Netfilter/IPVS updates for net-next
Subsystems (5)
Pablo Neira Ayuso
maintainercover Netfilter/IPVS updates for net-next
Hi David,
The following patchset contains Netfilter/IPVS updates for you net-next tree:
1) Missing NFTA_RULE_POSITION_ID netlink attribute validation, from Phil Sutter.
2) Restrict matching on tunnel metadata to rx/tx path, from wenxu.
3) Avoid indirect calls for IPV6=y, from Florian Westphal.
4) Add two indirections to prepare merger of IPV4 and IPV6 nat modules, from Florian Westphal.
5) Broken indentation in ctnetlink, from Colin Ian King.
6) Patches to use struct_size() from netfilter and IPVS, from Gustavo A. R. Silva.
7) Display kernel splat only once in case of racing to confirm conntrack from bridge plus nfqueue setups, from Chieh-Min Wang.
8) Skip checksum validation for layer 4 protocols that don't need it, patch from Alin Nastac.
9) Sparse warning due to symbol that should be static in CLUSTERIP, from Wei Yongjun.
10) Add new toggle to disable SDP payload translation when media endpoint is reachable though the same interface as the signalling peer, from Alin Nastac.
You can pull these changes from:
git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next.git
Thanks!
----------------------------------------------------------------
The following changes since commit bbcbf2eede69c5f54a431fb96c11248a7910748c:
enetc: include linux/vmalloc.h for vzalloc etc (2019-01-28 22:43:34 -0800)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next.git HEAD
for you to fetch changes up to a3419ce3356cf1fdc69a0524eced84cef730b3bf:
netfilter: nf_conntrack_sip: add sip_external_media logic (2019-02-16 10:49:12 +0100)
----------------------------------------------------------------
Alin Nastac (2):
netfilter: reject: skip csum verification for protocols that don't support it
netfilter: nf_conntrack_sip: add sip_external_media logic
Chieh-Min Wang (1):
netfilter: conntrack: fix cloned unconfirmed skb->_nfct race in __nf_conntrack_confirm
Colin Ian King (1):
netfilter: conntrack: fix indentation issue
Florian Westphal (3):
netfilter: nf_tables: add NFTA_RULE_POSITION_ID to nla_policy
netfilter: nat: remove module dependency on ipv6 core
netfilter: ipv6: avoid indirect calls for IPV6=y case
Gustavo A. R. Silva (2):
ipvs: Use struct_size() helper
netfilter: xt_recent: Use struct_size() in kvzalloc()
Wei Yongjun (1):
netfilter: ipt_CLUSTERIP: make symbol 'cip_netdev_notifier' static
wenxu (1):
netfilter: nft_tunnel: Add NFTA_TUNNEL_MODE options
include/linux/netfilter_ipv6.h | 60 +++++++++++++++++++++++++---- include/net/netfilter/ipv4/nf_reject.h | 1 + include/net/netfilter/ipv6/nf_reject.h | 1 + include/net/netfilter/nf_reject.h | 27 +++++++++++++ include/uapi/linux/netfilter/nf_tables.h | 9 +++++ net/bridge/netfilter/nft_reject_bridge.c | 10 ++--- net/ipv4/netfilter/ipt_CLUSTERIP.c | 2 +- net/ipv4/netfilter/nf_reject_ipv4.c | 9 +---- net/ipv6/netfilter.c | 13 +++++-- net/ipv6/netfilter/nf_nat_l3proto_ipv6.c | 17 +++++++- net/ipv6/netfilter/nf_nat_masquerade_ipv6.c | 21 +++++++++- net/ipv6/netfilter/nf_reject_ipv6.c | 3 ++ net/ipv6/netfilter/nft_fib_ipv6.c | 9 +---- net/netfilter/ipvs/ip_vs_ctl.c | 6 +-- net/netfilter/nf_conntrack_core.c | 14 +++++-- net/netfilter/nf_conntrack_netlink.c | 2 +- net/netfilter/nf_conntrack_sip.c | 42 ++++++++++++++++++++ net/netfilter/nf_tables_api.c | 1 + net/netfilter/nft_tunnel.c | 34 +++++++++++++++- net/netfilter/utils.c | 6 +-- net/netfilter/xt_addrtype.c | 16 +++----- net/netfilter/xt_recent.c | 4 +- 22 files changed, 244 insertions(+), 63 deletions(-) create mode 100644 include/net/netfilter/nf_reject.h
Pablo Neira Ayuso
maintainerPATCH 1/11 netfilter: nf_tables: add NFTA_RULE_POSITION_ID to nla_policy
From: Florian Westphal <[email protected]>
--- net/netfilter/nf_tables_api.c | 1 + 1 file changed, 1 insertion(+)
net/netfilter/nf_tables_api.c +1 -0
@@ -2239,6 +2239,7 @@ static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = { [NFTA_RULE_USERDATA ] = { .type =NLA_BINARY , .len = NFT_USERDATA_MAXLEN }, [NFTA_RULE_ID] = { .type = NLA_U32 }, + [NFTA_RULE_POSITION_ID] = { .type = NLA_U32 }, }; static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net,
Signature · 1 line
2.11.0
Pablo Neira Ayuso
maintainerPATCH 2/11 netfilter: nft_tunnel: Add NFTA_TUNNEL_MODE options
In reply to Pablo Neira AyusoFrom: wenxu <[email protected]>
nft "tunnel" expr match both the tun_info of RX and TX. This patch provide the NFTA_TUNNEL_MODE to individually match the tun_info of RX or TX.
--- include/uapi/linux/netfilter/nf_tables.h | 9 +++++++++ net/netfilter/nft_tunnel.c | 34 ++++++++++++++++++++++++++++++-- 2 files changed, 41 insertions(+), 2 deletions(-)
include/uapi/linux/netfilter/nf_tables.h +9 -0
@@ -1727,10 +1727,19 @@ enum nft_tunnel_keys { };#define NFT_TUNNEL_MAX (__NFT_TUNNEL_MAX - 1) +enum nft_tunnel_mode { +NFT_TUNNEL_MODE_NONE , +NFT_TUNNEL_MODE_RX , +NFT_TUNNEL_MODE_TX , + __NFT_TUNNEL_MODE_MAX +}; +#define NFT_TUNNEL_MODE_MAX (__NFT_TUNNEL_MODE_MAX - 1) +enum nft_tunnel_attributes {NFTA_TUNNEL_UNSPEC ,NFTA_TUNNEL_KEY ,NFTA_TUNNEL_DREG , +NFTA_TUNNEL_MODE , __NFTA_TUNNEL_MAX };#define NFTA_TUNNEL_MAX (__NFTA_TUNNEL_MAX - 1)
net/netfilter/nft_tunnel.c +32 -2
@@ -15,6 +15,7 @@struct nft_tunnel {enum nft_tunnel_keys key:8 ;enum nft_registers dreg:8 ; +enum nft_tunnel_mode mode:8 ; }; static void nft_tunnel_get_eval(const struct nft_expr *expr,
@@ -29,14 +30,32 @@ static void nft_tunnel_get_eval(const struct nft_expr *expr,switch (priv->key) {case NFT_TUNNEL_PATH : -nft_reg_store8 (dest, !!tun_info); +if (!tun_info) { +nft_reg_store8 (dest, false); +return ; + } +if (priv->mode ==NFT_TUNNEL_MODE_NONE || + (priv->mode ==NFT_TUNNEL_MODE_RX && + !(tun_info->mode &IP_TUNNEL_INFO_TX )) || + (priv->mode ==NFT_TUNNEL_MODE_TX && + (tun_info->mode &IP_TUNNEL_INFO_TX ))) +nft_reg_store8 (dest, true); +else +nft_reg_store8 (dest, false);break ;case NFT_TUNNEL_ID :if (!tun_info) { regs->verdict.code =NFT_BREAK ;return ; } - *dest =ntohl (tunnel_id_to_key32 (tun_info->key.tun_id)); +if (priv->mode ==NFT_TUNNEL_MODE_NONE || + (priv->mode ==NFT_TUNNEL_MODE_RX && + !(tun_info->mode &IP_TUNNEL_INFO_TX )) || + (priv->mode ==NFT_TUNNEL_MODE_TX && + (tun_info->mode &IP_TUNNEL_INFO_TX ))) + *dest =ntohl (tunnel_id_to_key32 (tun_info->key.tun_id)); +else + regs->verdict.code =NFT_BREAK ;break ;default :WARN_ON (1 );
@@ -47,6 +66,7 @@ static void nft_tunnel_get_eval(const struct nft_expr *expr,static const struct nla_policy nft_tunnel_policy[NFTA_TUNNEL_MAX +1 ] = { [NFTA_TUNNEL_KEY ] = { .type =NLA_U32 }, [NFTA_TUNNEL_DREG ] = { .type =NLA_U32 }, + [NFTA_TUNNEL_MODE ] = { .type =NLA_U32 }, }; static int nft_tunnel_get_init(const struct nft_ctx *ctx,
@@ -74,6 +94,14 @@ static int nft_tunnel_get_init(const struct nft_ctx *ctx, priv->dreg =nft_parse_register (tb[NFTA_TUNNEL_DREG ]); +if (tb[NFTA_TUNNEL_MODE ]) { + priv->mode =ntohl (nla_get_be32 (tb[NFTA_TUNNEL_MODE ])); +if (priv->mode >NFT_TUNNEL_MODE_MAX ) +return -EOPNOTSUPP ; + }else { + priv->mode =NFT_TUNNEL_MODE_NONE ; + } +return nft_validate_register_store (ctx, priv->dreg,NULL ,NFT_DATA_VALUE , len); }
@@ -87,6 +115,8 @@ static int nft_tunnel_get_dump(struct sk_buff *skb, goto nla_put_failure;if (nft_dump_register (skb,NFTA_TUNNEL_DREG , priv->dreg)) goto nla_put_failure; +if (nla_put_be32 (skb,NFTA_TUNNEL_MODE ,htonl (priv->mode))) + goto nla_put_failure;return 0 ; nla_put_failure:
Signature · 1 line
2.11.0
Pablo Neira Ayuso
maintainerPATCH 3/11 netfilter: nat: remove module dependency on ipv6 core
In reply to Pablo Neira AyusoFrom: Florian Westphal <[email protected]>
nf_nat_ipv6 calls two ipv6 core functions, so add those to v6ops to avoid the module dependency.
This is a prerequisite for merging ipv4 and ipv6 nat implementations.
Add wrappers to avoid the indirection if ipv6 is builtin.
--- include/linux/netfilter_ipv6.h | 6 ++++++ net/ipv6/netfilter.c | 4 ++++ net/ipv6/netfilter/nf_nat_l3proto_ipv6.c | 17 ++++++++++++++++- net/ipv6/netfilter/nf_nat_masquerade_ipv6.c | 21 +++++++++++++++++++-- 4 files changed, 45 insertions(+), 3 deletions(-)
include/linux/netfilter_ipv6.h +6 -0
@@ -33,6 +33,12 @@ struct nf_ipv6_ops {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); +#endif };#ifdef CONFIG_NETFILTER
net/ipv6/netfilter.c +4 -0
@@ -112,6 +112,10 @@ static const struct nf_ipv6_ops ipv6ops = { .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, +#endif };int __init ipv6_netfilter_init (void )
net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +16 -1
@@ -17,6 +17,7 @@#include <net/checksum.h> #include <net/ip6_checksum.h> #include <net/ip6_route.h> +#include <net/xfrm.h> #include <net/ipv6.h> #include <net/netfilter/nf_conntrack_core.h>
@@ -317,6 +318,20 @@ nf_nat_ipv6_out(void *priv, struct sk_buff *skb,return ret; } +static int nat_route_me_harder (struct net *net,struct sk_buff *skb) +{ +#ifdef CONFIG_IPV6_MODULE +const struct nf_ipv6_ops *v6_ops =nf_get_ipv6_ops (); + +if (!v6_ops) +return -EHOSTUNREACH ; + +return v6_ops->route_me_harder (net, skb); +#else +return ip6_route_me_harder (net, skb); +#endif +} +static unsigned int nf_nat_ipv6_local_fn (void *priv,struct sk_buff *skb,const struct nf_hook_state *state)
@@ -333,7 +348,7 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb,if (!nf_inet_addr_cmp (&ct->tuplehash[dir].tuple.dst.u3, &ct->tuplehash[!dir].tuple.src.u3)) { - err =ip6_route_me_harder (state->net, skb); + err =nat_route_me_harder (state->net, skb);if (err <0 ) ret =NF_DROP_ERR (err); }
net/ipv6/netfilter/nf_nat_masquerade_ipv6.c +19 -2
@@ -24,6 +24,23 @@static atomic_t v6_worker_count; +static int +nat_ipv6_dev_get_saddr (struct net *net,const struct net_device *dev, +const struct in6_addr *daddr,unsigned int srcprefs, +struct in6_addr *saddr) +{ +#ifdef CONFIG_IPV6_MODULE +const struct nf_ipv6_ops *v6_ops =nf_get_ipv6_ops (); + +if (!v6_ops) +return -EHOSTUNREACH ; + +return v6_ops->dev_get_saddr (net, dev, daddr, srcprefs, saddr); +#else +return ipv6_dev_get_saddr (net, dev, daddr, srcprefs, saddr); +#endif +} +unsigned int nf_nat_masquerade_ipv6 (struct sk_buff *skb,const struct nf_nat_range2 *range,const struct net_device *out)
@@ -38,8 +55,8 @@ nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range,WARN_ON (!(ct && (ctinfo ==IP_CT_NEW || ctinfo ==IP_CT_RELATED || ctinfo ==IP_CT_RELATED_REPLY ))); -if (ipv6_dev_get_saddr (nf_ct_net (ct), out, - &ipv6_hdr (skb)->daddr,0 , &src) <0 ) +if (nat_ipv6_dev_get_saddr (nf_ct_net (ct), out, + &ipv6_hdr (skb)->daddr,0 , &src) <0 )return NF_DROP ; nat =nf_ct_nat_ext_add (ct);
Signature · 1 line
2.11.0
Pablo Neira Ayuso
maintainerPATCH 4/11 netfilter: ipv6: avoid indirect calls for IPV6=y case
In reply to Pablo Neira AyusoFrom: Florian Westphal <[email protected]>
indirect calls are only needed if ipv6 is a module.
Add helpers to abstract the v6ops indirections and use them instead.
fragment, reroute and route_input are kept as indirect calls. The first two are not not used in hot path and route_input is only used by bridge netfilter.
--- include/linux/netfilter_ipv6.h | 64 +++++++++++++++++++++++++++++++-------- net/ipv6/netfilter.c | 15 ++++----- net/ipv6/netfilter/nft_fib_ipv6.c | 9 ++---- net/netfilter/utils.c | 6 ++-- net/netfilter/xt_addrtype.c | 16 +++------- 5 files changed, 68 insertions(+), 42 deletions(-)
include/linux/netfilter_ipv6.h +51 -13
@@ -25,29 +25,24 @@ 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 +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 (*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 )
@@ -55,6 +50,49 @@ 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 +} + +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 ; }
net/ipv6/netfilter.c +8 -7
@@ -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 = { - .chk_addr = ipv6_chk_addr, - .route_input = ip6_route_input, - .fragment = ip6_fragment, - .route = nf_ip6_route, - .reroute = nf_ip6_reroute, #if IS_MODULE(CONFIG_IPV6) + .chk_addr = ipv6_chk_addr, .route_me_harder = ip6_route_me_harder, .dev_get_saddr = ipv6_dev_get_saddr, + .route = __nf_ip6_route, #endif + .route_input = ip6_route_input, + .fragment = ip6_fragment, + .reroute = nf_ip6_reroute, };int __init ipv6_netfilter_init (void )
net/ipv6/netfilter/nft_fib_ipv6.c +2 -7
@@ -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;
net/netfilter/utils.c +2 -4
@@ -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 ; }
net/netfilter/xt_addrtype.c +5 -11
@@ -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 ;
Signature · 1 line
2.11.0
Pablo Neira Ayuso
maintainerPATCH 5/11 netfilter: conntrack: fix indentation issue
In reply to Pablo Neira AyusoFrom: Colin Ian King <[email protected]>
A statement in an if block is not indented correctly. Fix this.
--- net/netfilter/nf_conntrack_netlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/netfilter/nf_conntrack_netlink.c +1 -1
@@ -2675,7 +2675,7 @@ static int ctnetlink_exp_dump_mask(struct sk_buff *skb, ret =ctnetlink_dump_tuples_ip (skb, &m);if (ret >=0 ) { l4proto =nf_ct_l4proto_find (tuple->dst.protonum); - ret =ctnetlink_dump_tuples_proto (skb, &m, l4proto); + ret =ctnetlink_dump_tuples_proto (skb, &m, l4proto); }rcu_read_unlock ();
Signature · 1 line
2.11.0
Pablo Neira Ayuso
maintainerPATCH 6/11 ipvs: Use struct_size() helper
In reply to Pablo Neira AyusoFrom: "Gustavo A. R. Silva" <[email protected]>
One of the more common cases of allocation size calculations is finding the size of a structure that has a zero-sized array at the end, along with memory for some number of elements for that array. For example:
struct foo {
int stuff;
struct boo entry[];
};size = sizeof(struct foo) + count * sizeof(struct boo); instance = alloc(size, GFP_KERNEL)
Instead of leaving these open-coded and prone to type mistakes, we can now use the new struct_size() helper:
size = struct_size(instance, entry, count);
This code was detected with the help of Coccinelle.
--- net/netfilter/ipvs/ip_vs_ctl.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)
net/netfilter/ipvs/ip_vs_ctl.c +2 -4
@@ -2722,8 +2722,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)int size; get = (struct ip_vs_get_services *)arg; - size =sizeof (*get) + -sizeof (struct ip_vs_service_entry ) * get->num_services; + size =struct_size (get, entrytable, get->num_services);if (*len != size) {pr_err ("length: %u != %u\n" , *len, size); ret = -EINVAL ;
@@ -2764,8 +2763,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)int size; get = (struct ip_vs_get_dests *)arg; - size =sizeof (*get) + -sizeof (struct ip_vs_dest_entry ) * get->num_dests; + size =struct_size (get, entrytable, get->num_dests);if (*len != size) {pr_err ("length: %u != %u\n" , *len, size); ret = -EINVAL ;
Signature · 1 line
2.11.0
Pablo Neira Ayuso
maintainerPATCH 7/11 netfilter: xt_recent: Use struct_size() in kvzalloc()
In reply to Pablo Neira AyusoFrom: "Gustavo A. R. Silva" <[email protected]>
One of the more common cases of allocation size calculations is finding the size of a structure that has a zero-sized array at the end, along with memory for some number of elements for that array. For example:
struct foo {
int stuff;
void *entry[];
};size = sizeof(struct foo) + count * sizeof(void *); instance = alloc(size, GFP_KERNEL)
Instead of leaving these open-coded and prone to type mistakes, we can now use the new struct_size() helper:
size = struct_size(instance, entry, count);
instance = alloc(size, GFP_KERNEL)
Notice that, in this case, variable sz is not necessary, hence it is removed.
This code was detected with the help of Coccinelle.
--- net/netfilter/xt_recent.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)
net/netfilter/xt_recent.c +1 -3
@@ -337,7 +337,6 @@ static int recent_mt_check(const struct xt_mtchk_param *par,unsigned int nstamp_mask;unsigned int i;int ret = -EINVAL ; -size_t sz;net_get_random_once (&hash_rnd,sizeof (hash_rnd));
@@ -387,8 +386,7 @@ static int recent_mt_check(const struct xt_mtchk_param *par, goto out; } - sz =sizeof (*t) +sizeof (t->iphash[0 ]) * ip_list_hash_size; - t =kvzalloc (sz,GFP_KERNEL ); + t =kvzalloc (struct_size (t, iphash, ip_list_hash_size),GFP_KERNEL );if (t ==NULL ) { ret = -ENOMEM ; goto out;
Signature · 1 line
2.11.0
Pablo Neira Ayuso
maintainerPATCH 8/11 netfilter: conntrack: fix cloned unconfirmed skb->_nfct race in __nf_conntrack_confirm
In reply to Pablo Neira AyusoFrom: Chieh-Min Wang <[email protected]>
For bridge(br_flood) or broadcast/multicast packets, they could clone skb with unconfirmed conntrack which break the rule that unconfirmed skb->_nfct is never shared. With nfqueue running on my system, the race can be easily reproduced with following warning calltrace:
[13257.707525] CPU: 0 PID: 12132 Comm: main Tainted: P W 4.4.60 #7744 [13257.707568] Hardware name: Qualcomm (Flattened Device Tree) [13257.714700] [<c021f6dc>] (unwind_backtrace) from [<c021bce8>] (show_stack+0x10/0x14) [13257.720253] [<c021bce8>] (show_stack) from [<c0449e10>] (dump_stack+0x94/0xa8) [13257.728240] [<c0449e10>] (dump_stack) from [<c022a7e0>] (warn_slowpath_common+0x94/0xb0) [13257.735268] [<c022a7e0>] (warn_slowpath_common) from [<c022a898>] (warn_slowpath_null+0x1c/0x24) [13257.743519] [<c022a898>] (warn_slowpath_null) from [<c06ee450>] (__nf_conntrack_confirm+0xa8/0x618) [13257.752284] [<c06ee450>] (__nf_conntrack_confirm) from [<c0772670>] (ipv4_confirm+0xb8/0xfc) [13257.761049] [<c0772670>] (ipv4_confirm) from [<c06e7a60>] (nf_iterate+0x48/0xa8) [13257.769725] [<c06e7a60>] (nf_iterate) from [<c06e7af0>] (nf_hook_slow+0x30/0xb0) [13257.777108] [<c06e7af0>] (nf_hook_slow) from [<c07f20b4>] (br_nf_post_routing+0x274/0x31c) [13257.784486] [<c07f20b4>] (br_nf_post_routing) from [<c06e7a60>] (nf_iterate+0x48/0xa8) [13257.792556] [<c06e7a60>] (nf_iterate) from [<c06e7af0>] (nf_hook_slow+0x30/0xb0) [13257.800458] [<c06e7af0>] (nf_hook_slow) from [<c07e5580>] (br_forward_finish+0x94/0xa4) [13257.808010] [<c07e5580>] (br_forward_finish) from [<c07f22ac>] (br_nf_forward_finish+0x150/0x1ac) [13257.815736] [<c07f22ac>] (br_nf_forward_finish) from [<c06e8df0>] (nf_reinject+0x108/0x170) [13257.824762] [<c06e8df0>] (nf_reinject) from [<c06ea854>] (nfqnl_recv_verdict+0x3d8/0x420) [13257.832924] [<c06ea854>] (nfqnl_recv_verdict) from [<c06e940c>] (nfnetlink_rcv_msg+0x158/0x248) [13257.841256] [<c06e940c>] (nfnetlink_rcv_msg) from [<c06e5564>] (netlink_rcv_skb+0x54/0xb0) [13257.849762] [<c06e5564>] (netlink_rcv_skb) from [<c06e4ec8>] (netlink_unicast+0x148/0x23c) [13257.858093] [<c06e4ec8>] (netlink_unicast) from [<c06e5364>] (netlink_sendmsg+0x2ec/0x368) [13257.866348] [<c06e5364>] (netlink_sendmsg) from [<c069fb8c>] (sock_sendmsg+0x34/0x44) [13257.874590] [<c069fb8c>] (sock_sendmsg) from [<c06a03dc>] (___sys_sendmsg+0x1ec/0x200) [13257.882489] [<c06a03dc>] (___sys_sendmsg) from [<c06a11c8>] (__sys_sendmsg+0x3c/0x64) [13257.890300] [<c06a11c8>] (__sys_sendmsg) from [<c0209b40>] (ret_fast_syscall+0x0/0x34)
The original code just triggered the warning but do nothing. It will caused the shared conntrack moves to the dying list and the packet be droppped (nf_ct_resolve_clash returns NF_DROP for dying conntrack).
- Reproduce steps:
+----------------------------+
| br0(bridge) |
| |
+-+---------+---------+------+
| eth0| | eth1| | eth2|
| | | | | |
+--+--+ +--+--+ +---+-+
| | |
| | |
+--+-+ +-+--+ +--+-+
| PC1| | PC2| | PC3|
+----+ +----+ +----+iptables -A FORWARD -m mark --mark 0x1000000/0x1000000 -j NFQUEUE --queue-num 100 --queue-bypass
ps: Our nfq userspace program will set mark on packets whose connection has already been processed.
PC1 sends broadcast packets simulated by hping3:
hping3 --rand-source --udp 192.168.1.255 -i u100
- Broadcast racing flow chart is as follow:
br_handle_frame
BR_HOOK(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, br_handle_frame_finish) // skb->_nfct (unconfirmed conntrack) is constructed at PRE_ROUTING stage br_handle_frame_finish
// check if this packet is broadcast
br_flood_forward
br_flood
list_for_each_entry_rcu(p, &br->port_list, list) // iterate through each port
maybe_deliver
deliver_clone
skb = skb_clone(skb)
__br_forward
BR_HOOK(NFPROTO_BRIDGE, NF_BR_FORWARD,...)
// queue in our nfq and received by our userspace program
// goto __nf_conntrack_confirm with process context on CPU 1
br_pass_frame_up
BR_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN,...)
// goto __nf_conntrack_confirm with softirq context on CPU 0Because conntrack confirm can happen at both INPUT and POSTROUTING stage. So with NFQUEUE running, skb->_nfct with the same unconfirmed conntrack could race on different core.
This patch fixes a repeating kernel splat, now it is only displayed once.
--- net/netfilter/nf_conntrack_core.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-)
net/netfilter/nf_conntrack_core.c +11 -3
@@ -936,10 +936,18 @@ __nf_conntrack_confirm(struct sk_buff *skb)* REJECT will give spurious warnings here. */ -/* No external references means no one else could have -* confirmed us. +/* Another skb with the same unconfirmed conntrack may +* win the race. This may happen for bridge(br_flood) +* or broadcast/multicast packets do skb_clone with +* unconfirmed conntrack. */ -WARN_ON (nf_ct_is_confirmed (ct)); +if (unlikely (nf_ct_is_confirmed (ct))) { +WARN_ON_ONCE (1 ); +nf_conntrack_double_unlock (hash, reply_hash); +local_bh_enable (); +return NF_DROP ; + } +pr_debug ("Confirming conntrack %p\n" , ct);/* We have to check the DYING flag after unlink to prevent * a race against nf_ct_get_next_corpse() possibly called from
Signature · 1 line
2.11.0
Pablo Neira Ayuso
maintainerPATCH 9/11 netfilter: reject: skip csum verification for protocols that don't support it
In reply to Pablo Neira AyusoFrom: Alin Nastac <[email protected]>
Some protocols have other means to verify the payload integrity (AH, ESP, SCTP) while others are incompatible with nf_ip(6)_checksum implementation because checksum is either optional or might be partial (UDPLITE, DCCP, GRE). Because nf_ip(6)_checksum was used to validate the packets, ip(6)tables REJECT rules were not capable to generate ICMP(v6) errors for the protocols mentioned above.
This commit also fixes the incorrect pseudo-header protocol used for IPv4 packets that carry other transport protocols than TCP or UDP (pseudo-header used protocol 0 iso the proper value).
--- include/net/netfilter/ipv4/nf_reject.h | 1 + include/net/netfilter/ipv6/nf_reject.h | 1 + include/net/netfilter/nf_reject.h | 27 +++++++++++++++++++++++++++ net/bridge/netfilter/nft_reject_bridge.c | 10 +++++----- net/ipv4/netfilter/nf_reject_ipv4.c | 9 ++------- net/ipv6/netfilter/nf_reject_ipv6.c | 3 +++ 6 files changed, 39 insertions(+), 12 deletions(-) create mode 100644 include/net/netfilter/nf_reject.h
include/net/netfilter/ipv4/nf_reject.h +1 -0
@@ -5,6 +5,7 @@#include <linux/skbuff.h> #include <net/ip.h> #include <net/icmp.h> +#include <net/netfilter/nf_reject.h> void nf_send_unreach (struct sk_buff *skb_in,int code,int hook);void nf_send_reset (struct net *net,struct sk_buff *oldskb,int hook);
include/net/netfilter/ipv6/nf_reject.h +1 -0
@@ -3,6 +3,7 @@#define _IPV6_NF_REJECT_H#include <linux/icmpv6.h> +#include <net/netfilter/nf_reject.h> void nf_send_unreach6 (struct net *net,struct sk_buff *skb_in,unsigned char code,unsigned int hooknum);
include/net/netfilter/nf_reject.h new file +27 -0
@@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NF_REJECT_H +#define _NF_REJECT_H + +static inline bool nf_reject_verify_csum (__u8 proto) +{ +/* Skip protocols that don't use 16-bit one's complement checksum +* of the entire payload. +*/ +switch (proto) { +/* Protocols with other integrity checks. */ +case IPPROTO_AH : +case IPPROTO_ESP : +case IPPROTO_SCTP : + +/* Protocols with partial checksums. */ +case IPPROTO_UDPLITE : +case IPPROTO_DCCP : + +/* Protocols with optional checksums. */ +case IPPROTO_GRE : +return false; + } +return true; +} + +#endif /* _NF_REJECT_H */
net/bridge/netfilter/nft_reject_bridge.c +5 -5
@@ -125,13 +125,10 @@ static void nft_reject_br_send_v4_unreach(struct net *net,if (pskb_trim_rcsum (oldskb,ntohs (ip_hdr (oldskb)->tot_len)))return ; -if (ip_hdr (oldskb)->protocol ==IPPROTO_TCP || -ip_hdr (oldskb)->protocol ==IPPROTO_UDP ) - proto =ip_hdr (oldskb)->protocol; -else - proto =0 ; + proto =ip_hdr (oldskb)->protocol;if (!skb_csum_unnecessary (oldskb) && +nf_reject_verify_csum (proto) &&nf_ip_checksum (oldskb, hook,ip_hdrlen (oldskb), proto))return ;
@@ -234,6 +231,9 @@ static bool reject6_br_csum_ok(struct sk_buff *skb, int hook)if (thoff <0 || thoff >= skb->len || (fo &htons (~0x7 )) !=0 )return false; +if (!nf_reject_verify_csum (proto)) +return true; +return nf_ip6_checksum (skb, hook, thoff, proto) ==0 ; }
net/ipv4/netfilter/nf_reject_ipv4.c +2 -7
@@ -173,21 +173,16 @@ EXPORT_SYMBOL_GPL(nf_send_reset);void nf_send_unreach (struct sk_buff *skb_in,int code,int hook) {struct iphdr *iph =ip_hdr (skb_in); -u8 proto; +u8 proto = iph->protocol;if (iph->frag_off &htons (IP_OFFSET ))return ; -if (skb_csum_unnecessary (skb_in)) { +if (skb_csum_unnecessary (skb_in) || !nf_reject_verify_csum (proto)) {icmp_send (skb_in,ICMP_DEST_UNREACH , code,0 );return ; } -if (iph->protocol ==IPPROTO_TCP || iph->protocol ==IPPROTO_UDP ) - proto = iph->protocol; -else - proto =0 ; -if (nf_ip_checksum (skb_in, hook,ip_hdrlen (skb_in), proto) ==0 )icmp_send (skb_in,ICMP_DEST_UNREACH , code,0 ); }
net/ipv6/netfilter/nf_reject_ipv6.c +3 -0
@@ -233,6 +233,9 @@ static bool reject6_csum_ok(struct sk_buff *skb, int hook)if (thoff <0 || thoff >= skb->len || (fo &htons (~0x7 )) !=0 )return false; +if (!nf_reject_verify_csum (proto)) +return true; +return nf_ip6_checksum (skb, hook, thoff, proto) ==0 ; }
Signature · 1 line
2.11.0
Pablo Neira Ayuso
maintainerPATCH 10/11 netfilter: ipt_CLUSTERIP: make symbol 'cip_netdev_notifier' static
In reply to Pablo Neira AyusoFrom: Wei Yongjun <[email protected]>
Fixes the following sparse warnings:
net/ipv4/netfilter/ipt_CLUSTERIP.c:867:23: warning:
symbol 'cip_netdev_notifier' was not declared. Should it be static?
--- net/ipv4/netfilter/ipt_CLUSTERIP.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/ipv4/netfilter/ipt_CLUSTERIP.c +1 -1
@@ -864,7 +864,7 @@ static struct pernet_operations clusterip_net_ops = { .size = sizeof(struct clusterip_net), }; -struct notifier_block cip_netdev_notifier = { +static struct notifier_block cip_netdev_notifier = { .notifier_call = clusterip_netdev_event };
Signature · 1 line
2.11.0
Pablo Neira Ayuso
maintainerPATCH 11/11 netfilter: nf_conntrack_sip: add sip_external_media logic
In reply to Pablo Neira AyusoFrom: Alin Nastac <[email protected]>
When enabled, the sip_external_media logic will leave SDP payload untouched when it detects that interface towards INVITEd party is the same with the one towards media endpoint.
The typical scenario for this logic is when a LAN SIP agent has more than one IP address (uses a different address for media streams than the one used on signalling stream) and it also forwards calls to a voice mailbox located on the WAN side. In such case sip_direct_media must be disabled (so normal calls could be handled by the SIP helper), but media streams that are not traversing this router must also be excluded from address translation (e.g. call forwards).
--- net/netfilter/nf_conntrack_sip.c | 42 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+)
net/netfilter/nf_conntrack_sip.c +42 -0
@@ -21,6 +21,8 @@#include <linux/tcp.h> #include <linux/netfilter.h> +#include <net/route.h> +#include <net/ip6_route.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_expect.h>
@@ -54,6 +56,11 @@ module_param(sip_direct_media, int, 0600);MODULE_PARM_DESC (sip_direct_media,"Expect Media streams between signalling " "endpoints only (default 1)" ); +static int sip_external_media__read_mostly =0 ; +module_param (sip_external_media, int,0600 ); +MODULE_PARM_DESC (sip_external_media,"Expect Media streams between external " +"endpoints (default 0)" ); +const struct nf_nat_sip_hooks *nf_nat_sip_hooks;EXPORT_SYMBOL_GPL (nf_nat_sip_hooks);
@@ -861,6 +868,41 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,if (!nf_inet_addr_cmp (daddr, &ct->tuplehash[dir].tuple.src.u3))return NF_ACCEPT ; saddr = &ct->tuplehash[!dir].tuple.src.u3; + }else if (sip_external_media) { +struct net_device *dev =skb_dst (skb)->dev; +struct net *net =dev_net (dev); +struct rtable *rt; +struct flowi4 fl4 = {}; +#if IS_ENABLED (CONFIG_IPV6 ) +struct flowi6 fl6 = {}; +#endif +struct dst_entry *dst =NULL ; + +switch (nf_ct_l3num (ct)) { +case NFPROTO_IPV4 : + fl4.daddr = daddr->ip; + rt =ip_route_output_key (net, &fl4); +if (!IS_ERR (rt)) + dst = &rt->dst; +break ; + +#if IS_ENABLED (CONFIG_IPV6 ) +case NFPROTO_IPV6 : + fl6.daddr = daddr->in6; + dst =ip6_route_output (net,NULL , &fl6); +if (dst->error) { +dst_release (dst); + dst =NULL ; + } +break ; +#endif + } + +/* Don't predict any conntracks when media endpoint is reachable +* through the same interface as the signalling peer. +*/ +if (dst && dst->dev == dev) +return NF_ACCEPT ; }/* We need to check whether the registration exists before attempting
Signature · 1 line
2.11.0
David Miller
maintainerFrom: Pablo Neira Ayuso <[email protected]>
Date: Mon, 18 Feb 2019 00:23:46 +0100
Quoted 2 lines
The following patchset contains Netfilter/IPVS updates for you net-next tree:
...
Quoted 3 lines
You can pull these changes from:
git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next.git
Pulled, thanks Pablo.