This is a note to let you know that I've just added the patch titled
bonding: fix l23 and l34 load balancing in forwarding path
to the 3.8-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
bonding-fix-l23-and-l34-load-balancing-in-forwarding-path.patch
and it can be found in the queue-3.8 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <[email protected]> know about it.
>From 0829aedd0d4542e51664ac0f8748abd2cb0ba3f5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <[email protected]>
Date: Mon, 15 Apr 2013 17:03:24 +0000
Subject: bonding: fix l23 and l34 load balancing in forwarding path
From: Eric Dumazet <[email protected]>
[ Upstream commit 4394542ca4ec9f28c3c8405063d200b1e7c347d7 ]
Since commit 6b923cb7188d46 (bonding: support for IPv6 transmit hashing)
bonding doesn't properly hash traffic in forwarding setups.
Vitaly V. Bursov diagnosed that skb_network_header_len() returned 0 in
this case.
More generally, the transport header might not be in the skb head.
Use pskb_may_pull() & skb_header_pointer() to get it right, and use
proto_ports_offset() in bond_xmit_hash_policy_l34() to get support for
more protocols than TCP and UDP.
Reported-by: Vitaly V. Bursov <[email protected]>
Signed-off-by: Eric Dumazet <[email protected]>
Cc: Jay Vosburgh <[email protected]>
Cc: Andy Gospodarek <[email protected]>
Cc: John Eaglesham <[email protected]>
Tested-by: Vitaly V. Bursov <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>
---
drivers/net/bonding/bond_main.c | 55 +++++++++++++++++++++-------------------
1 file changed, 30 insertions(+), 25 deletions(-)
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3380,20 +3380,22 @@ static int bond_xmit_hash_policy_l2(stru
*/
static int bond_xmit_hash_policy_l23(struct sk_buff *skb, int count)
{
- struct ethhdr *data = (struct ethhdr *)skb->data;
- struct iphdr *iph;
- struct ipv6hdr *ipv6h;
+ const struct ethhdr *data;
+ const struct iphdr *iph;
+ const struct ipv6hdr *ipv6h;
u32 v6hash;
- __be32 *s, *d;
+ const __be32 *s, *d;
if (skb->protocol == htons(ETH_P_IP) &&
- skb_network_header_len(skb) >= sizeof(*iph)) {
+ pskb_network_may_pull(skb, sizeof(*iph))) {
iph = ip_hdr(skb);
+ data = (struct ethhdr *)skb->data;
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(*ipv6h)) {
+ pskb_network_may_pull(skb, sizeof(*ipv6h))) {
ipv6h = ipv6_hdr(skb);
+ data = (struct ethhdr *)skb->data;
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]);
@@ -3412,33 +3414,36 @@ static int bond_xmit_hash_policy_l23(str
static int bond_xmit_hash_policy_l34(struct sk_buff *skb, int count)
{
u32 layer4_xor = 0;
- struct iphdr *iph;
- struct ipv6hdr *ipv6h;
- __be32 *s, *d;
- __be16 *layer4hdr;
+ const struct iphdr *iph;
+ const struct ipv6hdr *ipv6h;
+ const __be32 *s, *d;
+ const __be16 *l4 = NULL;
+ __be16 _l4[2];
+ int noff = skb_network_offset(skb);
+ int poff;
if (skb->protocol == htons(ETH_P_IP) &&
- skb_network_header_len(skb) >= sizeof(*iph)) {
+ pskb_may_pull(skb, noff + sizeof(*iph))) {
iph = ip_hdr(skb);
- if (!ip_is_fragment(iph) &&
- (iph->protocol == IPPROTO_TCP ||
- iph->protocol == IPPROTO_UDP) &&
- (skb_headlen(skb) - skb_network_offset(skb) >=
- iph->ihl * sizeof(u32) + sizeof(*layer4hdr) * 2)) {
- layer4hdr = (__be16 *)((u32 *)iph + iph->ihl);
- layer4_xor = ntohs(*layer4hdr ^ *(layer4hdr + 1));
+ poff = proto_ports_offset(iph->protocol);
+
+ if (!ip_is_fragment(iph) && poff >= 0) {
+ l4 = skb_header_pointer(skb, noff + (iph->ihl << 2) +
poff,
+ sizeof(_l4), &_l4);
+ if (l4)
+ layer4_xor = ntohs(l4[0] ^ l4[1]);
}
return (layer4_xor ^
((ntohl(iph->saddr ^ iph->daddr)) & 0xffff)) % count;
} else if (skb->protocol == htons(ETH_P_IPV6) &&
- skb_network_header_len(skb) >= sizeof(*ipv6h)) {
+ pskb_may_pull(skb, noff + sizeof(*ipv6h))) {
ipv6h = ipv6_hdr(skb);
- if ((ipv6h->nexthdr == IPPROTO_TCP ||
- ipv6h->nexthdr == IPPROTO_UDP) &&
- (skb_headlen(skb) - skb_network_offset(skb) >=
- sizeof(*ipv6h) + sizeof(*layer4hdr) * 2)) {
- layer4hdr = (__be16 *)(ipv6h + 1);
- layer4_xor = ntohs(*layer4hdr ^ *(layer4hdr + 1));
+ poff = proto_ports_offset(ipv6h->nexthdr);
+ if (poff >= 0) {
+ l4 = skb_header_pointer(skb, noff + sizeof(*ipv6h) +
poff,
+ sizeof(_l4), &_l4);
+ if (l4)
+ layer4_xor = ntohs(l4[0] ^ l4[1]);
}
s = &ipv6h->saddr.s6_addr32[0];
d = &ipv6h->daddr.s6_addr32[0];
Patches currently in stable-queue which might be from [email protected] are
queue-3.8/tcp-reallocate-headroom-if-it-would-overflow-csum_start.patch
queue-3.8/ipv6-tcp-stop-processing-icmpv6-redirect-messages.patch
queue-3.8/tcp-call-tcp_replace_ts_recent-from-tcp_ack.patch
queue-3.8/net-drop-dst-before-queueing-fragments.patch
queue-3.8/cbq-incorrect-processing-of-high-limits.patch
queue-3.8/bonding-fix-l23-and-l34-load-balancing-in-forwarding-path.patch
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
