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

[Andrey Yurovsky]

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).

Looks good to me otherwise, thanks!

  -Andrey