[RFC/PATCH] net/libertas: remove GPIO-CS handling in SPI interface code

[Mike Rapoport]

Andrey Yurovsky wrote:
> On Mon, Jun 1, 2009 at 12:41 PM, Sebastian Andrzej Siewior
> <bigeasy at linutronix.de> wrote:
>> * Mike Rapoport | 2009-05-31 10:58:09 [+0300]:
>>
>>> Sebastian Andrzej Siewior wrote:
>>>> This removes the dependency on GPIO framework and lets the SPI host
>>>> driver handle the chip select. The SPI host driver is required to keep
>>>> the CS active for the entire message unless cs_change says otherwise.
>>>> This patch collects the two/three single SPI transfers into a message.
>>>> Also the delay in read path in case use_dummy_writes are not used is
>>>> moved into the SPI host driver.
>>>>
>>>> Signed-off-by: Sebastian Andrzej Siewior <bigeasy at linutronix.de>
>>> For PXA270 platform
>>> Tested-by: Mike Rapoport <mike at compulab.co.il>
>> That's good to hear. Thanks for that.
>> Once Andrey is happy with that I would Cc: wireless if there are no
>> objections.
> 
> It's working for me with dummy_writes disabled (that is, we use a
> fixed delay when reading) but it's not working with dummy_writes
> enabled (we clock dummy bytes when reading).
> 
> Mike and Sebastian -- have you tested with both dummy_writes enabled
> and disabled?  If not, which option did you choose?  Ideally, we will
> have both working or, if we get rid of one, it should be
> dummy_writes=0 (I'd prefer that we clock in dummy bytes rather than
> specifying a fixed delay).

I've tested with both dummy_writes enabled and disabled. Seems to be Ok in both
cases.

> Looks good to me otherwise, thanks!
> 
>   -Andrey
> 

-- 
Sincerely yours,
Mike.