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/fdtable.h>
#include <linux/mm.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/swap.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/perf_event.h>
#include <linux/highmem.h>
#include <linux/spinlock.h>
#include <linux/key.h>
#include <linux/personality.h>
#include <linux/binfmts.h>
#include <linux/utsname.h>
#include <linux/pid_namespace.h>
#include <linux/module.h>
#include <linux/namei.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/tsacct_kern.h>
#include <linux/cn_proc.h>
#include <linux/audit.h>
#include <linux/tracehook.h>
#include <linux/kmod.h>
#include <linux/fsnotify.h>
#include <linux/fs_struct.h>
#include <linux/pipe_fs_i.h>
#include <linux/oom.h>
#include <linux/compat.h>

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

#include <trace/events/task.h>
#include "internal.h"
#include "coredump.h"

#include <trace/events/sched.h>

int suid_dumpable = 0;

static LIST_HEAD(formats);
static DEFINE_RWLOCK(binfmt_lock);

void __register_binfmt(struct linux_binfmt * fmt, int insert)
{
	BUG_ON(!fmt);
	write_lock(&binfmt_lock);
	insert ? list_add(&fmt->lh, &formats) :
		 list_add_tail(&fmt->lh, &formats);
	write_unlock(&binfmt_lock);
}

EXPORT_SYMBOL(__register_binfmt);

void unregister_binfmt(struct linux_binfmt * fmt)
{
	write_lock(&binfmt_lock);
	list_del(&fmt->lh);
	write_unlock(&binfmt_lock);
}

EXPORT_SYMBOL(unregister_binfmt);

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

/*
 * Note that a shared library must be both readable and executable due to
 * security reasons.
 *
 * Also note that we take the address to load from from the file itself.
 */
SYSCALL_DEFINE1(uselib, const char __user *, library)
{
	struct file *file;
	struct filename *tmp = getname(library);
	int error = PTR_ERR(tmp);
	static const struct open_flags uselib_flags = {
		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
		.acc_mode = MAY_READ | MAY_EXEC | MAY_OPEN,
		.intent = LOOKUP_OPEN
	};

	if (IS_ERR(tmp))
		goto out;

	file = do_filp_open(AT_FDCWD, tmp, &uselib_flags, LOOKUP_FOLLOW);
	putname(tmp);
	error = PTR_ERR(file);
	if (IS_ERR(file))
		goto out;

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

	error = -EACCES;
	if (file->f_path.mnt->mnt_flags & MNT_NOEXEC)
		goto exit;

	fsnotify_open(file);

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

		read_lock(&binfmt_lock);
		list_for_each_entry(fmt, &formats, lh) {
			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);
	}
exit:
	fput(file);
out:
  	return error;
}

#ifdef CONFIG_MMU
/*
 * The nascent bprm->mm is not visible until exec_mmap() but it can
 * use a lot of memory, account these pages in current->mm temporary
 * for oom_badness()->get_mm_rss(). Once exec succeeds or fails, we
 * change the counter back via acct_arg_size(0).
 */
static void acct_arg_size(struct linux_binprm *bprm, unsigned long pages)
{
	struct mm_struct *mm = current->mm;
	long diff = (long)(pages - bprm->vma_pages);

	if (!mm || !diff)
		return;

	bprm->vma_pages = pages;
	add_mm_counter(mm, MM_ANONPAGES, diff);
}

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_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) {
		unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start;
		struct rlimit *rlim;

		acct_arg_size(bprm, size / PAGE_SIZE);

		/*
		 * We've historically supported up to 32 pages (ARG_MAX)
		 * of argument strings even with small stacks
		 */
		if (size <= ARG_MAX)
			return page;

		/*
		 * 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.
		 */
		rlim = current->signal->rlim;
		if (size > ACCESS_ONCE(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;
	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)
		return -ENOMEM;

	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.
	 */
	BUILD_BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP);
	vma->vm_end = STACK_TOP_MAX;
	vma->vm_start = vma->vm_end - PAGE_SIZE;
	vma->vm_flags = VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP;
	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
	INIT_LIST_HEAD(&vma->anon_vma_chain);

	err = insert_vm_struct(mm, vma);
	if (err)
		goto err;

	mm->stack_vm = mm->total_vm = 1;
	up_write(&mm->mmap_sem);
	bprm->p = vma->vm_end - sizeof(void *);
	return 0;
err:
	up_write(&mm->mmap_sem);
	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 inline void acct_arg_size(struct linux_binprm *bprm, unsigned long pages)
{
}

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;
}

struct user_arg_ptr {
#ifdef CONFIG_COMPAT
	bool is_compat;
#endif
	union {
		const char __user *const __user *native;
#ifdef CONFIG_COMPAT
		const compat_uptr_t __user *compat;
#endif
	} ptr;
};

static const char __user *get_user_arg_ptr(struct user_arg_ptr argv, int nr)
{
	const char __user *native;

#ifdef CONFIG_COMPAT
	if (unlikely(argv.is_compat)) {
		compat_uptr_t compat;

		if (get_user(compat, argv.ptr.compat + nr))
			return ERR_PTR(-EFAULT);

		return compat_ptr(compat);
	}
#endif

	if (get_user(native, argv.ptr.native + nr))
		return ERR_PTR(-EFAULT);

	return native;
}

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

	if (argv.ptr.native != NULL) {
		for (;;) {
			const char __user *p = get_user_arg_ptr(argv, i);

			if (!p)
				break;

			if (IS_ERR(p))
				return -EFAULT;

			if (i++ >= max)
				return -E2BIG;

			if (fatal_signal_pending(current))
				return -ERESTARTNOHAND;
			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, struct user_arg_ptr argv,
			struct linux_binprm *bprm)
{
	struct page *kmapped_page = NULL;
	char *kaddr = NULL;
	unsigned long kpos = 0;
	int ret;

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

		ret = -EFAULT;
		str = get_user_arg_ptr(argv, argc);
		if (IS_ERR(str))
			goto out;

		len = strnlen_user(str, MAX_ARG_STRLEN);
		if (!len)
			goto out;

		ret = -E2BIG;
		if (!valid_arg_len(bprm, len))
			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;

			if (fatal_signal_pending(current)) {
				ret = -ERESTARTNOHAND;
				goto out;
			}
			cond_resched();

			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, const char *const *__argv,
			struct linux_binprm *bprm)
{
	int r;
	mm_segment_t oldfs = get_fs();
	struct user_arg_ptr argv = {
		.ptr.native = (const char __user *const  __user *)__argv,
	};

	set_fs(KERNEL_DS);
	r = copy_strings(argc, 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)
	 */
	if (vma_adjust(vma, new_start, old_end, vma->vm_pgoff, NULL))
		return -ENOMEM;

	/*
	 * 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, false))
		return -ENOMEM;

	lru_add_drain();
	tlb_gather_mmu(&tlb, 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.  Always succeeds.
	 */
	vma_adjust(vma, new_start, new_end, vma->vm_pgoff, NULL);

	return 0;
}

/*
 * 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;
	unsigned long stack_size;
	unsigned long stack_expand;
	unsigned long rlim_stack;

#ifdef CONFIG_STACK_GROWSUP
	/* Limit stack size to 1GB */
	stack_base = rlimit_max(RLIMIT_STACK);
	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);

	if (unlikely(stack_top < mmap_min_addr) ||
	    unlikely(vma->vm_end - vma->vm_start >= stack_top - mmap_min_addr))
		return -ENOMEM;

	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 = VM_STACK_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;
	vm_flags |= VM_STACK_INCOMPLETE_SETUP;

	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)
			goto out_unlock;
	}

	/* mprotect_fixup is overkill to remove the temporary stack flags */
	vma->vm_flags &= ~VM_STACK_INCOMPLETE_SETUP;

	stack_expand = 131072UL; /* randomly 32*4k (or 2*64k) pages */
	stack_size = vma->vm_end - vma->vm_start;
	/*
	 * Align this down to a page boundary as expand_stack
	 * will align it up.
	 */
	rlim_stack = rlimit(RLIMIT_STACK) & PAGE_MASK;
#ifdef CONFIG_STACK_GROWSUP
	if (stack_size + stack_expand > rlim_stack)
		stack_base = vma->vm_start + rlim_stack;
	else
		stack_base = vma->vm_end + stack_expand;
#else
	if (stack_size + stack_expand > rlim_stack)
		stack_base = vma->vm_end - rlim_stack;
	else
		stack_base = vma->vm_start - stack_expand;
#endif
	current->mm->start_stack = bprm->p;
	ret = expand_stack(vma, stack_base);
	if (ret)
		ret = -EFAULT;

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

#endif /* CONFIG_MMU */

struct file *open_exec(const char *name)
{
	struct file *file;
	int err;
	struct filename tmp = { .name = name };
	static const struct open_flags open_exec_flags = {
		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
		.acc_mode = MAY_EXEC | MAY_OPEN,
		.intent = LOOKUP_OPEN
	};

	file = do_filp_open(AT_FDCWD, &tmp, &open_exec_flags, LOOKUP_FOLLOW);
	if (IS_ERR(file))
		goto out;

	err = -EACCES;
	if (!S_ISREG(file->f_path.dentry->d_inode->i_mode))
		goto exit;

	if (file->f_path.mnt->mnt_flags & MNT_NOEXEC)
		goto exit;

	fsnotify_open(file);

	err = deny_write_access(file);
	if (err)
		goto exit;

out:
	return file;

exit:
	fput(file);
	return ERR_PTR(err);
}
EXPORT_SYMBOL(open_exec);

int kernel_read(struct file *file, loff_t 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) {
		sync_mm_rss(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_state and changing tsk->mm.
		 */
		down_read(&old_mm->mmap_sem);
		if (unlikely(old_mm->core_state)) {
			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);
		setmax_mm_hiwater_rss(&tsk->signal->maxrss, old_mm);
		mm_update_next_owner(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 *oldsighand = tsk->sighand;
	spinlock_t *lock = &oldsighand->siglock;

	if (thread_group_empty(tsk))
		goto no_thread_group;

	/*
	 * Kill all other threads in the thread group.
	 */
	spin_lock_irq(lock);
	if (signal_group_exit(sig)) {
		/*
		 * Another group action in progress, just
		 * return so that the signal is processed.
		 */
		spin_unlock_irq(lock);
		return -EAGAIN;
	}

	sig->group_exit_task = tsk;
	sig->notify_count = zap_other_threads(tsk);
	if (!thread_group_leader(tsk))
		sig->notify_count--;

	while (sig->notify_count) {
		__set_current_state(TASK_KILLABLE);
		spin_unlock_irq(lock);
		schedule();
		if (unlikely(__fatal_signal_pending(tsk)))
			goto killed;
		spin_lock_irq(lock);
	}
	spin_unlock_irq(lock);

	/*
	 * At this point all other threads have exited, all we have to
	 * do is to wait for the thread group leader to become inactive,
	 * and to assume its PID:
	 */
	if (!thread_group_leader(tsk)) {
		struct task_struct *leader = tsk->group_leader;

		sig->notify_count = -1;	/* for exit_notify() */
		for (;;) {
			write_lock_irq(&tasklist_lock);
			if (likely(leader->exit_state))
				break;
			__set_current_state(TASK_KILLABLE);
			write_unlock_irq(&tasklist_lock);
			schedule();
			if (unlikely(__fatal_signal_pending(tsk)))
				goto killed;
		}

		/*
		 * 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;

		BUG_ON(!same_thread_group(leader, tsk));
		BUG_ON(has_group_leader_pid(tsk));
		/*
		 * 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,  task_pid(leader));
		transfer_pid(leader, tsk, PIDTYPE_PGID);
		transfer_pid(leader, tsk, PIDTYPE_SID);

		list_replace_rcu(&leader->tasks, &tsk->tasks);
		list_replace_init(&leader->sibling, &tsk->sibling);

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

		tsk->exit_signal = SIGCHLD;
		leader->exit_signal = -1;

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

		/*
		 * We are going to release_task()->ptrace_unlink() silently,
		 * the tracer can sleep in do_wait(). EXIT_DEAD guarantees
		 * the tracer wont't block again waiting for this thread.
		 */
		if (unlikely(leader->ptrace))
			__wake_up_parent(leader, leader->parent);
		write_unlock_irq(&tasklist_lock);

		release_task(leader);
	}

	sig->group_exit_task = NULL;
	sig->notify_count = 0;

no_thread_group:
	/* we have changed execution domain */
	tsk->exit_signal = SIGCHLD;

	exit_itimers(sig);
	flush_itimer_signals();

	if (atomic_read(&oldsighand->count) != 1) {
		struct sighand_struct *newsighand;
		/*
		 * This ->sighand is shared with the CLONE_SIGHAND
		 * but not CLONE_THREAD task, switch to the new one.
		 */
		newsighand = kmem_cache_alloc(sighand_cachep, GFP_KERNEL);
		if (!newsighand)
			return -ENOMEM;

		atomic_set(&newsighand->count, 1);
		memcpy(newsighand->action, oldsighand->action,
		       sizeof(newsighand->action));

		write_lock_irq(&tasklist_lock);
		spin_lock(&oldsighand->siglock);
		rcu_assign_pointer(tsk->sighand, newsighand);
		spin_unlock(&oldsighand->siglock);
		write_unlock_irq(&tasklist_lock);

		__cleanup_sighand(oldsighand);
	}

	BUG_ON(!thread_group_leader(tsk));
	return 0;