Revert "ALSA: firewire-lib: change structure member with proper type"
diff mbox

Message ID 20170105004131.19202-1-o-takashi@sakamocchi.jp
State New
Headers show

Commit Message

Takashi Sakamoto Jan. 5, 2017, 12:41 a.m. UTC
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.
---
 sound/firewire/amdtp-stream.c | 2 +-
 sound/firewire/amdtp-stream.h | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

Comments

Takashi Iwai Jan. 5, 2017, 6:34 a.m. UTC | #1
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.


Takashi
Takashi Sakamoto Jan. 5, 2017, 7:14 a.m. UTC | #2
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?


Thanks

Takashi Sakamoto
Takashi Iwai Jan. 5, 2017, 7:41 a.m. UTC | #3
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

Patch
diff mbox

diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c
index 8ce93cd..00060c4 100644
--- a/sound/firewire/amdtp-stream.c
+++ b/sound/firewire/amdtp-stream.c
@@ -69,7 +69,7 @@  static void pcm_period_tasklet(unsigned long data);
  * @protocol_size: the size to allocate newly for protocol
  */
 int amdtp_stream_init(struct amdtp_stream *s, struct fw_unit *unit,
-		      enum amdtp_stream_direction dir, int flags,
+		      enum amdtp_stream_direction dir, enum cip_flags flags,
 		      unsigned int fmt,
 		      amdtp_stream_process_data_blocks_t process_data_blocks,
 		      unsigned int protocol_size)
diff --git a/sound/firewire/amdtp-stream.h b/sound/firewire/amdtp-stream.h
index 7be2142..c1bc7fa 100644
--- a/sound/firewire/amdtp-stream.h
+++ b/sound/firewire/amdtp-stream.h
@@ -93,7 +93,7 @@  typedef unsigned int (*amdtp_stream_process_data_blocks_t)(
 						unsigned int *syt);
 struct amdtp_stream {
 	struct fw_unit *unit;
-	int flags;
+	enum cip_flags flags;
 	enum amdtp_stream_direction direction;
 	struct mutex mutex;
 
@@ -137,7 +137,7 @@  struct amdtp_stream {
 };
 
 int amdtp_stream_init(struct amdtp_stream *s, struct fw_unit *unit,
-		      enum amdtp_stream_direction dir, int flags,
+		      enum amdtp_stream_direction dir, enum cip_flags flags,
 		      unsigned int fmt,
 		      amdtp_stream_process_data_blocks_t process_data_blocks,
 		      unsigned int protocol_size);