提交 68d4fd30 编写于 作者: D David S. Miller

Merge branch 'net-bridge-mcast-IGMPv3-MLDv2-fast-path-part-2'

Nikolay Aleksandrov says:

====================
net: bridge: mcast: IGMPv3/MLDv2 fast-path (part 2)

This is the second part of the IGMPv3/MLDv2 support which adds support
for the fast-path. In order to be able to handle source entries we add
mdb support for S,G entries (i.e. we add source address support to
br_ip), that requires to extend the current mdb netlink API, fortunately
we just add another attribute which will contain nested future mdb
attributes, then we use it to add support for S,G user- add, del and
dump. The lookup sequence is simple: when IGMPv3/MLDv2 are enabled do
the S,G lookup first and if it fails fallback to *,G. The more complex
part is when we begin handling source lists and auto-installing S,G entries
and *,G filter mode transitions. We have the following cases:
 1) *,G INCLUDE -> EXCLUDE transition: we need to install the port in
    all of *,G's installed S,G entries for proper replication (except
    the ones explicitly blocked), this is also necessary when adding a
    new *,G EXCLUDE port group

 2) *,G EXCLUDE -> INCLUDE transition: we need to remove the port from
    all of *,G's installed S,G entries, this is also necessary when
    removing a *,G port group

 3) New S,G port entry: we need to install all current *,G EXCLUDE ports

 4) Remove S,G port entry: if all other port groups were auto-installed we
    can safely remove them and delete the whole S,G entry

Currently we compute these operations from the available ports, their
source lists and their filter mode. In the future we can extend the port
group structure and reduce the running time of these ops. Also one
current limitation is that host-joined S,G entries are not supported.
I.e. one cannot add "dev bridge port bridge" mdb S,G entries. The host
join is currently considered an EXCLUDE {} join, so it's reflected in
all of *,G's installed S,G entries. If an S,G,port entry is added as
temporary then the kernel can take it over if a source shows up from a
report, permanent entries are skipped. In order to properly handle
blocked sources we add a new port group blocked flag to avoid forwarding
to that port group in the S,G. Finally when forwarding we use the port
group filter mode (if it's INCLUDE and the port group is from a *,G then
don't replicate to it, respectively if it's EXCLUDE then forward) and the
blocked flag (obviously if it's set - skip that port unless it's a
router port) to decide if the port should be skipped. Another limitation
is that we can't do some of the above transitions without small traffic
drop while installing/removing entries. That will be taken care of when
we add atomic swap of port replication lists later.

Patch break down:
 patches 1-3: prepare the mdb code for better extack support which is
              used in future patches to return a more meaningful error
 patches 4-6: add the source address field to struct br_ip, and do minor
              cleanups around it
 patches 7-8: extend the mdb netlink API so we can send new mdb
              attributes and uses the new API for S,G entry add/del/dump
              support
 patch     9: takes care of S,G entries when doing a lookup (first S,G
              then *,G lookup)
 patch    10: adds a new port group field and attribute for origin protocol
              we use the already available RTPROT_ definitions,
              currently user-space entries are added as RTPROT_STATIC and
              kernel entries are added as RTPROT_KERNEL, we may allow
              user-space to set custom values later (e.g. for FRR, clag)
 patch    11: adds an internal S,G,port rhashtable to speed up filter
              mode transitions
 patch    12: initial automatic install of S,G entries based on port
              groups' source lists
 patch    13: handles port group modes on transitions or when new
              port group entries are added
 patch    14: self-explanatory - adds support for blocked port group
              entries needed to stop forwarding to particular S,G,port
              entries
 patch    15: handles host-join/leave state changes, treats host-joins
              as EXCLUDE {} groups (reflected in all *,G's S,G entries)
 patch    16: finally adds the fast-path filter mode and block flag
              support

Here're the sets that will come next (in order):
 - iproute2 support for IGMPv3/MLDv2
 - selftests for all mode transitions and group flags
 - explicit host tracking for proper fast-leave support
 - atomic port replication lists (these are also needed for broadcast
   forwarding optimizations)
 - mode transition optimization and removal of open-coded sorted lists

Not implemented yet:
 - Host IGMPv3/MLDv2 filter support (currently we handle only join/leave
   as before)
 - Proper other querier source timer and value updates
 - IGMPv3/v2 MLDv2/v1 compat (I have a few rough patches for this one)

v2: fix build with CONFIG_BATMAN_ADV_MCAST in patch 6
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
......@@ -19,7 +19,13 @@ struct br_ip {
#if IS_ENABLED(CONFIG_IPV6)
struct in6_addr ip6;
#endif
} u;
} src;
union {
__be32 ip4;
#if IS_ENABLED(CONFIG_IPV6)
struct in6_addr ip6;
#endif
} dst;
__be16 proto;
__u16 vid;
};
......
......@@ -457,6 +457,8 @@ enum {
MDBA_MDB_EATTR_TIMER,
MDBA_MDB_EATTR_SRC_LIST,
MDBA_MDB_EATTR_GROUP_MODE,
MDBA_MDB_EATTR_SOURCE,
MDBA_MDB_EATTR_RTPROT,
__MDBA_MDB_EATTR_MAX
};
#define MDBA_MDB_EATTR_MAX (__MDBA_MDB_EATTR_MAX - 1)
......@@ -516,6 +518,8 @@ struct br_mdb_entry {
__u8 state;
#define MDB_FLAGS_OFFLOAD (1 << 0)
#define MDB_FLAGS_FAST_LEAVE (1 << 1)
#define MDB_FLAGS_STAR_EXCL (1 << 2)
#define MDB_FLAGS_BLOCKED (1 << 3)
__u8 flags;
__u16 vid;
struct {
......@@ -530,10 +534,23 @@ struct br_mdb_entry {
enum {
MDBA_SET_ENTRY_UNSPEC,
MDBA_SET_ENTRY,
MDBA_SET_ENTRY_ATTRS,
__MDBA_SET_ENTRY_MAX,
};
#define MDBA_SET_ENTRY_MAX (__MDBA_SET_ENTRY_MAX - 1)
/* [MDBA_SET_ENTRY_ATTRS] = {
* [MDBE_ATTR_xxx]
* ...
* }
*/
enum {
MDBE_ATTR_UNSPEC,
MDBE_ATTR_SOURCE,
__MDBE_ATTR_MAX,
};
#define MDBE_ATTR_MAX (__MDBE_ATTR_MAX - 1)
/* Embedded inside LINK_XSTATS_TYPE_BRIDGE */
enum {
BRIDGE_XSTATS_UNSPEC,
......
......@@ -221,7 +221,7 @@ static u8 batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv,
* address here, only IPv6 ones
*/
if (br_ip_entry->addr.proto == htons(ETH_P_IPV6) &&
ipv6_addr_is_ll_all_routers(&br_ip_entry->addr.u.ip6))
ipv6_addr_is_ll_all_routers(&br_ip_entry->addr.dst.ip6))
flags &= ~BATADV_MCAST_WANT_NO_RTR6;
list_del(&br_ip_entry->list);
......@@ -562,10 +562,10 @@ batadv_mcast_mla_softif_get(struct net_device *dev,
static void batadv_mcast_mla_br_addr_cpy(char *dst, const struct br_ip *src)
{
if (src->proto == htons(ETH_P_IP))
ip_eth_mc_map(src->u.ip4, dst);
ip_eth_mc_map(src->dst.ip4, dst);
#if IS_ENABLED(CONFIG_IPV6)
else if (src->proto == htons(ETH_P_IPV6))
ipv6_eth_mc_map(&src->u.ip6, dst);
ipv6_eth_mc_map(&src->dst.ip6, dst);
#endif
else
eth_zero_addr(dst);
......@@ -609,11 +609,11 @@ static int batadv_mcast_mla_bridge_get(struct net_device *dev,
continue;
if (tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES &&
ipv4_is_local_multicast(br_ip_entry->addr.u.ip4))
ipv4_is_local_multicast(br_ip_entry->addr.dst.ip4))
continue;
if (!(tvlv_flags & BATADV_MCAST_WANT_NO_RTR4) &&
!ipv4_is_local_multicast(br_ip_entry->addr.u.ip4))
!ipv4_is_local_multicast(br_ip_entry->addr.dst.ip4))
continue;
}
......@@ -623,11 +623,11 @@ static int batadv_mcast_mla_bridge_get(struct net_device *dev,
continue;
if (tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES &&
ipv6_addr_is_ll_all_nodes(&br_ip_entry->addr.u.ip6))
ipv6_addr_is_ll_all_nodes(&br_ip_entry->addr.dst.ip6))
continue;
if (!(tvlv_flags & BATADV_MCAST_WANT_NO_RTR6) &&
IPV6_ADDR_MC_SCOPE(&br_ip_entry->addr.u.ip6) >
IPV6_ADDR_MC_SCOPE(&br_ip_entry->addr.dst.ip6) >
IPV6_ADDR_SCOPE_LINKLOCAL)
continue;
}
......
......@@ -274,14 +274,23 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
struct net_bridge *br = netdev_priv(dev);
struct net_bridge_port *prev = NULL;
struct net_bridge_port_group *p;
bool allow_mode_include = true;
struct hlist_node *rp;
rp = rcu_dereference(hlist_first_rcu(&br->router_list));
p = mdst ? rcu_dereference(mdst->ports) : NULL;
if (mdst) {
p = rcu_dereference(mdst->ports);
if (br_multicast_should_handle_mode(br, mdst->addr.proto) &&
br_multicast_is_star_g(&mdst->addr))
allow_mode_include = false;
} else {
p = NULL;
}
while (p || rp) {
struct net_bridge_port *port, *lport, *rport;
lport = p ? p->port : NULL;
lport = p ? p->key.port : NULL;
rport = hlist_entry_safe(rp, struct net_bridge_port, rlist);
if ((unsigned long)lport > (unsigned long)rport) {
......@@ -292,6 +301,10 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
local_orig);
goto delivered;
}
if ((!allow_mode_include &&
p->filter_mode == MCAST_INCLUDE) ||
(p->flags & MDB_PG_FLAGS_BLOCKED))
goto delivered;
} else {
port = rport;
}
......
......@@ -62,19 +62,33 @@ static void __mdb_entry_fill_flags(struct br_mdb_entry *e, unsigned char flags)
e->flags |= MDB_FLAGS_OFFLOAD;
if (flags & MDB_PG_FLAGS_FAST_LEAVE)
e->flags |= MDB_FLAGS_FAST_LEAVE;
if (flags & MDB_PG_FLAGS_STAR_EXCL)
e->flags |= MDB_FLAGS_STAR_EXCL;
if (flags & MDB_PG_FLAGS_BLOCKED)
e->flags |= MDB_FLAGS_BLOCKED;
}
static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip)
static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip,
struct nlattr **mdb_attrs)
{
memset(ip, 0, sizeof(struct br_ip));
ip->vid = entry->vid;
ip->proto = entry->addr.proto;
if (ip->proto == htons(ETH_P_IP))
ip->u.ip4 = entry->addr.u.ip4;
switch (ip->proto) {
case htons(ETH_P_IP):
ip->dst.ip4 = entry->addr.u.ip4;
if (mdb_attrs && mdb_attrs[MDBE_ATTR_SOURCE])
ip->src.ip4 = nla_get_in_addr(mdb_attrs[MDBE_ATTR_SOURCE]);
break;
#if IS_ENABLED(CONFIG_IPV6)
else
ip->u.ip6 = entry->addr.u.ip6;
case htons(ETH_P_IPV6):
ip->dst.ip6 = entry->addr.u.ip6;
if (mdb_attrs && mdb_attrs[MDBE_ATTR_SOURCE])
ip->src.ip6 = nla_get_in6_addr(mdb_attrs[MDBE_ATTR_SOURCE]);
break;
#endif
}
}
static int __mdb_fill_srcs(struct sk_buff *skb,
......@@ -91,14 +105,14 @@ static int __mdb_fill_srcs(struct sk_buff *skb,
return -EMSGSIZE;
hlist_for_each_entry_rcu(ent, &p->src_list, node,
lockdep_is_held(&p->port->br->multicast_lock)) {
lockdep_is_held(&p->key.port->br->multicast_lock)) {
nest_ent = nla_nest_start(skb, MDBA_MDB_SRCLIST_ENTRY);
if (!nest_ent)
goto out_cancel_err;
switch (ent->addr.proto) {
case htons(ETH_P_IP):
if (nla_put_in_addr(skb, MDBA_MDB_SRCATTR_ADDRESS,
ent->addr.u.ip4)) {
ent->addr.src.ip4)) {
nla_nest_cancel(skb, nest_ent);
goto out_cancel_err;
}
......@@ -106,7 +120,7 @@ static int __mdb_fill_srcs(struct sk_buff *skb,
#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
if (nla_put_in6_addr(skb, MDBA_MDB_SRCATTR_ADDRESS,
&ent->addr.u.ip6)) {
&ent->addr.src.ip6)) {
nla_nest_cancel(skb, nest_ent);
goto out_cancel_err;
}
......@@ -146,7 +160,7 @@ static int __mdb_fill_info(struct sk_buff *skb,
memset(&e, 0, sizeof(e));
if (p) {
ifindex = p->port->dev->ifindex;
ifindex = p->key.port->dev->ifindex;
mtimer = &p->timer;
flags = p->flags;
} else {
......@@ -158,10 +172,10 @@ static int __mdb_fill_info(struct sk_buff *skb,
e.ifindex = ifindex;
e.vid = mp->addr.vid;
if (mp->addr.proto == htons(ETH_P_IP))
e.addr.u.ip4 = mp->addr.u.ip4;
e.addr.u.ip4 = mp->addr.dst.ip4;
#if IS_ENABLED(CONFIG_IPV6)
if (mp->addr.proto == htons(ETH_P_IPV6))
e.addr.u.ip6 = mp->addr.u.ip6;
e.addr.u.ip6 = mp->addr.dst.ip6;
#endif
e.addr.proto = mp->addr.proto;
nest_ent = nla_nest_start_noflag(skb,
......@@ -172,30 +186,47 @@ static int __mdb_fill_info(struct sk_buff *skb,
if (nla_put_nohdr(skb, sizeof(e), &e) ||
nla_put_u32(skb,
MDBA_MDB_EATTR_TIMER,
br_timer_value(mtimer))) {
nla_nest_cancel(skb, nest_ent);
return -EMSGSIZE;
}
br_timer_value(mtimer)))
goto nest_err;
switch (mp->addr.proto) {
case htons(ETH_P_IP):
dump_srcs_mode = !!(p && mp->br->multicast_igmp_version == 3);
dump_srcs_mode = !!(mp->br->multicast_igmp_version == 3);
if (mp->addr.src.ip4) {
if (nla_put_in_addr(skb, MDBA_MDB_EATTR_SOURCE,
mp->addr.src.ip4))
goto nest_err;
break;
}
break;
#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
dump_srcs_mode = !!(p && mp->br->multicast_mld_version == 2);
dump_srcs_mode = !!(mp->br->multicast_mld_version == 2);
if (!ipv6_addr_any(&mp->addr.src.ip6)) {
if (nla_put_in6_addr(skb, MDBA_MDB_EATTR_SOURCE,
&mp->addr.src.ip6))
goto nest_err;
break;
}
break;
#endif
}
if (p) {
if (nla_put_u8(skb, MDBA_MDB_EATTR_RTPROT, p->rt_protocol))
goto nest_err;
if (dump_srcs_mode &&
(__mdb_fill_srcs(skb, p) ||
nla_put_u8(skb, MDBA_MDB_EATTR_GROUP_MODE, p->filter_mode))) {
nla_nest_cancel(skb, nest_ent);
return -EMSGSIZE;
nla_put_u8(skb, MDBA_MDB_EATTR_GROUP_MODE,
p->filter_mode)))
goto nest_err;
}
nla_nest_end(skb, nest_ent);
return 0;
nest_err:
nla_nest_cancel(skb, nest_ent);
return -EMSGSIZE;
}
static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
......@@ -236,7 +267,7 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL;
pp = &p->next) {
if (!p->port)
if (!p->key.port)
continue;
if (pidx < s_pidx)
goto skip_pg;
......@@ -393,15 +424,24 @@ static size_t rtnl_mdb_nlmsg_size(struct net_bridge_port_group *pg)
if (!pg)
goto out;
switch (pg->addr.proto) {
/* MDBA_MDB_EATTR_RTPROT */
nlmsg_size += nla_total_size(sizeof(u8));
switch (pg->key.addr.proto) {
case htons(ETH_P_IP):
if (pg->port->br->multicast_igmp_version == 2)
/* MDBA_MDB_EATTR_SOURCE */
if (pg->key.addr.src.ip4)
nlmsg_size += nla_total_size(sizeof(__be32));
if (pg->key.port->br->multicast_igmp_version == 2)
goto out;
addr_size = sizeof(__be32);
break;
#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
if (pg->port->br->multicast_mld_version == 1)
/* MDBA_MDB_EATTR_SOURCE */
if (!ipv6_addr_any(&pg->key.addr.src.ip6))
nlmsg_size += nla_total_size(sizeof(struct in6_addr));
if (pg->key.port->br->multicast_mld_version == 1)
goto out;
addr_size = sizeof(struct in6_addr);
break;
......@@ -450,7 +490,7 @@ static void br_mdb_complete(struct net_device *dev, int err, void *priv)
goto out;
for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL;
pp = &p->next) {
if (p->port != port)
if (p->key.port != port)
continue;
p->flags |= MDB_PG_FLAGS_OFFLOAD;
}
......@@ -474,10 +514,10 @@ static void br_mdb_switchdev_host_port(struct net_device *dev,
};
if (mp->addr.proto == htons(ETH_P_IP))
ip_eth_mc_map(mp->addr.u.ip4, mdb.addr);
ip_eth_mc_map(mp->addr.dst.ip4, mdb.addr);
#if IS_ENABLED(CONFIG_IPV6)
else
ipv6_eth_mc_map(&mp->addr.u.ip6, mdb.addr);
ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb.addr);
#endif
mdb.obj.orig_dev = dev;
......@@ -520,26 +560,26 @@ void br_mdb_notify(struct net_device *dev,
if (pg) {
if (mp->addr.proto == htons(ETH_P_IP))
ip_eth_mc_map(mp->addr.u.ip4, mdb.addr);
ip_eth_mc_map(mp->addr.dst.ip4, mdb.addr);
#if IS_ENABLED(CONFIG_IPV6)
else
ipv6_eth_mc_map(&mp->addr.u.ip6, mdb.addr);
ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb.addr);
#endif
mdb.obj.orig_dev = pg->port->dev;
mdb.obj.orig_dev = pg->key.port->dev;
switch (type) {
case RTM_NEWMDB:
complete_info = kmalloc(sizeof(*complete_info), GFP_ATOMIC);
if (!complete_info)
break;
complete_info->port = pg->port;
complete_info->port = pg->key.port;
complete_info->ip = mp->addr;
mdb.obj.complete_priv = complete_info;
mdb.obj.complete = br_mdb_complete;
if (switchdev_port_obj_add(pg->port->dev, &mdb.obj, NULL))
if (switchdev_port_obj_add(pg->key.port->dev, &mdb.obj, NULL))
kfree(complete_info);
break;
case RTM_DELMDB:
switchdev_port_obj_del(pg->port->dev, &mdb.obj);
switchdev_port_obj_del(pg->key.port->dev, &mdb.obj);
break;
}
} else {
......@@ -629,33 +669,94 @@ void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port,
rtnl_set_sk_err(net, RTNLGRP_MDB, err);
}
static bool is_valid_mdb_entry(struct br_mdb_entry *entry)
static bool is_valid_mdb_entry(struct br_mdb_entry *entry,
struct netlink_ext_ack *extack)
{
if (entry->ifindex == 0)
if (entry->ifindex == 0) {
NL_SET_ERR_MSG_MOD(extack, "Zero entry ifindex is not allowed");
return false;
}
if (entry->addr.proto == htons(ETH_P_IP)) {
if (!ipv4_is_multicast(entry->addr.u.ip4))
if (!ipv4_is_multicast(entry->addr.u.ip4)) {
NL_SET_ERR_MSG_MOD(extack, "IPv4 entry group address is not multicast");
return false;
if (ipv4_is_local_multicast(entry->addr.u.ip4))
}
if (ipv4_is_local_multicast(entry->addr.u.ip4)) {
NL_SET_ERR_MSG_MOD(extack, "IPv4 entry group address is local multicast");
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))
if (ipv6_addr_is_ll_all_nodes(&entry->addr.u.ip6)) {
NL_SET_ERR_MSG_MOD(extack, "IPv6 entry group address is link-local all nodes");
return false;
}
#endif
} else
} else {
NL_SET_ERR_MSG_MOD(extack, "Unknown entry protocol");
return false;
if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY)
}
if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY) {
NL_SET_ERR_MSG_MOD(extack, "Unknown entry state");
return false;
}
if (entry->vid >= VLAN_VID_MASK) {
NL_SET_ERR_MSG_MOD(extack, "Invalid entry VLAN id");
return false;
}
return true;
}
static bool is_valid_mdb_source(struct nlattr *attr, __be16 proto,
struct netlink_ext_ack *extack)
{
switch (proto) {
case htons(ETH_P_IP):
if (nla_len(attr) != sizeof(struct in_addr)) {
NL_SET_ERR_MSG_MOD(extack, "IPv4 invalid source address length");
return false;
}
if (ipv4_is_multicast(nla_get_in_addr(attr))) {
NL_SET_ERR_MSG_MOD(extack, "IPv4 multicast source address is not allowed");
return false;
}
break;
#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6): {
struct in6_addr src;
if (nla_len(attr) != sizeof(struct in6_addr)) {
NL_SET_ERR_MSG_MOD(extack, "IPv6 invalid source address length");
return false;
if (entry->vid >= VLAN_VID_MASK)
}
src = nla_get_in6_addr(attr);
if (ipv6_addr_is_multicast(&src)) {
NL_SET_ERR_MSG_MOD(extack, "IPv6 multicast source address is not allowed");
return false;
}
break;
}
#endif
default:
NL_SET_ERR_MSG_MOD(extack, "Invalid protocol used with source address");
return false;
}
return true;
}
static const struct nla_policy br_mdbe_attrs_pol[MDBE_ATTR_MAX + 1] = {
[MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY,
sizeof(struct in_addr),
sizeof(struct in6_addr)),
};
static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh,
struct net_device **pdev, struct br_mdb_entry **pentry)
struct net_device **pdev, struct br_mdb_entry **pentry,
struct nlattr **mdb_attrs, struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
struct br_mdb_entry *entry;
......@@ -671,51 +772,86 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh,
bpm = nlmsg_data(nlh);
if (bpm->ifindex == 0) {
pr_info("PF_BRIDGE: br_mdb_parse() with invalid ifindex\n");
NL_SET_ERR_MSG_MOD(extack, "Invalid bridge ifindex");
return -EINVAL;
}
dev = __dev_get_by_index(net, bpm->ifindex);
if (dev == NULL) {
pr_info("PF_BRIDGE: br_mdb_parse() with unknown ifindex\n");
NL_SET_ERR_MSG_MOD(extack, "Bridge device doesn't exist");
return -ENODEV;
}
if (!(dev->priv_flags & IFF_EBRIDGE)) {
pr_info("PF_BRIDGE: br_mdb_parse() with non-bridge\n");
NL_SET_ERR_MSG_MOD(extack, "Device is not a bridge");
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");
if (!tb[MDBA_SET_ENTRY]) {
NL_SET_ERR_MSG_MOD(extack, "Missing MDBA_SET_ENTRY attribute");
return -EINVAL;
}
if (nla_len(tb[MDBA_SET_ENTRY]) != sizeof(struct br_mdb_entry)) {
NL_SET_ERR_MSG_MOD(extack, "Invalid MDBA_SET_ENTRY attribute length");
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");
if (!is_valid_mdb_entry(entry, extack))
return -EINVAL;
*pentry = entry;
if (tb[MDBA_SET_ENTRY_ATTRS]) {
err = nla_parse_nested(mdb_attrs, MDBE_ATTR_MAX,
tb[MDBA_SET_ENTRY_ATTRS],
br_mdbe_attrs_pol, extack);
if (err)
return err;
if (mdb_attrs[MDBE_ATTR_SOURCE] &&
!is_valid_mdb_source(mdb_attrs[MDBE_ATTR_SOURCE],
entry->addr.proto, extack))
return -EINVAL;
} else {
memset(mdb_attrs, 0,
sizeof(struct nlattr *) * (MDBE_ATTR_MAX + 1));
}
*pentry = entry;
return 0;
}
static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
struct br_ip *group, struct br_mdb_entry *entry)
struct br_mdb_entry *entry,
struct nlattr **mdb_attrs,
struct netlink_ext_ack *extack)
{
struct net_bridge_mdb_entry *mp;
struct net_bridge_mdb_entry *mp, *star_mp;
struct net_bridge_port_group *p;
struct net_bridge_port_group __rcu **pp;
struct br_ip group, star_group;
unsigned long now = jiffies;
u8 filter_mode;
int err;
mp = br_mdb_ip_get(br, group);
__mdb_entry_to_br_ip(entry, &group, mdb_attrs);
/* host join errors which can happen before creating the group */
if (!port) {
/* don't allow any flags for host-joined groups */
if (entry->state) {
NL_SET_ERR_MSG_MOD(extack, "Flags are not allowed for host groups");
return -EINVAL;
}
if (!br_multicast_is_star_g(&group)) {
NL_SET_ERR_MSG_MOD(extack, "Groups with sources cannot be manually host joined");
return -EINVAL;
}
}
mp = br_mdb_ip_get(br, &group);
if (!mp) {
mp = br_multicast_new_group(br, group);
mp = br_multicast_new_group(br, &group);
err = PTR_ERR_OR_ZERO(mp);
if (err)
return err;
......@@ -723,11 +859,10 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
/* host join */
if (!port) {
/* don't allow any flags for host-joined groups */
if (entry->state)
return -EINVAL;
if (mp->host_joined)
if (mp->host_joined) {
NL_SET_ERR_MSG_MOD(extack, "Group is already joined by host");
return -EEXIST;
}
br_multicast_host_join(mp, false);
br_mdb_notify(br->dev, mp, NULL, RTM_NEWMDB);
......@@ -738,56 +873,69 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
for (pp = &mp->ports;
(p = mlock_dereference(*pp, br)) != NULL;
pp = &p->next) {
if (p->port == port)
if (p->key.port == port) {
NL_SET_ERR_MSG_MOD(extack, "Group is already joined by port");
return -EEXIST;
if ((unsigned long)p->port < (unsigned long)port)
}
if ((unsigned long)p->key.port < (unsigned long)port)
break;
}
p = br_multicast_new_port_group(port, group, *pp, entry->state, NULL,
MCAST_EXCLUDE);
if (unlikely(!p))
filter_mode = br_multicast_is_star_g(&group) ? MCAST_EXCLUDE :
MCAST_INCLUDE;
p = br_multicast_new_port_group(port, &group, *pp, entry->state, NULL,
filter_mode, RTPROT_STATIC);
if (unlikely(!p)) {
NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new port group");
return -ENOMEM;
}
rcu_assign_pointer(*pp, p);
if (entry->state == MDB_TEMPORARY)
mod_timer(&p->timer, now + br->multicast_membership_interval);
br_mdb_notify(br->dev, mp, p, RTM_NEWMDB);
/* if we are adding a new EXCLUDE port group (*,G) it needs to be also
* added to all S,G entries for proper replication, if we are adding
* a new INCLUDE port (S,G) then all of *,G EXCLUDE ports need to be
* added to it for proper replication
*/
if (br_multicast_should_handle_mode(br, group.proto)) {
switch (filter_mode) {
case MCAST_EXCLUDE:
br_multicast_star_g_handle_mode(p, MCAST_EXCLUDE);
break;
case MCAST_INCLUDE:
star_group = p->key.addr;
memset(&star_group.src, 0, sizeof(star_group.src));
star_mp = br_mdb_ip_get(br, &star_group);
if (star_mp)
br_multicast_sg_add_exclude_ports(star_mp, p);
break;
}
}
return 0;
}
static int __br_mdb_add(struct net *net, struct net_bridge *br,
struct br_mdb_entry *entry)
struct net_bridge_port *p,
struct br_mdb_entry *entry,
struct nlattr **mdb_attrs,
struct netlink_ext_ack *extack)
{
struct br_ip ip;
struct net_device *dev;
struct net_bridge_port *p = NULL;
int ret;
if (!netif_running(br->dev) || !br_opt_get(br, BROPT_MULTICAST_ENABLED))
return -EINVAL;
if (entry->ifindex != br->dev->ifindex) {
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;
}
__mdb_entry_to_br_ip(entry, &ip);
spin_lock_bh(&br->multicast_lock);
ret = br_mdb_add_group(br, p, &ip, entry);
ret = br_mdb_add_group(br, p, entry, mdb_attrs, extack);
spin_unlock_bh(&br->multicast_lock);
return ret;
}
static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct nlattr *mdb_attrs[MDBE_ATTR_MAX + 1];
struct net *net = sock_net(skb->sk);
struct net_bridge_vlan_group *vg;
struct net_bridge_port *p = NULL;
......@@ -797,20 +945,43 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
struct net_bridge *br;
int err;
err = br_mdb_parse(skb, nlh, &dev, &entry);
err = br_mdb_parse(skb, nlh, &dev, &entry, mdb_attrs, extack);
if (err < 0)
return err;
br = netdev_priv(dev);
if (!netif_running(br->dev)) {
NL_SET_ERR_MSG_MOD(extack, "Bridge device is not running");
return -EINVAL;
}
if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) {
NL_SET_ERR_MSG_MOD(extack, "Bridge's multicast processing is disabled");
return -EINVAL;
}
if (entry->ifindex != br->dev->ifindex) {
pdev = __dev_get_by_index(net, entry->ifindex);
if (!pdev)
if (!pdev) {
NL_SET_ERR_MSG_MOD(extack, "Port net device doesn't exist");
return -ENODEV;
}
p = br_port_get_rtnl(pdev);
if (!p || p->br != br || p->state == BR_STATE_DISABLED)
if (!p) {
NL_SET_ERR_MSG_MOD(extack, "Net device is not a bridge port");
return -EINVAL;
}
if (p->br != br) {
NL_SET_ERR_MSG_MOD(extack, "Port belongs to a different bridge device");
return -EINVAL;
}
if (p->state == BR_STATE_DISABLED) {
NL_SET_ERR_MSG_MOD(extack, "Port is in disabled state");
return -EINVAL;
}
vg = nbp_vlan_group(p);
} else {
vg = br_vlan_group(br);
......@@ -822,18 +993,19 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
if (br_vlan_enabled(br->dev) && vg && entry->vid == 0) {
list_for_each_entry(v, &vg->vlan_list, vlist) {
entry->vid = v->vid;
err = __br_mdb_add(net, br, entry);
err = __br_mdb_add(net, br, p, entry, mdb_attrs, extack);
if (err)
break;
}
} else {
err = __br_mdb_add(net, br, entry);
err = __br_mdb_add(net, br, p, entry, mdb_attrs, extack);
}
return err;
}
static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry,
struct nlattr **mdb_attrs)
{
struct net_bridge_mdb_entry *mp;
struct net_bridge_port_group *p;
......@@ -844,7 +1016,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
if (!netif_running(br->dev) || !br_opt_get(br, BROPT_MULTICAST_ENABLED))
return -EINVAL;
__mdb_entry_to_br_ip(entry, &ip);
__mdb_entry_to_br_ip(entry, &ip, mdb_attrs);
spin_lock_bh(&br->multicast_lock);
mp = br_mdb_ip_get(br, &ip);
......@@ -864,10 +1036,10 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
for (pp = &mp->ports;
(p = mlock_dereference(*pp, br)) != NULL;
pp = &p->next) {
if (!p->port || p->port->dev->ifindex != entry->ifindex)
if (!p->key.port || p->key.port->dev->ifindex != entry->ifindex)
continue;
if (p->port->state == BR_STATE_DISABLED)
if (p->key.port->state == BR_STATE_DISABLED)
goto unlock;
br_multicast_del_pg(mp, p, pp);
......@@ -883,6 +1055,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct nlattr *mdb_attrs[MDBE_ATTR_MAX + 1];
struct net *net = sock_net(skb->sk);
struct net_bridge_vlan_group *vg;
struct net_bridge_port *p = NULL;
......@@ -892,7 +1065,7 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
struct net_bridge *br;
int err;
err = br_mdb_parse(skb, nlh, &dev, &entry);
err = br_mdb_parse(skb, nlh, &dev, &entry, mdb_attrs, extack);
if (err < 0)
return err;
......@@ -917,10 +1090,10 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
if (br_vlan_enabled(br->dev) && vg && entry->vid == 0) {
list_for_each_entry(v, &vg->vlan_list, vlist) {
entry->vid = v->vid;
err = __br_mdb_del(br, entry);
err = __br_mdb_del(br, entry, mdb_attrs);
}
} else {
err = __br_mdb_del(br, entry);
err = __br_mdb_del(br, entry, mdb_attrs);
}
return err;
......
......@@ -41,6 +41,13 @@ static const struct rhashtable_params br_mdb_rht_params = {
.automatic_shrinking = true,
};
static const struct rhashtable_params br_sg_port_rht_params = {
.head_offset = offsetof(struct net_bridge_port_group, rhnode),
.key_offset = offsetof(struct net_bridge_port_group, key),
.key_len = sizeof(struct net_bridge_port_group_sg_key),
.automatic_shrinking = true,
};
static void br_multicast_start_querier(struct net_bridge *br,
struct bridge_mcast_own_query *query);
static void br_multicast_add_router(struct net_bridge *br,
......@@ -59,6 +66,26 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br,
const struct in6_addr *group,
__u16 vid, const unsigned char *src);
#endif
static struct net_bridge_port_group *
__br_multicast_add_group(struct net_bridge *br,
struct net_bridge_port *port,
struct br_ip *group,
const unsigned char *src,
u8 filter_mode,
bool igmpv2_mldv1,
bool blocked);
static void br_multicast_find_del_pg(struct net_bridge *br,
struct net_bridge_port_group *pg);
static struct net_bridge_port_group *
br_sg_port_find(struct net_bridge *br,
struct net_bridge_port_group_sg_key *sg_p)
{
lockdep_assert_held_once(&br->multicast_lock);
return rhashtable_lookup_fast(&br->sg_port_tbl, sg_p,
br_sg_port_rht_params);
}
static struct net_bridge_mdb_entry *br_mdb_ip_get_rcu(struct net_bridge *br,
struct br_ip *dst)
......@@ -86,7 +113,7 @@ static struct net_bridge_mdb_entry *br_mdb_ip4_get(struct net_bridge *br,
struct br_ip br_dst;
memset(&br_dst, 0, sizeof(br_dst));
br_dst.u.ip4 = dst;
br_dst.dst.ip4 = dst;
br_dst.proto = htons(ETH_P_IP);
br_dst.vid = vid;
......@@ -101,7 +128,7 @@ static struct net_bridge_mdb_entry *br_mdb_ip6_get(struct net_bridge *br,
struct br_ip br_dst;
memset(&br_dst, 0, sizeof(br_dst));
br_dst.u.ip6 = *dst;
br_dst.dst.ip6 = *dst;
br_dst.proto = htons(ETH_P_IPV6);
br_dst.vid = vid;
......@@ -126,11 +153,29 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
switch (skb->protocol) {
case htons(ETH_P_IP):
ip.u.ip4 = ip_hdr(skb)->daddr;
ip.dst.ip4 = ip_hdr(skb)->daddr;
if (br->multicast_igmp_version == 3) {
struct net_bridge_mdb_entry *mdb;
ip.src.ip4 = ip_hdr(skb)->saddr;
mdb = br_mdb_ip_get_rcu(br, &ip);
if (mdb)
return mdb;
ip.src.ip4 = 0;
}
break;
#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
ip.u.ip6 = ipv6_hdr(skb)->daddr;
ip.dst.ip6 = ipv6_hdr(skb)->daddr;
if (br->multicast_mld_version == 2) {
struct net_bridge_mdb_entry *mdb;
ip.src.ip6 = ipv6_hdr(skb)->saddr;
mdb = br_mdb_ip_get_rcu(br, &ip);
if (mdb)
return mdb;
memset(&ip.src.ip6, 0, sizeof(ip.src.ip6));
}
break;
#endif
default:
......@@ -140,6 +185,326 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
return br_mdb_ip_get_rcu(br, &ip);
}
static bool br_port_group_equal(struct net_bridge_port_group *p,
struct net_bridge_port *port,
const unsigned char *src)
{
if (p->key.port != port)
return false;
if (!(port->flags & BR_MULTICAST_TO_UNICAST))
return true;
return ether_addr_equal(src, p->eth_addr);
}
static void __fwd_add_star_excl(struct net_bridge_port_group *pg,
struct br_ip *sg_ip)
{
struct net_bridge_port_group_sg_key sg_key;
struct net_bridge *br = pg->key.port->br;
struct net_bridge_port_group *src_pg;
memset(&sg_key, 0, sizeof(sg_key));
sg_key.port = pg->key.port;
sg_key.addr = *sg_ip;
if (br_sg_port_find(br, &sg_key))
return;
src_pg = __br_multicast_add_group(br, pg->key.port, sg_ip, pg->eth_addr,
MCAST_INCLUDE, false, false);
if (IS_ERR_OR_NULL(src_pg) ||
src_pg->rt_protocol != RTPROT_KERNEL)
return;
src_pg->flags |= MDB_PG_FLAGS_STAR_EXCL;
}
static void __fwd_del_star_excl(struct net_bridge_port_group *pg,
struct br_ip *sg_ip)
{
struct net_bridge_port_group_sg_key sg_key;
struct net_bridge *br = pg->key.port->br;
struct net_bridge_port_group *src_pg;
memset(&sg_key, 0, sizeof(sg_key));
sg_key.port = pg->key.port;
sg_key.addr = *sg_ip;
src_pg = br_sg_port_find(br, &sg_key);
if (!src_pg || !(src_pg->flags & MDB_PG_FLAGS_STAR_EXCL) ||
src_pg->rt_protocol != RTPROT_KERNEL)
return;
br_multicast_find_del_pg(br, src_pg);
}
/* When a port group transitions to (or is added as) EXCLUDE we need to add it
* to all other ports' S,G entries which are not blocked by the current group
* for proper replication, the assumption is that any S,G blocked entries
* are already added so the S,G,port lookup should skip them.
* When a port group transitions from EXCLUDE -> INCLUDE mode or is being
* deleted we need to remove it from all ports' S,G entries where it was
* automatically installed before (i.e. where it's MDB_PG_FLAGS_STAR_EXCL).
*/
void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg,
u8 filter_mode)
{
struct net_bridge *br = pg->key.port->br;
struct net_bridge_port_group *pg_lst;
struct net_bridge_mdb_entry *mp;
struct br_ip sg_ip;
if (WARN_ON(!br_multicast_is_star_g(&pg->key.addr)))
return;
mp = br_mdb_ip_get(br, &pg->key.addr);
if (!mp)
return;
memset(&sg_ip, 0, sizeof(sg_ip));
sg_ip = pg->key.addr;
for (pg_lst = mlock_dereference(mp->ports, br);
pg_lst;
pg_lst = mlock_dereference(pg_lst->next, br)) {
struct net_bridge_group_src *src_ent;
if (pg_lst == pg)
continue;
hlist_for_each_entry(src_ent, &pg_lst->src_list, node) {
if (!(src_ent->flags & BR_SGRP_F_INSTALLED))
continue;
sg_ip.src = src_ent->addr.src;
switch (filter_mode) {
case MCAST_INCLUDE:
__fwd_del_star_excl(pg, &sg_ip);
break;
case MCAST_EXCLUDE:
__fwd_add_star_excl(pg, &sg_ip);
break;
}
}
}
}
/* called when adding a new S,G with host_joined == false by default */
static void br_multicast_sg_host_state(struct net_bridge_mdb_entry *star_mp,
struct net_bridge_port_group *sg)
{
struct net_bridge_mdb_entry *sg_mp;
if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr)))
return;
if (!star_mp->host_joined)
return;
sg_mp = br_mdb_ip_get(star_mp->br, &sg->key.addr);
if (!sg_mp)
return;
sg_mp->host_joined = true;
}
/* set the host_joined state of all of *,G's S,G entries */
static void br_multicast_star_g_host_state(struct net_bridge_mdb_entry *star_mp)
{
struct net_bridge *br = star_mp->br;
struct net_bridge_mdb_entry *sg_mp;
struct net_bridge_port_group *pg;
struct br_ip sg_ip;
if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr)))
return;
memset(&sg_ip, 0, sizeof(sg_ip));
sg_ip = star_mp->addr;
for (pg = mlock_dereference(star_mp->ports, br);
pg;
pg = mlock_dereference(pg->next, br)) {
struct net_bridge_group_src *src_ent;
hlist_for_each_entry(src_ent, &pg->src_list, node) {
if (!(src_ent->flags & BR_SGRP_F_INSTALLED))
continue;
sg_ip.src = src_ent->addr.src;
sg_mp = br_mdb_ip_get(br, &sg_ip);
if (!sg_mp)
continue;
sg_mp->host_joined = star_mp->host_joined;
}
}
}
static void br_multicast_sg_del_exclude_ports(struct net_bridge_mdb_entry *sgmp)
{
struct net_bridge_port_group __rcu **pp;
struct net_bridge_port_group *p;
/* *,G exclude ports are only added to S,G entries */
if (WARN_ON(br_multicast_is_star_g(&sgmp->addr)))
return;
/* we need the STAR_EXCLUDE ports if there are non-STAR_EXCLUDE ports
* we should ignore perm entries since they're managed by user-space
*/
for (pp = &sgmp->ports;
(p = mlock_dereference(*pp, sgmp->br)) != NULL;
pp = &p->next)
if (!(p->flags & (MDB_PG_FLAGS_STAR_EXCL |
MDB_PG_FLAGS_PERMANENT)))
return;
/* currently the host can only have joined the *,G which means
* we treat it as EXCLUDE {}, so for an S,G it's considered a
* STAR_EXCLUDE entry and we can safely leave it
*/
sgmp->host_joined = false;
for (pp = &sgmp->ports;
(p = mlock_dereference(*pp, sgmp->br)) != NULL;) {
if (!(p->flags & MDB_PG_FLAGS_PERMANENT))
br_multicast_del_pg(sgmp, p, pp);
else
pp = &p->next;
}
}
void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp,
struct net_bridge_port_group *sg)
{
struct net_bridge_port_group_sg_key sg_key;
struct net_bridge *br = star_mp->br;
struct net_bridge_port_group *pg;
if (WARN_ON(br_multicast_is_star_g(&sg->key.addr)))
return;
if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr)))
return;
br_multicast_sg_host_state(star_mp, sg);
memset(&sg_key, 0, sizeof(sg_key));
sg_key.addr = sg->key.addr;
/* we need to add all exclude ports to the S,G */
for (pg = mlock_dereference(star_mp->ports, br);
pg;
pg = mlock_dereference(pg->next, br)) {
struct net_bridge_port_group *src_pg;
if (pg == sg || pg->filter_mode == MCAST_INCLUDE)
continue;
sg_key.port = pg->key.port;
if (br_sg_port_find(br, &sg_key))
continue;
src_pg = __br_multicast_add_group(br, pg->key.port,
&sg->key.addr,
sg->eth_addr,
MCAST_INCLUDE, false, false);
if (IS_ERR_OR_NULL(src_pg) ||
src_pg->rt_protocol != RTPROT_KERNEL)
continue;
src_pg->flags |= MDB_PG_FLAGS_STAR_EXCL;
}
}
static void br_multicast_fwd_src_add(struct net_bridge_group_src *src)
{
struct net_bridge_mdb_entry *star_mp;
struct net_bridge_port_group *sg;
struct br_ip sg_ip;
if (src->flags & BR_SGRP_F_INSTALLED)
return;
memset(&sg_ip, 0, sizeof(sg_ip));
sg_ip = src->pg->key.addr;
sg_ip.src = src->addr.src;
sg = __br_multicast_add_group(src->br, src->pg->key.port, &sg_ip,
src->pg->eth_addr, MCAST_INCLUDE, false,
!timer_pending(&src->timer));
if (IS_ERR_OR_NULL(sg))
return;
src->flags |= BR_SGRP_F_INSTALLED;
sg->flags &= ~MDB_PG_FLAGS_STAR_EXCL;
/* if it was added by user-space as perm we can skip next steps */
if (sg->rt_protocol != RTPROT_KERNEL &&
(sg->flags & MDB_PG_FLAGS_PERMANENT))
return;
/* the kernel is now responsible for removing this S,G */
del_timer(&sg->timer);
star_mp = br_mdb_ip_get(src->br, &src->pg->key.addr);
if (!star_mp)
return;
br_multicast_sg_add_exclude_ports(star_mp, sg);
}
static void br_multicast_fwd_src_remove(struct net_bridge_group_src *src)
{
struct net_bridge_port_group *p, *pg = src->pg;
struct net_bridge_port_group __rcu **pp;
struct net_bridge_mdb_entry *mp;
struct br_ip sg_ip;
memset(&sg_ip, 0, sizeof(sg_ip));
sg_ip = pg->key.addr;
sg_ip.src = src->addr.src;
mp = br_mdb_ip_get(src->br, &sg_ip);
if (!mp)
return;
for (pp = &mp->ports;
(p = mlock_dereference(*pp, src->br)) != NULL;
pp = &p->next) {
if (!br_port_group_equal(p, pg->key.port, pg->eth_addr))
continue;
if (p->rt_protocol != RTPROT_KERNEL &&
(p->flags & MDB_PG_FLAGS_PERMANENT))
break;
br_multicast_del_pg(mp, p, pp);
break;
}
src->flags &= ~BR_SGRP_F_INSTALLED;
}
/* install S,G and based on src's timer enable or disable forwarding */
static void br_multicast_fwd_src_handle(struct net_bridge_group_src *src)
{
struct net_bridge_port_group_sg_key sg_key;
struct net_bridge_port_group *sg;
u8 old_flags;
br_multicast_fwd_src_add(src);
memset(&sg_key, 0, sizeof(sg_key));
sg_key.addr = src->pg->key.addr;
sg_key.addr.src = src->addr.src;
sg_key.port = src->pg->key.port;
sg = br_sg_port_find(src->br, &sg_key);
if (!sg || (sg->flags & MDB_PG_FLAGS_PERMANENT))
return;
old_flags = sg->flags;
if (timer_pending(&src->timer))
sg->flags &= ~MDB_PG_FLAGS_BLOCKED;
else
sg->flags |= MDB_PG_FLAGS_BLOCKED;
if (old_flags != sg->flags) {
struct net_bridge_mdb_entry *sg_mp;
sg_mp = br_mdb_ip_get(src->br, &sg_key.addr);
if (!sg_mp)
return;
br_mdb_notify(src->br->dev, sg_mp, sg, RTM_NEWMDB);
}
}
static void br_multicast_destroy_mdb_entry(struct net_bridge_mcast_gc *gc)
{
struct net_bridge_mdb_entry *mp;
......@@ -169,7 +534,8 @@ static void br_multicast_group_expired(struct timer_list *t)
struct net_bridge *br = mp->br;
spin_lock(&br->multicast_lock);
if (!netif_running(br->dev) || timer_pending(&mp->timer))
if (hlist_unhashed(&mp->mdb_node) || !netif_running(br->dev) ||
timer_pending(&mp->timer))
goto out;
br_multicast_host_leave(mp, true);
......@@ -194,8 +560,9 @@ static void br_multicast_destroy_group_src(struct net_bridge_mcast_gc *gc)
static void br_multicast_del_group_src(struct net_bridge_group_src *src)
{
struct net_bridge *br = src->pg->port->br;
struct net_bridge *br = src->pg->key.port->br;
br_multicast_fwd_src_remove(src);
hlist_del_init_rcu(&src->node);
src->pg->src_ents--;
hlist_add_head(&src->mcast_gc.gc_node, &br->mcast_gc_list);
......@@ -219,15 +586,21 @@ void br_multicast_del_pg(struct net_bridge_mdb_entry *mp,
struct net_bridge_port_group *pg,
struct net_bridge_port_group __rcu **pp)
{
struct net_bridge *br = pg->port->br;
struct net_bridge *br = pg->key.port->br;
struct net_bridge_group_src *ent;
struct hlist_node *tmp;
rhashtable_remove_fast(&br->sg_port_tbl, &pg->rhnode,
br_sg_port_rht_params);
rcu_assign_pointer(*pp, pg->next);
hlist_del_init(&pg->mglist);
hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node)
br_multicast_del_group_src(ent);
br_mdb_notify(br->dev, mp, pg, RTM_DELMDB);
if (!br_multicast_is_star_g(&mp->addr))
br_multicast_sg_del_exclude_ports(mp);
else
br_multicast_star_g_handle_mode(pg, MCAST_INCLUDE);
hlist_add_head(&pg->mcast_gc.gc_node, &br->mcast_gc_list);
queue_work(system_long_wq, &br->mcast_gc_work);
......@@ -242,7 +615,7 @@ static void br_multicast_find_del_pg(struct net_bridge *br,
struct net_bridge_mdb_entry *mp;
struct net_bridge_port_group *p;
mp = br_mdb_ip_get(br, &pg->addr);
mp = br_mdb_ip_get(br, &pg->key.addr);
if (WARN_ON(!mp))
return;
......@@ -263,7 +636,7 @@ static void br_multicast_port_group_expired(struct timer_list *t)
{
struct net_bridge_port_group *pg = from_timer(pg, t, timer);
struct net_bridge_group_src *src_ent;
struct net_bridge *br = pg->port->br;
struct net_bridge *br = pg->key.port->br;
struct hlist_node *tmp;
bool changed;
......@@ -284,7 +657,10 @@ static void br_multicast_port_group_expired(struct timer_list *t)
if (hlist_empty(&pg->src_list)) {
br_multicast_find_del_pg(br, pg);
} else if (changed) {
struct net_bridge_mdb_entry *mp = br_mdb_ip_get(br, &pg->addr);
struct net_bridge_mdb_entry *mp = br_mdb_ip_get(br, &pg->key.addr);
if (changed && br_multicast_is_star_g(&pg->key.addr))
br_multicast_star_g_handle_mode(pg, MCAST_INCLUDE);
if (WARN_ON(!mp))
goto out;
......@@ -312,7 +688,7 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
u8 sflag, u8 *igmp_type,
bool *need_rexmit)
{
struct net_bridge_port *p = pg ? pg->port : NULL;
struct net_bridge_port *p = pg ? pg->key.port : NULL;
struct net_bridge_group_src *ent;
size_t pkt_size, igmp_hdr_size;
unsigned long now = jiffies;
......@@ -423,7 +799,7 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
if (over_lmqt == time_after(ent->timer.expires,
lmqt) &&
ent->src_query_rexmit_cnt > 0) {
ihv3->srcs[lmqt_srcs++] = ent->addr.u.ip4;
ihv3->srcs[lmqt_srcs++] = ent->addr.src.ip4;
ent->src_query_rexmit_cnt--;
if (need_rexmit && ent->src_query_rexmit_cnt)
*need_rexmit = true;
......@@ -458,7 +834,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
u8 sflag, u8 *igmp_type,
bool *need_rexmit)
{
struct net_bridge_port *p = pg ? pg->port : NULL;
struct net_bridge_port *p = pg ? pg->key.port : NULL;
struct net_bridge_group_src *ent;
size_t pkt_size, mld_hdr_size;
unsigned long now = jiffies;
......@@ -584,7 +960,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
if (over_llqt == time_after(ent->timer.expires,
llqt) &&
ent->src_query_rexmit_cnt > 0) {
mld2q->mld2q_srcs[llqt_srcs++] = ent->addr.u.ip6;
mld2q->mld2q_srcs[llqt_srcs++] = ent->addr.src.ip6;
ent->src_query_rexmit_cnt--;
if (need_rexmit && ent->src_query_rexmit_cnt)
*need_rexmit = true;
......@@ -625,9 +1001,9 @@ static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br,
switch (group->proto) {
case htons(ETH_P_IP):
ip4_dst = ip_dst ? ip_dst->u.ip4 : htonl(INADDR_ALLHOSTS_GROUP);
ip4_dst = ip_dst ? ip_dst->dst.ip4 : htonl(INADDR_ALLHOSTS_GROUP);
return br_ip4_multicast_alloc_query(br, pg,
ip4_dst, group->u.ip4,
ip4_dst, group->dst.ip4,
with_srcs, over_lmqt,
sflag, igmp_type,
need_rexmit);
......@@ -636,13 +1012,13 @@ static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br,
struct in6_addr ip6_dst;
if (ip_dst)
ip6_dst = ip_dst->u.ip6;
ip6_dst = ip_dst->dst.ip6;
else
ipv6_addr_set(&ip6_dst, htonl(0xff020000), 0, 0,
htonl(1));
return br_ip6_multicast_alloc_query(br, pg,
&ip6_dst, &group->u.ip6,
&ip6_dst, &group->dst.ip6,
with_srcs, over_lmqt,
sflag, igmp_type,
need_rexmit);
......@@ -704,7 +1080,10 @@ static void br_multicast_group_src_expired(struct timer_list *t)
if (!hlist_empty(&pg->src_list))
goto out;
br_multicast_find_del_pg(br, pg);
} else {
br_multicast_fwd_src_handle(src);
}
out:
spin_unlock(&br->multicast_lock);
}
......@@ -717,13 +1096,13 @@ br_multicast_find_group_src(struct net_bridge_port_group *pg, struct br_ip *ip)
switch (ip->proto) {
case htons(ETH_P_IP):
hlist_for_each_entry(ent, &pg->src_list, node)
if (ip->u.ip4 == ent->addr.u.ip4)
if (ip->src.ip4 == ent->addr.src.ip4)
return ent;
break;
#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
hlist_for_each_entry(ent, &pg->src_list, node)
if (!ipv6_addr_cmp(&ent->addr.u.ip6, &ip->u.ip6))
if (!ipv6_addr_cmp(&ent->addr.src.ip6, &ip->src.ip6))
return ent;
break;
#endif
......@@ -742,14 +1121,14 @@ br_multicast_new_group_src(struct net_bridge_port_group *pg, struct br_ip *src_i
switch (src_ip->proto) {
case htons(ETH_P_IP):
if (ipv4_is_zeronet(src_ip->u.ip4) ||
ipv4_is_multicast(src_ip->u.ip4))
if (ipv4_is_zeronet(src_ip->src.ip4) ||
ipv4_is_multicast(src_ip->src.ip4))
return NULL;
break;
#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
if (ipv6_addr_any(&src_ip->u.ip6) ||
ipv6_addr_is_multicast(&src_ip->u.ip6))
if (ipv6_addr_any(&src_ip->src.ip6) ||
ipv6_addr_is_multicast(&src_ip->src.ip6))
return NULL;
break;
#endif
......@@ -760,7 +1139,7 @@ br_multicast_new_group_src(struct net_bridge_port_group *pg, struct br_ip *src_i
return NULL;
grp_src->pg = pg;
grp_src->br = pg->port->br;
grp_src->br = pg->key.port->br;
grp_src->addr = *src_ip;
grp_src->mcast_gc.destroy = br_multicast_destroy_group_src;
timer_setup(&grp_src->timer, br_multicast_group_src_expired, 0);
......@@ -777,7 +1156,8 @@ struct net_bridge_port_group *br_multicast_new_port_group(
struct net_bridge_port_group __rcu *next,
unsigned char flags,
const unsigned char *src,
u8 filter_mode)
u8 filter_mode,
u8 rt_protocol)
{
struct net_bridge_port_group *p;
......@@ -785,12 +1165,21 @@ struct net_bridge_port_group *br_multicast_new_port_group(
if (unlikely(!p))
return NULL;
p->addr = *group;
p->port = port;
p->key.addr = *group;
p->key.port = port;
p->flags = flags;
p->filter_mode = filter_mode;
p->rt_protocol = rt_protocol;
p->mcast_gc.destroy = br_multicast_destroy_port_group;
INIT_HLIST_HEAD(&p->src_list);
if (!br_multicast_is_star_g(group) &&
rhashtable_lookup_insert_fast(&port->br->sg_port_tbl, &p->rhnode,
br_sg_port_rht_params)) {
kfree(p);
return NULL;
}
rcu_assign_pointer(p->next, next);
timer_setup(&p->timer, br_multicast_port_group_expired, 0);
timer_setup(&p->rexmit_timer, br_multicast_port_group_rexmit, 0);
......@@ -804,23 +1193,12 @@ struct net_bridge_port_group *br_multicast_new_port_group(
return p;
}
static bool br_port_group_equal(struct net_bridge_port_group *p,
struct net_bridge_port *port,
const unsigned char *src)
{
if (p->port != port)
return false;
if (!(port->flags & BR_MULTICAST_TO_UNICAST))
return true;
return ether_addr_equal(src, p->eth_addr);
}
void br_multicast_host_join(struct net_bridge_mdb_entry *mp, bool notify)
{
if (!mp->host_joined) {
mp->host_joined = true;
if (br_multicast_is_star_g(&mp->addr))
br_multicast_star_g_host_state(mp);
if (notify)
br_mdb_notify(mp->br->dev, mp, NULL, RTM_NEWMDB);
}
......@@ -833,32 +1211,33 @@ void br_multicast_host_leave(struct net_bridge_mdb_entry *mp, bool notify)
return;
mp->host_joined = false;
if (br_multicast_is_star_g(&mp->addr))
br_multicast_star_g_host_state(mp);
if (notify)
br_mdb_notify(mp->br->dev, mp, NULL, RTM_DELMDB);
}
static int br_multicast_add_group(struct net_bridge *br,
static struct net_bridge_port_group *
__br_multicast_add_group(struct net_bridge *br,
struct net_bridge_port *port,
struct br_ip *group,
const unsigned char *src,
u8 filter_mode,
bool igmpv2_mldv1)
bool igmpv2_mldv1,
bool blocked)
{
struct net_bridge_port_group __rcu **pp;
struct net_bridge_port_group *p;
struct net_bridge_port_group *p = NULL;
struct net_bridge_mdb_entry *mp;
unsigned long now = jiffies;
int err;
spin_lock(&br->multicast_lock);
if (!netif_running(br->dev) ||
(port && port->state == BR_STATE_DISABLED))
goto out;
mp = br_multicast_new_group(br, group);
err = PTR_ERR(mp);
if (IS_ERR(mp))
goto err;
return ERR_PTR(PTR_ERR(mp));
if (!port) {
br_multicast_host_join(mp, true);
......@@ -870,14 +1249,19 @@ static int br_multicast_add_group(struct net_bridge *br,
pp = &p->next) {
if (br_port_group_equal(p, port, src))
goto found;
if ((unsigned long)p->port < (unsigned long)port)
if ((unsigned long)p->key.port < (unsigned long)port)
break;
}
p = br_multicast_new_port_group(port, group, *pp, 0, src, filter_mode);
if (unlikely(!p))
goto err;
p = br_multicast_new_port_group(port, group, *pp, 0, src, filter_mode,
RTPROT_KERNEL);
if (unlikely(!p)) {
p = ERR_PTR(-ENOMEM);
goto out;
}
rcu_assign_pointer(*pp, p);
if (blocked)
p->flags |= MDB_PG_FLAGS_BLOCKED;
br_mdb_notify(br->dev, mp, p, RTM_NEWMDB);
found:
......@@ -885,10 +1269,26 @@ static int br_multicast_add_group(struct net_bridge *br,
mod_timer(&p->timer, now + br->multicast_membership_interval);
out:
err = 0;
return p;
}
err:
static int br_multicast_add_group(struct net_bridge *br,
struct net_bridge_port *port,
struct br_ip *group,
const unsigned char *src,
u8 filter_mode,
bool igmpv2_mldv1)
{
struct net_bridge_port_group *pg;
int err;
spin_lock(&br->multicast_lock);
pg = __br_multicast_add_group(br, port, group, src, filter_mode,
igmpv2_mldv1, false);
/* NULL is considered valid for host joined groups */
err = IS_ERR(pg) ? PTR_ERR(pg) : 0;
spin_unlock(&br->multicast_lock);
return err;
}
......@@ -906,7 +1306,7 @@ static int br_ip4_multicast_add_group(struct net_bridge *br,
return 0;
memset(&br_group, 0, sizeof(br_group));
br_group.u.ip4 = group;
br_group.dst.ip4 = group;
br_group.proto = htons(ETH_P_IP);
br_group.vid = vid;
filter_mode = igmpv2 ? MCAST_EXCLUDE : MCAST_INCLUDE;
......@@ -930,7 +1330,7 @@ static int br_ip6_multicast_add_group(struct net_bridge *br,
return 0;
memset(&br_group, 0, sizeof(br_group));
br_group.u.ip6 = *group;
br_group.dst.ip6 = *group;
br_group.proto = htons(ETH_P_IPV6);
br_group.vid = vid;
filter_mode = mldv1 ? MCAST_EXCLUDE : MCAST_INCLUDE;
......@@ -1019,10 +1419,10 @@ static void br_multicast_select_own_querier(struct net_bridge *br,
struct sk_buff *skb)
{
if (ip->proto == htons(ETH_P_IP))
br->ip4_querier.addr.u.ip4 = ip_hdr(skb)->saddr;
br->ip4_querier.addr.src.ip4 = ip_hdr(skb)->saddr;
#if IS_ENABLED(CONFIG_IPV6)
else
br->ip6_querier.addr.u.ip6 = ipv6_hdr(skb)->saddr;
br->ip6_querier.addr.src.ip6 = ipv6_hdr(skb)->saddr;
#endif
}
......@@ -1079,7 +1479,7 @@ static void br_multicast_send_query(struct net_bridge *br,
!br_opt_get(br, BROPT_MULTICAST_QUERIER))
return;
memset(&br_group.u, 0, sizeof(br_group.u));
memset(&br_group.dst, 0, sizeof(br_group.dst));
if (port ? (own_query == &port->ip4_own_query) :
(own_query == &br->ip4_own_query)) {
......@@ -1145,7 +1545,7 @@ static void br_multicast_port_group_rexmit(struct timer_list *t)
{
struct net_bridge_port_group *pg = from_timer(pg, t, rexmit_timer);
struct bridge_mcast_other_query *other_query = NULL;
struct net_bridge *br = pg->port->br;
struct net_bridge *br = pg->key.port->br;
bool need_rexmit = false;
spin_lock(&br->multicast_lock);
......@@ -1154,7 +1554,7 @@ static void br_multicast_port_group_rexmit(struct timer_list *t)
!br_opt_get(br, BROPT_MULTICAST_QUERIER))
goto out;
if (pg->addr.proto == htons(ETH_P_IP))
if (pg->key.addr.proto == htons(ETH_P_IP))
other_query = &br->ip4_other_query;
#if IS_ENABLED(CONFIG_IPV6)
else
......@@ -1166,11 +1566,11 @@ static void br_multicast_port_group_rexmit(struct timer_list *t)
if (pg->grp_query_rexmit_cnt) {
pg->grp_query_rexmit_cnt--;
__br_multicast_send_query(br, pg->port, pg, &pg->addr,
&pg->addr, false, 1, NULL);
__br_multicast_send_query(br, pg->key.port, pg, &pg->key.addr,
&pg->key.addr, false, 1, NULL);
}
__br_multicast_send_query(br, pg->port, pg, &pg->addr,
&pg->addr, true, 0, &need_rexmit);
__br_multicast_send_query(br, pg->key.port, pg, &pg->key.addr,
&pg->key.addr, true, 0, &need_rexmit);
if (pg->grp_query_rexmit_cnt || need_rexmit)
mod_timer(&pg->rexmit_timer, jiffies +
......@@ -1301,10 +1701,17 @@ static int __grp_src_delete_marked(struct net_bridge_port_group *pg)
return deleted;
}
static void __grp_src_mod_timer(struct net_bridge_group_src *src,
unsigned long expires)
{
mod_timer(&src->timer, expires);
br_multicast_fwd_src_handle(src);
}
static void __grp_src_query_marked_and_rexmit(struct net_bridge_port_group *pg)
{
struct bridge_mcast_other_query *other_query = NULL;
struct net_bridge *br = pg->port->br;
struct net_bridge *br = pg->key.port->br;
u32 lmqc = br->multicast_last_member_count;
unsigned long lmqt, lmi, now = jiffies;
struct net_bridge_group_src *ent;
......@@ -1313,7 +1720,7 @@ static void __grp_src_query_marked_and_rexmit(struct net_bridge_port_group *pg)
!br_opt_get(br, BROPT_MULTICAST_ENABLED))
return;
if (pg->addr.proto == htons(ETH_P_IP))
if (pg->key.addr.proto == htons(ETH_P_IP))
other_query = &br->ip4_other_query;
#if IS_ENABLED(CONFIG_IPV6)
else
......@@ -1329,7 +1736,7 @@ static void __grp_src_query_marked_and_rexmit(struct net_bridge_port_group *pg)
other_query &&
!timer_pending(&other_query->timer))
ent->src_query_rexmit_cnt = lmqc;
mod_timer(&ent->timer, lmqt);
__grp_src_mod_timer(ent, lmqt);
}
}
}
......@@ -1338,8 +1745,8 @@ static void __grp_src_query_marked_and_rexmit(struct net_bridge_port_group *pg)
!other_query || timer_pending(&other_query->timer))
return;
__br_multicast_send_query(br, pg->port, pg, &pg->addr,
&pg->addr, true, 1, NULL);
__br_multicast_send_query(br, pg->key.port, pg, &pg->key.addr,
&pg->key.addr, true, 1, NULL);
lmi = now + br->multicast_last_member_interval;
if (!timer_pending(&pg->rexmit_timer) ||
......@@ -1350,14 +1757,14 @@ static void __grp_src_query_marked_and_rexmit(struct net_bridge_port_group *pg)
static void __grp_send_query_and_rexmit(struct net_bridge_port_group *pg)
{
struct bridge_mcast_other_query *other_query = NULL;
struct net_bridge *br = pg->port->br;
struct net_bridge *br = pg->key.port->br;
unsigned long now = jiffies, lmi;
if (!netif_running(br->dev) ||
!br_opt_get(br, BROPT_MULTICAST_ENABLED))
return;
if (pg->addr.proto == htons(ETH_P_IP))
if (pg->key.addr.proto == htons(ETH_P_IP))
other_query = &br->ip4_other_query;
#if IS_ENABLED(CONFIG_IPV6)
else
......@@ -1368,8 +1775,8 @@ static void __grp_send_query_and_rexmit(struct net_bridge_port_group *pg)
other_query && !timer_pending(&other_query->timer)) {
lmi = now + br->multicast_last_member_interval;
pg->grp_query_rexmit_cnt = br->multicast_last_member_count - 1;
__br_multicast_send_query(br, pg->port, pg, &pg->addr,
&pg->addr, false, 0, NULL);
__br_multicast_send_query(br, pg->key.port, pg, &pg->key.addr,
&pg->key.addr, false, 0, NULL);
if (!timer_pending(&pg->rexmit_timer) ||
time_after(pg->rexmit_timer.expires, lmi))
mod_timer(&pg->rexmit_timer, lmi);
......@@ -1389,7 +1796,7 @@ static void __grp_send_query_and_rexmit(struct net_bridge_port_group *pg)
static bool br_multicast_isinc_allow(struct net_bridge_port_group *pg,
void *srcs, u32 nsrcs, size_t src_size)
{
struct net_bridge *br = pg->port->br;
struct net_bridge *br = pg->key.port->br;
struct net_bridge_group_src *ent;
unsigned long now = jiffies;
bool changed = false;
......@@ -1397,9 +1804,9 @@ static bool br_multicast_isinc_allow(struct net_bridge_port_group *pg,
u32 src_idx;
memset(&src_ip, 0, sizeof(src_ip));
src_ip.proto = pg->addr.proto;
src_ip.proto = pg->key.addr.proto;
for (src_idx = 0; src_idx < nsrcs; src_idx++) {
memcpy(&src_ip.u, srcs, src_size);
memcpy(&src_ip.src, srcs, src_size);
ent = br_multicast_find_group_src(pg, &src_ip);
if (!ent) {
ent = br_multicast_new_group_src(pg, &src_ip);
......@@ -1408,7 +1815,7 @@ static bool br_multicast_isinc_allow(struct net_bridge_port_group *pg,
}
if (ent)
mod_timer(&ent->timer, now + br_multicast_gmi(br));
__grp_src_mod_timer(ent, now + br_multicast_gmi(br));
srcs += src_size;
}
......@@ -1431,14 +1838,16 @@ static void __grp_src_isexc_incl(struct net_bridge_port_group *pg,
ent->flags |= BR_SGRP_F_DELETE;
memset(&src_ip, 0, sizeof(src_ip));
src_ip.proto = pg->addr.proto;
src_ip.proto = pg->key.addr.proto;
for (src_idx = 0; src_idx < nsrcs; src_idx++) {
memcpy(&src_ip.u, srcs, src_size);
memcpy(&src_ip.src, srcs, src_size);
ent = br_multicast_find_group_src(pg, &src_ip);
if (ent)
ent->flags &= ~BR_SGRP_F_DELETE;
else
br_multicast_new_group_src(pg, &src_ip);
ent = br_multicast_new_group_src(pg, &src_ip);
if (ent)
br_multicast_fwd_src_handle(ent);
srcs += src_size;
}
......@@ -1454,7 +1863,7 @@ static void __grp_src_isexc_incl(struct net_bridge_port_group *pg,
static bool __grp_src_isexc_excl(struct net_bridge_port_group *pg,
void *srcs, u32 nsrcs, size_t src_size)
{
struct net_bridge *br = pg->port->br;
struct net_bridge *br = pg->key.port->br;
struct net_bridge_group_src *ent;
unsigned long now = jiffies;
bool changed = false;
......@@ -1465,16 +1874,16 @@ static bool __grp_src_isexc_excl(struct net_bridge_port_group *pg,
ent->flags |= BR_SGRP_F_DELETE;
memset(&src_ip, 0, sizeof(src_ip));
src_ip.proto = pg->addr.proto;
src_ip.proto = pg->key.addr.proto;
for (src_idx = 0; src_idx < nsrcs; src_idx++) {
memcpy(&src_ip.u, srcs, src_size);
memcpy(&src_ip.src, srcs, src_size);
ent = br_multicast_find_group_src(pg, &src_ip);
if (ent) {
ent->flags &= ~BR_SGRP_F_DELETE;
} else {
ent = br_multicast_new_group_src(pg, &src_ip);
if (ent) {
mod_timer(&ent->timer,
__grp_src_mod_timer(ent,
now + br_multicast_gmi(br));
changed = true;
}
......@@ -1491,12 +1900,13 @@ static bool __grp_src_isexc_excl(struct net_bridge_port_group *pg,
static bool br_multicast_isexc(struct net_bridge_port_group *pg,
void *srcs, u32 nsrcs, size_t src_size)
{
struct net_bridge *br = pg->port->br;
struct net_bridge *br = pg->key.port->br;
bool changed = false;
switch (pg->filter_mode) {
case MCAST_INCLUDE:
__grp_src_isexc_incl(pg, srcs, nsrcs, src_size);
br_multicast_star_g_handle_mode(pg, MCAST_EXCLUDE);
changed = true;
break;
case MCAST_EXCLUDE:
......@@ -1517,7 +1927,7 @@ static bool br_multicast_isexc(struct net_bridge_port_group *pg,
static bool __grp_src_toin_incl(struct net_bridge_port_group *pg,
void *srcs, u32 nsrcs, size_t src_size)
{
struct net_bridge *br = pg->port->br;
struct net_bridge *br = pg->key.port->br;
u32 src_idx, to_send = pg->src_ents;
struct net_bridge_group_src *ent;
unsigned long now = jiffies;
......@@ -1528,9 +1938,9 @@ static bool __grp_src_toin_incl(struct net_bridge_port_group *pg,
ent->flags |= BR_SGRP_F_SEND;
memset(&src_ip, 0, sizeof(src_ip));
src_ip.proto = pg->addr.proto;
src_ip.proto = pg->key.addr.proto;
for (src_idx = 0; src_idx < nsrcs; src_idx++) {
memcpy(&src_ip.u, srcs, src_size);
memcpy(&src_ip.src, srcs, src_size);
ent = br_multicast_find_group_src(pg, &src_ip);
if (ent) {
ent->flags &= ~BR_SGRP_F_SEND;
......@@ -1541,7 +1951,7 @@ static bool __grp_src_toin_incl(struct net_bridge_port_group *pg,
changed = true;
}
if (ent)
mod_timer(&ent->timer, now + br_multicast_gmi(br));
__grp_src_mod_timer(ent, now + br_multicast_gmi(br));
srcs += src_size;
}
......@@ -1559,7 +1969,7 @@ static bool __grp_src_toin_incl(struct net_bridge_port_group *pg,
static bool __grp_src_toin_excl(struct net_bridge_port_group *pg,
void *srcs, u32 nsrcs, size_t src_size)
{
struct net_bridge *br = pg->port->br;
struct net_bridge *br = pg->key.port->br;
u32 src_idx, to_send = pg->src_ents;
struct net_bridge_group_src *ent;
unsigned long now = jiffies;
......@@ -1571,9 +1981,9 @@ static bool __grp_src_toin_excl(struct net_bridge_port_group *pg,
ent->flags |= BR_SGRP_F_SEND;
memset(&src_ip, 0, sizeof(src_ip));
src_ip.proto = pg->addr.proto;
src_ip.proto = pg->key.addr.proto;
for (src_idx = 0; src_idx < nsrcs; src_idx++) {
memcpy(&src_ip.u, srcs, src_size);
memcpy(&src_ip.src, srcs, src_size);
ent = br_multicast_find_group_src(pg, &src_ip);
if (ent) {
if (timer_pending(&ent->timer)) {
......@@ -1586,7 +1996,7 @@ static bool __grp_src_toin_excl(struct net_bridge_port_group *pg,
changed = true;
}
if (ent)
mod_timer(&ent->timer, now + br_multicast_gmi(br));
__grp_src_mod_timer(ent, now + br_multicast_gmi(br));
srcs += src_size;
}
......@@ -1632,17 +2042,19 @@ static void __grp_src_toex_incl(struct net_bridge_port_group *pg,
ent->flags = (ent->flags & ~BR_SGRP_F_SEND) | BR_SGRP_F_DELETE;
memset(&src_ip, 0, sizeof(src_ip));
src_ip.proto = pg->addr.proto;
src_ip.proto = pg->key.addr.proto;
for (src_idx = 0; src_idx < nsrcs; src_idx++) {
memcpy(&src_ip.u, srcs, src_size);
memcpy(&src_ip.src, srcs, src_size);
ent = br_multicast_find_group_src(pg, &src_ip);
if (ent) {
ent->flags = (ent->flags & ~BR_SGRP_F_DELETE) |
BR_SGRP_F_SEND;
to_send++;
} else {
br_multicast_new_group_src(pg, &src_ip);
ent = br_multicast_new_group_src(pg, &src_ip);
}
if (ent)
br_multicast_fwd_src_handle(ent);
srcs += src_size;
}
......@@ -1670,16 +2082,16 @@ static bool __grp_src_toex_excl(struct net_bridge_port_group *pg,
ent->flags = (ent->flags & ~BR_SGRP_F_SEND) | BR_SGRP_F_DELETE;
memset(&src_ip, 0, sizeof(src_ip));
src_ip.proto = pg->addr.proto;
src_ip.proto = pg->key.addr.proto;
for (src_idx = 0; src_idx < nsrcs; src_idx++) {
memcpy(&src_ip.u, srcs, src_size);
memcpy(&src_ip.src, srcs, src_size);
ent = br_multicast_find_group_src(pg, &src_ip);
if (ent) {
ent->flags &= ~BR_SGRP_F_DELETE;
} else {
ent = br_multicast_new_group_src(pg, &src_ip);
if (ent) {
mod_timer(&ent->timer, pg->timer.expires);
__grp_src_mod_timer(ent, pg->timer.expires);
changed = true;
}
}
......@@ -1701,12 +2113,13 @@ static bool __grp_src_toex_excl(struct net_bridge_port_group *pg,
static bool br_multicast_toex(struct net_bridge_port_group *pg,
void *srcs, u32 nsrcs, size_t src_size)
{
struct net_bridge *br = pg->port->br;
struct net_bridge *br = pg->key.port->br;
bool changed = false;
switch (pg->filter_mode) {
case MCAST_INCLUDE:
__grp_src_toex_incl(pg, srcs, nsrcs, src_size);
br_multicast_star_g_handle_mode(pg, MCAST_EXCLUDE);
changed = true;
break;
case MCAST_EXCLUDE:
......@@ -1734,9 +2147,9 @@ static void __grp_src_block_incl(struct net_bridge_port_group *pg,
ent->flags &= ~BR_SGRP_F_SEND;
memset(&src_ip, 0, sizeof(src_ip));
src_ip.proto = pg->addr.proto;
src_ip.proto = pg->key.addr.proto;
for (src_idx = 0; src_idx < nsrcs; src_idx++) {
memcpy(&src_ip.u, srcs, src_size);
memcpy(&src_ip.src, srcs, src_size);
ent = br_multicast_find_group_src(pg, &src_ip);
if (ent) {
ent->flags |= BR_SGRP_F_SEND;
......@@ -1749,7 +2162,7 @@ static void __grp_src_block_incl(struct net_bridge_port_group *pg,
__grp_src_query_marked_and_rexmit(pg);
if (pg->filter_mode == MCAST_INCLUDE && hlist_empty(&pg->src_list))
br_multicast_find_del_pg(pg->port->br, pg);
br_multicast_find_del_pg(pg->key.port->br, pg);
}
/* State Msg type New state Actions
......@@ -1768,14 +2181,14 @@ static bool __grp_src_block_excl(struct net_bridge_port_group *pg,
ent->flags &= ~BR_SGRP_F_SEND;
memset(&src_ip, 0, sizeof(src_ip));
src_ip.proto = pg->addr.proto;
src_ip.proto = pg->key.addr.proto;
for (src_idx = 0; src_idx < nsrcs; src_idx++) {
memcpy(&src_ip.u, srcs, src_size);
memcpy(&src_ip.src, srcs, src_size);
ent = br_multicast_find_group_src(pg, &src_ip);
if (!ent) {
ent = br_multicast_new_group_src(pg, &src_ip);
if (ent) {
mod_timer(&ent->timer, pg->timer.expires);
__grp_src_mod_timer(ent, pg->timer.expires);
changed = true;
}
}
......@@ -2071,16 +2484,16 @@ static bool br_ip4_multicast_select_querier(struct net_bridge *br,
!timer_pending(&br->ip4_other_query.timer))
goto update;
if (!br->ip4_querier.addr.u.ip4)
if (!br->ip4_querier.addr.src.ip4)
goto update;
if (ntohl(saddr) <= ntohl(br->ip4_querier.addr.u.ip4))
if (ntohl(saddr) <= ntohl(br->ip4_querier.addr.src.ip4))
goto update;
return false;
update:
br->ip4_querier.addr.u.ip4 = saddr;
br->ip4_querier.addr.src.ip4 = saddr;
/* update protected by general multicast_lock by caller */
rcu_assign_pointer(br->ip4_querier.port, port);
......@@ -2097,13 +2510,13 @@ static bool br_ip6_multicast_select_querier(struct net_bridge *br,
!timer_pending(&br->ip6_other_query.timer))
goto update;
if (ipv6_addr_cmp(saddr, &br->ip6_querier.addr.u.ip6) <= 0)
if (ipv6_addr_cmp(saddr, &br->ip6_querier.addr.src.ip6) <= 0)
goto update;
return false;
update:
br->ip6_querier.addr.u.ip6 = *saddr;
br->ip6_querier.addr.src.ip6 = *saddr;
/* update protected by general multicast_lock by caller */
rcu_assign_pointer(br->ip6_querier.port, port);
......@@ -2118,10 +2531,10 @@ static bool br_multicast_select_querier(struct net_bridge *br,
{
switch (saddr->proto) {
case htons(ETH_P_IP):
return br_ip4_multicast_select_querier(br, port, saddr->u.ip4);
return br_ip4_multicast_select_querier(br, port, saddr->src.ip4);
#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
return br_ip6_multicast_select_querier(br, port, &saddr->u.ip6);
return br_ip6_multicast_select_querier(br, port, &saddr->src.ip6);
#endif
}
......@@ -2263,7 +2676,7 @@ static void br_ip4_multicast_query(struct net_bridge *br,
if (!group) {
saddr.proto = htons(ETH_P_IP);
saddr.u.ip4 = iph->saddr;
saddr.src.ip4 = iph->saddr;
br_multicast_query_received(br, port, &br->ip4_other_query,
&saddr, max_delay);
......@@ -2351,7 +2764,7 @@ static int br_ip6_multicast_query(struct net_bridge *br,
if (is_general_query) {
saddr.proto = htons(ETH_P_IPV6);
saddr.u.ip6 = ipv6_hdr(skb)->saddr;
saddr.src.ip6 = ipv6_hdr(skb)->saddr;
br_multicast_query_received(br, port, &br->ip6_other_query,
&saddr, max_delay);
......@@ -2475,7 +2888,7 @@ br_multicast_leave_group(struct net_bridge *br,
for (p = mlock_dereference(mp->ports, br);
p != NULL;
p = mlock_dereference(p->next, br)) {
if (p->port != port)
if (p->key.port != port)
continue;
if (!hlist_unhashed(&p->mglist) &&
......@@ -2506,7 +2919,7 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br,
own_query = port ? &port->ip4_own_query : &br->ip4_own_query;
memset(&br_group, 0, sizeof(br_group));
br_group.u.ip4 = group;
br_group.dst.ip4 = group;
br_group.proto = htons(ETH_P_IP);
br_group.vid = vid;
......@@ -2530,7 +2943,7 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br,
own_query = port ? &port->ip6_own_query : &br->ip6_own_query;
memset(&br_group, 0, sizeof(br_group));
br_group.u.ip6 = *group;
br_group.dst.ip6 = *group;
br_group.proto = htons(ETH_P_IPV6);
br_group.vid = vid;
......@@ -3235,7 +3648,7 @@ int br_multicast_list_adjacent(struct net_device *dev,
if (!entry)
goto unlock;
entry->addr = group->addr;
entry->addr = group->key.addr;
list_add(&entry->list, br_ip_list);
count++;
}
......@@ -3492,10 +3905,23 @@ void br_multicast_get_stats(const struct net_bridge *br,
int br_mdb_hash_init(struct net_bridge *br)
{
return rhashtable_init(&br->mdb_hash_tbl, &br_mdb_rht_params);
int err;
err = rhashtable_init(&br->sg_port_tbl, &br_sg_port_rht_params);
if (err)
return err;
err = rhashtable_init(&br->mdb_hash_tbl, &br_mdb_rht_params);
if (err) {
rhashtable_destroy(&br->sg_port_tbl);
return err;
}
return 0;
}
void br_mdb_hash_fini(struct net_bridge *br)
{
rhashtable_destroy(&br->sg_port_tbl);
rhashtable_destroy(&br->mdb_hash_tbl);
}
......@@ -213,11 +213,14 @@ struct net_bridge_fdb_entry {
#define MDB_PG_FLAGS_PERMANENT BIT(0)
#define MDB_PG_FLAGS_OFFLOAD BIT(1)
#define MDB_PG_FLAGS_FAST_LEAVE BIT(2)
#define MDB_PG_FLAGS_STAR_EXCL BIT(3)
#define MDB_PG_FLAGS_BLOCKED BIT(4)
#define PG_SRC_ENT_LIMIT 32
#define BR_SGRP_F_DELETE BIT(0)
#define BR_SGRP_F_SEND BIT(1)
#define BR_SGRP_F_INSTALLED BIT(2)
struct net_bridge_mcast_gc {
struct hlist_node gc_node;
......@@ -238,14 +241,19 @@ struct net_bridge_group_src {
struct rcu_head rcu;
};
struct net_bridge_port_group {
struct net_bridge_port_group_sg_key {
struct net_bridge_port *port;
struct net_bridge_port_group __rcu *next;
struct br_ip addr;
};
struct net_bridge_port_group {
struct net_bridge_port_group __rcu *next;
struct net_bridge_port_group_sg_key key;
unsigned char eth_addr[ETH_ALEN] __aligned(2);
unsigned char flags;
unsigned char filter_mode;
unsigned char grp_query_rexmit_cnt;
unsigned char rt_protocol;
struct hlist_head src_list;
unsigned int src_ents;
......@@ -253,6 +261,7 @@ struct net_bridge_port_group {
struct timer_list rexmit_timer;
struct hlist_node mglist;
struct rhash_head rhnode;
struct net_bridge_mcast_gc mcast_gc;
struct rcu_head rcu;
};
......@@ -440,6 +449,7 @@ struct net_bridge {
unsigned long multicast_startup_query_interval;
struct rhashtable mdb_hash_tbl;
struct rhashtable sg_port_tbl;
struct hlist_head mcast_gc_list;
struct hlist_head mdb_list;
......@@ -804,7 +814,7 @@ struct net_bridge_port_group *
br_multicast_new_port_group(struct net_bridge_port *port, struct br_ip *group,
struct net_bridge_port_group __rcu *next,
unsigned char flags, const unsigned char *src,
u8 filter_mode);
u8 filter_mode, u8 rt_protocol);
int br_mdb_hash_init(struct net_bridge *br);
void br_mdb_hash_fini(struct net_bridge *br);
void br_mdb_notify(struct net_device *dev, struct net_bridge_mdb_entry *mp,
......@@ -825,6 +835,10 @@ void br_mdb_init(void);
void br_mdb_uninit(void);
void br_multicast_host_join(struct net_bridge_mdb_entry *mp, bool notify);
void br_multicast_host_leave(struct net_bridge_mdb_entry *mp, bool notify);
void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg,
u8 filter_mode);
void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp,
struct net_bridge_port_group *sg);
#define mlock_dereference(X, br) \
rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
......@@ -873,6 +887,35 @@ static inline bool br_multicast_querier_exists(struct net_bridge *br,
}
}
static inline bool br_multicast_is_star_g(const struct br_ip *ip)
{
switch (ip->proto) {
case htons(ETH_P_IP):
return ipv4_is_zeronet(ip->src.ip4);
#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
return ipv6_addr_any(&ip->src.ip6);
#endif
default:
return false;
}
}
static inline bool br_multicast_should_handle_mode(const struct net_bridge *br,
__be16 proto)
{
switch (proto) {
case htons(ETH_P_IP):
return !!(br->multicast_igmp_version == 3);
#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
return !!(br->multicast_mld_version == 2);
#endif
default:
return false;
}
}
static inline int br_multicast_igmp_type(const struct sk_buff *skb)
{
return BR_INPUT_SKB_CB(skb)->igmp;
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册