exec.c

void remove_arg_zero(struct linux_binprm *bprm)
{
	if (bprm->argc) {
		unsigned long offset;
		char * kaddr;
		struct page *page;

		offset = bprm->p % PAGE_SIZE;
		goto inside;

		while (bprm->p++, *(kaddr+offset++)) {
			if (offset != PAGE_SIZE)
				continue;
			offset = 0;
			kunmap_atomic(kaddr, KM_USER0);
inside:
			page = bprm->page[bprm->p/PAGE_SIZE];
			kaddr = kmap_atomic(page, KM_USER0);
		}
		kunmap_atomic(kaddr, KM_USER0);
		bprm->argc--;
	}
}

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)
{
	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 = PAGE_SIZE*MAX_ARG_PAGES-sizeof(void *);

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

		/* Remember if the application is TASO.  */
		bprm->sh_bang = 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);
		for (fmt = formats ; fmt ; fmt = fmt->next) {
			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);
			if (retval >= 0) {
				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_KMOD
		}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);

/*
 * 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;
	int retval;
	int i;

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

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

	sched_exec();

	bprm->p = PAGE_SIZE*MAX_ARG_PAGES-sizeof(void *);

	bprm->file = file;
	bprm->filename = filename;
	bprm->interp = filename;
	bprm->mm = mm_alloc();
	retval = -ENOMEM;
	if (!bprm->mm)
		goto out_file;

	retval = init_new_context(current, bprm->mm);
	if (retval < 0)
		goto out_mm;

	bprm->argc = count(argv, bprm->p / sizeof(void *));
	if ((retval = bprm->argc) < 0)
		goto out_mm;

	bprm->envc = count(envp, bprm->p / sizeof(void *));
	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;

	retval = search_binary_handler(bprm,regs);
	if (retval >= 0) {
		free_arg_pages(bprm);

		/* execve success */
		security_bprm_free(bprm);
		acct_update_integrals(current);
		kfree(bprm);
		return retval;
	}

out:
	/* Something went wrong, return the inode and free the argument pages*/
	for (i = 0 ; i < MAX_ARG_PAGES ; i++) {
		struct page * page = bprm->page[i];
		if (page)
			__free_page(page);
	}

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

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

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

out_kfree:
	kfree(bprm);

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);

#define CORENAME_MAX_SIZE 64

/* 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 void format_corename(char *corename, const char *pattern, long signr)
{
	const char *pat_ptr = pattern;
	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", current->tgid);
				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", system_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;
			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 */
	if (!pid_in_pattern
            && (core_uses_pid || atomic_read(&current->mm->mm_users) != 1)) {
		rc = snprintf(out_ptr, out_end - out_ptr,
			      ".%d", current->tgid);
		if (rc > out_end - out_ptr)
			goto out;
		out_ptr += rc;
	}
      out:
	*out_ptr = 0;
}

static void zap_threads (struct mm_struct *mm)
{
	struct task_struct *g, *p;
	struct task_struct *tsk = current;
	struct completion *vfork_done = tsk->vfork_done;
	int traced = 0;

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

	read_lock(&tasklist_lock);
	do_each_thread(g,p)
		if (mm == p->mm && p != tsk) {
			force_sig_specific(SIGKILL, p);
			mm->core_waiters++;
			if (unlikely(p->ptrace) &&
			    unlikely(p->parent->mm == mm))
				traced = 1;
		}
	while_each_thread(g,p);

	read_unlock(&tasklist_lock);

	if (unlikely(traced)) {
		/*
		 * We are zapping a thread and the thread it ptraces.
		 * If the tracee went into a ptrace stop for exit tracing,
		 * we could deadlock since the tracer is waiting for this
		 * coredump to finish.  Detach them so they can both die.
		 */
		write_lock_irq(&tasklist_lock);
		do_each_thread(g,p) {
			if (mm == p->mm && p != tsk &&
			    p->ptrace && p->parent->mm == mm) {
				__ptrace_detach(p, 0);
			}
		} while_each_thread(g,p);
		write_unlock_irq(&tasklist_lock);
	}
}

static void coredump_wait(struct mm_struct *mm)
{
	DECLARE_COMPLETION(startup_done);
	int core_waiters;

	mm->core_startup_done = &startup_done;

	zap_threads(mm);
	core_waiters = mm->core_waiters;
	up_write(&mm->mmap_sem);

	if (core_waiters)
		wait_for_completion(&startup_done);
	BUG_ON(mm->core_waiters);
}

int do_coredump(long signr, int exit_code, struct pt_regs * regs)
{
	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;

	binfmt = current->binfmt;
	if (!binfmt || !binfmt->core_dump)
		goto fail;
	down_write(&mm->mmap_sem);
	if (!mm->dumpable) {
		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 (mm->dumpable == 2) {	/* Setuid core dump mode */
		flag = O_EXCL;		/* Stop rewrite attacks */
		current->fsuid = 0;	/* Dump root private */
	}
	mm->dumpable = 0;

	retval = -EAGAIN;
	spin_lock_irq(&current->sighand->siglock);
	if (!(current->signal->flags & SIGNAL_GROUP_EXIT)) {
		current->signal->flags = SIGNAL_GROUP_EXIT;
		current->signal->group_exit_code = exit_code;
		current->signal->group_stop_count = 0;
		retval = 0;
	}
	spin_unlock_irq(&current->sighand->siglock);
	if (retval) {
		up_write(&mm->mmap_sem);
		goto fail;
	}

	init_completion(&mm->core_done);
	coredump_wait(mm);

	/*
	 * 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);

	if (current->signal->rlim[RLIMIT_CORE].rlim_cur < binfmt->min_coredump)
		goto fail_unlock;

	/*
	 * lock_kernel() because format_corename() is controlled by sysctl, which
	 * uses lock_kernel()
	 */
 	lock_kernel();
	format_corename(corename, core_pattern, signr);
	unlock_kernel();
	file = filp_open(corename, O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag, 0600);
	if (IS_ERR(file))
		goto fail_unlock;
	inode = file->f_dentry->d_inode;
	if (inode->i_nlink > 1)
		goto close_fail;	/* multiple links - don't dump */
	if (d_unhashed(file->f_dentry))
		goto close_fail;

	if (!S_ISREG(inode->i_mode))
		goto close_fail;
	if (!file->f_op)
		goto close_fail;
	if (!file->f_op->write)
		goto close_fail;
	if (do_truncate(file->f_dentry, 0, 0, file) != 0)
		goto close_fail;

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

	if (retval)
		current->signal->group_exit_code |= 0x80;
close_fail:
	filp_close(file, NULL);
fail_unlock:
	current->fsuid = fsuid;
	complete_all(&mm->core_done);
fail:
	return retval;
}