diff options
Diffstat (limited to 'include/net/ip_vs.h')
| -rw-r--r-- | include/net/ip_vs.h | 223 |
1 files changed, 84 insertions, 139 deletions
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 624a8a54806..615b20b5854 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1,6 +1,5 @@ -/* - * IP Virtual Server - * data structure and functionality definitions +/* IP Virtual Server + * data structure and functionality definitions */ #ifndef _NET_IP_VS_H @@ -12,7 +11,7 @@ #include <linux/list.h> /* for struct list_head */ #include <linux/spinlock.h> /* for struct rwlock_t */ -#include <linux/atomic.h> /* for struct atomic_t */ +#include <linux/atomic.h> /* for struct atomic_t */ #include <linux/compiler.h> #include <linux/timer.h> #include <linux/bug.h> @@ -30,15 +29,13 @@ #endif #include <net/net_namespace.h> /* Netw namespace */ -/* - * Generic access of ipvs struct - */ +/* 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 + +/* 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) @@ -90,8 +87,8 @@ static inline struct net *skb_sknet(const struct sk_buff *skb) return &init_net; #endif } -/* - * This one needed for single_open_net since net is stored directly in + +/* This one needed for single_open_net since net is stored directly in * private not as a struct i.e. seq_file_net can't be used. */ static inline struct net *seq_file_single_net(struct seq_file *seq) @@ -108,7 +105,7 @@ extern int ip_vs_conn_tab_size; struct ip_vs_iphdr { __u32 len; /* IPv4 simply where L4 starts - IPv6 where L4 Transport Header starts */ + * IPv6 where L4 Transport Header starts */ __u16 fragoffs; /* IPv6 fragment offset, 0 if first frag (or not frag)*/ __s16 protocol; __s32 flags; @@ -304,16 +301,11 @@ static inline const char *ip_vs_dbg_addr(int af, char *buf, size_t buf_len, #define LeaveFunction(level) do {} while (0) #endif - -/* - * The port number of FTP service (in network order). - */ +/* The port number of FTP service (in network order). */ #define FTPPORT cpu_to_be16(21) #define FTPDATA cpu_to_be16(20) -/* - * TCP State Values - */ +/* TCP State Values */ enum { IP_VS_TCP_S_NONE = 0, IP_VS_TCP_S_ESTABLISHED, @@ -329,25 +321,19 @@ enum { IP_VS_TCP_S_LAST }; -/* - * UDP State Values - */ +/* UDP State Values */ enum { IP_VS_UDP_S_NORMAL, IP_VS_UDP_S_LAST, }; -/* - * ICMP State Values - */ +/* ICMP State Values */ enum { IP_VS_ICMP_S_NORMAL, IP_VS_ICMP_S_LAST, }; -/* - * SCTP State Values - */ +/* SCTP State Values */ enum ip_vs_sctp_states { IP_VS_SCTP_S_NONE, IP_VS_SCTP_S_INIT1, @@ -366,21 +352,18 @@ enum ip_vs_sctp_states { IP_VS_SCTP_S_LAST }; -/* - * Delta sequence info structure - * Each ip_vs_conn has 2 (output AND input seq. changes). - * Only used in the VS/NAT. +/* Delta sequence info structure + * Each ip_vs_conn has 2 (output AND input seq. changes). + * Only used in the VS/NAT. */ struct ip_vs_seq { __u32 init_seq; /* Add delta from this seq */ __u32 delta; /* Delta in sequence numbers */ __u32 previous_delta; /* Delta in sequence numbers - before last resized pkt */ + * before last resized pkt */ }; -/* - * counters per cpu - */ +/* counters per cpu */ struct ip_vs_counters { __u32 conns; /* connections scheduled */ __u32 inpkts; /* incoming packets */ @@ -388,17 +371,13 @@ struct ip_vs_counters { __u64 inbytes; /* incoming bytes */ __u64 outbytes; /* outgoing bytes */ }; -/* - * Stats per cpu - */ +/* Stats per cpu */ struct ip_vs_cpu_stats { struct ip_vs_counters ustats; struct u64_stats_sync syncp; }; -/* - * IPVS statistics objects - */ +/* IPVS statistics objects */ struct ip_vs_estimator { struct list_head list; @@ -491,9 +470,7 @@ struct ip_vs_protocol { void (*timeout_change)(struct ip_vs_proto_data *pd, int flags); }; -/* - * protocol data per netns - */ +/* protocol data per netns */ struct ip_vs_proto_data { struct ip_vs_proto_data *next; struct ip_vs_protocol *pp; @@ -520,9 +497,7 @@ struct ip_vs_conn_param { __u8 pe_data_len; }; -/* - * IP_VS structure allocated for each dynamically scheduled connection - */ +/* IP_VS structure allocated for each dynamically scheduled connection */ struct ip_vs_conn { struct hlist_node c_list; /* hashed list heads */ /* Protocol, addresses and port numbers */ @@ -535,6 +510,7 @@ struct ip_vs_conn { union nf_inet_addr daddr; /* destination address */ volatile __u32 flags; /* status flags */ __u16 protocol; /* Which protocol (TCP/UDP) */ + __u16 daf; /* Address family of the dest */ #ifdef CONFIG_NET_NS struct net *net; /* Name space */ #endif @@ -560,17 +536,18 @@ struct ip_vs_conn { struct ip_vs_dest *dest; /* real server */ atomic_t in_pkts; /* incoming packet counter */ - /* packet transmitter for different forwarding methods. If it - mangles the packet, it must return NF_DROP or better NF_STOLEN, - otherwise this must be changed to a sk_buff **. - NF_ACCEPT can be returned when destination is local. + /* Packet transmitter for different forwarding methods. If it + * mangles the packet, it must return NF_DROP or better NF_STOLEN, + * otherwise this must be changed to a sk_buff **. + * NF_ACCEPT can be returned when destination is local. */ int (*packet_xmit)(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph); /* Note: we can group the following members into a structure, - in order to save more space, and the following members are - only used in VS/NAT anyway */ + * in order to save more space, and the following members are + * only used in VS/NAT anyway + */ struct ip_vs_app *app; /* bound ip_vs_app object */ void *app_data; /* Application private data */ struct ip_vs_seq in_seq; /* incoming seq. struct */ @@ -583,9 +560,7 @@ struct ip_vs_conn { struct rcu_head rcu_head; }; -/* - * To save some memory in conn table when name space is disabled. - */ +/* 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 @@ -594,6 +569,7 @@ static inline struct net *ip_vs_conn_net(const struct ip_vs_conn *cp) return &init_net; #endif } + static inline void ip_vs_conn_net_set(struct ip_vs_conn *cp, struct net *net) { #ifdef CONFIG_NET_NS @@ -611,13 +587,12 @@ static inline int ip_vs_conn_net_eq(const struct ip_vs_conn *cp, #endif } -/* - * Extended internal versions of struct ip_vs_service_user and - * ip_vs_dest_user for IPv6 support. +/* Extended internal versions of struct ip_vs_service_user and ip_vs_dest_user + * for IPv6 support. * - * We need these to conveniently pass around service and destination - * options, but unfortunately, we also need to keep the old definitions to - * maintain userspace backwards compatibility for the setsockopt interface. + * We need these to conveniently pass around service and destination + * options, but unfortunately, we also need to keep the old definitions to + * maintain userspace backwards compatibility for the setsockopt interface. */ struct ip_vs_service_user_kern { /* virtual service addresses */ @@ -648,12 +623,15 @@ struct ip_vs_dest_user_kern { /* thresholds for active connections */ u32 u_threshold; /* upper threshold */ u32 l_threshold; /* lower threshold */ + + /* Address family of addr */ + u16 af; }; /* - * The information about the virtual service offered to the net - * and the forwarding entries + * The information about the virtual service offered to the net and the + * forwarding entries. */ struct ip_vs_service { struct hlist_node s_list; /* for normal service table */ @@ -693,9 +671,8 @@ struct ip_vs_dest_dst { struct rcu_head rcu_head; }; -/* - * The real server destination forwarding entry - * with ip address, port number, and so on. +/* The real server destination forwarding entry with ip address, port number, + * and so on. */ struct ip_vs_dest { struct list_head n_list; /* for the dests in the service */ @@ -734,10 +711,7 @@ struct ip_vs_dest { unsigned int in_rs_table:1; /* we are in rs_table */ }; - -/* - * The scheduler object - */ +/* The scheduler object */ struct ip_vs_scheduler { struct list_head n_list; /* d-linked list head */ char *name; /* scheduler name */ @@ -777,9 +751,7 @@ struct ip_vs_pe { int (*show_pe_data)(const struct ip_vs_conn *cp, char *buf); }; -/* - * The application module object (a.k.a. app incarnation) - */ +/* The application module object (a.k.a. app incarnation) */ struct ip_vs_app { struct list_head a_list; /* member in app list */ int type; /* IP_VS_APP_TYPE_xxx */ @@ -795,16 +767,14 @@ struct ip_vs_app { atomic_t usecnt; /* usage counter */ struct rcu_head rcu_head; - /* - * output hook: Process packet in inout direction, diff set for TCP. + /* output hook: Process packet in inout direction, diff set for TCP. * Return: 0=Error, 1=Payload Not Mangled/Mangled but checksum is ok, * 2=Mangled but checksum was not updated */ int (*pkt_out)(struct ip_vs_app *, struct ip_vs_conn *, struct sk_buff *, int *diff); - /* - * input hook: Process packet in outin direction, diff set for TCP. + /* input hook: Process packet in outin direction, diff set for TCP. * Return: 0=Error, 1=Payload Not Mangled/Mangled but checksum is ok, * 2=Mangled but checksum was not updated */ @@ -863,9 +833,7 @@ struct ipvs_master_sync_state { struct netns_ipvs { int gen; /* Generation */ int enable; /* enable like nf_hooks do */ - /* - * Hash table: for real service lookups - */ + /* 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) @@ -899,7 +867,7 @@ struct netns_ipvs { struct list_head sctp_apps[SCTP_APP_TAB_SIZE]; #endif /* ip_vs_conn */ - atomic_t conn_count; /* connection counter */ + atomic_t conn_count; /* connection counter */ /* ip_vs_ctl */ struct ip_vs_stats tot_stats; /* Statistics & est. */ @@ -986,6 +954,10 @@ struct netns_ipvs { char backup_mcast_ifn[IP_VS_IFNAME_MAXLEN]; /* net name space ptr */ struct net *net; /* Needed by timer routines */ + /* Number of heterogeneous destinations, needed becaus heterogeneous + * are not supported when synchronization is enabled. + */ + unsigned int mixed_address_family_dests; }; #define DEFAULT_SYNC_THRESHOLD 3 @@ -1139,9 +1111,8 @@ static inline int sysctl_backup_only(struct netns_ipvs *ipvs) #endif -/* - * IPVS core functions - * (from ip_vs_core.c) +/* IPVS core functions + * (from ip_vs_core.c) */ const char *ip_vs_proto_name(unsigned int proto); void ip_vs_init_hash_table(struct list_head *table, int rows); @@ -1149,11 +1120,9 @@ void ip_vs_init_hash_table(struct list_head *table, int rows); #define IP_VS_APP_TYPE_FTP 1 -/* - * ip_vs_conn handling functions - * (from ip_vs_conn.c) +/* ip_vs_conn handling functions + * (from ip_vs_conn.c) */ - enum { IP_VS_DIR_INPUT = 0, IP_VS_DIR_OUTPUT, @@ -1210,7 +1179,7 @@ static inline void __ip_vs_conn_put(struct ip_vs_conn *cp) void ip_vs_conn_put(struct ip_vs_conn *cp); 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, +struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af, const union nf_inet_addr *daddr, __be16 dport, unsigned int flags, struct ip_vs_dest *dest, __u32 fwmark); @@ -1284,9 +1253,7 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp) atomic_inc(&ctl_cp->n_control); } -/* - * IPVS netns init & cleanup functions - */ +/* IPVS netns init & cleanup functions */ int ip_vs_estimator_net_init(struct net *net); int ip_vs_control_net_init(struct net *net); int ip_vs_protocol_net_init(struct net *net); @@ -1301,9 +1268,8 @@ void ip_vs_estimator_net_cleanup(struct net *net); void ip_vs_sync_net_cleanup(struct net *net); void ip_vs_service_net_cleanup(struct net *net); -/* - * IPVS application functions - * (from ip_vs_app.c) +/* IPVS application functions + * (from ip_vs_app.c) */ #define IP_VS_APP_MAX_PORTS 8 struct ip_vs_app *register_ip_vs_app(struct net *net, struct ip_vs_app *app); @@ -1323,9 +1289,7 @@ int unregister_ip_vs_pe(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); -/* - * Use a #define to avoid all of module.h just for these trivial ops - */ +/* Use a #define to avoid all of module.h just for these trivial ops */ #define ip_vs_pe_get(pe) \ if (pe && pe->module) \ __module_get(pe->module); @@ -1334,9 +1298,7 @@ struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name); if (pe && pe->module) \ module_put(pe->module); -/* - * IPVS protocol functions (from ip_vs_proto.c) - */ +/* IPVS protocol functions (from ip_vs_proto.c) */ int ip_vs_protocol_init(void); void ip_vs_protocol_cleanup(void); void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags); @@ -1354,9 +1316,8 @@ extern struct ip_vs_protocol ip_vs_protocol_esp; extern struct ip_vs_protocol ip_vs_protocol_ah; extern struct ip_vs_protocol ip_vs_protocol_sctp; -/* - * Registering/unregistering scheduler functions - * (from ip_vs_sched.c) +/* Registering/unregistering scheduler functions + * (from ip_vs_sched.c) */ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler); int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler); @@ -1375,10 +1336,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg); - -/* - * IPVS control data and functions (from ip_vs_ctl.c) - */ +/* IPVS control data and functions (from ip_vs_ctl.c) */ extern struct ip_vs_stats ip_vs_stats; extern int sysctl_ip_vs_sync_ver; @@ -1396,8 +1354,9 @@ void ip_vs_unregister_nl_ioctl(void); int ip_vs_control_init(void); void ip_vs_control_cleanup(void); struct ip_vs_dest * -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, +ip_vs_find_dest(struct net *net, int svc_af, int dest_af, + const union nf_inet_addr *daddr, __be16 dport, + const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol, __u32 fwmark, __u32 flags); void ip_vs_try_bind_dest(struct ip_vs_conn *cp); @@ -1418,26 +1377,21 @@ static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest) kfree(dest); } -/* - * IPVS sync daemon data and function prototypes - * (from ip_vs_sync.c) +/* IPVS sync daemon data and function prototypes + * (from ip_vs_sync.c) */ int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid); int stop_sync_thread(struct net *net, int state); void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts); -/* - * IPVS rate estimator prototypes (from ip_vs_est.c) - */ +/* IPVS rate estimator prototypes (from ip_vs_est.c) */ void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats); void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats); void ip_vs_zero_estimator(struct ip_vs_stats *stats); void ip_vs_read_estimator(struct ip_vs_stats_user *dst, struct ip_vs_stats *stats); -/* - * Various IPVS packet transmitters (from ip_vs_xmit.c) - */ +/* Various IPVS packet transmitters (from ip_vs_xmit.c) */ int ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph); int ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, @@ -1468,12 +1422,10 @@ int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, #endif #ifdef CONFIG_SYSCTL -/* - * This is a simple mechanism to ignore packets when - * we are loaded. Just set ip_vs_drop_rate to 'n' and - * we start to drop 1/rate of the packets +/* This is a simple mechanism to ignore packets when + * we are loaded. Just set ip_vs_drop_rate to 'n' and + * we start to drop 1/rate of the packets */ - static inline int ip_vs_todrop(struct netns_ipvs *ipvs) { if (!ipvs->drop_rate) @@ -1487,9 +1439,7 @@ static inline int ip_vs_todrop(struct netns_ipvs *ipvs) static inline int ip_vs_todrop(struct netns_ipvs *ipvs) { return 0; } #endif -/* - * ip_vs_fwd_tag returns the forwarding tag of the connection - */ +/* ip_vs_fwd_tag returns the forwarding tag of the connection */ #define IP_VS_FWD_METHOD(cp) (cp->flags & IP_VS_CONN_F_FWD_MASK) static inline char ip_vs_fwd_tag(struct ip_vs_conn *cp) @@ -1548,9 +1498,7 @@ static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum) return csum_partial(diff, sizeof(diff), oldsum); } -/* - * Forget current conntrack (unconfirmed) and attach notrack entry - */ +/* Forget current conntrack (unconfirmed) and attach notrack entry */ static inline void ip_vs_notrack(struct sk_buff *skb) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) @@ -1567,9 +1515,8 @@ static inline void ip_vs_notrack(struct sk_buff *skb) } #ifdef CONFIG_IP_VS_NFCT -/* - * Netfilter connection tracking - * (from ip_vs_nfct.c) +/* Netfilter connection tracking + * (from ip_vs_nfct.c) */ static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs) { @@ -1608,14 +1555,12 @@ static inline int ip_vs_confirm_conntrack(struct sk_buff *skb) static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp) { } -/* CONFIG_IP_VS_NFCT */ -#endif +#endif /* CONFIG_IP_VS_NFCT */ static inline int ip_vs_dest_conn_overhead(struct ip_vs_dest *dest) { - /* - * We think the overhead of processing active connections is 256 + /* We think the overhead of processing active connections is 256 * times higher than that of inactive connections in average. (This * 256 times might not be accurate, we will change it later) We * use the following formula to estimate the overhead now: |