Re: [PATCH 2/3] ath9k: Fix power save count imbalance on ath_radio_enable()

["Luis R. Rodriguez" <lrodriguez@atheros.com>]

On Tue, Dec 07, 2010 at 01:01:30PM -0800, John W. Linville wrote:
> On Fri, Dec 03, 2010 at 05:34:08PM -0800, Luis R. Rodriguez wrote:
> > On Fri, Dec 3, 2010 at 5:20 PM, Luis R. Rodriguez
> > <lrodriguez@atheros.com> wrote:
> > > Upon a failure we never call ath9k_ps_restore() on ath_radio_enable(),
> > > this will throw off the sc->ps_usecount. When the sc->ps_usecount
> > > is > 0 we never put the chip to full sleep. This drains battery,
> > > and will also make the chip fail upon resume with:
> > >
> > > ath: Starting driver with initial channel: 5745 MHz
> > > ath: timeout (100000 us) on reg 0x7000: 0xdeadbeef & 0x00000003 != 0x00000000
> > >
> > > This would make the chip useless upon resume.
> > >
> > > I cannot prove this can happen but in theory it is so best to
> > > avoid this race completely and not have users complain about
> > > a broken device after resume.
> > >
> > > Cc: stable@kernel.org
> > > Cc: Paul Stewart <pstew@google.com>
> > > Cc: Amod Bodas <amod.bodas@atheros.com>
> > > Signed-off-by: Luis R. Rodriguez <lrodriguez@atheros.com>
> > 
> > John, this one is for you, sorry I failed to send it to you. And
> > Johannes, sorry, I forgot to remove you from my send script :)
> 
> So, this is for 2.6.37?

Yes.

> FWIW, it was the only PATCH in a series of RFCs...

Thanks, yes, I noted this on my PATCH 0 cover letter. If you want
you can disrecard this though and just consider the PATCH I posted
in my new series. Its in that series as well, but let me just iron
out that series first, please ignore that series as well for now.

  Luis