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 != 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 only >> 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? -- M.Sc. Benjamin Beichler Universität Rostock, Fakultät für Informatik und Elektrotechnik Institut für Angewandte Mikroelektronik und Datentechnik University of Rostock, Department of CS and EE Institute of Applied Microelectronics and CE Richard-Wagner-Straße 31 18119 Rostock Deutschland/Germany phone: +49 (0) 381 498 - 7278 email: benjamin.beich...@uni-rostock.de www: http://www.imd.uni-rostock.de/
