While merging rt30[79]0 support into rt28[67]0, drivers/staging/rt3070/md4.h
has been forgotten, while it isn't referenced from the remaining drivers
anymore; remove it.
Signed-off-by: NStefan Lippers-Hollmann <s.l-h@gmx.de>
Acked-by: NBartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Cc: Matti Lammi <mattij.lammi@gmail.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

I have fixed all errors in mlme.h and fixed all bar one in rtmp.h.
I think I can fix rtmp.h too by moving a brace up two lines, I just dont know if it will work.
If someone can confirm it will work I will change it.
Signed-off-by: NNeil Munro <neilmunro@gmail.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

VBIOS_VER_MAX_LENGTH was set to 4, but the value "0.84" is strcpy'd
into it.  That value is 5 long including the trailing NULL.
Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Remove 2 extern variables definations from XGI_accel.c that were
defined in other .h files.
Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

The code inside this #ifdef declared a couple extern functions that
weren't used anywhere, so remove the whole #ifdef
Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

This was not included anywhere and just defined a debugging macro.
Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

This removes all the remaining typedefs in vb_struct.h
Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

There is no need for these to be typedefs as a simple enum will do.
Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Remove code that was removed using #if 0
Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

PUCHAR was unsigned char *, use that instead
Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

The port related macros in osdef.h are replaced with calls to out?()
and in?().  This removes the last macros defined in osdef.h, so this
file is no longer needed.
Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

These were just macros for memset and memcpy, so use those instead.
Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Remove ifdefs that check LINUX_VERSION_CODE as this is
not needed in the staging tree.
Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

This fixes compiler warning  format '%x' expects type 'unsigned int',
but argument 2 has type 'long unsigned int'
Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Cc: Arnaud Patard <apatard@mandriva.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

The standard layer 3 ping utility can use the record route (RR) option
of IP to collect route data for sent ping messages (ping -R). This
patch introduces comparable functionality for batman-adv ICMP messages.

The patch adds a second batman ICMP packet format (icmp_packet_rr) such
that up to 17 MAC addresses can be recorded (sufficient for up to 8
hops per direction). When no RR is wanted, the old icmp_packet without
the RR overhead can be sent.
Signed-off-by: NDaniel Seither <post@tiwoc.de>
Signed-off-by: NMarek Lindner <lindner_marek@yahoo.de>
[sven.eckelmann@gmx.de: Rework on top of current version]
Signed-off-by: NSven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

This patch adds interface alternating to the new bonding feature. By
default, we now try to avoid forwarding packets on the receiving
interface, instead choosing alternative interfaces. This feature
works only on nodes which have multiple interfaces connected to the
mesh. This approach should reduce problems of the half-duplex nature
of WiFi Hardware and thus increase performance.
Signed-off-by: NSimon Wunderlich <siwu@hrz.tu-chemnitz.de>
Acked-by: NMarek Lindner <lindner_marek@yahoo.de>
[sven.eckelmann@gmx.de: Rework on top of current version]
Signed-off-by: NSven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

This patch introduces bonding functionality to batman-advanced, targeted
for the 0.3 release. As we are able to route the payload traffic as we
want, we may use multiple interfaces on multihomed hosts to transfer data
to achieve higher bandwidth. This can be considered as "light Multi Path
Routing" for single hop connections.

To detect which interfaces of a peer node belong to the same host, a
new flag PRIMARIES_FIRST_HOP is introduced. This flag is set on the first hop
of OGMs of the primary (first) interface, which is broadcasted on all
interfaces. When receiving such an OGM, we can learn which interfaces
belong to the same host (by assigning them to the primary originator).

Bonding works by sending packets in a round-robin fashion to the available
interfaces of a neighbor host, if multiple interfaces are available. The
neighbor interfaces should be almost equally good to reach.

To avoid interferences (i.e. sending on the same channel), only neighbor
interfaces with different mac addresses and different outgoing interfaces
are considered as candidates.

Bonding is deactivated by default, and can be activated by

echo 1 > /sys/class/net/bat0/mesh/bonding

for each individual node.
Signed-off-by: NSimon Wunderlich <siwu@hrz.tu-chemnitz.de>
[sven.eckelmann@gmx.de: Rework on top of current version]
Signed-off-by: NSven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

This patch changes the sequence number range from 8 or 16 bit to 32 bit.
This should avoid problems with the sequence number sliding window algorithm
which we had seen in the past for broadcast floods or malicious packet
injections. We can not assure 100% security with this patch, but it is quite
an improvement over the old 16 bit sequence numbers:

 * expected window size can be increased (4096 -> 65536)
 * 64k packets in the right order would now be needed to cause a loop,
   which seems practically impossible.

Furthermore, a TTL field has been added to the broadcast packet type, just to
make sure.

These changes required to increase the compatibility level once again.
Signed-off-by: NSimon Wunderlich <siwu@hrz.tu-chemnitz.de>
[sven.eckelmann@gmx.de: Change atomic64_* back to atomic_*, Rework on
top of current version]
Signed-off-by: NSven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NSimon Wunderlich <siwu@hrz.tu-chemnitz.de>
Signed-off-by: NSven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

When trying to set the originator interval to 40ms, we are asked to set
it to a minimum value of 40ms. This patch permits setting an
originator interval of JITTER*2 (40ms by default) now.
Signed-off-by: NLinus Lüssing <linus.luessing@web.de>
Signed-off-by: NSimon Wunderlich <siwu@hrz.tu-chemnitz.de>
Signed-off-by: NSven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

All code for debugfs is ignored when the creation of the batman-adv root
directory in debugfs fails. It must also be ignored when the
debugfs_create_dir tells us that debugfs is not implemented to prevent
possible crashes in the future.
Signed-off-by: NSven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Functions and variables which are used only inside one object file can
be declared as static. This helped to find unused functions/variables

 * mainIfAddr_default
 * main_if_was_up

and functions with declarations but missing definitions

 * hash_debug
 * orig_find
 * send_own_packet_work
Signed-off-by: NSven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Remove the last uses of MAC_FMT
Signed-off-by: NJoe Perches <joe@perches.com>
[sven.eckelmann@gmx.de: Adapted for current batman-adv version]
Signed-off-by: NSven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Signed-off-by: NMarek Lindner <lindner_marek@yahoo.de>
[sven.eckelmann@gmx.de: Rework on top of current version]
Signed-off-by: NSven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

This patch removes the extra usage output which came when
the sysfs files were read.
Signed-off-by: NMarek Lindner <lindner_marek@yahoo.de>
Signed-off-by: NSven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Files which represent more than a single attribute aren't allowed in
sysfs. As we have some files which aren't essential and are lists or
tables aggregated from data from different places inside batman-adv, we
must place them in a filesystem without such a restriction.
Signed-off-by: NSven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

batctl uses /dev/batman-adv to send special batman-adv icmp packets to
other nodes in the mesh. To get it working with multiple batX devices we
must ensure that every mesh device can have their own socket which is
used to inject those packets in exactly one mesh.

The current implementation still doesn't allow to use complete separated
meshes as we rely on structures which are not part of the private data
of a batman device.
Signed-off-by: NSven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>