| Age | Commit message (Collapse) | Author |
|---|
|
batman-adv is now moved to net/batman-adv/ and can be removed from
staging.
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
linux/etherdevice.h already provides functions to classify different
ethernet addresses. These inlineable functions should be used instead of
custom functions.
The check for multicast together with multicast can also be replaced
with a single test for multicast because for every ethernet address x
following is always true:
is_broadcast_ether_addr(x) => is_multicast_ether_addr(x)
or when looking more at the implementation:
(FF:FF:FF:FF:FF:FF == x) => [(01:00:00:00:00:00 & x) != 00:00:00:00:00:00]
Reported-by: Tobias Klauser <tklauser@distanz.ch>
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
Via the /sys filesystem you can change the gateway mode of a node using
gw_mode. Adjustments to it can be done using gw_bandwidth for server
mode and gw_sel_class for client mode.
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
[sven.eckelmann@gmx.de: Rework on top of current version]
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
spin_lock_irqsave disables the IRQs and stores them inside the flags
provided by the caller. This is needed to protect a bottom half handler
or a user context critical section from being interrupted by an
interrupt handler which also tries to acquire the spinlock and locks
forever.
The linux device drivers will receive the packets inside an interrupt
handler and the network infrastructure will process them inside bottom
half. Thus batman-adv will only run in user context and bottom half
handlers. We can conclude that batman-adv doesn't share its own
spinlocks with real interrupt handlers.
This makes it possible to exchange the quite complex spin_lock_irqsave
with spin_lock_bh which only stops bottom halves from running on the
current cpu, but allows interrupt handlers to take over to keep the
interrupt latency low.
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
The hash implementation is a complete implementation of a hash using
buckets as hash entries and overflow buckets attached to them.
The kernel already provides datastructures hlist_head and hlist_node
which can be used to implement an hash using lists as hash buckets. So
it is better to implement heavily used functionality on top of those
instead of providing a full hash implementation.
The rewrite changes the behavior of some functions slightly:
* hash_add add elements to the front instead of the tail
* hash_iterate doesn't provide pointer to access bucket->data directly,
but it can be accessed using hlist_entry
Reported-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
Function pointers cannot be inlined by a compiler and thus always has
the overhead of an call. hashdata_choose_cb's are one of the most often
called function pointers and its overhead must kept relative low.
As first step, every function which uses this function pointer takes it
as parameter instead of storing it inside the hash abstraction
structure.
This not generate any performance gain right now. The called functions
must also be able to be inlined by the calling functions to enable
inlining of the function pointer.
Reported-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
Function pointers cannot be inlined by a compiler and thus always has
the overhead of an call. hashdata_compare_cb's are one of the most often
called function pointers and its overhead must kept relative low.
As first step, every function which uses this function pointer takes it
as parameter instead of storing it inside the hash abstraction
structure.
This not generate any performance gain right now. The called functions
must also be able to be inlined by the calling functions to enable
inlining of the function pointer.
Reported-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
Both sysfs entries and variable names shall be as descriptive as
possible while not exceeding a certain length. This patch renames
bat_priv atomics to be equally descriptive with their according sysfs
entries.
Unifying sysfs and bat_priv atomic names also makes it easier to find
each others pendant.
The reduced ("type"-)information which was previously indicated with a
_enabled for booleans got substituted by a comment in bat_priv.
This patch has also been done in regards for the future BAT_ATTR_*
macros (they only need one name argument instead of a file and variable
name).
Signed-off-by: Linus Lüssing <linus.luessing@web.de>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
By connecting multiple batman-adv mesh nodes to the same ethernet
segment a loop can be created when the soft-interface is bridged
into that ethernet segment. A simple visualization of the loop
involving the most common case - a LAN as ethernet segment:
node1 <-- LAN --> node2
| |
wifi <-- mesh --> wifi
Packets from the LAN (e.g. ARP broadcasts) will circle forever from
node1 or node2 over the mesh back into the LAN.
This patch adds the functionality to detect other batman-adv nodes
connected to the LAN and select a 'gateway' to talk to the
non-batman-adv devices on this LAN. All traffic from and to the mesh
will be handled by this gateway to avoid the loop. OGMs received via
the soft-interface are interpreted as 'port announcements' to locate
potential batman-adv nodes. The patch can also deal with vlans on
top of batX and offers a list of LAN neighbors via debugfs.
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
[sven.eckelmann@gmx.de: Rework on top of current version]
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
Signed-off-by: Andreas Langer <an.langer@gmx.de>
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
If a packet is too big to be forwarded over an interface it will be
fragmented on-the-fly (if fragmentation is enabled).
Signed-off-by: Andreas Langer <an.langer@gmx.de>
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
Callers should check the if the received packet is for us before it
calls route_unicast_packet.
Signed-off-by: Andreas Langer <an.langer@gmx.de>
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
dedicated function
Signed-off-by: Andreas Langer <an.langer@gmx.de>
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
Signed-off-by: Andreas Langer <an.langer@gmx.de>
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
55d1666b521cbed95924c8d4775fe272c103f08c incidentally disabled bonding
of packets first entering the mesh along with also disabling interface
alternating regardless of where the packet came from. This re-enables
these options.
Signed-off-by: Chris Lang <clang@gateworks.com>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
Since all *printf() methods in the kernel understand '%pM' modifier the
conversion to the string is useless beforehand.
Additionally this patch decreases batman_if structure by 20 bytes.
Signed-off-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Cc: Marek Lindner <lindner_marek@yahoo.de>
Cc: Simon Wunderlich <siwu@hrz.tu-chemnitz.de>
Cc: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
receive_bat_packet is not called with rcu_read_lock so we must ensure by
ourself that we protect list_for_each_entry_rcu using the correct RCU
locks.
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
kmalloc() may fail, if so drop current packet.
Signed-off-by: Vasiliy Kulikov <segooon@gmail.com>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
[sven.eckelmann@gmx.de: Removed new introduced deadlock]
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
Information about dropped packets are usually only interesting for
debugging purposes and otherwise open the possibility to flood the logs
of the target machine with useless information.
pr_debug will not output those information on a nodebug kernel.
Reported-by: Vasiliy Kulikov <segooon@gmail.com>
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
batman_if has the name of the net_dev as extra string in its own
structure, but also holds a reference to the actual net_device structure
which always has the current name of the device. This makes it
unneccessary and also more complex because we must update the name in
situations when we receive a NETDEV_CHANGENAME event.
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
This patch removes all remaining global variables and includes the
necessary bits into the bat_priv structure. It is the last
remaining piece to allow multiple concurrent mesh clouds on the
same device.
A few global variables have been rendered obsolete during the process
and have been removed entirely.
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
[sven.eckelmann@gmx.de: Rework on top of current version]
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
This patch replaces the static bat0 interface with a dynamic/abstracted
approach. It is now possible to create multiple batX interfaces by
assigning hard interfaces to them. Each batX interface acts as an
independent mesh network. A soft interface is removed once no hard
interface references it any longer.
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
[sven.eckelmann@gmx.de: Rework on top of current version]
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
We must ensure that all interesting data is linear and not paged out to
access all information in a header or a full batman-adv related packet.
Otherwise we may drop packets which have non-linear headers but which
hold valid data.
This doesn't affect non-linear skbs which have all headers in a linear
head unless we must process the whole packet like in ogms or vis
packets.
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
We can use skb_cow instead of a handwritten function to test and create
a writable skb buffer. This also allows us to pre-allocate headroom to
be able to send the data without re-allocating the buffer again to add
the ethernet header.
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
This patch implements a simple layer2 fragmentation to allow traffic
exchange over network interfaces with a MTU smaller than 1500 bytes. The
fragmentation splits the big packets into two parts and marks the frames
accordingly. The receiving end buffers the packets to reassemble the
orignal packet before passing it to the higher layers. This feature
makes it necessary to modify the batman-adv encapsulation for unicast
packets by adding a sequence number, flags and the originator address.
This modifcation is part of a seperate packet type for fragemented
packets to keep the original overhead as low as possible. This patch
enables the feature by default to ensure the data traffic can travel
through the network. But it also prints a warning to notify the user
about the performance implications.
Note: Fragmentation should be avoided at all costs since it has a
dramatic impact on the performance, especially when it comes wifi
networks. Instead of a single packet, 2 packets have to be sent! Not
only valuable airtime is wasted but also packetloss decreases the
throughput. A link with 50% packetloss and fragmentation enabled is
pretty much unusable.
Signed-off-by: Andreas Langer <an.langer@gmx.de>
[sven.eckelmann@gmx.de: Rework on top of current version]
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
When receiving an batman icmp echo request or in case of a time-to-live
exceeded batman would reply with the mac address of the outgoing
interface which might be a secondary interface. Because secondary
interfaces are not globally known this might lead to confusion.
Now, replies are sent with the mac address of the primary interface.
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
Each general printk which is not informative by itself for a specific
batX device were moved to pr_(info|warning|err) as it provides an easy
interface which for example resolves the problem to add the prefix
"batman-adv: " before each line.
All information which is specific to a batX device will be printed using
a bat_(info|err|warning) macro to prefix it also with "batman-adv:
batX:" in each line.
Reported-by: Joe Perches <joe@perches.com>
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
All routing debug messages are saved in a ring buffer that can be
read via the debugfs file "log".
Note that CONFIG_BATMAN_ADV_DEBUG must be activated to have the
debug logs compiled in.
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
Useless but meaningfull patch that converts JavaStyle names into c_style
Signed-off-by: Antonio Quartulli <ordex@ritirata.org>
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg 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: Daniel Seither <post@tiwoc.de>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
[sven.eckelmann@gmx.de: Rework on top of current version]
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg 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: Simon Wunderlich <siwu@hrz.tu-chemnitz.de>
Acked-by: Marek Lindner <lindner_marek@yahoo.de>
[sven.eckelmann@gmx.de: Rework on top of current version]
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg 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: Simon Wunderlich <siwu@hrz.tu-chemnitz.de>
[sven.eckelmann@gmx.de: Rework on top of current version]
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg 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: Simon Wunderlich <siwu@hrz.tu-chemnitz.de>
[sven.eckelmann@gmx.de: Change atomic64_* back to atomic_*, Rework on
top of current version]
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg 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: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg 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: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
Documentation/CodingStyle sets a strongly prefered limit of 80
characters per line in "Chapter 2: Breaking long lines and strings".
Strings must be broken into smaller parts and long statements must be
rewritten.
Reported-by: Mikal Sande <mikal.sande@gmail.com>
Reported-by: Mark Rankilor <reodge@gmail.com>
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
We must ensure that all pointer to a socket buffer are updated when we
copy a socket buffer and free our reference to the old one.
Another part of the kernel could also free its reference which maybe
removes the buffer completely. In that situation we would would feed
wrong information to the routing algorithm after the memory area is
written again by someone else.
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
BATMAN and broadcast packets are tracked with a sequence number window of
currently 64 entries to measure and avoid duplicates. Packets which have a
sequence number smaller than the newest received packet minus 64 are not
within this sequence number window anymore and are called "old packets"
from now on.
When old packets are received, the routing code assumes that the host of the
originator has been restarted. This assumption however might be wrong as
packets can also be delayed by NIC drivers, e.g. because of long queues or
collision detection in dense WiFi? environments. This behaviour can be
reproduced by doing a broadcast ping flood in a dense node environment.
The effect is that the sequence number window is jumping forth and back,
accepting and forwarding any packet (because packets are assumed to be "new")
and causing loops.
To overcome this problem, the sequence number handling has been reorganized.
When an old packet is received, the window is reset back only once. Other old
packets are dropped for (currently) 30 seconds to "protect" the new sequence
number and avoid the hopping as described above.
The reorganization brings some code cleanups (at least i hope you feel the
same) and also fixes a bug in count_real_packets() which falsely updated
the last_real_seqno for slightly older packets within the seqno window
if they are no duplicates.
This second version of the patch also fixes a problem where for seq_diff==64
bit_shift() reads from outside of the seqno window, and removes the loop
for seq_diff == -64 which was present in the first patch.
The third iteration also adds a window for the next expected sequence numbers.
This minimizes sequence number flapping for packets with very big differences
(e.g. 3 packets with seqno 0, 25000 and 50000 might still cause problems
without this window).
Signed-off-by: Simon Wunderlich <siwu@hrz.tu-chemnitz.de>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
Instead of having a single /proc file "interfaces" in which you have
to echo the wanted interface batman-adv will create a subfolder in each
suitable /sys/class/net folder. This subfolder contains files for the
interface specific settings. For example, mesh_iface to add/remove an
interface from a virtual mesh network (at the moment only bat0 is
supported).
Example:
echo bat0 > /sys/class/net/eth0/batman-adv/mesh_iface
to deactivate:
echo none > /sys/class/net/eth0/batman-adv/mesh_iface
Interfaces which are not compatible with batman-adv won't contain the
batman-adv folder, therefore can't be activated. Not supported are:
loopback, non-ethernet, non-ARP and virtual mesh network interfaces
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
converted files:
vis_mode, vis_data
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
This patch fixes the 31 unnecessary whitespaces before a quoted
newline that the batman-adv files had.
Signed-off-by: Luis de Bethencourt <luisbg@ubuntu.com>
[sven.eckelmann@gmx.de: Redone to apply against current version]
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
Signed-off-by: Simon Wunderlich <siwu@hrz.tu-chemnitz.de>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
"tcpdump" and "batctl td" will receive packets with a wrong sequence
number on systems with a different endianess than network byte order.
This happens due to the reordering of bytes in the function which
handles aggregated bat packets. The function which receives the bat
packets must ensure that these buffers aren't shared with anything else
before that function tries to write into it. Otherwise it has to copy
the buffers so it is save again to change them.
Reported-by: Kevin Steen <batman@kevinsteen.net>
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
The vis code takes a copy of the data inside the skbuf if it is interesting
for us, so we always need to release the skbuf.
Reported-by: Linus Luessing <linus.luessing@web.de>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
This patch removes a variable that became obsolete since the skb handling
replaced the packet handling thread.
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
The routing code has 2 sections which warn about ttl exceeded. The
corresponding warnings were identical which makes it hard to debug. In
addition, batman-adv does not need to warn about ttl exceeded in case
we encountered an echo request as this is commonly used to generate
traceroute graphs.
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
Since we are now part of mainline, we don't need compat.h to allow
building of the module with old versions of the kernel.
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
printk() since kernel version 2.6.29 has supported printing MAC
addresses directly, as an extension to the %p processing. This patch
makes use of this for printk() and bat_dbg(). This will remove the
overhead of using addr_to_string() which is normally never actually
output.
Fixed a typo found by Gus Wirth.
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Simon Wunderlich <siwu@hrz.tu-chemnitz.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
|
This patch removes the (ugly and racy) packet receiving thread and the
kernel socket usage. Instead, packets are received directly by registering
the ethernet type and handling skbs instead of self-allocated buffers.
Some consequences and comments:
* we don't copy the payload data when forwarding/sending/receiving data
anymore. This should boost performance.
* packets from/to different interfaces can be (theoretically) processed
simultaneously. Only the big originator hash lock might be in the way.
* no more polling or sleeping/wakeup/scheduling issues when receiving
packets
* this might introduce new race conditions.
* aggregation and vis code still use packet buffers and are not (yet)
converted.
* all spinlocks were converted to irqsave/restore versions to solve
some lifelock issues when preempted. This might be overkill, some
of these locks might be reverted later.
* skb copies are only done if neccesary to avoid overhead
performance differences:
* we made some "benchmarks" with intel laptops.
* bandwidth on Gigabit Ethernet increased from ~500 MBit/s to ~920 MBit/s
* ping latency decresed from ~2ms to ~0.2 ms
I did some tests on my 9 node qemu environment and could confirm that
usual sending/receiving, forwarding, vis, batctl ping etc works.
Signed-off-by: Simon Wunderlich <siwu@hrz.tu-chemnitz.de>
Acked-by: Sven Eckelmann <sven.eckelmann@gmx.de>
Acked-by: Marek Lindner <lindner_marek@yahoo.de>
Acked-by: Linus Lüssing <linus.luessing@web.de>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
|
