summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* mac802154: remove pib lockAlexander Aring2015-05-235-16/+5
| | | | | | | | | | This patch removes the pib lock which is now replaced by rtnl lock. The new interface already use the rtnl lock only. Nevertheless this patch will fix issues while using new and old interface at the same time. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Reviewed-by: Stefan Schmidt <stefan@osg.samsung.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* mac802154: fix hold rtnl while ioctlAlexander Aring2015-05-231-2/+3
| | | | | | | | | | | | This patch fixes an issue to set address configuration with ioctl. Accessing the mib requires rtnl lock and the ndo_do_ioctl doesn't hold the rtnl lock while this callback is called. This patch do that manually. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Reported-by: Matteo Petracca <matteo.petracca@sssup.it> Reviewed-by: Stefan Schmidt <stefan@osg.samsung.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* ieee802154/atusb: Set default ed level to 0xbe like the rest of these driversStefan Schmidt2015-05-211-2/+2
| | | | | | Signed-off-by: Stefan Schmidt <stefan@osg.samsung.com> Acked-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* ieee802154/atusb: Mark driver as AACK enabled in hardware.Stefan Schmidt2015-05-211-1/+2
| | | | | | | | | Since firmware version 0.2 we use AACK handling directly in the firmware. Inform the stack that the hardware supports and uses it. Signed-off-by: Stefan Schmidt <stefan@osg.samsung.com> Acked-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* ieee802154/atusb: Warn about outdated device firmware.Stefan Schmidt2015-05-211-0/+6
| | | | | | | | | | | | | | Together with mainlining the driver we released a first public binary version of the device firmware. This is version 0.2. With this change we warn users who run outdated versions of the firmware. While we have not seen problems with it yet (thus no error, but a warning only) it would be better to run the released and tested firmware. You can find released versions here: http://downloads.qi-hardware.com/people/werner/wpan/web/ Signed-off-by: Stefan Schmidt <stefan@osg.samsung.com> Acked-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* at86rf230: add missing cca ed level valuesAlexander Aring2015-05-201-2/+2
| | | | | | | | | | This patch add missing values for at86rf212 ed level values. Currently there are 15 values and the register setting supports 16 different ed level values. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Reported-by: Craig Younkins <craig@freshtemp.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* Bluetooth: Add debug logs for legacy SMP crypto functionsJohan Hedberg2015-05-191-4/+16
| | | | | | | | To help debug legacy SMP crypto functions add debug logs of the various values involved. Signed-off-by: Johan Hedberg <johan.hedberg@intel.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* mac802154: select CRYPTO when neededArnd Bergmann2015-05-191-0/+1
| | | | | | | | | | | | | | | | | | | | | The mac802154 subsystem uses functions from the crypto layer and correctly selects the individual crypto algorithms, but fails to build when the crypto layer is disabled altogether: crypto/built-in.o: In function `crypto_ctr_free': :(.text+0x80): undefined reference to `crypto_drop_spawn' crypto/built-in.o: In function `crypto_rfc3686_free': :(.text+0xac): undefined reference to `crypto_drop_spawn' crypto/built-in.o: In function `crypto_ctr_crypt': :(.text+0x2f0): undefined reference to `blkcipher_walk_virt_block' :(.text+0x2f8): undefined reference to `crypto_inc' To solve that, this patch also selects the core crypto code, like all other users of that code do. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Reviewed-by: Stefan Schmidt <stefan@osg.samsung.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* fakelb: cleanup codeAlexander Aring2015-05-191-17/+12
| | | | | | | This patch just cleanups the code at several places. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* fakelb: add support for async xmit handlingAlexander Aring2015-05-191-1/+2
| | | | | | | This patch will add async xmit support for the fakelb driver. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* fakelb: remove fakelb_hw_deliverAlexander Aring2015-05-191-12/+6
| | | | | | | This patch cleanups the fakelb_hw_deliver function by removing them. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* fakelb: add virtual phy reset defaultsAlexander Aring2015-05-191-0/+5
| | | | | | | | This patch adds reset defaults for the fakelb phy. I used the channel 13 and page 0 which is the same default like at86rf233. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* fakelb: use own channel and page attributesAlexander Aring2015-05-191-3/+10
| | | | | | | | | | This patch adds an own phy attribute for page and channel into fakelb_phy. The current way is to use the internal mac802154 stored phy pib values which can occur in locking issues while using it inside the driver layer. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* fakelb: introduce fakelb ifup phys listAlexander Aring2015-05-191-33/+25
| | | | | | | | | | | This patch introduce a fakelb ifup phys list, which stores all registered phys which are in an operated mode. This will reduce the iterations of non-operated phys while transmit frames. There exists two locks now, one rwlock for the operated interfaces and the spinlock for protecting the list for all registered virtual phys. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* fakelb: move lock out of iterationAlexander Aring2015-05-191-3/+4
| | | | | | | | The list need to be protected while iteration which is need when other list iterates at the same time over this list. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* fakelb: declare fakelb list staticAlexander Aring2015-05-191-25/+7
| | | | | | | | This patch moves the fakelb list of all registered phy's in a static declaration in the fakelb driver. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* fakelb: declare rwlock staticAlexander Aring2015-05-191-9/+7
| | | | | | | This patch moves the rwlock declarition into a static variable. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* fakelb: don't deliver when one phyAlexander Aring2015-05-191-12/+8
| | | | | | | | | | A real phy don't transmit the transmitted frame back to the phy. This behaviour will confuse the 6LoWPAN and the upper IPv6 neighbour discovery cache. We need now at least two virtual phy's to creating a virtual wpan network. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* fakelb: rename fakelb_dev_priv to fakelb_phyAlexander Aring2015-05-191-46/+47
| | | | | | | | | | This patch renames fakelb_dev_priv to fakelb_phy. We don't faking devices here, we fake wpan phys. This avoids also confusing with the variable priv, which is used several times in this driver to represent this structure. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* fakelb: use list_for_each_entry_safeAlexander Aring2015-05-191-2/+2
| | | | | | | | | Iterate and removing items from a list, we should use list_for_each_entry_safe instead list_for_each_entry to avoid accidents by removing. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* fakelb: creating two virtual phys per defaultAlexander Aring2015-05-191-1/+1
| | | | | | | | | This patch change the default virtual wpan phys of fakelb driver from one to two. To have one virtual phy makes no sense, because it need at least two virtual phy's to speak to each other. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* ieee802154: add support for atusb transceiverAlexander Aring2015-05-196-197/+1009
| | | | | | | | | | | | | | | | | | This patch adds support for the atusb transceiver. The current driver supports basic functionality only. Possible further tasks would be to sync functionality with the at86rf230 driver, because the atusb use internally an at86rf231 transceiver. Some of these features need a firmware update like AACK and ARET handling. I did small changes to this driver to work with xmit_async callback and setting of a random extended perm address. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Cc: Werner Almesberger <werner@almesberger.net> Cc: Stefan Schmidt <s.schmidt@samsung.com> Cc: Richard Sharpe <realrichardsharpe@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* mac802154: tx: allow xmit complete from hard irqAlexander Aring2015-05-191-3/+2
| | | | | | | | Replace consume_skb with dev_consume_skb_any in ieee802154_xmit_complete which can be called in hard irq and other contexts. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* at86rf230: fix callback for aret handlingAlexander Aring2015-05-191-1/+1
| | | | | | | | | This patch fix the complete callback for going into aret on. Currently we starting after a state change into aret on again a state change into aret on which is not necessary. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* mac802154: fakelb: Fix potential NULL pointer dereference.Martin Townsend2015-05-191-1/+2
| | | | | | | | | | fakelb_hw_deliver creates a copy of the skb's header which can potentially return NULL so we now check for this before actually delivering to the 802.15.4 MAC layer. Signed-off-by: Martin Townsend <martin.townsend@xsilon.com> Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* nl802154: add support for dump phy capabilitiesAlexander Aring2015-05-192-1/+173
| | | | | | | | | | This patch add support to nl802154 to dump all phy capabilities which is inside the wpan_phy_supported struct. Also we introduce a new method to dumping supported channels. The new method will offer a easier interface and has lesser netlink traffic. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* at86rf230: add reset states of tx power levelAlexander Aring2015-05-191-0/+1
| | | | | | | | This patch adds the reset states for tx power levels after running reset procedure. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* at86rf230: add cca ed level reset valueAlexander Aring2015-05-191-2/+5
| | | | | | | | This patch adds reset values for cca ed level values after running reset procedure. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* at86rf230: rework tx cca energy detection levelAlexander Aring2015-05-191-20/+59
| | | | | | | | | This patch reworks the cca energy detection level handling. This contains a calculation which works on all transceiver types and add support for dump cca energy detection levels. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* at86rf230: rework tx power supportAlexander Aring2015-05-191-19/+64
| | | | | | | | This patch adds support for get transmit power levels and reworks the set of transmit power levels which was broken before. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* at86rf230: set cca_modes supported flagsAlexander Aring2015-05-191-0/+6
| | | | | | | | This patch sets the at86rf230 supported cca modes. In case of at86rf212 it also can support listen before transmit. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* ieee802154: add iftypes capabilityAlexander Aring2015-05-193-2/+9
| | | | | | | This patch adds capability flags for supported interface types. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* cfg802154: introduce wpan phy flagsAlexander Aring2015-05-195-37/+50
| | | | | | | | | | | | | | | | | | | | | | | This patch introduce a flag property for the wpan phy structure. The current flag settings in ieee802154_hw are accessable in mac802154 layer only which is okay for flags which indicates MAC handling which are done by phy. For real PHY layer settings like cca mode, transmit power, cca energy detection level. The difference between these flags are that the MAC handling flags are only handled in mac802154/HardMac layer e.g. on an interface up. The phy settings are direct netlink calls from nl802154 into the driver layer and the nl802154 need to have a chance to check if the driver supports this handling before sending to the next layer. We also check now on PHY flags while dumping and setting pib attributes. In comparing with MIB attributes the 802.15.4 gives us an default value which we assume when a transceiver implement less functionality. In case of MIB settings the nl802154 layer doesn't need to check on the ieee802154_hw flags then. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* mac802154: remove check if operation is supportedAlexander Aring2015-05-191-24/+0
| | | | | | | | | This patch removes the check if operation is supported by driver layer. This is done now by capabilities flags, if these are valid then the driver should support the operation, otherwise a WARN_ON occurs. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* mac802154: check for really changesAlexander Aring2015-05-192-0/+38
| | | | | | | | | | This patch adds check if the value is really changed inside pib/mib. If a transceiver do support only one value for e.g. max_be then this will also handle that the driver layer doesn't need to care about handling to set one value only. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* ieee802154: add several phy supported handlingAlexander Aring2015-05-194-6/+90
| | | | | | | | | | | | | | This patch adds support for phy supported handling for all other already existing handling 802.15.4 functionality. We assume now a fully 802.15.4 complaint transceiver at phy allocation. If a transceiver can support 802.15.4 default values only, then the values should be overwirtten by values the transceiver supports. If the transceiver doesn't set the according hardware flags, we assume the 802.15.4 defaults now which cannot be changed. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Suggested-by: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* ieee802154: introduce wpan_phy_supportedAlexander Aring2015-05-197-26/+30
| | | | | | | | | | | | | This patch introduce the wpan_phy_supported struct for wpan_phy. There is currently no way to check if a transceiver can handle IEEE 802.15.4 complaint values. With this struct we can check before if the transceiver supports these values before sending to driver layer. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Suggested-by: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de> Acked-by: Varka Bhadram <varkabhadram@gmail.com> Cc: Alan Ott <alan@signal11.us> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* ieee802154: change cca ed level to mbmAlexander Aring2015-05-195-8/+9
| | | | | | | | | | This patch change the handling of cca energy detection level from dbm to mbm. This prepares to handle floating point cca energy detection levels values. The old netlink 802.15.4 will convert the dbm value to mbm for handling backward compatibility. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* ieee802154: change transmit power to mbmAlexander Aring2015-05-195-7/+9
| | | | | | | | | | This patch change the handling of transmit power level from dbm to mbm. This prepares to handle floating point transmit power levels values. The old netlink 802.15.4 will convert the dbm value to mbm for handling backward compatibility. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* ieee802154: change transmit power to s32Alexander Aring2015-05-195-7/+7
| | | | | | | | | | This patch change the transmit power from s8 to s32. This prepares to store a mbm value instead dbm inside the transmit power variable. The old interface keep the a s8 dbm value, which should be backward compatibility when assign s8 to s32. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* ieee802154: move validation check out of softmacAlexander Aring2015-05-192-30/+27
| | | | | | | | | This patch moves the value validation out of softmac layer. We need to be sure now that this value is accepted by the transceiver/mac802154 or "possible" hardmac drivers before calling rdev-ops. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* nl802154: cleanup invalid argument handlingAlexander Aring2015-05-191-8/+4
| | | | | | | | This patch cleanups the -EINVAL cases by combining them in one condition. Signed-off-by: Alexander Aring <alex.aring@gmail.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* Bluetooth: btbcm: Fix calls to __hci_cmd_sync()Frederic Danis2015-05-151-6/+0
| | | | | | | | | | | | | | | | | | | Remove test of command reply status as it is already performed by __hci_cmd_sync(). __hci_cmd_sync_ev() function already returns an error if it got a non-zero status either through a Command Complete or a Command Status event. For both of these events the status is collected up in the event handlers called by hci_event_packet() and then passed as the second parameter to req_complete_skb(). The req_complete_skb() callback in turn is hci_req_sync_complete() for __hci_cmd_sync_ev() which stores the status in hdev->req_result. The hdev->req_result is then further converted through bt_to_errno() back in __hci_cmd_sync_ev(). Signed-off-by: Frederic Danis <frederic.danis@linux.intel.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* Bluetooth: btintel: Fix calls to __hci_cmd_sync()Frederic Danis2015-05-151-6/+0
| | | | | | | | | | | | | | | | | | | Remove test of command reply status as it is already performed by __hci_cmd_sync(). __hci_cmd_sync_ev() function already returns an error if it got a non-zero status either through a Command Complete or a Command Status event. For both of these events the status is collected up in the event handlers called by hci_event_packet() and then passed as the second parameter to req_complete_skb(). The req_complete_skb() callback in turn is hci_req_sync_complete() for __hci_cmd_sync_ev() which stores the status in hdev->req_result. The hdev->req_result is then further converted through bt_to_errno() back in __hci_cmd_sync_ev(). Signed-off-by: Frederic Danis <frederic.danis@linux.intel.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* Bluetooth: btusb: Fix calls to __hci_cmd_sync()Frederic Danis2015-05-151-36/+0
| | | | | | | | | | | | | | | | | | | Remove test of command reply status as it is already performed by __hci_cmd_sync(). __hci_cmd_sync_ev() function already returns an error if it got a non-zero status either through a Command Complete or a Command Status event. For both of these events the status is collected up in the event handlers called by hci_event_packet() and then passed as the second parameter to req_complete_skb(). The req_complete_skb() callback in turn is hci_req_sync_complete() for __hci_cmd_sync_ev() which stores the status in hdev->req_result. The hdev->req_result is then further converted through bt_to_errno() back in __hci_cmd_sync_ev(). Signed-off-by: Frederic Danis <frederic.danis@linux.intel.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* Bluetooth: Fix calls to __hci_cmd_sync()Frederic Danis2015-05-151-5/+0
| | | | | | | | | | | | | | | | | | | Remove test of command reply status as it is already performed by __hci_cmd_sync(). __hci_cmd_sync_ev() function already returns an error if it got a non-zero status either through a Command Complete or a Command Status event. For both of these events the status is collected up in the event handlers called by hci_event_packet() and then passed as the second parameter to req_complete_skb(). The req_complete_skb() callback in turn is hci_req_sync_complete() for __hci_cmd_sync_ev() which stores the status in hdev->req_result. The hdev->req_result is then further converted through bt_to_errno() back in __hci_cmd_sync_ev(). Signed-off-by: Frederic Danis <frederic.danis@linux.intel.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* Bluetooth: btrtl: Create separate module for Realtek BT driverCarlo Caione2015-05-145-373/+462
| | | | | | | | As already done for btintel and btbcm export setup as separate function in a vendor-specific module to hold all the Realtek specific commands. Signed-off-by: Carlo Caione <carlo@endlessm.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* Bluetooth: btmrvl: fix compilation warningXinming Hu2015-05-131-1/+1
| | | | | | | | | This patch fixes a compile warnning "dump_num maybe used uninitialized in this function". Signed-off-by: Xinming Hu <huxm@marvell.com> Signed-off-by: Amitkumar Karwar <akarwar@marvell.com> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* Bluetooth: btwilink: remove DEBUG defineLeo Yan2015-05-131-1/+1
| | | | | | | | Remove the DEBUG define as the debug code; so can remove mass debug info from log buffer when using dmesg. Signed-off-by: Leo Yan <leo.yan@linaro.org> Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
* net: kill useless net_*_ingress_queue() definitions when NET_CLS_ACT is unsetPablo Neira2015-05-131-8/+0
| | | | | | | | | | | | | | This fixes 4577139b2dabf589 ("net: use jump label patching for ingress qdisc in __netif_receive_skb_core"). The only client of this is sch_ingress and it depends on NET_CLS_ACT. So there is no way these definition can be of any help. Cc: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
OpenPOWER on IntegriCloud