| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Tue, 21 Aug 2012 12:19:55 -0700
From: Jay Vosburgh <fubar@...ibm.com>
To: Jeremy Brookman <jeremy.brookman@...il.com>
cc: linux@...2.net, netdev@...r.kernel.org
Subject: Re: [PATCH v6] bonding support for IPv6 transmit hashing
Jeremy Brookman <jeremy.brookman@...il.com> wrote:
>> You should use a mix of tabs, as necessary, to get things to line up
>> how I told you they need to line up.
>
>Unless I'm missing something, this change doesn't seem to have made it
>through to the kernel tip, but we could really use this bugfix. Is it
>in a repository I didn't notice, or not yet through the review? If
>it's not through the review, is any help needed to get it there?
The submitter (John Eaglesham) never posted an updated version
that addressed the various comments, nor did his original patch
submission include a Signed-off-by.
I went ahead and updated the patch to address the comments; I've
only compile tested this. Are you (Jeremy or John) able to test this to
confirm that it will hash ipv6 traffic as expected (I can test it, but
it won't be today)?
John, can you post a Signed-off-by for your patch (really, this
updated version of your patch)?
If John signs off and somebody tests this, I'll post a formal
submssion with the full commit message.
-J
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index 6b1c711..834c919 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -752,12 +752,23 @@ xmit_hash_policy
protocol information to generate the hash.
Uses XOR of hardware MAC addresses and IP addresses to
- generate the hash. The formula is
+ generate the hash. The IPv4 formula is
(((source IP XOR dest IP) AND 0xffff) XOR
( source MAC XOR destination MAC ))
modulo slave count
+ The IPv6 formula is
+
+ hash =
+ (source ip quad 2 XOR dest IP quad 2) XOR
+ (source ip quad 3 XOR dest IP quad 3) XOR
+ (source ip quad 4 XOR dest IP quad 4)
+
+ (((hash >> 24) XOR (hash >> 16) XOR (hash >> 8) XOR hash)
+ 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
@@ -778,19 +789,30 @@ xmit_hash_policy
slaves, although a single connection will not span
multiple slaves.
- The formula for unfragmented TCP and UDP packets is
+ The formula for unfragmented IPv4 TCP and UDP packets is
((source port XOR dest port) XOR
((source IP XOR dest IP) AND 0xffff)
modulo slave count
- For fragmented TCP or UDP packets and all other IP
- protocol traffic, the source and destination port
+ The formula for unfragmented IPv6 TCP and UDP packets is
+
+ hash =
+ (source ip quad 2 XOR dest IP quad 2) XOR
+ (source ip quad 3 XOR dest IP quad 3) XOR
+ (source ip quad 4 XOR dest IP quad 4)
+
+ ((source port XOR dest port) XOR
+ (hash >> 24) XOR (hash >> 16) XOR (hash >> 8) XOR hash)
+ modulo slave count
+
+ For fragmented TCP or UDP packets and all other IPv4 and
+ IPv6 protocol traffic, the source and destination port
information is omitted. For non-IP traffic, the
formula is the same as for the layer2 transmit hash
policy.
- This policy is intended to mimic the behavior of
+ The IPv4 policy is intended to mimic the behavior of
certain switches, notably Cisco switches with PFC2 as
well as some Foundry and IBM products.
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index d95fbc3..4dfe7e3 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3354,56 +3354,99 @@ static struct notifier_block bond_netdev_notifier = {
/*---------------------------- 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) >= offsetof(struct ethhdr, h_proto))
+ 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)) {
+ struct iphdr *iph;
+ struct ipv6hdr *ipv6h;
+ u32 v6hash;
+ __be32 *s, *d;
+
+ if (skb->protocol == htons(ETH_P_IP) &&
+ skb_network_header_len(skb) >= sizeof(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)) {
+ ipv6h = ipv6_hdr(skb);
+ s = &ipv6h->saddr.s6_addr32[0];
+ d = &ipv6h->daddr.s6_addr32[0];
+ v6hash = (s[1] ^ d[1]) ^ (s[2] ^ d[2]) ^ (s[3] ^ d[3]);
+ v6hash ^= (v6hash >> 24) ^ (v6hash >> 16) ^ (v6hash >> 8);
+ 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;
+ struct iphdr *iph;
+ struct ipv6hdr *ipv6h;
+ __be32 *s, *d;
+ __be16 *layer4hdr;
if (skb->protocol == htons(ETH_P_IP)) {
+ iph = ip_hdr(skb);
if (!ip_is_fragment(iph) &&
(iph->protocol == IPPROTO_TCP ||
iph->protocol == IPPROTO_UDP)) {
+ if (iph->ihl * sizeof(u32) + sizeof(__be16) * 2 >
+ skb_headlen(skb) - skb_network_offset(skb))
+ goto short_header;
+ layer4hdr = (__be16 *)((u32 *)iph + iph->ihl);
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)) {
+ ipv6h = ipv6_hdr(skb);
+ if (ipv6h->nexthdr == IPPROTO_TCP ||
+ ipv6h->nexthdr == IPPROTO_UDP) {
+ layer4hdr = (__be16 *)(ipv6h + 1);
+ if (sizeof(struct ipv6hdr) + sizeof(__be16) * 2 >
+ skb_headlen(skb) - skb_network_offset(skb))
+ goto short_header;
+ layer4_xor = (*layer4hdr ^ *(layer4hdr + 1));
+ } else if (skb_network_header_len(skb) <
+ sizeof(struct ipv6hdr)) {
+ goto short_header;
+ }
+ s = &ipv6h->saddr.s6_addr32[0];
+ d = &ipv6h->daddr.s6_addr32[0];
+ layer4_xor ^= (s[1] ^ d[1]) ^ (s[2] ^ d[2]) ^ (s[3] ^ d[3]);
+ layer4_xor ^= (layer4_xor >> 24) ^ (layer4_xor >> 16) ^
+ (layer4_xor >> 8);
+ return 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 ----------------------------*/
---
-Jay Vosburgh, IBM Linux Technology Center, fubar@...ibm.com
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists