indirect calls are only needed if ipv6 is a module. Add helpers to abstract the v6ops indirections and use them instead. reroute is kept as indirect call here; its only used with nfqueue and only when userspace modified packet or metadata (nfmark). v2: - fix build failure with CONFIG_NETFILTER=n - fix build failure with CONFIG_IPV6=n Signed-off-by: Florian Westphal <fw@xxxxxxxxx> --- include/linux/netfilter_ipv6.h | 87 +++++++++++++++++++++++++++---- net/bridge/br_netfilter_hooks.c | 7 +-- net/bridge/br_netfilter_ipv6.c | 22 ++++++-- net/ipv6/netfilter.c | 13 ++--- net/ipv6/netfilter/nft_fib_ipv6.c | 9 +--- net/netfilter/utils.c | 6 +-- net/netfilter/xt_addrtype.c | 16 ++---- net/openvswitch/actions.c | 6 +-- 8 files changed, 113 insertions(+), 53 deletions(-) diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index ad4223c10488..ab446bee56a2 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -9,6 +9,10 @@ #include <uapi/linux/netfilter_ipv6.h> +/* IPV6=y -- need prototypes for direct calls */ +#include <net/addrconf.h> +#include <net/ip6_route.h> + /* Extra routing may needed on local out, as the QUEUE target never returns * control to the table. */ @@ -25,29 +29,24 @@ struct nf_queue_entry; * if IPv6 is a module. */ struct nf_ipv6_ops { +#if IS_MODULE(CONFIG_IPV6) int (*chk_addr)(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict); void (*route_input)(struct sk_buff *skb); int (*fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); - int (*route)(struct net *net, struct dst_entry **dst, struct flowi *fl, - bool strict); - int (*reroute)(struct sk_buff *skb, const struct nf_queue_entry *entry); -#if IS_MODULE(CONFIG_IPV6) int (*route_me_harder)(struct net *net, struct sk_buff *skb); int (*dev_get_saddr)(struct net *net, const struct net_device *dev, const struct in6_addr *daddr, unsigned int srcprefs, struct in6_addr *saddr); + int (*route)(struct net *net, struct dst_entry **dst, struct flowi *fl, + bool strict); #endif + int (*reroute)(struct sk_buff *skb, const struct nf_queue_entry *entry); }; #ifdef CONFIG_NETFILTER -int ip6_route_me_harder(struct net *net, struct sk_buff *skb); -__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, - unsigned int dataoff, u_int8_t protocol); - -int ipv6_netfilter_init(void); -void ipv6_netfilter_fini(void); +#include <net/addrconf.h> extern const struct nf_ipv6_ops __rcu *nf_ipv6_ops; static inline const struct nf_ipv6_ops *nf_get_ipv6_ops(void) @@ -55,10 +54,78 @@ static inline const struct nf_ipv6_ops *nf_get_ipv6_ops(void) return rcu_dereference(nf_ipv6_ops); } +static inline int nf_ipv6_chk_addr(struct net *net, const struct in6_addr *addr, + const struct net_device *dev, int strict) +{ +#if IS_MODULE(CONFIG_IPV6) + const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); + + if (!v6_ops) + return 1; + + return v6_ops->chk_addr(net, addr, dev, strict); +#else + return ipv6_chk_addr(net, addr, dev, strict); +#endif +} + +static inline int +nf_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)) +{ +#if IS_MODULE(CONFIG_IPV6) + const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); + + if (v6ops) + return v6ops->fragment(net, sk, skb, output); +#endif +#if IS_BUILTIN(CONFIG_IPV6) + return ip6_fragment(net, sk, skb, output); +#endif + kfree_skb(skb); + return -EMSGSIZE; +} + +int __nf_ip6_route(struct net *net, struct dst_entry **dst, + struct flowi *fl, bool strict); + +static inline int nf_ip6_route(struct net *net, struct dst_entry **dst, + struct flowi *fl, bool strict) +{ +#if IS_MODULE(CONFIG_IPV6) + const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); + + if (v6ops) + return v6ops->route(net, dst, fl, strict); + + return -EHOSTUNREACH; +#endif +#if IS_BUILTIN(CONFIG_IPV6) + return __nf_ip6_route(net, dst, fl, strict); +#else + return -EHOSTUNREACH; +#endif +} + +int ip6_route_me_harder(struct net *net, struct sk_buff *skb); +__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, + unsigned int dataoff, u_int8_t protocol); + +int ipv6_netfilter_init(void); +void ipv6_netfilter_fini(void); + #else /* CONFIG_NETFILTER */ static inline int ipv6_netfilter_init(void) { return 0; } static inline void ipv6_netfilter_fini(void) { return; } static inline const struct nf_ipv6_ops *nf_get_ipv6_ops(void) { return NULL; } + +static inline int +nf_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)) +{ + kfree_skb(skb); + return -EMSGSIZE; +} #endif /* CONFIG_NETFILTER */ #endif /*__LINUX_IP6_NETFILTER_H*/ diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 40d058378b52..9e7686bef5b9 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -744,7 +744,6 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff } if (IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) && skb->protocol == htons(ETH_P_IPV6)) { - const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); struct brnf_frag_data *data; if (br_validate_ipv6(net, skb)) @@ -761,11 +760,7 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff skb_copy_from_linear_data_offset(skb, -data->size, data->mac, data->size); - if (v6ops) - return v6ops->fragment(net, sk, skb, br_nf_push_frag_xmit); - - kfree_skb(skb); - return -EMSGSIZE; + return nf_ip6_fragment(net, sk, skb, br_nf_push_frag_xmit); } nf_bridge_info_free(skb); return br_dev_queue_push_xmit(net, sk, skb); diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index 94039f588f1d..424c77817aff 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -35,7 +35,7 @@ #include <net/ip.h> #include <net/ipv6.h> #include <net/addrconf.h> -#include <net/route.h> +#include <net/ip6_route.h> #include <net/netfilter/br_netfilter.h> #include <linux/uaccess.h> @@ -155,6 +155,22 @@ br_nf_ipv6_daddr_was_changed(const struct sk_buff *skb, sizeof(ipv6_hdr(skb)->daddr)) != 0; } +static bool br_nf_ip6_route_input(struct sk_buff *skb) +{ +#if IS_MODULE(CONFIG_IPV6) + const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); + + if (!v6ops) + return false; + + v6ops->route_input(skb); +#else + ip6_route_input(skb); +#endif + + return skb_dst(skb)->error ? false : true; +} + /* PF_BRIDGE/PRE_ROUTING: Undo the changes made for ip6tables * PREROUTING and continue the bridge PRE_ROUTING hook. See comment * for br_nf_pre_routing_finish(), same logic is used here but @@ -165,7 +181,6 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct rtable *rt; struct net_device *dev = skb->dev; - const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size; @@ -176,9 +191,8 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc nf_bridge->in_prerouting = 0; if (br_nf_ipv6_daddr_was_changed(skb, nf_bridge)) { skb_dst_drop(skb); - v6ops->route_input(skb); - if (skb_dst(skb)->error) { + if (!br_nf_ip6_route_input(skb)) { kfree_skb(skb); return 0; } diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 0a5caf263889..8de3574e1377 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -84,8 +84,8 @@ static int nf_ip6_reroute(struct sk_buff *skb, return 0; } -static int nf_ip6_route(struct net *net, struct dst_entry **dst, - struct flowi *fl, bool strict) +int __nf_ip6_route(struct net *net, struct dst_entry **dst, + struct flowi *fl, bool strict) { static const struct ipv6_pinfo fake_pinfo; static const struct inet_sock fake_sk = { @@ -105,17 +105,18 @@ static int nf_ip6_route(struct net *net, struct dst_entry **dst, *dst = result; return err; } +EXPORT_SYMBOL_GPL(__nf_ip6_route); static const struct nf_ipv6_ops ipv6ops = { +#if IS_MODULE(CONFIG_IPV6) .chk_addr = ipv6_chk_addr, - .route_input = ip6_route_input, + .route_input = ip6_route_input, .fragment = ip6_fragment, - .route = nf_ip6_route, - .reroute = nf_ip6_reroute, -#if IS_MODULE(CONFIG_IPV6) .route_me_harder = ip6_route_me_harder, .dev_get_saddr = ipv6_dev_get_saddr, + .route = __nf_ip6_route, #endif + .reroute = nf_ip6_reroute, }; int __init ipv6_netfilter_init(void) diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index 36be3cf0adef..73cdc0bc63f7 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -59,7 +59,6 @@ static u32 __nft_fib6_eval_type(const struct nft_fib *priv, struct ipv6hdr *iph) { const struct net_device *dev = NULL; - const struct nf_ipv6_ops *v6ops; int route_err, addrtype; struct rt6_info *rt; struct flowi6 fl6 = { @@ -68,10 +67,6 @@ static u32 __nft_fib6_eval_type(const struct nft_fib *priv, }; u32 ret = 0; - v6ops = nf_get_ipv6_ops(); - if (!v6ops) - return RTN_UNREACHABLE; - if (priv->flags & NFTA_FIB_F_IIF) dev = nft_in(pkt); else if (priv->flags & NFTA_FIB_F_OIF) @@ -79,10 +74,10 @@ static u32 __nft_fib6_eval_type(const struct nft_fib *priv, nft_fib6_flowi_init(&fl6, priv, pkt, dev, iph); - if (dev && v6ops->chk_addr(nft_net(pkt), &fl6.daddr, dev, true)) + if (dev && nf_ipv6_chk_addr(nft_net(pkt), &fl6.daddr, dev, true)) ret = RTN_LOCAL; - route_err = v6ops->route(nft_net(pkt), (struct dst_entry **)&rt, + route_err = nf_ip6_route(nft_net(pkt), (struct dst_entry **)&rt, flowi6_to_flowi(&fl6), false); if (route_err) goto err; diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c index 55af9f247993..06dc55590441 100644 --- a/net/netfilter/utils.c +++ b/net/netfilter/utils.c @@ -162,7 +162,7 @@ EXPORT_SYMBOL_GPL(nf_checksum_partial); int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict, unsigned short family) { - const struct nf_ipv6_ops *v6ops; + const struct nf_ipv6_ops *v6ops __maybe_unused; int ret = 0; switch (family) { @@ -170,9 +170,7 @@ int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl, ret = nf_ip_route(net, dst, fl, strict); break; case AF_INET6: - v6ops = rcu_dereference(nf_ipv6_ops); - if (v6ops) - ret = v6ops->route(net, dst, fl, strict); + ret = nf_ip6_route(net, dst, fl, strict); break; } diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c index 89e281b3bfc2..29987ff03621 100644 --- a/net/netfilter/xt_addrtype.c +++ b/net/netfilter/xt_addrtype.c @@ -36,7 +36,6 @@ MODULE_ALIAS("ip6t_addrtype"); static u32 match_lookup_rt6(struct net *net, const struct net_device *dev, const struct in6_addr *addr, u16 mask) { - const struct nf_ipv6_ops *v6ops; struct flowi6 flow; struct rt6_info *rt; u32 ret = 0; @@ -47,18 +46,13 @@ static u32 match_lookup_rt6(struct net *net, const struct net_device *dev, if (dev) flow.flowi6_oif = dev->ifindex; - v6ops = nf_get_ipv6_ops(); - if (v6ops) { - if (dev && (mask & XT_ADDRTYPE_LOCAL)) { - if (v6ops->chk_addr(net, addr, dev, true)) - ret = XT_ADDRTYPE_LOCAL; - } - route_err = v6ops->route(net, (struct dst_entry **)&rt, - flowi6_to_flowi(&flow), false); - } else { - route_err = 1; + if (dev && (mask & XT_ADDRTYPE_LOCAL)) { + if (nf_ipv6_chk_addr(net, addr, dev, true)) + ret = XT_ADDRTYPE_LOCAL; } + route_err = nf_ip6_route(net, (struct dst_entry **)&rt, + flowi6_to_flowi(&flow), false); if (route_err) return XT_ADDRTYPE_UNREACHABLE; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index e47ebbbe71b8..a1437c12bf6b 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -915,13 +915,9 @@ static void ovs_fragment(struct net *net, struct vport *vport, ip_do_fragment(net, skb->sk, skb, ovs_vport_output); refdst_drop(orig_dst); } else if (key->eth.type == htons(ETH_P_IPV6)) { - const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); unsigned long orig_dst; struct rt6_info ovs_rt; - if (!v6ops) - goto err; - prepare_frag(vport, skb, orig_network_offset, ovs_key_mac_proto(key)); memset(&ovs_rt, 0, sizeof(ovs_rt)); @@ -933,7 +929,7 @@ static void ovs_fragment(struct net *net, struct vport *vport, skb_dst_set_noref(skb, &ovs_rt.dst); IP6CB(skb)->frag_max_size = mru; - v6ops->fragment(net, skb->sk, skb, ovs_vport_output); + nf_ip6_fragment(net, skb->sk, skb, ovs_vport_output); refdst_drop(orig_dst); } else { WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.", -- 2.19.2