bonding support for IPv6 transmit hashing

I think you should combine this into the first patch, there is no reason to separate these two changes.
--
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

From: John Eaglesham <[email protected]>
Date: Sun, 1 Jul 2012 01:07:43 -0700

drivers/net/bonding/bond_main.c static struct notifier_block bond_netdev_notifier = { · line 3382

Quoted 4 lines

drivers/net/bonding/bond_main.c +4 -0

+		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]);

You completely ignored my feedback:

This is rediculous, just put &ipv6h->saddr into a local pointer named 's' and then you won't have use such gymnastics to indent the code.
--
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

Currently the "bonding" driver does not support load balancing outgoing traffic in LACP mode for IPv6 traffic. IPv4 (and TCP or UDP over IPv4) are currently supported; this patch adds transmit hashing for IPv6 (and TCP or UDP over IPv6), bringing IPv6 up to par with IPv4 support in the bonding driver.

The algorithm chosen (xor'ing the bottom three quads of the source and destination addresses together, then xor'ing each byte of that result into the bottom byte, finally xor'ing with the last bytes of the MAC addresses) was selected after testing almost 400,000 unique IPv6 addresses harvested from server logs. This algorithm had the most even distribution for both big- and little-endian architectures while still using few instructions. Its behavior also attempts to closely match that of the IPv4 algorithm.

The IPv6 flow label was intentionally not included in the hash as it appears to be unset in the vast majority of IPv6 traffic sampled, and the current algorithm not using the flow label already offers a very even distribution.

Fragmented IPv6 packets are handled the same way as fragmented IPv4 packets, ie, they are not balanced based on layer 4 information. Additionally, IPv6 packets with intermediate headers are not balanced based on layer 4 information. In practice these intermediate headers are not common and this should not cause any problems, and the alternative (a packet-parsing loop and look-up table) seemed slow and complicated for little gain.

This is an update to prior patches I submitted. This version includes:
* Updated and clarified description
* IPv6 algorithm more closely matches that of IPv4
* Thorough bounds checking on all xmit functions
* Consolidate layer 2 hashing logic into one function
* Update style as per Jay Vosburgh and David Miller
* Patches against net-next as one patch

Patch has been tested and performs as expected.

John Eaglesham

---
Documentation/networking/bonding.txt | 32 +++++++++++--
drivers/net/bonding/bond_main.c | 91 +++++++++++++++++++++++++-----------

2 files changed, 92 insertions(+), 31 deletions(-)

Documentation/networking/bonding.txt +1 -1

index bfea8a3..3851dad 100644
@@ -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
 

Documentation/networking/bonding.txt +16 -4

+
 		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.
 

drivers/net/bonding/bond_main.c +35 -10

index f5a40b9..c733d55 100644
@@ -3345,56 +3345,95 @@ 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;

drivers/net/bonding/bond_main.c +14 -11

+			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 ----------------------------*/

Signature · 1 line

1.7.11

Documentation/networking/bonding.txt xmit_hash_policy · line 770

Quoted 4 lines

Documentation/networking/bonding.txt +4 -0

+
+		(((hash >> 24) XOR (hash >> 16) XOR (hash >> 8) XOR hash)
+			(source MAC XOR destination MAC))
+				modulo slave count

This seems to be missing an XOR, between the end of "XOR hash)"
and the start of "(source MAC".

drivers/net/bonding/bond_main.c static struct notifier_block bond_netdev_notifier = { · line 3407

Quoted 7 lines

	if (skb->protocol == htons(ETH_P_IP)) {

(quoted diff) +1 -0

+		iph = ip_hdr(skb);

		if (!ip_is_fragment(iph) &&

drivers/net/bonding/bond_main.c +2 -2

-		    (iph->protocol == IPPROTO_TCP ||
-		     iph->protocol == IPPROTO_UDP)) {
+			(iph->protocol == IPPROTO_TCP ||
+			iph->protocol == IPPROTO_UDP)) {

Why did these two lines change?

Quoted 7 lines

drivers/net/bonding/bond_main.c +4 -0

+			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)));

(quoted diff) +2 -0

+		} else if (skb_network_header_len(skb) < sizeof(struct iphdr)) {
+			goto short_header;

drivers/net/bonding/bond_main.c static struct notifier_block bond_netdev_notifier = { · line 3416

Quoted 5 lines

		}

drivers/net/bonding/bond_main.c +1 -3

-		return (layer4_xor ^
-			((ntohl(iph->saddr ^ iph->daddr)) & 0xffff)) % count;
-
+		return (layer4_xor ^ ((ntohl(iph->saddr ^ iph->daddr)) & 0xffff)) % count;

This line runs past 80 columns. There are a few more of these
further down.

drivers/net/bonding/bond_main.c static struct notifier_block bond_netdev_notifier = { · line 3420

Quoted 4 lines

drivers/net/bonding/bond_main.c +4 -0

+	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		ipv6h = ipv6_hdr(skb);
+		if (ipv6h->nexthdr == IPPROTO_TCP || ipv6h->nexthdr == IPPROTO_UDP) {
+			layer4hdr = (__be16 *)((u8 *)ipv6h + sizeof(struct ipv6hdr));

	Could this be written as

			layer4hdr = (__be16 *)(ipv6h + 1);

	instead?

	-J

I replaced the mixed tabs and spaces with all tabs when I updated that function, but in retrospect the tabs and spaces were likely intentional. I will revert.

From: John Eaglesham <[email protected]>
Date: Mon, 02 Jul 2012 22:01:20 -0700

Quoted 3 lines

I replaced the mixed tabs and spaces with all tabs when I updated that function, but in retrospect the tabs and spaces were likely intentional. I will revert.

They were. Don't change existing coding style unless you are certain it is wrong.

Besides any such changes are completely outside of the scope of the changes you are making, so you should have left them out in any event.
--
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

Quoted 10 lines

From: John Eaglesham <[email protected]>
Date: Mon, 02 Jul 2012 22:01:20 -0700

Quoted 3 lines

I replaced the mixed tabs and spaces with all tabs when I updated that function, but in retrospect the tabs and spaces were likely intentional. I will revert.

They were. Don't change existing coding style unless you are certain it is wrong.

Quoted 8 lines

Besides any such changes are completely outside of the scope of the changes you are making, so you should have left them out in any event.
--
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

Should the indents in the code I am adding follow the style guide and use only tabs, or follow the style already present and mix spaces and tabs for indentation?

You should use a mix of tabs, as necessary, to get things to line up how I told you they need to line up.

Quoted 2 lines

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?

Quoted 7 lines · Jeremy Brookman

Quoted 2 lines

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

Quoted 2 lines

If John signs off and somebody tests this, I'll post a formal
submssion with the full commit message.

Since my last submission I ended up making some changes on my end to streamline the logic. I can fold together my patch with yours and test them later tonight. If everything looks good I'll post the changes back to the list.

Quoted 25 lines · Jay Vosburgh

Quoted 8 lines · Jeremy Brookman

Quoted 2 lines

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)?

static int bond_xmit_hash_policy_l23(struct sk_buff *skb, int count)

drivers/net/bonding/bond_main.c +3 -0

+       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) ^

/*
* 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() */

Signed-off-by John Eaglesham

From: John Eaglesham <[email protected]>

Currently the "bonding" driver does not support load balancing outgoing traffic in LACP mode for IPv6 traffic. IPv4 (and TCP or UDP over IPv4) are currently supported; this patch adds transmit hashing for IPv6 (and TCP or UDP over IPv6), bringing IPv6 up to par with IPv4 support in the bonding driver. In addition, bounds checking has been added to all transmit hashing functions.

The algorithm chosen (xor'ing the bottom three quads of the source and destination addresses together, then xor'ing each byte of that result into the bottom byte, finally xor'ing with the last bytes of the MAC addresses) was selected after testing almost 400,000 unique IPv6 addresses harvested from server logs. This algorithm had the most even distribution for both big- and little-endian architectures while still using few instructions. Its behavior also attempts to closely match that of the IPv4 algorithm.

The IPv6 flow label was intentionally not included in the hash as it appears to be unset in the vast majority of IPv6 traffic sampled, and the current algorithm not using the flow label already offers a very even distribution.

Fragmented IPv6 packets are handled the same way as fragmented IPv4 packets, ie, they are not balanced based on layer 4 information. Additionally, IPv6 packets with intermediate headers are not balanced based on layer 4 information. In practice these intermediate headers are not common and this should not cause any problems, and the alternative (a packet-parsing loop and look-up table) seemed slow and complicated for little gain.

Tested-by John Eaglesham <[email protected]>

Signed-off-by John Eaglesham <[email protected]>

From: John Eaglesham <[email protected]>

Currently the "bonding" driver does not support load balancing outgoing traffic in LACP mode for IPv6 traffic. IPv4 (and TCP or UDP over IPv4) are currently supported; this patch adds transmit hashing for IPv6 (and TCP or UDP over IPv6), bringing IPv6 up to par with IPv4 support in the bonding driver. In addition, bounds checking has been added to all transmit hashing functions.

The algorithm chosen (xor'ing the bottom three quads of the source and destination addresses together, then xor'ing each byte of that result into the bottom byte, finally xor'ing with the last bytes of the MAC addresses) was selected after testing almost 400,000 unique IPv6 addresses harvested from server logs. This algorithm had the most even distribution for both big- and little-endian architectures while still using few instructions. Its behavior also attempts to closely match that of the IPv4 algorithm.

The IPv6 flow label was intentionally not included in the hash as it appears to be unset in the vast majority of IPv6 traffic sampled, and the current algorithm not using the flow label already offers a very even distribution.

Fragmented IPv6 packets are handled the same way as fragmented IPv4 packets, ie, they are not balanced based on layer 4 information. Additionally, IPv6 packets with intermediate headers are not balanced based on layer 4 information. In practice these intermediate headers are not common and this should not cause any problems, and the alternative (a packet-parsing loop and look-up table) seemed slow and complicated for little gain.

Tested-by John Eaglesham <[email protected]>

Signed-off-by John Eaglesham <[email protected]>

---

Changes:
v2)
* Clarify description
* Add bounds checking to more functions
* All functions call bond_xmit_hash_policy_l2 rather than re- implement the same logic.
v3)
* Patch against net-next.
* Style corrections.
v4)
* Correct indenting.
v5)
* Squash documentation and code patches into one.
v6)
* Modify IPv6 hash to behave more like the IPv4 hash, update documentation with modified algorithm.
* Clean up formatting.
* Move all variable declaration to the top of the function.
* Minor change to IPv6 layer 4 hash to match IPv4 hash behavior (mix all hashed address bits together rather than just the bottom 24 bits).
v7)
* Improve bounds checking code (handle truncated IPv6 header, removed goto, fewer if statements).
* Re-write pseudocode in documentation to match actual code more closely.
* Correct indenting, align parentheses, wrap code at <= 80 columns (based on Jay's changes).
v8)
* Correct patch submission format.

 Documentation/networking/bonding.txt | 30 ++++++++++--
 drivers/net/bonding/bond_main.c      | 89 +++++++++++++++++++++++++-----------
 2 files changed, 88 insertions(+), 31 deletions(-)

Documentation/networking/bonding.txt +25 -5

index 6b1c711..10a015c 100644
@@ -752,12 +752,22 @@ 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 +788,29 @@ 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 port XOR dest port) XOR
+                      ((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)
+                       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.
 

drivers/net/bonding/bond_main.c +63 -27

index d95fbc3..4221e57 100644
@@ -3354,56 +3354,93 @@ 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(*iph)) {
+               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(*ipv6h)) {
+               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;
-
-       if (skb->protocol == htons(ETH_P_IP)) {
+       u32 layer4_xor = 0;
+       struct iphdr *iph;
+       struct ipv6hdr *ipv6h;
+       __be32 *s, *d;
+       __be16 *layer4hdr;
+
+       if (skb->protocol == htons(ETH_P_IP) &&
+           skb_network_header_len(skb) >= sizeof(*iph)) {
+               iph = ip_hdr(skb);
                if (!ip_is_fragment(iph) &&
                    (iph->protocol == IPPROTO_TCP ||
-                    iph->protocol == IPPROTO_UDP)) {
-                       layer4_xor = ntohs((*layer4hdr ^ *(layer4hdr + 1)));
+                    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));
                }
                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)) {
+               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));
+               }
+               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;
+       return bond_xmit_hash_policy_l2(skb, count);
 }
 
 /*-------------------------- Device entry points ----------------------------*/
--

1.7.11

--
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