linux_dsm_epyc7002/net/bridge/br_forward.c
Yunjian Wang 28c1382fa2 net: bridge: Fix ethernet header pointer before check skb forwardable
The skb header should be set to ethernet header before using
is_skb_forwardable. Because the ethernet header length has been
considered in is_skb_forwardable(including dev->hard_header_len
length).

To reproduce the issue:
1, add 2 ports on linux bridge br using following commands:
$ brctl addbr br
$ brctl addif br eth0
$ brctl addif br eth1
2, the MTU of eth0 and eth1 is 1500
3, send a packet(Data 1480, UDP 8, IP 20, Ethernet 14, VLAN 4)
from eth0 to eth1

So the expect result is packet larger than 1500 cannot pass through
eth0 and eth1. But currently, the packet passes through success, it
means eth1's MTU limit doesn't take effect.

Fixes: f6367b4660 ("bridge: use is_skb_forwardable in forward path")
Cc: bridge@lists.linux-foundation.org
Cc: Nkolay Aleksandrov <nikolay@cumulusnetworks.com>
Cc: Roopa Prabhu <roopa@cumulusnetworks.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-17 21:55:15 -08:00

334 lines
7.6 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"
/* 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_rcu(p);
return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) &&
br_allowed_egress(vg, skb) && p->state == BR_STATE_FORWARDING &&
nbp_switchdev_allowed_egress(p, skb) &&
!br_skb_isolated(p, skb);
}
int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
{
skb_push(skb, ETH_HLEN);
if (!is_skb_forwardable(skb->dev, skb))
goto drop;
br_drop_fake_rtable(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)
{
skb->tstamp = 0;
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_forward(const struct net_bridge_port *to,
struct sk_buff *skb, bool local_orig)
{
struct net_bridge_vlan_group *vg;
struct net_device *indev;
struct net *net;
int br_hook;
vg = nbp_vlan_group_rcu(to);
skb = br_handle_vlan(to->br, to, vg, skb);
if (!skb)
return;
indev = skb->dev;
skb->dev = to->dev;
if (!local_orig) {
if (skb_warn_if_lro(skb)) {
kfree_skb(skb);
return;
}
br_hook = NF_BR_FORWARD;
skb_forward_csum(skb);
net = dev_net(indev);
} else {
if (unlikely(netpoll_tx_running(to->br->dev))) {
skb_push(skb, ETH_HLEN);
if (!is_skb_forwardable(skb->dev, skb))
kfree_skb(skb);
else
br_netpoll_send_skb(to, skb);
return;
}
br_hook = NF_BR_LOCAL_OUT;
net = dev_net(skb->dev);
indev = NULL;
}
NF_HOOK(NFPROTO_BRIDGE, br_hook,
net, NULL, skb, indev, skb->dev,
br_forward_finish);
}
static int deliver_clone(const struct net_bridge_port *prev,
struct sk_buff *skb, bool local_orig)
{
struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev;
skb = skb_clone(skb, GFP_ATOMIC);
if (!skb) {
dev->stats.tx_dropped++;
return -ENOMEM;
}
__br_forward(prev, skb, local_orig);
return 0;
}
/**
* br_forward - forward a packet to a specific port
* @to: destination port
* @skb: packet being forwarded
* @local_rcv: packet will be received locally after forwarding
* @local_orig: packet is locally originated
*
* Should be called with rcu_read_lock.
*/
void br_forward(const struct net_bridge_port *to,
struct sk_buff *skb, bool local_rcv, bool local_orig)
{
if (unlikely(!to))
goto out;
/* redirect to backup link if the destination port is down */
if (rcu_access_pointer(to->backup_port) && !netif_carrier_ok(to->dev)) {
struct net_bridge_port *backup_port;
backup_port = rcu_dereference(to->backup_port);
if (unlikely(!backup_port))
goto out;
to = backup_port;
}
if (should_deliver(to, skb)) {
if (local_rcv)
deliver_clone(to, skb, local_orig);
else
__br_forward(to, skb, local_orig);
return;
}
out:
if (!local_rcv)
kfree_skb(skb);
}
EXPORT_SYMBOL_GPL(br_forward);
static struct net_bridge_port *maybe_deliver(
struct net_bridge_port *prev, struct net_bridge_port *p,
struct sk_buff *skb, bool local_orig)
{
int err;
if (!should_deliver(p, skb))
return prev;
if (!prev)
goto out;
err = deliver_clone(prev, skb, local_orig);
if (err)
return ERR_PTR(err);
out:
return p;
}
/* called under rcu_read_lock */
void br_flood(struct net_bridge *br, struct sk_buff *skb,
enum br_pkt_type pkt_type, bool local_rcv, bool local_orig)
{
u8 igmp_type = br_multicast_igmp_type(skb);
struct net_bridge_port *prev = NULL;
struct net_bridge_port *p;
list_for_each_entry_rcu(p, &br->port_list, list) {
/* Do not flood unicast traffic to ports that turn it off, nor
* other traffic if flood off, except for traffic we originate
*/
switch (pkt_type) {
case BR_PKT_UNICAST:
if (!(p->flags & BR_FLOOD))
continue;
break;
case BR_PKT_MULTICAST:
if (!(p->flags & BR_MCAST_FLOOD) && skb->dev != br->dev)
continue;
break;
case BR_PKT_BROADCAST:
if (!(p->flags & BR_BCAST_FLOOD) && skb->dev != br->dev)
continue;
break;
}
/* Do not flood to ports that enable proxy ARP */
if (p->flags & BR_PROXYARP)
continue;
if ((p->flags & (BR_PROXYARP_WIFI | BR_NEIGH_SUPPRESS)) &&
BR_INPUT_SKB_CB(skb)->proxyarp_replied)
continue;
prev = maybe_deliver(prev, p, skb, local_orig);
if (IS_ERR(prev))
goto out;
if (prev == p)
br_multicast_count(p->br, p, skb, igmp_type,
BR_MCAST_DIR_TX);
}
if (!prev)
goto out;
if (local_rcv)
deliver_clone(prev, skb, local_orig);
else
__br_forward(prev, skb, local_orig);
return;
out:
if (!local_rcv)
kfree_skb(skb);
}
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb,
const unsigned char *addr, bool local_orig)
{
struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev;
const unsigned char *src = eth_hdr(skb)->h_source;
if (!should_deliver(p, skb))
return;
/* Even with hairpin, no soliloquies - prevent breaking IPv6 DAD */
if (skb->dev == p->dev && ether_addr_equal(src, addr))
return;
skb = skb_copy(skb, GFP_ATOMIC);
if (!skb) {
dev->stats.tx_dropped++;
return;
}
if (!is_broadcast_ether_addr(addr))
memcpy(eth_hdr(skb)->h_dest, addr, ETH_ALEN);
__br_forward(p, skb, local_orig);
}
/* called with rcu_read_lock */
void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
struct sk_buff *skb,
bool local_rcv, bool local_orig)
{
struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev;
u8 igmp_type = br_multicast_igmp_type(skb);
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 = hlist_entry_safe(rp, struct net_bridge_port, rlist);
if ((unsigned long)lport > (unsigned long)rport) {
port = lport;
if (port->flags & BR_MULTICAST_TO_UNICAST) {
maybe_deliver_addr(lport, skb, p->eth_addr,
local_orig);
goto delivered;
}
} else {
port = rport;
}
prev = maybe_deliver(prev, port, skb, local_orig);
delivered:
if (IS_ERR(prev))
goto out;
if (prev == port)
br_multicast_count(port->br, port, skb, igmp_type,
BR_MCAST_DIR_TX);
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 (local_rcv)
deliver_clone(prev, skb, local_orig);
else
__br_forward(prev, skb, local_orig);
return;
out:
if (!local_rcv)
kfree_skb(skb);
}
#endif