tsk->pid));
861 862 863
		transfer_pid(leader, tsk, PIDTYPE_PGID);
		transfer_pid(leader, tsk, PIDTYPE_SID);
		list_replace_rcu(&leader->tasks, &tsk->tasks);
L
Linus Torvalds 已提交
864

865 866
		tsk->group_leader = tsk;
		leader->group_leader = tsk;
867

868
		tsk->exit_signal = SIGCHLD;
869 870 871

		BUG_ON(leader->exit_state != EXIT_ZOMBIE);
		leader->exit_state = EXIT_DEAD;
L
Linus Torvalds 已提交
872 873 874 875

		write_unlock_irq(&tasklist_lock);
        }

876 877
	sig->group_exit_task = NULL;
	sig->notify_count = 0;
L
Linus Torvalds 已提交
878
	/*
879 880
	 * 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
881 882 883 884 885
	 */
	sig->flags = 0;

no_thread_group:
	exit_itimers(sig);
886 887 888
	if (leader)
		release_task(leader);

889 890
	if (atomic_read(&oldsighand->count) != 1) {
		struct sighand_struct *newsighand;
L
Linus Torvalds 已提交
891
		/*
892 893
		 * This ->sighand is shared with the CLONE_SIGHAND
		 * but not CLONE_THREAD task, switch to the new one.
L
Linus Torvalds 已提交
894
		 */
895 896 897 898
		newsighand = kmem_cache_alloc(sighand_cachep, GFP_KERNEL);
		if (!newsighand)
			return -ENOMEM;

L
Linus Torvalds 已提交
899 900 901 902 903 904
		atomic_set(&newsighand->count, 1);
		memcpy(newsighand->action, oldsighand->action,
		       sizeof(newsighand->action));

		write_lock_irq(&tasklist_lock);
		spin_lock(&oldsighand->siglock);
905
		rcu_assign_pointer(tsk->sighand, newsighand);
L
Linus Torvalds 已提交
906 907 908
		spin_unlock(&oldsighand->siglock);
		write_unlock_irq(&tasklist_lock);

909
		__cleanup_sighand(oldsighand);
L
Linus Torvalds 已提交
910 911
	}

912
	BUG_ON(!thread_group_leader(tsk));
L
Linus Torvalds 已提交
913 914
	return 0;
}
O
Oleg Nesterov 已提交
915

L
Linus Torvalds 已提交
916 917 918 919
/*
 * These functions flushes out all traces of the currently running executable
 * so that a new one can be started
 */
920
static void flush_old_files(struct files_struct * files)
L
Linus Torvalds 已提交
921 922
{
	long j = -1;
923
	struct fdtable *fdt;
L
Linus Torvalds 已提交
924 925 926 927 928 929 930

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

		j++;
		i = j * __NFDBITS;
931
		fdt = files_fdtable(files);
932
		if (i >= fdt->max_fds)
L
Linus Torvalds 已提交
933
			break;
934
		set = fdt->close_on_exec->fds_bits[j];
L
Linus Torvalds 已提交
935 936
		if (!set)
			continue;
937
		fdt->close_on_exec->fds_bits[j] = 0;
L
Linus Torvalds 已提交
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
		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 */
	put_files_struct(files);

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

	if (current->euid == current->uid && current->egid == current->gid)
1004
		set_dumpable(current->mm, 1);
A
Alan Cox 已提交
1005
	else
1006
		set_dumpable(current->mm, suid_dumpable);
A
Alan Cox 已提交
1007

L
Linus Torvalds 已提交
1008
	name = bprm->filename;
1009 1010

	/* Copies the binary name from after last slash */
L
Linus Torvalds 已提交
1011 1012
	for (i=0; (ch = *(name++)) != '\0';) {
		if (ch == '/')
1013
			i = 0; /* overwrite what we wrote */
L
Linus Torvalds 已提交
1014 1015 1016 1017 1018 1019 1020 1021 1022 1023
		else
			if (i < (sizeof(tcomm) - 1))
				tcomm[i++] = ch;
	}
	tcomm[i] = '\0';
	set_task_comm(current, tcomm);

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

1024 1025 1026 1027 1028 1029
	/* Set the new mm task size. We have to do that late because it may
	 * depend on TIF_32BIT which is only updated in flush_thread() on
	 * some architectures like powerpc
	 */
	current->mm->task_size = TASK_SIZE;

1030 1031 1032 1033 1034 1035
	if (bprm->e_uid != current->euid || bprm->e_gid != current->egid) {
		suid_keys(current);
		set_dumpable(current->mm, suid_dumpable);
		current->pdeath_signal = 0;
	} else if (file_permission(bprm->file, MAY_READ) ||
			(bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP)) {
L
Linus Torvalds 已提交
1036
		suid_keys(current);
1037
		set_dumpable(current->mm, suid_dumpable);
L
Linus Torvalds 已提交
1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050
	}

	/* 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:
1051
	reset_files_struct(current, files);
L
Linus Torvalds 已提交
1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064
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;
1065
	struct inode * inode = bprm->file->f_path.dentry->d_inode;
L
Linus Torvalds 已提交
1066 1067 1068 1069 1070 1071 1072 1073 1074
	int retval;

	mode = inode->i_mode;
	if (bprm->file->f_op == NULL)
		return -EACCES;

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

1075
	if(!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)) {
L
Linus Torvalds 已提交
1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104
		/* 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);

1105
static int unsafe_exec(struct task_struct *p)
L
Linus Torvalds 已提交
1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125
{
	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;

1126
	if (bprm->e_uid != current->uid) {
L
Linus Torvalds 已提交
1127
		suid_keys(current);
1128 1129
		current->pdeath_signal = 0;
	}
L
Linus Torvalds 已提交
1130 1131 1132 1133 1134 1135 1136 1137 1138 1139
	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);

N
Nick Piggin 已提交
1140 1141 1142 1143 1144
/*
 * Arguments are '\0' separated strings found at the location bprm->p
 * points to; chop off the first by relocating brpm->p to right after
 * the first '\0' encountered.
 */
1145
int remove_arg_zero(struct linux_binprm *bprm)
L
Linus Torvalds 已提交
1146
{
1147 1148 1149 1150
	int ret = 0;
	unsigned long offset;
	char *kaddr;
	struct page *page;
N
Nick Piggin 已提交
1151

1152 1153
	if (!bprm->argc)
		return 0;
L
Linus Torvalds 已提交
1154

1155 1156 1157 1158 1159 1160 1161 1162
	do {
		offset = bprm->p & ~PAGE_MASK;
		page = get_arg_page(bprm, bprm->p, 0);
		if (!page) {
			ret = -EFAULT;
			goto out;
		}
		kaddr = kmap_atomic(page, KM_USER0);
N
Nick Piggin 已提交
1163

1164 1165 1166
		for (; offset < PAGE_SIZE && kaddr[offset];
				offset++, bprm->p++)
			;
N
Nick Piggin 已提交
1167

1168 1169
		kunmap_atomic(kaddr, KM_USER0);
		put_arg_page(page);
N
Nick Piggin 已提交
1170

1171 1172 1173
		if (offset == PAGE_SIZE)
			free_arg_page(bprm, (bprm->p >> PAGE_SHIFT) - 1);
	} while (offset == PAGE_SIZE);
N
Nick Piggin 已提交
1174

1175 1176 1177
	bprm->p++;
	bprm->argc--;
	ret = 0;
N
Nick Piggin 已提交
1178

1179 1180
out:
	return ret;
L
Linus Torvalds 已提交
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
}
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;

1206
		loader = bprm->vma->vm_end - sizeof(void *);
L
Linus Torvalds 已提交
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

		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);
A
Al Viro 已提交
1233 1234 1235 1236 1237

	retval = audit_bprm(bprm);
	if (retval)
		return retval;

L
Linus Torvalds 已提交
1238 1239 1240
	retval = -ENOENT;
	for (try=0; try<2; try++) {
		read_lock(&binfmt_lock);
A
Alexey Dobriyan 已提交
1241
		list_for_each_entry(fmt, &formats, lh) {
L
Linus Torvalds 已提交
1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255
			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
1256
				proc_exec_connector(current);
L
Linus Torvalds 已提交
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
				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;
P
Peter Zijlstra 已提交
1298
	unsigned long env_p;
L
Linus Torvalds 已提交
1299 1300 1301
	int retval;

	retval = -ENOMEM;
1302
	bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
L
Linus Torvalds 已提交
1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316
	if (!bprm)
		goto out_ret;

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

	sched_exec();

	bprm->file = file;
	bprm->filename = filename;
	bprm->interp = filename;

1317 1318 1319
	retval = bprm_mm_init(bprm);
	if (retval)
		goto out_file;
L
Linus Torvalds 已提交
1320

1321
	bprm->argc = count(argv, MAX_ARG_STRINGS);
L
Linus Torvalds 已提交
1322 1323 1324
	if ((retval = bprm->argc) < 0)
		goto out_mm;

1325
	bprm->envc = count(envp, MAX_ARG_STRINGS);
L
Linus Torvalds 已提交
1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345
	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;

P
Peter Zijlstra 已提交
1346
	env_p = bprm->p;
L
Linus Torvalds 已提交
1347 1348 1349
	retval = copy_strings(bprm->argc, argv, bprm);
	if (retval < 0)
		goto out;
P
Peter Zijlstra 已提交
1350
	bprm->argv_len = env_p - bprm->p;
L
Linus Torvalds 已提交
1351 1352 1353 1354

	retval = search_binary_handler(bprm,regs);
	if (retval >= 0) {
		/* execve success */
1355
		free_arg_pages(bprm);
L
Linus Torvalds 已提交
1356 1357 1358 1359 1360 1361 1362
		security_bprm_free(bprm);
		acct_update_integrals(current);
		kfree(bprm);
		return retval;
	}

out:
1363
	free_arg_pages(bprm);
L
Linus Torvalds 已提交
1364 1365 1366 1367 1368
	if (bprm->security)
		security_bprm_free(bprm);

out_mm:
	if (bprm->mm)
1369
		mmput (bprm->mm);
L
Linus Torvalds 已提交
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

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);

/* 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.
 */
1403
static int format_corename(char *corename, const char *pattern, long signr)
L
Linus Torvalds 已提交
1404 1405 1406 1407 1408 1409
{
	const char *pat_ptr = pattern;
	char *out_ptr = corename;
	char *const out_end = corename + CORENAME_MAX_SIZE;
	int rc;
	int pid_in_pattern = 0;
1410 1411 1412 1413
	int ispipe = 0;

	if (*pattern == '|')
		ispipe = 1;
L
Linus Torvalds 已提交
1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479

	/* 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,
1480
					      "%s", utsname()->nodename);
L
Linus Torvalds 已提交
1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493
				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;
1494 1495 1496 1497 1498 1499 1500 1501
			/* core limit size */
			case 'c':
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%lu", current->signal->rlim[RLIMIT_CORE].rlim_cur);
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
L
Linus Torvalds 已提交
1502 1503 1504 1505 1506 1507 1508 1509 1510 1511
			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
1512 1513
	 * the filename. Do not do this for piped commands. */
	if (!ispipe && !pid_in_pattern
L
Linus Torvalds 已提交
1514 1515 1516 1517 1518 1519 1520
            && (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;
	}
1521
out:
L
Linus Torvalds 已提交
1522
	*out_ptr = 0;
1523
	return ispipe;
L
Linus Torvalds 已提交
1524 1525
}

1526
static void zap_process(struct task_struct *start)
1527 1528
{
	struct task_struct *t;
1529

1530 1531
	start->signal->flags = SIGNAL_GROUP_EXIT;
	start->signal->group_stop_count = 0;
1532 1533 1534 1535 1536

	t = start;
	do {
		if (t != current && t->mm) {
			t->mm->core_waiters++;
1537 1538
			sigaddset(&t->pending.signal, SIGKILL);
			signal_wake_up(t, 1);
1539 1540 1541 1542
		}
	} while ((t = next_thread(t)) != start);
}

1543 1544
static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
				int exit_code)
L
Linus Torvalds 已提交
1545 1546
{
	struct task_struct *g, *p;
1547
	unsigned long flags;
1548 1549 1550 1551 1552
	int err = -EAGAIN;

	spin_lock_irq(&tsk->sighand->siglock);
	if (!(tsk->signal->flags & SIGNAL_GROUP_EXIT)) {
		tsk->signal->group_exit_code = exit_code;
1553
		zap_process(tsk);
1554
		err = 0;
L
Linus Torvalds 已提交
1555
	}
1556 1557 1558
	spin_unlock_irq(&tsk->sighand->siglock);
	if (err)
		return err;
L
Linus Torvalds 已提交
1559

1560 1561 1562
	if (atomic_read(&mm->mm_users) == mm->core_waiters + 1)
		goto done;

1563
	rcu_read_lock();
1564
	for_each_process(g) {
1565 1566 1567
		if (g == tsk->group_leader)
			continue;

1568 1569 1570
		p = g;
		do {
			if (p->mm) {
1571 1572 1573 1574 1575 1576
				if (p->mm == mm) {
					/*
					 * p->sighand can't disappear, but
					 * may be changed by de_thread()
					 */
					lock_task_sighand(p, &flags);
1577
					zap_process(p);
1578 1579
					unlock_task_sighand(p, &flags);
				}
1580 1581 1582 1583
				break;
			}
		} while ((p = next_thread(p)) != g);
	}
1584
	rcu_read_unlock();
1585
done:
1586
	return mm->core_waiters;
L
Linus Torvalds 已提交
1587 1588
}

1589
static int coredump_wait(int exit_code)
L
Linus Torvalds 已提交
1590
{
1591 1592 1593 1594
	struct task_struct *tsk = current;
	struct mm_struct *mm = tsk->mm;
	struct completion startup_done;
	struct completion *vfork_done;
O
Oleg Nesterov 已提交
1595
	int core_waiters;
L
Linus Torvalds 已提交
1596

1597 1598
	init_completion(&mm->core_done);
	init_completion(&startup_done);
L
Linus Torvalds 已提交
1599 1600
	mm->core_startup_done = &startup_done;

1601
	core_waiters = zap_threads(tsk, mm, exit_code);
O
Oleg Nesterov 已提交
1602 1603
	up_write(&mm->mmap_sem);

1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616
	if (unlikely(core_waiters < 0))
		goto fail;

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

O
Oleg Nesterov 已提交
1617
	if (core_waiters)
L
Linus Torvalds 已提交
1618
		wait_for_completion(&startup_done);
1619
fail:
L
Linus Torvalds 已提交
1620
	BUG_ON(mm->core_waiters);
1621
	return core_waiters;
L
Linus Torvalds 已提交
1622 1623
}

1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672
/*
 * set_dumpable converts traditional three-value dumpable to two flags and
 * stores them into mm->flags.  It modifies lower two bits of mm->flags, but
 * these bits are not changed atomically.  So get_dumpable can observe the
 * intermediate state.  To avoid doing unexpected behavior, get get_dumpable
 * return either old dumpable or new one by paying attention to the order of
 * modifying the bits.
 *
 * dumpable |   mm->flags (binary)
 * old  new | initial interim  final
 * ---------+-----------------------
 *  0    1  |   00      01      01
 *  0    2  |   00      10(*)   11
 *  1    0  |   01      00      00
 *  1    2  |   01      11      11
 *  2    0  |   11      10(*)   00
 *  2    1  |   11      11      01
 *
 * (*) get_dumpable regards interim value of 10 as 11.
 */
void set_dumpable(struct mm_struct *mm, int value)
{
	switch (value) {
	case 0:
		clear_bit(MMF_DUMPABLE, &mm->flags);
		smp_wmb();
		clear_bit(MMF_DUMP_SECURELY, &mm->flags);
		break;
	case 1:
		set_bit(MMF_DUMPABLE, &mm->flags);
		smp_wmb();
		clear_bit(MMF_DUMP_SECURELY, &mm->flags);
		break;
	case 2:
		set_bit(MMF_DUMP_SECURELY, &mm->flags);
		smp_wmb();
		set_bit(MMF_DUMPABLE, &mm->flags);
		break;
	}
}

int get_dumpable(struct mm_struct *mm)
{
	int ret;

	ret = mm->flags & 0x3;
	return (ret >= 2) ? 2 : ret;
}

L
Linus Torvalds 已提交
1673 1674 1675 1676 1677 1678 1679 1680
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
1681 1682
	int fsuid = current->fsuid;
	int flag = 0;
1683
	int ispipe = 0;
1684
	unsigned long core_limit = current->signal->rlim[RLIMIT_CORE].rlim_cur;
1685 1686 1687
	char **helper_argv = NULL;
	int helper_argc = 0;
	char *delimit;
L
Linus Torvalds 已提交
1688

S
Steve Grubb 已提交
1689 1690
	audit_core_dumps(signr);

L
Linus Torvalds 已提交
1691 1692 1693 1694
	binfmt = current->binfmt;
	if (!binfmt || !binfmt->core_dump)
		goto fail;
	down_write(&mm->mmap_sem);
1695
	if (!get_dumpable(mm)) {
L
Linus Torvalds 已提交
1696 1697 1698
		up_write(&mm->mmap_sem);
		goto fail;
	}
A
Alan Cox 已提交
1699 1700 1701 1702 1703 1704

	/*
	 *	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.
	 */
1705
	if (get_dumpable(mm) == 2) {	/* Setuid core dump mode */
A
Alan Cox 已提交
1706 1707 1708
		flag = O_EXCL;		/* Stop rewrite attacks */
		current->fsuid = 0;	/* Dump root private */
	}
1709
	set_dumpable(mm, 0);
1710

1711 1712
	retval = coredump_wait(exit_code);
	if (retval < 0)
1713
		goto fail;
L
Linus Torvalds 已提交
1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725

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

	/*
	 * lock_kernel() because format_corename() is controlled by sysctl, which
	 * uses lock_kernel()
	 */
 	lock_kernel();
1726
	ispipe = format_corename(corename, core_pattern, signr);
L
Linus Torvalds 已提交
1727
	unlock_kernel();
1728 1729 1730 1731 1732 1733 1734 1735
	/*
	 * Don't bother to check the RLIMIT_CORE value if core_pattern points
	 * to a pipe.  Since we're not writing directly to the filesystem
	 * RLIMIT_CORE doesn't really apply, as no actual core file will be
	 * created unless the pipe reader choses to write out the core file
	 * at which point file size limits and permissions will be imposed
	 * as it does with any other process
	 */
1736
	if ((!ispipe) && (core_limit < binfmt->min_coredump))
1737 1738
		goto fail_unlock;

1739
 	if (ispipe) {
1740 1741 1742 1743 1744
		helper_argv = argv_split(GFP_KERNEL, corename+1, &helper_argc);
		/* Terminate the string before the first option */
		delimit = strchr(corename, ' ');
		if (delimit)
			*delimit = '\0';
1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757
		delimit = strrchr(helper_argv[0], '/');
		if (delimit)
			delimit++;
		else
			delimit = helper_argv[0];
		if (!strcmp(delimit, current->comm)) {
			printk(KERN_NOTICE "Recursive core dump detected, "
					"aborting\n");
			goto fail_unlock;
		}

		core_limit = RLIM_INFINITY;

1758
		/* SIGPIPE can happen, but it's just never processed */
1759 1760
 		if (call_usermodehelper_pipe(corename+1, helper_argv, NULL,
				&file)) {
1761 1762 1763 1764 1765 1766
 			printk(KERN_INFO "Core dump to %s pipe failed\n",
			       corename);
 			goto fail_unlock;
 		}
 	} else
 		file = filp_open(corename,
1767 1768
				 O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag,
				 0600);
L
Linus Torvalds 已提交
1769 1770
	if (IS_ERR(file))
		goto fail_unlock;
1771
	inode = file->f_path.dentry->d_inode;
L
Linus Torvalds 已提交
1772 1773
	if (inode->i_nlink > 1)
		goto close_fail;	/* multiple links - don't dump */
1774
	if (!ispipe && d_unhashed(file->f_path.dentry))
L
Linus Torvalds 已提交
1775 1776
		goto close_fail;

1777 1778 1779
	/* AK: actually i see no reason to not allow this for named pipes etc.,
	   but keep the previous behaviour for now. */
	if (!ispipe && !S_ISREG(inode->i_mode))
L
Linus Torvalds 已提交
1780 1781 1782 1783 1784
		goto close_fail;
	if (!file->f_op)
		goto close_fail;
	if (!file->f_op->write)
		goto close_fail;
1785
	if (!ispipe && do_truncate(file->f_path.dentry, 0, 0, file) != 0)
L
Linus Torvalds 已提交
1786 1787
		goto close_fail;

1788
	retval = binfmt->core_dump(signr, regs, file, core_limit);
L
Linus Torvalds 已提交
1789 1790 1791 1792 1793 1794

	if (retval)
		current->signal->group_exit_code |= 0x80;
close_fail:
	filp_close(file, NULL);
fail_unlock:
1795 1796 1797
	if (helper_argv)
		argv_free(helper_argv);

A
Alan Cox 已提交
1798
	current->fsuid = fsuid;
L
Linus Torvalds 已提交
1799 1800 1801 1802
	complete_all(&mm->core_done);
fail:
	return retval;
}