diff options
Diffstat (limited to 'net/bridge/br_netfilter.c')
-rw-r--r-- | net/bridge/br_netfilter.c | 131 |
1 files changed, 118 insertions, 13 deletions
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 0ee453fad3de..f3884a1b942f 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -37,17 +37,16 @@ #include <net/route.h> #include <net/netfilter/br_netfilter.h> +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include <net/netfilter/nf_conntrack.h> +#endif + #include <asm/uaccess.h> #include "br_private.h" #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif -#define skb_origaddr(skb) (((struct bridge_skb_cb *) \ - (skb->nf_bridge->data))->daddr.ipv4) -#define store_orig_dstaddr(skb) (skb_origaddr(skb) = ip_hdr(skb)->daddr) -#define dnat_took_place(skb) (skb_origaddr(skb) != ip_hdr(skb)->daddr) - #ifdef CONFIG_SYSCTL static struct ctl_table_header *brnf_sysctl_header; static int brnf_call_iptables __read_mostly = 1; @@ -154,6 +153,18 @@ static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb) return nf_bridge; } +static unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb) +{ + switch (skb->protocol) { + case __cpu_to_be16(ETH_P_8021Q): + return VLAN_HLEN; + case __cpu_to_be16(ETH_P_PPP_SES): + return PPPOE_SES_HLEN; + default: + return 0; + } +} + static inline void nf_bridge_push_encap_header(struct sk_buff *skb) { unsigned int len = nf_bridge_encap_header_len(skb); @@ -239,6 +250,14 @@ drop: return -1; } +static void nf_bridge_update_protocol(struct sk_buff *skb) +{ + if (skb->nf_bridge->mask & BRNF_8021Q) + skb->protocol = htons(ETH_P_8021Q); + else if (skb->nf_bridge->mask & BRNF_PPPoE) + skb->protocol = htons(ETH_P_PPP_SES); +} + /* PF_BRIDGE/PRE_ROUTING *********************************************/ /* Undo the changes made for ip6tables PREROUTING and continue the * bridge PRE_ROUTING hook. */ @@ -314,6 +333,22 @@ free_skb: return 0; } +static bool dnat_took_place(const struct sk_buff *skb) +{ +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct || nf_ct_is_untracked(ct)) + return false; + + return test_bit(IPS_DST_NAT_BIT, &ct->status); +#else + return false; +#endif +} + /* This requires some explaining. If DNAT has taken place, * we will need to fix up the destination Ethernet address. * @@ -617,7 +652,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, return NF_DROP; if (!setup_pre_routing(skb)) return NF_DROP; - store_orig_dstaddr(skb); + skb->protocol = htons(ETH_P_IP); NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, skb->dev, NULL, @@ -713,8 +748,6 @@ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops, if (pf == NFPROTO_IPV4 && br_parse_ip_options(skb)) return NF_DROP; - /* The physdev module checks on this */ - nf_bridge->mask |= BRNF_BRIDGED; nf_bridge->physoutdev = skb->dev; if (pf == NFPROTO_IPV4) skb->protocol = htons(ETH_P_IP); @@ -764,23 +797,53 @@ static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops, } #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) +static bool nf_bridge_copy_header(struct sk_buff *skb) +{ + int err; + unsigned int header_size; + + nf_bridge_update_protocol(skb); + header_size = ETH_HLEN + nf_bridge_encap_header_len(skb); + err = skb_cow_head(skb, header_size); + if (err) + return false; + + skb_copy_to_linear_data_offset(skb, -header_size, + skb->nf_bridge->data, header_size); + __skb_push(skb, nf_bridge_encap_header_len(skb)); + return true; +} + +static int br_nf_push_frag_xmit(struct sk_buff *skb) +{ + if (!nf_bridge_copy_header(skb)) { + kfree_skb(skb); + return 0; + } + + return br_dev_queue_push_xmit(skb); +} + static int br_nf_dev_queue_xmit(struct sk_buff *skb) { int ret; int frag_max_size; + unsigned int mtu_reserved; + + if (skb_is_gso(skb) || skb->protocol != htons(ETH_P_IP)) + return br_dev_queue_push_xmit(skb); + mtu_reserved = nf_bridge_mtu_reduction(skb); /* This is wrong! We should preserve the original fragment * boundaries by preserving frag_list rather than refragmenting. */ - if (skb->protocol == htons(ETH_P_IP) && - skb->len + nf_bridge_mtu_reduction(skb) > skb->dev->mtu && - !skb_is_gso(skb)) { + if (skb->len + mtu_reserved > skb->dev->mtu) { frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size; if (br_parse_ip_options(skb)) /* Drop invalid packet */ return NF_DROP; IPCB(skb)->frag_max_size = frag_max_size; - ret = ip_fragment(skb, br_dev_queue_push_xmit); + ret = ip_fragment(skb, br_nf_push_frag_xmit); } else ret = br_dev_queue_push_xmit(skb); @@ -804,7 +867,12 @@ static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops, struct net_device *realoutdev = bridge_parent(skb->dev); u_int8_t pf; - if (!nf_bridge || !(nf_bridge->mask & BRNF_BRIDGED)) + /* if nf_bridge is set, but ->physoutdev is NULL, this packet came in + * on a bridge, but was delivered locally and is now being routed: + * + * POST_ROUTING was already invoked from the ip stack. + */ + if (!nf_bridge || !nf_bridge->physoutdev) return NF_ACCEPT; if (!realoutdev) @@ -854,6 +922,41 @@ static unsigned int ip_sabotage_in(const struct nf_hook_ops *ops, return NF_ACCEPT; } +/* This is called when br_netfilter has called into iptables/netfilter, + * and DNAT has taken place on a bridge-forwarded packet. + * + * neigh->output has created a new MAC header, with local br0 MAC + * as saddr. + * + * This restores the original MAC saddr of the bridged packet + * before invoking bridge forward logic to transmit the packet. + */ +static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) +{ + struct nf_bridge_info *nf_bridge = skb->nf_bridge; + + skb_pull(skb, ETH_HLEN); + nf_bridge->mask &= ~BRNF_BRIDGED_DNAT; + + skb_copy_to_linear_data_offset(skb, -(ETH_HLEN-ETH_ALEN), + skb->nf_bridge->data, ETH_HLEN-ETH_ALEN); + skb->dev = nf_bridge->physindev; + br_handle_frame_finish(skb); +} + +static int br_nf_dev_xmit(struct sk_buff *skb) +{ + if (skb->nf_bridge && (skb->nf_bridge->mask & BRNF_BRIDGED_DNAT)) { + br_nf_pre_routing_finish_bridge_slow(skb); + return 1; + } + return 0; +} + +static const struct nf_br_ops br_ops = { + .br_dev_xmit_hook = br_nf_dev_xmit, +}; + void br_netfilter_enable(void) { } @@ -991,12 +1094,14 @@ static int __init br_netfilter_init(void) return -ENOMEM; } #endif + RCU_INIT_POINTER(nf_br_ops, &br_ops); printk(KERN_NOTICE "Bridge firewalling registered\n"); return 0; } static void __exit br_netfilter_fini(void) { + RCU_INIT_POINTER(nf_br_ops, NULL); nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops)); #ifdef CONFIG_SYSCTL unregister_net_sysctl_table(brnf_sysctl_header); |