- 11 Jun, 2007 40 commits
-
-
David Woodhouse authored
Signed-off-by:
David Woodhouse <dwmw2@infradead.org> Signed-off-by:
John W. Linville <linville@tuxdriver.com>
-
Dan Williams authored
Fix various issues reported by sparse. Signed-off-by:
Dan Williams <dcbw@redhat.com> Signed-off-by:
-
David Woodhouse authored
Signed-off-by:
-
Luis Carlos Cobo Rus authored
Signed-off-by:
Luis Carlos Cobo Rus <luisca@cozybit.com> Signed-off-by:
-
Luis Carlos Cobo Rus authored
Separate wireless handlers of mshX and ethX. ethX remains as before. For mshX, it has been disabled set/get essid, wap and set mode. Get mode always returns "Repeater" and by now we use the Nickname to show if the mesh is active ("Mesh") or not (empty). The rest remains as before. Signed-off-by: -
Luis Carlos Cobo Rus authored
Signed-off-by:
Luis Carlos Cobo Rus <luiscarlos@gmail.com> Signed-off-by:
-
Luis Carlos Cobo Rus authored
Fix some wording and blinding table command options, clarify argument list for fwt_add and fwt_list, simplify fwt_list_route Signed-off-by:
-
Dan Williams authored
Fix WPA so it works up through the supplicant 4-Way handshake process. Doesn't successfully pass traffic yet; may be problems installing the GTK to the firmware. - RSN needs to be enabled before the association command is sent - Use keys from the association request not the adapter structure - cmd_act_mac_strict_protection_enable != IW_AUTH_DROP_UNENCRYPTED - Fix network filtering logic in is_network_compatible() WPA helpers Signed-off-by:
-
Dan Williams authored
Signed-off-by:
-
Dan Williams authored
Signed-off-by:
-
Dan Williams authored
Any time the driver gets new scan results, even from partial scans, it should send the scan event to userspace. Signed-off-by:
-
Dan Williams authored
Previously if a fixed channel was specified along with an SSID, the channel request would be ignored during the association process. Instead, when searching for an adhoc or infrastructure network to join, allow filtering results based on channel so that the driver doesn't pick a BSS on a different channel than requested. Signed-off-by:
-
Dan Williams authored
Inadvertently removed on a previous commit; causes the first adhoc start to fail if a channel has not been set or no other association has been made. Signed-off-by:
-
Dan Williams authored
Update signal quality before the locked scan result translation loop, because calling libertas_prepare_and_send_command() with the 'waitforrsp' option grabs adapter->lock in the command return processing, leading to the deadlock. Signed-off-by:
-
Dan Williams authored
Ensure the leave debug print gets triggered when necessary. Signed-off-by:
-
Dan Williams authored
adapter->lock should released after unlocking adapter->driver_lock to balance the order in which they were locked at the top of the function. Signed-off-by:
-
Dan Williams authored
Signed-off-by:
-
Dan Williams authored
Signed-off-by:
-
Dan Williams authored
Signed-off-by:
-
Dan Williams authored
The BSS to associate with (in either Infrastructure or IBSS join operations) is now stored in _one_ place in the association request (the bss member), not two places as before (pattemptedbss and curbssparams->bssdescriptor). Association requests are passed to the necessary association functions to (a) give them access to the bss member and (b) ensure that association/join/start setup uses settings from the request, not the current adapter settings (which may not be valid for the requested settings). Because the 'bss' member of the association request is used now, the command return functions from associate and adhoc join/start need access to the in-progress association request to update curbssparams when everything is done. The association worker moves the request from pending to in-progress for the duration of the association attempt. Signed-off-by:
-
Dan Williams authored
Handle channel changes through the deferred association framework rather than directly. Fixes errors when setting channels along with other parameters like mode and SSID. Signed-off-by:
-
Marcelo Tosatti authored
Use list_for_each_entry_safe, to protect against list_del(). Signed-off-by:
Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by:
-
Luis Carlos Cobo Rus authored
Signed-off-by:
-
Dan Williams authored
Do not clear the scan list except under specific conditions, such as when (a) user-requested, or (b) joining/starting an adhoc network. Furthermore, only clear entries which match the SSID or BSSID of the request, not the whole scan list. Signed-off-by:
-
Dan Williams authored
- use a linked list for scan results - age scan results - pass bss_descriptors around instead of indexes into the scan table - lock access to the scan results - stop returning EAGAIN from SIOCGIWSCAN handler Signed-off-by:
-
Luis Carlos Cobo authored
Updated commands fwt_add and fwt_list, bt_list. New commands: bt_get_invert, bt_set_invert, to invert the blinding table, i.e., receive only frames from nodes listed in the BT. This patch needs/is needed for firmware 5.220.9.p11. Signed-off-by:
-
Luis Carlos Cobo Rus authored
This patch along with the previous commands update one, is necessary for mesh and fwt ioctls to work properly with firmware version 5.220.10.p0 and later. Signed-off-by:
-
Dan Williams authored
libertas_activate_card() doesn't create the netdev, and shouldn't free it on error. The caller of libertas_activate_card() is responsible for cleaning up errors from libertas_add_card(), not libertas_activate_card(). Signed-off-by:
-
Dan Williams authored
Subject says it all. Signed-off-by:
-
Dan Williams authored
Start to normalize bss_descriptor with ieee80211_network so we can eventually replace bss_descriptor more easily. Signed-off-by:
-
Dan Williams authored
Move usage of SET_NETDEV_DEV into common code since it has nothing to do with bus-specific devices. Also fixes a bug where the mesh device was getting SET_NETDEV_DEV called after register_netdevice, resulting in no 'device' link in /sys/class/net/mshX/. Signed-off-by:
-
Luis Carlos Cobo authored
Fixed kernel oops on module/card removal (using dongles) Signed-off-by:
-
Luis Carlos Cobo authored
Signed-off-by:
-
Luis Carlos Cobo authored
Signed-off-by:
-
Holger Schurig authored
Actually, this patch removev wlan_dev_t totally and puts the used variables of it directly into wlan_private. That reduces one level of indirection and looks a little bit simpler. It's now "priv->card" and not "priv->wlan_dev.card" and "priv->dev" instead of "priv->wlan_dev.netdev" Changed two occurences of "((wlan_private *) dev->priv)->wlan_dev.netdev" into "dev", because I didn't see the point in doing pointer-ping-pong. The variables "ioport", "upld_rcv" and "upld_type" where unused. They have been removed. Signed-off-by:
Holger Schurig <hs4233@mail.mn-solutions.de> Signed-off-by:
-
Holger Schurig authored
For now, it's "libertas" by default, but that is overwritten in if_usb.c/if_bootcmd.c and in if_cs.c. Signed-off-by:
-
Holger Schurig authored
Previously, we had a fixed array of 5 elements where we remembered all initialized devices. This has been changed to use a "struct list_head" organization, which is IMHO cleaner. Also renamed usb_cardp to cardp, as in the reset of the code. Renamed reset_device() to if_usb_reset_device() like many other functions. Signed-off-by:
-
Holger Schurig authored
* add CONFIG_LIBERTAS to Kconfig * remove global variable libertas_fw_name, the USB module might want to use a different default FW name than the CF module, so libertas_fw_name is now local to if_usb.c * exported some symbols as GPL Signed-off-by: -
Holger Schurig authored
Also removes some useless "extern" declarations from function declaration. Signed-off-by:
-
Holger Schurig authored
This functions makes all libertas_sbi_XXX functions static to the if_usb.c file and renames them to if_usb_XXXX(). The get called from other places of the source code via priv->hw_XXXX(). Signed-off-by:
-
