Skip to content
Snippets Groups Projects
exec.c 34.3 KiB
Newer Older
  • Learn to ignore specific revisions
  • Linus Torvalds's avatar
    Linus Torvalds committed
    /*
     *  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/config.h>
    #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/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/acct.h>
    
    #include <linux/cn_proc.h>
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    
    #include <asm/uaccess.h>
    #include <asm/mmu_context.h>
    
    #ifdef CONFIG_KMOD
    #include <linux/kmod.h>
    #endif
    
    int core_uses_pid;
    char core_pattern[65] = "core";
    
    Alan Cox's avatar
    Alan Cox committed
    int suid_dumpable = 0;
    
    EXPORT_SYMBOL(suid_dumpable);
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    /* 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;
    			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);
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    	if (error)
    		goto out;
    
    	error = -EINVAL;
    	if (!S_ISREG(nd.dentry->d_inode->i_mode))
    		goto exit;
    
    
    	error = vfs_permission(&nd, MAY_READ | MAY_EXEC);
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    	if (error)
    		goto exit;
    
    
    	file = nameidata_to_filp(&nd, O_RDONLY);
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    	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:
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    	path_release(&nd);
    	goto out;
    }
    
    /*
     * 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 user
     * memory to free pages in kernel mem. These are in a format ready
     * to be put directly into the top of new user memory.
     */
    
    static int copy_strings(int argc, char __user * __user * argv,
    			struct linux_binprm *bprm)
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    {
    	struct page *kmapped_page = NULL;
    	char *kaddr = NULL;
    	int ret;
    
    	while (argc-- > 0) {
    		char __user *str;
    		int len;
    		unsigned long pos;
    
    		if (get_user(str, argv+argc) ||
    				!(len = strnlen_user(str, bprm->p))) {
    			ret = -EFAULT;
    			goto out;
    		}
    
    		if (bprm->p < len)  {
    			ret = -E2BIG;
    			goto out;
    		}
    
    		bprm->p -= len;
    		/* XXX: add architecture specific overflow check here. */
    		pos = bprm->p;
    
    		while (len > 0) {
    			int i, new, err;
    			int offset, bytes_to_copy;
    			struct page *page;
    
    			offset = pos % PAGE_SIZE;
    			i = pos/PAGE_SIZE;
    			page = bprm->page[i];
    			new = 0;
    			if (!page) {
    				page = alloc_page(GFP_HIGHUSER);
    				bprm->page[i] = page;
    				if (!page) {
    					ret = -ENOMEM;
    					goto out;
    				}
    				new = 1;
    			}
    
    			if (page != kmapped_page) {
    				if (kmapped_page)
    					kunmap(kmapped_page);
    				kmapped_page = page;
    				kaddr = kmap(kmapped_page);
    			}
    			if (new && offset)
    				memset(kaddr, 0, offset);
    			bytes_to_copy = PAGE_SIZE - offset;
    			if (bytes_to_copy > len) {
    				bytes_to_copy = len;
    				if (new)
    					memset(kaddr+offset+len, 0,
    						PAGE_SIZE-offset-len);
    			}
    			err = copy_from_user(kaddr+offset, str, bytes_to_copy);
    			if (err) {
    				ret = -EFAULT;
    				goto out;
    			}
    
    			pos += bytes_to_copy;
    			str += bytes_to_copy;
    			len -= bytes_to_copy;
    		}
    	}
    	ret = 0;
    out:
    	if (kmapped_page)
    		kunmap(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
    /*
     * This routine is used to map in a page into an address space: needed by
     * execve() for the initial stack and environment pages.
     *
     * vma->vm_mm->mmap_sem is held for writing.
     */
    void install_arg_page(struct vm_area_struct *vma,
    			struct page *page, unsigned long address)
    {
    	struct mm_struct *mm = vma->vm_mm;
    	pte_t * pte;
    
    	spinlock_t *ptl;
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    
    	if (unlikely(anon_vma_prepare(vma)))
    
    		goto out;
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    
    	flush_dcache_page(page);
    
    	pte = get_locked_pte(mm, address, &ptl);
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    	if (!pte)
    		goto out;
    	if (!pte_none(*pte)) {
    
    		pte_unmap_unlock(pte, ptl);
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    		goto out;
    	}
    
    	inc_mm_counter(mm, anon_rss);
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    	lru_cache_add_active(page);
    	set_pte_at(mm, address, pte, pte_mkdirty(pte_mkwrite(mk_pte(
    					page, vma->vm_page_prot))));
    
    	page_add_new_anon_rmap(page, vma, address);
    
    	pte_unmap_unlock(pte, ptl);
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    
    	/* no need for flush_tlb */
    	return;
    out:
    	__free_page(page);
    	force_sig(SIGKILL, current);
    }
    
    #define EXTRA_STACK_VM_PAGES	20	/* random */
    
    int setup_arg_pages(struct linux_binprm *bprm,
    		    unsigned long stack_top,
    		    int executable_stack)
    {
    	unsigned long stack_base;
    	struct vm_area_struct *mpnt;
    	struct mm_struct *mm = current->mm;
    	int i, ret;
    	long arg_size;
    
    #ifdef CONFIG_STACK_GROWSUP
    	/* Move the argument and environment strings to the bottom of the
    	 * stack space.
    	 */
    	int offset, j;
    	char *to, *from;
    
    	/* Start by shifting all the pages down */
    	i = 0;
    	for (j = 0; j < MAX_ARG_PAGES; j++) {
    		struct page *page = bprm->page[j];
    		if (!page)
    			continue;
    		bprm->page[i++] = page;
    	}
    
    	/* Now move them within their pages */
    	offset = bprm->p % PAGE_SIZE;
    	to = kmap(bprm->page[0]);
    	for (j = 1; j < i; j++) {
    		memmove(to, to + offset, PAGE_SIZE - offset);
    		from = kmap(bprm->page[j]);
    		memcpy(to + PAGE_SIZE - offset, from, offset);
    		kunmap(bprm->page[j - 1]);
    		to = from;
    	}
    	memmove(to, to + offset, PAGE_SIZE - offset);
    	kunmap(bprm->page[j - 1]);
    
    	/* Limit stack size to 1GB */
    	stack_base = current->signal->rlim[RLIMIT_STACK].rlim_max;
    	if (stack_base > (1 << 30))
    		stack_base = 1 << 30;
    	stack_base = PAGE_ALIGN(stack_top - stack_base);
    
    	/* Adjust bprm->p to point to the end of the strings. */
    	bprm->p = stack_base + PAGE_SIZE * i - offset;
    
    	mm->arg_start = stack_base;
    	arg_size = i << PAGE_SHIFT;
    
    	/* zero pages that were copied above */
    	while (i < MAX_ARG_PAGES)
    		bprm->page[i++] = NULL;
    #else
    	stack_base = arch_align_stack(stack_top - MAX_ARG_PAGES*PAGE_SIZE);
    	stack_base = PAGE_ALIGN(stack_base);
    	bprm->p += stack_base;
    	mm->arg_start = bprm->p;
    	arg_size = stack_top - (PAGE_MASK & (unsigned long) mm->arg_start);
    #endif
    
    	arg_size += EXTRA_STACK_VM_PAGES * PAGE_SIZE;
    
    	if (bprm->loader)
    		bprm->loader += stack_base;
    	bprm->exec += stack_base;
    
    	mpnt = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
    	if (!mpnt)
    		return -ENOMEM;
    
    	memset(mpnt, 0, sizeof(*mpnt));
    
    	down_write(&mm->mmap_sem);
    	{
    		mpnt->vm_mm = mm;
    #ifdef CONFIG_STACK_GROWSUP
    		mpnt->vm_start = stack_base;
    		mpnt->vm_end = stack_base + arg_size;
    #else
    		mpnt->vm_end = stack_top;
    		mpnt->vm_start = mpnt->vm_end - arg_size;
    #endif
    		/* 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))
    			mpnt->vm_flags = VM_STACK_FLAGS |  VM_EXEC;
    		else if (executable_stack == EXSTACK_DISABLE_X)
    			mpnt->vm_flags = VM_STACK_FLAGS & ~VM_EXEC;
    		else
    			mpnt->vm_flags = VM_STACK_FLAGS;
    		mpnt->vm_flags |= mm->def_flags;
    		mpnt->vm_page_prot = protection_map[mpnt->vm_flags & 0x7];
    		if ((ret = insert_vm_struct(mm, mpnt))) {
    			up_write(&mm->mmap_sem);
    			kmem_cache_free(vm_area_cachep, mpnt);
    			return ret;
    		}
    		mm->stack_vm = mm->total_vm = vma_pages(mpnt);
    	}
    
    	for (i = 0 ; i < MAX_ARG_PAGES ; i++) {
    		struct page *page = bprm->page[i];
    		if (page) {
    			bprm->page[i] = NULL;
    			install_arg_page(mpnt, page, stack_base);
    		}
    		stack_base += PAGE_SIZE;
    	}
    	up_write(&mm->mmap_sem);
    	
    	return 0;
    }
    
    EXPORT_SYMBOL(setup_arg_pages);
    
    #define free_arg_pages(bprm) do { } while (0)
    
    #else
    
    static inline void free_arg_pages(struct linux_binprm *bprm)
    {
    	int i;
    
    	for (i = 0; i < MAX_ARG_PAGES; i++) {
    		if (bprm->page[i])
    			__free_page(bprm->page[i]);
    		bprm->page[i] = NULL;
    	}
    }
    
    #endif /* CONFIG_MMU */
    
    struct file *open_exec(const char *name)
    {
    	struct nameidata nd;
    	int err;
    	struct file *file;
    
    
    	err = path_lookup_open(name, LOOKUP_FOLLOW, &nd, FMODE_READ);
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    	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);
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    			if (!err && !(inode->i_mode & 0111))
    				err = -EACCES;
    			file = ERR_PTR(err);
    			if (!err) {
    
    				file = nameidata_to_filp(&nd, O_RDONLY);
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    				if (!IS_ERR(file)) {
    					err = deny_write_access(file);
    					if (err) {
    						fput(file);
    						file = ERR_PTR(err);
    					}
    				}
    out:
    				return file;
    			}
    		}
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    		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);
    		if (active_mm != old_mm) BUG();
    		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)
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    {
    	struct signal_struct *sig = tsk->signal;
    	struct sighand_struct *newsighand, *oldsighand = tsk->sighand;
    	spinlock_t *lock = &oldsighand->siglock;
    
    	struct task_struct *leader = NULL;
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    	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) {
    		BUG_ON(atomic_read(&sig->count) != 1);
    		exit_itimers(sig);
    		return 0;
    	}
    
    	newsighand = kmem_cache_alloc(sighand_cachep, GFP_KERNEL);
    	if (!newsighand)
    		return -ENOMEM;
    
    	if (thread_group_empty(current))
    		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;
    	}
    	zap_other_threads(current);
    	read_unlock(&tasklist_lock);
    
    	/*
    	 * Account for the thread group leader hanging around:
    	 */
    
    	count = 1;
    	if (!thread_group_leader(current)) {
    		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->real_timer.data = current;
    
    		spin_unlock_irq(lock);
    
    		if (hrtimer_cancel(&sig->real_timer))
    			hrtimer_restart(&sig->real_timer);
    
    		spin_lock_irq(lock);
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    	while (atomic_read(&sig->count) > count) {
    		sig->group_exit_task = current;
    		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(current)) {
    
    		struct task_struct *parent;
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    		struct dentry *proc_dentry1, *proc_dentry2;
    
    		unsigned long ptrace;
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    
    		/*
    		 * Wait for the thread group leader to be a zombie.
    		 * It should already be zombie at this point, most
    		 * of the time.
    		 */
    
    		leader = current->group_leader;
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    		while (leader->exit_state != EXIT_ZOMBIE)
    			yield();
    
    		spin_lock(&leader->proc_lock);
    		spin_lock(&current->proc_lock);
    		proc_dentry1 = proc_pid_unhash(current);
    		proc_dentry2 = proc_pid_unhash(leader);
    		write_lock_irq(&tasklist_lock);
    
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    		BUG_ON(leader->tgid != current->tgid);
    		BUG_ON(current->pid == current->tgid);
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    		/*
    		 * 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:
    		 */
    		ptrace = leader->ptrace;
    		parent = leader->parent;
    		if (unlikely(ptrace) && unlikely(parent == current)) {
    			/*
    			 * Joker was ptracing his own group leader,
    			 * and now he wants to be his own parent!
    			 * We can't have that.
    			 */
    			ptrace = 0;
    		}
    
    		ptrace_unlink(current);
    		ptrace_unlink(leader);
    		remove_parent(current);
    		remove_parent(leader);
    
    		switch_exec_pids(leader, current);
    
    		current->parent = current->real_parent = leader->real_parent;
    		leader->parent = leader->real_parent = child_reaper;
    		current->group_leader = current;
    		leader->group_leader = leader;
    
    		add_parent(current, current->parent);
    		add_parent(leader, leader->parent);
    		if (ptrace) {
    			current->ptrace = ptrace;
    			__ptrace_link(current, parent);
    		}
    
    		list_del(&current->tasks);
    		list_add_tail(&current->tasks, &init_task.tasks);
    		current->exit_signal = SIGCHLD;
    
    
    		BUG_ON(leader->exit_state != EXIT_ZOMBIE);
    		leader->exit_state = EXIT_DEAD;
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    
    		write_unlock_irq(&tasklist_lock);
    		spin_unlock(&leader->proc_lock);
    		spin_unlock(&current->proc_lock);
    		proc_pid_flush(proc_dentry1);
    		proc_pid_flush(proc_dentry2);
            }
    
    	/*
    
    	 * There may be one thread left which is just exiting,
    	 * but it's safe to stop telling the group to kill themselves.
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    	 */
    	sig->flags = 0;
    
    no_thread_group:
    	exit_itimers(sig);
    
    	if (leader)
    		release_task(leader);
    
    	BUG_ON(atomic_read(&sig->count) != 1);
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    
    	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.
    		 */
    		spin_lock_init(&newsighand->siglock);
    		atomic_set(&newsighand->count, 1);
    		memcpy(newsighand->action, oldsighand->action,
    		       sizeof(newsighand->action));
    
    		write_lock_irq(&tasklist_lock);
    		spin_lock(&oldsighand->siglock);
    		spin_lock(&newsighand->siglock);
    
    
    Ingo Molnar's avatar
    Ingo Molnar committed
    		rcu_assign_pointer(current->sighand, newsighand);
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    		recalc_sigpending();
    
    		spin_unlock(&newsighand->siglock);
    		spin_unlock(&oldsighand->siglock);
    		write_unlock_irq(&tasklist_lock);
    
    		if (atomic_dec_and_test(&oldsighand->count))
    
    Ingo Molnar's avatar
    Ingo Molnar committed
    			sighand_free(oldsighand);
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    	BUG_ON(!thread_group_leader(current));
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    	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)
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    {
    	long j = -1;
    
    	struct fdtable *fdt;
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    
    	spin_lock(&files->file_lock);
    	for (;;) {
    		unsigned long set, i;
    
    		j++;
    		i = j * __NFDBITS;
    
    		fdt = files_fdtable(files);
    		if (i >= fdt->max_fds || i >= fdt->max_fdset)
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    			break;
    
    		set = fdt->close_on_exec->fds_bits[j];
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    		if (!set)
    			continue;
    
    		fdt->close_on_exec->fds_bits[j] = 0;
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    		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));
    	task_unlock(tsk);
    }
    
    void set_task_comm(struct task_struct *tsk, char *buf)
    {
    	task_lock(tsk);
    	strlcpy(tsk->comm, buf, sizeof(tsk->comm));
    	task_unlock(tsk);
    }
    
    int flush_old_exec(struct linux_binprm * bprm)
    {
    	char * name;
    	int i, ch, retval;
    	struct files_struct *files;
    	char tcomm[sizeof(current->comm)];
    
    	/*
    	 * Make sure we have a private signal table and that
    	 * we are unassociated from the previous thread group.
    	 */
    	retval = de_thread(current);
    	if (retval)
    		goto out;
    
    	/*
    	 * Make sure we have private file handles. Ask the
    	 * fork helper to do the work for us and the exit
    	 * helper to do the cleanup of the old one.
    	 */
    	files = current->files;		/* refcounted so safe to hold */
    	retval = unshare_files();
    	if (retval)
    		goto out;
    	/*
    	 * Release all of the old mmap stuff
    	 */
    	retval = exec_mmap(bprm->mm);
    	if (retval)
    		goto mmap_failed;
    
    	bprm->mm = NULL;		/* We're using it now */
    
    	/* This is the point of no return */
    	steal_locks(files);
    	put_files_struct(files);
    
    	current->sas_ss_sp = current->sas_ss_size = 0;
    
    	if (current->euid == current->uid && current->egid == current->gid)
    		current->mm->dumpable = 1;
    
    Alan Cox's avatar
    Alan Cox committed
    	else
    		current->mm->dumpable = suid_dumpable;
    
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    	name = bprm->filename;
    
    
    	/* Copies the binary name from after last slash */
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    	for (i=0; (ch = *(name++)) != '\0';) {
    		if (ch == '/')
    
    			i = 0; /* overwrite what we wrote */
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    		else
    			if (i < (sizeof(tcomm) - 1))
    				tcomm[i++] = ch;
    	}
    	tcomm[i] = '\0';
    	set_task_comm(current, tcomm);
    
    	current->flags &= ~PF_RANDOMIZE;
    	flush_thread();
    
    	if (bprm->e_uid != current->euid || bprm->e_gid != current->egid || 
    
    	    file_permission(bprm->file, MAY_READ) ||
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    	    (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP)) {
    		suid_keys(current);
    
    Alan Cox's avatar
    Alan Cox committed
    		current->mm->dumpable = suid_dumpable;
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    	}
    
    	/* An exec changes our domain. We are no longer part of the thread
    	   group */
    
    	current->self_exec_id++;
    			
    	flush_signal_handlers(current, 0);
    	flush_old_files(current->files);
    
    	return 0;
    
    mmap_failed:
    	put_files_struct(current->files);
    	current->files = files;
    out:
    	return retval;
    }
    
    EXPORT_SYMBOL(flush_old_exec);
    
    /* 
     * Fill the binprm structure from the inode. 
     * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes
     */
    int prepare_binprm(struct linux_binprm *bprm)
    {
    	int mode;
    	struct inode * inode = bprm->file->f_dentry->d_inode;
    	int retval;
    
    	mode = inode->i_mode;
    	/*
    	 * Check execute perms again - if the caller has CAP_DAC_OVERRIDE,
    	 * generic_permission lets a non-executable through
    	 */
    	if (!(mode & 0111))	/* with at least _one_ execute bit set */
    		return -EACCES;
    	if (bprm->file->f_op == NULL)
    		return -EACCES;
    
    	bprm->e_uid = current->euid;
    	bprm->e_gid = current->egid;
    
    	if(!(bprm->file->f_vfsmnt->mnt_flags & MNT_NOSUID)) {
    		/* Set-uid? */
    		if (mode & S_ISUID) {
    			current->personality &= ~PER_CLEAR_ON_SETID;
    			bprm->e_uid = inode->i_uid;
    		}
    
    		/* Set-gid? */
    		/*
    		 * If setgid is set but no group execute bit then this
    		 * is a candidate for mandatory locking, not a setgid
    		 * executable.
    		 */
    		if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
    			current->personality &= ~PER_CLEAR_ON_SETID;
    			bprm->e_gid = inode->i_gid;
    		}
    	}
    
    	/* fill in binprm security blob */
    	retval = security_bprm_set(bprm);
    	if (retval)
    		return retval;
    
    	memset(bprm->buf,0,BINPRM_BUF_SIZE);
    	return kernel_read(bprm->file,0,bprm->buf,BINPRM_BUF_SIZE);
    }
    
    EXPORT_SYMBOL(prepare_binprm);
    
    
    static int unsafe_exec(struct task_struct *p)
    
    Linus Torvalds's avatar
    Linus Torvalds committed
    {
    	int unsafe = 0;
    	if (p->ptrace & PT_PTRACED) {
    		if (p->ptrace & PT_PTRACE_CAP)
    			unsafe |= LSM_UNSAFE_PTRACE_CAP;
    		else
    			unsafe |= LSM_UNSAFE_PTRACE;
    	}
    	if (atomic_read(&p->fs->count) > 1 ||
    	    atomic_read(&p->files->count) > 1 ||
    	    atomic_read(&p->sighand->count) > 1)
    		unsafe |= LSM_UNSAFE_SHARE;
    
    	return unsafe;
    }
    
    void compute_creds(struct linux_binprm *bprm)
    {
    	int unsafe;
    
    	if (bprm->e_uid != current->uid)
    		suid_keys(current);
    	exec_keys(current);
    
    	task_lock(current);
    	unsafe = unsafe_exec(current);
    	security_bprm_apply_creds(bprm, unsafe);
    	task_unlock(current);
    	security_bprm_post_apply_creds(bprm);
    }
    
    EXPORT_SYMBOL(compute_creds);