Re: pci_set_mwi() and ath5k

["Luis R. Rodriguez" <mcgrof@gmail.com>]

On Wed, Nov 4, 2009 at 1:36 PM, Luis R. Rodriguez <mcgrof@gmail.com> wrote:
> On Wed, Nov 4, 2009 at 1:30 PM, Luis R. Rodriguez <mcgrof@gmail.com> wrote:
>> On Wed, Nov 4, 2009 at 12:12 PM, Nick Kossifidis <mickflemm@gmail.com> wrote:
>>> 2009/11/4 Luis R. Rodriguez <mcgrof@gmail.com>:
>>>> Curious if anyone recalls the issues seen with enabling MWI on ath5k.
>>>> I could have sworn there was some discussion on this but for the life
>>>> of me I cannot find it.
>>>>
>>>>  Luis
>>>
>>> Maybe this one ?
>>> http://osdir.com/ml/linux.drivers.ath5k.devel/2008-07/msg00088.html
>>
>> That was it, thanks! For the record then Kyle pointed to this bug:
>>
>> http://marc.info/?t=121430463700001&r=1&w=2
>>
>> as a reference for possible issues.
>
> Actually the threads above are for MSI, not MWI, which would be set
> with pci_set_mwi() not pci_disable_msi().
>
> MWI is for enabling memory write invalidate.
>
> I guess we never had the MWI discussion then for ath5k,
>
> Either way I'm reluctant to enable it and was actually considering
> simplifying the the PCI cache line size thing on ath/ath5k/ath9k. Will
> send an RFC.

Even better: I just confirmation from our systems team that our legacy
devices and 11n PCI devices don't support MWR so I'll remove all that
cruft crap.

  Luis