kernel_optimize_test/net/bridge/br_forward.c
Roopa Prabhu b7af1472af bridge: set is_local and is_static before fdb entry is added to the fdb hashtable
Problem Description:
We can add fdbs pointing to the bridge with NULL ->dst but that has a
few race conditions because br_fdb_insert() is used which first creates
the fdb and then, after the fdb has been published/linked, sets
"is_local" to 1 and in that time frame if a packet arrives for that fdb
it may see it as non-local and either do a NULL ptr dereference in
br_forward() or attach the fdb to the port where it arrived, and later
br_fdb_insert() will make it local thus getting a wrong fdb entry.
Call chain br_handle_frame_finish() -> br_forward():
But in br_handle_frame_finish() in order to call br_forward() the dst
should not be local i.e. skb != NULL, whenever the dst is
found to be local skb is set to NULL so we can't forward it,
and here comes the problem since it's running only
with RCU when forwarding packets it can see the entry before "is_local"
is set to 1 and actually try to dereference NULL.
The main issue is that if someone sends a packet to the switch while
it's adding the entry which points to the bridge device, it may
dereference NULL ptr. This is needed now after we can add fdbs
pointing to the bridge.  This poses a problem for
br_fdb_update() as well, while someone's adding a bridge fdb, but
before it has is_local == 1, it might get moved to a port if it comes
as a source mac and then it may get its "is_local" set to 1

This patch changes fdb_create to take is_local and is_static as
arguments to set these values in the fdb entry before it is added to the
hash. Also adds null check for port in br_forward.

Fixes: 3741873b4f ("bridge: allow adding of fdb entries pointing to the bridge device")
Reported-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-30 12:13:05 +09:00

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_rcu(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_rcu(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_rcu(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 (to && 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