Re: 3.7.8/amd64 full interrupt hangs due to iwlwifi under big nfs copies out

[Johannes Berg <johannes@sipsolutions.net>]

On Wed, 2013-02-20 at 08:55 -0800, Eric Dumazet wrote:

> > > Unless wifi speed reaches 10Gbps, following patch should do the trick
> > > 
> > > 
> > > diff --git a/drivers/net/wireless/iwlwifi/dvm/rx.c b/drivers/net/wireless/iwlwifi/dvm/rx.c
> > > index a4eed20..77a3ee3 100644
> > > --- a/drivers/net/wireless/iwlwifi/dvm/rx.c
> > > +++ b/drivers/net/wireless/iwlwifi/dvm/rx.c
> > > @@ -750,7 +750,12 @@ static void iwlagn_pass_packet_to_mac80211(struct iwl_priv *priv,
> > >  	/* Dont use dev_alloc_skb(), we'll have enough headroom once
> > >  	 * ieee80211_hdr pulled.
> > >  	 */
> > > -	skb = alloc_skb(128, GFP_ATOMIC);
> > > +	fraglen = 128;
> > > +	/* if we use order-1 pages, copy to get better TCP performance */
> > > +	if (rxb->truesize > PAGE_SIZE)
> > > +		fraglen = max_t(unsigned, fraglen, len);
> > > +
> > > +	skb = alloc_skb(fraglen, GFP_ATOMIC);
> > 
> > Hmm, I don't quite understand -- that's not doing any copy?
> > 
> > FWIW if you do the copy you should not "steal" the pages, then they'd be
> > recycled in the RX ring right away.
> 
> Code should just works, please read the following lines in the same
> function....

FWIW, I think just using order-0 pages and turning 8k A-MSDUs off by
default makes more sense, A-MSDU is rarely used to begin with ...

Also, if we copy larger frames here, we should also take into account
the (variable) 802.11 header length to avoid copying into a position
where the IP header ends up being unaligned.

johannes