Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753198AbcD0QUG (ORCPT ); Wed, 27 Apr 2016 12:20:06 -0400 Received: from mail-oi0-f53.google.com ([209.85.218.53]:35393 "EHLO mail-oi0-f53.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752210AbcD0QUE (ORCPT ); Wed, 27 Apr 2016 12:20:04 -0400 MIME-Version: 1.0 X-Originating-IP: [108.49.39.189] In-Reply-To: <1461750975-2735137-1-git-send-email-arnd@arndb.de> References: <1461750975-2735137-1-git-send-email-arnd@arndb.de> Date: Wed, 27 Apr 2016 12:20:02 -0400 Message-ID: Subject: Re: [PATCH] tty: provide tty_name() even without CONFIG_TTY From: Paul Moore To: Arnd Bergmann Cc: Greg Kroah-Hartman , Jiri Slaby , Richard Guy Briggs , Peter Hurley , Rasmus Villemoes , linux-kernel@vger.kernel.org Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2009 Lines: 52 On Wed, Apr 27, 2016 at 5:56 AM, Arnd Bergmann wrote: > The audit subsystem just started printing the name of the tty, > but that causes a build failure when CONFIG_TTY is disabled: > > kernel/built-in.o: In function `audit_log_task_info': > memremap.c:(.text+0x5e34c): undefined reference to `tty_name' > kernel/built-in.o: In function `audit_set_loginuid': > memremap.c:(.text+0x63b34): undefined reference to `tty_name' > > This adds tty_name() to the list of functions that are provided > as trivial stubs in that configuration. > > Signed-off-by: Arnd Bergmann > Fixes: db0a6fb5d97a ("audit: add tty field to LOGIN event") > --- > include/linux/tty.h | 4 +++- > 1 file changed, 3 insertions(+), 1 deletion(-) Thanks for reporting this and providing a patch; I'll be happy to merge this into the audit#next branch with commit db0a6fb5d97a but I have one question (see below). > diff --git a/include/linux/tty.h b/include/linux/tty.h > index 3b09f235db66..17b247c94440 100644 > --- a/include/linux/tty.h > +++ b/include/linux/tty.h > @@ -371,6 +371,7 @@ extern void proc_clear_tty(struct task_struct *p); > extern struct tty_struct *get_current_tty(void); > /* tty_io.c */ > extern int __init tty_init(void); > +extern const char *tty_name(const struct tty_struct *tty); > #else > static inline void console_init(void) > { } > @@ -391,6 +392,8 @@ static inline struct tty_struct *get_current_tty(void) > /* tty_io.c */ > static inline int __init tty_init(void) > { return 0; } > +static inline const char *tty_name(const struct tty_struct *tty) > +{ return "(none)"; } > #endif As it currently stands tty_name() returns "NULL tty" when the passed tty_struct is NULL while this patch returns "(none)" in the case of CONFIG_TTY=n; it seems like some consistency might be good, yes? Or do you think there is value in differentiating between the two cases? >From an audit point of view, we would prefer if both were "(none)". -- paul moore www.paul-moore.com