Jan-Bernd Themann wrote: > This patch provides a functionality that allows parallel > RX processing on multiple RX queues by using dummy netdevices. > > > +static inline int ehea_hash_skb(struct sk_buff *skb, int num_qps) > +{ > + u32 tmp; > + if ((skb->nh.iph->protocol == IPPROTO_TCP) > + && skb->protocol == ETH_P_IP) {
skb->protocol has network byte order. The ETH_P_IP test should also logically come before checking the IP protocol. > + tmp = (skb->h.th->source + (skb->h.th->dest << 16)) % 31; Only locally generated packets have a valid h.th pointer. > + tmp += skb->nh.iph->daddr % 31; > + return tmp % num_qps; > + } > + else > + return 0; > +} > + > static int ehea_start_xmit(struct sk_buff *skb, struct net_device *dev) > { > struct ehea_port *port = netdev_priv(dev); > @@ -1796,9 +1818,18 @@ static int ehea_start_xmit(struct sk_buf > unsigned long flags; > u32 lkey; > int swqe_index; > - struct ehea_port_res *pr = &port->port_res[0]; > + struct ehea_port_res *pr; > + > + pr = &port->port_res[ehea_hash_skb(skb, port->num_tx_qps)]; > + - To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html