The issue is that this hides the problem per se. The ioctl and pfctl loading of ruleset is not ready for handling failures here!
/me Does not understand why people do not ask for review first? On Tue, Sep 18, 2012 at 2:53 PM, Sergey Kandaurov <pluk...@freebsd.org> wrote: > On 18 September 2012 16:34, Gleb Smirnoff <gleb...@freebsd.org> wrote: >> Author: glebius >> Date: Tue Sep 18 12:34:35 2012 >> New Revision: 240646 >> URL: http://svn.freebsd.org/changeset/base/240646 >> >> Log: >> Do more than r236298 did in the projects/pf branch: use M_NOWAIT in >> altq_add() and its descendants. Currently altq(4) in FreeBSD is configured >> via pf(4) ioctls, which can't configure altq(4) w/o holding locks. >> Fortunately, altq(4) code in spife of using M_WAITOK is ready to receive >> NULL from malloc(9), so change is mostly mechanical. While here, utilize >> M_ZERO instead of bzero(). >> >> A large redesign needed to achieve M_WAITOK usage when configuring altq(4). >> Or an alternative (not pf(4)) configuration interface should be >> implemented. >> >> Reported by: pluknet > > Actually Kim Culhan was initial reporter. > I just reposted the problem closer to glebius and pointed out the roots. > > -- > wbr, > pluknet -- Ermal _______________________________________________ freebsd-pf@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-pf To unsubscribe, send any mail to "freebsd-pf-unsubscr...@freebsd.org"
