mirror of
https://github.com/torvalds/linux.git
synced 2024-12-23 19:31:53 +00:00
2594e9064a
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>
316 lines
7.1 KiB
C
316 lines
7.1 KiB
C
/*
|
|
* Forwarding decision
|
|
* Linux ethernet bridge
|
|
*
|
|
* Authors:
|
|
* Lennert Buytenhek <buytenh@gnu.org>
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; either version
|
|
* 2 of the License, or (at your option) any later version.
|
|
*/
|
|
|
|
#include <linux/err.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/netdevice.h>
|
|
#include <linux/netpoll.h>
|
|
#include <linux/skbuff.h>
|
|
#include <linux/if_vlan.h>
|
|
#include <linux/netfilter_bridge.h>
|
|
#include "br_private.h"
|
|
|
|
static int deliver_clone(const struct net_bridge_port *prev,
|
|
struct sk_buff *skb,
|
|
void (*__packet_hook)(const struct net_bridge_port *p,
|
|
struct sk_buff *skb));
|
|
|
|
/* Don't forward packets to originating port or forwarding disabled */
|
|
static inline int should_deliver(const struct net_bridge_port *p,
|
|
const struct sk_buff *skb)
|
|
{
|
|
struct net_bridge_vlan_group *vg;
|
|
|
|
vg = nbp_vlan_group(p);
|
|
return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) &&
|
|
br_allowed_egress(vg, skb) && p->state == BR_STATE_FORWARDING;
|
|
}
|
|
|
|
int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
|
|
{
|
|
if (!is_skb_forwardable(skb->dev, skb))
|
|
goto drop;
|
|
|
|
skb_push(skb, ETH_HLEN);
|
|
br_drop_fake_rtable(skb);
|
|
skb_sender_cpu_clear(skb);
|
|
|
|
if (skb->ip_summed == CHECKSUM_PARTIAL &&
|
|
(skb->protocol == htons(ETH_P_8021Q) ||
|
|
skb->protocol == htons(ETH_P_8021AD))) {
|
|
int depth;
|
|
|
|
if (!__vlan_get_protocol(skb, skb->protocol, &depth))
|
|
goto drop;
|
|
|
|
skb_set_network_header(skb, depth);
|
|
}
|
|
|
|
dev_queue_xmit(skb);
|
|
|
|
return 0;
|
|
|
|
drop:
|
|
kfree_skb(skb);
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit);
|
|
|
|
int br_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
|
|
{
|
|
return NF_HOOK(NFPROTO_BRIDGE, NF_BR_POST_ROUTING,
|
|
net, sk, skb, NULL, skb->dev,
|
|
br_dev_queue_push_xmit);
|
|
|
|
}
|
|
EXPORT_SYMBOL_GPL(br_forward_finish);
|
|
|
|
static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb)
|
|
{
|
|
struct net_bridge_vlan_group *vg;
|
|
|
|
vg = nbp_vlan_group(to);
|
|
skb = br_handle_vlan(to->br, vg, skb);
|
|
if (!skb)
|
|
return;
|
|
|
|
skb->dev = to->dev;
|
|
|
|
if (unlikely(netpoll_tx_running(to->br->dev))) {
|
|
if (!is_skb_forwardable(skb->dev, skb))
|
|
kfree_skb(skb);
|
|
else {
|
|
skb_push(skb, ETH_HLEN);
|
|
br_netpoll_send_skb(to, skb);
|
|
}
|
|
return;
|
|
}
|
|
|
|
NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT,
|
|
dev_net(skb->dev), NULL, skb,NULL, skb->dev,
|
|
br_forward_finish);
|
|
}
|
|
|
|
static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb)
|
|
{
|
|
struct net_bridge_vlan_group *vg;
|
|
struct net_device *indev;
|
|
|
|
if (skb_warn_if_lro(skb)) {
|
|
kfree_skb(skb);
|
|
return;
|
|
}
|
|
|
|
vg = nbp_vlan_group(to);
|
|
skb = br_handle_vlan(to->br, vg, skb);
|
|
if (!skb)
|
|
return;
|
|
|
|
indev = skb->dev;
|
|
skb->dev = to->dev;
|
|
skb_forward_csum(skb);
|
|
|
|
NF_HOOK(NFPROTO_BRIDGE, NF_BR_FORWARD,
|
|
dev_net(indev), NULL, skb, indev, skb->dev,
|
|
br_forward_finish);
|
|
}
|
|
|
|
/* called with rcu_read_lock */
|
|
void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb)
|
|
{
|
|
if (to && should_deliver(to, skb)) {
|
|
__br_deliver(to, skb);
|
|
return;
|
|
}
|
|
|
|
kfree_skb(skb);
|
|
}
|
|
EXPORT_SYMBOL_GPL(br_deliver);
|
|
|
|
/* called with rcu_read_lock */
|
|
void br_forward(const struct net_bridge_port *to, struct sk_buff *skb, struct sk_buff *skb0)
|
|
{
|
|
if (should_deliver(to, skb)) {
|
|
if (skb0)
|
|
deliver_clone(to, skb, __br_forward);
|
|
else
|
|
__br_forward(to, skb);
|
|
return;
|
|
}
|
|
|
|
if (!skb0)
|
|
kfree_skb(skb);
|
|
}
|
|
|
|
static int deliver_clone(const struct net_bridge_port *prev,
|
|
struct sk_buff *skb,
|
|
void (*__packet_hook)(const struct net_bridge_port *p,
|
|
struct sk_buff *skb))
|
|
{
|
|
struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev;
|
|
|
|
skb = skb_clone(skb, GFP_ATOMIC);
|
|
if (!skb) {
|
|
dev->stats.tx_dropped++;
|
|
return -ENOMEM;
|
|
}
|
|
|
|
__packet_hook(prev, skb);
|
|
return 0;
|
|
}
|
|
|
|
static struct net_bridge_port *maybe_deliver(
|
|
struct net_bridge_port *prev, struct net_bridge_port *p,
|
|
struct sk_buff *skb,
|
|
void (*__packet_hook)(const struct net_bridge_port *p,
|
|
struct sk_buff *skb))
|
|
{
|
|
int err;
|
|
|
|
if (!should_deliver(p, skb))
|
|
return prev;
|
|
|
|
if (!prev)
|
|
goto out;
|
|
|
|
err = deliver_clone(prev, skb, __packet_hook);
|
|
if (err)
|
|
return ERR_PTR(err);
|
|
|
|
out:
|
|
return p;
|
|
}
|
|
|
|
/* called under bridge lock */
|
|
static void br_flood(struct net_bridge *br, struct sk_buff *skb,
|
|
struct sk_buff *skb0,
|
|
void (*__packet_hook)(const struct net_bridge_port *p,
|
|
struct sk_buff *skb),
|
|
bool unicast)
|
|
{
|
|
struct net_bridge_port *p;
|
|
struct net_bridge_port *prev;
|
|
|
|
prev = NULL;
|
|
|
|
list_for_each_entry_rcu(p, &br->port_list, list) {
|
|
/* Do not flood unicast traffic to ports that turn it off */
|
|
if (unicast && !(p->flags & BR_FLOOD))
|
|
continue;
|
|
|
|
/* Do not flood to ports that enable proxy ARP */
|
|
if (p->flags & BR_PROXYARP)
|
|
continue;
|
|
if ((p->flags & BR_PROXYARP_WIFI) &&
|
|
BR_INPUT_SKB_CB(skb)->proxyarp_replied)
|
|
continue;
|
|
|
|
prev = maybe_deliver(prev, p, skb, __packet_hook);
|
|
if (IS_ERR(prev))
|
|
goto out;
|
|
}
|
|
|
|
if (!prev)
|
|
goto out;
|
|
|
|
if (skb0)
|
|
deliver_clone(prev, skb, __packet_hook);
|
|
else
|
|
__packet_hook(prev, skb);
|
|
return;
|
|
|
|
out:
|
|
if (!skb0)
|
|
kfree_skb(skb);
|
|
}
|
|
|
|
|
|
/* called with rcu_read_lock */
|
|
void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb, bool unicast)
|
|
{
|
|
br_flood(br, skb, NULL, __br_deliver, unicast);
|
|
}
|
|
|
|
/* called under bridge lock */
|
|
void br_flood_forward(struct net_bridge *br, struct sk_buff *skb,
|
|
struct sk_buff *skb2, bool unicast)
|
|
{
|
|
br_flood(br, skb, skb2, __br_forward, unicast);
|
|
}
|
|
|
|
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
|
|
/* called with rcu_read_lock */
|
|
static void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
|
|
struct sk_buff *skb, struct sk_buff *skb0,
|
|
void (*__packet_hook)(
|
|
const struct net_bridge_port *p,
|
|
struct sk_buff *skb))
|
|
{
|
|
struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev;
|
|
struct net_bridge *br = netdev_priv(dev);
|
|
struct net_bridge_port *prev = NULL;
|
|
struct net_bridge_port_group *p;
|
|
struct hlist_node *rp;
|
|
|
|
rp = rcu_dereference(hlist_first_rcu(&br->router_list));
|
|
p = mdst ? rcu_dereference(mdst->ports) : NULL;
|
|
while (p || rp) {
|
|
struct net_bridge_port *port, *lport, *rport;
|
|
|
|
lport = p ? p->port : NULL;
|
|
rport = rp ? hlist_entry(rp, struct net_bridge_port, rlist) :
|
|
NULL;
|
|
|
|
port = (unsigned long)lport > (unsigned long)rport ?
|
|
lport : rport;
|
|
|
|
prev = maybe_deliver(prev, port, skb, __packet_hook);
|
|
if (IS_ERR(prev))
|
|
goto out;
|
|
|
|
if ((unsigned long)lport >= (unsigned long)port)
|
|
p = rcu_dereference(p->next);
|
|
if ((unsigned long)rport >= (unsigned long)port)
|
|
rp = rcu_dereference(hlist_next_rcu(rp));
|
|
}
|
|
|
|
if (!prev)
|
|
goto out;
|
|
|
|
if (skb0)
|
|
deliver_clone(prev, skb, __packet_hook);
|
|
else
|
|
__packet_hook(prev, skb);
|
|
return;
|
|
|
|
out:
|
|
if (!skb0)
|
|
kfree_skb(skb);
|
|
}
|
|
|
|
/* called with rcu_read_lock */
|
|
void br_multicast_deliver(struct net_bridge_mdb_entry *mdst,
|
|
struct sk_buff *skb)
|
|
{
|
|
br_multicast_flood(mdst, skb, NULL, __br_deliver);
|
|
}
|
|
|
|
/* called with rcu_read_lock */
|
|
void br_multicast_forward(struct net_bridge_mdb_entry *mdst,
|
|
struct sk_buff *skb, struct sk_buff *skb2)
|
|
{
|
|
br_multicast_flood(mdst, skb, skb2, __br_forward);
|
|
}
|
|
#endif
|