> -----Original Message----- > From: Arend Van Spriel [mailto:arend.vanspriel@xxxxxxxxxxxx] > Sent: Sunday, September 18, 2016 22:54 > To: Luca Coelho <luca@xxxxxxxxx>; johannes@xxxxxxxxxxxxxxxx > Cc: linux-wireless@xxxxxxxxxxxxxxx; Beker, Ayala <ayala.beker@xxxxxxxxx>; > Otcheretianski, Andrei <andrei.otcheretianski@xxxxxxxxx>; Grumbach, > Emmanuel <emmanuel.grumbach@xxxxxxxxx>; Coelho, Luciano > <luciano.coelho@xxxxxxxxx> > Subject: Re: [PATCH v2 3/9] cfg80211: add add_nan_func / rm_nan_func > > On 16-9-2016 10:33, Luca Coelho wrote: > > From: Ayala Beker <ayala.beker@xxxxxxxxx> > > > > A NAN function can be either publish, subscribe or follow up. Make all > > the necessary verifications and just pass the request to the driver. > > Allow the user space application that starts NAN to forbid any other > > socket to add or remove functions. > > > > Signed-off-by: Andrei Otcheretianski <andrei.otcheretianski@xxxxxxxxx> > > Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@xxxxxxxxx> > > Signed-off-by: Ayala Beker <ayala.beker@xxxxxxxxx> > > Signed-off-by: Luca Coelho <luciano.coelho@xxxxxxxxx> > > --- > > [...] > > > diff --git a/include/uapi/linux/nl80211.h > > b/include/uapi/linux/nl80211.h index 7ab18c8..ab16c8e 100644 > > --- a/include/uapi/linux/nl80211.h > > +++ b/include/uapi/linux/nl80211.h > > @@ -847,6 +847,24 @@ > > * After this command NAN functions can be added. > > * @NL80211_CMD_STOP_NAN: Stop the NAN operation, identified by > > * its %NL80211_ATTR_WDEV interface. > > + * @NL80211_CMD_ADD_NAN_FUNCTION: Add a NAN function. The > function is defined > > + * with %NL80211_ATTR_NAN_FUNC nested attribute. When called, > this > > + * operation returns the strictly positive and unique instance id > > + * (%NL80211_ATTR_NAN_FUNC_INST_ID) and a cookie > (%NL80211_ATTR_COOKIE) > > + * of the function upon success. > > + * Since instance ID's can be re-used, this cookie is the right > > + * way to identify the function. This will avoid races when a termination > > + * event is handled by the user space after it has already added a new > > + * function that got the same instance id from the kernel as the one > > + * which just terminated. > > + * This cookie may be used in NAN events even before the command > > + * returns, so userspace shouldn't process NAN events until it > processes > > + * the response to this command. > > + * Look at %NL80211_ATTR_SOCKET_OWNER as well. > > + * @NL80211_CMD_RM_NAN_FUNCTION: Remove a NAN function by > cookie. > > + * This command is also used as a notification sent when a NAN function > is > > + * terminated. This will contain a %NL80211_ATTR_NAN_FUNC_INST_ID > > + * and %NL80211_ATTR_COOKIE attributes. > > This patch does not show the notification scenario as it is added in patch 6. So > those three lines could be added by that patch instead to keep things > logically together. > Good point. Thanks > Regards, > Arend
