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

Andrey Yurovsky andrey at cozybit.com
Wed Jun 3 15:09:05 EDT 2009

On Tue, Jun 2, 2009 at 10:47 PM, Mike Rapoport <mike at compulab.co.il> wrote:
> 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.

Thanks Mike.  In that case, it may be an issue with my SPI host
controller (on the Blackfin BF527 SoC) but I've at least been able to
confirm with dummy_writes=0 so that's a great start.  I'll probably be
able to work out the dummy_writes issue in the near future.

Sebastian -- would you like to go ahead and send the patch (rebased if
needed) to wireless-testing?  Please CC Dan Williams as well.  You can
add a "Tested-by: Andrey Yurovsky <andrey at cozybit.com>" (and one for
Mike as well, I suppose?).  I'll update the wireless Wiki about the
Chip Select and dummy_wires after the patch is merged.  Thanks!


>> Looks good to me otherwise, thanks!
>>   -Andrey
> --
> Sincerely yours,
> Mike.

More information about the libertas-dev mailing list