fork.c 42.2 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>
S
Serge E. Hallyn 已提交
30
#include <linux/nsproxy.h>
31
#include <linux/capability.h>
L
Linus Torvalds 已提交
32 33 34 35 36 37 38
#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>
39
#include <linux/rcupdate.h>
L
Linus Torvalds 已提交
40 41 42 43 44 45
#include <linux/ptrace.h>
#include <linux/mount.h>
#include <linux/audit.h>
#include <linux/profile.h>
#include <linux/rmap.h>
#include <linux/acct.h>
46
#include <linux/tsacct_kern.h>
M
Matt Helsley 已提交
47
#include <linux/cn_proc.h>
48
#include <linux/delayacct.h>
49
#include <linux/taskstats_kern.h>
50
#include <linux/random.h>
L
Linus Torvalds 已提交
51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68

#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;

69
__cacheline_aligned DEFINE_RWLOCK(tasklist_lock);  /* outer */
L
Linus Torvalds 已提交
70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88

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) */
89
static kmem_cache_t *signal_cachep;
L
Linus Torvalds 已提交
90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108

/* 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
109
	rt_mutex_debug_task_free(tsk);
L
Linus Torvalds 已提交
110 111 112 113
	free_task_struct(tsk);
}
EXPORT_SYMBOL(free_task);

114
void __put_task_struct(struct task_struct *tsk)
L
Linus Torvalds 已提交
115 116 117 118 119 120 121 122
{
	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);
123
	delayacct_tsk_free(tsk);
L
Linus Torvalds 已提交
124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178

	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;
179
	setup_thread_stack(tsk, orig);
L
Linus Torvalds 已提交
180

181 182 183 184
#ifdef CONFIG_CC_STACKPROTECTOR
	tsk->stack_canary = get_random_int();
#endif

L
Linus Torvalds 已提交
185 186
	/* One for us, one for whoever does the "release_task()" (usually parent) */
	atomic_set(&tsk->usage,2);
187
	atomic_set(&tsk->fs_excl, 0);
188
#ifdef CONFIG_BLK_DEV_IO_TRACE
189
	tsk->btrace_seq = 0;
190
#endif
191
	tsk->splice_pipe = NULL;
L
Linus Torvalds 已提交
192 193 194 195
	return tsk;
}

#ifdef CONFIG_MMU
H
Hugh Dickins 已提交
196
static inline int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
L
Linus Torvalds 已提交
197
{
H
Hugh Dickins 已提交
198
	struct vm_area_struct *mpnt, *tmp, **pprev;
L
Linus Torvalds 已提交
199 200 201 202 203 204
	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
205
	flush_cache_mm(oldmm);
206 207 208 209
	/*
	 * Not linked in yet - no deadlock potential:
	 */
	down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING);
210

L
Linus Torvalds 已提交
211 212 213 214
	mm->locked_vm = 0;
	mm->mmap = NULL;
	mm->mmap_cache = NULL;
	mm->free_area_cache = oldmm->mmap_base;
215
	mm->cached_hole_size = ~0UL;
L
Linus Torvalds 已提交
216 217 218 219 220 221 222
	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
223
	for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
L
Linus Torvalds 已提交
224 225 226
		struct file *file;

		if (mpnt->vm_flags & VM_DONTCOPY) {
227 228
			long pages = vma_pages(mpnt);
			mm->total_vm -= pages;
229
			vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file,
230
								-pages);
L
Linus Torvalds 已提交
231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269
			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);
		}

		/*
270
		 * Link in the new vma and copy the page table entries.
L
Linus Torvalds 已提交
271 272 273 274 275 276 277 278 279
		 */
		*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++;
280
		retval = copy_page_range(mm, oldmm, mpnt);
L
Linus Torvalds 已提交
281 282 283 284 285 286 287 288 289

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

		if (retval)
			goto out;
	}
	retval = 0;
out:
290
	up_write(&mm->mmap_sem);
H
Hugh Dickins 已提交
291
	flush_tlb_mm(oldmm);
L
Linus Torvalds 已提交
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
	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;
335
	set_mm_counter(mm, file_rss, 0);
H
Hugh Dickins 已提交
336
	set_mm_counter(mm, anon_rss, 0);
L
Linus Torvalds 已提交
337 338 339 340
	spin_lock_init(&mm->page_table_lock);
	rwlock_init(&mm->ioctx_list_lock);
	mm->ioctx_list = NULL;
	mm->free_area_cache = TASK_UNMAPPED_BASE;
341
	mm->cached_hole_size = ~0UL;
L
Linus Torvalds 已提交
342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383

	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
384 385
	might_sleep();

L
Linus Torvalds 已提交
386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463
	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);
	}
}

464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512
/*
 * 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
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
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;
540
	mm = dup_mm(tsk);
L
Linus Torvalds 已提交
541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596
	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;
}

597
static int count_open_files(struct fdtable *fdt)
L
Linus Torvalds 已提交
598
{
599
	int size = fdt->max_fdset;
L
Linus Torvalds 已提交
600 601 602 603
	int i;

	/* Find the last open fd */
	for (i = size/(8*sizeof(long)); i > 0; ) {
604
		if (fdt->open_fds->fds_bits[--i])
L
Linus Torvalds 已提交
605 606 607 608 609 610
			break;
	}
	i = (i+1) * 8 * sizeof(long);
	return i;
}

611 612 613 614 615 616 617 618 619 620 621 622
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);
623
	newf->next_fd = 0;
624
	fdt = &newf->fdtab;
625
	fdt->max_fds = NR_OPEN_DEFAULT;
626 627 628
	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;
629
	fdt->fd = &newf->fd_array[0];
630 631 632 633
	INIT_RCU_HEAD(&fdt->rcu);
	fdt->free_files = NULL;
	fdt->next = NULL;
	rcu_assign_pointer(newf->fdt, fdt);
634 635 636 637
out:
	return newf;
}

638 639 640
/*
 * Allocate a new files structure and copy contents from the
 * passed in files structure.
P
Prasanna Meda 已提交
641
 * errorp will be valid only when the returned files_struct is NULL.
642 643
 */
static struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
L
Linus Torvalds 已提交
644
{
645
	struct files_struct *newf;
L
Linus Torvalds 已提交
646
	struct file **old_fds, **new_fds;
647
	int open_files, size, i, expand;
648
	struct fdtable *old_fdt, *new_fdt;
L
Linus Torvalds 已提交
649

P
Prasanna Meda 已提交
650
	*errorp = -ENOMEM;
651 652
	newf = alloc_files();
	if (!newf)
L
Linus Torvalds 已提交
653 654 655
		goto out;

	spin_lock(&oldf->file_lock);
656 657 658
	old_fdt = files_fdtable(oldf);
	new_fdt = files_fdtable(newf);
	size = old_fdt->max_fdset;
659
	open_files = count_open_files(old_fdt);
L
Linus Torvalds 已提交
660 661 662 663 664 665
	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.
	 */
666 667
	if (open_files > new_fdt->max_fdset) {
		new_fdt->max_fdset = 0;
L
Linus Torvalds 已提交
668 669
		expand = 1;
	}
670 671
	if (open_files > new_fdt->max_fds) {
		new_fdt->max_fds = 0;
L
Linus Torvalds 已提交
672 673 674 675 676 677 678
		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);
679
		*errorp = expand_files(newf, open_files-1);
L
Linus Torvalds 已提交
680
		spin_unlock(&newf->file_lock);
681
		if (*errorp < 0)
L
Linus Torvalds 已提交
682
			goto out_release;
683 684 685 686 687 688
		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
689
		spin_lock(&oldf->file_lock);
690
		old_fdt = files_fdtable(oldf);
L
Linus Torvalds 已提交
691 692
	}

693 694
	old_fds = old_fdt->fd;
	new_fds = new_fdt->fd;
L
Linus Torvalds 已提交
695

696 697
	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
698 699 700 701 702 703 704 705 706 707 708 709

	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.
			 */
710
			FD_CLR(open_files - i, new_fdt->open_fds);
L
Linus Torvalds 已提交
711
		}
712
		rcu_assign_pointer(*new_fds++, f);
L
Linus Torvalds 已提交
713 714 715 716
	}
	spin_unlock(&oldf->file_lock);

	/* compute the remainder to be cleared */
717
	size = (new_fdt->max_fds - open_files) * sizeof(struct file *);
L
Linus Torvalds 已提交
718 719 720 721

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

722 723
	if (new_fdt->max_fdset > open_files) {
		int left = (new_fdt->max_fdset-open_files)/8;
L
Linus Torvalds 已提交
724 725
		int start = open_files / (8 * sizeof(unsigned long));

726 727
		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
728 729 730
	}

out:
731
	return newf;
L
Linus Torvalds 已提交
732 733

out_release:
734 735 736
	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
737
	kmem_cache_free(files_cachep, newf);
738
	return NULL;
L
Linus Torvalds 已提交
739 740
}

741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773
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
774 775 776 777 778 779 780 781 782 783 784
/*
 *	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;

785
	BUG_ON(!files);
L
Linus Torvalds 已提交
786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810

	/* 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
811
	rcu_assign_pointer(tsk->sighand, sig);
L
Linus Torvalds 已提交
812 813 814 815 816 817 818
	if (!sig)
		return -ENOMEM;
	atomic_set(&sig->count, 1);
	memcpy(sig->action, current->sighand->action, sizeof(sig->action));
	return 0;
}

819
void __cleanup_sighand(struct sighand_struct *sighand)
820 821 822 823 824
{
	if (atomic_dec_and_test(&sighand->count))
		kmem_cache_free(sighand_cachep, sighand);
}

L
Linus Torvalds 已提交
825 826 827 828 829 830 831 832
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);
833
		taskstats_tgid_alloc(current);
L
Linus Torvalds 已提交
834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857
		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);

858
	hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_REL);
859
	sig->it_real_incr.tv64 = 0;
L
Linus Torvalds 已提交
860
	sig->real_timer.function = it_real_fn;
861
	sig->tsk = tsk;
L
Linus Torvalds 已提交
862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877

	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]);
878
	taskstats_tgid_init(sig);
L
Linus Torvalds 已提交
879 880 881 882 883 884 885 886 887 888 889 890 891

	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);
	}
892
	acct_init_pacct(&sig->pacct);
L
Linus Torvalds 已提交
893 894 895 896

	return 0;
}

897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912
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
913 914 915 916
static inline void copy_flags(unsigned long clone_flags, struct task_struct *p)
{
	unsigned long new_flags = p->flags;

917
	new_flags &= ~(PF_SUPERPRIV | PF_NOFREEZE);
L
Linus Torvalds 已提交
918 919 920 921 922 923 924 925 926 927 928 929 930
	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
931 932 933 934 935 936 937 938 939
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
940 941 942 943 944 945 946 947
/*
 * 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.
 */
948 949 950 951 952 953 954
static struct task_struct *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)
L
Linus Torvalds 已提交
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
{
	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;

986 987
	rt_mutex_init_task(p);

988 989 990 991
#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
992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011
	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
1012
	if (!try_module_get(task_thread_info(p)->exec_domain->module))
L
Linus Torvalds 已提交
1013 1014 1015 1016 1017 1018
		goto bad_fork_cleanup_count;

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

	p->did_exec = 0;
1019
	delayacct_tsk_init(p);	/* Must remain after dup_task_struct() */
L
Linus Torvalds 已提交
1020 1021 1022 1023 1024
	copy_flags(clone_flags, p);
	p->pid = pid;
	retval = -EFAULT;
	if (clone_flags & CLONE_PARENT_SETTID)
		if (put_user(p->pid, parent_tidptr))
1025
			goto bad_fork_cleanup_delays_binfmt;
L
Linus Torvalds 已提交
1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056

	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
1057
	cpuset_fork(p);
L
Linus Torvalds 已提交
1058 1059 1060 1061 1062
#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
1063
 		goto bad_fork_cleanup_cpuset;
L
Linus Torvalds 已提交
1064
 	}
1065
	mpol_fix_fork_child_flag(p);
L
Linus Torvalds 已提交
1066
#endif
1067 1068
#ifdef CONFIG_TRACE_IRQFLAGS
	p->irq_events = 0;
1069 1070 1071
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
	p->hardirqs_enabled = 1;
#else
1072
	p->hardirqs_enabled = 0;
1073
#endif
1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085
	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
1086 1087 1088 1089 1090
#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
1091

1092 1093 1094 1095
#ifdef CONFIG_DEBUG_MUTEXES
	p->blocked_on = NULL; /* not blocked yet */
#endif

L
Linus Torvalds 已提交
1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118
	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;
S
Serge E. Hallyn 已提交
1119
	if ((retval = copy_namespaces(clone_flags, p)))
L
Linus Torvalds 已提交
1120 1121 1122
		goto bad_fork_cleanup_keys;
	retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
	if (retval)
1123
		goto bad_fork_cleanup_namespaces;
L
Linus Torvalds 已提交
1124 1125 1126 1127 1128 1129

	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;
1130 1131 1132 1133
	p->robust_list = NULL;
#ifdef CONFIG_COMPAT
	p->compat_robust_list = NULL;
#endif
1134 1135 1136
	INIT_LIST_HEAD(&p->pi_state_list);
	p->pi_state_cache = NULL;

1137 1138 1139 1140 1141 1142
	/*
	 * 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
1143 1144 1145 1146 1147
	/*
	 * Syscall tracing should be turned off in the child regardless
	 * of CLONE_PTRACE.
	 */
	clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
1148 1149 1150
#ifdef TIF_SYSCALL_EMU
	clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
#endif
L
Linus Torvalds 已提交
1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165

	/* 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
1166
	INIT_LIST_HEAD(&p->thread_group);
L
Linus Torvalds 已提交
1167 1168 1169
	INIT_LIST_HEAD(&p->ptrace_children);
	INIT_LIST_HEAD(&p->ptrace_list);

N
Nick Piggin 已提交
1170 1171 1172
	/* Perform scheduler related setup. Assign this task to a CPU. */
	sched_fork(p, clone_flags);

L
Linus Torvalds 已提交
1173 1174 1175
	/* Need tasklist lock for parent etc handling! */
	write_lock_irq(&tasklist_lock);

1176 1177 1178
	/* for sys_ioprio_set(IOPRIO_WHO_PGRP) */
	p->ioprio = current->ioprio;

L
Linus Torvalds 已提交
1179
	/*
N
Nick Piggin 已提交
1180 1181 1182 1183 1184 1185 1186
	 * 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
1187 1188
	 */
	p->cpus_allowed = current->cpus_allowed;
1189 1190
	if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed) ||
			!cpu_online(task_cpu(p))))
N
Nick Piggin 已提交
1191
		set_task_cpu(p, smp_processor_id());
L
Linus Torvalds 已提交
1192 1193 1194 1195 1196 1197 1198 1199

	/* 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;

1200
	spin_lock(&current->sighand->siglock);
1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214

	/*
	 * 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;
1215
		goto bad_fork_cleanup_namespaces;
1216 1217
	}

L
Linus Torvalds 已提交
1218 1219
	if (clone_flags & CLONE_THREAD) {
		p->group_leader = current->group_leader;
O
Oleg Nesterov 已提交
1220
		list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
L
Linus Torvalds 已提交
1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237

		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);
		}
	}

1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249
	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);

1250
			list_add_tail_rcu(&p->tasks, &init_task.tasks);
L
Linus Torvalds 已提交
1251
			__get_cpu_var(process_counts)++;
1252 1253 1254
		}
		attach_pid(p, PIDTYPE_PID, p->pid);
		nr_threads++;
L
Linus Torvalds 已提交
1255 1256 1257
	}

	total_forks++;
1258
	spin_unlock(&current->sighand->siglock);
L
Linus Torvalds 已提交
1259
	write_unlock_irq(&tasklist_lock);
1260
	proc_fork_connector(p);
L
Linus Torvalds 已提交
1261 1262
	return p;

S
Serge E. Hallyn 已提交
1263 1264
bad_fork_cleanup_namespaces:
	exit_task_namespaces(p);
L
Linus Torvalds 已提交
1265 1266 1267 1268 1269 1270
bad_fork_cleanup_keys:
	exit_keys(p);
bad_fork_cleanup_mm:
	if (p->mm)
		mmput(p->mm);
bad_fork_cleanup_signal:
1271
	cleanup_signal(p);
L
Linus Torvalds 已提交
1272
bad_fork_cleanup_sighand:
1273
	__cleanup_sighand(p->sighand);
L
Linus Torvalds 已提交
1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286
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
1287
bad_fork_cleanup_cpuset:
L
Linus Torvalds 已提交
1288
#endif
P
Paul Jackson 已提交
1289
	cpuset_exit(p);
1290 1291
bad_fork_cleanup_delays_binfmt:
	delayacct_tsk_free(p);
L
Linus Torvalds 已提交
1292 1293 1294
	if (p->binfmt)
		module_put(p->binfmt->module);
bad_fork_cleanup_put_domain:
A
Al Viro 已提交
1295
	module_put(task_thread_info(p)->exec_domain->module);
L
Linus Torvalds 已提交
1296 1297 1298 1299 1300 1301
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);
1302 1303
fork_out:
	return ERR_PTR(retval);
L
Linus Torvalds 已提交
1304 1305 1306 1307 1308 1309 1310 1311
}

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

1312
struct task_struct * __devinit fork_idle(int cpu)
L
Linus Torvalds 已提交
1313
{
1314
	struct task_struct *task;
L
Linus Torvalds 已提交
1315 1316 1317 1318 1319 1320
	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);
1321

L
Linus Torvalds 已提交
1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355
	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;
1356 1357
	struct pid *pid = alloc_pid();
	long nr;
L
Linus Torvalds 已提交
1358

1359
	if (!pid)
L
Linus Torvalds 已提交
1360
		return -EAGAIN;
1361
	nr = pid->nr;
L
Linus Torvalds 已提交
1362 1363 1364 1365 1366 1367
	if (unlikely(current->ptrace)) {
		trace = fork_traceflag (clone_flags);
		if (trace)
			clone_flags |= CLONE_PTRACE;
	}

1368
	p = copy_process(clone_flags, stack_start, regs, stack_size, parent_tidptr, child_tidptr, nr);
L
Linus Torvalds 已提交
1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394
	/*
	 * 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)) {
1395
			current->ptrace_message = nr;
L
Linus Torvalds 已提交
1396 1397 1398 1399 1400
			ptrace_notify ((trace << 8) | SIGTRAP);
		}

		if (clone_flags & CLONE_VFORK) {
			wait_for_completion(&vfork);
1401 1402
			if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE)) {
				current->ptrace_message = nr;
L
Linus Torvalds 已提交
1403
				ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP);
1404
			}
L
Linus Torvalds 已提交
1405 1406
		}
	} else {
1407 1408
		free_pid(pid);
		nr = PTR_ERR(p);
L
Linus Torvalds 已提交
1409
	}
1410
	return nr;
L
Linus Torvalds 已提交
1411 1412
}

1413 1414 1415 1416
#ifndef ARCH_MIN_MMSTRUCT_ALIGN
#define ARCH_MIN_MMSTRUCT_ALIGN 0
#endif

1417 1418 1419 1420 1421 1422 1423 1424 1425
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
1426 1427 1428 1429
void __init proc_caches_init(void)
{
	sighand_cachep = kmem_cache_create("sighand_cache",
			sizeof(struct sighand_struct), 0,
1430 1431
			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU,
			sighand_ctor, NULL);
L
Linus Torvalds 已提交
1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444
	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",
1445
			sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
L
Linus Torvalds 已提交
1446 1447
			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
}
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 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495


/*
 * 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;
}

/*
1496
 * Unshare the filesystem structure if it is being shared
1497 1498 1499 1500 1501 1502
 */
static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
{
	struct fs_struct *fs = current->fs;

	if ((unshare_flags & CLONE_FS) &&
1503 1504 1505 1506 1507
	    (fs && atomic_read(&fs->count) > 1)) {
		*new_fsp = __copy_fs_struct(current->fs);
		if (!*new_fsp)
			return -ENOMEM;
	}
1508 1509 1510 1511 1512

	return 0;
}

/*
1513
 * Unshare the namespace structure if it is being shared
1514
 */
1515
static int unshare_namespace(unsigned long unshare_flags, struct namespace **new_nsp, struct fs_struct *new_fs)
1516
{
1517
	struct namespace *ns = current->nsproxy->namespace;
1518

1519
	if ((unshare_flags & CLONE_NEWNS) && ns) {
1520 1521 1522 1523 1524 1525 1526
		if (!capable(CAP_SYS_ADMIN))
			return -EPERM;

		*new_nsp = dup_namespace(current, new_fs ? new_fs : current->fs);
		if (!*new_nsp)
			return -ENOMEM;
	}
1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546

	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;
}

/*
1547
 * Unshare vm if it is being shared
1548 1549 1550 1551 1552 1553
 */
static int unshare_vm(unsigned long unshare_flags, struct mm_struct **new_mmp)
{
	struct mm_struct *mm = current->mm;

	if ((unshare_flags & CLONE_VM) &&
1554
	    (mm && atomic_read(&mm->mm_users) > 1)) {
1555
		return -EINVAL;
1556
	}
1557 1558 1559 1560 1561

	return 0;
}

/*
1562
 * Unshare file descriptor table if it is being shared
1563 1564 1565 1566
 */
static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp)
{
	struct files_struct *fd = current->files;
1567
	int error = 0;
1568 1569

	if ((unshare_flags & CLONE_FILES) &&
1570 1571 1572 1573 1574
	    (fd && atomic_read(&fd->count) > 1)) {
		*new_fdp = dup_fd(fd, &error);
		if (!*new_fdp)
			return error;
	}
1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590

	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;
}

K
Kirill Korotaev 已提交
1591 1592 1593 1594 1595 1596 1597 1598 1599 1600
#ifndef CONFIG_IPC_NS
static inline int unshare_ipcs(unsigned long flags, struct ipc_namespace **ns)
{
	if (flags & CLONE_NEWIPC)
		return -EINVAL;

	return 0;
}
#endif

1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617
/*
 * 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;
1618
	struct nsproxy *new_nsproxy = NULL, *old_nsproxy = NULL;
1619
	struct uts_namespace *uts, *new_uts = NULL;
K
Kirill Korotaev 已提交
1620
	struct ipc_namespace *ipc, *new_ipc = NULL;
1621 1622 1623

	check_unshare_flags(&unshare_flags);

1624 1625 1626
	/* Return -EINVAL for all unsupported flags */
	err = -EINVAL;
	if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND|
K
Kirill Korotaev 已提交
1627 1628
				CLONE_VM|CLONE_FILES|CLONE_SYSVSEM|
				CLONE_NEWUTS|CLONE_NEWIPC))
1629 1630
		goto bad_unshare_out;

1631 1632 1633 1634
	if ((err = unshare_thread(unshare_flags)))
		goto bad_unshare_out;
	if ((err = unshare_fs(unshare_flags, &new_fs)))
		goto bad_unshare_cleanup_thread;
1635
	if ((err = unshare_namespace(unshare_flags, &new_ns, new_fs)))
1636 1637 1638 1639 1640 1641 1642 1643 1644
		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;
1645 1646
	if ((err = unshare_utsname(unshare_flags, &new_uts)))
		goto bad_unshare_cleanup_semundo;
K
Kirill Korotaev 已提交
1647 1648
	if ((err = unshare_ipcs(unshare_flags, &new_ipc)))
		goto bad_unshare_cleanup_uts;
1649

K
Kirill Korotaev 已提交
1650
	if (new_ns || new_uts || new_ipc) {
S
Serge E. Hallyn 已提交
1651 1652 1653 1654
		old_nsproxy = current->nsproxy;
		new_nsproxy = dup_namespaces(old_nsproxy);
		if (!new_nsproxy) {
			err = -ENOMEM;
K
Kirill Korotaev 已提交
1655
			goto bad_unshare_cleanup_ipc;
S
Serge E. Hallyn 已提交
1656
		}
1657 1658 1659
	}

	if (new_fs || new_ns || new_sigh || new_mm || new_fd || new_ulist ||
K
Kirill Korotaev 已提交
1660
				new_uts || new_ipc) {
S
Serge E. Hallyn 已提交
1661

1662
		task_lock(current);
1663 1664 1665 1666 1667

		if (new_nsproxy) {
			current->nsproxy = new_nsproxy;
			new_nsproxy = old_nsproxy;
		}
1668 1669 1670 1671 1672 1673 1674 1675

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

		if (new_ns) {
1676 1677
			ns = current->nsproxy->namespace;
			current->nsproxy->namespace = new_ns;
1678 1679 1680 1681 1682
			new_ns = ns;
		}

		if (new_sigh) {
			sigh = current->sighand;
1683
			rcu_assign_pointer(current->sighand, new_sigh);
1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701
			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;
		}

1702 1703 1704 1705 1706 1707
		if (new_uts) {
			uts = current->nsproxy->uts_ns;
			current->nsproxy->uts_ns = new_uts;
			new_uts = uts;
		}

K
Kirill Korotaev 已提交
1708 1709 1710 1711 1712 1713
		if (new_ipc) {
			ipc = current->nsproxy->ipc_ns;
			current->nsproxy->ipc_ns = new_ipc;
			new_ipc = ipc;
		}

1714 1715 1716
		task_unlock(current);
	}

1717 1718 1719
	if (new_nsproxy)
		put_nsproxy(new_nsproxy);

K
Kirill Korotaev 已提交
1720 1721 1722 1723
bad_unshare_cleanup_ipc:
	if (new_ipc)
		put_ipc_ns(new_ipc);

1724 1725 1726 1727
bad_unshare_cleanup_uts:
	if (new_uts)
		put_uts_ns(new_uts);

S
Serge E. Hallyn 已提交
1728
bad_unshare_cleanup_semundo:
1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753
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;
}