Re: [PATCH 5.4 086/129] net: core: use listified Rx for GRO_NORMAL in napi_gro_receive()

From: Greg Kroah-Hartman
Date: Wed Sep 09 2020 - 02:37:13 EST


On Tue, Sep 08, 2020 at 10:35:22PM +0100, Edward Cree wrote:
> On 08/09/2020 16:25, Greg Kroah-Hartman wrote:
> > From: Alexander Lobakin <alobakin@xxxxxxxx>
> >
> > commit 6570bc79c0dfff0f228b7afd2de720fb4e84d61d upstream.
> >
> > Commit 323ebb61e32b4 ("net: use listified RX for handling GRO_NORMAL
> > skbs") made use of listified skb processing for the users of
> > napi_gro_frags().
> > The same technique can be used in a way more common napi_gro_receive()
> > to speed up non-merged (GRO_NORMAL) skbs for a wide range of drivers
> > including gro_cells and mac80211 users.
> > This slightly changes the return value in cases where skb is being
> > dropped by the core stack, but it seems to have no impact on related
> > drivers' functionality.
> > gro_normal_batch is left untouched as it's very individual for every
> > single system configuration and might be tuned in manual order to
> > achieve an optimal performance.
> >
> > Signed-off-by: Alexander Lobakin <alobakin@xxxxxxxx>
> > Acked-by: Edward Cree <ecree@xxxxxxxxxxxxxx>
> > Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
> > Signed-off-by: Hyunsoon Kim <h10.kim@xxxxxxxxxxx>
> > Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
> I'm not quite sure why this is stable material(it's a performance
>  enhancement, rather than a fix).  But if you do want to take it,
>  make sure you've also got
> c80794323e82 ("net: Fix packet reordering caused by GRO and listified RX cooperation")
> b167191e2a85 ("net: wireless: intel: iwlwifi: fix GRO_NORMAL packet stalling")
>  in your tree, particularly the latter as without it this commit
>  triggers a severe regression in iwlwifi.

Hm, that feels bad, I'll go drop this for now.

Hyunsoon was the one who asked for this, so I will let them defend the
request. I thought they were asking for this because it was a bug fix,
but if it is a performance issue, that's fine as long as it doesn't also
cause problems :)

Hyunsoon, should all of these be taken, and if so, what exactly is the
performance increase here?

thanks,

greg k-h