summaryrefslogtreecommitdiff
path: root/drivers/net/bonding/bond_main.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/bonding/bond_main.c')
-rw-r--r--drivers/net/bonding/bond_main.c324
1 files changed, 272 insertions, 52 deletions
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index aebeb46e6fa6..15eddca7b4b6 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -88,6 +88,7 @@
#if IS_ENABLED(CONFIG_TLS_DEVICE)
#include <net/tls.h>
#endif
+#include <net/ip6_route.h>
#include "bonding_priv.h"
@@ -2793,31 +2794,15 @@ static bool bond_has_this_ip(struct bonding *bond, __be32 ip)
return ret;
}
-/* We go to the (large) trouble of VLAN tagging ARP frames because
- * switches in VLAN mode (especially if ports are configured as
- * "native" to a VLAN) might not pass non-tagged frames.
- */
-static void bond_arp_send(struct slave *slave, int arp_op, __be32 dest_ip,
- __be32 src_ip, struct bond_vlan_tag *tags)
+static bool bond_handle_vlan(struct slave *slave, struct bond_vlan_tag *tags,
+ struct sk_buff *skb)
{
- struct sk_buff *skb;
- struct bond_vlan_tag *outer_tag = tags;
- struct net_device *slave_dev = slave->dev;
struct net_device *bond_dev = slave->bond->dev;
-
- slave_dbg(bond_dev, slave_dev, "arp %d on slave: dst %pI4 src %pI4\n",
- arp_op, &dest_ip, &src_ip);
-
- skb = arp_create(arp_op, ETH_P_ARP, dest_ip, slave_dev, src_ip,
- NULL, slave_dev->dev_addr, NULL);
-
- if (!skb) {
- net_err_ratelimited("ARP packet allocation failed\n");
- return;
- }
+ struct net_device *slave_dev = slave->dev;
+ struct bond_vlan_tag *outer_tag = tags;
if (!tags || tags->vlan_proto == VLAN_N_VID)
- goto xmit;
+ return true;
tags++;
@@ -2834,7 +2819,7 @@ static void bond_arp_send(struct slave *slave, int arp_op, __be32 dest_ip,
tags->vlan_id);
if (!skb) {
net_err_ratelimited("failed to insert inner VLAN tag\n");
- return;
+ return false;
}
tags++;
@@ -2847,8 +2832,34 @@ static void bond_arp_send(struct slave *slave, int arp_op, __be32 dest_ip,
outer_tag->vlan_id);
}
-xmit:
- arp_xmit(skb);
+ return true;
+}
+
+/* We go to the (large) trouble of VLAN tagging ARP frames because
+ * switches in VLAN mode (especially if ports are configured as
+ * "native" to a VLAN) might not pass non-tagged frames.
+ */
+static void bond_arp_send(struct slave *slave, int arp_op, __be32 dest_ip,
+ __be32 src_ip, struct bond_vlan_tag *tags)
+{
+ struct net_device *bond_dev = slave->bond->dev;
+ struct net_device *slave_dev = slave->dev;
+ struct sk_buff *skb;
+
+ slave_dbg(bond_dev, slave_dev, "arp %d on slave: dst %pI4 src %pI4\n",
+ arp_op, &dest_ip, &src_ip);
+
+ skb = arp_create(arp_op, ETH_P_ARP, dest_ip, slave_dev, src_ip,
+ NULL, slave_dev->dev_addr, NULL);
+
+ if (!skb) {
+ net_err_ratelimited("ARP packet allocation failed\n");
+ return;
+ }
+
+ if (bond_handle_vlan(slave, tags, skb))
+ arp_xmit(skb);
+ return;
}
/* Validate the device path between the @start_dev and the @end_dev.
@@ -2965,30 +2976,17 @@ static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32
slave->target_last_arp_rx[i] = jiffies;
}
-int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
- struct slave *slave)
+static int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
+ struct slave *slave)
{
struct arphdr *arp = (struct arphdr *)skb->data;
struct slave *curr_active_slave, *curr_arp_slave;
unsigned char *arp_ptr;
__be32 sip, tip;
- int is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP);
unsigned int alen;
- if (!slave_do_arp_validate(bond, slave)) {
- if ((slave_do_arp_validate_only(bond) && is_arp) ||
- !slave_do_arp_validate_only(bond))
- slave->last_rx = jiffies;
- return RX_HANDLER_ANOTHER;
- } else if (!is_arp) {
- return RX_HANDLER_ANOTHER;
- }
-
alen = arp_hdr_len(bond->dev);
- slave_dbg(bond->dev, slave->dev, "%s: skb->dev %s\n",
- __func__, skb->dev->name);
-
if (alen > skb_headlen(skb)) {
arp = kmalloc(alen, GFP_ATOMIC);
if (!arp)
@@ -3059,6 +3057,216 @@ out_unlock:
return RX_HANDLER_ANOTHER;
}
+#if IS_ENABLED(CONFIG_IPV6)
+static void bond_ns_send(struct slave *slave, const struct in6_addr *daddr,
+ const struct in6_addr *saddr, struct bond_vlan_tag *tags)
+{
+ struct net_device *bond_dev = slave->bond->dev;
+ struct net_device *slave_dev = slave->dev;
+ struct in6_addr mcaddr;
+ struct sk_buff *skb;
+
+ slave_dbg(bond_dev, slave_dev, "NS on slave: dst %pI6c src %pI6c\n",
+ daddr, saddr);
+
+ skb = ndisc_ns_create(slave_dev, daddr, saddr, 0);
+ if (!skb) {
+ net_err_ratelimited("NS packet allocation failed\n");
+ return;
+ }
+
+ addrconf_addr_solict_mult(daddr, &mcaddr);
+ if (bond_handle_vlan(slave, tags, skb))
+ ndisc_send_skb(skb, &mcaddr, saddr);
+}
+
+static void bond_ns_send_all(struct bonding *bond, struct slave *slave)
+{
+ struct in6_addr *targets = bond->params.ns_targets;
+ struct bond_vlan_tag *tags;
+ struct dst_entry *dst;
+ struct in6_addr saddr;
+ struct flowi6 fl6;
+ int i;
+
+ for (i = 0; i < BOND_MAX_NS_TARGETS && !ipv6_addr_any(&targets[i]); i++) {
+ slave_dbg(bond->dev, slave->dev, "%s: target %pI6c\n",
+ __func__, &targets[i]);
+ tags = NULL;
+
+ /* Find out through which dev should the packet go */
+ memset(&fl6, 0, sizeof(struct flowi6));
+ fl6.daddr = targets[i];
+ fl6.flowi6_oif = bond->dev->ifindex;
+
+ dst = ip6_route_output(dev_net(bond->dev), NULL, &fl6);
+ if (dst->error) {
+ dst_release(dst);
+ /* there's no route to target - try to send arp
+ * probe to generate any traffic (arp_validate=0)
+ */
+ if (bond->params.arp_validate)
+ pr_warn_once("%s: no route to ns_ip6_target %pI6c and arp_validate is set\n",
+ bond->dev->name,
+ &targets[i]);
+ bond_ns_send(slave, &targets[i], &in6addr_any, tags);
+ continue;
+ }
+
+ /* bond device itself */
+ if (dst->dev == bond->dev)
+ goto found;
+
+ rcu_read_lock();
+ tags = bond_verify_device_path(bond->dev, dst->dev, 0);
+ rcu_read_unlock();
+
+ if (!IS_ERR_OR_NULL(tags))
+ goto found;
+
+ /* Not our device - skip */
+ slave_dbg(bond->dev, slave->dev, "no path to ns_ip6_target %pI6c via dst->dev %s\n",
+ &targets[i], dst->dev ? dst->dev->name : "NULL");
+
+ dst_release(dst);
+ continue;
+
+found:
+ if (!ipv6_dev_get_saddr(dev_net(dst->dev), dst->dev, &targets[i], 0, &saddr))
+ bond_ns_send(slave, &targets[i], &saddr, tags);
+ dst_release(dst);
+ kfree(tags);
+ }
+}
+
+static int bond_confirm_addr6(struct net_device *dev,
+ struct netdev_nested_priv *priv)
+{
+ struct in6_addr *addr = (struct in6_addr *)priv->data;
+
+ return ipv6_chk_addr(dev_net(dev), addr, dev, 0);
+}
+
+static bool bond_has_this_ip6(struct bonding *bond, struct in6_addr *addr)
+{
+ struct netdev_nested_priv priv = {
+ .data = addr,
+ };
+ int ret = false;
+
+ if (bond_confirm_addr6(bond->dev, &priv))
+ return true;
+
+ rcu_read_lock();
+ if (netdev_walk_all_upper_dev_rcu(bond->dev, bond_confirm_addr6, &priv))
+ ret = true;
+ rcu_read_unlock();
+
+ return ret;
+}
+
+static void bond_validate_ns(struct bonding *bond, struct slave *slave,
+ struct in6_addr *saddr, struct in6_addr *daddr)
+{
+ int i;
+
+ if (ipv6_addr_any(saddr) || !bond_has_this_ip6(bond, daddr)) {
+ slave_dbg(bond->dev, slave->dev, "%s: sip %pI6c tip %pI6c not found\n",
+ __func__, saddr, daddr);
+ return;
+ }
+
+ i = bond_get_targets_ip6(bond->params.ns_targets, saddr);
+ if (i == -1) {
+ slave_dbg(bond->dev, slave->dev, "%s: sip %pI6c not found in targets\n",
+ __func__, saddr);
+ return;
+ }
+ slave->last_rx = jiffies;
+ slave->target_last_arp_rx[i] = jiffies;
+}
+
+static int bond_na_rcv(const struct sk_buff *skb, struct bonding *bond,
+ struct slave *slave)
+{
+ struct slave *curr_active_slave, *curr_arp_slave;
+ struct icmp6hdr *hdr = icmp6_hdr(skb);
+ struct in6_addr *saddr, *daddr;
+
+ if (skb->pkt_type == PACKET_OTHERHOST ||
+ skb->pkt_type == PACKET_LOOPBACK ||
+ hdr->icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT)
+ goto out;
+
+ saddr = &ipv6_hdr(skb)->saddr;
+ daddr = &ipv6_hdr(skb)->daddr;
+
+ slave_dbg(bond->dev, slave->dev, "%s: %s/%d av %d sv %d sip %pI6c tip %pI6c\n",
+ __func__, slave->dev->name, bond_slave_state(slave),
+ bond->params.arp_validate, slave_do_arp_validate(bond, slave),
+ saddr, daddr);
+
+ curr_active_slave = rcu_dereference(bond->curr_active_slave);
+ curr_arp_slave = rcu_dereference(bond->current_arp_slave);
+
+ /* We 'trust' the received ARP enough to validate it if:
+ * see bond_arp_rcv().
+ */
+ if (bond_is_active_slave(slave))
+ bond_validate_ns(bond, slave, saddr, daddr);
+ else if (curr_active_slave &&
+ time_after(slave_last_rx(bond, curr_active_slave),
+ curr_active_slave->last_link_up))
+ bond_validate_ns(bond, slave, saddr, daddr);
+ else if (curr_arp_slave &&
+ bond_time_in_interval(bond,
+ dev_trans_start(curr_arp_slave->dev), 1))
+ bond_validate_ns(bond, slave, saddr, daddr);
+
+out:
+ return RX_HANDLER_ANOTHER;
+}
+#endif
+
+int bond_rcv_validate(const struct sk_buff *skb, struct bonding *bond,
+ struct slave *slave)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+ bool is_ipv6 = skb->protocol == __cpu_to_be16(ETH_P_IPV6);
+#endif
+ bool is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP);
+
+ slave_dbg(bond->dev, slave->dev, "%s: skb->dev %s\n",
+ __func__, skb->dev->name);
+
+ /* Use arp validate logic for both ARP and NS */
+ if (!slave_do_arp_validate(bond, slave)) {
+ if ((slave_do_arp_validate_only(bond) && is_arp) ||
+#if IS_ENABLED(CONFIG_IPV6)
+ (slave_do_arp_validate_only(bond) && is_ipv6) ||
+#endif
+ !slave_do_arp_validate_only(bond))
+ slave->last_rx = jiffies;
+ return RX_HANDLER_ANOTHER;
+ } else if (is_arp) {
+ return bond_arp_rcv(skb, bond, slave);
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (is_ipv6) {
+ return bond_na_rcv(skb, bond, slave);
+#endif
+ } else {
+ return RX_HANDLER_ANOTHER;
+ }
+}
+
+static void bond_send_validate(struct bonding *bond, struct slave *slave)
+{
+ bond_arp_send_all(bond, slave);
+#if IS_ENABLED(CONFIG_IPV6)
+ bond_ns_send_all(bond, slave);
+#endif
+}
+
/* function to verify if we're in the arp_interval timeslice, returns true if
* (last_act - arp_interval) <= jiffies <= (last_act + mod * arp_interval +
* arp_interval/2) . the arp_interval/2 is needed for really fast networks.
@@ -3154,7 +3362,7 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
* to be unstable during low/no traffic periods
*/
if (bond_slave_is_up(slave))
- bond_arp_send_all(bond, slave);
+ bond_send_validate(bond, slave);
}
rcu_read_unlock();
@@ -3368,7 +3576,7 @@ static bool bond_ab_arp_probe(struct bonding *bond)
curr_active_slave->dev->name);
if (curr_active_slave) {
- bond_arp_send_all(bond, curr_active_slave);
+ bond_send_validate(bond, curr_active_slave);
return should_notify_rtnl;
}
@@ -3420,7 +3628,7 @@ static bool bond_ab_arp_probe(struct bonding *bond)
bond_set_slave_link_state(new_slave, BOND_LINK_BACK,
BOND_SLAVE_NOTIFY_LATER);
bond_set_slave_active_flags(new_slave, BOND_SLAVE_NOTIFY_LATER);
- bond_arp_send_all(bond, new_slave);
+ bond_send_validate(bond, new_slave);
new_slave->last_link_up = jiffies;
rcu_assign_pointer(bond->current_arp_slave, new_slave);
@@ -3956,7 +4164,7 @@ static int bond_open(struct net_device *bond_dev)
if (bond->params.arp_interval) { /* arp interval, in milliseconds. */
queue_delayed_work(bond->wq, &bond->arp_work, 0);
- bond->recv_probe = bond_arp_rcv;
+ bond->recv_probe = bond_rcv_validate;
}
if (BOND_MODE(bond) == BOND_MODE_8023AD) {
@@ -4912,7 +5120,7 @@ static netdev_tx_t bond_xmit_broadcast(struct sk_buff *skb,
if (xmit_suc)
return NETDEV_TX_OK;
- atomic_long_inc(&bond_dev->tx_dropped);
+ dev_core_stats_tx_dropped_inc(bond_dev);
return NET_XMIT_DROP;
}
@@ -5937,6 +6145,7 @@ static int bond_check_params(struct bond_params *params)
strscpy_pad(params->primary, primary, sizeof(params->primary));
memcpy(params->arp_targets, arp_target, sizeof(arp_target));
+ memset(params->ns_targets, 0, sizeof(struct in6_addr) * BOND_MAX_NS_TARGETS);
return 0;
}
@@ -6047,27 +6256,38 @@ static int __net_init bond_net_init(struct net *net)
return 0;
}
-static void __net_exit bond_net_exit(struct net *net)
+static void __net_exit bond_net_exit_batch(struct list_head *net_list)
{
- struct bond_net *bn = net_generic(net, bond_net_id);
- struct bonding *bond, *tmp_bond;
+ struct bond_net *bn;
+ struct net *net;
LIST_HEAD(list);
- bond_destroy_sysfs(bn);
+ list_for_each_entry(net, net_list, exit_list) {
+ bn = net_generic(net, bond_net_id);
+ bond_destroy_sysfs(bn);
+ }
/* Kill off any bonds created after unregistering bond rtnl ops */
rtnl_lock();
- list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list)
- unregister_netdevice_queue(bond->dev, &list);
+ list_for_each_entry(net, net_list, exit_list) {
+ struct bonding *bond, *tmp_bond;
+
+ bn = net_generic(net, bond_net_id);
+ list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list)
+ unregister_netdevice_queue(bond->dev, &list);
+ }
unregister_netdevice_many(&list);
rtnl_unlock();
- bond_destroy_proc_dir(bn);
+ list_for_each_entry(net, net_list, exit_list) {
+ bn = net_generic(net, bond_net_id);
+ bond_destroy_proc_dir(bn);
+ }
}
static struct pernet_operations bond_net_ops = {
.init = bond_net_init,
- .exit = bond_net_exit,
+ .exit_batch = bond_net_exit_batch,
.id = &bond_net_id,
.size = sizeof(struct bond_net),
};