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.
