❦ 21 septembre 2017 08:15 -0700, Stephen Hemminger
<step...@networkplumber.org> :
>> Currently, there is a difference in netlink events received when an
>> interface is modified through bridge ioctl() or through netlink. This
>> patch generates additional events when an interface is added to or
>> removed from a bridge via ioctl().
>>
>> When adding then removing an interface from a bridge with netlink, we
>> get:
>>
>> 5: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue master
>> bridge0 state UNKNOWN group default
>> link/ether 9e:da:60:ee:cf:c8 brd ff:ff:ff:ff:ff:ff
>> 5: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 master bridge0 state
>> UNKNOWN
>> link/ether 9e:da:60:ee:cf:c8
>> 5: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 master bridge0 state
>> UNKNOWN
>> link/ether 9e:da:60:ee:cf:c8
>> 5: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 master bridge0 state
>> UNKNOWN
>> link/ether 9e:da:60:ee:cf:c8
>> 5: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 master bridge0 state
>> UNKNOWN
>> link/ether 9e:da:60:ee:cf:c8
>> 5: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue master
>> bridge0 state UNKNOWN group default
>> link/ether 9e:da:60:ee:cf:c8 brd ff:ff:ff:ff:ff:ff
>>
>> 5: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue master
>> bridge0 state UNKNOWN group default
>> link/ether 9e:da:60:ee:cf:c8 brd ff:ff:ff:ff:ff:ff
>> 5: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 master bridge0 state
>> UNKNOWN
>> link/ether 9e:da:60:ee:cf:c8
>> Deleted 5: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 master bridge0
>> state UNKNOWN
>> link/ether 9e:da:60:ee:cf:c8
>> 5: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue state
>> UNKNOWN group default
>> link/ether 9e:da:60:ee:cf:c8 brd ff:ff:ff:ff:ff:ff
>>
>> When using ioctl():
>>
>> 5: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue master
>> bridge0 state UNKNOWN group default
>> link/ether 9e:da:60:ee:cf:c8 brd ff:ff:ff:ff:ff:ff
>> 5: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 master bridge0 state
>> UNKNOWN
>> link/ether 9e:da:60:ee:cf:c8
>> 5: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 master bridge0 state
>> UNKNOWN
>> link/ether 9e:da:60:ee:cf:c8
>> 5: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 master bridge0 state
>> UNKNOWN
>> link/ether 9e:da:60:ee:cf:c8
>> 5: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue master
>> bridge0 state UNKNOWN group default
>> link/ether 9e:da:60:ee:cf:c8 brd ff:ff:ff:ff:ff:ff
>>
>> 5: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue master
>> bridge0 state UNKNOWN group default
>> link/ether 9e:da:60:ee:cf:c8 brd ff:ff:ff:ff:ff:ff
>> 5: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 master bridge0 state
>> UNKNOWN
>> link/ether 9e:da:60:ee:cf:c8
>> Deleted 5: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 master bridge0
>> state UNKNOWN
>> link/ether 9e:da:60:ee:cf:c8
>> 5: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue state
>> UNKNOWN group default
>> link/ether 9e:da:60:ee:cf:c8 brd ff:ff:ff:ff:ff:ff
>>
>> Without this patch, the last netlink notification is not sent.
>>
>> Signed-off-by: Vincent Bernat <vinc...@bernat.im>
>
> This makes sense, you should probably add a Fixes: tag to help maintainers
> of long term stable kernels.
>
> Reviewed-by: Stephen Hemminger <step...@networkplumber.org>
I wouldn't know which commit would be fixed since this is not a
regression, just a behavior difference.
--
Make sure special cases are truly special.
- The Elements of Programming Style (Kernighan & Plauger)
