exec.c

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

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

#include <linux/slab.h>
#include <linux/file.h>
#include <linux/mman.h>
#include <linux/a.out.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/spinlock.h>
#include <linux/key.h>
#include <linux/personality.h>
#include <linux/binfmts.h>
#include <linux/swap.h>
#include <linux/utsname.h>
#include <linux/pid_namespace.h>
#include <linux/module.h>
#include <linux/namei.h>
#include <linux/proc_fs.h>
#include <linux/ptrace.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/rmap.h>
#include <linux/tsacct_kern.h>
#include <linux/cn_proc.h>
#include <linux/audit.h>

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

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

int core_uses_pid;
char core_pattern[CORENAME_MAX_SIZE] = "core";
int suid_dumpable = 0;

EXPORT_SYMBOL(suid_dumpable);
/* The maximal length of core_pattern is also specified in sysctl.c */

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

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

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

EXPORT_SYMBOL(register_binfmt);

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

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

EXPORT_SYMBOL(unregister_binfmt);

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

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

	error = __user_path_lookup_open(library, LOOKUP_FOLLOW, &nd, FMODE_READ|FMODE_EXEC);
	if (error)
		goto out;

	error = -EACCES;
	if (nd.mnt->mnt_flags & MNT_NOEXEC)
		goto exit;
	error = -EINVAL;
	if (!S_ISREG(nd.dentry->d_inode->i_mode))
		goto exit;

	error = vfs_permission(&nd, MAY_READ | MAY_EXEC);
	if (error)
		goto exit;

	file = nameidata_to_filp(&nd, O_RDONLY);
	error = PTR_ERR(file);
	if (IS_ERR(file))
		goto out;

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

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

#ifdef CONFIG_MMU

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

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

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

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

	return page;
}

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

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

static void free_arg_pages(struct linux_binprm *bprm)
{
}

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

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

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

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

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

	vma->vm_flags = VM_STACK_FLAGS;
	vma->vm_page_prot = protection_map[vma->vm_flags & 0x7];
	err = insert_vm_struct(mm, vma);
	if (err) {
		up_write(&mm->mmap_sem);
		goto err;
	}

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

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

	return 0;

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

	return err;
}

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

#else

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

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

	return page;
}

static void put_arg_page(struct page *page)
{
}

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

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

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

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

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

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

#endif /* CONFIG_MMU */

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

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

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

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

	return 0;

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

	return err;
}

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

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

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

/*
 * 'copy_strings()' copies argument/environment strings from the old
 * processes's memory to the new process's stack.  The call to get_user_pages()
 * ensures the destination page is created and not swapped out.
 */
static int copy_strings(int argc, char __user * __user * argv,
			struct linux_binprm *bprm)
{
	struct page *kmapped_page = NULL;
	char *kaddr = NULL;
	unsigned long kpos = 0;
	int ret;

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

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

		if (!valid_arg_len(bprm, len)) {
			ret = -E2BIG;
			goto out;
		}

		/* We're going to work our way backwords. */
		pos = bprm->p;
		str += len;
		bprm->p -= len;

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

			offset = pos % PAGE_SIZE;
			if (offset == 0)
				offset = PAGE_SIZE;

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

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

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

				page = get_arg_page(bprm, pos, 1);
				if (!page) {
					ret = -E2BIG;
					goto out;
				}

				if (kmapped_page) {
					flush_kernel_dcache_page(kmapped_page);
					kunmap(kmapped_page);
					put_arg_page(kmapped_page);
				}
				kmapped_page = page;
				kaddr = kmap(kmapped_page);
				kpos = pos & PAGE_MASK;
				flush_arg_page(bprm, kpos, kmapped_page);
			}
			if (copy_from_user(kaddr+offset, str, bytes_to_copy)) {
				ret = -EFAULT;
				goto out;
			}
		}
	}
	ret = 0;
out:
	if (kmapped_page) {
		flush_kernel_dcache_page(kmapped_page);
		kunmap(kmapped_page);
		put_arg_page(kmapped_page);
	}
	return ret;
}

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

#ifdef CONFIG_MMU

/*
 * During bprm_mm_init(), we create a temporary stack at STACK_TOP_MAX.  Once
 * the binfmt code determines where the new stack should reside, we shift it to
 * its final location.  The process proceeds as follows:
 *
 * 1) Use shift to calculate the new vma endpoints.
 * 2) Extend vma to cover both the old and new ranges.  This ensures the
 *    arguments passed to subsequent functions are consistent.
 * 3) Move vma's page tables to the new range.
 * 4) Free up any cleared pgd range.
 * 5) Shrink the vma to cover only the new range.
 */
static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
{
	struct mm_struct *mm = vma->vm_mm;
	unsigned long old_start = vma->vm_start;
	unsigned long old_end = vma->vm_end;
	unsigned long length = old_end - old_start;
	unsigned long new_start = old_start - shift;
	unsigned long new_end = old_end - shift;
	struct mmu_gather *tlb;

	BUG_ON(new_start > new_end);

	/*
	 * ensure there are no vmas between where we want to go
	 * and where we are
	 */
	if (vma != find_vma(mm, new_start))
		return -EFAULT;

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

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

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

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

	return 0;
}

#define EXTRA_STACK_VM_PAGES	20	/* random */

/*
 * Finalizes the stack vm_area_struct. The flags and permissions are updated,
 * the stack is optionally relocated, and some extra space is added.
 */
int setup_arg_pages(struct linux_binprm *bprm,
		    unsigned long stack_top,
		    int executable_stack)
{
	unsigned long ret;
	unsigned long stack_shift;
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma = bprm->vma;
	struct vm_area_struct *prev = NULL;
	unsigned long vm_flags;
	unsigned long stack_base;

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

	/* Make sure we didn't let the argument array grow too large. */
	if (vma->vm_end - vma->vm_start > stack_base)
		return -ENOMEM;

	stack_base = PAGE_ALIGN(stack_top - stack_base);

	stack_shift = vma->vm_start - stack_base;
	mm->arg_start = bprm->p - stack_shift;
	bprm->p = vma->vm_end - stack_shift;
#else
	stack_top = arch_align_stack(stack_top);
	stack_top = PAGE_ALIGN(stack_top);
	stack_shift = vma->vm_end - stack_top;

	bprm->p -= stack_shift;
	mm->arg_start = bprm->p;
#endif

	if (bprm->loader)
		bprm->loader -= stack_shift;
	bprm->exec -= stack_shift;

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

	/*
	 * Adjust stack execute permissions; explicitly enable for
	 * EXSTACK_ENABLE_X, disable for EXSTACK_DISABLE_X and leave alone
	 * (arch default) otherwise.
	 */
	if (unlikely(executable_stack == EXSTACK_ENABLE_X))
		vm_flags |= VM_EXEC;
	else if (executable_stack == EXSTACK_DISABLE_X)
		vm_flags &= ~VM_EXEC;
	vm_flags |= mm->def_flags;

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

	/* Move stack pages down in memory. */
	if (stack_shift) {
		ret = shift_arg_pages(vma, stack_shift);
		if (ret) {
			up_write(&mm->mmap_sem);
			return ret;
		}
	}

#ifdef CONFIG_STACK_GROWSUP
	stack_base = vma->vm_end + EXTRA_STACK_VM_PAGES * PAGE_SIZE;
#else
	stack_base = vma->vm_start - EXTRA_STACK_VM_PAGES * PAGE_SIZE;
#endif
	ret = expand_stack(vma, stack_base);
	if (ret)
		ret = -EFAULT;

out_unlock:
	up_write(&mm->mmap_sem);
	return 0;
}
EXPORT_SYMBOL(setup_arg_pages);

#endif /* CONFIG_MMU */

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

	err = path_lookup_open(AT_FDCWD, name, LOOKUP_FOLLOW, &nd, FMODE_READ|FMODE_EXEC);
	file = ERR_PTR(err);

	if (!err) {
		struct inode *inode = nd.dentry->d_inode;
		file = ERR_PTR(-EACCES);
		if (!(nd.mnt->mnt_flags & MNT_NOEXEC) &&
		    S_ISREG(inode->i_mode)) {
			int err = vfs_permission(&nd, MAY_EXEC);
			file = ERR_PTR(err);
			if (!err) {
				file = nameidata_to_filp(&nd, O_RDONLY);
				if (!IS_ERR(file)) {
					err = deny_write_access(file);
					if (err) {
						fput(file);
						file = ERR_PTR(err);
					}
				}
out:
				return file;
			}
		}
		release_open_intent(&nd);
		path_release(&nd);
	}
	goto out;
}

EXPORT_SYMBOL(open_exec);

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

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

EXPORT_SYMBOL(kernel_read);

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

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

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

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

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

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

	if (thread_group_empty(tsk))
		goto no_thread_group;

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

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

	zap_other_threads(tsk);
	read_unlock(&tasklist_lock);

	/*
	 * Account for the thread group leader hanging around:
	 */
	count = 1;
	if (!thread_group_leader(tsk)) {
		count = 2;
		/*
		 * The SIGALRM timer survives the exec, but needs to point
		 * at us as the new group leader now.  We have a race with
		 * a timer firing now getting the old leader, so we need to
		 * synchronize with any firing (by calling del_timer_sync)
		 * before we can safely let the old group leader die.
		 */
		sig->tsk = tsk;
		spin_unlock_irq(lock);
		if (hrtimer_cancel(&sig->real_timer))
			hrtimer_restart(&sig->real_timer);
		spin_lock_irq(lock);
	}
	while (atomic_read(&sig->count) > count) {
		sig->group_exit_task = tsk;
		sig->notify_count = count;
		__set_current_state(TASK_UNINTERRUPTIBLE);
		spin_unlock_irq(lock);
		schedule();
		spin_lock_irq(lock);
	}
	sig->group_exit_task = NULL;
	sig->notify_count = 0;
	spin_unlock_irq(lock);

	/*
	 * At this point all other threads have exited, all we have to
	 * do is to wait for the thread group leader to become inactive,
	 * and to assume its PID:
	 */
	if (!thread_group_leader(tsk)) {
		/*
		 * Wait for the thread group leader to be a zombie.
		 * It should already be zombie at this point, most
		 * of the time.
		 */
		leader = tsk->group_leader;
		while (leader->exit_state != EXIT_ZOMBIE)
			yield();

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

		write_lock_irq(&tasklist_lock);

		BUG_ON(leader->tgid != tsk->tgid);
		BUG_ON(tsk->pid == tsk->tgid);
		/*
		 * An exec() starts a new thread group with the
		 * TGID of the previous thread group. Rehash the
		 * two threads with a switched PID, and release
		 * the former thread group leader:
		 */

		/* Become a process group leader with the old leader's pid.
		 * The old leader becomes a thread of the this thread group.
		 * Note: The old leader also uses this pid until release_task
		 *       is called.  Odd but simple and correct.
		 */
		detach_pid(tsk, PIDTYPE_PID);
		tsk->pid = leader->pid;
		attach_pid(tsk, PIDTYPE_PID,  find_pid(tsk->pid));
		transfer_pid(leader, tsk, PIDTYPE_PGID);
		transfer_pid(leader, tsk, PIDTYPE_SID);
		list_replace_rcu(&leader->tasks, &tsk->tasks);

		tsk->group_leader = tsk;
		leader->group_leader = tsk;

		tsk->exit_signal = SIGCHLD;

		BUG_ON(leader->exit_state != EXIT_ZOMBIE);
		leader->exit_state = EXIT_DEAD;

		write_unlock_irq(&tasklist_lock);
        }

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

no_thread_group:
	exit_itimers(sig);
	if (leader)
		release_task(leader);

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

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

		rcu_assign_pointer(tsk->sighand, newsighand);
		recalc_sigpending();

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

		__cleanup_sighand(oldsighand);
	}

	BUG_ON(!thread_group_leader(tsk));
	return 0;
}
	
/*
 * These functions flushes out all traces of the currently running executable
 * so that a new one can be started
 */

static void flush_old_files(struct files_struct * files)
{
	long j = -1;
	struct fdtable *fdt;

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

		j++;
		i = j * __NFDBITS;
		fdt = files_fdtable(files);
		if (i >= fdt->max_fds)
			break;
		set = fdt->close_on_exec->fds_bits[j];
		if (!set)
			continue;
		fdt->close_on_exec->fds_bits[j] = 0;
		spin_unlock(&files->file_lock);
		for ( ; set ; i++,set >>= 1) {
			if (set & 1) {
				sys_close(i);
			}
		}
		spin_lock(&files->file_lock);

	}
	spin_unlock(&files->file_lock);
}

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