fork.c

/*
 *  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>
#include <linux/nsproxy.h>
#include <linux/capability.h>
#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>
#include <linux/rcupdate.h>
#include <linux/ptrace.h>
#include <linux/mount.h>
#include <linux/audit.h>
#include <linux/profile.h>
#include <linux/rmap.h>
#include <linux/acct.h>
#include <linux/tsacct_kern.h>
#include <linux/cn_proc.h>
#include <linux/delayacct.h>
#include <linux/taskstats_kern.h>
#include <linux/random.h>

#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 */

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) */
static kmem_cache_t *signal_cachep;

/* 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);
	rt_mutex_debug_task_free(tsk);
	free_task_struct(tsk);
}
EXPORT_SYMBOL(free_task);

void __put_task_struct(struct task_struct *tsk)
{
	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);
	delayacct_tsk_free(tsk);

	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;
	setup_thread_stack(tsk, orig);

#ifdef CONFIG_CC_STACKPROTECTOR
	tsk->stack_canary = get_random_int();
#endif

	/* One for us, one for whoever does the "release_task()" (usually parent) */
	atomic_set(&tsk->usage,2);
	atomic_set(&tsk->fs_excl, 0);
#ifdef CONFIG_BLK_DEV_IO_TRACE
	tsk->btrace_seq = 0;
#endif
	tsk->splice_pipe = NULL;
	return tsk;
}

#ifdef CONFIG_MMU
static inline int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
{
	struct vm_area_struct *mpnt, *tmp, **pprev;
	struct rb_node **rb_link, *rb_parent;
	int retval;
	unsigned long charge;
	struct mempolicy *pol;

	down_write(&oldmm->mmap_sem);
	flush_cache_mm(oldmm);
	/*
	 * Not linked in yet - no deadlock potential:
	 */
	down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING);

	mm->locked_vm = 0;
	mm->mmap = NULL;
	mm->mmap_cache = NULL;
	mm->free_area_cache = oldmm->mmap_base;
	mm->cached_hole_size = ~0UL;
	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;

	for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
		struct file *file;

		if (mpnt->vm_flags & VM_DONTCOPY) {
			long pages = vma_pages(mpnt);
			mm->total_vm -= pages;
			vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file,
								-pages);
			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, GFP_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);
		}

		/*
		 * Link in the new vma and copy the page table entries.
		 */
		*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++;
		retval = copy_page_range(mm, oldmm, mpnt);

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

		if (retval)
			goto out;
	}
	retval = 0;
out:
	up_write(&mm->mmap_sem);
	flush_tlb_mm(oldmm);
	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, GFP_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;
	set_mm_counter(mm, file_rss, 0);
	set_mm_counter(mm, anon_rss, 0);
	spin_lock_init(&mm->page_table_lock);
	rwlock_init(&mm->ioctx_list_lock);
	mm->ioctx_list = NULL;
	mm->free_area_cache = TASK_UNMAPPED_BASE;
	mm->cached_hole_size = ~0UL;

	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)
{
	might_sleep();

	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);
	}
}

/*
 * 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));

	/* Initializing for Swap token stuff */
	mm->token_priority = 0;
	mm->last_interval = 0;

	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;
}

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;
	mm = dup_mm(tsk);
	if (!mm)
		goto fail_nomem;

good_mm:
	/* Initializing for Swap token stuff */
	mm->token_priority = 0;
	mm->last_interval = 0;

	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;
}

static int count_open_files(struct fdtable *fdt)
{
	int size = fdt->max_fdset;
	int i;

	/* Find the last open fd */
	for (i = size/(8*sizeof(long)); i > 0; ) {
		if (fdt->open_fds->fds_bits[--i])
			break;
	}
	i = (i+1) * 8 * sizeof(long);
	return i;
}

static struct files_struct *alloc_files(void)
{
	struct files_struct *newf;
	struct fdtable *fdt;

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

	atomic_set(&newf->count, 1);

	spin_lock_init(&newf->file_lock);
	newf->next_fd = 0;
	fdt = &newf->fdtab;
	fdt->max_fds = NR_OPEN_DEFAULT;
	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;
	fdt->fd = &newf->fd_array[0];
	INIT_RCU_HEAD(&fdt->rcu);
	fdt->free_files = NULL;
	fdt->next = NULL;
	rcu_assign_pointer(newf->fdt, fdt);
out:
	return newf;
}

/*
 * Allocate a new files structure and copy contents from the
 * passed in files structure.
 * errorp will be valid only when the returned files_struct is NULL.
 */
static struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
{
	struct files_struct *newf;
	struct file **old_fds, **new_fds;
	int open_files, size, i, expand;
	struct fdtable *old_fdt, *new_fdt;

	*errorp = -ENOMEM;
	newf = alloc_files();
	if (!newf)
		goto out;

	spin_lock(&oldf->file_lock);
	old_fdt = files_fdtable(oldf);
	new_fdt = files_fdtable(newf);
	size = old_fdt->max_fdset;
	open_files = count_open_files(old_fdt);
	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.
	 */
	if (open_files > new_fdt->max_fdset) {
		new_fdt->max_fdset = 0;
		expand = 1;
	}
	if (open_files > new_fdt->max_fds) {
		new_fdt->max_fds = 0;
		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);
		*errorp = expand_files(newf, open_files-1);
		spin_unlock(&newf->file_lock);
		if (*errorp < 0)
			goto out_release;
		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.
		 */
		spin_lock(&oldf->file_lock);
		old_fdt = files_fdtable(oldf);
	}

	old_fds = old_fdt->fd;
	new_fds = new_fdt->fd;

	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);

	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.
			 */
			FD_CLR(open_files - i, new_fdt->open_fds);
		}
		rcu_assign_pointer(*new_fds++, f);
	}
	spin_unlock(&oldf->file_lock);

	/* compute the remainder to be cleared */
	size = (new_fdt->max_fds - open_files) * sizeof(struct file *);

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

	if (new_fdt->max_fdset > open_files) {
		int left = (new_fdt->max_fdset-open_files)/8;
		int start = open_files / (8 * sizeof(unsigned long));

		memset(&new_fdt->open_fds->fds_bits[start], 0, left);
		memset(&new_fdt->close_on_exec->fds_bits[start], 0, left);
	}

out:
	return newf;

out_release:
	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);
	kmem_cache_free(files_cachep, newf);
	return NULL;
}

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;
}

/*
 *	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;

	BUG_ON(!files);

	/* 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);
	rcu_assign_pointer(tsk->sighand, sig);
	if (!sig)
		return -ENOMEM;
	atomic_set(&sig->count, 1);
	memcpy(sig->action, current->sighand->action, sizeof(sig->action));
	return 0;
}

void __cleanup_sighand(struct sighand_struct *sighand)
{
	if (atomic_dec_and_test(&sighand->count))
		kmem_cache_free(sighand_cachep, sighand);
}

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);
		taskstats_tgid_alloc(current);
		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);

	hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_REL);
	sig->it_real_incr.tv64 = 0;
	sig->real_timer.function = it_real_fn;
	sig->tsk = tsk;

	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]);
	taskstats_tgid_init(sig);

	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);
	}
	acct_init_pacct(&sig->pacct);

	return 0;
}

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);
}

static inline void copy_flags(unsigned long clone_flags, struct task_struct *p)
{
	unsigned long new_flags = p->flags;

	new_flags &= ~(PF_SUPERPRIV | PF_NOFREEZE);
	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;
}

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
}

/*
 * 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 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)
{
	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;

	rt_mutex_init_task(p);

#ifdef CONFIG_TRACE_IRQFLAGS
	DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
	DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
#endif
	retval = -EAGAIN;