- 22 Jun, 2010 40 commits
-
-
Prashant P. Shah authored
This is a patch to the wl_cs.c file that fixes the space style issues found by the checkpatch.pl tool. Signed-off-by:
Prashant P. Shah <pshah.mumbai@gmail.com> Signed-off-by:
Greg Kroah-Hartman <gregkh@suse.de>
-
Samuel Ortiz authored
Getting a probe response after sending a probe request to a specific SSID doesnt mean we're trying to associate with this SSID. wpa_supplicant should be the only one deciding when to join an SSID, not the kernel. Signed-off-by:
Samuel Ortiz <sameo@linux.intel.com> Signed-off-by:
-
Samuel Ortiz authored
If we're not associated, we should not send wireless events to let userspace know that we just left an ESSID, simply because we havent yet joined it. If we keep on doing that, wpa_supplicant could receive such events while actually trying to join an ESSID, and thus decide to stop trying. This leads to a lot of connection failures as this driver seems to be sending GIWAP events quite a lot. Signed-off-by:
-
Samuel Ortiz authored
Toggling the link carrier is a non sense and is the grossest locking I can think of. Moreover, it's giving a completely inaccurate status to userspace who could for example decide to turn the interface down on carrier off detection. Signed-off-by:
-
Stefan Lippers-Hollmann authored
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:
Stefan Lippers-Hollmann <s.l-h@gmx.de> Acked-by:
Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Matti Lammi <mattij.lammi@gmail.com> Signed-off-by:
-
Niadh authored
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:
Neil Munro <neilmunro@gmail.com> Signed-off-by:
-
Bill Pemberton authored
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:
Bill Pemberton <wfp5p@virginia.edu> Cc: Arnaud Patard <apatard@mandriva.com> Signed-off-by:
-
Bill Pemberton authored
Remove 2 extern variables definations from XGI_accel.c that were defined in other .h files. Signed-off-by:
-
Bill Pemberton authored
The code inside this #ifdef declared a couple extern functions that weren't used anywhere, so remove the whole #ifdef Signed-off-by:
-
Bill Pemberton authored
This was not included anywhere and just defined a debugging macro. Signed-off-by:
-
Bill Pemberton authored
Signed-off-by:
-
Bill Pemberton authored
Signed-off-by:
-
Bill Pemberton authored
This removes all the remaining typedefs in vb_struct.h Signed-off-by:
-
Bill Pemberton authored
Signed-off-by:
-
Bill Pemberton authored
Signed-off-by:
-
Bill Pemberton authored
There is no need for these to be typedefs as a simple enum will do. Signed-off-by:
-
Bill Pemberton authored
Signed-off-by:
-
Bill Pemberton authored
Signed-off-by:
-
Bill Pemberton authored
Remove code that was removed using #if 0 Signed-off-by:
-
Bill Pemberton authored
Signed-off-by:
-
Bill Pemberton authored
PUCHAR was unsigned char *, use that instead Signed-off-by:
-
Bill Pemberton authored
Signed-off-by:
-
Bill Pemberton authored
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:
-
Bill Pemberton authored
These were just macros for memset and memcpy, so use those instead. Signed-off-by:
-
Bill Pemberton authored
Signed-off-by:
-
Bill Pemberton authored
Signed-off-by:
-
Bill Pemberton authored
Signed-off-by:
-
Bill Pemberton authored
Signed-off-by:
-
Bill Pemberton authored
Signed-off-by:
-
Bill Pemberton authored
Remove ifdefs that check LINUX_VERSION_CODE as this is not needed in the staging tree. Signed-off-by:
-
Bill Pemberton authored
This fixes compiler warning format '%x' expects type 'unsigned int', but argument 2 has type 'long unsigned int' Signed-off-by:
-
Daniel Seither authored
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:
-
Simon Wunderlich authored
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:
-
Simon Wunderlich authored
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 authored
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 authored
Signed-off-by:
-
Linus Lüssing authored
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:
Linus Lüssing <linus.luessing@web.de> Signed-off-by:
-
Sven Eckelmann authored
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:
-
Sven Eckelmann authored
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:
-
Joe Perches authored
Remove the last uses of MAC_FMT Signed-off-by:
Joe Perches <joe@perches.com> [sven.eckelmann@gmx.de: Adapted for current batman-adv version] Signed-off-by:
-
