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

Takashi Sakamoto o-takashi at sakamocchi.jp
Thu Jan 5 08:14:22 CET 2017


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 at sakamocchi.jp>

Should I re-post this with the sign-off?


Thanks

Takashi Sakamoto


More information about the Alsa-devel mailing list