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>

1 files changed, 86 insertions, 2 deletions

diff --git a/fs/exec.c b/fs/exec.c
index f8135dc149b3..3698252719a3 100644
--- a/fs/exec.c
+++ b/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)