All of lore.kernel.org
 help / color / mirror / Atom feed
From: Sun Shouxin <sunshouxin@chinatelecom.cn>
To: j.vosburgh@gmail.com, vfalico@gmail.com, andy@greyhouse.net,
	davem@davemloft.net, kuba@kernel.org
Cc: netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
	huyd12@chinatelecom.cn
Subject: [PATCH V2] net: bonding: Add support for IPV6 ns/na
Date: Fri, 10 Dec 2021 21:08:11 +0800	[thread overview]
Message-ID: <1639141691-3741-1-git-send-email-sunshouxin@chinatelecom.cn> (raw)

Since ipv6 neighbor solicitation and advertisement messages
isn't handled gracefully in bonding6 driver, we can see packet
drop due to inconsistency bewteen mac address in the option
message and source MAC .

Another examples is ipv6 neighbor solicitation and advertisement
messages from VM via tap attached to host brighe, the src mac
mighe be changed through balance-alb mode, but it is not synced
with Link-layer address in the option message.

The patch implements bond6's tx handle for ipv6 neighbor
solicitation and advertisement messages.

			Border-Leaf
			/        \
		       /          \
		    Tunnel1    Tunnel2
		     /              \
	            /                \
		  Leaf-1--Tunnel3--Leaf-2
		    \                /
		     \              /
		      \            /
		       \          /
		       NIC1    NIC2
			\      /
			server

We can see in our lab the Border-Leaf receives occasionally
a NA packet which is assigned to NIC1 mac in ND/NS option
message, but actaully send out via NIC2 mac due to tx-alb,
as a result, it will cause inconsistency between MAC table
and ND Table in Border-Leaf, i.e, NIC1 = Tunnel2 in ND table
and  NIC1 = Tunnel1 in mac table.

And then, Border-Leaf starts to forward packet destinated
to the Server, it will only check the ND table entry in some
switch to encapsulate the destination MAC of the message as
NIC1 MAC, and then send it out from Tunnel2 by ND table.
Then, Leaf-2 receives the packet, it notices the destination
MAC of message is NIC1 MAC and should forword it to Tunne1
by Tunnel3.

However, this traffic forward will be failure due to split
horizon of VxLAN tunnels.

Suggested-by: Hu Yadi <huyd12@chinatelecom.cn>
Signed-off-by: Sun Shouxin <sunshouxin@chinatelecom.cn>
---
 drivers/net/bonding/bond_alb.c | 131 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 131 insertions(+)

diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 533e476..afa386b 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -22,6 +22,7 @@
 #include <asm/byteorder.h>
 #include <net/bonding.h>
 #include <net/bond_alb.h>
+#include <net/ndisc.h>
 
 static const u8 mac_v6_allmcast[ETH_ALEN + 2] __long_aligned = {
 	0x33, 0x33, 0x00, 0x00, 0x00, 0x01
@@ -1269,6 +1270,119 @@ static int alb_set_mac_address(struct bonding *bond, void *addr)
 	return res;
 }
 
+/*determine if the packet is NA or NS*/
+static bool alb_determine_nd(struct icmp6hdr *hdr)
+{
+	if (hdr->icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT ||
+	    hdr->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) {
+		return true;
+	}
+
+	return false;
+}
+
+static void alb_change_nd_option(struct sk_buff *skb, void *data)
+{
+	struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
+	struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)msg->opt;
+	struct net_device *dev = skb->dev;
+	struct icmp6hdr *icmp6h = icmp6_hdr(skb);
+	struct ipv6hdr *ip6hdr = ipv6_hdr(skb);
+	u8 *lladdr = NULL;
+	u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) +
+				offsetof(struct nd_msg, opt));
+
+	while (ndoptlen) {
+		int l;
+
+		switch (nd_opt->nd_opt_type) {
+		case ND_OPT_SOURCE_LL_ADDR:
+		case ND_OPT_TARGET_LL_ADDR:
+		lladdr = ndisc_opt_addr_data(nd_opt, dev);
+		break;
+
+		default:
+		lladdr = NULL;
+		break;
+		}
+
+		l = nd_opt->nd_opt_len << 3;
+
+		if (ndoptlen < l || l == 0)
+			return;
+
+		if (lladdr) {
+			memcpy(lladdr, data, dev->addr_len);
+			icmp6h->icmp6_cksum = 0;
+
+			icmp6h->icmp6_cksum = csum_ipv6_magic(&ip6hdr->saddr,
+							      &ip6hdr->daddr,
+						ntohs(ip6hdr->payload_len),
+						IPPROTO_ICMPV6,
+						csum_partial(icmp6h,
+							     ntohs(ip6hdr->payload_len), 0));
+		}
+		ndoptlen -= l;
+		nd_opt = ((void *)nd_opt) + l;
+	}
+}
+
+static u8 *alb_get_lladdr(struct sk_buff *skb)
+{
+	struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
+	struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)msg->opt;
+	struct net_device *dev = skb->dev;
+	u8 *lladdr = NULL;
+	u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) +
+				offsetof(struct nd_msg, opt));
+
+	while (ndoptlen) {
+		int l;
+
+		switch (nd_opt->nd_opt_type) {
+		case ND_OPT_SOURCE_LL_ADDR:
+		case ND_OPT_TARGET_LL_ADDR:
+			lladdr = ndisc_opt_addr_data(nd_opt, dev);
+			break;
+
+		default:
+			break;
+		}
+
+		l = nd_opt->nd_opt_len << 3;
+
+		if (ndoptlen < l || l == 0)
+			return lladdr;
+
+		if (lladdr)
+			return lladdr;
+
+		ndoptlen -= l;
+		nd_opt = ((void *)nd_opt) + l;
+	}
+
+	return lladdr;
+}
+
+static void alb_set_nd_option(struct sk_buff *skb, struct bonding *bond,
+			      struct slave *tx_slave)
+{
+	struct ipv6hdr *ip6hdr;
+	struct icmp6hdr *hdr = NULL;
+
+	if (skb->protocol == htons(ETH_P_IPV6)) {
+		if (tx_slave && tx_slave !=
+		    rcu_access_pointer(bond->curr_active_slave)) {
+			ip6hdr = ipv6_hdr(skb);
+			if (ip6hdr->nexthdr == IPPROTO_ICMPV6) {
+				hdr = icmp6_hdr(skb);
+				if (alb_determine_nd(hdr))
+					alb_change_nd_option(skb, tx_slave->dev->dev_addr);
+			}
+		}
+	}
+}
+
 /************************ exported alb functions ************************/
 
 int bond_alb_initialize(struct bonding *bond, int rlb_enabled)
@@ -1415,6 +1529,7 @@ struct slave *bond_xmit_alb_slave_get(struct bonding *bond,
 	}
 	case ETH_P_IPV6: {
 		const struct ipv6hdr *ip6hdr;
+		struct icmp6hdr *hdr = NULL;
 
 		/* IPv6 doesn't really use broadcast mac address, but leave
 		 * that here just in case.
@@ -1446,6 +1561,21 @@ struct slave *bond_xmit_alb_slave_get(struct bonding *bond,
 			break;
 		}
 
+		if (ip6hdr->nexthdr == IPPROTO_ICMPV6) {
+			hdr = icmp6_hdr(skb);
+			if (alb_determine_nd(hdr)) {
+				u8 *lladdr = NULL;
+
+				lladdr = alb_get_lladdr(skb);
+				if (lladdr) {
+					if (!bond_slave_has_mac_rx(bond, lladdr)) {
+						do_tx_balance = false;
+						break;
+					}
+				}
+			}
+		}
+
 		hash_start = (char *)&ip6hdr->daddr;
 		hash_size = sizeof(ip6hdr->daddr);
 		break;
@@ -1489,6 +1619,7 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 	struct slave *tx_slave = NULL;
 
 	tx_slave = bond_xmit_alb_slave_get(bond, skb);
+	alb_set_nd_option(skb, bond, tx_slave);
 	return bond_do_alb_xmit(skb, bond, tx_slave);
 }
 
-- 
1.8.3.1


             reply	other threads:[~2021-12-10 13:09 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-12-10 13:08 Sun Shouxin [this message]
2021-12-10 18:03 ` [PATCH V2] net: bonding: Add support for IPV6 ns/na kernel test robot
2021-12-10 18:03   ` kernel test robot
2021-12-10 18:13 ` kernel test robot
2021-12-10 18:13   ` kernel test robot
2021-12-14  1:02 ` 回复: " huyd12
2021-12-14  1:06   ` Jakub Kicinski
2021-12-14  8:05 ` Eric Dumazet
2021-12-20  1:57   ` 孙守鑫
2021-12-20 15:05     ` Eric Dumazet

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1639141691-3741-1-git-send-email-sunshouxin@chinatelecom.cn \
    --to=sunshouxin@chinatelecom.cn \
    --cc=andy@greyhouse.net \
    --cc=davem@davemloft.net \
    --cc=huyd12@chinatelecom.cn \
    --cc=j.vosburgh@gmail.com \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=vfalico@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.