openwrt/staging/blogic.git
14 years agoiwlwifi: remove code repetition
Wey-Yi Guy [Sat, 4 Sep 2010 16:00:14 +0000 (09:00 -0700)]
iwlwifi: remove code repetition

Move the duplicated code into single static function.

Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: make sure runtime calibration is enabled after association
Wey-Yi Guy [Fri, 3 Sep 2010 18:42:04 +0000 (11:42 -0700)]
iwlwifi: make sure runtime calibration is enabled after association

Clear the "start calib" flag only for new association,
The flag will be set in post_associate function to trigger
the runtime calibration. Set this flag to "0" will stop the
runtime sensitivity calibration

Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: fix and describe iwl_adjust_beacon_interval
Johannes Berg [Fri, 3 Sep 2010 13:30:55 +0000 (06:30 -0700)]
iwlwifi: fix and describe iwl_adjust_beacon_interval

The iwl_adjust_beacon_interval function is a bit
of black magic, so add comments to it describing
what it does. Also, in the case when there's no
beacon interval set, program the default into
the device (instead of adjusting, which results
in the max) since using the max in that case
interacts badly with dual-mode/PAN parameters.

Also update the PAN parameters accordingly and
use the same constant as here.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: improve timing handling with dual-mode
Johannes Berg [Fri, 3 Sep 2010 13:31:26 +0000 (06:31 -0700)]
iwlwifi: improve timing handling with dual-mode

In dual-mode, a number of scenarios need to be
considered, and the firmware can be very picky
about them. Adjust the timing (most importantly
the beacon interval) according to the different
modes.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: avoid sending too many commands
Johannes Berg [Fri, 3 Sep 2010 13:32:21 +0000 (06:32 -0700)]
iwlwifi: avoid sending too many commands

When the PAN context is unused, there's no
need to continually update it in the device.
So track which contexts are active (with the
special case that the WLAN context is always
active ...) and only send their commands to
the device when needed.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: allow configure protection mode
Wey-Yi Guy [Thu, 2 Sep 2010 00:10:51 +0000 (17:10 -0700)]
iwlwifi: allow configure protection mode

Even driver use rts/cts protection mode for aggregation packets by default.
Allow the protection mode to be configure through debugfs

Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: implement beacon interval change
Johannes Berg [Mon, 30 Aug 2010 13:13:42 +0000 (06:13 -0700)]
iwlwifi: implement beacon interval change

When the beacon interval needs to be changed,
all we need to do is send updated timing to
the device.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: fix PAN parameters while scanning
Johannes Berg [Mon, 30 Aug 2010 13:12:00 +0000 (06:12 -0700)]
iwlwifi: fix PAN parameters while scanning

When only the PAN side was active, we gave no
time to the WLAN context, which is OK unless
we are scanning, which always happens on the
WLAN context. Fix this.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: remember the last uCode sysassert error code
Wey-Yi Guy [Fri, 27 Aug 2010 17:41:37 +0000 (10:41 -0700)]
iwlwifi: remember the last uCode sysassert error code

When sysassert happen, uCode will report the error code,
driver dump the information to dmesg. Here also remember
the last error code for future reference.

Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: fix default LQ table in 5.2 band
Tomas Winkler [Mon, 23 Aug 2010 21:00:54 +0000 (14:00 -0700)]
iwlwifi: fix default LQ table in 5.2 band

The default LQ is filled decreasingly using
iwl_get_prev_ieee_rate from a starting rate.
Since the starting rate is already the lowest one for
a specific band it should be actually filled evenly with
the starting rate: 1M and 6M for 5.2GHZ and 2.4GH respectively.
The bug is that for for A or G-only it decreases to
CCK rates which are not supported.
iwl_get_prev_ieee_rate function is just not band aware.
This affects broadcast station which lq table
is not updated by rs algorithm

G-only scenario is not treated by this patch

iwl_get_prev_ieee_rate is removed completely as it
is not used in other contexts

Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agodrivers/net/wireless/iwlwifi/iwl-agn.c: Fix return value from an unsigned function
Julia Lawall [Sun, 5 Sep 2010 19:00:26 +0000 (21:00 +0200)]
drivers/net/wireless/iwlwifi/iwl-agn.c: Fix return value from an unsigned function

The function has an unsigned return type, but returns a negative constant
to indicate an error condition.  Another error condition in the same
function is indicated by returning 0, and indeed the only call to the
function checks for 0 to detect errors, so the return of a negative value
it converted to a return of 0.

A sematic match that finds this problem is as follows:
(http://coccinelle.lip6.fr/)

// <smpl>
@exists@
identifier f;
constant C;
@@

 unsigned f(...)
 { <+...
*  return -C;
 ...+> }
// </smpl>

Signed-off-by: Julia Lawall <julia@diku.dk>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agop54spi: Add error message for eeprom failure
Michael Büsch [Sat, 4 Sep 2010 22:55:38 +0000 (00:55 +0200)]
p54spi: Add error message for eeprom failure

This adds an error message for the eeprom request failure
case. This way it's easier for the user to figure out
what went wrong.

Signed-off-by: Michael Büsch <mb@bu3sch.de>
Acked-by: Christian Lamparter <chunkeey@googlemail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agoath9k_hw: Restore ANI registers to default during partial reset for AR9271
Rajkumar Manoharan [Fri, 3 Sep 2010 10:30:00 +0000 (16:00 +0530)]
ath9k_hw: Restore ANI registers to default during partial reset for AR9271

For AR9271 chips, if partial reset is done while scanning, the cycpwrThr1
will be set to maximum. This causes the degrade in DL throughput.
So restore the ANI registers to default during the partial reset.

Signed-off-by: Rajkumar Manoharan <rmanoharan@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agoath9k_htc: Enable fastcc for HTC devices.
Rajkumar Manoharan [Fri, 3 Sep 2010 07:11:28 +0000 (12:41 +0530)]
ath9k_htc: Enable fastcc for HTC devices.

By enabling fastcc, the scan time reduced to half.

Signed-off-by: Rajkumar Manoharan <rmanoharan@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agoath9k: Implement an algorithm for Antenna diversity and combining
Vasanthakumar Thiagarajan [Thu, 2 Sep 2010 08:34:43 +0000 (01:34 -0700)]
ath9k: Implement an algorithm for Antenna diversity and combining

This algorithm chooses the best main and alt lna out of
LNA1, LNA2, LNA1+LNA2 and LNA1-LNA2 to improve rx for single
chain chips(AR9285). This would greatly improve rx when there
is only one antenna is connected with AR9285.

Signed-off-by: Vasanthakumar Thiagarajan <vasanth@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agoath9k_hw: Add functions to get/set antenna diversity configuration
Vasanthakumar Thiagarajan [Thu, 2 Sep 2010 08:34:42 +0000 (01:34 -0700)]
ath9k_hw: Add functions to get/set antenna diversity configuration

Signed-off-by: Vasanthakumar Thiagarajan <vasanth@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agoath9k_hw: Add capability flag for Antenna diversity and combining feature
Vasanthakumar Thiagarajan [Thu, 2 Sep 2010 08:34:41 +0000 (01:34 -0700)]
ath9k_hw: Add capability flag for Antenna diversity and combining feature

This is enabled only for ar9285.

Signed-off-by: Vasanthakumar Thiagarajan <vasanth@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agoairo: make strings const
Stephen Hemminger [Thu, 2 Sep 2010 01:17:21 +0000 (18:17 -0700)]
airo: make strings const

Make read/only data structures const. Compile tested only.

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agoray_cs: make data const
Stephen Hemminger [Thu, 2 Sep 2010 01:16:22 +0000 (18:16 -0700)]
ray_cs: make data const

Make the startup and other data parameters that are read/only
const. Compile tested only.

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agoiwlagn: open/close envlope to force move BT state machine
Wey-Yi Guy [Mon, 23 Aug 2010 22:24:49 +0000 (15:24 -0700)]
iwlagn: open/close envlope to force move BT state machine

In uCode, BT state machine need to receive open envlope
command before perform calibration; followed by close envlope
command to move to next stage.

Since Linux has two separated uCode, one for init and the second
one for runtime; we use open envlope commands for init uCode to
indicate we are ready to perform calibration operation.
But for runtime uCode, we are not doing any init calibration,
so we issue open/close envlope commands to force uCode move to
"BT COEX ON" state.

Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agomac80211: only cancel software-based scans on suspend
John W. Linville [Wed, 1 Sep 2010 20:12:28 +0000 (16:12 -0400)]
mac80211: only cancel software-based scans on suspend

Otherwise the hardware scan handler could access an invalid scan request
structure.  The driver should cancel any pending hardware scans during
the suspend process anyway, so also add a warning if the hardware scan
is still pending when the device resumes.

Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agomac80211: cancel scan in ieee80211_restart_hw if software scan pending
John W. Linville [Mon, 30 Aug 2010 19:12:02 +0000 (15:12 -0400)]
mac80211: cancel scan in ieee80211_restart_hw if software scan pending

This function exists to clean-up after a hardware error or something
similar.  The restart is accomplished using the same infrastructure used
to resume after a suspend.  The suspend path cancels running scans, so
it seems appropriate to do that here as well for software-based scans.
If a hardware-based scan is pending, issue a warning message since this
indicates that the drivers has failed to clean-up after itself.

Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agort2x00: Cleanup rt2x00usb_watchdog_reset_tx
Ivo van Doorn [Mon, 30 Aug 2010 19:15:51 +0000 (21:15 +0200)]
rt2x00: Cleanup rt2x00usb_watchdog_reset_tx

rt2x00usb_watchdog_reset_tx performs the same task
as rt2x00usb_kill_tx_queue, with the only difference
is that it waits for all entries to be returned to
the driver and for all frames the status has been
reported to mac80211.

We can easily split this task by calling rt2x00usb_kill_tx_queue,
sleep for a short period and invoke the TX status reporting
function. By adding the sleep() to the kill_entry we make sure
that even during shutdown we guarentee the entry has been killed when
the function returns. To make this work correctly the interrupt
handlers have to be updated to prevent checking for the RADIO_ENABLED
flag too early which prevents the ownership of the entry to be reset.
Additionally a check for the DEVICE_PRESENT flag is not required but
is nice to prevent race conditions when the device was unplugged.

Additionally rather then calling rt2x00usb_work_txdone() for
status reporting we let the driver perform the TX status reporting
first. If this is not sufficient then rt2x00usb_work_txdone() will
still be used to cleanup the mess.

Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com>
Acked-by: Gertjan van Wingerde <gwingerde@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agort2x00: Split watchdog check into a DMA and STATUS timeout
Ivo van Doorn [Mon, 30 Aug 2010 19:15:19 +0000 (21:15 +0200)]
rt2x00: Split watchdog check into a DMA and STATUS timeout

The watchdog for rt2800usb triggers frequently causing all URB's
to be canceled often enough to interrupt the normal TX flow.
More research indicated that not the URB upload to the USB host
were hanging, but instead the TX status reports.

To correctly detect what is going on, we introduce Q_INDEX_DMA_DONE
which is an index counter between Q_INDEX_DONE and Q_INDEX and indicates
if the frame has been transfered to the device.

This also requires the rt2x00queue timeout functions to be updated
to differentiate between a DMA timeout (time between Q_INDEX and
Q_INDEX_DMA_DONE timeout) and a STATUS timeout (time between
Q_INDEX_DMA_DONE and Q_INDEX_DONE timeout)

All Q_INDEX_DMA_DONE code was taken from the RFC from
Helmut Schaa <helmut.schaa@googlemail.com> for the implementation
for watchdog for rt2800pci.

Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com>
Acked-by: Gertjan van Wingerde <gwingerde@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agort2x00: Correctly kill beacon queue
Ivo van Doorn [Mon, 30 Aug 2010 19:14:56 +0000 (21:14 +0200)]
rt2x00: Correctly kill beacon queue

USB devices upload their beacon and then automatically send
it out every beacon interval. However when killing a TX queue
we only kill the URB and not the actual transmission of the beacon.

This will reset the Beacon register to prevent any beacons from
being transmitted.

Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com>
Acked-by: Gertjan van Wingerde <gwingerde@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agort2x00: Set PWR_PIN_CFG during initialization
Ivo van Doorn [Mon, 30 Aug 2010 19:14:38 +0000 (21:14 +0200)]
rt2x00: Set PWR_PIN_CFG during initialization

Add PWR_PIN_CFG initialization for rt2800usb at the same point
as rt2800pci.

Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com>
Acked-by: Gertjan van Wingerde <gwingerde@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agort2x00: Don't set unicast/BSSID masks when clearning MAC or BSSID
Ivo van Doorn [Mon, 30 Aug 2010 19:14:15 +0000 (21:14 +0200)]
rt2x00: Don't set unicast/BSSID masks when clearning MAC or BSSID

When configuring the MAC_ADDR or MAC_BSSID with an empty address,
the UNICAST_TO_ME_MASK and BSS_ID_MASK must also be reset to prevent
invalid interpretation of the addresses.

Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com>
Acked-by: Gertjan van Wingerde <gwingerde@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agort2x00: Wakeup hardware before loading firmware
Ivo van Doorn [Mon, 30 Aug 2010 19:13:54 +0000 (21:13 +0200)]
rt2x00: Wakeup hardware before loading firmware

According to the legacy drivers the AUTOWAKEUP_CFG
register must be reset to 0 before loading the firmware.

Instead of during rt2800{pci,usb}_write_firmware it
must actually be done in rt2800_load_firmware() before
resetting the WPDMA_GLO_CFG and PWR_PIN_CFG registers.

Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com>
Acked-by: Gertjan van Wingerde <gwingerde@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agort2x00: Validate TX status results with current data entry
Ivo van Doorn [Mon, 30 Aug 2010 19:13:30 +0000 (21:13 +0200)]
rt2x00: Validate TX status results with current data entry

Instead of printing a warning when the PID, ACK, or WCID of
an entry don't match the TX status report, we should skip the
entry to search for the entry which actually does match
the TX status data.

This reduces the number of watchdog errors on the TX queues
for rt2800usb, and seems to improve the reliability of the
TX flow a bit.

Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com>
Acked-by: Gertjan van Wingerde <gwingerde@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agort2x00: Add rt2800_wait_csr_ready
Ivo van Doorn [Mon, 30 Aug 2010 19:13:08 +0000 (21:13 +0200)]
rt2x00: Add rt2800_wait_csr_ready

Similar to rt2800_wait_wpdma_ready() we can add a
function to waiting until the CSR is ready. This
centralizes some additional code into rt2800lib.

Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com>
Acked-by: Gertjan van Wingerde <gwingerde@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agort2x00: Update rt2800 comments regarding AMPDU and PACKET_ID in TXWI
Helmut Schaa [Mon, 30 Aug 2010 19:12:47 +0000 (21:12 +0200)]
rt2x00: Update rt2800 comments regarding AMPDU and PACKET_ID in TXWI

Signed-off-by: Helmut Schaa <helmut.schaa@googlemail.com>
Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agort2x00: Rename txentry_desc.queue -> txentry_desc.qid
Helmut Schaa [Mon, 30 Aug 2010 19:12:24 +0000 (21:12 +0200)]
rt2x00: Rename txentry_desc.queue -> txentry_desc.qid

Variables containing queue ids are called qid everywhere else, hence
rename the queue field in txentry_desc to qid as well.

Signed-off-by: Helmut Schaa <helmut.schaa@googlemail.com>
Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agoath9k: fix spurious MIC failure reports
Felix Fietkau [Sat, 28 Aug 2010 16:21:21 +0000 (18:21 +0200)]
ath9k: fix spurious MIC failure reports

According to the hardware documentation, the MIC failure bit is only
valid if the frame was decrypted using a valid TKIP key and is not a
fragment.
In some setups I've seen hardware-reported MIC failures on an AP that
was configured for CCMP only, so it's clear that additional checks are
necessary.

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Cc: stable@kernel.org
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agonet/wireless: Remove double test
Julia Lawall [Sat, 28 Aug 2010 15:41:06 +0000 (17:41 +0200)]
net/wireless: Remove double test

The same expression is tested twice and the result is the same each time.

The sematic match that finds this problem is as follows:
(http://coccinelle.lip6.fr/)

// <smpl>
@expression@
expression E;
@@

(
* E
  || ... || E
|
* E
  && ... && E
)
// </smpl>

Signed-off-by: Julia Lawall <julia@diku.dk>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agowl1251: Fix queue stopping/waking for TX path
Denis 'GNUtoo' Carikli [Fri, 27 Aug 2010 21:48:19 +0000 (23:48 +0200)]
wl1251: Fix queue stopping/waking for TX path

This patch was adapted from 06f7bc7db79fabe6b2ec16eff0f59e4acc21eb72
(from linus's linux-2.6 tree of kernel.org)

here's the original message:
    The queue stopping/waking functionality was broken in a way that could
    cause huge latencies in TX transfers and even cause the TX to stall in the
    right circumstances. Correct these problems.

Signed-off-by: Denis 'GNUtoo' Carikli <GNUtoo@no-log.org>
Acked-by: Kalle Valo <kvalo@adurom.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agomac80211: Do not generate CQM events based on first Beacon frames
Jouni Malinen [Fri, 27 Aug 2010 19:22:00 +0000 (22:22 +0300)]
mac80211: Do not generate CQM events based on first Beacon frames

The signal strength value in a single RX frame is not that reliable,
so it is better to delay start of CQM events until there is a real
average signal strength from more than a single Beacon frame
available.

Signed-off-by: Jouni Malinen <j@w1.fi>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agomac80211: Fix signal strength average initialization for CQM events
Jouni Malinen [Fri, 27 Aug 2010 19:21:13 +0000 (22:21 +0300)]
mac80211: Fix signal strength average initialization for CQM events

The ave_beacon_signal value uses 1/16 dB unit and as such, must be
initialized with the signal level of the first Beacon frame multiplied
by 16. This fixes an issue where the initial CQM events are reported
incorrectly with a burst of events while the running average
approaches the correct value after the incorrect initialization. This
could cause user space -based roaming decision process to get quite
confused at the moment when we would like to go through authentication
and DHCP.

Cc: stable@kernel.org
Signed-off-by: Jouni Malinen <j@w1.fi>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agoMerge branch 'wireless-next-2.6' of git://git.kernel.org/pub/scm/linux/kernel/git...
John W. Linville [Tue, 31 Aug 2010 18:12:19 +0000 (14:12 -0400)]
Merge branch 'wireless-next-2.6' of git://git./linux/kernel/git/iwlwifi/iwlwifi-2.6

14 years agomac80211: fix offchannel queue stop
Johannes Berg [Fri, 27 Aug 2010 11:45:28 +0000 (13:45 +0200)]
mac80211: fix offchannel queue stop

Somebody noticed this problem, and I outlined
to them how to fix it, but haven't heard back
from them. So while I was adding the state
field I figured I could use it to fix it.

The problem, as I understand it, is that when
we go offchannel while the driver has a queue
stopped, the driver will likely start draining
the queue and then enable it while offchannel.
This in turn will enable the interface queue,
and that leads to transmitting data frames on
the wrong channel.

Fix this by keeping track of offchannel status
per interface, and not enabling the interface
queues on interfaces that are offchannel when
the driver enables a queue.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agomac80211_hwsim: support runtime iftype changes
Johannes Berg [Fri, 27 Aug 2010 10:35:59 +0000 (12:35 +0200)]
mac80211_hwsim: support runtime iftype changes

Add the trivial support for runtime interface
type changes to mac80211_hwsim for testing.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agomac80211: support runtime interface type changes
Johannes Berg [Fri, 27 Aug 2010 10:35:58 +0000 (12:35 +0200)]
mac80211: support runtime interface type changes

Add support to mac80211 for changing the interface
type even when the interface is UP, if the driver
supports it.

To achieve this
 * add a new driver callback for switching,
 * split some of the interface up/down code out
   into new functions (do_open/do_stop), and
 * maintain an own __SDATA_RUNNING bit that will
   not be set during interface type, so that any
   other code doesn't use the interface.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agomac80211: split out concurrent vif checks
Johannes Berg [Fri, 27 Aug 2010 10:35:57 +0000 (12:35 +0200)]
mac80211: split out concurrent vif checks

Split the concurrent virtual interface checks
into a new function that can be used to check
for any given new interface type.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agomac80211: simplify zero address checks
Johannes Berg [Fri, 27 Aug 2010 10:35:56 +0000 (12:35 +0200)]
mac80211: simplify zero address checks

The libertas_tf special code for zero addresses
is a bit too complex, it compares against a stack
value instead of using is_zero_ether_addr() and
tries to update all interfaces even if just the
one that's being brought up needs to be changed.
Additionally, the repeated check for a valid MAC
address need only be done if we actually changed
it on the fly.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agomac80211: switch to ieee80211_sdata_running
Johannes Berg [Fri, 27 Aug 2010 10:35:55 +0000 (12:35 +0200)]
mac80211: switch to ieee80211_sdata_running

Since the introduction of ieee80211_sdata_running(),
some new code was introduced that uses netif_running()
instead. Switch all these instances over.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agomac80211: clean up ifdown/cleanup paths
Johannes Berg [Fri, 27 Aug 2010 10:35:54 +0000 (12:35 +0200)]
mac80211: clean up ifdown/cleanup paths

There's a lot of redundant code in mac80211's
interface cleanup/down, for example freeing
AP beacons is done both when the interface is
set DOWN as well as when it is torn down, of
which only the former has any effect.

Also, a bunch of things should be closer to
where they matter, like the MLME timers that
we should cancel when disassociating, rather
than only when the interface is set DOWN.

Clean up all this code.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agomac80211: use subqueue helpers
Johannes Berg [Fri, 27 Aug 2010 11:36:49 +0000 (13:36 +0200)]
mac80211: use subqueue helpers

There are subqueue helpers so that we don't
need to get the TX queue and then wake/stop
it, use those helpers.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agomac80211: allow changing port control protocol
Johannes Berg [Fri, 27 Aug 2010 11:26:54 +0000 (14:26 +0300)]
mac80211: allow changing port control protocol

Some vendor specified mechanisms for 802.1X-style
functionality use a different protocol than EAP
(even if EAP is vendor-extensible). Support this
in mac80211 via the cfg80211 API for it.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Juuso Oikarinen <juuso.oikarinen@nokia.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agocfg80211: allow changing port control protocol
Johannes Berg [Fri, 27 Aug 2010 11:26:53 +0000 (14:26 +0300)]
cfg80211: allow changing port control protocol

Some vendor specified mechanisms for 802.1X-style
functionality use a different protocol than EAP
(even if EAP is vendor-extensible). Allow setting
the ethertype for the protocol when a driver has
support for this. The default if unspecified is
EAP, of course.

Note: This is suitable only for station mode, not
      for AP implementation.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Juuso Oikarinen <juuso.oikarinen@nokia.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agomac80211: allow vendor specific cipher suites
Johannes Berg [Fri, 27 Aug 2010 11:26:52 +0000 (14:26 +0300)]
mac80211: allow vendor specific cipher suites

Allow drivers to specify their own set of cipher
suites to advertise vendor-specific ciphers. The
driver is then required to implement hardware
crypto offload for it.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Juuso Oikarinen <juuso.oikarinen@nokia.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agocfg80211: allow vendor specific cipher suites
Johannes Berg [Fri, 27 Aug 2010 11:26:51 +0000 (14:26 +0300)]
cfg80211: allow vendor specific cipher suites

cfg80211 currently rejects all cipher suites it
doesn't know about for key length checking
purposes. This can lead to inconsistencies when
a driver advertises an algorithm that cfg80211
doesn't know about. Remove this rejection so
drivers can specify any algorithm they like.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Juuso Oikarinen <juuso.oikarinen@nokia.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agocfg80211 docbook: remove erronous !A
Johannes Berg [Fri, 27 Aug 2010 09:29:24 +0000 (11:29 +0200)]
cfg80211 docbook: remove erronous !A

My previous patch erroneously included an
!A line (for some checking I am working on)
that isn't yet supported by the docbook
tools, so remove it.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agoath9k_htc: Enable ANI in associated state only
Rajkumar Manoharan [Fri, 27 Aug 2010 06:39:00 +0000 (12:09 +0530)]
ath9k_htc: Enable ANI in associated state only

While scanning, ANI is triggered unnecessarily where sta is in
unassociated state. And cancelling ani work in ath9k_htc_stop
is not required.

Signed-off-by: Rajkumar Manoharan <rmanoharan@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agowl12xx: remove unneeded locking
Johannes Berg [Thu, 26 Aug 2010 11:30:27 +0000 (13:30 +0200)]
wl12xx: remove unneeded locking

With the scan callback now being callable from
any context, these unlocks/locks can go away.
This makes the code easier to understand, since
callers of these functions must no longer be
aware that the mutex may be dropped.

As Stanislaw is working on iwlwifi scanning, I
didn't change it to take advantage of the new
mac80211 semantics.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agomac80211: allow scan to complete from any context
Johannes Berg [Thu, 26 Aug 2010 11:30:26 +0000 (13:30 +0200)]
mac80211: allow scan to complete from any context

The ieee80211_scan_completed() function was a frequent
source of potential deadlocks, since it is called by
drivers but may call back into drivers, so drivers had
to make sure to call it without any locks held, which
frequently lead to more complex code in drivers. Avoid
that problem by allowing the function to be called in
any context, and queueing the actual work it does.
Also update the documentation for it to indicate this.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agomac80211: remove unused scan expire define
Johannes Berg [Thu, 26 Aug 2010 11:30:25 +0000 (13:30 +0200)]
mac80211: remove unused scan expire define

Since cfg80211 manages the BSS list completely,
this define hasn't been used for a long time
and will never be used again.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agoath9k: Change the default LED pattern.
Vivek Natarajan [Wed, 25 Aug 2010 14:04:52 +0000 (19:34 +0530)]
ath9k: Change the default LED pattern.

All major Atheros customers require the led to be in continuous
ON state rather than the blinking pattern.

Signed-off-by: Vivek Natarajan <vnatarajan@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agoath5k: fix off-by-one in pilot magnitude mask
Bob Copeland [Wed, 25 Aug 2010 01:37:14 +0000 (21:37 -0400)]
ath5k: fix off-by-one in pilot magnitude mask

If the symbol offset is 46, it will be counted in both
the third and fourth bytes of the mask, and in this
case the shift will be negative which can pollute
high order bits in the mask.  This may negatively impact
OFDM symbol detection.

Signed-off-by: Bob Copeland <me@bobcopeland.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agoath5k: re-order one of the frees on unwind
Dan Carpenter [Sat, 21 Aug 2010 19:24:59 +0000 (21:24 +0200)]
ath5k: re-order one of the frees on unwind

There was a small misordering here.  In the original code, if we were to
go to err_free_ah then it wouldn't free the irq.

Signed-off-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agoiwlwifi: allow using multiple contexts
Johannes Berg [Mon, 23 Aug 2010 08:46:58 +0000 (10:46 +0200)]
iwlwifi: allow using multiple contexts

We're now ready to start using multiple contexts.
We do this by keeping track of the valid interface
types per context (exclusive [ibss] and normal)
and checking which context is "free" when a new
interface is added.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: follow main beacon interval
Johannes Berg [Mon, 23 Aug 2010 08:46:57 +0000 (10:46 +0200)]
iwlwifi: follow main beacon interval

It is necessary that the PAN context always
use the same beacon interval as the BSS
context unless it is in dual-station mode,
ie. the PAN context is a station as well,
so implement that.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlagn: always send RXON timing
Johannes Berg [Mon, 23 Aug 2010 08:46:56 +0000 (10:46 +0200)]
iwlagn: always send RXON timing

The PAN context requires also getting
RXON timing when we send an unassociated
RXON in some cases.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: pass context to iwl_send_rxon_timing
Johannes Berg [Mon, 23 Aug 2010 08:46:55 +0000 (10:46 +0200)]
iwlwifi: pass context to iwl_send_rxon_timing

Sometimes we need to send RXON timing even
when we don't have a virtual interface yet,
so pass the context and allow passing one
without a virtual interface pointer.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: send PAN parameters
Johannes Berg [Fri, 27 Aug 2010 16:44:50 +0000 (09:44 -0700)]
iwlwifi: send PAN parameters

In order for the microcode to be able to handle
multiple interfaces, we need to give it the PAN
parameters that state how to allocate the time
between the two interfaces. Do this, and update
it wherever necessary.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlagn: send beacon before committing associated RXON
Johannes Berg [Mon, 23 Aug 2010 08:46:53 +0000 (10:46 +0200)]
iwlagn: send beacon before committing associated RXON

Newer AGN microcode requires know the beacon
before starting the AP so that it can start
beaconing right away. Implement that.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlagn: send RXON timing before associating
Johannes Berg [Mon, 23 Aug 2010 08:46:52 +0000 (10:46 +0200)]
iwlagn: send RXON timing before associating

The PAN functionality requires us to send the
timing including a valid DTIM period to the
microcode before associating, so request this
data from mac80211 and send it to the device.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlagn: queue frames according to context
Johannes Berg [Mon, 23 Aug 2010 08:46:51 +0000 (10:46 +0200)]
iwlagn: queue frames according to context

Frames for different contexts need to be put
on different queues, and multicast after DTIM
frames have a special queue yet which also
depends on the context, so put all this into
the context.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlagn: remove iw_mode check for beacon
Johannes Berg [Mon, 23 Aug 2010 08:46:50 +0000 (10:46 +0200)]
iwlagn: remove iw_mode check for beacon

Since we have the beacon context now, we no
longer need to rely on iw_mode but can check
the beacon context interface's type. However,
that check must be in the work item instead
due to locking constraints (mutex must be
held when dereferencing beacon_ctx pointer).

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlagn: detect PAN capability
Johannes Berg [Mon, 23 Aug 2010 08:46:49 +0000 (10:46 +0200)]
iwlagn: detect PAN capability

Detect whether or not the ucode is PAN
capable and adjust the valid contexts
accordingly. To be able to do this, add
the PAN context to the array as well.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: add PAN API
Johannes Berg [Mon, 23 Aug 2010 08:46:48 +0000 (10:46 +0200)]
iwlwifi: add PAN API

Define the new host commands and notifications
REPLY_WIPAN_PARAMS
REPLY_WIPAN_RXON
REPLY_WIPAN_RXON_TIMING
REPLY_WIPAN_RXON_ASSOC
REPLY_WIPAN_QOS_PARAM
REPLY_WIPAN_WEPKEY
REPLY_WIPAN_P2P_CHANNEL_SWITCH
REPLY_WIPAN_NOA_NOTIFICATION

and their corresponding structures along with the PAN
station flag, the PAN AP sta ID and new dev types for
the second context.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: introduce beacon context
Johannes Berg [Mon, 23 Aug 2010 08:46:47 +0000 (10:46 +0200)]
iwlwifi: introduce beacon context

Only one context can be beaconing at a time,
but we need to track which one. Introduce a
new variable priv->beacon_ctx to do that.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: move HT configuration data into context
Johannes Berg [Mon, 23 Aug 2010 08:46:46 +0000 (10:46 +0200)]
iwlwifi: move HT configuration data into context

A lot of HT configuration semantically belongs into
the context, even if right now it will never be
different between contexts. Move it so we're better
prepared for future changes in mac80211.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: add context pointer to station
Johannes Berg [Mon, 23 Aug 2010 08:46:45 +0000 (10:46 +0200)]
iwlwifi: add context pointer to station

Sometimes we only pass around station
pointers but need to find the context
they belong to, so store it in there.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: store default station flags in context
Johannes Berg [Mon, 23 Aug 2010 08:46:44 +0000 (10:46 +0200)]
iwlwifi: store default station flags in context

Since the default context is initialised to zero,
and the default flags are zero, no more code is
needed to initialise them right now, but another
context can have different default flags.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: make hw crypto context aware
Johannes Berg [Mon, 23 Aug 2010 08:46:43 +0000 (10:46 +0200)]
iwlwifi: make hw crypto context aware

HW crypto needs to be aware of the context, and there
are different command IDs for the WEP keys per context,
so move the key tracking variables and command IDs into
the context structure.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: move AP sta ID to context
Johannes Berg [Mon, 23 Aug 2010 08:46:42 +0000 (10:46 +0200)]
iwlwifi: move AP sta ID to context

Each context needs to use a different AP sta
ID, so we need to move that into the context
struct instead of hardcoding it.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: clamp scanning dwell time to all contexts
Johannes Berg [Mon, 23 Aug 2010 08:46:41 +0000 (10:46 +0200)]
iwlwifi: clamp scanning dwell time to all contexts

The dwell time should at least fit into all
context's beacon intervals.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: move virtual interface pointer into context
Johannes Berg [Mon, 23 Aug 2010 08:46:40 +0000 (10:46 +0200)]
iwlwifi: move virtual interface pointer into context

iwlwifi occasionally needs to find the virtual
interface pointer to give it to mac80211, but right
now it only keeps one. Move it into the context so
that we can keep one pointer each.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: add context into tx descriptor
Johannes Berg [Mon, 23 Aug 2010 08:46:39 +0000 (10:46 +0200)]
iwlwifi: add context into tx descriptor

In status processing we'll need to find the context
for a given frame, so add a context pointer to the
TX info for each frame.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: move QoS into context
Johannes Berg [Mon, 23 Aug 2010 08:46:38 +0000 (10:46 +0200)]
iwlwifi: move QoS into context

Since mac80211 doesn't currently enable/disable
QoS per interface, we can't yet do it properly,
but we can already prepare for it and move the
QoS data and command ID into the context struct.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: contextify command sending
Johannes Berg [Mon, 23 Aug 2010 08:46:37 +0000 (10:46 +0200)]
iwlwifi: contextify command sending

Some commands will have different command IDs
for different contexts, so we need to store
those IDs in the context structure and use
them instead of hardcoding the commands.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: contextify-stations-completely
Johannes Berg [Fri, 27 Aug 2010 15:55:52 +0000 (08:55 -0700)]
iwlwifi: contextify-stations-completely

The microcode tracks stations per context, so
the driver needs to do that as well for adding,
deleting and restoring them, especially in the
implicit removal case when we send an RXON.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: contextify broadcast station
Johannes Berg [Fri, 27 Aug 2010 15:53:46 +0000 (08:53 -0700)]
iwlwifi: contextify broadcast station

The broadcast station ID is per context, so
add a variable for the ID in the context and
use it everywhere we previously hardcoded it.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: define PAN queues/FIFOs
Johannes Berg [Mon, 23 Aug 2010 08:46:34 +0000 (10:46 +0200)]
iwlwifi: define PAN queues/FIFOs

PAN capable microcode has a different
queue assignment (not just more queues
for PAN) due to the way multicast is
handled for AP mode.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: prepare for PAN queue/fifo assignment
Johannes Berg [Mon, 23 Aug 2010 08:46:33 +0000 (10:46 +0200)]
iwlwifi: prepare for PAN queue/fifo assignment

PAN ucode will require a different queue assignment,
in particular queue 9 instead of 4 should be used for
commands.

This is required because the ucode will stop/start
queues 4 and 8 depending on the PAN state, since
queue 8 will be used for PAN multicast (after DTIM).

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: initial contextification
Johannes Berg [Mon, 23 Aug 2010 08:46:32 +0000 (10:46 +0200)]
iwlwifi: initial contextification

In order to support multiple interfaces, we must move
a lot of data into per-context structures so we can
use the contexts the device offers. To start with,
this makes a lot of code context-aware, more changes
will move more things into the context structure.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
14 years agoiwlwifi: fix compile error without debugging support
Wey-Yi Guy [Tue, 24 Aug 2010 14:27:56 +0000 (07:27 -0700)]
iwlwifi: fix compile error without debugging support

Encounter compiler error when iwlwifi debugging support is
disabled, fix it.

This compiler error was introduced by the previous WiFi/BT coexist patchset.

Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agomac80211: fix mesh advertisement
Johannes Berg [Wed, 25 Aug 2010 12:34:01 +0000 (14:34 +0200)]
mac80211: fix mesh advertisement

When a mac80211-based driver advertises mesh mode
support, this will be advertised to userspace.
However, if mac80211 was compiled without mesh
support, then that won't actually be true. Fix
this by removing the bit for mesh if mesh isn't
compiled in.

Since this synchronizes what we advertise to
cfg80211 and actually support, it means we can
now rely on cfg80211's interface type checks
and need not check again in mac80211.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agop54: better rssi->dbm conversion for longbow phys
Christian Lamparter [Tue, 24 Aug 2010 21:29:05 +0000 (23:29 +0200)]
p54: better rssi->dbm conversion for longbow phys

This patch should fix the dodgy signal and noise value
reports for most longbow (p54spi) users:

e.g.: (an older tcpdump extract)
> 2.0 Mb/s 2437 MHz (0x00a0) -49dB signal -41dB noise
> 1.0 Mb/s 2437 MHz (0x00a0) 4dB signal -41dB noise

The formula is taken from stlc45xx:
http://gitorious.org/stlc45xx/mainline/blobs/master/stlc45xx.c#line1199

Signed-off-by: Christian Lamparter <chunkeey@googlemail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agomac80211: fix rcu-unsafe pointer dereference
Christian Lamparter [Tue, 24 Aug 2010 17:22:42 +0000 (19:22 +0200)]
mac80211: fix rcu-unsafe pointer dereference

This patch fixes a potential crash (null-pointer de-
reference) which was introduced in my previous patch:
 "mac80211: AMPDU rx reorder timeout timer"

During a BA teardown, the pointer to the soon-to-be-gone
tid_ampdu_rx element will be nullified. Therefore the
release timer mechanism has to be careful not to
accidentally access the item without any RCU protection.

Signed-off-by: Christian Lamparter <chunkeey@googlemail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agonl80211: fix missing nesting
Johannes Berg [Tue, 24 Aug 2010 10:15:53 +0000 (12:15 +0200)]
nl80211: fix missing nesting

commit 95a6ccbb46c70cff376684c752831c014c87029d
Author: Johannes Berg <johannes.berg@intel.com>
Date:   Thu Aug 12 15:38:38 2010 +0200

    cfg80211/mac80211: extensible frame processing

introduced a netlink bug that caused parsing errors
in userspace because it forgot to close a nesting,
which would advertise a nesting length of zero to
userspace, which then completely threw off parsing
and led to

Illegal nla->nla_type == 0

being printed by libnl.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agort2x00: fix "buffer size not provably correct" build warning
Arnaud Patard (Rtp) [Mon, 23 Aug 2010 21:02:22 +0000 (23:02 +0200)]
rt2x00: fix "buffer size not provably correct" build warning

rt2x00 debugfs interface doesn't check the size of the data coming
from userspace, leading to a build warning. Fix That.

v2: return EINVAL if input is too long

Signed-off-by: Arnaud Patard <arnaud.patard@rtp-net.org>
Acked-by: Ivo van Doorn <IvDoorn@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agort2x00: Fix max TX power settings
Ivo van Doorn [Mon, 23 Aug 2010 17:56:07 +0000 (19:56 +0200)]
rt2x00: Fix max TX power settings

During initialization each driver reads the default TX power
for each individual channel. However mac80211 only accepts the
maximum value (which is also handled as default value).

As a result, the TX power of the device was being limited to
the default value, which is often quite low compared to the
real maximum acceptable value.

This patch allows each driver to set the maximum value on a
per-channel basis which is forwarded to mac80211. The default
value will be preserved for now, in case we want to update
mac80211 to differentiate between the maximum and default txpower.

This fixes bug complaining about limited TX power values like:
https://bugzilla.kernel.org/show_bug.cgi?id=16358

Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com>
Acked-by: Helmut Schaa <helmut.schaa@googlemail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agort2x00: Fix channel configuration for RF3052
Ivo van Doorn [Mon, 23 Aug 2010 17:55:43 +0000 (19:55 +0200)]
rt2x00: Fix channel configuration for RF3052

We missed a check for RF3052 in the config_channel
configuration function. As a result the channel is not
properly configured for RF3052 devices. This also
requires rt2800_config_channel_rf3xxx to support 5GHz
channels, so we must apply the TXPOWER_A_TO_DEV and
TXPOWER_G_TO_DEV conversions during rt2800_config_channel()

Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com>
Acked-by: Helmut Schaa <helmut.schaa@googlemail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agort2x00: Merge rt2800{pci/usb} radio enabling/disabling code to rt2800lib
Ivo van Doorn [Mon, 23 Aug 2010 17:55:22 +0000 (19:55 +0200)]
rt2x00: Merge rt2800{pci/usb} radio enabling/disabling code to rt2800lib

The functions rt2800pci_enable_radio and rt2800usb_disable_radio are
almost equal and can be merged into rt2800lib. This reduces the number
of functions which must be exported from rt2800lib to the drivers at
the same time.

Also rt2800pci_disable_radio and rt2800usb_disable_radio are almost
equal and can be merged into rt2800lib in a similar fashion.

Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com>
Acked-by: Helmut Schaa <helmut.schaa@googlemail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agort2x00: Fix rt2800 retry calculation
Ivo van Doorn [Mon, 23 Aug 2010 17:55:01 +0000 (19:55 +0200)]
rt2x00: Fix rt2800 retry calculation

The retry count for a frame is calculated by the realized MCS rate
subtracting of the requested MCS rate. However during TX done reporting
we accidently override the requested MCS rate with the realized MCS
rate. This causes the retry count to be reset to 0 always, and feeding
invalid rate information into minstrel_ht.

Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com>
Acked-by: Helmut Schaa <helmut.schaa@googlemail.com>
Acked-by: Gertjan van Wingerde <gwingerde@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agort2x00: Remove Q_INDEX_CRYPTO and ENTRY_OWNER_DEVICE_CRYPTO
Ivo van Doorn [Mon, 23 Aug 2010 17:54:41 +0000 (19:54 +0200)]
rt2x00: Remove Q_INDEX_CRYPTO and ENTRY_OWNER_DEVICE_CRYPTO

Q_INDEX_CRYPTO and ENTRY_OWNER_DEVICE_CRYPTO where initially
added with the plan to implement hardware encryption for rt2500pci.
However there are no plans to do so anymore as the crypto
mechanism in rt2500pci is very different then any other Ralink
device.

So we can now safely remove the definitions, and don't think
about this feature anymore. :)

Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com>
Acked-by: Helmut Schaa <helmut.schaa@googlemail.com>
Acked-by: Gertjan van Wingerde <gwingerde@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agort2x00: Move direct access to queue->entries to rt2x00queue.c
Ivo van Doorn [Mon, 23 Aug 2010 17:54:21 +0000 (19:54 +0200)]
rt2x00: Move direct access to queue->entries to rt2x00queue.c

All access to queue->entries through the Q_INDEX/Q_INDEX_DONE
variables must be done using spinlock protection. It is best
to manage this completely from rt2x00queue.c.

For safely looping through all entries in the queue, the function
rt2x00queue_for_each_entry is added which will walk from from a index
range in a safe manner.

This also fixes rt2x00usb which walked the entries list from
0 to length to kill each entry (killing entries must be done
from Q_INDEX_DONE to Q_INDEX to enforce TX status reporting to
occur in the correct order.

Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com>
Acked-by: Gertjan van Wingerde <gwingerde@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agort2x00: Reduce indenting
Ivo van Doorn [Mon, 23 Aug 2010 17:54:02 +0000 (19:54 +0200)]
rt2x00: Reduce indenting

Cosmetic change, reduce indenting.

Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com>
Acked-by: Helmut Schaa <helmut.schaa@googlemail.com>
Acked-by: Gertjan van Wingerde <gwingerde@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agort2x00: Simplify arguments to rt2x00 driver callback functions
Ivo van Doorn [Mon, 23 Aug 2010 17:53:39 +0000 (19:53 +0200)]
rt2x00: Simplify arguments to rt2x00 driver callback functions

write_tx_desc shouldn't pass a rt2x00dev and skb pointer,
instead it should use the same format as other TX frame
callback functions, which is passing the data_entry pointer
which contains all the information which is needed to work
on a TX frame.

Most callers of the kick_tx_queue and kill_tx_queue already
have the data_queue pointer, so rather then sending the QID
with the given function, when the driver requests a new
pointer to the data_queue, it is more efficient to just
send the data_queue pointer directly.

Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com>
Acked-by: Gertjan van Wingerde <gwingerde@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
14 years agoiwlwifi: disable aggregation queue if stopped early
Johannes Berg [Mon, 23 Aug 2010 14:57:17 +0000 (07:57 -0700)]
iwlwifi: disable aggregation queue if stopped early

When aggregation is stopped again for some reason
before the queue we selected has drained, we will
currently leak the TX queue and keep it enabled
for aggregation. Normally this doesn't happen, so
the problem is rarely seen.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>