Merge branch 'bonding-ipv6-NA-NS-monitor'

Hangbin Liu says:

====================
bonding: add IPv6 NS/NA monitor support

This patch add bond IPv6 NS/NA monitor support. A new option
ns_ip6_target is added, which is similar with arp_ip_target.
The IPv6 NS/NA monitor will take effect when there is a valid IPv6
address. Both ARP monitor and NS monitor will working at the same time.

A new extra storage field is added to struct bond_opt_value for IPv6 support.

Function bond_handle_vlan() is split from bond_arp_send() for both
IPv4/IPv6 usage.

To alloc NS message and send out. ndisc_ns_create() and ndisc_send_skb()
are exported.

v1 -> v2:
1. remove sysfs entry[1] and only keep netlink support.

RFC -> v1:
1. define BOND_MAX_ND_TARGETS as BOND_MAX_ARP_TARGETS
2. adjust for reverse xmas tree ordering of local variables
3. remove bond_do_ns_validate()
4. add extra field for bond_opt_value
5. set IS_ENABLED(CONFIG_IPV6) for IPv6 codes

[1] https://lore.kernel.org/netdev/8863.1645071997@famine
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/networking/bonding.rst

@@ -313,6 +313,17 @@ arp_ip_target
 	maximum number of targets that can be specified is 16.  The
 	default value is no IP addresses.
 
+ns_ip6_target
+
+	Specifies the IPv6 addresses to use as IPv6 monitoring peers when
+	arp_interval is > 0.  These are the targets of the NS request
+	sent to determine the health of the link to the targets.
+	Specify these values in ffff:ffff::ffff:ffff format.  Multiple IPv6
+	addresses must be separated by a comma.  At least one IPv6
+	address must be given for NS/NA monitoring to function.  The
+	maximum number of targets that can be specified is 16.  The
+	default value is no IPv6 addresses.
+
 arp_validate
 
 	Specifies whether or not ARP probes and replies should be

drivers/net/bonding/bond_netlink.c

@@ -14,6 +14,7 @@
 #include <net/netlink.h>
 #include <net/rtnetlink.h>
 #include <net/bonding.h>
+#include <net/ipv6.h>
 
 static size_t bond_get_slave_size(const struct net_device *bond_dev,
 				  const struct net_device *slave_dev)
@@ -111,6 +112,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_TLB_DYNAMIC_LB]	= { .type = NLA_U8 },
 	[IFLA_BOND_PEER_NOTIF_DELAY]    = { .type = NLA_U32 },
 	[IFLA_BOND_MISSED_MAX]		= { .type = NLA_U8 },
+	[IFLA_BOND_NS_IP6_TARGET]	= { .type = NLA_NESTED },
 };
 
 static const struct nla_policy bond_slave_policy[IFLA_BOND_SLAVE_MAX + 1] = {
@@ -272,6 +274,40 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[],
 		if (err)
 			return err;
 	}
+#if IS_ENABLED(CONFIG_IPV6)
+	if (data[IFLA_BOND_NS_IP6_TARGET]) {
+		struct nlattr *attr;
+		int i = 0, rem;
+
+		bond_option_ns_ip6_targets_clear(bond);
+		nla_for_each_nested(attr, data[IFLA_BOND_NS_IP6_TARGET], rem) {
+			struct in6_addr addr6;
+
+			if (nla_len(attr) < sizeof(addr6)) {
+				NL_SET_ERR_MSG(extack, "Invalid IPv6 address");
+				return -EINVAL;
+			}
+
+			addr6 = nla_get_in6_addr(attr);
+
+			if (ipv6_addr_type(&addr6) & IPV6_ADDR_LINKLOCAL) {
+				NL_SET_ERR_MSG(extack, "Invalid IPv6 addr6");
+				return -EINVAL;
+			}
+
+			bond_opt_initextra(&newval, &addr6, sizeof(addr6));
+			err = __bond_opt_set(bond, BOND_OPT_NS_TARGETS,
+					     &newval);
+			if (err)
+				break;
+			i++;
+		}
+		if (i == 0 && bond->params.arp_interval)
+			netdev_warn(bond->dev, "Removing last ns target with arp_interval on\n");
+		if (err)
+			return err;
+	}
+#endif
 	if (data[IFLA_BOND_ARP_VALIDATE]) {
 		int arp_validate = nla_get_u32(data[IFLA_BOND_ARP_VALIDATE]);
 
@@ -526,6 +562,9 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u8)) + /* IFLA_BOND_TLB_DYNAMIC_LB */
 		nla_total_size(sizeof(u32)) +	/* IFLA_BOND_PEER_NOTIF_DELAY */
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_MISSED_MAX */
+						/* IFLA_BOND_NS_IP6_TARGET */
+		nla_total_size(sizeof(struct nlattr)) +
+		nla_total_size(sizeof(struct in6_addr)) * BOND_MAX_NS_TARGETS +
 		0;
 }
 
@@ -603,6 +642,26 @@ static int bond_fill_info(struct sk_buff *skb,
 			bond->params.arp_all_targets))
 		goto nla_put_failure;
 
+#if IS_ENABLED(CONFIG_IPV6)
+	targets = nla_nest_start(skb, IFLA_BOND_NS_IP6_TARGET);
+	if (!targets)
+		goto nla_put_failure;
+
+	targets_added = 0;
+	for (i = 0; i < BOND_MAX_NS_TARGETS; i++) {
+		if (!ipv6_addr_any(&bond->params.ns_targets[i])) {
+			if (nla_put_in6_addr(skb, i, &bond->params.ns_targets[i]))
+				goto nla_put_failure;
+			targets_added = 1;
+		}
+	}
+
+	if (targets_added)
+		nla_nest_end(skb, targets);
+	else
+		nla_nest_cancel(skb, targets);
+#endif
+
 	primary = rtnl_dereference(bond->primary_slave);
 	if (primary &&
 	    nla_put_u32(skb, IFLA_BOND_PRIMARY, primary->dev->ifindex))

drivers/net/bonding/bond_options.c

@@ -34,6 +34,10 @@ static int bond_option_arp_ip_target_add(struct bonding *bond, __be32 target);
 static int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target);
 static int bond_option_arp_ip_targets_set(struct bonding *bond,
 					  const struct bond_opt_value *newval);
+#if IS_ENABLED(CONFIG_IPV6)
+static int bond_option_ns_ip6_targets_set(struct bonding *bond,
+					  const struct bond_opt_value *newval);
+#endif
 static int bond_option_arp_validate_set(struct bonding *bond,
 					const struct bond_opt_value *newval);
 static int bond_option_arp_all_targets_set(struct bonding *bond,
@@ -295,6 +299,15 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = {
 		.flags = BOND_OPTFLAG_RAWVAL,
 		.set = bond_option_arp_ip_targets_set
 	},
+#if IS_ENABLED(CONFIG_IPV6)
+	[BOND_OPT_NS_TARGETS] = {
+		.id = BOND_OPT_NS_TARGETS,
+		.name = "ns_ip6_target",
+		.desc = "NS targets in ffff:ffff::ffff:ffff form",
+		.flags = BOND_OPTFLAG_RAWVAL,
+		.set = bond_option_ns_ip6_targets_set
+	},
+#endif
 	[BOND_OPT_DOWNDELAY] = {
 		.id = BOND_OPT_DOWNDELAY,
 		.name = "downdelay",
@@ -1052,7 +1065,7 @@ static int bond_option_arp_interval_set(struct bonding *bond,
 			cancel_delayed_work_sync(&bond->arp_work);
 		} else {
 			/* arp_validate can be set only in active-backup mode */
-			bond->recv_probe = bond_arp_rcv;
+			bond->recv_probe = bond_rcv_validate;
 			cancel_delayed_work_sync(&bond->mii_work);
 			queue_delayed_work(bond->wq, &bond->arp_work, 0);
 		}
@@ -1184,6 +1197,65 @@ static int bond_option_arp_ip_targets_set(struct bonding *bond,
 	return ret;
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
+static void _bond_options_ns_ip6_target_set(struct bonding *bond, int slot,
+					    struct in6_addr *target,
+					    unsigned long last_rx)
+{
+	struct in6_addr *targets = bond->params.ns_targets;
+	struct list_head *iter;
+	struct slave *slave;
+
+	if (slot >= 0 && slot < BOND_MAX_NS_TARGETS) {
+		bond_for_each_slave(bond, slave, iter)
+			slave->target_last_arp_rx[slot] = last_rx;
+		targets[slot] = *target;
+	}
+}
+
+void bond_option_ns_ip6_targets_clear(struct bonding *bond)
+{
+	struct in6_addr addr_any = in6addr_any;
+	int i;
+
+	for (i = 0; i < BOND_MAX_NS_TARGETS; i++)
+		_bond_options_ns_ip6_target_set(bond, i, &addr_any, 0);
+}
+
+static int bond_option_ns_ip6_targets_set(struct bonding *bond,
+					  const struct bond_opt_value *newval)
+{
+	struct in6_addr *target = (struct in6_addr *)newval->extra;
+	struct in6_addr *targets = bond->params.ns_targets;
+	struct in6_addr addr_any = in6addr_any;
+	int index;
+
+	if (!bond_is_ip6_target_ok(target)) {
+		netdev_err(bond->dev, "invalid NS target %pI6c specified for addition\n",
+			   target);
+		return -EINVAL;
+	}
+
+	if (bond_get_targets_ip6(targets, target) != -1) { /* dup */
+		netdev_err(bond->dev, "NS target %pI6c is already present\n",
+			   target);
+		return -EINVAL;
+	}
+
+	index = bond_get_targets_ip6(targets, &addr_any); /* first free slot */
+	if (index == -1) {
+		netdev_err(bond->dev, "NS target table is full!\n");
+		return -EINVAL;
+	}
+
+	netdev_dbg(bond->dev, "Adding NS target %pI6c\n", target);
+
+	_bond_options_ns_ip6_target_set(bond, index, target, jiffies);
+
+	return 0;
+}
+#endif
+
 static int bond_option_arp_validate_set(struct bonding *bond,
 					const struct bond_opt_value *newval)
 {

include/net/bond_options.h

@@ -66,19 +66,24 @@ enum {
 	BOND_OPT_PEER_NOTIF_DELAY,
 	BOND_OPT_LACP_ACTIVE,
 	BOND_OPT_MISSED_MAX,
+	BOND_OPT_NS_TARGETS,
 	BOND_OPT_LAST
 };
 
 /* This structure is used for storing option values and for passing option
  * values when changing an option. The logic when used as an arg is as follows:
- * - if string != NULL -> parse it, if the opt is RAW type then return it, else
- *   return the parse result
- * - if string == NULL -> parse value
+ * - if value != ULLONG_MAX -> parse value
+ * - if string != NULL -> parse string
+ * - if the opt is RAW data and length less than maxlen,
+ *   copy the data to extra storage
  */
+
+#define BOND_OPT_EXTRA_MAXLEN 16
 struct bond_opt_value {
 	char *string;
 	u64 value;
 	u32 flags;
+	char extra[BOND_OPT_EXTRA_MAXLEN];
 };
 
 struct bonding;
@@ -118,18 +123,26 @@ const struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val);
  * When value is ULLONG_MAX then string will be used.
  */
 static inline void __bond_opt_init(struct bond_opt_value *optval,
-				   char *string, u64 value)
+				   char *string, u64 value,
+				   void *extra, size_t extra_len)
 {
 	memset(optval, 0, sizeof(*optval));
 	optval->value = ULLONG_MAX;
-	if (value == ULLONG_MAX)
-		optval->string = string;
-	else
+	if (value != ULLONG_MAX)
 		optval->value = value;
+	else if (string)
+		optval->string = string;
+	else if (extra_len <= BOND_OPT_EXTRA_MAXLEN)
+		memcpy(optval->extra, extra, extra_len);
 }
-#define bond_opt_initval(optval, value) __bond_opt_init(optval, NULL, value)
-#define bond_opt_initstr(optval, str) __bond_opt_init(optval, str, ULLONG_MAX)
+#define bond_opt_initval(optval, value) __bond_opt_init(optval, NULL, value, NULL, 0)
+#define bond_opt_initstr(optval, str) __bond_opt_init(optval, str, ULLONG_MAX, NULL, 0)
+#define bond_opt_initextra(optval, extra, extra_len) \
+	__bond_opt_init(optval, NULL, ULLONG_MAX, extra, extra_len)
 
 void bond_option_arp_ip_targets_clear(struct bonding *bond);
+#if IS_ENABLED(CONFIG_IPV6)
+void bond_option_ns_ip6_targets_clear(struct bonding *bond);
+#endif
 
 #endif /* _NET_BOND_OPTIONS_H */

include/net/bonding.h

@@ -29,8 +29,11 @@
 #include <net/bond_3ad.h>
 #include <net/bond_alb.h>
 #include <net/bond_options.h>
+#include <net/ipv6.h>
+#include <net/addrconf.h>
 
 #define BOND_MAX_ARP_TARGETS	16
+#define BOND_MAX_NS_TARGETS	BOND_MAX_ARP_TARGETS
 
 #define BOND_DEFAULT_MIIMON	100
 
@@ -146,6 +149,7 @@ struct bond_params {
 	struct reciprocal_value reciprocal_packets_per_slave;
 	u16 ad_actor_sys_prio;
 	u16 ad_user_port_key;
+	struct in6_addr ns_targets[BOND_MAX_NS_TARGETS];
 
 	/* 2 bytes of padding : see ether_addr_equal_64bits() */
 	u8 ad_actor_system[ETH_ALEN + 2];
@@ -499,6 +503,13 @@ static inline int bond_is_ip_target_ok(__be32 addr)
 	return !ipv4_is_lbcast(addr) && !ipv4_is_zeronet(addr);
 }
 
+static inline int bond_is_ip6_target_ok(struct in6_addr *addr)
+{
+	return !ipv6_addr_any(addr) &&
+	       !ipv6_addr_loopback(addr) &&
+	       !ipv6_addr_is_multicast(addr);
+}
+
 /* Get the oldest arp which we've received on this slave for bond's
  * arp_targets.
  */
@@ -628,7 +639,7 @@ struct bond_net {
 	struct class_attribute	class_attr_bonding_masters;
 };
 
-int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave);
+int bond_rcv_validate(const struct sk_buff *skb, struct bonding *bond, struct slave *slave);
 netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev);
 int bond_create(struct net *net, const char *name);
 int bond_create_sysfs(struct bond_net *net);
@@ -735,6 +746,19 @@ static inline int bond_get_targets_ip(__be32 *targets, __be32 ip)
 	return -1;
 }
 
+static inline int bond_get_targets_ip6(struct in6_addr *targets, struct in6_addr *ip)
+{
+	int i;
+
+	for (i = 0; i < BOND_MAX_NS_TARGETS; i++)
+		if (ipv6_addr_equal(&targets[i], ip))
+			return i;
+		else if (ipv6_addr_any(&targets[i]))
+			break;
+
+	return -1;
+}
+
 /* exported from bond_main.c */
 extern unsigned int bond_net_id;
 

include/net/ndisc.h

@@ -447,10 +447,15 @@ void ndisc_cleanup(void);
 
 int ndisc_rcv(struct sk_buff *skb);
 
+struct sk_buff *ndisc_ns_create(struct net_device *dev, const struct in6_addr *solicit,
+				const struct in6_addr *saddr, u64 nonce);
 void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
 		   const struct in6_addr *daddr, const struct in6_addr *saddr,
 		   u64 nonce);
 
+void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr,
+		    const struct in6_addr *saddr);
+
 void ndisc_send_rs(struct net_device *dev,
 		   const struct in6_addr *saddr, const struct in6_addr *daddr);
 void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr,

include/uapi/linux/if_link.h

@@ -860,6 +860,7 @@ enum {
 	IFLA_BOND_PEER_NOTIF_DELAY,
 	IFLA_BOND_AD_LACP_ACTIVE,
 	IFLA_BOND_MISSED_MAX,
+	IFLA_BOND_NS_IP6_TARGET,
 	__IFLA_BOND_MAX,
 };
 

net/ipv6/ndisc.c

@@ -466,9 +466,8 @@ static void ip6_nd_hdr(struct sk_buff *skb,
 	hdr->daddr = *daddr;
 }
 
-static void ndisc_send_skb(struct sk_buff *skb,
-			   const struct in6_addr *daddr,
-			   const struct in6_addr *saddr)
+void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr,
+		    const struct in6_addr *saddr)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct net *net = dev_net(skb->dev);
@@ -515,6 +514,7 @@ static void ndisc_send_skb(struct sk_buff *skb,
 
 	rcu_read_unlock();
 }
+EXPORT_SYMBOL(ndisc_send_skb);
 
 void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr,
 		   const struct in6_addr *solicited_addr,
@@ -598,22 +598,16 @@ static void ndisc_send_unsol_na(struct net_device *dev)
 	in6_dev_put(idev);
 }
 
-void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
-		   const struct in6_addr *daddr, const struct in6_addr *saddr,
-		   u64 nonce)
+struct sk_buff *ndisc_ns_create(struct net_device *dev, const struct in6_addr *solicit,
+				const struct in6_addr *saddr, u64 nonce)
 {
-	struct sk_buff *skb;
-	struct in6_addr addr_buf;
 	int inc_opt = dev->addr_len;
-	int optlen = 0;
+	struct sk_buff *skb;
 	struct nd_msg *msg;
+	int optlen = 0;
 
-	if (!saddr) {
-		if (ipv6_get_lladdr(dev, &addr_buf,
-				   (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)))
-			return;
-		saddr = &addr_buf;
-	}
+	if (!saddr)
+		return NULL;
 
 	if (ipv6_addr_any(saddr))
 		inc_opt = false;
@@ -625,7 +619,7 @@ void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
 
 	skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
 	if (!skb)
-		return;
+		return NULL;
 
 	msg = skb_put(skb, sizeof(*msg));
 	*msg = (struct nd_msg) {
@@ -647,7 +641,28 @@ void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
 		memcpy(opt + 2, &nonce, 6);
 	}
 
-	ndisc_send_skb(skb, daddr, saddr);
+	return skb;
+}
+EXPORT_SYMBOL(ndisc_ns_create);
+
+void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
+		   const struct in6_addr *daddr, const struct in6_addr *saddr,
+		   u64 nonce)
+{
+	struct in6_addr addr_buf;
+	struct sk_buff *skb;
+
+	if (!saddr) {
+		if (ipv6_get_lladdr(dev, &addr_buf,
+				    (IFA_F_TENTATIVE | IFA_F_OPTIMISTIC)))
+			return;
+		saddr = &addr_buf;
+	}
+
+	skb = ndisc_ns_create(dev, solicit, saddr, nonce);
+
+	if (skb)
+		ndisc_send_skb(skb, daddr, saddr);
 }
 
 void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr,

tools/include/uapi/linux/if_link.h

@@ -860,6 +860,7 @@ enum {
 	IFLA_BOND_PEER_NOTIF_DELAY,
 	IFLA_BOND_AD_LACP_ACTIVE,
 	IFLA_BOND_MISSED_MAX,
+	IFLA_BOND_NS_IP6_TARGET,
 	__IFLA_BOND_MAX,
 };