diff options
author | Takashi Sakamoto <o-takashi@sakamocchi.jp> | 2017-01-05 09:41:31 +0900 |
---|---|---|
committer | Takashi Iwai <tiwai@suse.de> | 2017-01-05 08:39:47 +0100 |
commit | e4f34cf6d59160818dcdcf41f4116cc88093ece3 (patch) | |
tree | 12e7b2cb15199014ebffff2c0d92550a66f189ac /Documentation | |
parent | 13a6c8328e6056932dc680e447d4c5e8ad9add17 (diff) |
Revert "ALSA: firewire-lib: change structure member with proper type"
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.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Diffstat (limited to 'Documentation')
0 files changed, 0 insertions, 0 deletions