Re: [PATCH] Revert "ALSA: firewire-lib: change structure member with proper type"

[Takashi Iwai <tiwai@suse.de>]

On Thu, 05 Jan 2017 08:14:22 +0100,
Takashi Sakamoto wrote:
> 
> On Jan 5 2017 15:34, Takashi Iwai wrote:
> > On Thu, 05 Jan 2017 01:41:31 +0100,
> > Takashi Sakamoto wrote:
> >>
> >> This reverts commit 6b7e95d1336b9eb0d4c6db190ce756480496bd13. This commit
> >> is based on a concern about value of the given parameter. It's expected
> >> to be ORed value with some enumeration-constants, thus often it can not be
> >> one of the enumeration-constants. I understood that this is out of
> >> specification and causes implementation-dependent issues.
> >>
> >> In C language specification, enumerated type can be interpreted as an
> >> integer type, in which all of enumeration-constants in corresponding
> >> enumerator-list can be stored. Implementations can select one of char,
> >> signed int and unsigned int as its type, and this selection is
> >> implementation-dependent.
> >>
> >> In GCC, a signed integer is selected when at least one of
> >> enumeration-constants has negative value, else an unsigned integer is
> >> selected. This behaviour can be switched by -fshort-enums to short type.
> >> Anyway, the type can be decided after scanning all of
> >> enumeration-constants.
> >>
> >> Totally, there's no rules to constrain the value of enumerated type to
> >> be one of enumeration-constants. In short, in enumerated type, decision
> >> of actual type for the type is the most important and
> >> enumeration-constants are just used for the decision, thus it's permitted
> >> to have an integer value in a range of enumeration-constants. In our case,
> >> actual type for the type is currently deterministic to be either char or
> >> unsigned int. Under GCC, it's unsigned int.
> >
> > You sign-off is missing.
> 
> Oops...
> 
> Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
> 
> Should I re-post this with the sign-off?

No, I applied with a manual adjustment now.  Thanks.


Takashi