On Mon, Apr 04, 2016 at 09:26:55PM -0700, Alexander Duyck wrote: > > The problem is right now we are mangling the IP ID for outer headers > on tunnels. We end up totally ignoring the delta between the values > so if you have two flows that get interleaved over the same tunnel GRO > will currently mash the IP IDs for the two tunnels so that they end up > overlapping.
Then it should be fixed. I never reviewed those patches or I would have objected at the time. > The reason why I keep referencing RFC 6864 is because it specifies > that the IP ID field must not be read if the DF bit is set, and that > if we are manipulating headers we can handle the IP ID as though we > are the transmitting station. What this means is that if DF is not > set we have to have unique values per packet, otherwise we can ignore > the values if DF is set. As I said GRO itself should not be visible. The fact that it is for tunnels is a bug. > The question I would have is what are you really losing with increment > from 0 versus fixed 0? From what I see it is essentially just garbage > in/garbage out. GRO is meant to be lossless, that is, you should not be able to detect its presence from the outside. If you lose information then you're breaking this rule and people will soon start asking for it to be disabled in various situations. I'm not against doing this per se but it should not be part of the default configuration. Cheers, -- Email: Herbert Xu <herb...@gondor.apana.org.au> Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
