Re: [PATCH v2 3/5] mac80211_hwsim: add generation count for netlink dump operation

[Benjamin Beichler <Benjamin.Beichler@uni-rostock.de>]

Am 11.12.2017 um 14:07 schrieb Johannes Berg:
> On Mon, 2017-12-11 at 14:02 +0100, Benjamin Beichler wrote:
>>> But you added this:
>>>
>>> +       /* list changed */
>>> +       if (cb->prev_seq && cb->seq !=3D cb->prev_seq)
>>> +               goto cleanup;
>>>
>>> which is mostly just a copy of the inline.
>>>
>>> johannes
>> Year you are right, but for nl_dump_check_consistent() I also need a
>> header struct to write the flag to it and I thought a ghost header onl=
y
>> to this function is also misleading. But if you think this is better, =
I
>> can do that. Or we introduce a function, which really only check
>> consistency and not also set the flag. I also thought the line is
>> readable at it's own, because it's simply inconsistent if the sequence=

>> numbers are not equal.
> It's readable, but there should be an indication to userspace in this
> case, no?
>
> johannes
>
Mhh, OK you are totally right.

I think we need to send something like an empty message, containing the
flag. Because there exist the corner case, that while a dump is
interrupted the complete list is deleted. Currently this could not
happen because of non-parallel netlink callbacks, but maybe in the
future parallel callbacks are enabled.

Would it break things, if I simply create an header with
HWSIM_CMD_GET_RADIO, but put no other information in it? Or how could it
be done correctly?

--=20
M.Sc. Benjamin Beichler

Universit=C3=A4t Rostock, Fakult=C3=A4t f=C3=BCr Informatik und Elektrote=
chnik
Institut f=C3=BCr Angewandte Mikroelektronik und Datentechnik

University of Rostock, Department of CS and EE
Institute of Applied Microelectronics and CE

Richard-Wagner-Stra=C3=9Fe 31
18119 Rostock
Deutschland/Germany

phone: +49 (0) 381 498 - 7278
email: Benjamin.Beichler@uni-rostock.de
www: http://www.imd.uni-rostock.de/