exec: Implement kernel_execve

To allow the kernel not to play games with set_fs to call exec
implement kernel_execve.  The function kernel_execve takes pointers
into kernel memory and copies the values pointed to onto the new
userspace stack.

The calls with arguments from kernel space of do_execve are replaced
with calls to kernel_execve.

The calls do_execve and do_execveat are made static as there are now
no callers outside of exec.

The comments that mention do_execve are updated to refer to
kernel_execve or execve depending on the circumstances.  In addition
to correcting the comments, this makes it easy to grep for do_execve
and verify it is not used.

Inspired-by: https://lkml.kernel.org/r/20200627072704.2447163-1-hch@lst.de
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/87wo365ikj.fsf@x220.int.ebiederm.org
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

arch/x86/entry/entry_32.S

@@ -854,7 +854,7 @@ SYM_CODE_START(ret_from_fork)
 	CALL_NOSPEC ebx
 	/*
 	 * A kernel thread is allowed to return here after successfully
-	 * calling do_execve().  Exit to userspace to complete the execve()
+	 * calling kernel_execve().  Exit to userspace to complete the execve()
 	 * syscall.
 	 */
 	movl	$0, PT_EAX(%esp)

arch/x86/entry/entry_64.S

@@ -293,7 +293,7 @@ SYM_CODE_START(ret_from_fork)
 	CALL_NOSPEC rbx
 	/*
 	 * A kernel thread is allowed to return here after successfully
-	 * calling do_execve().  Exit to userspace to complete the execve()
+	 * calling kernel_execve().  Exit to userspace to complete the execve()
 	 * syscall.
 	 */
 	movq	$0, RAX(%rsp)

arch/x86/kernel/unwind_frame.c

@@ -275,7 +275,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		 * This user_mode() check is slightly broader than a PF_KTHREAD
 		 * check because it also catches the awkward situation where a
 		 * newly forked kthread transitions into a user task by calling
-		 * do_execve(), which eventually clears PF_KTHREAD.
+		 * kernel_execve(), which eventually clears PF_KTHREAD.
 		 */
 		if (!user_mode(regs))
 			goto the_end;

fs/exec.c

@@ -448,6 +448,23 @@ static int count(struct user_arg_ptr argv, int max)
 	return i;
 }
 
+static int count_strings_kernel(const char *const *argv)
+{
+	int i;
+
+	if (!argv)
+		return 0;
+
+	for (i = 0; argv[i]; ++i) {
+		if (i >= MAX_ARG_STRINGS)
+			return -E2BIG;
+		if (fatal_signal_pending(current))
+			return -ERESTARTNOHAND;
+		cond_resched();
+	}
+	return i;
+}
+
 static int bprm_stack_limits(struct linux_binprm *bprm)
 {
 	unsigned long limit, ptr_size;
@@ -624,6 +641,20 @@ int copy_string_kernel(const char *arg, struct linux_binprm *bprm)
 }
 EXPORT_SYMBOL(copy_string_kernel);
 
+static int copy_strings_kernel(int argc, const char *const *argv,
+			       struct linux_binprm *bprm)
+{
+	while (argc-- > 0) {
+		int ret = copy_string_kernel(argv[argc], bprm);
+		if (ret < 0)
+			return ret;
+		if (fatal_signal_pending(current))
+			return -ERESTARTNOHAND;
+		cond_resched();
+	}
+	return 0;
+}
+
 #ifdef CONFIG_MMU
 
 /*
@@ -1991,7 +2022,60 @@ out_ret:
 	return retval;
 }
 
-int do_execve(struct filename *filename,
+int kernel_execve(const char *kernel_filename,
+		  const char *const *argv, const char *const *envp)
+{
+	struct filename *filename;
+	struct linux_binprm *bprm;
+	int fd = AT_FDCWD;
+	int retval;
+
+	filename = getname_kernel(kernel_filename);
+	if (IS_ERR(filename))
+		return PTR_ERR(filename);
+
+	bprm = alloc_bprm(fd, filename);
+	if (IS_ERR(bprm)) {
+		retval = PTR_ERR(bprm);
+		goto out_ret;
+	}
+
+	retval = count_strings_kernel(argv);
+	if (retval < 0)
+		goto out_free;
+	bprm->argc = retval;
+
+	retval = count_strings_kernel(envp);
+	if (retval < 0)
+		goto out_free;
+	bprm->envc = retval;
+
+	retval = bprm_stack_limits(bprm);
+	if (retval < 0)
+		goto out_free;
+
+	retval = copy_string_kernel(bprm->filename, bprm);
+	if (retval < 0)
+		goto out_free;
+	bprm->exec = bprm->p;
+
+	retval = copy_strings_kernel(bprm->envc, envp, bprm);
+	if (retval < 0)
+		goto out_free;
+
+	retval = copy_strings_kernel(bprm->argc, argv, bprm);
+	if (retval < 0)
+		goto out_free;
+
+	retval = bprm_execve(bprm, fd, filename, 0);
+out_free:
+	free_bprm(bprm);
+out_ret:
+	putname(filename);
+	return retval;
+}
+
+static int do_execve(struct filename *filename,
 	const char __user *const __user *__argv,
 	const char __user *const __user *__envp)
 {
@@ -2000,7 +2084,7 @@ int do_execve(struct filename *filename,
 	return do_execveat_common(AT_FDCWD, filename, argv, envp, 0);
 }
 
-int do_execveat(int fd, struct filename *filename,
+static int do_execveat(int fd, struct filename *filename,
 		const char __user *const __user *__argv,
 		const char __user *const __user *__envp,
 		int flags)

include/linux/binfmts.h

@@ -135,12 +135,7 @@ int copy_string_kernel(const char *arg, struct linux_binprm *bprm);
 extern void set_binfmt(struct linux_binfmt *new);
 extern ssize_t read_code(struct file *, unsigned long, loff_t, size_t);
 
-extern int do_execve(struct filename *,
-		     const char __user * const __user *,
-		     const char __user * const __user *);
-extern int do_execveat(int, struct filename *,
-		       const char __user * const __user *,
-		       const char __user * const __user *,
-		       int);
+int kernel_execve(const char *filename,
+		  const char *const *argv, const char *const *envp);
 
 #endif /* _LINUX_BINFMTS_H */

init/main.c

@@ -1329,9 +1329,7 @@ static int run_init_process(const char *init_filename)
 	pr_debug("  with environment:\n");
 	for (p = envp_init; *p; p++)
 		pr_debug("    %s\n", *p);
-	return do_execve(getname_kernel(init_filename),
-		(const char __user *const __user *)argv_init,
-		(const char __user *const __user *)envp_init);
+	return kernel_execve(init_filename, argv_init, envp_init);
 }
 
 static int try_to_run_init_process(const char *init_filename)

kernel/umh.c

@@ -98,9 +98,9 @@ static int call_usermodehelper_exec_async(void *data)
 
 	commit_creds(new);
 
-	retval = do_execve(getname_kernel(sub_info->path),
-			   (const char __user *const __user *)sub_info->argv,
-			   (const char __user *const __user *)sub_info->envp);
+	retval = kernel_execve(sub_info->path,
+			       (const char *const *)sub_info->argv,
+			       (const char *const *)sub_info->envp);
 out:
 	sub_info->retval = retval;
 	/*

security/tomoyo/common.h

@@ -425,7 +425,7 @@ struct tomoyo_request_info {
 	struct tomoyo_obj_info *obj;
 	/*
 	 * For holding parameters specific to execve() request.
-	 * NULL if not dealing do_execve().
+	 * NULL if not dealing execve().
 	 */
 	struct tomoyo_execve *ee;
 	struct tomoyo_domain_info *domain;

security/tomoyo/domain.c

@@ -767,7 +767,7 @@ retry:
 
 	/*
 	 * Check for domain transition preference if "file execute" matched.
-	 * If preference is given, make do_execve() fail if domain transition
+	 * If preference is given, make execve() fail if domain transition
 	 * has failed, for domain transition preference should be used with
 	 * destination domain defined.
 	 */
@@ -810,7 +810,7 @@ force_reset_domain:
 		snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "<%s>",
 			 candidate->name);
 		/*
-		 * Make do_execve() fail if domain transition across namespaces
+		 * Make execve() fail if domain transition across namespaces
 		 * has failed.
 		 */
 		reject_on_transition_failure = true;

security/tomoyo/tomoyo.c

@@ -93,7 +93,7 @@ static int tomoyo_bprm_check_security(struct linux_binprm *bprm)
 	struct tomoyo_task *s = tomoyo_task(current);
 
 	/*
-	 * Execute permission is checked against pathname passed to do_execve()
+	 * Execute permission is checked against pathname passed to execve()
 	 * using current domain.
 	 */
 	if (!s->old_domain_info) {
@@ -307,7 +307,7 @@ static int tomoyo_file_fcntl(struct file *file, unsigned int cmd,
  */
 static int tomoyo_file_open(struct file *f)
 {
-	/* Don't check read permission here if called from do_execve(). */
+	/* Don't check read permission here if called from execve(). */
 	if (current->in_execve)
 		return 0;
 	return tomoyo_check_open_permission(tomoyo_domain(), &f->f_path,