exec: load_script: Do not exec truncated interpreter path

Commit 8099b047ecc4 ("exec: load_script: don't blindly truncate
shebang string") was trying to protect against a confused exec of a
truncated interpreter path. However, it was overeager and also refused
to truncate arguments as well, which broke userspace, and it was
reverted. This attempts the protection again, but allows arguments to
remain truncated. In an effort to improve readability, helper functions
and comments have been added.

Co-developed-by: Linus Torvalds <[e-mail]>
Signed-off-by: Kees Cook <[e-mail]>
Cc: Andrew Morton <[e-mail]>
Cc: Oleg Nesterov <[e-mail]>
Cc: Samuel Dionne-Riel <[e-mail]>
Cc: Richard Weinberger <[e-mail]>
Cc: Graham Christensen <[e-mail]>
Cc: Michal Hocko <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

fs/binfmt_script.c

···
 #include <linux/err.h>
 #include <linux/fs.h>
 
+static inline bool spacetab(char c) { return c == ' ' || c == '\t'; }
+static inline char *next_non_spacetab(char *first, const char *last)
+{
+	for (; first <= last; first++)
+		if (!spacetab(*first))
+			return first;
+	return NULL;
+}
+static inline char *next_terminator(char *first, const char *last)
+{
+	for (; first <= last; first++)
+		if (spacetab(*first) || !*first)
+			return first;
+	return NULL;
+}
+
 static int load_script(struct linux_binprm *bprm)
 {
 	const char *i_arg, *i_name;
-	char *cp;
+	char *cp, *buf_end;
 	struct file *file;
 	int retval;
 
+	/* Not ours to exec if we don't start with "#!". */
 	if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!'))
 		return -ENOEXEC;
 
···
 	if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
 		return -ENOENT;
 
-	/*
-	 * This section does the #! interpretation.
-	 * Sorta complicated, but hopefully it will work.  -TYT
-	 */
-
+	/* Release since we are not mapping a binary into memory. */
 	allow_write_access(bprm->file);
 	fput(bprm->file);
 	bprm->file = NULL;
 
-	bprm->buf[BINPRM_BUF_SIZE - 1] = '\0';
-	if ((cp = strchr(bprm->buf, '\n')) == NULL)
-		cp = bprm->buf+BINPRM_BUF_SIZE-1;
+	/*
+	 * This section handles parsing the #! line into separate
+	 * interpreter path and argument strings. We must be careful
+	 * because bprm->buf is not yet guaranteed to be NUL-terminated
+	 * (though the buffer will have trailing NUL padding when the
+	 * file size was smaller than the buffer size).
+	 *
+	 * We do not want to exec a truncated interpreter path, so either
+	 * we find a newline (which indicates nothing is truncated), or
+	 * we find a space/tab/NUL after the interpreter path (which
+	 * itself may be preceded by spaces/tabs). Truncating the
+	 * arguments is fine: the interpreter can re-read the script to
+	 * parse them on its own.
+	 */
+	buf_end = bprm->buf + sizeof(bprm->buf) - 1;
+	cp = strnchr(bprm->buf, sizeof(bprm->buf), '\n');
+	if (!cp) {
+		cp = next_non_spacetab(bprm->buf + 2, buf_end);
+		if (!cp)
+			return -ENOEXEC; /* Entire buf is spaces/tabs */
+		/*
+		 * If there is no later space/tab/NUL we must assume the
+		 * interpreter path is truncated.
+		 */
+		if (!next_terminator(cp, buf_end))
+			return -ENOEXEC;
+		cp = buf_end;
+	}
+	/* NUL-terminate the buffer and any trailing spaces/tabs. */
 	*cp = '\0';
 	while (cp > bprm->buf) {
 		cp--;