linux/net/bridge/br_mdb.c

647 lines
15 KiB
C
Raw Normal View History

#include <linux/err.h>
#include <linux/igmp.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/rculist.h>
#include <linux/skbuff.h>
#include <linux/if_ether.h>
#include <net/ip.h>
#include <net/netlink.h>
#include <net/switchdev.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#include <net/addrconf.h>
#endif
#include "br_private.h"
static int br_rports_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
struct net_bridge_port *p;
struct nlattr *nest;
if (!br->multicast_router || hlist_empty(&br->router_list))
return 0;
nest = nla_nest_start(skb, MDBA_ROUTER);
if (nest == NULL)
return -EMSGSIZE;
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
hlist_for_each_entry_rcu(p, &br->router_list, rlist) {
if (p && nla_put_u32(skb, MDBA_ROUTER_PORT, p->dev->ifindex))
goto fail;
}
nla_nest_end(skb, nest);
return 0;
fail:
nla_nest_cancel(skb, nest);
return -EMSGSIZE;
}
static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
struct net_bridge_mdb_htable *mdb;
struct nlattr *nest, *nest2;
int i, err = 0;
int idx = 0, s_idx = cb->args[1];
if (br->multicast_disabled)
return 0;
mdb = rcu_dereference(br->mdb);
if (!mdb)
return 0;
nest = nla_nest_start(skb, MDBA_MDB);
if (nest == NULL)
return -EMSGSIZE;
for (i = 0; i < mdb->max; i++) {
struct net_bridge_mdb_entry *mp;
struct net_bridge_port_group *p;
struct net_bridge_port_group __rcu **pp;
struct net_bridge_port *port;
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
hlist_for_each_entry_rcu(mp, &mdb->mhash[i], hlist[mdb->ver]) {
if (idx < s_idx)
goto skip;
nest2 = nla_nest_start(skb, MDBA_MDB_ENTRY);
if (nest2 == NULL) {
err = -EMSGSIZE;
goto out;
}
for (pp = &mp->ports;
(p = rcu_dereference(*pp)) != NULL;
pp = &p->next) {
port = p->port;
if (port) {
struct br_mdb_entry e;
memset(&e, 0, sizeof(e));
e.ifindex = port->dev->ifindex;
e.state = p->state;
e.vid = p->addr.vid;
if (p->addr.proto == htons(ETH_P_IP))
e.addr.u.ip4 = p->addr.u.ip4;
#if IS_ENABLED(CONFIG_IPV6)
if (p->addr.proto == htons(ETH_P_IPV6))
e.addr.u.ip6 = p->addr.u.ip6;
#endif
e.addr.proto = p->addr.proto;
if (nla_put(skb, MDBA_MDB_ENTRY_INFO, sizeof(e), &e)) {
nla_nest_cancel(skb, nest2);
err = -EMSGSIZE;
goto out;
}
}
}
nla_nest_end(skb, nest2);
skip:
idx++;
}
}
out:
cb->args[1] = idx;
nla_nest_end(skb, nest);
return err;
}
static int br_mdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net_device *dev;
struct net *net = sock_net(skb->sk);
struct nlmsghdr *nlh = NULL;
int idx = 0, s_idx;
s_idx = cb->args[0];
rcu_read_lock();
/* In theory this could be wrapped to 0... */
cb->seq = net->dev_base_seq + br_mdb_rehash_seq;
for_each_netdev_rcu(net, dev) {
if (dev->priv_flags & IFF_EBRIDGE) {
struct br_port_msg *bpm;
if (idx < s_idx)
goto skip;
nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, RTM_GETMDB,
sizeof(*bpm), NLM_F_MULTI);
if (nlh == NULL)
break;
bpm = nlmsg_data(nlh);
memset(bpm, 0, sizeof(*bpm));
bpm->ifindex = dev->ifindex;
if (br_mdb_fill_info(skb, cb, dev) < 0)
goto out;
if (br_rports_fill_info(skb, cb, dev) < 0)
goto out;
cb->args[1] = 0;
nlmsg_end(skb, nlh);
skip:
idx++;
}
}
out:
if (nlh)
nlmsg_end(skb, nlh);
rcu_read_unlock();
cb->args[0] = idx;
return skb->len;
}
static int nlmsg_populate_mdb_fill(struct sk_buff *skb,
struct net_device *dev,
struct br_mdb_entry *entry, u32 pid,
u32 seq, int type, unsigned int flags)
{
struct nlmsghdr *nlh;
struct br_port_msg *bpm;
struct nlattr *nest, *nest2;
nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), 0);
if (!nlh)
return -EMSGSIZE;
bpm = nlmsg_data(nlh);
memset(bpm, 0, sizeof(*bpm));
bpm->family = AF_BRIDGE;
bpm->ifindex = dev->ifindex;
nest = nla_nest_start(skb, MDBA_MDB);
if (nest == NULL)
goto cancel;
nest2 = nla_nest_start(skb, MDBA_MDB_ENTRY);
if (nest2 == NULL)
goto end;
if (nla_put(skb, MDBA_MDB_ENTRY_INFO, sizeof(*entry), entry))
goto end;
nla_nest_end(skb, nest2);
nla_nest_end(skb, nest);
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-16 21:09:00 +00:00
nlmsg_end(skb, nlh);
return 0;
end:
nla_nest_end(skb, nest);
cancel:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
static inline size_t rtnl_mdb_nlmsg_size(void)
{
return NLMSG_ALIGN(sizeof(struct br_port_msg))
+ nla_total_size(sizeof(struct br_mdb_entry));
}
static void __br_mdb_notify(struct net_device *dev, struct br_mdb_entry *entry,
int type)
{
struct switchdev_obj_port_mdb mdb = {
.obj = {
.id = SWITCHDEV_OBJ_ID_PORT_MDB,
.flags = SWITCHDEV_F_DEFER,
},
.vid = entry->vid,
};
struct net_device *port_dev;
struct net *net = dev_net(dev);
struct sk_buff *skb;
int err = -ENOBUFS;
port_dev = __dev_get_by_index(net, entry->ifindex);
if (entry->addr.proto == htons(ETH_P_IP))
ip_eth_mc_map(entry->addr.u.ip4, mdb.addr);
#if IS_ENABLED(CONFIG_IPV6)
else
ipv6_eth_mc_map(&entry->addr.u.ip6, mdb.addr);
#endif
mdb.obj.orig_dev = port_dev;
if (port_dev && type == RTM_NEWMDB)
switchdev_port_obj_add(port_dev, &mdb.obj);
else if (port_dev && type == RTM_DELMDB)
switchdev_port_obj_del(port_dev, &mdb.obj);
skb = nlmsg_new(rtnl_mdb_nlmsg_size(), GFP_ATOMIC);
if (!skb)
goto errout;
err = nlmsg_populate_mdb_fill(skb, dev, entry, 0, 0, type, NTF_SELF);
if (err < 0) {
kfree_skb(skb);
goto errout;
}
rtnl_notify(skb, net, 0, RTNLGRP_MDB, NULL, GFP_ATOMIC);
return;
errout:
rtnl_set_sk_err(net, RTNLGRP_MDB, err);
}
void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port,
struct br_ip *group, int type, u8 state)
{
struct br_mdb_entry entry;
memset(&entry, 0, sizeof(entry));
entry.ifindex = port->dev->ifindex;
entry.addr.proto = group->proto;
entry.addr.u.ip4 = group->u.ip4;
#if IS_ENABLED(CONFIG_IPV6)
entry.addr.u.ip6 = group->u.ip6;
#endif
entry.state = state;
entry.vid = group->vid;
__br_mdb_notify(dev, &entry, type);
}
static int nlmsg_populate_rtr_fill(struct sk_buff *skb,
struct net_device *dev,
int ifindex, u32 pid,
u32 seq, int type, unsigned int flags)
{
struct br_port_msg *bpm;
struct nlmsghdr *nlh;
struct nlattr *nest;
nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), NLM_F_MULTI);
if (!nlh)
return -EMSGSIZE;
bpm = nlmsg_data(nlh);
memset(bpm, 0, sizeof(*bpm));
bpm->family = AF_BRIDGE;
bpm->ifindex = dev->ifindex;
nest = nla_nest_start(skb, MDBA_ROUTER);
if (!nest)
goto cancel;
if (nla_put_u32(skb, MDBA_ROUTER_PORT, ifindex))
goto end;
nla_nest_end(skb, nest);
nlmsg_end(skb, nlh);
return 0;
end:
nla_nest_end(skb, nest);
cancel:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
static inline size_t rtnl_rtr_nlmsg_size(void)
{
return NLMSG_ALIGN(sizeof(struct br_port_msg))
+ nla_total_size(sizeof(__u32));
}
void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port,
int type)
{
struct net *net = dev_net(dev);
struct sk_buff *skb;
int err = -ENOBUFS;
int ifindex;
ifindex = port ? port->dev->ifindex : 0;
skb = nlmsg_new(rtnl_rtr_nlmsg_size(), GFP_ATOMIC);
if (!skb)
goto errout;
err = nlmsg_populate_rtr_fill(skb, dev, ifindex, 0, 0, type, NTF_SELF);
if (err < 0) {
kfree_skb(skb);
goto errout;
}
rtnl_notify(skb, net, 0, RTNLGRP_MDB, NULL, GFP_ATOMIC);
return;
errout:
rtnl_set_sk_err(net, RTNLGRP_MDB, err);
}
static bool is_valid_mdb_entry(struct br_mdb_entry *entry)
{
if (entry->ifindex == 0)
return false;
if (entry->addr.proto == htons(ETH_P_IP)) {
if (!ipv4_is_multicast(entry->addr.u.ip4))
return false;
if (ipv4_is_local_multicast(entry->addr.u.ip4))
return false;
#if IS_ENABLED(CONFIG_IPV6)
} else if (entry->addr.proto == htons(ETH_P_IPV6)) {
if (ipv6_addr_is_ll_all_nodes(&entry->addr.u.ip6))
return false;
#endif
} else
return false;
if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY)
return false;
if (entry->vid >= VLAN_VID_MASK)
return false;
return true;
}
static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh,
struct net_device **pdev, struct br_mdb_entry **pentry)
{
struct net *net = sock_net(skb->sk);
struct br_mdb_entry *entry;
struct br_port_msg *bpm;
struct nlattr *tb[MDBA_SET_ENTRY_MAX+1];
struct net_device *dev;
int err;
err = nlmsg_parse(nlh, sizeof(*bpm), tb, MDBA_SET_ENTRY_MAX, NULL);
if (err < 0)
return err;
bpm = nlmsg_data(nlh);
if (bpm->ifindex == 0) {
pr_info("PF_BRIDGE: br_mdb_parse() with invalid ifindex\n");
return -EINVAL;
}
dev = __dev_get_by_index(net, bpm->ifindex);
if (dev == NULL) {
pr_info("PF_BRIDGE: br_mdb_parse() with unknown ifindex\n");
return -ENODEV;
}
if (!(dev->priv_flags & IFF_EBRIDGE)) {
pr_info("PF_BRIDGE: br_mdb_parse() with non-bridge\n");
return -EOPNOTSUPP;
}
*pdev = dev;
if (!tb[MDBA_SET_ENTRY] ||
nla_len(tb[MDBA_SET_ENTRY]) != sizeof(struct br_mdb_entry)) {
pr_info("PF_BRIDGE: br_mdb_parse() with invalid attr\n");
return -EINVAL;
}
entry = nla_data(tb[MDBA_SET_ENTRY]);
if (!is_valid_mdb_entry(entry)) {
pr_info("PF_BRIDGE: br_mdb_parse() with invalid entry\n");
return -EINVAL;
}
*pentry = entry;
return 0;
}
static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
struct br_ip *group, unsigned char state)
{
struct net_bridge_mdb_entry *mp;
struct net_bridge_port_group *p;
struct net_bridge_port_group __rcu **pp;
struct net_bridge_mdb_htable *mdb;
unsigned long now = jiffies;
int err;
mdb = mlock_dereference(br->mdb, br);
mp = br_mdb_ip_get(mdb, group);
if (!mp) {
mp = br_multicast_new_group(br, port, group);
err = PTR_ERR(mp);
if (IS_ERR(mp))
return err;
}
for (pp = &mp->ports;
(p = mlock_dereference(*pp, br)) != NULL;
pp = &p->next) {
if (p->port == port)
return -EEXIST;
if ((unsigned long)p->port < (unsigned long)port)
break;
}
p = br_multicast_new_port_group(port, group, *pp, state);
if (unlikely(!p))
return -ENOMEM;
rcu_assign_pointer(*pp, p);
if (state == MDB_TEMPORARY)
mod_timer(&p->timer, now + br->multicast_membership_interval);
return 0;
}
static int __br_mdb_add(struct net *net, struct net_bridge *br,
struct br_mdb_entry *entry)
{
struct br_ip ip;
struct net_device *dev;
struct net_bridge_port *p;
int ret;
if (!netif_running(br->dev) || br->multicast_disabled)
return -EINVAL;
dev = __dev_get_by_index(net, entry->ifindex);
if (!dev)
return -ENODEV;
p = br_port_get_rtnl(dev);
if (!p || p->br != br || p->state == BR_STATE_DISABLED)
return -EINVAL;
memset(&ip, 0, sizeof(ip));
ip.vid = entry->vid;
ip.proto = entry->addr.proto;
if (ip.proto == htons(ETH_P_IP))
ip.u.ip4 = entry->addr.u.ip4;
#if IS_ENABLED(CONFIG_IPV6)
else
ip.u.ip6 = entry->addr.u.ip6;
#endif
spin_lock_bh(&br->multicast_lock);
ret = br_mdb_add_group(br, p, &ip, entry->state);
spin_unlock_bh(&br->multicast_lock);
return ret;
}
static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
struct net_bridge_vlan_group *vg;
struct net_device *dev, *pdev;
struct br_mdb_entry *entry;
struct net_bridge_port *p;
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
struct net_bridge_vlan *v;
struct net_bridge *br;
int err;
err = br_mdb_parse(skb, nlh, &dev, &entry);
if (err < 0)
return err;
br = netdev_priv(dev);
/* If vlan filtering is enabled and VLAN is not specified
* install mdb entry on all vlans configured on the port.
*/
pdev = __dev_get_by_index(net, entry->ifindex);
if (!pdev)
return -ENODEV;
p = br_port_get_rtnl(pdev);
if (!p || p->br != br || p->state == BR_STATE_DISABLED)
return -EINVAL;
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
vg = nbp_vlan_group(p);
if (br_vlan_enabled(br) && vg && entry->vid == 0) {
list_for_each_entry(v, &vg->vlan_list, vlist) {
entry->vid = v->vid;
err = __br_mdb_add(net, br, entry);
if (err)
break;
__br_mdb_notify(dev, entry, RTM_NEWMDB);
}
} else {
err = __br_mdb_add(net, br, entry);
if (!err)
__br_mdb_notify(dev, entry, RTM_NEWMDB);
}
return err;
}
static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
{
struct net_bridge_mdb_htable *mdb;
struct net_bridge_mdb_entry *mp;
struct net_bridge_port_group *p;
struct net_bridge_port_group __rcu **pp;
struct br_ip ip;
int err = -EINVAL;
if (!netif_running(br->dev) || br->multicast_disabled)
return -EINVAL;
memset(&ip, 0, sizeof(ip));
ip.vid = entry->vid;
ip.proto = entry->addr.proto;
if (ip.proto == htons(ETH_P_IP))
ip.u.ip4 = entry->addr.u.ip4;
#if IS_ENABLED(CONFIG_IPV6)
else
ip.u.ip6 = entry->addr.u.ip6;
#endif
spin_lock_bh(&br->multicast_lock);
mdb = mlock_dereference(br->mdb, br);
mp = br_mdb_ip_get(mdb, &ip);
if (!mp)
goto unlock;
for (pp = &mp->ports;
(p = mlock_dereference(*pp, br)) != NULL;
pp = &p->next) {
if (!p->port || p->port->dev->ifindex != entry->ifindex)
continue;
if (p->port->state == BR_STATE_DISABLED)
goto unlock;
bridge: mdb: fix delmdb state in the notification Since mdb states were introduced when deleting an entry the state was left as it was set in the delete request from the user which leads to the following output when doing a monitor (for example): $ bridge mdb add dev br0 port eth3 grp 239.0.0.1 permanent (monitor) dev br0 port eth3 grp 239.0.0.1 permanent $ bridge mdb del dev br0 port eth3 grp 239.0.0.1 permanent (monitor) dev br0 port eth3 grp 239.0.0.1 temp ^^^ Note the "temp" state in the delete notification which is wrong since the entry was permanent, the state in a delete is always reported as "temp" regardless of the real state of the entry. After this patch: $ bridge mdb add dev br0 port eth3 grp 239.0.0.1 permanent (monitor) dev br0 port eth3 grp 239.0.0.1 permanent $ bridge mdb del dev br0 port eth3 grp 239.0.0.1 permanent (monitor) dev br0 port eth3 grp 239.0.0.1 permanent There's one important note to make here that the state is actually not matched when doing a delete, so one can delete a permanent entry by stating "temp" in the end of the command, I've chosen this fix in order not to break user-space tools which rely on this (incorrect) behaviour. So to give an example after this patch and using the wrong state: $ bridge mdb add dev br0 port eth3 grp 239.0.0.1 permanent (monitor) dev br0 port eth3 grp 239.0.0.1 permanent $ bridge mdb del dev br0 port eth3 grp 239.0.0.1 temp (monitor) dev br0 port eth3 grp 239.0.0.1 permanent Note the state of the entry that got deleted is correct in the notification. Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Fixes: ccb1c31a7a87 ("bridge: add flags to distinguish permanent mdb entires") Signed-off-by: David S. Miller <davem@davemloft.net>
2015-07-28 11:10:44 +00:00
entry->state = p->state;
rcu_assign_pointer(*pp, p->next);
hlist_del_init(&p->mglist);
del_timer(&p->timer);
call_rcu_bh(&p->rcu, br_multicast_free_pg);
err = 0;
Revert "bridge: only expire the mdb entry when query is received" While this commit was a good attempt to fix issues occuring when no multicast querier is present, this commit still has two more issues: 1) There are cases where mdb entries do not expire even if there is a querier present. The bridge will unnecessarily continue flooding multicast packets on the according ports. 2) Never removing an mdb entry could be exploited for a Denial of Service by an attacker on the local link, slowly, but steadily eating up all memory. Actually, this commit became obsolete with "bridge: disable snooping if there is no querier" (b00589af3b) which included fixes for a few more cases. Therefore reverting the following commits (the commit stated in the commit message plus three of its follow up fixes): ==================== Revert "bridge: update mdb expiration timer upon reports." This reverts commit f144febd93d5ee534fdf23505ab091b2b9088edc. Revert "bridge: do not call setup_timer() multiple times" This reverts commit 1faabf2aab1fdaa1ace4e8c829d1b9cf7bfec2f1. Revert "bridge: fix some kernel warning in multicast timer" This reverts commit c7e8e8a8f7a70b343ca1e0f90a31e35ab2d16de1. Revert "bridge: only expire the mdb entry when query is received" This reverts commit 9f00b2e7cf241fa389733d41b615efdaa2cb0f5b. ==================== CC: Cong Wang <amwang@redhat.com> Signed-off-by: Linus Lüssing <linus.luessing@web.de> Reviewed-by: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-19 22:58:57 +00:00
if (!mp->ports && !mp->mglist &&
netif_running(br->dev))
mod_timer(&mp->timer, jiffies);
break;
}
unlock:
spin_unlock_bh(&br->multicast_lock);
return err;
}
static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
struct net_bridge_vlan_group *vg;
struct net_device *dev, *pdev;
struct br_mdb_entry *entry;
struct net_bridge_port *p;
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
struct net_bridge_vlan *v;
struct net_bridge *br;
int err;
err = br_mdb_parse(skb, nlh, &dev, &entry);
if (err < 0)
return err;
br = netdev_priv(dev);
/* If vlan filtering is enabled and VLAN is not specified
* delete mdb entry on all vlans configured on the port.
*/
pdev = __dev_get_by_index(net, entry->ifindex);
if (!pdev)
return -ENODEV;
p = br_port_get_rtnl(pdev);
if (!p || p->br != br || p->state == BR_STATE_DISABLED)
return -EINVAL;
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
vg = nbp_vlan_group(p);
if (br_vlan_enabled(br) && vg && entry->vid == 0) {
list_for_each_entry(v, &vg->vlan_list, vlist) {
entry->vid = v->vid;
err = __br_mdb_del(br, entry);
if (!err)
__br_mdb_notify(dev, entry, RTM_DELMDB);
}
} else {
err = __br_mdb_del(br, entry);
if (!err)
__br_mdb_notify(dev, entry, RTM_DELMDB);
}
return err;
}
void br_mdb_init(void)
{
rtnl_register(PF_BRIDGE, RTM_GETMDB, NULL, br_mdb_dump, NULL);
rtnl_register(PF_BRIDGE, RTM_NEWMDB, br_mdb_add, NULL, NULL);
rtnl_register(PF_BRIDGE, RTM_DELMDB, br_mdb_del, NULL, NULL);
}
void br_mdb_uninit(void)
{
rtnl_unregister(PF_BRIDGE, RTM_GETMDB);
rtnl_unregister(PF_BRIDGE, RTM_NEWMDB);
rtnl_unregister(PF_BRIDGE, RTM_DELMDB);
}