[PATCH upstream for stable 2/8] staging: vt6656: 64 bit- Correctly address void structure.

[Malcolm Priestley]

On Fri, 2012-12-28 at 00:52 +0100, Ben Hutchings wrote:
> On Thu, 2012-12-27 at 22:47 +0000, Malcolm Priestley wrote:
> > On Thu, 2012-12-27 at 20:09 +0100, Ben Hutchings wrote:
> > > On Thu, 2012-12-27 at 13:01 +0000, Malcolm Priestley wrote:
> > > > upstream 
> > > > commit e2efba763b472835fdface597fe2216b3403967e
> > > > 
> > > > Tested on kernels 2.6.35, 3.0, 3.2, 3.5 & 3.7
> > > > 
> > > > staging: vt6656: 64 bit- Correctly address void structure.
> > > >     
> > > > Fixes 64 bit deadlock on successful association.
> > > > 
> > > > Cc: stable at kernel.org  # 2.6.35+
> > > > Signed-off-by: Malcolm Priestley <tvboxspy at gmail.com>
> > > > Signed-off-by: Greg Kroah-Hartman <gregkh at linuxfoundation.org>
> > > > 
> > > > diff --git a/drivers/staging/vt6656/rxtx.c b/drivers/staging/vt6656/rxtx.c
> > > > index 0f35a9a..1f87213 100644
> > > > --- a/drivers/staging/vt6656/rxtx.c
> > > > +++ b/drivers/staging/vt6656/rxtx.c
> > > > @@ -1452,12 +1452,10 @@ s_bPacketToWirelessUsb(
> > > >  
> > > 
> > Hi Ben,
> > 
> > Ah, you are correct.
> > 
> > However, as it stands, reverting upstream on 64 bit will cause
> > a regression.
> 
> I don't understand why you think this has something to do with '64 bit'.
> 
> > I haven't found any regressions on 32bit and it is only a
> > condition check. Only WEP 256 users affected and the chances
> > of the address hitting TRUE(1) during WEP/WPA negotiation.
> > 
> > I would prefer to submit a patch to correct upstream.
> 
> It's not my decision, anyway.  But if this is reverted first then we can
> cherry-pick just the real fix for stable.
> 

Hmm, something has already fix it upstream on the driver.

So, both upstream commits

e2efba763b472835fdface597fe2216b3403967e
and
eb304bddc47b59927b650d43c3f35b9266c807a9

need to be reversed.

I will try and find out what fixed it.

Regards


Malcolm
> Ben.
>