Based on a quick test with AR9271, TDLS seems to be working fine.
Tests were done with 2 Atheros AR9271 based devices with firmware
1.3 (sha1 8d49f928aa40ac53c729189bff1333cd373a7fb5), associated
with a WAP54G access point. TDLS worked fine both in WPA2 mode and
without encryption. Stations maintained ping flood traffic between
each other and towards the AP without significant losses.
Not tested with AR7010.
TDLS was enabled in earlier patches the same way for other
Atheros drivers:
ath9k (fd6562344dea2b8b2a5d644cf971f4e56004500a),
and carl9170 (d1f3de71a584a82ee4e84505fce9acccf40215ff).
Signed-off-by: Csaba Kiraly <[email protected]>
---
drivers/net/wireless/ath/ath9k/htc_drv_init.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
index 8a3bd5f..d779f4f 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
@@ -592,6 +592,8 @@ static void ath9k_set_hw_capab(struct ath9k_htc_priv *priv,
hw->wiphy->flags |= WIPHY_FLAG_IBSS_RSN |
WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL;
+ hw->wiphy->flags |= WIPHY_FLAG_SUPPORTS_TDLS;
+
hw->queues = 4;
hw->max_listen_interval = 1;
--
1.9.1
Am 18.08.2014 um 01:53 schrieb Csaba Kiraly:
> Based on a quick test with AR9271, TDLS seems to be working fine.
>
> Tests were done with 2 Atheros AR9271 based devices with firmware
> 1.3 (sha1 8d49f928aa40ac53c729189bff1333cd373a7fb5), associated
> with a WAP54G access point.
please, don't use firmware 1.3. Use git source, or you can get
precompiled version here:
https://github.com/olerem/ath9k-htc-firmware-blob
> TDLS worked fine both in WPA2 mode and
> without encryption. Stations maintained ping flood traffic between
> each other and towards the AP without significant losses.
>
> Not tested with AR7010.
Seems ok for me. How can i reproduce testing environment?
> TDLS was enabled in earlier patches the same way for other
> Atheros drivers:
> ath9k (fd6562344dea2b8b2a5d644cf971f4e56004500a),
> and carl9170 (d1f3de71a584a82ee4e84505fce9acccf40215ff).
>
> Signed-off-by: Csaba Kiraly <[email protected]>
> ---
> drivers/net/wireless/ath/ath9k/htc_drv_init.c | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
> index 8a3bd5f..d779f4f 100644
> --- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c
> +++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
> @@ -592,6 +592,8 @@ static void ath9k_set_hw_capab(struct ath9k_htc_priv *priv,
> hw->wiphy->flags |= WIPHY_FLAG_IBSS_RSN |
> WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL;
>
> + hw->wiphy->flags |= WIPHY_FLAG_SUPPORTS_TDLS;
> +
> hw->queues = 4;
> hw->max_listen_interval = 1;
>
>
On 19/08/2014 10:27, Oleksij Rempel wrote:
> Oppss... wrong email address.
>
> Am 19.08.2014 um 10:25 schrieb Oleksij Rempel:
>> Am 18.08.2014 um 01:53 schrieb Csaba Kiraly:
>>> Based on a quick test with AR9271, TDLS seems to be working fine.
>>>
>>> Tests were done with 2 Atheros AR9271 based devices with firmware
>>> 1.3 (sha1 8d49f928aa40ac53c729189bff1333cd373a7fb5), associated
>>> with a WAP54G access point.
>>
>> please, don't use firmware 1.3. Use git source, or you can get
>> precompiled version here:
>> https://github.com/olerem/ath9k-htc-firmware-blob
I have just tried it with the latest firmware from git
(dc465e811c0272df7ec93b67de393129ff614173). Works fine.
>>
>>> TDLS worked fine both in WPA2 mode and
>>> without encryption. Stations maintained ping flood traffic between
>>> each other and towards the AP without significant losses.
>>>
>>> Not tested with AR7010.
>>
>> Seems ok for me. How can i reproduce testing environment?
Here it comes. I try to give a detailed description, although I suppose
you don't need most of it :)
I have used two laptops, two TP-Link TL-WN722N USB devices, and a
Linksys WAP54g AP.
# 0) stop conflicting services, clean up files
service network-manager stop
killall wpa_supplicant
killall dhclient
rm -rf /run/wpa_supplicant
# 1) on both nodes, start wpa_supplicant and connect to the same AP.
# Conf files attached
hostap/wpa_supplicant/wpa_supplicant -D nl80211 -i wlan2 -c wpa_supplicant_wap54g_WPA2.conf
# 2) on each node, configure IP addresses (or start dhclient)
ifconfig wlan2 $IP1
ifconfig wlan2 $IP2
# 3) start pinging the other node
ping $IP2
# 4) start pinging the AP
ping $IPAP
# 5) get MAC of node2's Atheros card
# get it on node2, or directly on node1 from the arp cache
arp -n
# 6) on node1, start wpa_cli
hostap/wpa_supplicant/wpa_cli -i wlan2
# 7) on node1, in wpa_cli, start the TDLS setup
tdls_setup <MAC2>
# 8) verify that TDLS works
# - ping time will reduce (in my case it went from 1.6 ms to 1 ms)
# - ping time to the AP should remain the same
# - node2's MAC will appear in ath9k_htc debugfs
ls /sys/kernel/debug/ieee80211/phy1/netdev:wlan2/stations
# - look inside the debugfs folder for more details
# 9) stress test
ping -f $IP2
# 10) disable encryption in the AP and repeat the same with the "open" config file
# pitfalls and notes
- APs could interfere in various ways with the test. Some models could
set the TDLS prohibit flag. Others (like my Huawei E587) could
work at the beginning but deauthenticate the nodes after 20-30 seconds.
- I didn't check 802.11n
- I have used the stock 3.16.0 kernel as the base, since
wireless-testing with tag master-2014-08-11 gave kernel panic
during wlan scan, even without my patch (but this is for another mail)
- use wpa_passphrase to generate the wpa_supplicant WPA2 config file
Csaba
>>
>>> TDLS was enabled in earlier patches the same way for other
>>> Atheros drivers:
>>> ath9k (fd6562344dea2b8b2a5d644cf971f4e56004500a),
>>> and carl9170 (d1f3de71a584a82ee4e84505fce9acccf40215ff).
>>>
>>> Signed-off-by: Csaba Kiraly <[email protected]>
>>> ---
>>> drivers/net/wireless/ath/ath9k/htc_drv_init.c | 2 ++
>>> 1 file changed, 2 insertions(+)
>>>
>>> diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
>>> index 8a3bd5f..d779f4f 100644
>>> --- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c
>>> +++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
>>> @@ -592,6 +592,8 @@ static void ath9k_set_hw_capab(struct ath9k_htc_priv *priv,
>>> hw->wiphy->flags |= WIPHY_FLAG_IBSS_RSN |
>>> WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL;
>>>
>>> + hw->wiphy->flags |= WIPHY_FLAG_SUPPORTS_TDLS;
>>> +
>>> hw->queues = 4;
>>> hw->max_listen_interval = 1;
>>>
>>>
>>
>>
>
>
Oppss... wrong email address.
Am 19.08.2014 um 10:25 schrieb Oleksij Rempel:
> Am 18.08.2014 um 01:53 schrieb Csaba Kiraly:
>> Based on a quick test with AR9271, TDLS seems to be working fine.
>>
>> Tests were done with 2 Atheros AR9271 based devices with firmware
>> 1.3 (sha1 8d49f928aa40ac53c729189bff1333cd373a7fb5), associated
>> with a WAP54G access point.
>
> please, don't use firmware 1.3. Use git source, or you can get
> precompiled version here:
> https://github.com/olerem/ath9k-htc-firmware-blob
>
>> TDLS worked fine both in WPA2 mode and
>> without encryption. Stations maintained ping flood traffic between
>> each other and towards the AP without significant losses.
>>
>> Not tested with AR7010.
>
> Seems ok for me. How can i reproduce testing environment?
>
>> TDLS was enabled in earlier patches the same way for other
>> Atheros drivers:
>> ath9k (fd6562344dea2b8b2a5d644cf971f4e56004500a),
>> and carl9170 (d1f3de71a584a82ee4e84505fce9acccf40215ff).
>>
>> Signed-off-by: Csaba Kiraly <[email protected]>
>> ---
>> drivers/net/wireless/ath/ath9k/htc_drv_init.c | 2 ++
>> 1 file changed, 2 insertions(+)
>>
>> diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
>> index 8a3bd5f..d779f4f 100644
>> --- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c
>> +++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
>> @@ -592,6 +592,8 @@ static void ath9k_set_hw_capab(struct ath9k_htc_priv *priv,
>> hw->wiphy->flags |= WIPHY_FLAG_IBSS_RSN |
>> WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL;
>>
>> + hw->wiphy->flags |= WIPHY_FLAG_SUPPORTS_TDLS;
>> +
>> hw->queues = 4;
>> hw->max_listen_interval = 1;
>>
>>
>
>
--
Regards,
Oleksij