exits, it causes a select() exception.
Handle these select() exceptions on link descriptors in pretty
much the same way as loss of carrier rather than dropping out
in confusion.
for our interface address. We're about to call ip_Input()
anyway, and ip_Input() does the PacketAliasIn().
Stack trace provided by: Cameron Grant <gandalf@vilnya.demon.co.uk>
match - otherwise, with a delayed (\\d) ``send'', the
timeout may happen during the send and cause a failure.
Problem reported by: David L. Vondrasek <dallas.tx@airmail.net>
are done in the same way as command execution.
For example, ``set proctitle USER INTERFACE PROCESSID'' would
be useful in a -direct profile for identifying who's connected.
for every machine on every class C or smaller subnet that we
route to.
Add ``set {send,recv}pipe'' for controlling our socket buffer
sizes.
Mention the IP number with the problem in a few error messages.
All submitted by: Craig Leres <leres@ee.lbl.gov>
Modified slightly by: me
like
tun0: flags=blah
10.0.0.1 -> 10.0.0.100
10.0.0.2 -> 10.0.0.100
10.0.0.3 -> 10.0.0.100
to DTRT, despite the SIOCAIFADDR for each new alias returning
-1 & EEXIST while adding the alias anyway. In real life, once
we have the second alias with the same destination, nothing will
route any more ! Also, because I was ignoring EEXIST, the
dynamic IP assignment code was assigning duplicate addresses
('cos it was being lied to by iface_inAdd()).
Now we have
tun0: flags=blah
10.0.0.1 -> 255.255.255.255
10.0.0.2 -> 10.0.0.100
10.0.0.3 -> 255.255.255.255
This works - stuff bound to 10.1 & 10.3 will be considered alive
by the kernel, and when they route back to the tun device, the
packets get aliased to 10.2 and go out to 10.100 (as with the
original plan).
We still see the EEXIST in SIOCAIFADDR, but ignore it when our
destination is 255.255.255.255, assuming that the alias *was*
actually added.
Additionally, ``iface add'' may now optionally be given only
the interface address. The mask & destination default to
255.255.255.255.
shortseq, authname and authkey.
o Auth{name,key} may additionally be set in PHASE_ESTABLISH.
o The others may be set in PHASE_ESTABLISH as long as no links
have yet reached DATALINK_LCP.
demand-dial links with dynamic IP numbers where the program
that causes the dial bind()s to an interface address that is
subsequently changed after ppp negotiation.
The problem is defeated by adding negotiated addresses to the
tun interface as additional alias addresses and providing a set
of ``iface'' commands for managing the interface. Libalias is
also required (and what a name clash!) - it happily IP-aliases
the address so that the source is that of the primary (negotiated)
interface and un-IP-aliases it on the way back.
An ``enable iface-alias'' is done implicitly by the -alias command
line switch. If -alias isn't given, iface-aliasing is disabled by
default and can't be enabled 'till an ``alias enable yes'' is done.
``alias enable no'' silently disables iface-alias.
So, for dynamic-IP-type-connections, running ``ppp -alias -auto blah''
will work for the first connection, although existing bindings will
not survive a disconnect/connect as the TCP peer will be trying to
send to the old IP address - the packets won't route.
It's now a lot easier to add IPXCP to ppp with minor updates to
the new iface.[ch] (if anyone ever gets 'round to it).
It's also now possible to manually add interface aliases with
something like ``iface add 1.2.3.4/24 5.6.7.8''. This allows
multi-homed ppp links :-)
command:
AUTHNAME: The local authname
ENDDISC: The local endpoint discriminator
LABEL: The configuration label in use
PEER_ENDDISC: The peers endpoint discriminator
USER: The peers authname
anything for two mintues (see ``set choked'' and ``show
bundle''), nuke the ip, mp and link level buffer queues.
This should fix problems where ``ppp -auto'' seems to stop
responding after failing to connect to the peer a few times.