From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jay Vosburgh Subject: [PATCH 7/8] bonding: Add new layer2+3 hash for xor/802.3ad modes Date: Thu, 6 Dec 2007 23:40:34 -0800 Message-ID: <1197013239283-git-send-email-fubar@us.ibm.com> References: <11970132353950-git-send-email-fubar@us.ibm.com> <11970132363756-git-send-email-fubar@us.ibm.com> <11970132372293-git-send-email-fubar@us.ibm.com> <1197013237259-git-send-email-fubar@us.ibm.com> <11970132382296-git-send-email-fubar@us.ibm.com> <11970132381345-git-send-email-fubar@us.ibm.com> <11970132394126-git-send-email-fubar@us.ibm.com> Cc: jgarzik@pobox.com, "Glenn Griffin" , Jay Vosburgh To: netdev@vger.kernel.org Return-path: Received: from e36.co.us.ibm.com ([32.97.110.154]:43189 "EHLO e36.co.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751890AbXLGHkr (ORCPT ); Fri, 7 Dec 2007 02:40:47 -0500 Received: from d03relay02.boulder.ibm.com (d03relay02.boulder.ibm.com [9.17.195.227]) by e36.co.us.ibm.com (8.13.8/8.13.8) with ESMTP id lB77efv5000960 for ; Fri, 7 Dec 2007 02:40:41 -0500 Received: from d03av01.boulder.ibm.com (d03av01.boulder.ibm.com [9.17.195.167]) by d03relay02.boulder.ibm.com (8.13.8/8.13.8/NCO v8.7) with ESMTP id lB77efAc120800 for ; Fri, 7 Dec 2007 00:40:41 -0700 Received: from d03av01.boulder.ibm.com (loopback [127.0.0.1]) by d03av01.boulder.ibm.com (8.12.11.20060308/8.13.3) with ESMTP id lB77eePf018160 for ; Fri, 7 Dec 2007 00:40:40 -0700 In-Reply-To: <11970132394126-git-send-email-fubar@us.ibm.com> Sender: netdev-owner@vger.kernel.org List-ID: Add new hash for balance-xor and 802.3ad modes. Originally submitted by "Glenn Griffin" ; modified by Jay Vosburgh to move setting of hash policy out of line, tweak the documentation update and add version update to 3.2.2. Glenn's original comment follows: Included is a patch for a new xmit_hash_policy for the bonding driver that selects slaves based on MAC and IP information. This is a middle ground between what currently exists in the layer2 only policy and the layer3+4 policy. This policy strives to be fully 802.3ad compliant by transmitting every packet of any particular flow over the same link. As documented the layer3+4 policy is not fully compliant for extreme cases such as ip fragmentation, so this policy is a nice compromise for environments that require full compliance but desire more than the layer2 only policy. Signed-off-by: "Glenn Griffin" Signed-off-by: Jay Vosburgh --- Documentation/networking/bonding.txt | 29 +++++++++++++++++++- drivers/net/bonding/bond_main.c | 48 ++++++++++++++++++++++++++------- drivers/net/bonding/bonding.h | 4 +- include/linux/if_bonding.h | 3 +- 4 files changed, 69 insertions(+), 15 deletions(-) diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index eda0f06..a0cda06 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -559,6 +559,30 @@ xmit_hash_policy This algorithm is 802.3ad compliant. + layer2+3 + + This policy uses a combination of layer2 and layer3 + protocol information to generate the hash. + + Uses XOR of hardware MAC addresses and IP addresses to + generate the hash. The formula is + + (((source IP XOR dest IP) AND 0xffff) XOR + ( source MAC XOR destination MAC )) + modulo slave count + + This algorithm will place all traffic to a particular + network peer on the same slave. For non-IP traffic, + the formula is the same as for the layer2 transmit + hash policy. + + This policy is intended to provide a more balanced + distribution of traffic than layer2 alone, especially + in environments where a layer3 gateway device is + required to reach most destinations. + + This algorithm is 802.3ad complient. + layer3+4 This policy uses upper layer protocol information, @@ -594,8 +618,9 @@ xmit_hash_policy or may not tolerate this noncompliance. The default value is layer2. This option was added in bonding -version 2.6.3. In earlier versions of bonding, this parameter does -not exist, and the layer2 policy is the only policy. + version 2.6.3. In earlier versions of bonding, this parameter + does not exist, and the layer2 policy is the only policy. The + layer2+3 value was added for bonding version 3.2.2. 3. Configuring Bonding Devices diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index e4a4714..08879d5 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -175,6 +175,7 @@ struct bond_parm_tbl bond_mode_tbl[] = { struct bond_parm_tbl xmit_hashtype_tbl[] = { { "layer2", BOND_XMIT_POLICY_LAYER2}, { "layer3+4", BOND_XMIT_POLICY_LAYER34}, +{ "layer2+3", BOND_XMIT_POLICY_LAYER23}, { NULL, -1}, }; @@ -3605,6 +3606,24 @@ void bond_unregister_arp(struct bonding *bond) /*---------------------------- Hashing Policies -----------------------------*/ /* + * 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() + */ +static int bond_xmit_hash_policy_l23(struct sk_buff *skb, + struct net_device *bond_dev, int count) +{ + struct ethhdr *data = (struct ethhdr *)skb->data; + struct iphdr *iph = ip_hdr(skb); + + if (skb->protocol == __constant_htons(ETH_P_IP)) { + return ((ntohl(iph->saddr ^ iph->daddr) & 0xffff) ^ + (data->h_dest[5] ^ bond_dev->dev_addr[5])) % count; + } + + return (data->h_dest[5] ^ bond_dev->dev_addr[5]) % 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() @@ -4306,6 +4325,22 @@ out: /*------------------------- Device initialization ---------------------------*/ +static void bond_set_xmit_hash_policy(struct bonding *bond) +{ + switch (bond->params.xmit_policy) { + case BOND_XMIT_POLICY_LAYER23: + bond->xmit_hash_policy = bond_xmit_hash_policy_l23; + break; + case BOND_XMIT_POLICY_LAYER34: + bond->xmit_hash_policy = bond_xmit_hash_policy_l34; + break; + case BOND_XMIT_POLICY_LAYER2: + default: + bond->xmit_hash_policy = bond_xmit_hash_policy_l2; + break; + } +} + /* * set bond mode specific net device operations */ @@ -4322,10 +4357,7 @@ void bond_set_mode_ops(struct bonding *bond, int mode) break; case BOND_MODE_XOR: bond_dev->hard_start_xmit = bond_xmit_xor; - if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34) - bond->xmit_hash_policy = bond_xmit_hash_policy_l34; - else - bond->xmit_hash_policy = bond_xmit_hash_policy_l2; + bond_set_xmit_hash_policy(bond); break; case BOND_MODE_BROADCAST: bond_dev->hard_start_xmit = bond_xmit_broadcast; @@ -4333,10 +4365,7 @@ void bond_set_mode_ops(struct bonding *bond, int mode) case BOND_MODE_8023AD: bond_set_master_3ad_flags(bond); bond_dev->hard_start_xmit = bond_3ad_xmit_xor; - if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34) - bond->xmit_hash_policy = bond_xmit_hash_policy_l34; - else - bond->xmit_hash_policy = bond_xmit_hash_policy_l2; + bond_set_xmit_hash_policy(bond); break; case BOND_MODE_ALB: bond_set_master_alb_flags(bond); @@ -4498,8 +4527,7 @@ int bond_parse_parm(char *mode_arg, struct bond_parm_tbl *tbl) for (i = 0; tbl[i].modename; i++) { if ((isdigit(*mode_arg) && tbl[i].mode == simple_strtol(mode_arg, NULL, 0)) || - (strncmp(mode_arg, tbl[i].modename, - strlen(tbl[i].modename)) == 0)) { + (strcmp(mode_arg, tbl[i].modename) == 0)) { return tbl[i].mode; } } diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index 61c1b45..ccafc74 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -22,8 +22,8 @@ #include "bond_3ad.h" #include "bond_alb.h" -#define DRV_VERSION "3.2.1" -#define DRV_RELDATE "October 15, 2007" +#define DRV_VERSION "3.2.2" +#define DRV_RELDATE "December 6, 2007" #define DRV_NAME "bonding" #define DRV_DESCRIPTION "Ethernet Channel Bonding Driver" diff --git a/include/linux/if_bonding.h b/include/linux/if_bonding.h index 84598fa..65c2d24 100644 --- a/include/linux/if_bonding.h +++ b/include/linux/if_bonding.h @@ -85,7 +85,8 @@ /* hashing types */ #define BOND_XMIT_POLICY_LAYER2 0 /* layer 2 (MAC only), default */ -#define BOND_XMIT_POLICY_LAYER34 1 /* layer 3+4 (IP ^ MAC) */ +#define BOND_XMIT_POLICY_LAYER34 1 /* layer 3+4 (IP ^ (TCP || UDP)) */ +#define BOND_XMIT_POLICY_LAYER23 2 /* layer 2+3 (IP ^ MAC) */ typedef struct ifbond { __s32 bond_mode; -- 1.5.3.4.206.g58ba4-dirty