exec.c

	current->flags &= ~PF_RANDOMIZE;
	flush_thread();

	/* Set the new mm task size. We have to do that late because it may
	 * depend on TIF_32BIT which is only updated in flush_thread() on
	 * some architectures like powerpc
	 */
	current->mm->task_size = TASK_SIZE;

	if (bprm->e_uid != current->euid || bprm->e_gid != current->egid) {
		suid_keys(current);
		set_dumpable(current->mm, suid_dumpable);
		current->pdeath_signal = 0;
	} else if (file_permission(bprm->file, MAY_READ) ||
			(bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP)) {
		suid_keys(current);
		set_dumpable(current->mm, suid_dumpable);
	}

	/* 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;

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_path.dentry->d_inode;
	int retval;

	mode = inode->i_mode;
	if (bprm->file->f_op == NULL)
		return -EACCES;

	bprm->e_uid = current->euid;
	bprm->e_gid = current->egid;

	if(!(bprm->file->f_path.mnt->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)
{
	int unsafe = tracehook_unsafe_exec(p);

	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);
		current->pdeath_signal = 0;
	}
	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);

/*
 * Arguments are '\0' separated strings found at the location bprm->p
 * points to; chop off the first by relocating brpm->p to right after
 * the first '\0' encountered.
 */
int remove_arg_zero(struct linux_binprm *bprm)
{
	int ret = 0;
	unsigned long offset;
	char *kaddr;
	struct page *page;

	if (!bprm->argc)
		return 0;

	do {
		offset = bprm->p & ~PAGE_MASK;
		page = get_arg_page(bprm, bprm->p, 0);
		if (!page) {
			ret = -EFAULT;
			goto out;
		}
		kaddr = kmap_atomic(page, KM_USER0);

		for (; offset < PAGE_SIZE && kaddr[offset];
				offset++, bprm->p++)
			;

		kunmap_atomic(kaddr, KM_USER0);
		put_arg_page(page);

		if (offset == PAGE_SIZE)
			free_arg_page(bprm, (bprm->p >> PAGE_SHIFT) - 1);
	} while (offset == PAGE_SIZE);

	bprm->p++;
	bprm->argc--;
	ret = 0;

out:
	return ret;
}
EXPORT_SYMBOL(remove_arg_zero);

/*
 * cycle the list of binary formats handler, until one recognizes the image
 */
int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
{
	unsigned int depth = bprm->recursion_depth;
	int try,retval;
	struct linux_binfmt *fmt;
#ifdef __alpha__
	/* handle /sbin/loader.. */
	{
	    struct exec * eh = (struct exec *) bprm->buf;

	    if (!bprm->loader && eh->fh.f_magic == 0x183 &&
		(eh->fh.f_flags & 0x3000) == 0x3000)
	    {
		struct file * file;
		unsigned long loader;

		allow_write_access(bprm->file);
		fput(bprm->file);
		bprm->file = NULL;

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

		file = open_exec("/sbin/loader");
		retval = PTR_ERR(file);
		if (IS_ERR(file))
			return retval;

		/* Remember if the application is TASO.  */
		bprm->taso = eh->ah.entry < 0x100000000UL;

		bprm->file = file;
		bprm->loader = loader;
		retval = prepare_binprm(bprm);
		if (retval<0)
			return retval;
		/* should call search_binary_handler recursively here,
		   but it does not matter */
	    }
	}
#endif
	retval = security_bprm_check(bprm);
	if (retval)
		return retval;

	/* kernel module loader fixup */
	/* so we don't try to load run modprobe in kernel space. */
	set_fs(USER_DS);

	retval = audit_bprm(bprm);
	if (retval)
		return retval;

	retval = -ENOENT;
	for (try=0; try<2; try++) {
		read_lock(&binfmt_lock);
		list_for_each_entry(fmt, &formats, lh) {
			int (*fn)(struct linux_binprm *, struct pt_regs *) = fmt->load_binary;
			if (!fn)
				continue;
			if (!try_module_get(fmt->module))
				continue;
			read_unlock(&binfmt_lock);
			retval = fn(bprm, regs);
			/*
			 * Restore the depth counter to its starting value
			 * in this call, so we don't have to rely on every
			 * load_binary function to restore it on return.
			 */
			bprm->recursion_depth = depth;
			if (retval >= 0) {
				if (depth == 0)
					tracehook_report_exec(fmt, bprm, regs);
				put_binfmt(fmt);
				allow_write_access(bprm->file);
				if (bprm->file)
					fput(bprm->file);
				bprm->file = NULL;
				current->did_exec = 1;
				proc_exec_connector(current);
				return retval;
			}
			read_lock(&binfmt_lock);
			put_binfmt(fmt);
			if (retval != -ENOEXEC || bprm->mm == NULL)
				break;
			if (!bprm->file) {
				read_unlock(&binfmt_lock);
				return retval;
			}
		}
		read_unlock(&binfmt_lock);
		if (retval != -ENOEXEC || bprm->mm == NULL) {
			break;
#ifdef CONFIG_MODULES
		} else {
#define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e))
			if (printable(bprm->buf[0]) &&
			    printable(bprm->buf[1]) &&
			    printable(bprm->buf[2]) &&
			    printable(bprm->buf[3]))
				break; /* -ENOEXEC */
			request_module("binfmt-%04x", *(unsigned short *)(&bprm->buf[2]));
#endif
		}
	}
	return retval;
}

EXPORT_SYMBOL(search_binary_handler);

void free_bprm(struct linux_binprm *bprm)
{
	free_arg_pages(bprm);
	kfree(bprm);
}

/*
 * sys_execve() executes a new program.
 */
int do_execve(char * filename,
	char __user *__user *argv,
	char __user *__user *envp,
	struct pt_regs * regs)
{
	struct linux_binprm *bprm;
	struct file *file;
	struct files_struct *displaced;
	int retval;

	retval = unshare_files(&displaced);
	if (retval)
		goto out_ret;

	retval = -ENOMEM;
	bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
	if (!bprm)
		goto out_files;

	file = open_exec(filename);
	retval = PTR_ERR(file);
	if (IS_ERR(file))
		goto out_kfree;

	sched_exec();

	bprm->file = file;
	bprm->filename = filename;
	bprm->interp = filename;

	retval = bprm_mm_init(bprm);
	if (retval)
		goto out_file;

	bprm->argc = count(argv, MAX_ARG_STRINGS);
	if ((retval = bprm->argc) < 0)
		goto out_mm;

	bprm->envc = count(envp, MAX_ARG_STRINGS);
	if ((retval = bprm->envc) < 0)
		goto out_mm;

	retval = security_bprm_alloc(bprm);
	if (retval)
		goto out;

	retval = prepare_binprm(bprm);
	if (retval < 0)
		goto out;

	retval = copy_strings_kernel(1, &bprm->filename, bprm);
	if (retval < 0)
		goto out;

	bprm->exec = bprm->p;
	retval = copy_strings(bprm->envc, envp, bprm);
	if (retval < 0)
		goto out;

	retval = copy_strings(bprm->argc, argv, bprm);
	if (retval < 0)
		goto out;

	current->flags &= ~PF_KTHREAD;
	retval = search_binary_handler(bprm,regs);
	if (retval >= 0) {
		/* execve success */
		security_bprm_free(bprm);
		acct_update_integrals(current);
		free_bprm(bprm);
		if (displaced)
			put_files_struct(displaced);
		return retval;
	}

out:
	if (bprm->security)
		security_bprm_free(bprm);

out_mm:
	if (bprm->mm)
		mmput (bprm->mm);

out_file:
	if (bprm->file) {
		allow_write_access(bprm->file);
		fput(bprm->file);
	}
out_kfree:
	free_bprm(bprm);

out_files:
	if (displaced)
		reset_files_struct(displaced);
out_ret:
	return retval;
}

int set_binfmt(struct linux_binfmt *new)
{
	struct linux_binfmt *old = current->binfmt;

	if (new) {
		if (!try_module_get(new->module))
			return -1;
	}
	current->binfmt = new;
	if (old)
		module_put(old->module);
	return 0;
}

EXPORT_SYMBOL(set_binfmt);

/* format_corename will inspect the pattern parameter, and output a
 * name into corename, which must have space for at least
 * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator.
 */
static int format_corename(char *corename, long signr)
{
	const char *pat_ptr = core_pattern;
	int ispipe = (*pat_ptr == '|');
	char *out_ptr = corename;
	char *const out_end = corename + CORENAME_MAX_SIZE;
	int rc;
	int pid_in_pattern = 0;

	/* Repeat as long as we have more pattern to process and more output
	   space */
	while (*pat_ptr) {
		if (*pat_ptr != '%') {
			if (out_ptr == out_end)
				goto out;
			*out_ptr++ = *pat_ptr++;
		} else {
			switch (*++pat_ptr) {
			case 0:
				goto out;
			/* Double percent, output one percent */
			case '%':
				if (out_ptr == out_end)
					goto out;
				*out_ptr++ = '%';
				break;
			/* pid */
			case 'p':
				pid_in_pattern = 1;
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%d", task_tgid_vnr(current));
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			/* uid */
			case 'u':
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%d", current->uid);
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			/* gid */
			case 'g':
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%d", current->gid);
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			/* signal that caused the coredump */
			case 's':
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%ld", signr);
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			/* UNIX time of coredump */
			case 't': {
				struct timeval tv;
				do_gettimeofday(&tv);
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%lu", tv.tv_sec);
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			}
			/* hostname */
			case 'h':
				down_read(&uts_sem);
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%s", utsname()->nodename);
				up_read(&uts_sem);
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			/* executable */
			case 'e':
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%s", current->comm);
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			/* core limit size */
			case 'c':
				rc = snprintf(out_ptr, out_end - out_ptr,
					      "%lu", current->signal->rlim[RLIMIT_CORE].rlim_cur);
				if (rc > out_end - out_ptr)
					goto out;
				out_ptr += rc;
				break;
			default:
				break;
			}
			++pat_ptr;
		}
	}
	/* Backward compatibility with core_uses_pid:
	 *
	 * If core_pattern does not include a %p (as is the default)
	 * and core_uses_pid is set, then .%pid will be appended to
	 * the filename. Do not do this for piped commands. */
	if (!ispipe && !pid_in_pattern && core_uses_pid) {
		rc = snprintf(out_ptr, out_end - out_ptr,
			      ".%d", task_tgid_vnr(current));
		if (rc > out_end - out_ptr)
			goto out;
		out_ptr += rc;
	}
out:
	*out_ptr = 0;
	return ispipe;
}

static int zap_process(struct task_struct *start)
{
	struct task_struct *t;
	int nr = 0;

	start->signal->flags = SIGNAL_GROUP_EXIT;
	start->signal->group_stop_count = 0;

	t = start;
	do {
		if (t != current && t->mm) {
			sigaddset(&t->pending.signal, SIGKILL);
			signal_wake_up(t, 1);
			nr++;
		}
	} while_each_thread(start, t);

	return nr;
}

static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
				struct core_state *core_state, int exit_code)
{
	struct task_struct *g, *p;
	unsigned long flags;
	int nr = -EAGAIN;

	spin_lock_irq(&tsk->sighand->siglock);
	if (!signal_group_exit(tsk->signal)) {
		mm->core_state = core_state;
		tsk->signal->group_exit_code = exit_code;
		nr = zap_process(tsk);
	}
	spin_unlock_irq(&tsk->sighand->siglock);
	if (unlikely(nr < 0))
		return nr;

	if (atomic_read(&mm->mm_users) == nr + 1)
		goto done;
	/*
	 * We should find and kill all tasks which use this mm, and we should
	 * count them correctly into ->nr_threads. We don't take tasklist
	 * lock, but this is safe wrt:
	 *
	 * fork:
	 *	None of sub-threads can fork after zap_process(leader). All
	 *	processes which were created before this point should be
	 *	visible to zap_threads() because copy_process() adds the new
	 *	process to the tail of init_task.tasks list, and lock/unlock
	 *	of ->siglock provides a memory barrier.
	 *
	 * do_exit:
	 *	The caller holds mm->mmap_sem. This means that the task which
	 *	uses this mm can't pass exit_mm(), so it can't exit or clear
	 *	its ->mm.
	 *
	 * de_thread:
	 *	It does list_replace_rcu(&leader->tasks, &current->tasks),
	 *	we must see either old or new leader, this does not matter.
	 *	However, it can change p->sighand, so lock_task_sighand(p)
	 *	must be used. Since p->mm != NULL and we hold ->mmap_sem
	 *	it can't fail.
	 *
	 *	Note also that "g" can be the old leader with ->mm == NULL
	 *	and already unhashed and thus removed from ->thread_group.
	 *	This is OK, __unhash_process()->list_del_rcu() does not
	 *	clear the ->next pointer, we will find the new leader via
	 *	next_thread().
	 */
	rcu_read_lock();
	for_each_process(g) {
		if (g == tsk->group_leader)
			continue;
		if (g->flags & PF_KTHREAD)
			continue;
		p = g;
		do {
			if (p->mm) {
				if (unlikely(p->mm == mm)) {
					lock_task_sighand(p, &flags);
					nr += zap_process(p);
					unlock_task_sighand(p, &flags);
				}
				break;
			}
		} while_each_thread(g, p);
	}
	rcu_read_unlock();
done:
	atomic_set(&core_state->nr_threads, nr);
	return nr;
}

static int coredump_wait(int exit_code, struct core_state *core_state)
{
	struct task_struct *tsk = current;
	struct mm_struct *mm = tsk->mm;
	struct completion *vfork_done;
	int core_waiters;

	init_completion(&core_state->startup);
	core_state->dumper.task = tsk;
	core_state->dumper.next = NULL;
	core_waiters = zap_threads(tsk, mm, core_state, exit_code);
	up_write(&mm->mmap_sem);

	if (unlikely(core_waiters < 0))
		goto fail;

	/*
	 * Make sure nobody is waiting for us to release the VM,
	 * otherwise we can deadlock when we wait on each other
	 */
	vfork_done = tsk->vfork_done;
	if (vfork_done) {
		tsk->vfork_done = NULL;
		complete(vfork_done);
	}

	if (core_waiters)
		wait_for_completion(&core_state->startup);
fail:
	return core_waiters;
}

static void coredump_finish(struct mm_struct *mm)
{
	struct core_thread *curr, *next;
	struct task_struct *task;

	next = mm->core_state->dumper.next;
	while ((curr = next) != NULL) {
		next = curr->next;
		task = curr->task;
		/*
		 * see exit_mm(), curr->task must not see
		 * ->task == NULL before we read ->next.
		 */
		smp_mb();
		curr->task = NULL;
		wake_up_process(task);
	}

	mm->core_state = NULL;
}

/*
 * set_dumpable converts traditional three-value dumpable to two flags and
 * stores them into mm->flags.  It modifies lower two bits of mm->flags, but
 * these bits are not changed atomically.  So get_dumpable can observe the
 * intermediate state.  To avoid doing unexpected behavior, get get_dumpable
 * return either old dumpable or new one by paying attention to the order of
 * modifying the bits.
 *
 * dumpable |   mm->flags (binary)
 * old  new | initial interim  final
 * ---------+-----------------------
 *  0    1  |   00      01      01
 *  0    2  |   00      10(*)   11
 *  1    0  |   01      00      00
 *  1    2  |   01      11      11
 *  2    0  |   11      10(*)   00
 *  2    1  |   11      11      01
 *
 * (*) get_dumpable regards interim value of 10 as 11.
 */
void set_dumpable(struct mm_struct *mm, int value)
{
	switch (value) {
	case 0:
		clear_bit(MMF_DUMPABLE, &mm->flags);
		smp_wmb();
		clear_bit(MMF_DUMP_SECURELY, &mm->flags);
		break;
	case 1:
		set_bit(MMF_DUMPABLE, &mm->flags);
		smp_wmb();
		clear_bit(MMF_DUMP_SECURELY, &mm->flags);
		break;
	case 2:
		set_bit(MMF_DUMP_SECURELY, &mm->flags);
		smp_wmb();
		set_bit(MMF_DUMPABLE, &mm->flags);
		break;
	}
}

int get_dumpable(struct mm_struct *mm)
{
	int ret;

	ret = mm->flags & 0x3;
	return (ret >= 2) ? 2 : ret;
}

int do_coredump(long signr, int exit_code, struct pt_regs * regs)
{
	struct core_state core_state;
	char corename[CORENAME_MAX_SIZE + 1];
	struct mm_struct *mm = current->mm;
	struct linux_binfmt * binfmt;
	struct inode * inode;
	struct file * file;
	int retval = 0;
	int fsuid = current->fsuid;
	int flag = 0;
	int ispipe = 0;
	unsigned long core_limit = current->signal->rlim[RLIMIT_CORE].rlim_cur;
	char **helper_argv = NULL;
	int helper_argc = 0;
	char *delimit;

	audit_core_dumps(signr);

	binfmt = current->binfmt;
	if (!binfmt || !binfmt->core_dump)
		goto fail;
	down_write(&mm->mmap_sem);
	/*
	 * If another thread got here first, or we are not dumpable, bail out.
	 */
	if (mm->core_state || !get_dumpable(mm)) {
		up_write(&mm->mmap_sem);
		goto fail;
	}

	/*
	 *	We cannot trust fsuid as being the "true" uid of the
	 *	process nor do we know its entire history. We only know it
	 *	was tainted so we dump it as root in mode 2.
	 */
	if (get_dumpable(mm) == 2) {	/* Setuid core dump mode */
		flag = O_EXCL;		/* Stop rewrite attacks */
		current->fsuid = 0;	/* Dump root private */
	}

	retval = coredump_wait(exit_code, &core_state);
	if (retval < 0)
		goto fail;

	/*
	 * Clear any false indication of pending signals that might
	 * be seen by the filesystem code called to write the core file.
	 */
	clear_thread_flag(TIF_SIGPENDING);

	/*
	 * lock_kernel() because format_corename() is controlled by sysctl, which
	 * uses lock_kernel()
	 */
 	lock_kernel();
	ispipe = format_corename(corename, signr);
	unlock_kernel();
	/*
	 * Don't bother to check the RLIMIT_CORE value if core_pattern points
	 * to a pipe.  Since we're not writing directly to the filesystem
	 * RLIMIT_CORE doesn't really apply, as no actual core file will be
	 * created unless the pipe reader choses to write out the core file
	 * at which point file size limits and permissions will be imposed
	 * as it does with any other process
	 */
	if ((!ispipe) && (core_limit < binfmt->min_coredump))
		goto fail_unlock;

 	if (ispipe) {
		helper_argv = argv_split(GFP_KERNEL, corename+1, &helper_argc);
		/* Terminate the string before the first option */
		delimit = strchr(corename, ' ');
		if (delimit)
			*delimit = '\0';
		delimit = strrchr(helper_argv[0], '/');
		if (delimit)
			delimit++;
		else
			delimit = helper_argv[0];
		if (!strcmp(delimit, current->comm)) {
			printk(KERN_NOTICE "Recursive core dump detected, "
					"aborting\n");
			goto fail_unlock;
		}

		core_limit = RLIM_INFINITY;

		/* SIGPIPE can happen, but it's just never processed */
 		if (call_usermodehelper_pipe(corename+1, helper_argv, NULL,
				&file)) {
 			printk(KERN_INFO "Core dump to %s pipe failed\n",
			       corename);
 			goto fail_unlock;
 		}
 	} else
 		file = filp_open(corename,
				 O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag,
				 0600);
	if (IS_ERR(file))
		goto fail_unlock;
	inode = file->f_path.dentry->d_inode;
	if (inode->i_nlink > 1)
		goto close_fail;	/* multiple links - don't dump */
	if (!ispipe && d_unhashed(file->f_path.dentry))
		goto close_fail;

	/* AK: actually i see no reason to not allow this for named pipes etc.,
	   but keep the previous behaviour for now. */
	if (!ispipe && !S_ISREG(inode->i_mode))
		goto close_fail;
	/*
	 * Dont allow local users get cute and trick others to coredump
	 * into their pre-created files:
	 */
	if (inode->i_uid != current->fsuid)
		goto close_fail;
	if (!file->f_op)
		goto close_fail;
	if (!file->f_op->write)
		goto close_fail;
	if (!ispipe && do_truncate(file->f_path.dentry, 0, 0, file) != 0)
		goto close_fail;

	retval = binfmt->core_dump(signr, regs, file, core_limit);

	if (retval)
		current->signal->group_exit_code |= 0x80;
close_fail:
	filp_close(file, NULL);
fail_unlock:
	if (helper_argv)
		argv_free(helper_argv);

	current->fsuid = fsuid;
	coredump_finish(mm);
fail:
	return retval;
}