diff options
Diffstat (limited to 'include/net')
| -rw-r--r-- | include/net/dst.h | 2 | ||||
| -rw-r--r-- | include/net/ip_fib.h | 6 | ||||
| -rw-r--r-- | include/net/ip_vs.h | 295 | ||||
| -rw-r--r-- | include/net/net_namespace.h | 2 | ||||
| -rw-r--r-- | include/net/netfilter/nf_conntrack.h | 23 | ||||
| -rw-r--r-- | include/net/netfilter/nf_conntrack_ecache.h | 12 | ||||
| -rw-r--r-- | include/net/netfilter/nf_conntrack_extend.h | 10 | ||||
| -rw-r--r-- | include/net/netfilter/nf_conntrack_helper.h | 6 | ||||
| -rw-r--r-- | include/net/netfilter/nf_conntrack_l3proto.h | 2 | ||||
| -rw-r--r-- | include/net/netfilter/nf_conntrack_timestamp.h | 65 | ||||
| -rw-r--r-- | include/net/netfilter/nf_nat.h | 6 | ||||
| -rw-r--r-- | include/net/netfilter/nf_nat_core.h | 4 | ||||
| -rw-r--r-- | include/net/netns/conntrack.h | 4 | ||||
| -rw-r--r-- | include/net/netns/ip_vs.h | 143 | ||||
| -rw-r--r-- | include/net/netns/ipv4.h | 1 | ||||
| -rw-r--r-- | include/net/sch_generic.h | 59 | ||||
| -rw-r--r-- | include/net/sock.h | 2 |
17 files changed, 540 insertions, 102 deletions
diff --git a/include/net/dst.h b/include/net/dst.h index 93b0310317be..be5a0d4c491d 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -72,7 +72,7 @@ struct dst_entry { u32 _metrics[RTAX_MAX]; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID __u32 tclassid; #else __u32 __pad2; diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 07bdb5e9e8ac..65d1fcdbc63b 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -55,7 +55,7 @@ struct fib_nh { int nh_weight; int nh_power; #endif -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID __u32 nh_tclassid; #endif int nh_oif; @@ -201,7 +201,7 @@ static inline int fib_lookup(struct net *net, const struct flowi *flp, extern int __net_init fib4_rules_init(struct net *net); extern void __net_exit fib4_rules_exit(struct net *net); -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID extern u32 fib_rules_tclass(struct fib_result *res); #endif @@ -235,7 +235,7 @@ extern struct fib_table *fib_hash_table(u32 id); static inline void fib_combine_itag(u32 *itag, struct fib_result *res) { -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID #ifdef CONFIG_IP_MULTIPLE_TABLES u32 rtag; #endif diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index b7bbd6c28cfa..b23bea62f708 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -28,6 +28,80 @@ #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) #include <net/netfilter/nf_conntrack.h> #endif +#include <net/net_namespace.h> /* Netw namespace */ + +/* + * Generic access of ipvs struct + */ +static inline struct netns_ipvs *net_ipvs(struct net* net) +{ + return net->ipvs; +} +/* + * Get net ptr from skb in traffic cases + * use skb_sknet when call is from userland (ioctl or netlink) + */ +static inline struct net *skb_net(const struct sk_buff *skb) +{ +#ifdef CONFIG_NET_NS +#ifdef CONFIG_IP_VS_DEBUG + /* + * This is used for debug only. + * Start with the most likely hit + * End with BUG + */ + if (likely(skb->dev && skb->dev->nd_net)) + return dev_net(skb->dev); + if (skb_dst(skb)->dev) + return dev_net(skb_dst(skb)->dev); + WARN(skb->sk, "Maybe skb_sknet should be used in %s() at line:%d\n", + __func__, __LINE__); + if (likely(skb->sk && skb->sk->sk_net)) + return sock_net(skb->sk); + pr_err("There is no net ptr to find in the skb in %s() line:%d\n", + __func__, __LINE__); + BUG(); +#else + return dev_net(skb->dev ? : skb_dst(skb)->dev); +#endif +#else + return &init_net; +#endif +} + +static inline struct net *skb_sknet(const struct sk_buff *skb) +{ +#ifdef CONFIG_NET_NS +#ifdef CONFIG_IP_VS_DEBUG + /* Start with the most likely hit */ + if (likely(skb->sk && skb->sk->sk_net)) + return sock_net(skb->sk); + WARN(skb->dev, "Maybe skb_net should be used instead in %s() line:%d\n", + __func__, __LINE__); + if (likely(skb->dev && skb->dev->nd_net)) + return dev_net(skb->dev); + pr_err("There is no net ptr to find in the skb in %s() line:%d\n", + __func__, __LINE__); + BUG(); +#else + return sock_net(skb->sk); +#endif +#else + return &init_net; +#endif +} +/* + * This one needed for single_open_net since net is stored directly in + * private not as a struct i.e. seq_file_net cant be used. + */ +static inline struct net *seq_file_single_net(struct seq_file *seq) +{ +#ifdef CONFIG_NET_NS + return (struct net *)seq->private; +#else + return &init_net; +#endif +} /* Connections' size value needed by ip_vs_ctl.c */ extern int ip_vs_conn_tab_size; @@ -258,6 +332,23 @@ struct ip_vs_seq { before last resized pkt */ }; +/* + * counters per cpu + */ +struct ip_vs_counters { + __u32 conns; /* connections scheduled */ + __u32 inpkts; /* incoming packets */ + __u32 outpkts; /* outgoing packets */ + __u64 inbytes; /* incoming bytes */ + __u64 outbytes; /* outgoing bytes */ +}; +/* + * Stats per cpu + */ +struct ip_vs_cpu_stats { + struct ip_vs_counters ustats; + struct u64_stats_sync syncp; +}; /* * IPVS statistics objects @@ -279,17 +370,34 @@ struct ip_vs_estimator { }; struct ip_vs_stats { - struct ip_vs_stats_user ustats; /* statistics */ + struct ip_vs_stats_user ustats; /* statistics */ struct ip_vs_estimator est; /* estimator */ - - spinlock_t lock; /* spin lock */ + struct ip_vs_cpu_stats *cpustats; /* per cpu counters */ + spinlock_t lock; /* spin lock */ }; +/* + * Helper Macros for per cpu + * ipvs->tot_stats->ustats.count + */ +#define IPVS_STAT_INC(ipvs, count) \ + __this_cpu_inc((ipvs)->ustats->count) + +#define IPVS_STAT_ADD(ipvs, count, value) \ + do {\ + write_seqcount_begin(per_cpu_ptr((ipvs)->ustats_seq, \ + raw_smp_processor_id())); \ + __this_cpu_add((ipvs)->ustats->count, value); \ + write_seqcount_end(per_cpu_ptr((ipvs)->ustats_seq, \ + raw_smp_processor_id())); \ + } while (0) + struct dst_entry; struct iphdr; struct ip_vs_conn; struct ip_vs_app; struct sk_buff; +struct ip_vs_proto_data; struct ip_vs_protocol { struct ip_vs_protocol *next; @@ -297,21 +405,22 @@ struct ip_vs_protocol { u16 protocol; u16 num_states; int dont_defrag; - atomic_t appcnt; /* counter of proto app incs */ - int *timeout_table; /* protocol timeout table */ void (*init)(struct ip_vs_protocol *pp); void (*exit)(struct ip_vs_protocol *pp); + void (*init_netns)(struct net *net, struct ip_vs_proto_data *pd); + + void (*exit_netns)(struct net *net, struct ip_vs_proto_data *pd); + int (*conn_schedule)(int af, struct sk_buff *skb, - struct ip_vs_protocol *pp, + struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp); struct ip_vs_conn * (*conn_in_get)(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse); @@ -319,7 +428,6 @@ struct ip_vs_protocol { struct ip_vs_conn * (*conn_out_get)(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse); @@ -337,11 +445,11 @@ struct ip_vs_protocol { int (*state_transition)(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_protocol *pp); + struct ip_vs_proto_data *pd); - int (*register_app)(struct ip_vs_app *inc); + int (*register_app)(struct net *net, struct ip_vs_app *inc); - void (*unregister_app)(struct ip_vs_app *inc); + void (*unregister_app)(struct net *net, struct ip_vs_app *inc); int (*app_conn_bind)(struct ip_vs_conn *cp); @@ -350,14 +458,26 @@ struct ip_vs_protocol { int offset, const char *msg); - void (*timeout_change)(struct ip_vs_protocol *pp, int flags); + void (*timeout_change)(struct ip_vs_proto_data *pd, int flags); +}; - int (*set_state_timeout)(struct ip_vs_protocol *pp, char *sname, int to); +/* + * protocol data per netns + */ +struct ip_vs_proto_data { + struct ip_vs_proto_data *next; + struct ip_vs_protocol *pp; + int *timeout_table; /* protocol timeout table */ + atomic_t appcnt; /* counter of proto app incs. */ + struct tcp_states_t *tcp_state_table; }; -extern struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto); +extern struct ip_vs_protocol *ip_vs_proto_get(unsigned short proto); +extern struct ip_vs_proto_data *ip_vs_proto_data_get(struct net *net, + unsigned short proto); struct ip_vs_conn_param { + struct net *net; const union nf_inet_addr *caddr; const union nf_inet_addr *vaddr; __be16 cport; @@ -375,16 +495,19 @@ struct ip_vs_conn_param { */ struct ip_vs_conn { struct list_head c_list; /* hashed list heads */ - +#ifdef CONFIG_NET_NS + struct net *net; /* Name space */ +#endif /* Protocol, addresses and port numbers */ - u16 af; /* address family */ - union nf_inet_addr caddr; /* client address */ - union nf_inet_addr vaddr; /* virtual address */ - union nf_inet_addr daddr; /* destination address */ - volatile __u32 flags; /* status flags */ - __be16 cport; - __be16 vport; - __be16 dport; + u16 af; /* address family */ + __be16 cport; + __be16 vport; + __be16 dport; + __u32 fwmark; /* Fire wall mark from skb */ + union nf_inet_addr caddr; /* client address */ + union nf_inet_addr vaddr; /* virtual address */ + union nf_inet_addr daddr; /* destination address */ + volatile __u32 flags; /* status flags */ __u16 protocol; /* Which protocol (TCP/UDP) */ /* counter and timer */ @@ -422,10 +545,38 @@ struct ip_vs_conn { struct ip_vs_seq in_seq; /* incoming seq. struct */ struct ip_vs_seq out_seq; /* outgoing seq. struct */ + const struct ip_vs_pe *pe; char *pe_data; __u8 pe_data_len; }; +/* + * To save some memory in conn table when name space is disabled. + */ +static inline struct net *ip_vs_conn_net(const struct ip_vs_conn *cp) +{ +#ifdef CONFIG_NET_NS + return cp->net; +#else + return &init_net; +#endif +} +static inline void ip_vs_conn_net_set(struct ip_vs_conn *cp, struct net *net) +{ +#ifdef CONFIG_NET_NS + cp->net = net; +#endif +} + +static inline int ip_vs_conn_net_eq(const struct ip_vs_conn *cp, + struct net *net) +{ +#ifdef CONFIG_NET_NS + return cp->net == net; +#else + return 1; +#endif +} /* * Extended internal versions of struct ip_vs_service_user and @@ -485,6 +636,7 @@ struct ip_vs_service { unsigned flags; /* service status flags */ unsigned timeout; /* persistent timeout in ticks */ __be32 netmask; /* grouping granularity */ + struct net *net; struct list_head destinations; /* real server d-linked list */ __u32 num_dests; /* number of servers */ @@ -510,8 +662,8 @@ struct ip_vs_dest { struct list_head d_list; /* for table with all the dests */ u16 af; /* address family */ - union nf_inet_addr addr; /* IP address of the server */ __be16 port; /* port number of the server */ + union nf_inet_addr addr; /* IP address of the server */ volatile unsigned flags; /* dest status flags */ atomic_t conn_flags; /* flags to copy to conn */ atomic_t weight; /* server weight */ @@ -538,8 +690,8 @@ struct ip_vs_dest { /* for virtual service */ struct ip_vs_service *svc; /* service it belongs to */ __u16 protocol; /* which protocol (TCP/UDP) */ - union nf_inet_addr vaddr; /* virtual IP address */ __be16 vport; /* virtual port number */ + union nf_inet_addr vaddr; /* virtual IP address */ __u32 vfwmark; /* firewall mark of service */ }; @@ -674,13 +826,14 @@ enum { IP_VS_DIR_LAST, }; -static inline void ip_vs_conn_fill_param(int af, int protocol, +static inline void ip_vs_conn_fill_param(struct net *net, int af, int protocol, const union nf_inet_addr *caddr, __be16 cport, const union nf_inet_addr *vaddr, __be16 vport, struct ip_vs_conn_param *p) { + p->net = net; p->af = af; p->protocol = protocol; p->caddr = caddr; @@ -695,7 +848,6 @@ struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p); struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p); struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse); @@ -703,7 +855,6 @@ struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p); struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse); @@ -719,14 +870,14 @@ extern void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport); struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p, const union nf_inet_addr *daddr, __be16 dport, unsigned flags, - struct ip_vs_dest *dest); + struct ip_vs_dest *dest, __u32 fwmark); extern void ip_vs_conn_expire_now(struct ip_vs_conn *cp); extern const char * ip_vs_state_name(__u16 proto, int state); -extern void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp); +extern void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp); extern int ip_vs_check_template(struct ip_vs_conn *ct); -extern void ip_vs_random_dropentry(void); +extern void ip_vs_random_dropentry(struct net *net); extern int ip_vs_conn_init(void); extern void ip_vs_conn_cleanup(void); @@ -796,12 +947,12 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp) * (from ip_vs_app.c) */ #define IP_VS_APP_MAX_PORTS 8 -extern int register_ip_vs_app(struct ip_vs_app *app); -extern void unregister_ip_vs_app(struct ip_vs_app *app); +extern int register_ip_vs_app(struct net *net, struct ip_vs_app *app); +extern void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app); extern int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp); extern void ip_vs_unbind_app(struct ip_vs_conn *cp); -extern int -register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port); +extern int register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, + __u16 proto, __u16 port); extern int ip_vs_app_inc_get(struct ip_vs_app *inc); extern void ip_vs_app_inc_put(struct ip_vs_app *inc); @@ -814,15 +965,27 @@ void ip_vs_bind_pe(struct ip_vs_service *svc, struct ip_vs_pe *pe); void ip_vs_unbind_pe(struct ip_vs_service *svc); int register_ip_vs_pe(struct ip_vs_pe *pe); int unregister_ip_vs_pe(struct ip_vs_pe *pe); -extern struct ip_vs_pe *ip_vs_pe_get(const char *name); -extern void ip_vs_pe_put(struct ip_vs_pe *pe); +struct ip_vs_pe *ip_vs_pe_getbyname(const char *name); +struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name); + +static inline void ip_vs_pe_get(const struct ip_vs_pe *pe) +{ + if (pe && pe->module) + __module_get(pe->module); +} + +static inline void ip_vs_pe_put(const struct ip_vs_pe *pe) +{ + if (pe && pe->module) + module_put(pe->module); +} /* * IPVS protocol functions (from ip_vs_proto.c) */ extern int ip_vs_protocol_init(void); extern void ip_vs_protocol_cleanup(void); -extern void ip_vs_protocol_timeout_change(int flags); +extern void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags); extern int *ip_vs_create_timeout_table(int *table, int size); extern int ip_vs_set_state_timeout(int *table, int num, const char *const *names, @@ -852,26 +1015,21 @@ extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name); extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler); extern struct ip_vs_conn * ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, - struct ip_vs_protocol *pp, int *ignored); + struct ip_vs_proto_data *pd, int *ignored); extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, - struct ip_vs_protocol *pp); + struct ip_vs_proto_data *pd); /* * IPVS control data and functions (from ip_vs_ctl.c) */ -extern int sysctl_ip_vs_cache_bypass; -extern int sysctl_ip_vs_expire_nodest_conn; -extern int sysctl_ip_vs_expire_quiescent_template; -extern int sysctl_ip_vs_sync_threshold[2]; -extern int sysctl_ip_vs_nat_icmp_send; -extern int sysctl_ip_vs_conntrack; -extern int sysctl_ip_vs_snat_reroute; extern struct ip_vs_stats ip_vs_stats; extern const struct ctl_path net_vs_ctl_path[]; +extern int sysctl_ip_vs_sync_ver; +extern void ip_vs_sync_switch_mode(struct net *net, int mode); extern struct ip_vs_service * -ip_vs_service_get(int af, __u32 fwmark, __u16 protocol, +ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport); static inline void ip_vs_service_put(struct ip_vs_service *svc) @@ -880,7 +1038,7 @@ static inline void ip_vs_service_put(struct ip_vs_service *svc) } extern struct ip_vs_dest * -ip_vs_lookup_real_service(int af, __u16 protocol, +ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol, const union nf_inet_addr *daddr, __be16 dport); extern int ip_vs_use_count_inc(void); @@ -888,8 +1046,9 @@ extern void ip_vs_use_count_dec(void); extern int ip_vs_control_init(void); extern void ip_vs_control_cleanup(void); extern struct ip_vs_dest * -ip_vs_find_dest(int af, const union nf_inet_addr *daddr, __be16 dport, - const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol); +ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr, + __be16 dport, const union nf_inet_addr *vaddr, __be16 vport, + __u16 protocol, __u32 fwmark); extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp); @@ -897,14 +1056,12 @@ extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp); * IPVS sync daemon data and function prototypes * (from ip_vs_sync.c) */ -extern volatile int ip_vs_sync_state; -extern volatile int ip_vs_master_syncid; -extern volatile int ip_vs_backup_syncid; -extern char ip_vs_master_mcast_ifn[IP_VS_IFNAME_MAXLEN]; -extern char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN]; -extern int start_sync_thread(int state, char *mcast_ifn, __u8 syncid); -extern int stop_sync_thread(int state); -extern void ip_vs_sync_conn(struct ip_vs_conn *cp); +extern int start_sync_thread(struct net *net, int state, char *mcast_ifn, + __u8 syncid); +extern int stop_sync_thread(struct net *net, int state); +extern void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp); +extern int ip_vs_sync_init(void); +extern void ip_vs_sync_cleanup(void); /* @@ -912,8 +1069,8 @@ extern void ip_vs_sync_conn(struct ip_vs_conn *cp); */ extern int ip_vs_estimator_init(void); extern void ip_vs_estimator_cleanup(void); -extern void ip_vs_new_estimator(struct ip_vs_stats *stats); -extern void ip_vs_kill_estimator(struct ip_vs_stats *stats); +extern void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats); +extern void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats); extern void ip_vs_zero_estimator(struct ip_vs_stats *stats); /* @@ -955,11 +1112,13 @@ extern int ip_vs_icmp_xmit_v6 extern int ip_vs_drop_rate; extern int ip_vs_drop_counter; -static __inline__ int ip_vs_todrop(void) +static inline int ip_vs_todrop(struct netns_ipvs *ipvs) { - if (!ip_vs_drop_rate) return 0; - if (--ip_vs_drop_counter > 0) return 0; - ip_vs_drop_counter = ip_vs_drop_rate; + if (!ipvs->drop_rate) + return 0; + if (--ipvs->drop_counter > 0) + return 0; + ipvs->drop_counter = ipvs->drop_rate; return 1; } @@ -1047,9 +1206,9 @@ static inline void ip_vs_notrack(struct sk_buff *skb) * Netfilter connection tracking * (from ip_vs_nfct.c) */ -static inline int ip_vs_conntrack_enabled(void) +static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs) { - return sysctl_ip_vs_conntrack; + return ipvs->sysctl_conntrack; } extern void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, @@ -1062,7 +1221,7 @@ extern void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp); #else -static inline int ip_vs_conntrack_enabled(void) +static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs) { return 0; } diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 1bf812b21fb7..b3b4a34cb2cc 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -20,6 +20,7 @@ #include <net/netns/conntrack.h> #endif #include <net/netns/xfrm.h> +#include <net/netns/ip_vs.h> struct proc_dir_entry; struct net_device; @@ -94,6 +95,7 @@ struct net { #ifdef CONFIG_XFRM struct netns_xfrm xfrm; #endif + struct netns_ipvs *ipvs; }; diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index d85cff10e169..d0d13378991e 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -50,11 +50,24 @@ union nf_conntrack_expect_proto { /* per conntrack: application helper private data */ union nf_conntrack_help { /* insert conntrack helper private data (master) here */ +#if defined(CONFIG_NF_CONNTRACK_FTP) || defined(CONFIG_NF_CONNTRACK_FTP_MODULE) struct nf_ct_ftp_master ct_ftp_info; +#endif +#if defined(CONFIG_NF_CONNTRACK_PPTP) || \ + defined(CONFIG_NF_CONNTRACK_PPTP_MODULE) struct nf_ct_pptp_master ct_pptp_info; +#endif +#if defined(CONFIG_NF_CONNTRACK_H323) || \ + defined(CONFIG_NF_CONNTRACK_H323_MODULE) struct nf_ct_h323_master ct_h323_info; +#endif +#if defined(CONFIG_NF_CONNTRACK_SANE) || \ + defined(CONFIG_NF_CONNTRACK_SANE_MODULE) struct nf_ct_sane_master ct_sane_info; +#endif +#if defined(CONFIG_NF_CONNTRACK_SIP) || defined(CONFIG_NF_CONNTRACK_SIP_MODULE) struct nf_ct_sip_master ct_sip_info; +#endif }; #include <linux/types.h> @@ -116,14 +129,14 @@ struct nf_conn { u_int32_t secmark; #endif - /* Storage reserved for other modules: */ - union nf_conntrack_proto proto; - /* Extensions */ struct nf_ct_ext *ext; #ifdef CONFIG_NET_NS struct net *ct_net; #endif + + /* Storage reserved for other modules, must be the last member */ + union nf_conntrack_proto proto; }; static inline struct nf_conn * @@ -189,9 +202,9 @@ extern void nf_ct_l3proto_module_put(unsigned short l3proto); * Allocate a hashtable of hlist_head (if nulls == 0), * or hlist_nulls_head (if nulls == 1) */ -extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int nulls); +extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls); -extern void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size); +extern void nf_ct_free_hashtable(void *hash, unsigned int size); extern struct nf_conntrack_tuple_hash * __nf_conntrack_find(struct net *net, u16 zone, diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 96ba5f7dcab6..8fdb04b8cce0 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -23,12 +23,17 @@ struct nf_conntrack_ecache { static inline struct nf_conntrack_ecache * nf_ct_ecache_find(const struct nf_conn *ct) { +#ifdef CONFIG_NF_CONNTRACK_EVENTS return nf_ct_ext_find(ct, NF_CT_EXT_ECACHE); +#else + return NULL; +#endif } static inline struct nf_conntrack_ecache * nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) { +#ifdef CONFIG_NF_CONNTRACK_EVENTS struct net *net = nf_ct_net(ct); struct nf_conntrack_ecache *e; @@ -45,6 +50,9 @@ nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) e->expmask = expmask; } return e; +#else + return NULL; +#endif }; #ifdef CONFIG_NF_CONNTRACK_EVENTS @@ -59,7 +67,7 @@ struct nf_ct_event_notifier { int (*fcn)(unsigned int events, struct nf_ct_event *item); }; -extern struct nf_ct_event_notifier *nf_conntrack_event_cb; +extern struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb; extern int nf_conntrack_register_notifier(struct nf_ct_event_notifier *nb); extern void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *nb); @@ -159,7 +167,7 @@ struct nf_exp_event_notifier { int (*fcn)(unsigned int events, struct nf_exp_event *item); }; -extern struct nf_exp_event_notifier *nf_expect_event_cb; +extern struct nf_exp_event_notifier __rcu *nf_expect_event_cb; extern int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *nb); extern void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *nb); diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 0772d296dfdb..2dcf31703acb 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -7,10 +7,19 @@ enum nf_ct_ext_id { NF_CT_EXT_HELPER, +#if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE) NF_CT_EXT_NAT, +#endif NF_CT_EXT_ACCT, +#ifdef CONFIG_NF_CONNTRACK_EVENTS NF_CT_EXT_ECACHE, +#endif +#ifdef CONFIG_NF_CONNTRACK_ZONES NF_CT_EXT_ZONE, +#endif +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + NF_CT_EXT_TSTAMP, +#endif NF_CT_EXT_NUM, }; @@ -19,6 +28,7 @@ enum nf_ct_ext_id { #define NF_CT_EXT_ACCT_TYPE struct nf_conn_counter #define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache #define NF_CT_EXT_ZONE_TYPE struct nf_conntrack_zone +#define NF_CT_EXT_TSTAMP_TYPE struct nf_conn_tstamp /* Extensions: optional stuff which isn't permanently in struct. */ struct nf_ct_ext { diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 32c305dbdab6..f1c1311adc2c 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -63,4 +63,10 @@ static inline struct nf_conn_help *nfct_help(const struct nf_conn *ct) extern int nf_conntrack_helper_init(void); extern void nf_conntrack_helper_fini(void); +extern int nf_conntrack_broadcast_help(struct sk_buff *skb, + unsigned int protoff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int timeout); + #endif /*_NF_CONNTRACK_HELPER_H*/ diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h index a7547611e8f1..e8010f445ae1 100644 --- a/include/net/netfilter/nf_conntrack_l3proto.h +++ b/include/net/netfilter/nf_conntrack_l3proto.h @@ -73,7 +73,7 @@ struct nf_conntrack_l3proto { struct module *me; }; -extern struct nf_conntrack_l3proto *nf_ct_l3protos[AF_MAX]; +extern struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[AF_MAX]; /* Protocol registration. */ extern int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto); diff --git a/include/net/netfilter/nf_conntrack_timestamp.h b/include/net/netfilter/nf_conntrack_timestamp.h new file mode 100644 index 000000000000..fc9c82b1f06b --- /dev/null +++ b/include/net/netfilter/nf_conntrack_timestamp.h @@ -0,0 +1,65 @@ +#ifndef _NF_CONNTRACK_TSTAMP_H +#define _NF_CONNTRACK_TSTAMP_H + +#include <net/net_namespace.h> +#include <linux/netfilter/nf_conntrack_common.h> +#include <linux/netfilter/nf_conntrack_tuple_common.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_extend.h> + +struct nf_conn_tstamp { + u_int64_t start; + u_int64_t stop; +}; + +static inline +struct nf_conn_tstamp *nf_conn_tstamp_find(const struct nf_conn *ct) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + return nf_ct_ext_find(ct, NF_CT_EXT_TSTAMP); +#else + return NULL; +#endif +} + +static inline +struct nf_conn_tstamp *nf_ct_tstamp_ext_add(struct nf_conn *ct, gfp_t gfp) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + struct net *net = nf_ct_net(ct); + + if (!net->ct.sysctl_tstamp) + return NULL; + + return nf_ct_ext_add(ct, NF_CT_EXT_TSTAMP, gfp); +#else + return NULL; +#endif +}; + +static inline bool nf_ct_tstamp_enabled(struct net *net) +{ + return net->ct.sysctl_tstamp != 0; +} + +static inline void nf_ct_set_tstamp(struct net *net, bool enable) +{ + net->ct.sysctl_tstamp = enable; +} + +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP +extern int nf_conntrack_tstamp_init(struct net *net); +extern void nf_conntrack_tstamp_fini(struct net *net); +#else +static inline int nf_conntrack_tstamp_init(struct net *net) +{ + return 0; +} + +static inline void nf_conntrack_tstamp_fini(struct net *net) +{ + return; +} +#endif /* CONFIG_NF_CONNTRACK_TIMESTAMP */ + +#endif /* _NF_CONNTRACK_TSTAMP_H */ diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index f5f09f032a90..aff80b190c12 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -56,7 +56,9 @@ struct nf_nat_multi_range_compat { /* per conntrack: nat application helper private data */ union nf_conntrack_nat_help { /* insert nat helper private data here */ +#if defined(CONFIG_NF_NAT_PPTP) || defined(CONFIG_NF_NAT_PPTP_MODULE) struct nf_nat_pptp nat_pptp_info; +#endif }; struct nf_conn; @@ -84,7 +86,11 @@ extern int nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple, static inline struct nf_conn_nat *nfct_nat(const struct nf_conn *ct) { +#if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE) return nf_ct_ext_find(ct, NF_CT_EXT_NAT); +#else + return NULL; +#endif } #else /* !__KERNEL__: iptables wants this to compile. */ diff --git a/include/net/netfilter/nf_nat_core.h b/include/net/netfilter/nf_nat_core.h index 33602ab66190..3dc7b98effeb 100644 --- a/include/net/netfilter/nf_nat_core.h +++ b/include/net/netfilter/nf_nat_core.h @@ -21,9 +21,9 @@ static inline int nf_nat_initialized(struct nf_conn *ct, enum nf_nat_manip_type manip) { if (manip == IP_NAT_MANIP_SRC) - return test_bit(IPS_SRC_NAT_DONE_BIT, &ct->status); + return ct->status & IPS_SRC_NAT_DONE; else - return test_bit(IPS_DST_NAT_DONE_BIT, &ct->status); + return ct->status & IPS_DST_NAT_DONE; } struct nlattr; diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index d4958d4c6574..341eb089349e 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -21,15 +21,15 @@ struct netns_ct { int sysctl_events; unsigned int sysctl_events_retry_timeout; int sysctl_acct; + int sysctl_tstamp; int sysctl_checksum; unsigned int sysctl_log_invalid; /* Log invalid packets */ #ifdef CONFIG_SYSCTL struct ctl_table_header *sysctl_header; struct ctl_table_header *acct_sysctl_header; + struct ctl_table_header *tstamp_sysctl_header; struct ctl_table_header *event_sysctl_header; #endif - int hash_vmalloc; - int expect_vmalloc; char *slabname; }; #endif diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h new file mode 100644 index 000000000000..259ebac904bf --- /dev/null +++ b/include/net/netns/ip_vs.h @@ -0,0 +1,143 @@ +/* + * IP Virtual Server + * Data structure for network namspace + * + */ + +#ifndef IP_VS_H_ +#define IP_VS_H_ + +#include <linux/list.h> +#include <linux/mutex.h> +#include <linux/list_nulls.h> +#include <linux/ip_vs.h> +#include <asm/atomic.h> +#include <linux/in.h> + +struct ip_vs_stats; +struct ip_vs_sync_buff; +struct ctl_table_header; + +struct netns_ipvs { + int gen; /* Generation */ + /* + * Hash table: for real service lookups + */ + #define IP_VS_RTAB_BITS 4 + #define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS) + #define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1) + + struct list_head rs_table[IP_VS_RTAB_SIZE]; + /* ip_vs_app */ + struct list_head app_list; + struct mutex app_mutex; + struct lock_class_key app_key; /* mutex debuging */ + + /* ip_vs_proto */ + #define IP_VS_PROTO_TAB_SIZE 32 /* must be power of 2 */ + struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE]; + /* ip_vs_proto_tcp */ +#ifdef CONFIG_IP_VS_PROTO_TCP + #define TCP_APP_TAB_BITS 4 + #define TCP_APP_TAB_SIZE (1 << TCP_APP_TAB_BITS) + #define TCP_APP_TAB_MASK (TCP_APP_TAB_SIZE - 1) + struct list_head tcp_apps[TCP_APP_TAB_SIZE]; + spinlock_t tcp_app_lock; +#endif + /* ip_vs_proto_udp */ +#ifdef CONFIG_IP_VS_PROTO_UDP + #define UDP_APP_TAB_BITS 4 + #define UDP_APP_TAB_SIZE (1 << UDP_APP_TAB_BITS) + #define UDP_APP_TAB_MASK (UDP_APP_TAB_SIZE - 1) + struct list_head udp_apps[UDP_APP_TAB_SIZE]; + spinlock_t udp_app_lock; +#endif + /* ip_vs_proto_sctp */ +#ifdef CONFIG_IP_VS_PROTO_SCTP + #define SCTP_APP_TAB_BITS 4 + #define SCTP_APP_TAB_SIZE (1 << SCTP_APP_TAB_BITS) + #define SCTP_APP_TAB_MASK (SCTP_APP_TAB_SIZE - 1) + /* Hash table for SCTP application incarnations */ + struct list_head sctp_apps[SCTP_APP_TAB_SIZE]; + spinlock_t sctp_app_lock; +#endif + /* ip_vs_conn */ + atomic_t conn_count; /* connection counter */ + + /* ip_vs_ctl */ + struct ip_vs_stats *tot_stats; /* Statistics & est. */ + struct ip_vs_cpu_stats __percpu *cpustats; /* Stats per cpu */ + seqcount_t *ustats_seq; /* u64 read retry */ + + int num_services; /* no of virtual services */ + /* 1/rate drop and drop-entry variables */ + struct delayed_work defense_work; /* Work handler */ + int drop_rate; + int drop_counter; + atomic_t dropentry; + /* locks in ctl.c */ + spinlock_t dropentry_lock; /* drop entry handling */ + spinlock_t droppacket_lock; /* drop packet handling */ + spinlock_t securetcp_lock; /* state and timeout tables */ + rwlock_t rs_lock; /* real services table */ + /* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */ + struct lock_class_key ctl_key; /* ctl_mutex debuging */ + /* Trash for destinations */ + struct list_head dest_trash; + /* Service counters */ + atomic_t ftpsvc_counter; + atomic_t nullsvc_counter; + + /* sys-ctl struct */ + struct ctl_table_header *sysctl_hdr; + struct ctl_table *sysctl_tbl; + /* sysctl variables */ + int sysctl_amemthresh; + int sysctl_am_droprate; + int sysctl_drop_entry; + int sysctl_drop_packet; + int sysctl_secure_tcp; +#ifdef CONFIG_IP_VS_NFCT + int sysctl_conntrack; +#endif + int sysctl_snat_reroute; + int sysctl_sync_ver; + int sysctl_cache_bypass; + int sysctl_expire_nodest_conn; + int sysctl_expire_quiescent_template; + int sysctl_sync_threshold[2]; + int sysctl_nat_icmp_send; + + /* ip_vs_lblc */ + int sysctl_lblc_expiration; + struct ctl_table_header *lblc_ctl_header; + struct ctl_table *lblc_ctl_table; + /* ip_vs_lblcr */ + int sysctl_lblcr_expiration; + struct ctl_table_header *lblcr_ctl_header; + struct ctl_table *lblcr_ctl_table; + /* ip_vs_est */ + struct list_head est_list; /* estimator list */ + spinlock_t est_lock; + struct timer_list est_timer; /* Estimation timer */ + /* ip_vs_sync */ + struct list_head sync_queue; + spinlock_t sync_lock; + struct ip_vs_sync_buff *sync_buff; + spinlock_t sync_buff_lock; + struct sockaddr_in sync_mcast_addr; + struct task_struct *master_thread; + struct task_struct *backup_thread; + int send_mesg_maxlen; + int recv_mesg_maxlen; + volatile int sync_state; + volatile int master_syncid; + volatile int backup_syncid; + /* multicast interface name */ + char master_mcast_ifn[IP_VS_IFNAME_MAXLEN]; + char backup_mcast_ifn[IP_VS_IFNAME_MAXLEN]; + /* net name space ptr */ + struct net *net; /* Needed by timer routines */ +}; + +#endif /* IP_VS_H_ */ diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index d68c3f121774..e2e2ef57eca2 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -43,7 +43,6 @@ struct netns_ipv4 { struct xt_table *nat_table; struct hlist_head *nat_bysource; unsigned int nat_htable_size; - int nat_vmalloced; #endif int sysctl_icmp_echo_ignore_all; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 160a407c1963..16626a04cb03 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -31,10 +31,12 @@ enum qdisc_state_t { * following bits are only changed while qdisc lock is held */ enum qdisc___state_t { - __QDISC___STATE_RUNNING, + __QDISC___STATE_RUNNING = 1, + __QDISC___STATE_THROTTLED = 2, }; struct qdisc_size_table { + struct rcu_head rcu; struct list_head list; struct tc_sizespec szopts; int refcnt; @@ -46,14 +48,13 @@ struct Qdisc { struct sk_buff * (*dequeue)(struct Qdisc *dev); unsigned flags; #define TCQ_F_BUILTIN 1 -#define TCQ_F_THROTTLED 2 -#define TCQ_F_INGRESS 4 -#define TCQ_F_CAN_BYPASS 8 -#define TCQ_F_MQROOT 16 +#define TCQ_F_INGRESS 2 +#define TCQ_F_CAN_BYPASS 4 +#define TCQ_F_MQROOT 8 #define TCQ_F_WARN_NONWC (1 << 16) int padded; struct Qdisc_ops *ops; - struct qdisc_size_table *stab; + struct qdisc_size_table __rcu *stab; struct list_head list; u32 handle; u32 parent; @@ -78,25 +79,43 @@ struct Qdisc { unsigned long state; struct sk_buff_head q; struct gnet_stats_basic_packed bstats; - unsigned long __state; + unsigned int __state; struct gnet_stats_queue qstats; struct rcu_head rcu_head; spinlock_t busylock; }; -static inline bool qdisc_is_running(struct Qdisc *qdisc) +static inline bool qdisc_is_running(const struct Qdisc *qdisc) { - return test_bit(__QDISC___STATE_RUNNING, &qdisc->__state); + return (qdisc->__state & __QDISC___STATE_RUNNING) ? true : false; } static inline bool qdisc_run_begin(struct Qdisc *qdisc) { - return !__test_and_set_bit(__QDISC___STATE_RUNNING, &qdisc->__state); + if (qdisc_is_running(qdisc)) + return false; + qdisc->__state |= __QDISC___STATE_RUNNING; + return true; } static inline void qdisc_run_end(struct Qdisc *qdisc) { - __clear_bit(__QDISC___STATE_RUNNING, &qdisc->__state); + qdisc->__state &= ~__QDISC___STATE_RUNNING; +} + +static inline bool qdisc_is_throttled(const struct Qdisc *qdisc) +{ + return (qdisc->__state & __QDISC___STATE_THROTTLED) ? true : false; +} + +static inline void qdisc_throttled(struct Qdisc *qdisc) +{ + qdisc->__state |= __QDISC___STATE_THROTTLED; +} + +static inline void qdisc_unthrottled(struct Qdisc *qdisc) +{ + qdisc->__state &= ~__QDISC___STATE_THROTTLED; } struct Qdisc_class_ops { @@ -331,8 +350,8 @@ extern struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, struct Qdisc_ops *ops); extern struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, struct Qdisc_ops *ops, u32 parentid); -extern void qdisc_calculate_pkt_len(struct sk_buff *skb, - struct qdisc_size_table *stab); +extern void __qdisc_calculate_pkt_len(struct sk_buff *skb, + const struct qdisc_size_table *stab); extern void tcf_destroy(struct tcf_proto *tp); extern void tcf_destroy_chain(struct tcf_proto **fl); @@ -411,12 +430,20 @@ enum net_xmit_qdisc_t { #define net_xmit_drop_count(e) (1) #endif -static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch) +static inline void qdisc_calculate_pkt_len(struct sk_buff *skb, + const struct Qdisc *sch) { #ifdef CONFIG_NET_SCHED - if (sch->stab) - qdisc_calculate_pkt_len(skb, sch->stab); + struct qdisc_size_table *stab = rcu_dereference_bh(sch->stab); + + if (stab) + __qdisc_calculate_pkt_len(skb, stab); #endif +} + +static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch) +{ + qdisc_calculate_pkt_len(skb, sch); return sch->enqueue(skb, sch); } diff --git a/include/net/sock.h b/include/net/sock.h index d884d268c704..ba6465bf7c7a 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1189,7 +1189,7 @@ extern void sk_filter_release_rcu(struct rcu_head *rcu); static inline void sk_filter_release(struct sk_filter *fp) { if (atomic_dec_and_test(&fp->refcnt)) - call_rcu_bh(&fp->rcu, sk_filter_release_rcu); + call_rcu(&fp->rcu, sk_filter_release_rcu); } static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) |