- 14 Sep, 2010 6 commits
-
-
Christian Lamparter authored
Signed-off-by:
Christian Lamparter <chunkeey@googlemail.com> Signed-off-by:
John W. Linville <linville@tuxdriver.com>
-
Christian Lamparter authored
Signed-off-by:
-
Christian Lamparter authored
Signed-off-by:
-
Christian Lamparter authored
Signed-off-by:
-
Christian Lamparter authored
Signed-off-by:
-
Christian Lamparter authored
Signed-off-by:
-
- 11 Sep, 2010 10 commits
-
-
Wey-Yi Guy authored
Move the duplicated code into single static function. Signed-off-by:Wey-Yi Guy <wey-yi.w.guy@intel.com>
-
Wey-Yi Guy authored
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: -
Johannes Berg authored
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:
-
Johannes Berg authored
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 authored
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:
-
Wey-Yi Guy authored
Even driver use rts/cts protection mode for aggregation packets by default. Allow the protection mode to be configure through debugfs Signed-off-by: -
Johannes Berg authored
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 authored
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:
-
Wey-Yi Guy authored
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: -
Tomas Winkler authored
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:
-
- 07 Sep, 2010 9 commits
-
-
Julia Lawall authored
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:
-
Michael Büsch authored
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:
-
Rajkumar Manoharan authored
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:
-
Rajkumar Manoharan authored
By enabling fastcc, the scan time reduced to half. Signed-off-by:
-
Vasanthakumar Thiagarajan authored
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:
-
Vasanthakumar Thiagarajan authored
Signed-off-by:
-
Vasanthakumar Thiagarajan authored
This is enabled only for ar9285. Signed-off-by:
-
Stephen Hemminger authored
Make read/only data structures const. Compile tested only. Signed-off-by:
Stephen Hemminger <shemminger@vyatta.com> Signed-off-by:
-
Stephen Hemminger authored
Make the startup and other data parameters that are read/only const. Compile tested only. Signed-off-by:
-
- 03 Sep, 2010 1 commit
-
-
Wey-Yi Guy authored
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:
-
- 01 Sep, 2010 1 commit
-
-
John W. Linville authored
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:
-
- 31 Aug, 2010 13 commits
-
-
John W. Linville authored
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: -
Ivo van Doorn authored
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:
-
Ivo van Doorn authored
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 authored
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 authored
Add PWR_PIN_CFG initialization for rt2800usb at the same point as rt2800pci. Signed-off-by:
-
Ivo van Doorn authored
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 authored
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 authored
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 authored
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:
-
Helmut Schaa authored
Signed-off-by:
Helmut Schaa <helmut.schaa@googlemail.com> Signed-off-by:
-
Helmut Schaa authored
Variables containing queue ids are called qid everywhere else, hence rename the queue field in txentry_desc to qid as well. Signed-off-by:
-
Felix Fietkau authored
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:
-
Julia Lawall authored
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:
-
