linux/net/bridge/br_forward.c
Eric Dumazet 44bdb313da net: bridge: use DEV_STATS_INC()
syzbot/KCSAN reported data-races in br_handle_frame_finish() [1]
This function can run from multiple cpus without mutual exclusion.

Adopt SMP safe DEV_STATS_INC() to update dev->stats fields.

Handles updates to dev->stats.tx_dropped while we are at it.

[1]
BUG: KCSAN: data-race in br_handle_frame_finish / br_handle_frame_finish

read-write to 0xffff8881374b2178 of 8 bytes by interrupt on cpu 1:
br_handle_frame_finish+0xd4f/0xef0 net/bridge/br_input.c:189
br_nf_hook_thresh+0x1ed/0x220
br_nf_pre_routing_finish_ipv6+0x50f/0x540
NF_HOOK include/linux/netfilter.h:304 [inline]
br_nf_pre_routing_ipv6+0x1e3/0x2a0 net/bridge/br_netfilter_ipv6.c:178
br_nf_pre_routing+0x526/0xba0 net/bridge/br_netfilter_hooks.c:508
nf_hook_entry_hookfn include/linux/netfilter.h:144 [inline]
nf_hook_bridge_pre net/bridge/br_input.c:272 [inline]
br_handle_frame+0x4c9/0x940 net/bridge/br_input.c:417
__netif_receive_skb_core+0xa8a/0x21e0 net/core/dev.c:5417
__netif_receive_skb_one_core net/core/dev.c:5521 [inline]
__netif_receive_skb+0x57/0x1b0 net/core/dev.c:5637
process_backlog+0x21f/0x380 net/core/dev.c:5965
__napi_poll+0x60/0x3b0 net/core/dev.c:6527
napi_poll net/core/dev.c:6594 [inline]
net_rx_action+0x32b/0x750 net/core/dev.c:6727
__do_softirq+0xc1/0x265 kernel/softirq.c:553
run_ksoftirqd+0x17/0x20 kernel/softirq.c:921
smpboot_thread_fn+0x30a/0x4a0 kernel/smpboot.c:164
kthread+0x1d7/0x210 kernel/kthread.c:388
ret_from_fork+0x48/0x60 arch/x86/kernel/process.c:147
ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:304

read-write to 0xffff8881374b2178 of 8 bytes by interrupt on cpu 0:
br_handle_frame_finish+0xd4f/0xef0 net/bridge/br_input.c:189
br_nf_hook_thresh+0x1ed/0x220
br_nf_pre_routing_finish_ipv6+0x50f/0x540
NF_HOOK include/linux/netfilter.h:304 [inline]
br_nf_pre_routing_ipv6+0x1e3/0x2a0 net/bridge/br_netfilter_ipv6.c:178
br_nf_pre_routing+0x526/0xba0 net/bridge/br_netfilter_hooks.c:508
nf_hook_entry_hookfn include/linux/netfilter.h:144 [inline]
nf_hook_bridge_pre net/bridge/br_input.c:272 [inline]
br_handle_frame+0x4c9/0x940 net/bridge/br_input.c:417
__netif_receive_skb_core+0xa8a/0x21e0 net/core/dev.c:5417
__netif_receive_skb_one_core net/core/dev.c:5521 [inline]
__netif_receive_skb+0x57/0x1b0 net/core/dev.c:5637
process_backlog+0x21f/0x380 net/core/dev.c:5965
__napi_poll+0x60/0x3b0 net/core/dev.c:6527
napi_poll net/core/dev.c:6594 [inline]
net_rx_action+0x32b/0x750 net/core/dev.c:6727
__do_softirq+0xc1/0x265 kernel/softirq.c:553
do_softirq+0x5e/0x90 kernel/softirq.c:454
__local_bh_enable_ip+0x64/0x70 kernel/softirq.c:381
__raw_spin_unlock_bh include/linux/spinlock_api_smp.h:167 [inline]
_raw_spin_unlock_bh+0x36/0x40 kernel/locking/spinlock.c:210
spin_unlock_bh include/linux/spinlock.h:396 [inline]
batadv_tt_local_purge+0x1a8/0x1f0 net/batman-adv/translation-table.c:1356
batadv_tt_purge+0x2b/0x630 net/batman-adv/translation-table.c:3560
process_one_work kernel/workqueue.c:2630 [inline]
process_scheduled_works+0x5b8/0xa30 kernel/workqueue.c:2703
worker_thread+0x525/0x730 kernel/workqueue.c:2784
kthread+0x1d7/0x210 kernel/kthread.c:388
ret_from_fork+0x48/0x60 arch/x86/kernel/process.c:147
ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:304

value changed: 0x00000000000d7190 -> 0x00000000000d7191

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 14848 Comm: kworker/u4:11 Not tainted 6.6.0-rc1-syzkaller-00236-gad8a69f361b9 #0

Fixes: 1c29fc4989 ("[BRIDGE]: keep track of received multicast packets")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Roopa Prabhu <roopa@nvidia.com>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Cc: bridge@lists.linux-foundation.org
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20230918091351.1356153-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2023-09-19 13:35:15 +02:00

350 lines
8.0 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Forwarding decision
* Linux ethernet bridge
*
* Authors:
* Lennert Buytenhek <buytenh@gnu.org>
*/
#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) &&
p->state == BR_STATE_FORWARDING && br_allowed_egress(vg, skb) &&
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 &&
eth_type_vlan(skb->protocol)) {
int depth;
if (!vlan_get_protocol_and_depth(skb, skb->protocol, &depth))
goto drop;
skb_set_network_header(skb, depth);
}
br_switchdev_frame_set_offload_fwd_mark(skb);
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_clear_tstamp(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_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;
/* Mark the skb for forwarding offload early so that br_handle_vlan()
* can know whether to pop the VLAN header on egress or keep it.
*/
nbp_switchdev_frame_mark_tx_fwd_offload(to, skb);
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_INC(dev, 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;
BR_INPUT_SKB_CB(skb)->backup_nhid = READ_ONCE(to->backup_nhid);
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)
{
u8 igmp_type = br_multicast_igmp_type(skb);
int err;
if (!should_deliver(p, skb))
return prev;
nbp_switchdev_frame_mark_tx_fwd_to_hwdom(p, skb);
if (!prev)
goto out;
err = deliver_clone(prev, skb, local_orig);
if (err)
return ERR_PTR(err);
out:
br_multicast_count(p->br, p, skb, igmp_type, BR_MCAST_DIR_TX);
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,
u16 vid)
{
struct net_bridge_port *prev = NULL;
struct net_bridge_port *p;
br_tc_skb_miss_set(skb, pkt_type != BR_PKT_BROADCAST);
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 (BR_INPUT_SKB_CB(skb)->proxyarp_replied &&
((p->flags & BR_PROXYARP_WIFI) ||
br_is_neigh_suppress_enabled(p, vid)))
continue;
prev = maybe_deliver(prev, p, skb, local_orig);
if (IS_ERR(prev))
goto out;
}
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_INC(dev, 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,
struct net_bridge_mcast *brmctx,
bool local_rcv, bool local_orig)
{
struct net_bridge_port *prev = NULL;
struct net_bridge_port_group *p;
bool allow_mode_include = true;
struct hlist_node *rp;
rp = br_multicast_get_first_rport_node(brmctx, skb);
if (mdst) {
p = rcu_dereference(mdst->ports);
if (br_multicast_should_handle_mode(brmctx, mdst->addr.proto) &&
br_multicast_is_star_g(&mdst->addr))
allow_mode_include = false;
} else {
p = NULL;
br_tc_skb_miss_set(skb, true);
}
while (p || rp) {
struct net_bridge_port *port, *lport, *rport;
lport = p ? p->key.port : NULL;
rport = br_multicast_rport_from_node_skb(rp, skb);
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;
}
if ((!allow_mode_include &&
p->filter_mode == MCAST_INCLUDE) ||
(p->flags & MDB_PG_FLAGS_BLOCKED))
goto delivered;
} else {
port = rport;
}
prev = maybe_deliver(prev, port, skb, local_orig);
if (IS_ERR(prev))
goto out;
delivered:
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