Subject: Re: [PATCH] tty: provide tty_name() even without CONFIG_TTY
To: Arnd Bergmann <arnd@arndb.de>, Paul Moore <paul@paul-moore.com>
References: <1461750975-2735137-1-git-send-email-arnd@arndb.de>
 <CAHC9VhT+ejGgD56EFnEh_bJmSUf4=WGhWjXEBSzGn-Su5FtThQ@mail.gmail.com>
 <7168707.KQDjLLKe2j@wuerfel>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        Jiri Slaby <jslaby@suse.com>, Richard Guy Briggs <rgb@redhat.com>,
        Rasmus Villemoes <linux@rasmusvillemoes.dk>,
        linux-kernel@vger.kernel.org
From: Peter Hurley <peter@hurleysoftware.com>
Message-ID: <5721030E.7000304@hurleysoftware.com>
Date: Wed, 27 Apr 2016 11:21:02 -0700
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20100101
 Thunderbird/38.6.0
MIME-Version: 1.0
In-Reply-To: <7168707.KQDjLLKe2j@wuerfel>
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1703
Lines: 38

On 04/27/2016 10:24 AM, Arnd Bergmann wrote:
> On Wednesday 27 April 2016 12:20:02 Paul Moore wrote:
>>> 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)".
> 
> Right, I noticed that the audit code prints "(none)" here while the
> tty code prints "NULL tty", and that meant I could not make it behave
> the same way as all the existing code. I picked "(none)" because
> in case of CONFIG_TTY being disabled that is more logical: it's
> not a NULL pointer because something went wrong, but instead the
> pointer doesn't matter and we know there is no tty.

Apologies for not having foreseen this in the review.
Arnd's solution looks good to me.