Hello! > Is there any nicer way to expand the tail that can avoid copies? No. > Or better is any way (planned in future kernel relases) that can allow a > netdevice to specify to the upper layers that it wants to reserve some > tailroom, similar to hard_header_len? No. Until now no examples are known when this is even useful. If you have one, which could justify abuse for main stream, please, give some details. It is really interesting. Alexey - : send the line "unsubscribe linux-net" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
