aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/net/wireless
Commit message (Collapse)AuthorAge
* [PATCH] libertas: add more verbose debugging to libertas_cmd_80211_authenticateDan Williams2007-06-11
| | | | | Signed-off-by: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: debug print spacing fixes in assoc.cDan Williams2007-06-11
| | | | | Signed-off-by: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: send SIOCGIWSCAN event after partial scans tooDan Williams2007-06-11
| | | | | | | | 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 <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: honor specific channel requests during associationDan Williams2007-06-11
| | | | | | | | | | | | 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 <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: fix default adhoc channelDan Williams2007-06-11
| | | | | | | | | 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 <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: fix deadlock SIOCGIWSCAN handlerDan Williams2007-06-11
| | | | | | | | | | 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 <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: correct error report paths for wlan_fwt_list_ioctlDan Williams2007-06-11
| | | | | | | Ensure the leave debug print gets triggered when necessary. Signed-off-by: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: correctly balance locking in libertas_process_rx_commandDan Williams2007-06-11
| | | | | | | | 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 <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: fix debug enter/leave prints for libertas_execute_next_commandDan Williams2007-06-11
| | | | | Signed-off-by: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: use compare_ether_addr() rather than memcmp() where ↵Dan Williams2007-06-11
| | | | | | | appropriate Signed-off-by: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: use MAC_FMT and MAC_ARG where appropriateDan Williams2007-06-11
| | | | | Signed-off-by: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: make association paths consistentDan Williams2007-06-11
| | | | | | | | | | | | | | | | | | | | | | 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 <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: move channel changing into association frameworkDan Williams2007-06-11
| | | | | | | | | 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: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: fix oops on rmmodMarcelo Tosatti2007-06-11
| | | | | | | Use list_for_each_entry_safe, to protect against list_del(). Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: cleanup of fwt_list_route processingLuis Carlos Cobo Rus2007-06-11
| | | | | | Signed-off-by: Luis Carlos Cobo Rus <luisca@cozybit.com> Acked-by: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: fix 'keep previous scan' behaviorDan Williams2007-06-11
| | | | | | | | | | 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 <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: make scan result handling more flexibleDan Williams2007-06-11
| | | | | | | | | | | - 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: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: updated mesh commands for 5.220.9.p11Luis Carlos Cobo2007-06-11
| | | | | | | | | | | 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 <luisca@cozybit.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: version bump (321p0) and cmds update for new fw (5.220.10.p0)Luis Carlos Cobo Rus2007-06-11
| | | | | | | | | 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: Luis Carlos Cobo Rus <luiscarlos@gmail.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: don't tear down netdev in libertas_activate_cardDan Williams2007-06-11
| | | | | | | | | | 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 <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: correctly unregister mesh netdev on errorDan Williams2007-06-11
| | | | | | | Subject says it all. Signed-off-by: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: replace 'macaddress' with 'bssid'Dan Williams2007-06-11
| | | | | | | | Start to normalize bss_descriptor with ieee80211_network so we can eventually replace bss_descriptor more easily. Signed-off-by: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: call SET_NETDEV_DEV from common codeDan Williams2007-06-11
| | | | | | | | | | 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: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: fixed kernel oops on module/card removalLuis Carlos Cobo2007-06-11
| | | | | | | Fixed kernel oops on module/card removal (using dongles) Signed-off-by: Luis Carlos Cobo <luisca@cozybit.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: add URB debug infoLuis Carlos Cobo2007-06-11
| | | | | Signed-off-by: Luis Carlos Cobo <luisca@cozybit.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: fixed incorrect assigment of fcs errors to frag errorsLuis Carlos Cobo2007-06-11
| | | | | Signed-off-by: Luis Carlos Cobo <luisca@cozybit.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: remove unused variables in wlan_dev_tHolger Schurig2007-06-11
| | | | | | | | | | | | | | | | 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: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: let DRV_NAME be overridableHolger Schurig2007-06-11
| | | | | | | | 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 <hs4233@mail.mn-solutions.de> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: fix RESET logic at unload timeHolger Schurig2007-06-11
| | | | | | | | | | | | | 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 <hs4233@mail.mn-solutions.de> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: split module into two (libertas.ko and usb8xxx.ko)Holger Schurig2007-06-11
| | | | | | | | | | | * 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 <hs4233@mail.mn-solutions.de> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: move contents of fw.h to decl.hHolger Schurig2007-06-11
| | | | | | | Also removes some useless "extern" declarations from function declaration. Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: indirect all hardware access via hw_XXXX functionsHolger Schurig2007-06-11
| | | | | | | | | 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: Holger Schurig <hs4233@mail.mn-solutions.de> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: wakeup both mesh and normal wakeup when getting out of scanChris Ball2007-06-11
| | | | | | | | The previous patch wakes up the mesh device *instead* of the wlan device when coming out of scan. We need to wake up both of them. Signed-off-by: Chris Ball <cjb@laptop.org> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: added transmission failures to mesh statisticsJavier Cardona2007-06-11
| | | | | | | | Added transmission failures to mesh statistics. Removed whitespace before newlines. Signed-off-by: Javier Cardona <javier@cozybit.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: fix error handling of card initializationMarcelo Tosatti2007-06-11
| | | | | | | Subject says it all. Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: fixed transmission flow control on the mesh interfaceJavier Cardona2007-06-11
| | | | | | | This patch implements proper transmission flow control on mshX. Signed-off-by: Javier Cardona <javier@cozybit.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: split wlan_add_card()Holger Schurig2007-06-11
| | | | | | | | | | | | | | | | | | | Split wlan_add_card() into a part that just setups kernel parameters and into the function libertas_activate_card(), which will implizitly use hardware functions by the started thread. This allows us later to do something like this: priv = libertas_add_card(); priv->hw_command_to_host = if_usb_command_to_host; priv->hw_xxxx = if_usb_xxxx; priv->hw_yyyy = if_usb_yyyy; wlan_activate_card() and of course the CF driver can set it's own functions. Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: move reset_device() code main.c to if_usb.cHolger Schurig2007-06-11
| | | | | | | | The reset_device() logic is only needed for USB devices, not for CF devices. Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: changed some occurences of kmalloc() + memset(&a,0,sz) to ↵Holger Schurig2007-06-11
| | | | | | | | | kzalloc() The subject says it all. Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: fix SSID outputHolger Schurig2007-06-11
| | | | | | | | * a newline was missing * changed %32s to '%s', no need to right justify the ESSID Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: get rid of libertas_sbi_get_priv()Holger Schurig2007-06-11
| | | | | | | | It's not really needed, because we can call wlan_remove_card() with wlan_private* anyway. Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: change debug output of libertas_interrupt()Holger Schurig2007-06-11
| | | | | | | | | It used to be LBS_DEB_MAIN, now it's LBS_DEB_THREAD Also fixed a missing ":" in lbs_deb_enter() Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: single out mesh codeHolger Schurig2007-06-11
| | | | | | | | | This patches adds the two functions wlan_add_mesh() and wlan_remove_mesh(), which are responsible for the mshX interface. In a CF driver with a non- mesh-aware firmware you can omit the calls to this functions. Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: tune debug codeHolger Schurig2007-06-11
| | | | | | | | | | * renamed module parameter back to libertas_debug * change from bit shifts to constants, that way it's easier to look at the source and specify the libertas_debug=0xXXXX module parameter * moved module_param from fw.c to main.c, where it belongs better Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: make debug configurableHolger Schurig2007-06-11
| | | | | | | | | The debug output of libertas was either not present or it was overwhelming. This patch adds the possibility to specify a bitmask for the area of interest. One should then only get the desired output. Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: exclude non-used code when PROC_DEBUG is not setHolger Schurig2007-06-11
| | | | | | | | This reduces usb8xxx.ko by 951 bytes (text) and 256 bytes (data) when PROC_DEBUG isn't defined. Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: fix scanning from associate pathMarcelo Tosatti2007-06-11
| | | | | | | | | | | The previous scan fix did not account for scan paths other than set_scan() that need to do a full scan at once. Add a "full_scan" parameter to wlan_scan_networks() to control such behaviour. Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: make libertas_wlan_data_rates staticHolger Schurig2007-06-11
| | | | | | | | Move libertas_wlan_data_rates into wext.c and make it static. wext.c is the only user of this array. Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: move vendor & product id's into if_usb.cHolger Schurig2007-06-11
| | | | | | | For me it looks cleaner, because it removes one level of indirection. Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* [PATCH] libertas: remove unused/superfluous definitions of DEV_NAME_LENHolger Schurig2007-06-11
| | | | | | | DEV_NAME_LEN is already defined in defs.h and that is sufficient. Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Signed-off-by: John W. Linville <linville@tuxdriver.com>
generated by cgit v1.2.2 (git 2.25.0) at 2024-11-16 23:39:53 -0500