On Mon, Jun 03, 2024 at 10:19:27AM +0100, Donald Hunter wrote: > Simon Horman <horms@xxxxxxxxxx> writes: > > > On Tue, May 28, 2024 at 11:37:54AM +0100, Donald Hunter wrote: > >> Use consume_skb in the batch code path to avoid generating spurious > >> NOT_SPECIFIED skb drop reasons. > >> > >> Signed-off-by: Donald Hunter <donald.hunter@xxxxxxxxx> > > > > Hi Donald, > > > > I do wonder if this is the correct approach. I'm happy to stand corrected, > > but my understanding is that consume_skb() is for situations where the skb > > is no longer needed for reasons other than errors. But some of these > > call-sites do appear to be error paths of sorts. > > > > ... > > Hi Simon, > > They all look to be application layer errors which are either > communicated back to the client or cause a replay. My understanding is > that consume_skb() should be used here since kfree_skb() now implies a > (transport?) drop. Hi Donald, Thanks, that makes sense to me.
