Commit 45ebcce5 authored by Elad Raz's avatar Elad Raz Committed by David S. Miller

bridge: mdb: Marking port-group as offloaded

There is a race-condition when updating the mdb offload flag without using
the mulicast_lock. This reverts commit 9e8430f8 ("bridge: mdb:
Passing the port-group pointer to br_mdb module").

This patch marks offloaded MDB entry as "offload" by changing the port-
group flags and marks it as MDB_PG_FLAGS_OFFLOAD.

When switchdev PORT_MDB succeeded and adds a multicast group, a completion
callback is been invoked "br_mdb_complete". The completion function
locks the multicast_lock and finds the right net_bridge_port_group and
marks it as offloaded.

Fixes: 9e8430f8 ("bridge: mdb: Passing the port-group pointer to br_mdb module")
Reported-by: default avatarNikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: default avatarElad Raz <eladr@mellanox.com>
Signed-off-by: default avatarJiri Pirko <jiri@mellanox.com>
Reviewed-by: default avatarIdo Schimmel <idosch@mellanox.com>
Acked-by: default avatarNikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 6dd684c0
...@@ -256,9 +256,45 @@ static inline size_t rtnl_mdb_nlmsg_size(void) ...@@ -256,9 +256,45 @@ static inline size_t rtnl_mdb_nlmsg_size(void)
+ nla_total_size(sizeof(struct br_mdb_entry)); + nla_total_size(sizeof(struct br_mdb_entry));
} }
static void __br_mdb_notify(struct net_device *dev, struct br_mdb_entry *entry, struct br_mdb_complete_info {
int type, struct net_bridge_port_group *pg) struct net_bridge_port *port;
struct br_ip ip;
};
static void br_mdb_complete(struct net_device *dev, int err, void *priv)
{
struct br_mdb_complete_info *data = priv;
struct net_bridge_port_group __rcu **pp;
struct net_bridge_port_group *p;
struct net_bridge_mdb_htable *mdb;
struct net_bridge_mdb_entry *mp;
struct net_bridge_port *port = data->port;
struct net_bridge *br = port->br;
if (err)
goto err;
spin_lock_bh(&br->multicast_lock);
mdb = mlock_dereference(br->mdb, br);
mp = br_mdb_ip_get(mdb, &data->ip);
if (!mp)
goto out;
for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL;
pp = &p->next) {
if (p->port != port)
continue;
p->flags |= MDB_PG_FLAGS_OFFLOAD;
}
out:
spin_unlock_bh(&br->multicast_lock);
err:
kfree(priv);
}
static void __br_mdb_notify(struct net_device *dev, struct net_bridge_port *p,
struct br_mdb_entry *entry, int type)
{ {
struct br_mdb_complete_info *complete_info;
struct switchdev_obj_port_mdb mdb = { struct switchdev_obj_port_mdb mdb = {
.obj = { .obj = {
.id = SWITCHDEV_OBJ_ID_PORT_MDB, .id = SWITCHDEV_OBJ_ID_PORT_MDB,
...@@ -281,9 +317,14 @@ static void __br_mdb_notify(struct net_device *dev, struct br_mdb_entry *entry, ...@@ -281,9 +317,14 @@ static void __br_mdb_notify(struct net_device *dev, struct br_mdb_entry *entry,
mdb.obj.orig_dev = port_dev; mdb.obj.orig_dev = port_dev;
if (port_dev && type == RTM_NEWMDB) { if (port_dev && type == RTM_NEWMDB) {
err = switchdev_port_obj_add(port_dev, &mdb.obj); complete_info = kmalloc(sizeof(*complete_info), GFP_ATOMIC);
if (!err && pg) if (complete_info) {
pg->flags |= MDB_PG_FLAGS_OFFLOAD; complete_info->port = p;
__mdb_entry_to_br_ip(entry, &complete_info->ip);
mdb.obj.complete_priv = complete_info;
mdb.obj.complete = br_mdb_complete;
switchdev_port_obj_add(port_dev, &mdb.obj);
}
} else if (port_dev && type == RTM_DELMDB) { } else if (port_dev && type == RTM_DELMDB) {
switchdev_port_obj_del(port_dev, &mdb.obj); switchdev_port_obj_del(port_dev, &mdb.obj);
} }
...@@ -304,21 +345,21 @@ static void __br_mdb_notify(struct net_device *dev, struct br_mdb_entry *entry, ...@@ -304,21 +345,21 @@ static void __br_mdb_notify(struct net_device *dev, struct br_mdb_entry *entry,
rtnl_set_sk_err(net, RTNLGRP_MDB, err); rtnl_set_sk_err(net, RTNLGRP_MDB, err);
} }
void br_mdb_notify(struct net_device *dev, struct net_bridge_port_group *pg, void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port,
int type) struct br_ip *group, int type, u8 flags)
{ {
struct br_mdb_entry entry; struct br_mdb_entry entry;
memset(&entry, 0, sizeof(entry)); memset(&entry, 0, sizeof(entry));
entry.ifindex = pg->port->dev->ifindex; entry.ifindex = port->dev->ifindex;
entry.addr.proto = pg->addr.proto; entry.addr.proto = group->proto;
entry.addr.u.ip4 = pg->addr.u.ip4; entry.addr.u.ip4 = group->u.ip4;
#if IS_ENABLED(CONFIG_IPV6) #if IS_ENABLED(CONFIG_IPV6)
entry.addr.u.ip6 = pg->addr.u.ip6; entry.addr.u.ip6 = group->u.ip6;
#endif #endif
entry.vid = pg->addr.vid; entry.vid = group->vid;
__mdb_entry_fill_flags(&entry, pg->flags); __mdb_entry_fill_flags(&entry, flags);
__br_mdb_notify(dev, &entry, type, pg); __br_mdb_notify(dev, port, &entry, type);
} }
static int nlmsg_populate_rtr_fill(struct sk_buff *skb, static int nlmsg_populate_rtr_fill(struct sk_buff *skb,
...@@ -463,8 +504,7 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh, ...@@ -463,8 +504,7 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh,
} }
static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
struct br_ip *group, unsigned char state, struct br_ip *group, unsigned char state)
struct net_bridge_port_group **pg)
{ {
struct net_bridge_mdb_entry *mp; struct net_bridge_mdb_entry *mp;
struct net_bridge_port_group *p; struct net_bridge_port_group *p;
...@@ -495,7 +535,6 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, ...@@ -495,7 +535,6 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
if (unlikely(!p)) if (unlikely(!p))
return -ENOMEM; return -ENOMEM;
rcu_assign_pointer(*pp, p); rcu_assign_pointer(*pp, p);
*pg = p;
if (state == MDB_TEMPORARY) if (state == MDB_TEMPORARY)
mod_timer(&p->timer, now + br->multicast_membership_interval); mod_timer(&p->timer, now + br->multicast_membership_interval);
...@@ -503,8 +542,7 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, ...@@ -503,8 +542,7 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
} }
static int __br_mdb_add(struct net *net, struct net_bridge *br, static int __br_mdb_add(struct net *net, struct net_bridge *br,
struct br_mdb_entry *entry, struct br_mdb_entry *entry)
struct net_bridge_port_group **pg)
{ {
struct br_ip ip; struct br_ip ip;
struct net_device *dev; struct net_device *dev;
...@@ -525,7 +563,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, ...@@ -525,7 +563,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br,
__mdb_entry_to_br_ip(entry, &ip); __mdb_entry_to_br_ip(entry, &ip);
spin_lock_bh(&br->multicast_lock); spin_lock_bh(&br->multicast_lock);
ret = br_mdb_add_group(br, p, &ip, entry->state, pg); ret = br_mdb_add_group(br, p, &ip, entry->state);
spin_unlock_bh(&br->multicast_lock); spin_unlock_bh(&br->multicast_lock);
return ret; return ret;
} }
...@@ -533,7 +571,6 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, ...@@ -533,7 +571,6 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br,
static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
{ {
struct net *net = sock_net(skb->sk); struct net *net = sock_net(skb->sk);
struct net_bridge_port_group *pg;
struct net_bridge_vlan_group *vg; struct net_bridge_vlan_group *vg;
struct net_device *dev, *pdev; struct net_device *dev, *pdev;
struct br_mdb_entry *entry; struct br_mdb_entry *entry;
...@@ -563,15 +600,15 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) ...@@ -563,15 +600,15 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
if (br_vlan_enabled(br) && vg && entry->vid == 0) { if (br_vlan_enabled(br) && vg && entry->vid == 0) {
list_for_each_entry(v, &vg->vlan_list, vlist) { list_for_each_entry(v, &vg->vlan_list, vlist) {
entry->vid = v->vid; entry->vid = v->vid;
err = __br_mdb_add(net, br, entry, &pg); err = __br_mdb_add(net, br, entry);
if (err) if (err)
break; break;
__br_mdb_notify(dev, entry, RTM_NEWMDB, pg); __br_mdb_notify(dev, p, entry, RTM_NEWMDB);
} }
} else { } else {
err = __br_mdb_add(net, br, entry, &pg); err = __br_mdb_add(net, br, entry);
if (!err) if (!err)
__br_mdb_notify(dev, entry, RTM_NEWMDB, pg); __br_mdb_notify(dev, p, entry, RTM_NEWMDB);
} }
return err; return err;
...@@ -659,12 +696,12 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) ...@@ -659,12 +696,12 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
entry->vid = v->vid; entry->vid = v->vid;
err = __br_mdb_del(br, entry); err = __br_mdb_del(br, entry);
if (!err) if (!err)
__br_mdb_notify(dev, entry, RTM_DELMDB, NULL); __br_mdb_notify(dev, p, entry, RTM_DELMDB);
} }
} else { } else {
err = __br_mdb_del(br, entry); err = __br_mdb_del(br, entry);
if (!err) if (!err)
__br_mdb_notify(dev, entry, RTM_DELMDB, NULL); __br_mdb_notify(dev, p, entry, RTM_DELMDB);
} }
return err; return err;
......
...@@ -283,7 +283,8 @@ static void br_multicast_del_pg(struct net_bridge *br, ...@@ -283,7 +283,8 @@ static void br_multicast_del_pg(struct net_bridge *br,
rcu_assign_pointer(*pp, p->next); rcu_assign_pointer(*pp, p->next);
hlist_del_init(&p->mglist); hlist_del_init(&p->mglist);
del_timer(&p->timer); del_timer(&p->timer);
br_mdb_notify(br->dev, p, RTM_DELMDB); br_mdb_notify(br->dev, p->port, &pg->addr, RTM_DELMDB,
p->flags);
call_rcu_bh(&p->rcu, br_multicast_free_pg); call_rcu_bh(&p->rcu, br_multicast_free_pg);
if (!mp->ports && !mp->mglist && if (!mp->ports && !mp->mglist &&
...@@ -705,7 +706,7 @@ static int br_multicast_add_group(struct net_bridge *br, ...@@ -705,7 +706,7 @@ static int br_multicast_add_group(struct net_bridge *br,
if (unlikely(!p)) if (unlikely(!p))
goto err; goto err;
rcu_assign_pointer(*pp, p); rcu_assign_pointer(*pp, p);
br_mdb_notify(br->dev, p, RTM_NEWMDB); br_mdb_notify(br->dev, port, group, RTM_NEWMDB, 0);
found: found:
mod_timer(&p->timer, now + br->multicast_membership_interval); mod_timer(&p->timer, now + br->multicast_membership_interval);
...@@ -1461,7 +1462,8 @@ br_multicast_leave_group(struct net_bridge *br, ...@@ -1461,7 +1462,8 @@ br_multicast_leave_group(struct net_bridge *br,
hlist_del_init(&p->mglist); hlist_del_init(&p->mglist);
del_timer(&p->timer); del_timer(&p->timer);
call_rcu_bh(&p->rcu, br_multicast_free_pg); call_rcu_bh(&p->rcu, br_multicast_free_pg);
br_mdb_notify(br->dev, p, RTM_DELMDB); br_mdb_notify(br->dev, port, group, RTM_DELMDB,
p->flags);
if (!mp->ports && !mp->mglist && if (!mp->ports && !mp->mglist &&
netif_running(br->dev)) netif_running(br->dev))
......
...@@ -560,8 +560,8 @@ br_multicast_new_port_group(struct net_bridge_port *port, struct br_ip *group, ...@@ -560,8 +560,8 @@ br_multicast_new_port_group(struct net_bridge_port *port, struct br_ip *group,
unsigned char flags); unsigned char flags);
void br_mdb_init(void); void br_mdb_init(void);
void br_mdb_uninit(void); void br_mdb_uninit(void);
void br_mdb_notify(struct net_device *dev, struct net_bridge_port_group *pg, void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port,
int type); struct br_ip *group, int type, u8 flags);
void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port, void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port,
int type); int type);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment