From patchwork Wed Apr 18 00:27:57 2012 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: John X-Patchwork-Id: 153351 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming@ozlabs.org Delivered-To: patchwork-incoming@ozlabs.org Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 8C5C3B707D for ; Wed, 18 Apr 2012 10:37:56 +1000 (EST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753559Ab2DRAht (ORCPT ); Tue, 17 Apr 2012 20:37:49 -0400 Received: from smtp191.dfw.emailsrvr.com ([67.192.241.191]:33032 "EHLO smtp191.dfw.emailsrvr.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753399Ab2DRAho (ORCPT ); Tue, 17 Apr 2012 20:37:44 -0400 Received: from localhost (localhost.localdomain [127.0.0.1]) by smtp9.relay.dfw1a.emailsrvr.com (SMTP Server) with ESMTP id ED8943C036E for ; Tue, 17 Apr 2012 20:27:55 -0400 (EDT) X-Virus-Scanned: OK Received: by smtp9.relay.dfw1a.emailsrvr.com (Authenticated sender: john-AT-8192.net) with ESMTPSA id A0E0A3C0264 for ; Tue, 17 Apr 2012 20:27:55 -0400 (EDT) Message-ID: <4F8E0A8D.9080803@8192.net> Date: Tue, 17 Apr 2012 17:27:57 -0700 From: John User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:11.0) Gecko/20120327 Thunderbird/11.0.1 MIME-Version: 1.0 To: netdev@vger.kernel.org Subject: [PATCH V2 1/2] bonding support for IPv6 transmit hashing Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html --- a/drivers/net/bonding/bond_main.c 2012-03-18 16:15:34.000000000 -0700 +++ b/drivers/net/bonding/bond_main.c 2012-04-14 20:23:26.000000000 -0700 @@ -3352,56 +3352,87 @@ /*---------------------------- Hashing Policies -----------------------------*/ /* + * Hash for the output device based upon layer 2 data + */ +static int bond_xmit_hash_policy_l2(struct sk_buff *skb, int count) +{ + struct ethhdr *data = (struct ethhdr *)skb->data; + + if (skb_headlen(skb) >= 6) + return (data->h_dest[5] ^ data->h_source[5]) % count; + + return 0; +} + +/* * Hash for the output device based upon layer 2 and layer 3 data. If - * the packet is not IP mimic bond_xmit_hash_policy_l2() + * the packet is not IP, fall back on bond_xmit_hash_policy_l2() */ static int bond_xmit_hash_policy_l23(struct sk_buff *skb, int count) { struct ethhdr *data = (struct ethhdr *)skb->data; - struct iphdr *iph = ip_hdr(skb); - if (skb->protocol == htons(ETH_P_IP)) { + if (skb->protocol == htons(ETH_P_IP) && + skb_network_header_len(skb) >= sizeof(struct iphdr)) { + struct iphdr *iph = ip_hdr(skb); return ((ntohl(iph->saddr ^ iph->daddr) & 0xffff) ^ (data->h_dest[5] ^ data->h_source[5])) % count; + } else if (skb->protocol == htons(ETH_P_IPV6) && + skb_network_header_len(skb) >= sizeof(struct ipv6hdr)) { + struct ipv6hdr *ipv6h = ipv6_hdr(skb); + u32 v6hash = + (ipv6h->saddr.s6_addr32[1] ^ ipv6h->daddr.s6_addr32[1]) ^ + (ipv6h->saddr.s6_addr32[2] ^ ipv6h->daddr.s6_addr32[2]) ^ + (ipv6h->saddr.s6_addr32[3] ^ ipv6h->daddr.s6_addr32[3]); + v6hash = (v6hash >> 16) ^ (v6hash >> 8) ^ v6hash; + return (v6hash ^ data->h_dest[5] ^ data->h_source[5]) % count; } - return (data->h_dest[5] ^ data->h_source[5]) % count; + return bond_xmit_hash_policy_l2(skb, count); } /* * Hash for the output device based upon layer 3 and layer 4 data. If * the packet is a frag or not TCP or UDP, just use layer 3 data. If it is - * altogether not IP, mimic bond_xmit_hash_policy_l2() + * altogether not IP, fall back on bond_xmit_hash_policy_l2() */ static int bond_xmit_hash_policy_l34(struct sk_buff *skb, int count) { - struct ethhdr *data = (struct ethhdr *)skb->data; - struct iphdr *iph = ip_hdr(skb); - __be16 *layer4hdr = (__be16 *)((u32 *)iph + iph->ihl); - int layer4_xor = 0; + u32 layer4_xor = 0; if (skb->protocol == htons(ETH_P_IP)) { + struct iphdr *iph = ip_hdr(skb); if (!ip_is_fragment(iph) && - (iph->protocol == IPPROTO_TCP || - iph->protocol == IPPROTO_UDP)) { + (iph->protocol == IPPROTO_TCP || + iph->protocol == IPPROTO_UDP)) { + __be16 *layer4hdr = (__be16 *)((u32 *)iph + iph->ihl); + if (iph->ihl * sizeof(u32) + sizeof(__be16) * 2 > + skb_headlen(skb) - skb_network_offset(skb)) goto SHORT_HEADER; layer4_xor = ntohs((*layer4hdr ^ *(layer4hdr + 1))); + } else if (skb_network_header_len(skb) < sizeof(struct iphdr)) { + goto SHORT_HEADER; } return (layer4_xor ^ ((ntohl(iph->saddr ^ iph->daddr)) & 0xffff)) % count; - + } else if (skb->protocol == htons(ETH_P_IPV6)) { + struct ipv6hdr *ipv6h = ipv6_hdr(skb); + if (ipv6h->nexthdr == IPPROTO_TCP || ipv6h->nexthdr == IPPROTO_UDP) { + __be16 *layer4hdrv6 = (__be16 *)((u8 *)ipv6h + sizeof(struct ipv6hdr)); + if (sizeof(struct ipv6hdr) + sizeof(__be16) * 2 > + skb_headlen(skb) - skb_network_offset(skb)) goto SHORT_HEADER; + layer4_xor = (*layer4hdrv6 ^ *(layer4hdrv6 + 1)); + } else if (skb_network_header_len(skb) < sizeof(struct ipv6hdr)) { + goto SHORT_HEADER; + } + layer4_xor ^= + (ipv6h->saddr.s6_addr32[1] ^ ipv6h->daddr.s6_addr32[1]) ^ + (ipv6h->saddr.s6_addr32[2] ^ ipv6h->daddr.s6_addr32[2]) ^ + (ipv6h->saddr.s6_addr32[3] ^ ipv6h->daddr.s6_addr32[3]); + return ((layer4_xor >> 16) ^ (layer4_xor >> 8) ^ layer4_xor) % count; } - return (data->h_dest[5] ^ data->h_source[5]) % count; -} - -/* - * Hash for the output device based upon layer 2 data - */ -static int bond_xmit_hash_policy_l2(struct sk_buff *skb, int count) -{ - struct ethhdr *data = (struct ethhdr *)skb->data; - - return (data->h_dest[5] ^ data->h_source[5]) % count; + SHORT_HEADER: + return bond_xmit_hash_policy_l2(skb, count); } /*-------------------------- Device entry points ----------------------------*/