fork.c 40.3 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
/*
 *  linux/kernel/fork.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

/*
 *  'fork.c' contains the help-routines for the 'fork' system call
 * (see also entry.S and others).
 * Fork is rather simple, once you get the hang of it, but the memory
 * management can be a bitch. See 'mm/memory.c': 'copy_page_range()'
 */

#include <linux/slab.h>
#include <linux/init.h>
#include <linux/unistd.h>
#include <linux/smp_lock.h>
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/completion.h>
#include <linux/namespace.h>
#include <linux/personality.h>
#include <linux/mempolicy.h>
#include <linux/sem.h>
#include <linux/file.h>
#include <linux/key.h>
#include <linux/binfmts.h>
#include <linux/mman.h>
#include <linux/fs.h>
30
#include <linux/capability.h>
L
Linus Torvalds 已提交
31 32 33 34 35 36 37
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/security.h>
#include <linux/swap.h>
#include <linux/syscalls.h>
#include <linux/jiffies.h>
#include <linux/futex.h>
38
#include <linux/rcupdate.h>
L
Linus Torvalds 已提交
39 40 41 42 43 44
#include <linux/ptrace.h>
#include <linux/mount.h>
#include <linux/audit.h>
#include <linux/profile.h>
#include <linux/rmap.h>
#include <linux/acct.h>
M
Matt Helsley 已提交
45
#include <linux/cn_proc.h>
L
Linus Torvalds 已提交
46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85

#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>

/*
 * Protected counters by write_lock_irq(&tasklist_lock)
 */
unsigned long total_forks;	/* Handle normal Linux uptimes. */
int nr_threads; 		/* The idle threads do not count.. */

int max_threads;		/* tunable limit on nr_threads */

DEFINE_PER_CPU(unsigned long, process_counts) = 0;

 __cacheline_aligned DEFINE_RWLOCK(tasklist_lock);  /* outer */

EXPORT_SYMBOL(tasklist_lock);

int nr_processes(void)
{
	int cpu;
	int total = 0;

	for_each_online_cpu(cpu)
		total += per_cpu(process_counts, cpu);

	return total;
}

#ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR
# define alloc_task_struct()	kmem_cache_alloc(task_struct_cachep, GFP_KERNEL)
# define free_task_struct(tsk)	kmem_cache_free(task_struct_cachep, (tsk))
static kmem_cache_t *task_struct_cachep;
#endif

/* SLAB cache for signal_struct structures (tsk->signal) */
86
static kmem_cache_t *signal_cachep;
L
Linus Torvalds 已提交
87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105

/* SLAB cache for sighand_struct structures (tsk->sighand) */
kmem_cache_t *sighand_cachep;

/* SLAB cache for files_struct structures (tsk->files) */
kmem_cache_t *files_cachep;

/* SLAB cache for fs_struct structures (tsk->fs) */
kmem_cache_t *fs_cachep;

/* SLAB cache for vm_area_struct structures */
kmem_cache_t *vm_area_cachep;

/* SLAB cache for mm_struct structures (tsk->mm) */
static kmem_cache_t *mm_cachep;

void free_task(struct task_struct *tsk)
{
	free_thread_info(tsk->thread_info);
I
Ingo Molnar 已提交
106
	rt_mutex_debug_task_free(tsk);
L
Linus Torvalds 已提交
107 108 109 110
	free_task_struct(tsk);
}
EXPORT_SYMBOL(free_task);

111
void __put_task_struct(struct task_struct *tsk)
L
Linus Torvalds 已提交
112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174
{
	WARN_ON(!(tsk->exit_state & (EXIT_DEAD | EXIT_ZOMBIE)));
	WARN_ON(atomic_read(&tsk->usage));
	WARN_ON(tsk == current);

	security_task_free(tsk);
	free_uid(tsk->user);
	put_group_info(tsk->group_info);

	if (!profile_handoff_task(tsk))
		free_task(tsk);
}

void __init fork_init(unsigned long mempages)
{
#ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR
#ifndef ARCH_MIN_TASKALIGN
#define ARCH_MIN_TASKALIGN	L1_CACHE_BYTES
#endif
	/* create a slab on which task_structs can be allocated */
	task_struct_cachep =
		kmem_cache_create("task_struct", sizeof(struct task_struct),
			ARCH_MIN_TASKALIGN, SLAB_PANIC, NULL, NULL);
#endif

	/*
	 * The default maximum number of threads is set to a safe
	 * value: the thread structures can take up at most half
	 * of memory.
	 */
	max_threads = mempages / (8 * THREAD_SIZE / PAGE_SIZE);

	/*
	 * we need to allow at least 20 threads to boot a system
	 */
	if(max_threads < 20)
		max_threads = 20;

	init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2;
	init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2;
	init_task.signal->rlim[RLIMIT_SIGPENDING] =
		init_task.signal->rlim[RLIMIT_NPROC];
}

static struct task_struct *dup_task_struct(struct task_struct *orig)
{
	struct task_struct *tsk;
	struct thread_info *ti;

	prepare_to_copy(orig);

	tsk = alloc_task_struct();
	if (!tsk)
		return NULL;

	ti = alloc_thread_info(tsk);
	if (!ti) {
		free_task_struct(tsk);
		return NULL;
	}

	*tsk = *orig;
	tsk->thread_info = ti;
175
	setup_thread_stack(tsk, orig);
L
Linus Torvalds 已提交
176 177 178

	/* One for us, one for whoever does the "release_task()" (usually parent) */
	atomic_set(&tsk->usage,2);
179
	atomic_set(&tsk->fs_excl, 0);
180
	tsk->btrace_seq = 0;
181
	tsk->splice_pipe = NULL;
L
Linus Torvalds 已提交
182 183 184 185
	return tsk;
}

#ifdef CONFIG_MMU
H
Hugh Dickins 已提交
186
static inline int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
L
Linus Torvalds 已提交
187
{
H
Hugh Dickins 已提交
188
	struct vm_area_struct *mpnt, *tmp, **pprev;
L
Linus Torvalds 已提交
189 190 191 192 193 194
	struct rb_node **rb_link, *rb_parent;
	int retval;
	unsigned long charge;
	struct mempolicy *pol;

	down_write(&oldmm->mmap_sem);
H
Hugh Dickins 已提交
195
	flush_cache_mm(oldmm);
196 197
	down_write(&mm->mmap_sem);

L
Linus Torvalds 已提交
198 199 200 201
	mm->locked_vm = 0;
	mm->mmap = NULL;
	mm->mmap_cache = NULL;
	mm->free_area_cache = oldmm->mmap_base;
202
	mm->cached_hole_size = ~0UL;
L
Linus Torvalds 已提交
203 204 205 206 207 208 209
	mm->map_count = 0;
	cpus_clear(mm->cpu_vm_mask);
	mm->mm_rb = RB_ROOT;
	rb_link = &mm->mm_rb.rb_node;
	rb_parent = NULL;
	pprev = &mm->mmap;

H
Hugh Dickins 已提交
210
	for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
L
Linus Torvalds 已提交
211 212 213
		struct file *file;

		if (mpnt->vm_flags & VM_DONTCOPY) {
214 215
			long pages = vma_pages(mpnt);
			mm->total_vm -= pages;
216
			vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file,
217
								-pages);
L
Linus Torvalds 已提交
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
			continue;
		}
		charge = 0;
		if (mpnt->vm_flags & VM_ACCOUNT) {
			unsigned int len = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT;
			if (security_vm_enough_memory(len))
				goto fail_nomem;
			charge = len;
		}
		tmp = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
		if (!tmp)
			goto fail_nomem;
		*tmp = *mpnt;
		pol = mpol_copy(vma_policy(mpnt));
		retval = PTR_ERR(pol);
		if (IS_ERR(pol))
			goto fail_nomem_policy;
		vma_set_policy(tmp, pol);
		tmp->vm_flags &= ~VM_LOCKED;
		tmp->vm_mm = mm;
		tmp->vm_next = NULL;
		anon_vma_link(tmp);
		file = tmp->vm_file;
		if (file) {
			struct inode *inode = file->f_dentry->d_inode;
			get_file(file);
			if (tmp->vm_flags & VM_DENYWRITE)
				atomic_dec(&inode->i_writecount);
      
			/* insert tmp into the share list, just after mpnt */
			spin_lock(&file->f_mapping->i_mmap_lock);
			tmp->vm_truncate_count = mpnt->vm_truncate_count;
			flush_dcache_mmap_lock(file->f_mapping);
			vma_prio_tree_add(tmp, mpnt);
			flush_dcache_mmap_unlock(file->f_mapping);
			spin_unlock(&file->f_mapping->i_mmap_lock);
		}

		/*
257
		 * Link in the new vma and copy the page table entries.
L
Linus Torvalds 已提交
258 259 260 261 262 263 264 265 266
		 */
		*pprev = tmp;
		pprev = &tmp->vm_next;

		__vma_link_rb(mm, tmp, rb_link, rb_parent);
		rb_link = &tmp->vm_rb.rb_right;
		rb_parent = &tmp->vm_rb;

		mm->map_count++;
267
		retval = copy_page_range(mm, oldmm, mpnt);
L
Linus Torvalds 已提交
268 269 270 271 272 273 274 275 276

		if (tmp->vm_ops && tmp->vm_ops->open)
			tmp->vm_ops->open(tmp);

		if (retval)
			goto out;
	}
	retval = 0;
out:
277
	up_write(&mm->mmap_sem);
H
Hugh Dickins 已提交
278
	flush_tlb_mm(oldmm);
L
Linus Torvalds 已提交
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
	up_write(&oldmm->mmap_sem);
	return retval;
fail_nomem_policy:
	kmem_cache_free(vm_area_cachep, tmp);
fail_nomem:
	retval = -ENOMEM;
	vm_unacct_memory(charge);
	goto out;
}

static inline int mm_alloc_pgd(struct mm_struct * mm)
{
	mm->pgd = pgd_alloc(mm);
	if (unlikely(!mm->pgd))
		return -ENOMEM;
	return 0;
}

static inline void mm_free_pgd(struct mm_struct * mm)
{
	pgd_free(mm->pgd);
}
#else
#define dup_mmap(mm, oldmm)	(0)
#define mm_alloc_pgd(mm)	(0)
#define mm_free_pgd(mm)
#endif /* CONFIG_MMU */

 __cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock);

#define allocate_mm()	(kmem_cache_alloc(mm_cachep, SLAB_KERNEL))
#define free_mm(mm)	(kmem_cache_free(mm_cachep, (mm)))

#include <linux/init_task.h>

static struct mm_struct * mm_init(struct mm_struct * mm)
{
	atomic_set(&mm->mm_users, 1);
	atomic_set(&mm->mm_count, 1);
	init_rwsem(&mm->mmap_sem);
	INIT_LIST_HEAD(&mm->mmlist);
	mm->core_waiters = 0;
	mm->nr_ptes = 0;
322
	set_mm_counter(mm, file_rss, 0);
H
Hugh Dickins 已提交
323
	set_mm_counter(mm, anon_rss, 0);
L
Linus Torvalds 已提交
324 325 326 327
	spin_lock_init(&mm->page_table_lock);
	rwlock_init(&mm->ioctx_list_lock);
	mm->ioctx_list = NULL;
	mm->free_area_cache = TASK_UNMAPPED_BASE;
328
	mm->cached_hole_size = ~0UL;
L
Linus Torvalds 已提交
329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370

	if (likely(!mm_alloc_pgd(mm))) {
		mm->def_flags = 0;
		return mm;
	}
	free_mm(mm);
	return NULL;
}

/*
 * Allocate and initialize an mm_struct.
 */
struct mm_struct * mm_alloc(void)
{
	struct mm_struct * mm;

	mm = allocate_mm();
	if (mm) {
		memset(mm, 0, sizeof(*mm));
		mm = mm_init(mm);
	}
	return mm;
}

/*
 * Called when the last reference to the mm
 * is dropped: either by a lazy thread or by
 * mmput. Free the page directory and the mm.
 */
void fastcall __mmdrop(struct mm_struct *mm)
{
	BUG_ON(mm == &init_mm);
	mm_free_pgd(mm);
	destroy_context(mm);
	free_mm(mm);
}

/*
 * Decrement the use count and release all resources for an mm.
 */
void mmput(struct mm_struct *mm)
{
A
Andrew Morton 已提交
371 372
	might_sleep();

L
Linus Torvalds 已提交
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
	if (atomic_dec_and_test(&mm->mm_users)) {
		exit_aio(mm);
		exit_mmap(mm);
		if (!list_empty(&mm->mmlist)) {
			spin_lock(&mmlist_lock);
			list_del(&mm->mmlist);
			spin_unlock(&mmlist_lock);
		}
		put_swap_token(mm);
		mmdrop(mm);
	}
}
EXPORT_SYMBOL_GPL(mmput);

/**
 * get_task_mm - acquire a reference to the task's mm
 *
 * Returns %NULL if the task has no mm.  Checks PF_BORROWED_MM (meaning
 * this kernel workthread has transiently adopted a user mm with use_mm,
 * to do its AIO) is not set and if so returns a reference to it, after
 * bumping up the use count.  User must release the mm via mmput()
 * after use.  Typically used by /proc and ptrace.
 */
struct mm_struct *get_task_mm(struct task_struct *task)
{
	struct mm_struct *mm;

	task_lock(task);
	mm = task->mm;
	if (mm) {
		if (task->flags & PF_BORROWED_MM)
			mm = NULL;
		else
			atomic_inc(&mm->mm_users);
	}
	task_unlock(task);
	return mm;
}
EXPORT_SYMBOL_GPL(get_task_mm);

/* Please note the differences between mmput and mm_release.
 * mmput is called whenever we stop holding onto a mm_struct,
 * error success whatever.
 *
 * mm_release is called after a mm_struct has been removed
 * from the current process.
 *
 * This difference is important for error handling, when we
 * only half set up a mm_struct for a new process and need to restore
 * the old one.  Because we mmput the new mm_struct before
 * restoring the old one. . .
 * Eric Biederman 10 January 1998
 */
void mm_release(struct task_struct *tsk, struct mm_struct *mm)
{
	struct completion *vfork_done = tsk->vfork_done;

	/* Get rid of any cached register state */
	deactivate_mm(tsk, mm);

	/* notify parent sleeping on vfork() */
	if (vfork_done) {
		tsk->vfork_done = NULL;
		complete(vfork_done);
	}
	if (tsk->clear_child_tid && atomic_read(&mm->mm_users) > 1) {
		u32 __user * tidptr = tsk->clear_child_tid;
		tsk->clear_child_tid = NULL;

		/*
		 * We don't check the error code - if userspace has
		 * not set up a proper pointer then tough luck.
		 */
		put_user(0, tidptr);
		sys_futex(tidptr, FUTEX_WAKE, 1, NULL, NULL, 0);
	}
}

451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499
/*
 * Allocate a new mm structure and copy contents from the
 * mm structure of the passed in task structure.
 */
static struct mm_struct *dup_mm(struct task_struct *tsk)
{
	struct mm_struct *mm, *oldmm = current->mm;
	int err;

	if (!oldmm)
		return NULL;

	mm = allocate_mm();
	if (!mm)
		goto fail_nomem;

	memcpy(mm, oldmm, sizeof(*mm));

	if (!mm_init(mm))
		goto fail_nomem;

	if (init_new_context(tsk, mm))
		goto fail_nocontext;

	err = dup_mmap(mm, oldmm);
	if (err)
		goto free_pt;

	mm->hiwater_rss = get_mm_rss(mm);
	mm->hiwater_vm = mm->total_vm;

	return mm;

free_pt:
	mmput(mm);

fail_nomem:
	return NULL;

fail_nocontext:
	/*
	 * If init_new_context() failed, we cannot use mmput() to free the mm
	 * because it calls destroy_context()
	 */
	mm_free_pgd(mm);
	free_mm(mm);
	return NULL;
}

L
Linus Torvalds 已提交
500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526
static int copy_mm(unsigned long clone_flags, struct task_struct * tsk)
{
	struct mm_struct * mm, *oldmm;
	int retval;

	tsk->min_flt = tsk->maj_flt = 0;
	tsk->nvcsw = tsk->nivcsw = 0;

	tsk->mm = NULL;
	tsk->active_mm = NULL;

	/*
	 * Are we cloning a kernel thread?
	 *
	 * We need to steal a active VM for that..
	 */
	oldmm = current->mm;
	if (!oldmm)
		return 0;

	if (clone_flags & CLONE_VM) {
		atomic_inc(&oldmm->mm_users);
		mm = oldmm;
		goto good_mm;
	}

	retval = -ENOMEM;
527
	mm = dup_mm(tsk);
L
Linus Torvalds 已提交
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
	if (!mm)
		goto fail_nomem;

good_mm:
	tsk->mm = mm;
	tsk->active_mm = mm;
	return 0;

fail_nomem:
	return retval;
}

static inline struct fs_struct *__copy_fs_struct(struct fs_struct *old)
{
	struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL);
	/* We don't need to lock fs - think why ;-) */
	if (fs) {
		atomic_set(&fs->count, 1);
		rwlock_init(&fs->lock);
		fs->umask = old->umask;
		read_lock(&old->lock);
		fs->rootmnt = mntget(old->rootmnt);
		fs->root = dget(old->root);
		fs->pwdmnt = mntget(old->pwdmnt);
		fs->pwd = dget(old->pwd);
		if (old->altroot) {
			fs->altrootmnt = mntget(old->altrootmnt);
			fs->altroot = dget(old->altroot);
		} else {
			fs->altrootmnt = NULL;
			fs->altroot = NULL;
		}
		read_unlock(&old->lock);
	}
	return fs;
}

struct fs_struct *copy_fs_struct(struct fs_struct *old)
{
	return __copy_fs_struct(old);
}

EXPORT_SYMBOL_GPL(copy_fs_struct);

static inline int copy_fs(unsigned long clone_flags, struct task_struct * tsk)
{
	if (clone_flags & CLONE_FS) {
		atomic_inc(&current->fs->count);
		return 0;
	}
	tsk->fs = __copy_fs_struct(current->fs);
	if (!tsk->fs)
		return -ENOMEM;
	return 0;
}

584
static int count_open_files(struct fdtable *fdt)
L
Linus Torvalds 已提交
585
{
586
	int size = fdt->max_fdset;
L
Linus Torvalds 已提交
587 588 589 590
	int i;

	/* Find the last open fd */
	for (i = size/(8*sizeof(long)); i > 0; ) {
591
		if (fdt->open_fds->fds_bits[--i])
L
Linus Torvalds 已提交
592 593 594 595 596 597
			break;
	}
	i = (i+1) * 8 * sizeof(long);
	return i;
}

598 599 600 601 602 603 604 605 606 607 608 609
static struct files_struct *alloc_files(void)
{
	struct files_struct *newf;
	struct fdtable *fdt;

	newf = kmem_cache_alloc(files_cachep, SLAB_KERNEL);
	if (!newf)
		goto out;

	atomic_set(&newf->count, 1);

	spin_lock_init(&newf->file_lock);
610
	newf->next_fd = 0;
611
	fdt = &newf->fdtab;
612
	fdt->max_fds = NR_OPEN_DEFAULT;
613 614 615
	fdt->max_fdset = EMBEDDED_FD_SET_SIZE;
	fdt->close_on_exec = (fd_set *)&newf->close_on_exec_init;
	fdt->open_fds = (fd_set *)&newf->open_fds_init;
616
	fdt->fd = &newf->fd_array[0];
617 618 619 620
	INIT_RCU_HEAD(&fdt->rcu);
	fdt->free_files = NULL;
	fdt->next = NULL;
	rcu_assign_pointer(newf->fdt, fdt);
621 622 623 624
out:
	return newf;
}

625 626 627
/*
 * Allocate a new files structure and copy contents from the
 * passed in files structure.
P
Prasanna Meda 已提交
628
 * errorp will be valid only when the returned files_struct is NULL.
629 630
 */
static struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
L
Linus Torvalds 已提交
631
{
632
	struct files_struct *newf;
L
Linus Torvalds 已提交
633
	struct file **old_fds, **new_fds;
634
	int open_files, size, i, expand;
635
	struct fdtable *old_fdt, *new_fdt;
L
Linus Torvalds 已提交
636

P
Prasanna Meda 已提交
637
	*errorp = -ENOMEM;
638 639
	newf = alloc_files();
	if (!newf)
L
Linus Torvalds 已提交
640 641 642
		goto out;

	spin_lock(&oldf->file_lock);
643 644 645
	old_fdt = files_fdtable(oldf);
	new_fdt = files_fdtable(newf);
	size = old_fdt->max_fdset;
646
	open_files = count_open_files(old_fdt);
L
Linus Torvalds 已提交
647 648 649 650 651 652
	expand = 0;

	/*
	 * Check whether we need to allocate a larger fd array or fd set.
	 * Note: we're not a clone task, so the open count won't  change.
	 */
653 654
	if (open_files > new_fdt->max_fdset) {
		new_fdt->max_fdset = 0;
L
Linus Torvalds 已提交
655 656
		expand = 1;
	}
657 658
	if (open_files > new_fdt->max_fds) {
		new_fdt->max_fds = 0;
L
Linus Torvalds 已提交
659 660 661 662 663 664 665
		expand = 1;
	}

	/* if the old fdset gets grown now, we'll only copy up to "size" fds */
	if (expand) {
		spin_unlock(&oldf->file_lock);
		spin_lock(&newf->file_lock);
666
		*errorp = expand_files(newf, open_files-1);
L
Linus Torvalds 已提交
667
		spin_unlock(&newf->file_lock);
668
		if (*errorp < 0)
L
Linus Torvalds 已提交
669
			goto out_release;
670 671 672 673 674 675
		new_fdt = files_fdtable(newf);
		/*
		 * Reacquire the oldf lock and a pointer to its fd table
		 * who knows it may have a new bigger fd table. We need
		 * the latest pointer.
		 */
L
Linus Torvalds 已提交
676
		spin_lock(&oldf->file_lock);
677
		old_fdt = files_fdtable(oldf);
L
Linus Torvalds 已提交
678 679
	}

680 681
	old_fds = old_fdt->fd;
	new_fds = new_fdt->fd;
L
Linus Torvalds 已提交
682

683 684
	memcpy(new_fdt->open_fds->fds_bits, old_fdt->open_fds->fds_bits, open_files/8);
	memcpy(new_fdt->close_on_exec->fds_bits, old_fdt->close_on_exec->fds_bits, open_files/8);
L
Linus Torvalds 已提交
685 686 687 688 689 690 691 692 693 694 695 696

	for (i = open_files; i != 0; i--) {
		struct file *f = *old_fds++;
		if (f) {
			get_file(f);
		} else {
			/*
			 * The fd may be claimed in the fd bitmap but not yet
			 * instantiated in the files array if a sibling thread
			 * is partway through open().  So make sure that this
			 * fd is available to the new process.
			 */
697
			FD_CLR(open_files - i, new_fdt->open_fds);
L
Linus Torvalds 已提交
698
		}
699
		rcu_assign_pointer(*new_fds++, f);
L
Linus Torvalds 已提交
700 701 702 703
	}
	spin_unlock(&oldf->file_lock);

	/* compute the remainder to be cleared */
704
	size = (new_fdt->max_fds - open_files) * sizeof(struct file *);
L
Linus Torvalds 已提交
705 706 707 708

	/* This is long word aligned thus could use a optimized version */ 
	memset(new_fds, 0, size); 

709 710
	if (new_fdt->max_fdset > open_files) {
		int left = (new_fdt->max_fdset-open_files)/8;
L
Linus Torvalds 已提交
711 712
		int start = open_files / (8 * sizeof(unsigned long));

713 714
		memset(&new_fdt->open_fds->fds_bits[start], 0, left);
		memset(&new_fdt->close_on_exec->fds_bits[start], 0, left);
L
Linus Torvalds 已提交
715 716 717
	}

out:
718
	return newf;
L
Linus Torvalds 已提交
719 720

out_release:
721 722 723
	free_fdset (new_fdt->close_on_exec, new_fdt->max_fdset);
	free_fdset (new_fdt->open_fds, new_fdt->max_fdset);
	free_fd_array(new_fdt->fd, new_fdt->max_fds);
L
Linus Torvalds 已提交
724
	kmem_cache_free(files_cachep, newf);
725
	return NULL;
L
Linus Torvalds 已提交
726 727
}

728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760
static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
{
	struct files_struct *oldf, *newf;
	int error = 0;

	/*
	 * A background process may not have any files ...
	 */
	oldf = current->files;
	if (!oldf)
		goto out;

	if (clone_flags & CLONE_FILES) {
		atomic_inc(&oldf->count);
		goto out;
	}

	/*
	 * Note: we may be using current for both targets (See exec.c)
	 * This works because we cache current->files (old) as oldf. Don't
	 * break this.
	 */
	tsk->files = NULL;
	newf = dup_fd(oldf, &error);
	if (!newf)
		goto out;

	tsk->files = newf;
	error = 0;
out:
	return error;
}

L
Linus Torvalds 已提交
761 762 763 764 765 766 767 768 769 770 771
/*
 *	Helper to unshare the files of the current task.
 *	We don't want to expose copy_files internals to
 *	the exec layer of the kernel.
 */

int unshare_files(void)
{
	struct files_struct *files  = current->files;
	int rc;

772
	BUG_ON(!files);
L
Linus Torvalds 已提交
773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797

	/* This can race but the race causes us to copy when we don't
	   need to and drop the copy */
	if(atomic_read(&files->count) == 1)
	{
		atomic_inc(&files->count);
		return 0;
	}
	rc = copy_files(0, current);
	if(rc)
		current->files = files;
	return rc;
}

EXPORT_SYMBOL(unshare_files);

static inline int copy_sighand(unsigned long clone_flags, struct task_struct * tsk)
{
	struct sighand_struct *sig;

	if (clone_flags & (CLONE_SIGHAND | CLONE_THREAD)) {
		atomic_inc(&current->sighand->count);
		return 0;
	}
	sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL);
I
Ingo Molnar 已提交
798
	rcu_assign_pointer(tsk->sighand, sig);
L
Linus Torvalds 已提交
799 800 801 802 803 804 805
	if (!sig)
		return -ENOMEM;
	atomic_set(&sig->count, 1);
	memcpy(sig->action, current->sighand->action, sizeof(sig->action));
	return 0;
}

806
void __cleanup_sighand(struct sighand_struct *sighand)
807 808 809 810 811
{
	if (atomic_dec_and_test(&sighand->count))
		kmem_cache_free(sighand_cachep, sighand);
}

L
Linus Torvalds 已提交
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
static inline int copy_signal(unsigned long clone_flags, struct task_struct * tsk)
{
	struct signal_struct *sig;
	int ret;

	if (clone_flags & CLONE_THREAD) {
		atomic_inc(&current->signal->count);
		atomic_inc(&current->signal->live);
		return 0;
	}
	sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
	tsk->signal = sig;
	if (!sig)
		return -ENOMEM;

	ret = copy_thread_group_keys(tsk);
	if (ret < 0) {
		kmem_cache_free(signal_cachep, sig);
		return ret;
	}

	atomic_set(&sig->count, 1);
	atomic_set(&sig->live, 1);
	init_waitqueue_head(&sig->wait_chldexit);
	sig->flags = 0;
	sig->group_exit_code = 0;
	sig->group_exit_task = NULL;
	sig->group_stop_count = 0;
	sig->curr_target = NULL;
	init_sigpending(&sig->shared_pending);
	INIT_LIST_HEAD(&sig->posix_timers);

844
	hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_REL);
845
	sig->it_real_incr.tv64 = 0;
L
Linus Torvalds 已提交
846
	sig->real_timer.function = it_real_fn;
847
	sig->tsk = tsk;
L
Linus Torvalds 已提交
848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876

	sig->it_virt_expires = cputime_zero;
	sig->it_virt_incr = cputime_zero;
	sig->it_prof_expires = cputime_zero;
	sig->it_prof_incr = cputime_zero;

	sig->leader = 0;	/* session leadership doesn't inherit */
	sig->tty_old_pgrp = 0;

	sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero;
	sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
	sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
	sig->sched_time = 0;
	INIT_LIST_HEAD(&sig->cpu_timers[0]);
	INIT_LIST_HEAD(&sig->cpu_timers[1]);
	INIT_LIST_HEAD(&sig->cpu_timers[2]);

	task_lock(current->group_leader);
	memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim);
	task_unlock(current->group_leader);

	if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
		/*
		 * New sole thread in the process gets an expiry time
		 * of the whole CPU time limit.
		 */
		tsk->it_prof_expires =
			secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur);
	}
877
	acct_init_pacct(&sig->pacct);
L
Linus Torvalds 已提交
878 879 880 881

	return 0;
}

882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897
void __cleanup_signal(struct signal_struct *sig)
{
	exit_thread_group_keys(sig);
	kmem_cache_free(signal_cachep, sig);
}

static inline void cleanup_signal(struct task_struct *tsk)
{
	struct signal_struct *sig = tsk->signal;

	atomic_dec(&sig->live);

	if (atomic_dec_and_test(&sig->count))
		__cleanup_signal(sig);
}

L
Linus Torvalds 已提交
898 899 900 901
static inline void copy_flags(unsigned long clone_flags, struct task_struct *p)
{
	unsigned long new_flags = p->flags;

902
	new_flags &= ~(PF_SUPERPRIV | PF_NOFREEZE);
L
Linus Torvalds 已提交
903 904 905 906 907 908 909 910 911 912 913 914 915
	new_flags |= PF_FORKNOEXEC;
	if (!(clone_flags & CLONE_PTRACE))
		p->ptrace = 0;
	p->flags = new_flags;
}

asmlinkage long sys_set_tid_address(int __user *tidptr)
{
	current->clear_child_tid = tidptr;

	return current->pid;
}

I
Ingo Molnar 已提交
916 917 918 919 920 921 922 923 924
static inline void rt_mutex_init_task(struct task_struct *p)
{
#ifdef CONFIG_RT_MUTEXES
	spin_lock_init(&p->pi_lock);
	plist_head_init(&p->pi_waiters, &p->pi_lock);
	p->pi_blocked_on = NULL;
#endif
}

L
Linus Torvalds 已提交
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
/*
 * This creates a new process as a copy of the old one,
 * but does not actually start it yet.
 *
 * It copies the registers, and all the appropriate
 * parts of the process environment (as per the clone
 * flags). The actual kick-off is left to the caller.
 */
static task_t *copy_process(unsigned long clone_flags,
				 unsigned long stack_start,
				 struct pt_regs *regs,
				 unsigned long stack_size,
				 int __user *parent_tidptr,
				 int __user *child_tidptr,
				 int pid)
{
	int retval;
	struct task_struct *p = NULL;

	if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
		return ERR_PTR(-EINVAL);

	/*
	 * Thread groups must share signals as well, and detached threads
	 * can only be started up within the thread group.
	 */
	if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND))
		return ERR_PTR(-EINVAL);

	/*
	 * Shared signal handlers imply shared VM. By way of the above,
	 * thread groups also imply shared VM. Blocking this case allows
	 * for various simplifications in other code.
	 */
	if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM))
		return ERR_PTR(-EINVAL);

	retval = security_task_create(clone_flags);
	if (retval)
		goto fork_out;

	retval = -ENOMEM;
	p = dup_task_struct(current);
	if (!p)
		goto fork_out;

971 972 973 974
#ifdef CONFIG_TRACE_IRQFLAGS
	DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
	DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
#endif
L
Linus Torvalds 已提交
975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994
	retval = -EAGAIN;
	if (atomic_read(&p->user->processes) >=
			p->signal->rlim[RLIMIT_NPROC].rlim_cur) {
		if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
				p->user != &root_user)
			goto bad_fork_free;
	}

	atomic_inc(&p->user->__count);
	atomic_inc(&p->user->processes);
	get_group_info(p->group_info);

	/*
	 * If multiple threads are within copy_process(), then this check
	 * triggers too late. This doesn't hurt, the check is only there
	 * to stop root fork bombs.
	 */
	if (nr_threads >= max_threads)
		goto bad_fork_cleanup_count;

A
Al Viro 已提交
995
	if (!try_module_get(task_thread_info(p)->exec_domain->module))
L
Linus Torvalds 已提交
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
		goto bad_fork_cleanup_count;

	if (p->binfmt && !try_module_get(p->binfmt->module))
		goto bad_fork_cleanup_put_domain;

	p->did_exec = 0;
	copy_flags(clone_flags, p);
	p->pid = pid;
	retval = -EFAULT;
	if (clone_flags & CLONE_PARENT_SETTID)
		if (put_user(p->pid, parent_tidptr))
			goto bad_fork_cleanup;

	INIT_LIST_HEAD(&p->children);
	INIT_LIST_HEAD(&p->sibling);
	p->vfork_done = NULL;
	spin_lock_init(&p->alloc_lock);

	clear_tsk_thread_flag(p, TIF_SIGPENDING);
	init_sigpending(&p->pending);

	p->utime = cputime_zero;
	p->stime = cputime_zero;
 	p->sched_time = 0;
	p->rchar = 0;		/* I/O counter: bytes read */
	p->wchar = 0;		/* I/O counter: bytes written */
	p->syscr = 0;		/* I/O counter: read syscalls */
	p->syscw = 0;		/* I/O counter: write syscalls */
	acct_clear_integrals(p);

 	p->it_virt_expires = cputime_zero;
	p->it_prof_expires = cputime_zero;
 	p->it_sched_expires = 0;
 	INIT_LIST_HEAD(&p->cpu_timers[0]);
 	INIT_LIST_HEAD(&p->cpu_timers[1]);
 	INIT_LIST_HEAD(&p->cpu_timers[2]);

	p->lock_depth = -1;		/* -1 = no lock */
	do_posix_clock_monotonic_gettime(&p->start_time);
	p->security = NULL;
	p->io_context = NULL;
	p->io_wait = NULL;
	p->audit_context = NULL;
P
Paul Jackson 已提交
1039
	cpuset_fork(p);
L
Linus Torvalds 已提交
1040 1041 1042 1043 1044
#ifdef CONFIG_NUMA
 	p->mempolicy = mpol_copy(p->mempolicy);
 	if (IS_ERR(p->mempolicy)) {
 		retval = PTR_ERR(p->mempolicy);
 		p->mempolicy = NULL;
P
Paul Jackson 已提交
1045
 		goto bad_fork_cleanup_cpuset;
L
Linus Torvalds 已提交
1046
 	}
1047
	mpol_fix_fork_child_flag(p);
L
Linus Torvalds 已提交
1048
#endif
1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063
#ifdef CONFIG_TRACE_IRQFLAGS
	p->irq_events = 0;
	p->hardirqs_enabled = 0;
	p->hardirq_enable_ip = 0;
	p->hardirq_enable_event = 0;
	p->hardirq_disable_ip = _THIS_IP_;
	p->hardirq_disable_event = 0;
	p->softirqs_enabled = 1;
	p->softirq_enable_ip = _THIS_IP_;
	p->softirq_enable_event = 0;
	p->softirq_disable_ip = 0;
	p->softirq_disable_event = 0;
	p->hardirq_context = 0;
	p->softirq_context = 0;
#endif
I
Ingo Molnar 已提交
1064 1065 1066 1067 1068
#ifdef CONFIG_LOCKDEP
	p->lockdep_depth = 0; /* no locks held yet */
	p->curr_chain_key = 0;
	p->lockdep_recursion = 0;
#endif
L
Linus Torvalds 已提交
1069

I
Ingo Molnar 已提交
1070 1071
	rt_mutex_init_task(p);

1072 1073 1074 1075
#ifdef CONFIG_DEBUG_MUTEXES
	p->blocked_on = NULL; /* not blocked yet */
#endif

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 1105 1106 1107 1108 1109
	p->tgid = p->pid;
	if (clone_flags & CLONE_THREAD)
		p->tgid = current->tgid;

	if ((retval = security_task_alloc(p)))
		goto bad_fork_cleanup_policy;
	if ((retval = audit_alloc(p)))
		goto bad_fork_cleanup_security;
	/* copy all the process information */
	if ((retval = copy_semundo(clone_flags, p)))
		goto bad_fork_cleanup_audit;
	if ((retval = copy_files(clone_flags, p)))
		goto bad_fork_cleanup_semundo;
	if ((retval = copy_fs(clone_flags, p)))
		goto bad_fork_cleanup_files;
	if ((retval = copy_sighand(clone_flags, p)))
		goto bad_fork_cleanup_fs;
	if ((retval = copy_signal(clone_flags, p)))
		goto bad_fork_cleanup_sighand;
	if ((retval = copy_mm(clone_flags, p)))
		goto bad_fork_cleanup_signal;
	if ((retval = copy_keys(clone_flags, p)))
		goto bad_fork_cleanup_mm;
	if ((retval = copy_namespace(clone_flags, p)))
		goto bad_fork_cleanup_keys;
	retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
	if (retval)
		goto bad_fork_cleanup_namespace;

	p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
	/*
	 * Clear TID on mm_release()?
	 */
	p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL;
1110 1111 1112 1113
	p->robust_list = NULL;
#ifdef CONFIG_COMPAT
	p->compat_robust_list = NULL;
#endif
1114 1115 1116
	INIT_LIST_HEAD(&p->pi_state_list);
	p->pi_state_cache = NULL;

1117 1118 1119 1120 1121 1122
	/*
	 * sigaltstack should be cleared when sharing the same VM
	 */
	if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
		p->sas_ss_sp = p->sas_ss_size = 0;

L
Linus Torvalds 已提交
1123 1124 1125 1126 1127
	/*
	 * Syscall tracing should be turned off in the child regardless
	 * of CLONE_PTRACE.
	 */
	clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
1128 1129 1130
#ifdef TIF_SYSCALL_EMU
	clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
#endif
L
Linus Torvalds 已提交
1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146

	/* Our parent execution domain becomes current domain
	   These must match for thread signalling to apply */
	   
	p->parent_exec_id = p->self_exec_id;

	/* ok, now we should be set up.. */
	p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL);
	p->pdeath_signal = 0;
	p->exit_state = 0;

	/*
	 * Ok, make it visible to the rest of the system.
	 * We dont wake it up yet.
	 */
	p->group_leader = p;
O
Oleg Nesterov 已提交
1147
	INIT_LIST_HEAD(&p->thread_group);
L
Linus Torvalds 已提交
1148 1149 1150
	INIT_LIST_HEAD(&p->ptrace_children);
	INIT_LIST_HEAD(&p->ptrace_list);

N
Nick Piggin 已提交
1151 1152 1153
	/* Perform scheduler related setup. Assign this task to a CPU. */
	sched_fork(p, clone_flags);

L
Linus Torvalds 已提交
1154 1155 1156 1157
	/* Need tasklist lock for parent etc handling! */
	write_lock_irq(&tasklist_lock);

	/*
N
Nick Piggin 已提交
1158 1159 1160 1161 1162 1163 1164
	 * The task hasn't been attached yet, so its cpus_allowed mask will
	 * not be changed, nor will its assigned CPU.
	 *
	 * The cpus_allowed mask of the parent may have changed after it was
	 * copied first time - so re-copy it here, then check the child's CPU
	 * to ensure it is on a valid CPU (and if not, just force it back to
	 * parent's CPU). This avoids alot of nasty races.
L
Linus Torvalds 已提交
1165 1166
	 */
	p->cpus_allowed = current->cpus_allowed;
1167 1168
	if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed) ||
			!cpu_online(task_cpu(p))))
N
Nick Piggin 已提交
1169
		set_task_cpu(p, smp_processor_id());
L
Linus Torvalds 已提交
1170 1171 1172 1173 1174 1175 1176 1177

	/* CLONE_PARENT re-uses the old parent */
	if (clone_flags & (CLONE_PARENT|CLONE_THREAD))
		p->real_parent = current->real_parent;
	else
		p->real_parent = current;
	p->parent = p->real_parent;

1178
	spin_lock(&current->sighand->siglock);
1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195

	/*
	 * Process group and session signals need to be delivered to just the
	 * parent before the fork or both the parent and the child after the
	 * fork. Restart if a signal comes in before we add the new process to
	 * it's process group.
	 * A fatal signal pending means that current will exit, so the new
	 * thread can't slip out of an OOM kill (or normal SIGKILL).
 	 */
 	recalc_sigpending();
	if (signal_pending(current)) {
		spin_unlock(&current->sighand->siglock);
		write_unlock_irq(&tasklist_lock);
		retval = -ERESTARTNOINTR;
		goto bad_fork_cleanup_namespace;
	}

L
Linus Torvalds 已提交
1196 1197
	if (clone_flags & CLONE_THREAD) {
		p->group_leader = current->group_leader;
O
Oleg Nesterov 已提交
1198
		list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
L
Linus Torvalds 已提交
1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215

		if (!cputime_eq(current->signal->it_virt_expires,
				cputime_zero) ||
		    !cputime_eq(current->signal->it_prof_expires,
				cputime_zero) ||
		    current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY ||
		    !list_empty(&current->signal->cpu_timers[0]) ||
		    !list_empty(&current->signal->cpu_timers[1]) ||
		    !list_empty(&current->signal->cpu_timers[2])) {
			/*
			 * Have child wake up on its first tick to check
			 * for process CPU timers.
			 */
			p->it_prof_expires = jiffies_to_cputime(1);
		}
	}

1216 1217 1218 1219 1220
	/*
	 * inherit ioprio
	 */
	p->ioprio = current->ioprio;

1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232
	if (likely(p->pid)) {
		add_parent(p);
		if (unlikely(p->ptrace & PT_PTRACED))
			__ptrace_link(p, current->parent);

		if (thread_group_leader(p)) {
			p->signal->tty = current->signal->tty;
			p->signal->pgrp = process_group(current);
			p->signal->session = current->signal->session;
			attach_pid(p, PIDTYPE_PGID, process_group(p));
			attach_pid(p, PIDTYPE_SID, p->signal->session);

1233
			list_add_tail_rcu(&p->tasks, &init_task.tasks);
L
Linus Torvalds 已提交
1234
			__get_cpu_var(process_counts)++;
1235 1236 1237
		}
		attach_pid(p, PIDTYPE_PID, p->pid);
		nr_threads++;
L
Linus Torvalds 已提交
1238 1239 1240
	}

	total_forks++;
1241
	spin_unlock(&current->sighand->siglock);
L
Linus Torvalds 已提交
1242
	write_unlock_irq(&tasklist_lock);
1243
	proc_fork_connector(p);
L
Linus Torvalds 已提交
1244 1245 1246 1247 1248 1249 1250 1251 1252 1253
	return p;

bad_fork_cleanup_namespace:
	exit_namespace(p);
bad_fork_cleanup_keys:
	exit_keys(p);
bad_fork_cleanup_mm:
	if (p->mm)
		mmput(p->mm);
bad_fork_cleanup_signal:
1254
	cleanup_signal(p);
L
Linus Torvalds 已提交
1255
bad_fork_cleanup_sighand:
1256
	__cleanup_sighand(p->sighand);
L
Linus Torvalds 已提交
1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269
bad_fork_cleanup_fs:
	exit_fs(p); /* blocking */
bad_fork_cleanup_files:
	exit_files(p); /* blocking */
bad_fork_cleanup_semundo:
	exit_sem(p);
bad_fork_cleanup_audit:
	audit_free(p);
bad_fork_cleanup_security:
	security_task_free(p);
bad_fork_cleanup_policy:
#ifdef CONFIG_NUMA
	mpol_free(p->mempolicy);
P
Paul Jackson 已提交
1270
bad_fork_cleanup_cpuset:
L
Linus Torvalds 已提交
1271
#endif
P
Paul Jackson 已提交
1272
	cpuset_exit(p);
L
Linus Torvalds 已提交
1273 1274 1275 1276
bad_fork_cleanup:
	if (p->binfmt)
		module_put(p->binfmt->module);
bad_fork_cleanup_put_domain:
A
Al Viro 已提交
1277
	module_put(task_thread_info(p)->exec_domain->module);
L
Linus Torvalds 已提交
1278 1279 1280 1281 1282 1283
bad_fork_cleanup_count:
	put_group_info(p->group_info);
	atomic_dec(&p->user->processes);
	free_uid(p->user);
bad_fork_free:
	free_task(p);
1284 1285
fork_out:
	return ERR_PTR(retval);
L
Linus Torvalds 已提交
1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302
}

struct pt_regs * __devinit __attribute__((weak)) idle_regs(struct pt_regs *regs)
{
	memset(regs, 0, sizeof(struct pt_regs));
	return regs;
}

task_t * __devinit fork_idle(int cpu)
{
	task_t *task;
	struct pt_regs regs;

	task = copy_process(CLONE_VM, 0, idle_regs(&regs), 0, NULL, NULL, 0);
	if (!task)
		return ERR_PTR(-ENOMEM);
	init_idle(task, cpu);
1303

L
Linus Torvalds 已提交
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
	return task;
}

static inline int fork_traceflag (unsigned clone_flags)
{
	if (clone_flags & CLONE_UNTRACED)
		return 0;
	else if (clone_flags & CLONE_VFORK) {
		if (current->ptrace & PT_TRACE_VFORK)
			return PTRACE_EVENT_VFORK;
	} else if ((clone_flags & CSIGNAL) != SIGCHLD) {
		if (current->ptrace & PT_TRACE_CLONE)
			return PTRACE_EVENT_CLONE;
	} else if (current->ptrace & PT_TRACE_FORK)
		return PTRACE_EVENT_FORK;

	return 0;
}

/*
 *  Ok, this is the main fork-routine.
 *
 * It copies the process, and if successful kick-starts
 * it and waits for it to finish using the VM if required.
 */
long do_fork(unsigned long clone_flags,
	      unsigned long stack_start,
	      struct pt_regs *regs,
	      unsigned long stack_size,
	      int __user *parent_tidptr,
	      int __user *child_tidptr)
{
	struct task_struct *p;
	int trace = 0;
1338 1339
	struct pid *pid = alloc_pid();
	long nr;
L
Linus Torvalds 已提交
1340

1341
	if (!pid)
L
Linus Torvalds 已提交
1342
		return -EAGAIN;
1343
	nr = pid->nr;
L
Linus Torvalds 已提交
1344 1345 1346 1347 1348 1349
	if (unlikely(current->ptrace)) {
		trace = fork_traceflag (clone_flags);
		if (trace)
			clone_flags |= CLONE_PTRACE;
	}

1350
	p = copy_process(clone_flags, stack_start, regs, stack_size, parent_tidptr, child_tidptr, nr);
L
Linus Torvalds 已提交
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
	/*
	 * Do this prior waking up the new thread - the thread pointer
	 * might get invalid after that point, if the thread exits quickly.
	 */
	if (!IS_ERR(p)) {
		struct completion vfork;

		if (clone_flags & CLONE_VFORK) {
			p->vfork_done = &vfork;
			init_completion(&vfork);
		}

		if ((p->ptrace & PT_PTRACED) || (clone_flags & CLONE_STOPPED)) {
			/*
			 * We'll start up with an immediate SIGSTOP.
			 */
			sigaddset(&p->pending.signal, SIGSTOP);
			set_tsk_thread_flag(p, TIF_SIGPENDING);
		}

		if (!(clone_flags & CLONE_STOPPED))
			wake_up_new_task(p, clone_flags);
		else
			p->state = TASK_STOPPED;

		if (unlikely (trace)) {
1377
			current->ptrace_message = nr;
L
Linus Torvalds 已提交
1378 1379 1380 1381 1382 1383 1384 1385 1386
			ptrace_notify ((trace << 8) | SIGTRAP);
		}

		if (clone_flags & CLONE_VFORK) {
			wait_for_completion(&vfork);
			if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE))
				ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP);
		}
	} else {
1387 1388
		free_pid(pid);
		nr = PTR_ERR(p);
L
Linus Torvalds 已提交
1389
	}
1390
	return nr;
L
Linus Torvalds 已提交
1391 1392
}

1393 1394 1395 1396
#ifndef ARCH_MIN_MMSTRUCT_ALIGN
#define ARCH_MIN_MMSTRUCT_ALIGN 0
#endif

1397 1398 1399 1400 1401 1402 1403 1404 1405
static void sighand_ctor(void *data, kmem_cache_t *cachep, unsigned long flags)
{
	struct sighand_struct *sighand = data;

	if ((flags & (SLAB_CTOR_VERIFY | SLAB_CTOR_CONSTRUCTOR)) ==
					SLAB_CTOR_CONSTRUCTOR)
		spin_lock_init(&sighand->siglock);
}

L
Linus Torvalds 已提交
1406 1407 1408 1409
void __init proc_caches_init(void)
{
	sighand_cachep = kmem_cache_create("sighand_cache",
			sizeof(struct sighand_struct), 0,
1410 1411
			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU,
			sighand_ctor, NULL);
L
Linus Torvalds 已提交
1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424
	signal_cachep = kmem_cache_create("signal_cache",
			sizeof(struct signal_struct), 0,
			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
	files_cachep = kmem_cache_create("files_cache", 
			sizeof(struct files_struct), 0,
			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
	fs_cachep = kmem_cache_create("fs_cache", 
			sizeof(struct fs_struct), 0,
			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
	vm_area_cachep = kmem_cache_create("vm_area_struct",
			sizeof(struct vm_area_struct), 0,
			SLAB_PANIC, NULL, NULL);
	mm_cachep = kmem_cache_create("mm_struct",
1425
			sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
L
Linus Torvalds 已提交
1426 1427
			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
}
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


/*
 * Check constraints on flags passed to the unshare system call and
 * force unsharing of additional process context as appropriate.
 */
static inline void check_unshare_flags(unsigned long *flags_ptr)
{
	/*
	 * If unsharing a thread from a thread group, must also
	 * unshare vm.
	 */
	if (*flags_ptr & CLONE_THREAD)
		*flags_ptr |= CLONE_VM;

	/*
	 * If unsharing vm, must also unshare signal handlers.
	 */
	if (*flags_ptr & CLONE_VM)
		*flags_ptr |= CLONE_SIGHAND;

	/*
	 * If unsharing signal handlers and the task was created
	 * using CLONE_THREAD, then must unshare the thread
	 */
	if ((*flags_ptr & CLONE_SIGHAND) &&
	    (atomic_read(&current->signal->count) > 1))
		*flags_ptr |= CLONE_THREAD;

	/*
	 * If unsharing namespace, must also unshare filesystem information.
	 */
	if (*flags_ptr & CLONE_NEWNS)
		*flags_ptr |= CLONE_FS;
}

/*
 * Unsharing of tasks created with CLONE_THREAD is not supported yet
 */
static int unshare_thread(unsigned long unshare_flags)
{
	if (unshare_flags & CLONE_THREAD)
		return -EINVAL;

	return 0;
}

/*
1476
 * Unshare the filesystem structure if it is being shared
1477 1478 1479 1480 1481 1482
 */
static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
{
	struct fs_struct *fs = current->fs;

	if ((unshare_flags & CLONE_FS) &&
1483 1484 1485 1486 1487
	    (fs && atomic_read(&fs->count) > 1)) {
		*new_fsp = __copy_fs_struct(current->fs);
		if (!*new_fsp)
			return -ENOMEM;
	}
1488 1489 1490 1491 1492

	return 0;
}

/*
1493
 * Unshare the namespace structure if it is being shared
1494
 */
1495
static int unshare_namespace(unsigned long unshare_flags, struct namespace **new_nsp, struct fs_struct *new_fs)
1496 1497 1498 1499
{
	struct namespace *ns = current->namespace;

	if ((unshare_flags & CLONE_NEWNS) &&
1500 1501 1502 1503 1504 1505 1506 1507
	    (ns && atomic_read(&ns->count) > 1)) {
		if (!capable(CAP_SYS_ADMIN))
			return -EPERM;

		*new_nsp = dup_namespace(current, new_fs ? new_fs : current->fs);
		if (!*new_nsp)
			return -ENOMEM;
	}
1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527

	return 0;
}

/*
 * Unsharing of sighand for tasks created with CLONE_SIGHAND is not
 * supported yet
 */
static int unshare_sighand(unsigned long unshare_flags, struct sighand_struct **new_sighp)
{
	struct sighand_struct *sigh = current->sighand;

	if ((unshare_flags & CLONE_SIGHAND) &&
	    (sigh && atomic_read(&sigh->count) > 1))
		return -EINVAL;
	else
		return 0;
}

/*
1528
 * Unshare vm if it is being shared
1529 1530 1531 1532 1533 1534
 */
static int unshare_vm(unsigned long unshare_flags, struct mm_struct **new_mmp)
{
	struct mm_struct *mm = current->mm;

	if ((unshare_flags & CLONE_VM) &&
1535
	    (mm && atomic_read(&mm->mm_users) > 1)) {
1536
		return -EINVAL;
1537
	}
1538 1539 1540 1541 1542

	return 0;
}

/*
1543
 * Unshare file descriptor table if it is being shared
1544 1545 1546 1547
 */
static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp)
{
	struct files_struct *fd = current->files;
1548
	int error = 0;
1549 1550

	if ((unshare_flags & CLONE_FILES) &&
1551 1552 1553 1554 1555
	    (fd && atomic_read(&fd->count) > 1)) {
		*new_fdp = dup_fd(fd, &error);
		if (!*new_fdp)
			return error;
	}
1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591

	return 0;
}

/*
 * Unsharing of semundo for tasks created with CLONE_SYSVSEM is not
 * supported yet
 */
static int unshare_semundo(unsigned long unshare_flags, struct sem_undo_list **new_ulistp)
{
	if (unshare_flags & CLONE_SYSVSEM)
		return -EINVAL;

	return 0;
}

/*
 * unshare allows a process to 'unshare' part of the process
 * context which was originally shared using clone.  copy_*
 * functions used by do_fork() cannot be used here directly
 * because they modify an inactive task_struct that is being
 * constructed. Here we are modifying the current, active,
 * task_struct.
 */
asmlinkage long sys_unshare(unsigned long unshare_flags)
{
	int err = 0;
	struct fs_struct *fs, *new_fs = NULL;
	struct namespace *ns, *new_ns = NULL;
	struct sighand_struct *sigh, *new_sigh = NULL;
	struct mm_struct *mm, *new_mm = NULL, *active_mm = NULL;
	struct files_struct *fd, *new_fd = NULL;
	struct sem_undo_list *new_ulist = NULL;

	check_unshare_flags(&unshare_flags);

1592 1593 1594 1595 1596 1597
	/* Return -EINVAL for all unsupported flags */
	err = -EINVAL;
	if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND|
				CLONE_VM|CLONE_FILES|CLONE_SYSVSEM))
		goto bad_unshare_out;

1598 1599 1600 1601
	if ((err = unshare_thread(unshare_flags)))
		goto bad_unshare_out;
	if ((err = unshare_fs(unshare_flags, &new_fs)))
		goto bad_unshare_cleanup_thread;
1602
	if ((err = unshare_namespace(unshare_flags, &new_ns, new_fs)))
1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630
		goto bad_unshare_cleanup_fs;
	if ((err = unshare_sighand(unshare_flags, &new_sigh)))
		goto bad_unshare_cleanup_ns;
	if ((err = unshare_vm(unshare_flags, &new_mm)))
		goto bad_unshare_cleanup_sigh;
	if ((err = unshare_fd(unshare_flags, &new_fd)))
		goto bad_unshare_cleanup_vm;
	if ((err = unshare_semundo(unshare_flags, &new_ulist)))
		goto bad_unshare_cleanup_fd;

	if (new_fs || new_ns || new_sigh || new_mm || new_fd || new_ulist) {

		task_lock(current);

		if (new_fs) {
			fs = current->fs;
			current->fs = new_fs;
			new_fs = fs;
		}

		if (new_ns) {
			ns = current->namespace;
			current->namespace = new_ns;
			new_ns = ns;
		}

		if (new_sigh) {
			sigh = current->sighand;
1631
			rcu_assign_pointer(current->sighand, new_sigh);
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 1673 1674 1675 1676 1677
			new_sigh = sigh;
		}

		if (new_mm) {
			mm = current->mm;
			active_mm = current->active_mm;
			current->mm = new_mm;
			current->active_mm = new_mm;
			activate_mm(active_mm, new_mm);
			new_mm = mm;
		}

		if (new_fd) {
			fd = current->files;
			current->files = new_fd;
			new_fd = fd;
		}

		task_unlock(current);
	}

bad_unshare_cleanup_fd:
	if (new_fd)
		put_files_struct(new_fd);

bad_unshare_cleanup_vm:
	if (new_mm)
		mmput(new_mm);

bad_unshare_cleanup_sigh:
	if (new_sigh)
		if (atomic_dec_and_test(&new_sigh->count))
			kmem_cache_free(sighand_cachep, new_sigh);

bad_unshare_cleanup_ns:
	if (new_ns)
		put_namespace(new_ns);

bad_unshare_cleanup_fs:
	if (new_fs)
		put_fs_struct(new_fs);

bad_unshare_cleanup_thread:
bad_unshare_out:
	return err;
}