headers
Luis R. Rodriguez | 10 Jul 2009 20:02
Picon
Gravatar

Re: [PATCH] ath9k: Fix enabling OFDM weak signal detection

On Thu, Jul 9, 2009 at 2:12 PM, Steven Luo<steven <at> steven676.net> wrote:
> From: Steven Luo <steven <at> steven676.net>
>
> It seems that OFDM weak signal detection should be enabled after an ANI
> state reset, as indicated by the initial setting of ofdmWeakSigDetectOff
> and what the open Atheros HAL does.  Unfortunately, the reversed sense
> of ofdmWeakSigDetectOff (true if weak signal detection is NOT enabled)
> seems to have resulted in a mixup here, causing weak signal detection to
> be disabled.
>
> This patch significantly improves reception and throughput from distant
> stations for my AR5416-based AP running compat-wireless 2009-06-25.
>
> Signed-off-by: Steven Luo <steven <at> steven676.net>
> Cc: stable <at> kernel.org
> ---

NACK for now, please give us a chance to review this -- this may
actually be correct.

  Luis

> --- a/drivers/net/wireless/ath/ath9k/ani.c      2009-06-24 21:14:00.000000000 -0700
> +++ b/drivers/net/wireless/ath/ath9k/ani.c      2009-07-06 02:45:57.000000000 -0700
>  <at>  <at>  -482,7 +482,7  <at>  <at>  void ath9k_ani_reset(struct ath_hw *ah)
>                ath9k_hw_ani_control(ah, ATH9K_ANI_SPUR_IMMUNITY_LEVEL, 0);
>                ath9k_hw_ani_control(ah, ATH9K_ANI_FIRSTEP_LEVEL, 0);
>                ath9k_hw_ani_control(ah, ATH9K_ANI_OFDM_WEAK_SIGNAL_DETECTION,
> -                                    !ATH9K_ANI_USE_OFDM_WEAK_SIG);
> +                                    ATH9K_ANI_USE_OFDM_WEAK_SIG);
(Continue reading)

Permalink | Reply |
headers
Luis R. Rodriguez | 14 Jul 2009 20:03
Favicon

Re: [ath9k-devel] [PATCH] ath9k: Fix enabling OFDM weak signal detection

On Fri, Jul 10, 2009 at 11:02:58AM -0700, Luis R. Rodriguez wrote:
> On Thu, Jul 9, 2009 at 2:12 PM, Steven Luo<steven@...> wrote:
> > From: Steven Luo <steven@...>
> >
> > It seems that OFDM weak signal detection should be enabled after an ANI
> > state reset, as indicated by the initial setting of ofdmWeakSigDetectOff
> > and what the open Atheros HAL does.  Unfortunately, the reversed sense
> > of ofdmWeakSigDetectOff (true if weak signal detection is NOT enabled)
> > seems to have resulted in a mixup here, causing weak signal detection to
> > be disabled.
> >
> > This patch significantly improves reception and throughput from distant
> > stations for my AR5416-based AP running compat-wireless 2009-06-25.
> >
> > Signed-off-by: Steven Luo <steven@...>
> > Cc: stable@...
> > ---
> 
> NACK for now, please give us a chance to review this -- this may
> actually be correct.

Please try this patch instead, I've only compile tested this.

From: Luis R. Rodriguez <lrodriguez@...>
Subject: [PATCH] ath9k: Tune ANI function processing on AP mode during ANI reset

For AP mode we must tune ANI specially for 2 GHz and
for 5 GHz. We mask in only the flags we want to toggle
on ath9k_hw_ani_control() through the ah->ani_function
bitmask, this will take care of ignoring changes during
(Continue reading)

Permalink | Reply |
headers
Luis R. Rodriguez | 14 Jul 2009 20:11
Favicon

Re: [ath9k-devel] [PATCH] ath9k: Fix enabling OFDM weak signal detection

On Tue, Jul 14, 2009 at 11:03:48AM -0700, Luis Rodriguez wrote:
> On Fri, Jul 10, 2009 at 11:02:58AM -0700, Luis R. Rodriguez wrote:
> > On Thu, Jul 9, 2009 at 2:12 PM, Steven Luo<steven@...> wrote:
> > > From: Steven Luo <steven@...>
> > >
> > > It seems that OFDM weak signal detection should be enabled after an ANI
> > > state reset, as indicated by the initial setting of ofdmWeakSigDetectOff
> > > and what the open Atheros HAL does.  Unfortunately, the reversed sense
> > > of ofdmWeakSigDetectOff (true if weak signal detection is NOT enabled)
> > > seems to have resulted in a mixup here, causing weak signal detection to
> > > be disabled.
> > >
> > > This patch significantly improves reception and throughput from distant
> > > stations for my AR5416-based AP running compat-wireless 2009-06-25.
> > >
> > > Signed-off-by: Steven Luo <steven@...>
> > > Cc: stable@...
> > > ---
> >
> > NACK for now, please give us a chance to review this -- this may
> > actually be correct.
> 
> Please try this patch instead, I've only compile tested this.

Now without the double AP check :)

From: Luis R. Rodriguez <lrodriguez@...>
Subject: [PATCH] ath9k: Tune ANI function processing on AP mode during ANI reset

For AP mode we must tune ANI specially for 2 GHz and
(Continue reading)

Permalink | Reply |
headers
Steven Luo | 15 Jul 2009 06:04

Re: [ath9k-devel] [PATCH] ath9k: Fix enabling OFDM weak signal detection

On Tue, Jul 14, 2009 at 11:11:48AM -0700, Luis R. Rodriguez wrote:
> On Tue, Jul 14, 2009 at 11:03:48AM -0700, Luis Rodriguez wrote:
> > Please try this patch instead, I've only compile tested this.

Yeah, this works too.  Thanks!

-Steven Luo

> Now without the double AP check :)
> 
> From: Luis R. Rodriguez <lrodriguez@...>
> Subject: [PATCH] ath9k: Tune ANI function processing on AP mode during ANI reset
> 
> For AP mode we must tune ANI specially for 2 GHz and
> for 5 GHz. We mask in only the flags we want to toggle
> on ath9k_hw_ani_control() through the ah->ani_function
> bitmask, this will take care of ignoring changes during
> ANI reset which we were disabling before.
> 
> Reported-by: Steven Luo <steven@...>
> Cc: Bennyam Malavazi <Bennyam.Malavazi@...
> Cc: Jouni Malinen <Jouni.Malinen@...>
> Signed-off-by: Luis R. Rodriguez <lrodriguez@...>
> ---
>  drivers/net/wireless/ath/ath9k/ani.c |   12 ++++++++++++
>  1 files changed, 12 insertions(+), 0 deletions(-)
> 
> diff --git a/drivers/net/wireless/ath/ath9k/ani.c b/drivers/net/wireless/ath/ath9k/ani.c
> --- a/drivers/net/wireless/ath/ath9k/ani.c
> +++ b/drivers/net/wireless/ath/ath9k/ani.c
(Continue reading)

Permalink | Reply |
headers
Nick Kossifidis | 11 Jul 2009 17:23
Picon

Re: [ath9k-devel] [PATCH] ath9k: Fix enabling OFDM weak signal detection

2009/7/10 Luis R. Rodriguez <mcgrof@...>:
> On Thu, Jul 9, 2009 at 2:12 PM, Steven Luo<steven@...> wrote:
>> From: Steven Luo <steven@...>
>>
>> It seems that OFDM weak signal detection should be enabled after an ANI
>> state reset, as indicated by the initial setting of ofdmWeakSigDetectOff
>> and what the open Atheros HAL does.  Unfortunately, the reversed sense
>> of ofdmWeakSigDetectOff (true if weak signal detection is NOT enabled)
>> seems to have resulted in a mixup here, causing weak signal detection to
>> be disabled.
>>
>> This patch significantly improves reception and throughput from distant
>> stations for my AR5416-based AP running compat-wireless 2009-06-25.
>>
>> Signed-off-by: Steven Luo <steven@...>
>> Cc: stable@...
>> ---
>
> NACK for now, please give us a chance to review this -- this may
> actually be correct.
>
>  Luis
>
>> --- a/drivers/net/wireless/ath/ath9k/ani.c      2009-06-24 21:14:00.000000000 -0700
>> +++ b/drivers/net/wireless/ath/ath9k/ani.c      2009-07-06 02:45:57.000000000 -0700
>>  <at>  <at>  -482,7 +482,7  <at>  <at>  void ath9k_ani_reset(struct ath_hw *ah)
>>                ath9k_hw_ani_control(ah, ATH9K_ANI_SPUR_IMMUNITY_LEVEL, 0);
>>                ath9k_hw_ani_control(ah, ATH9K_ANI_FIRSTEP_LEVEL, 0);
>>                ath9k_hw_ani_control(ah, ATH9K_ANI_OFDM_WEAK_SIGNAL_DETECTION,
>> -                                    !ATH9K_ANI_USE_OFDM_WEAK_SIG);
(Continue reading)

Permalink | Reply |
headers
Luis R. Rodriguez | 10 Jul 2009 20:08
Picon
Gravatar

Re: [PATCH] ath9k: Fix enabling OFDM weak signal detection

On Fri, Jul 10, 2009 at 11:02 AM, Luis R. Rodriguez<mcgrof <at> gmail.com> wrote:
> On Thu, Jul 9, 2009 at 2:12 PM, Steven Luo<steven <at> steven676.net> wrote:
>> From: Steven Luo <steven <at> steven676.net>
>>
>> It seems that OFDM weak signal detection should be enabled after an ANI
>> state reset, as indicated by the initial setting of ofdmWeakSigDetectOff
>> and what the open Atheros HAL does.  Unfortunately, the reversed sense
>> of ofdmWeakSigDetectOff (true if weak signal detection is NOT enabled)
>> seems to have resulted in a mixup here, causing weak signal detection to
>> be disabled.
>>
>> This patch significantly improves reception and throughput from distant
>> stations for my AR5416-based AP running compat-wireless 2009-06-25.
>>
>> Signed-off-by: Steven Luo <steven <at> steven676.net>
>> Cc: stable <at> kernel.org
>> ---
>
> NACK for now, please give us a chance to review this -- this may
> actually be correct.

Benny, Jouni indicated this matches current Fusion, know Fusion
correct? Do we know if AR5416 should have OFDM weak signal detection
enabled after an ANI state reset? It seemed to help this particular
user. Or do we know for sure it should be disabled for all 11n cards?

Since this may come up for legacy cards, how about for that case?

  Luis
(Continue reading)

Permalink | Reply |

Gmane