diff options
Diffstat (limited to 'include/net')
39 files changed, 958 insertions, 363 deletions
diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h index a8e7852..e5983c9 100644 --- a/include/net/dcbnl.h +++ b/include/net/dcbnl.h @@ -43,6 +43,8 @@ struct dcbnl_rtnl_ops { int (*ieee_setpfc) (struct net_device *, struct ieee_pfc *); int (*ieee_getapp) (struct net_device *, struct dcb_app *); int (*ieee_setapp) (struct net_device *, struct dcb_app *); + int (*ieee_peer_getets) (struct net_device *, struct ieee_ets *); + int (*ieee_peer_getpfc) (struct net_device *, struct ieee_pfc *); /* CEE std */ u8 (*getstate)(struct net_device *); @@ -77,7 +79,14 @@ struct dcbnl_rtnl_ops { u8 (*getdcbx)(struct net_device *); u8 (*setdcbx)(struct net_device *, u8); + /* peer apps */ + int (*peer_getappinfo)(struct net_device *, struct dcb_peer_app_info *, + u16 *); + int (*peer_getapptable)(struct net_device *, struct dcb_app *); + /* CEE peer */ + int (*cee_peer_getpg) (struct net_device *, struct cee_pg *); + int (*cee_peer_getpfc) (struct net_device *, struct cee_pfc *); }; #endif /* __NET_DCBNL_H__ */ diff --git a/include/net/dst.h b/include/net/dst.h index 93b0310..2a46cba 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -40,24 +40,10 @@ struct dst_entry { struct rcu_head rcu_head; struct dst_entry *child; struct net_device *dev; - short error; - short obsolete; - int flags; -#define DST_HOST 0x0001 -#define DST_NOXFRM 0x0002 -#define DST_NOPOLICY 0x0004 -#define DST_NOHASH 0x0008 -#define DST_NOCACHE 0x0010 + struct dst_ops *ops; + unsigned long _metrics; unsigned long expires; - - unsigned short header_len; /* more space at head required */ - unsigned short trailer_len; /* space to reserve at tail */ - - unsigned int rate_tokens; - unsigned long rate_last; /* rate limiting for ICMP */ - struct dst_entry *path; - struct neighbour *neighbour; struct hh_cache *hh; #ifdef CONFIG_XFRM @@ -68,17 +54,16 @@ struct dst_entry { int (*input)(struct sk_buff*); int (*output)(struct sk_buff*); - struct dst_ops *ops; - - u32 _metrics[RTAX_MAX]; - -#ifdef CONFIG_NET_CLS_ROUTE + short error; + short obsolete; + unsigned short header_len; /* more space at head required */ + unsigned short trailer_len; /* space to reserve at tail */ +#ifdef CONFIG_IP_ROUTE_CLASSID __u32 tclassid; #else __u32 __pad2; #endif - /* * Align __refcnt to a 64 bytes alignment * (L1_CACHE_SIZE would be too much) @@ -93,6 +78,12 @@ struct dst_entry { atomic_t __refcnt; /* client references */ int __use; unsigned long lastuse; + int flags; +#define DST_HOST 0x0001 +#define DST_NOXFRM 0x0002 +#define DST_NOPOLICY 0x0004 +#define DST_NOHASH 0x0008 +#define DST_NOCACHE 0x0010 union { struct dst_entry *next; struct rtable __rcu *rt_next; @@ -103,10 +94,70 @@ struct dst_entry { #ifdef __KERNEL__ +extern u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old); +extern const u32 dst_default_metrics[RTAX_MAX]; + +#define DST_METRICS_READ_ONLY 0x1UL +#define __DST_METRICS_PTR(Y) \ + ((u32 *)((Y) & ~DST_METRICS_READ_ONLY)) +#define DST_METRICS_PTR(X) __DST_METRICS_PTR((X)->_metrics) + +static inline bool dst_metrics_read_only(const struct dst_entry *dst) +{ + return dst->_metrics & DST_METRICS_READ_ONLY; +} + +extern void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old); + +static inline void dst_destroy_metrics_generic(struct dst_entry *dst) +{ + unsigned long val = dst->_metrics; + if (!(val & DST_METRICS_READ_ONLY)) + __dst_destroy_metrics_generic(dst, val); +} + +static inline u32 *dst_metrics_write_ptr(struct dst_entry *dst) +{ + unsigned long p = dst->_metrics; + + if (p & DST_METRICS_READ_ONLY) + return dst->ops->cow_metrics(dst, p); + return __DST_METRICS_PTR(p); +} + +/* This may only be invoked before the entry has reached global + * visibility. + */ +static inline void dst_init_metrics(struct dst_entry *dst, + const u32 *src_metrics, + bool read_only) +{ + dst->_metrics = ((unsigned long) src_metrics) | + (read_only ? DST_METRICS_READ_ONLY : 0); +} + +static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src) +{ + u32 *dst_metrics = dst_metrics_write_ptr(dest); + + if (dst_metrics) { + u32 *src_metrics = DST_METRICS_PTR(src); + + memcpy(dst_metrics, src_metrics, RTAX_MAX * sizeof(u32)); + } +} + +static inline u32 *dst_metrics_ptr(struct dst_entry *dst) +{ + return DST_METRICS_PTR(dst); +} + static inline u32 dst_metric_raw(const struct dst_entry *dst, const int metric) { - return dst->_metrics[metric-1]; + u32 *p = DST_METRICS_PTR(dst); + + return p[metric-1]; } static inline u32 @@ -131,22 +182,10 @@ dst_metric_advmss(const struct dst_entry *dst) static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val) { - dst->_metrics[metric-1] = val; -} + u32 *p = dst_metrics_write_ptr(dst); -static inline void dst_import_metrics(struct dst_entry *dst, const u32 *src_metrics) -{ - memcpy(dst->_metrics, src_metrics, RTAX_MAX * sizeof(u32)); -} - -static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src) -{ - dst_import_metrics(dest, src->_metrics); -} - -static inline u32 *dst_metrics_ptr(struct dst_entry *dst) -{ - return dst->_metrics; + if (p) + p[metric-1] = val; } static inline u32 @@ -181,8 +220,6 @@ static inline u32 dst_allfrag(const struct dst_entry *dst) { int ret = dst_feature(dst, RTAX_FEATURE_ALLFRAG); - /* Yes, _exactly_. This is paranoia. */ - barrier(); return ret; } @@ -315,7 +352,7 @@ static inline struct dst_entry *skb_dst_pop(struct sk_buff *skb) } extern int dst_discard(struct sk_buff *skb); -extern void * dst_alloc(struct dst_ops * ops); +extern void *dst_alloc(struct dst_ops * ops, int initial_ref); extern void __dst_free(struct dst_entry * dst); extern struct dst_entry *dst_destroy(struct dst_entry * dst); @@ -384,27 +421,22 @@ extern void dst_init(void); /* Flags for xfrm_lookup flags argument. */ enum { - XFRM_LOOKUP_WAIT = 1 << 0, - XFRM_LOOKUP_ICMP = 1 << 1, + XFRM_LOOKUP_ICMP = 1 << 0, }; struct flowi; #ifndef CONFIG_XFRM -static inline int xfrm_lookup(struct net *net, struct dst_entry **dst_p, - struct flowi *fl, struct sock *sk, int flags) +static inline struct dst_entry *xfrm_lookup(struct net *net, + struct dst_entry *dst_orig, + const struct flowi *fl, struct sock *sk, + int flags) { - return 0; + return dst_orig; } -static inline int __xfrm_lookup(struct net *net, struct dst_entry **dst_p, - struct flowi *fl, struct sock *sk, int flags) -{ - return 0; -} #else -extern int xfrm_lookup(struct net *net, struct dst_entry **dst_p, - struct flowi *fl, struct sock *sk, int flags); -extern int __xfrm_lookup(struct net *net, struct dst_entry **dst_p, - struct flowi *fl, struct sock *sk, int flags); +extern struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, + const struct flowi *fl, struct sock *sk, + int flags); #endif #endif diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 21a320b..dc07463 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -18,6 +18,7 @@ struct dst_ops { struct dst_entry * (*check)(struct dst_entry *, __u32 cookie); unsigned int (*default_advmss)(const struct dst_entry *); unsigned int (*default_mtu)(const struct dst_entry *); + u32 * (*cow_metrics)(struct dst_entry *, unsigned long); void (*destroy)(struct dst_entry *); void (*ifdown)(struct dst_entry *, struct net_device *dev, int how); diff --git a/include/net/flow.h b/include/net/flow.h index 240b7f3..fd04138 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -48,7 +48,9 @@ struct flowi { __u8 proto; __u8 flags; -#define FLOWI_FLAG_ANYSRC 0x01 +#define FLOWI_FLAG_ANYSRC 0x01 +#define FLOWI_FLAG_PRECOW_METRICS 0x02 +#define FLOWI_FLAG_CAN_SLEEP 0x04 union { struct { __be16 sport; @@ -101,17 +103,18 @@ struct flow_cache_ops { }; typedef struct flow_cache_object *(*flow_resolve_t)( - struct net *net, struct flowi *key, u16 family, + struct net *net, const struct flowi *key, u16 family, u8 dir, struct flow_cache_object *oldobj, void *ctx); extern struct flow_cache_object *flow_cache_lookup( - struct net *net, struct flowi *key, u16 family, + struct net *net, const struct flowi *key, u16 family, u8 dir, flow_resolve_t resolver, void *ctx); extern void flow_cache_flush(void); extern atomic_t flow_cache_genid; -static inline int flow_cache_uli_match(struct flowi *fl1, struct flowi *fl2) +static inline int flow_cache_uli_match(const struct flowi *fl1, + const struct flowi *fl2) { return (fl1->proto == fl2->proto && !memcmp(&fl1->uli_u, &fl2->uli_u, sizeof(fl1->uli_u))); diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 8a64b81..b4c7c1c 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -195,7 +195,8 @@ static inline int genlmsg_end(struct sk_buff *skb, void *hdr) */ static inline void genlmsg_cancel(struct sk_buff *skb, void *hdr) { - nlmsg_cancel(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); + if (hdr) + nlmsg_cancel(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); } /** diff --git a/include/net/icmp.h b/include/net/icmp.h index 6e991e0..f0698b9 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -45,7 +45,4 @@ extern int icmp_ioctl(struct sock *sk, int cmd, unsigned long arg); extern int icmp_init(void); extern void icmp_out_count(struct net *net, unsigned char type); -/* Move into dst.h ? */ -extern int xrlim_allow(struct dst_entry *dst, int timeout); - #endif /* _ICMP_H */ diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 8181498..7a37369 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -86,6 +86,19 @@ static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) return (struct inet_request_sock *)sk; } +struct inet_cork { + unsigned int flags; + unsigned int fragsize; + struct ip_options *opt; + struct dst_entry *dst; + int length; /* Total length of all frames */ + __be32 addr; + struct flowi fl; + struct page *page; + u32 off; + u8 tx_flags; +}; + struct ip_mc_socklist; struct ipv6_pinfo; struct rtable; @@ -143,15 +156,7 @@ struct inet_sock { int mc_index; __be32 mc_addr; struct ip_mc_socklist __rcu *mc_list; - struct { - unsigned int flags; - unsigned int fragsize; - struct ip_options *opt; - struct dst_entry *dst; - int length; /* Total length of all frames */ - __be32 addr; - struct flowi fl; - } cork; + struct inet_cork cork; }; #define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */ @@ -219,7 +224,13 @@ static inline struct request_sock *inet_reqsk_alloc(struct request_sock_ops *ops static inline __u8 inet_sk_flowi_flags(const struct sock *sk) { - return inet_sk(sk)->transparent ? FLOWI_FLAG_ANYSRC : 0; + __u8 flags = 0; + + if (inet_sk(sk)->transparent) + flags |= FLOWI_FLAG_ANYSRC; + if (sk->sk_protocol == IPPROTO_TCP) + flags |= FLOWI_FLAG_PRECOW_METRICS; + return flags; } #endif /* _INET_SOCK_H */ diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 599d96e..e6dd8da6 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -11,15 +11,20 @@ #include <linux/init.h> #include <linux/jiffies.h> #include <linux/spinlock.h> +#include <linux/rtnetlink.h> #include <net/ipv6.h> #include <asm/atomic.h> -struct inetpeer_addr { +struct inetpeer_addr_base { union { - __be32 a4; - __be32 a6[4]; + __be32 a4; + __be32 a6[4]; }; - __u16 family; +}; + +struct inetpeer_addr { + struct inetpeer_addr_base addr; + __u16 family; }; struct inet_peer { @@ -33,15 +38,22 @@ struct inet_peer { atomic_t refcnt; /* * Once inet_peer is queued for deletion (refcnt == -1), following fields - * are not available: rid, ip_id_count, tcp_ts, tcp_ts_stamp - * We can share memory with rcu_head to keep inet_peer small + * are not available: rid, ip_id_count, tcp_ts, tcp_ts_stamp, metrics + * We can share memory with rcu_head to help keep inet_peer small. */ union { struct { - atomic_t rid; /* Frag reception counter */ - atomic_t ip_id_count; /* IP ID for the next packet */ - __u32 tcp_ts; - __u32 tcp_ts_stamp; + atomic_t rid; /* Frag reception counter */ + atomic_t ip_id_count; /* IP ID for the next packet */ + __u32 tcp_ts; + __u32 tcp_ts_stamp; + u32 metrics[RTAX_MAX]; + u32 rate_tokens; /* rate limiting for ICMP */ + unsigned long rate_last; + unsigned long pmtu_expires; + u32 pmtu_orig; + u32 pmtu_learned; + struct inetpeer_addr_base redirect_learned; }; struct rcu_head rcu; }; @@ -49,6 +61,13 @@ struct inet_peer { void inet_initpeers(void) __init; +#define INETPEER_METRICS_NEW (~(u32) 0) + +static inline bool inet_metrics_new(const struct inet_peer *p) +{ + return p->metrics[RTAX_LOCK-1] == INETPEER_METRICS_NEW; +} + /* can be called with or without local BH being disabled */ struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create); @@ -56,7 +75,7 @@ static inline struct inet_peer *inet_getpeer_v4(__be32 v4daddr, int create) { struct inetpeer_addr daddr; - daddr.a4 = v4daddr; + daddr.addr.a4 = v4daddr; daddr.family = AF_INET; return inet_getpeer(&daddr, create); } @@ -65,13 +84,14 @@ static inline struct inet_peer *inet_getpeer_v6(struct in6_addr *v6daddr, int cr { struct inetpeer_addr daddr; - ipv6_addr_copy((struct in6_addr *)daddr.a6, v6daddr); + ipv6_addr_copy((struct in6_addr *)daddr.addr.a6, v6daddr); daddr.family = AF_INET6; return inet_getpeer(&daddr, create); } /* can be called from BH context or outside */ extern void inet_putpeer(struct inet_peer *p); +extern bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout); /* * temporary check to make sure we dont access rid, ip_id_count, tcp_ts, diff --git a/include/net/ip.h b/include/net/ip.h index 67fac78..a4f6311 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -116,8 +116,24 @@ extern int ip_append_data(struct sock *sk, extern int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb); extern ssize_t ip_append_page(struct sock *sk, struct page *page, int offset, size_t size, int flags); +extern struct sk_buff *__ip_make_skb(struct sock *sk, + struct sk_buff_head *queue, + struct inet_cork *cork); +extern int ip_send_skb(struct sk_buff *skb); extern int ip_push_pending_frames(struct sock *sk); extern void ip_flush_pending_frames(struct sock *sk); +extern struct sk_buff *ip_make_skb(struct sock *sk, + int getfrag(void *from, char *to, int offset, int len, + int odd, struct sk_buff *skb), + void *from, int length, int transhdrlen, + struct ipcm_cookie *ipc, + struct rtable **rtp, + unsigned int flags); + +static inline struct sk_buff *ip_finish_skb(struct sock *sk) +{ + return __ip_make_skb(sk, &sk->sk_write_queue, &inet_sk(sk)->cork); +} /* datagram.c */ extern int ip4_datagram_connect(struct sock *sk, diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 708ff7c..46a6e8a 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -108,6 +108,7 @@ struct rt6_info { u32 rt6i_flags; struct rt6key rt6i_src; u32 rt6i_metric; + u32 rt6i_peer_genid; struct inet6_dev *rt6i_idev; struct inet_peer *rt6i_peer; diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 07bdb5e..d948e23 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -51,15 +51,17 @@ struct fib_nh { struct fib_info *nh_parent; unsigned nh_flags; unsigned char nh_scope; + unsigned char nh_cfg_scope; #ifdef CONFIG_IP_ROUTE_MULTIPATH int nh_weight; int nh_power; #endif -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID __u32 nh_tclassid; #endif int nh_oif; __be32 nh_gw; + __be32 nh_saddr; }; /* @@ -77,7 +79,7 @@ struct fib_info { int fib_protocol; __be32 fib_prefsrc; u32 fib_priority; - u32 fib_metrics[RTAX_MAX]; + u32 *fib_metrics; #define fib_mtu fib_metrics[RTAX_MTU-1] #define fib_window fib_metrics[RTAX_WINDOW-1] #define fib_rtt fib_metrics[RTAX_RTT-1] @@ -96,12 +98,15 @@ struct fib_info { struct fib_rule; #endif +struct fib_table; struct fib_result { unsigned char prefixlen; unsigned char nh_sel; unsigned char type; unsigned char scope; struct fib_info *fi; + struct fib_table *table; + struct list_head *fa_head; #ifdef CONFIG_IP_MULTIPLE_TABLES struct fib_rule *r; #endif @@ -136,11 +141,13 @@ struct fib_result_nl { #endif /* CONFIG_IP_ROUTE_MULTIPATH */ -#define FIB_RES_PREFSRC(res) ((res).fi->fib_prefsrc ? : __fib_res_prefsrc(&res)) +#define FIB_RES_SADDR(res) (FIB_RES_NH(res).nh_saddr) #define FIB_RES_GW(res) (FIB_RES_NH(res).nh_gw) #define FIB_RES_DEV(res) (FIB_RES_NH(res).nh_dev) #define FIB_RES_OIF(res) (FIB_RES_NH(res).nh_oif) +#define FIB_RES_PREFSRC(res) ((res).fi->fib_prefsrc ? : FIB_RES_SADDR(res)) + struct fib_table { struct hlist_node tb_hlist; u32 tb_id; @@ -155,9 +162,6 @@ extern int fib_table_delete(struct fib_table *, struct fib_config *); extern int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb); extern int fib_table_flush(struct fib_table *table); -extern void fib_table_select_default(struct fib_table *table, - const struct flowi *flp, - struct fib_result *res); extern void fib_free_table(struct fib_table *tb); @@ -201,8 +205,8 @@ 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 -extern u32 fib_rules_tclass(struct fib_result *res); +#ifdef CONFIG_IP_ROUTE_CLASSID +extern u32 fib_rules_tclass(const struct fib_result *res); #endif extern int fib_lookup(struct net *n, struct flowi *flp, struct fib_result *res); @@ -218,24 +222,23 @@ extern void ip_fib_init(void); extern int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, __be32 *spec_dst, u32 *itag, u32 mark); -extern void fib_select_default(struct net *net, const struct flowi *flp, - struct fib_result *res); +extern void fib_select_default(struct fib_result *res); /* Exported by fib_semantics.c */ extern int ip_fib_check_default(__be32 gw, struct net_device *dev); extern int fib_sync_down_dev(struct net_device *dev, int force); extern int fib_sync_down_addr(struct net *net, __be32 local); +extern void fib_update_nh_saddrs(struct net_device *dev); extern int fib_sync_up(struct net_device *dev); -extern __be32 __fib_res_prefsrc(struct fib_result *res); -extern void fib_select_multipath(const struct flowi *flp, struct fib_result *res); +extern void fib_select_multipath(struct fib_result *res); -/* Exported by fib_{hash|trie}.c */ -extern void fib_hash_init(void); -extern struct fib_table *fib_hash_table(u32 id); +/* Exported by fib_trie.c */ +extern void fib_trie_init(void); +extern struct fib_table *fib_trie_table(u32 id); -static inline void fib_combine_itag(u32 *itag, struct fib_result *res) +static inline void fib_combine_itag(u32 *itag, const 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 b7bbd6c..e74da41e 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; @@ -374,17 +494,20 @@ struct ip_vs_conn_param { * IP_VS structure allocated for each dynamically scheduled connection */ struct ip_vs_conn { - struct list_head c_list; /* hashed list heads */ - + struct hlist_node 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 +1015,23 @@ 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); + +extern void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg); /* * 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 +1040,7 @@ 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 +1048,9 @@ 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 +1058,12 @@ 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 +1071,8 @@ 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); /* @@ -952,14 +1111,14 @@ extern int ip_vs_icmp_xmit_v6 * we are loaded. Just set ip_vs_drop_rate to 'n' and * we start to drop 1/rate of the packets */ -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; } @@ -1084,6 +1243,20 @@ static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp) /* CONFIG_IP_VS_NFCT */ #endif +static inline unsigned int +ip_vs_dest_conn_overhead(struct ip_vs_dest *dest) +{ + /* + * 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: + * dest->activeconns*256 + dest->inactconns + */ + return (atomic_read(&dest->activeconns) << 8) + + atomic_read(&dest->inactconns); +} + #endif /* __KERNEL__ */ #endif /* _NET_IP_VS_H */ diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 4a3cd2c..4635a5c 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -89,6 +89,18 @@ #define IPV6_ADDR_SCOPE_GLOBAL 0x0e /* + * Addr flags + */ +#ifdef __KERNEL__ +#define IPV6_ADDR_MC_FLAG_TRANSIENT(a) \ + ((a)->s6_addr[1] & 0x10) +#define IPV6_ADDR_MC_FLAG_PREFIX(a) \ + ((a)->s6_addr[1] & 0x20) +#define IPV6_ADDR_MC_FLAG_RENDEZVOUS(a) \ + ((a)->s6_addr[1] & 0x40) +#endif + +/* * fragmentation header */ @@ -512,12 +524,16 @@ extern void ip6_flush_pending_frames(struct sock *sk); extern int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl); -extern int ip6_dst_blackhole(struct sock *sk, - struct dst_entry **dst, - struct flowi *fl); -extern int ip6_sk_dst_lookup(struct sock *sk, - struct dst_entry **dst, - struct flowi *fl); +extern struct dst_entry * ip6_dst_lookup_flow(struct sock *sk, + struct flowi *fl, + const struct in6_addr *final_dst, + bool can_sleep); +extern struct dst_entry * ip6_sk_dst_lookup_flow(struct sock *sk, + struct flowi *fl, + const struct in6_addr *final_dst, + bool can_sleep); +extern struct dst_entry * ip6_blackhole_route(struct net *net, + struct dst_entry *orig_dst); /* * skb processing functions diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 1bf812b..b3b4a34 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/netevent.h b/include/net/netevent.h index e82b7ba..22b239c 100644 --- a/include/net/netevent.h +++ b/include/net/netevent.h @@ -21,7 +21,6 @@ struct netevent_redirect { enum netevent_notif_type { NETEVENT_NEIGH_UPDATE = 1, /* arg is struct neighbour ptr */ - NETEVENT_PMTU_UPDATE, /* arg is struct dst_entry ptr */ NETEVENT_REDIRECT, /* arg is struct netevent_redirect ptr */ }; diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index d85cff1..d0d1337 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 96ba5f7..4283508 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); @@ -77,9 +85,6 @@ nf_conntrack_event_cache(enum ip_conntrack_events event, struct nf_conn *ct) if (e == NULL) return; - if (!(e->ctmask & (1 << event))) - return; - set_bit(event, &e->cache); } @@ -159,7 +164,7 @@ 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 0772d29..2dcf317 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 32c305d..f1c1311 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 a754761..e8010f4 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 0000000..fc9c82b --- /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 f5f09f0..aff80b1 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 33602ab..3dc7b98 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/netfilter/nf_tproxy_core.h b/include/net/netfilter/nf_tproxy_core.h index cd85b3b..e505358 100644 --- a/include/net/netfilter/nf_tproxy_core.h +++ b/include/net/netfilter/nf_tproxy_core.h @@ -201,18 +201,8 @@ nf_tproxy_get_sock_v6(struct net *net, const u8 protocol, } #endif -static inline void -nf_tproxy_put_sock(struct sock *sk) -{ - /* TIME_WAIT inet sockets have to be handled differently */ - if ((sk->sk_protocol == IPPROTO_TCP) && (sk->sk_state == TCP_TIME_WAIT)) - inet_twsk_put(inet_twsk(sk)); - else - sock_put(sk); -} - /* assign a socket to the skb -- consumes sk */ -int +void nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk); #endif diff --git a/include/net/netlink.h b/include/net/netlink.h index 373f1a9..8a3906a 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -856,18 +856,27 @@ static inline int nla_put_msecs(struct sk_buff *skb, int attrtype, #define NLA_PUT_BE16(skb, attrtype, value) \ NLA_PUT_TYPE(skb, __be16, attrtype, value) +#define NLA_PUT_NET16(skb, attrtype, value) \ + NLA_PUT_BE16(skb, attrtype | NLA_F_NET_BYTEORDER, value) + #define NLA_PUT_U32(skb, attrtype, value) \ NLA_PUT_TYPE(skb, u32, attrtype, value) #define NLA_PUT_BE32(skb, attrtype, value) \ NLA_PUT_TYPE(skb, __be32, attrtype, value) +#define NLA_PUT_NET32(skb, attrtype, value) \ + NLA_PUT_BE32(skb, attrtype | NLA_F_NET_BYTEORDER, value) + #define NLA_PUT_U64(skb, attrtype, value) \ NLA_PUT_TYPE(skb, u64, attrtype, value) #define NLA_PUT_BE64(skb, attrtype, value) \ NLA_PUT_TYPE(skb, __be64, attrtype, value) +#define NLA_PUT_NET64(skb, attrtype, value) \ + NLA_PUT_BE64(skb, attrtype | NLA_F_NET_BYTEORDER, value) + #define NLA_PUT_STRING(skb, attrtype, value) \ NLA_PUT(skb, attrtype, strlen(value) + 1, value) diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index d4958d4..341eb08 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 0000000..259ebac --- /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 d68c3f1..e2e2ef5 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/phonet/pep.h b/include/net/phonet/pep.h index b60b28c..b669fe6 100644 --- a/include/net/phonet/pep.h +++ b/include/net/phonet/pep.h @@ -28,7 +28,6 @@ struct pep_sock { /* XXX: union-ify listening vs connected stuff ? */ /* Listening socket stuff: */ - struct hlist_head ackq; struct hlist_head hlist; /* Connected socket stuff: */ @@ -45,10 +44,6 @@ struct pep_sock { u8 tx_fc; /* TX flow control */ u8 init_enable; /* auto-enable at creation */ u8 aligned; -#ifdef CONFIG_PHONET_PIPECTRLR - u8 pipe_state; - struct sockaddr_pn remote_pep; -#endif }; static inline struct pep_sock *pep_sk(struct sock *sk) @@ -158,6 +153,7 @@ enum { PN_LEGACY_FLOW_CONTROL, PN_ONE_CREDIT_FLOW_CONTROL, PN_MULTI_CREDIT_FLOW_CONTROL, + PN_MAX_FLOW_CONTROL, }; #define pn_flow_safe(fc) ((fc) >> 1) @@ -169,21 +165,4 @@ enum { PEP_IND_READY, }; -#ifdef CONFIG_PHONET_PIPECTRLR -#define PNS_PEP_CONNECT_UTID 0x02 -#define PNS_PIPE_CREATED_IND_UTID 0x04 -#define PNS_PIPE_ENABLE_UTID 0x0A -#define PNS_PIPE_ENABLED_IND_UTID 0x0C -#define PNS_PIPE_DISABLE_UTID 0x0F -#define PNS_PIPE_DISABLED_IND_UTID 0x11 -#define PNS_PEP_DISCONNECT_UTID 0x06 - -/* Used for tracking state of a pipe */ -enum { - PIPE_IDLE, - PIPE_DISABLED, - PIPE_ENABLED, -}; -#endif /* CONFIG_PHONET_PIPECTRLR */ - #endif diff --git a/include/net/phonet/phonet.h b/include/net/phonet/phonet.h index 5395e09..68e5097 100644 --- a/include/net/phonet/phonet.h +++ b/include/net/phonet/phonet.h @@ -36,6 +36,7 @@ struct pn_sock { struct sock sk; u16 sobject; + u16 dobject; u8 resource; }; diff --git a/include/net/protocol.h b/include/net/protocol.h index dc07495..6f7eb80 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -38,7 +38,7 @@ struct net_protocol { void (*err_handler)(struct sk_buff *skb, u32 info); int (*gso_send_check)(struct sk_buff *skb); struct sk_buff *(*gso_segment)(struct sk_buff *skb, - int features); + u32 features); struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb); @@ -57,7 +57,7 @@ struct inet6_protocol { int (*gso_send_check)(struct sk_buff *skb); struct sk_buff *(*gso_segment)(struct sk_buff *skb, - int features); + u32 features); struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb); diff --git a/include/net/route.h b/include/net/route.h index 93e10c4..9257f5f 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -49,36 +49,43 @@ struct fib_nh; struct inet_peer; +struct fib_info; struct rtable { struct dst_entry dst; - /* Cache lookup keys */ - struct flowi fl; + /* Lookup key. */ + __be32 rt_key_dst; + __be32 rt_key_src; int rt_genid; unsigned rt_flags; __u16 rt_type; + __u8 rt_tos; __be32 rt_dst; /* Path destination */ __be32 rt_src; /* Path source */ int rt_iif; + int rt_oif; + __u32 rt_mark; /* Info on neighbour */ __be32 rt_gateway; /* Miscellaneous cached information */ __be32 rt_spec_dst; /* RFC1122 specific destination */ + u32 rt_peer_genid; struct inet_peer *peer; /* long-living peer info */ + struct fib_info *fi; /* for client ref to shared metrics */ }; static inline bool rt_is_input_route(struct rtable *rt) { - return rt->fl.iif != 0; + return rt->rt_iif != 0; } static inline bool rt_is_output_route(struct rtable *rt) { - return rt->fl.iif == 0; + return rt->rt_iif == 0; } struct ip_rt_acct { @@ -115,9 +122,15 @@ extern void ip_rt_redirect(__be32 old_gw, __be32 dst, __be32 new_gw, __be32 src, struct net_device *dev); extern void rt_cache_flush(struct net *net, int how); extern void rt_cache_flush_batch(struct net *net); -extern int __ip_route_output_key(struct net *, struct rtable **, const struct flowi *flp); -extern int ip_route_output_key(struct net *, struct rtable **, struct flowi *flp); -extern int ip_route_output_flow(struct net *, struct rtable **rp, struct flowi *flp, struct sock *sk, int flags); +extern struct rtable *__ip_route_output_key(struct net *, const struct flowi *flp); +extern struct rtable *ip_route_output_flow(struct net *, struct flowi *flp, + struct sock *sk); +extern struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig); + +static inline struct rtable *ip_route_output_key(struct net *net, struct flowi *flp) +{ + return ip_route_output_flow(net, flp, NULL); +} extern int ip_route_input_common(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin, bool noref); @@ -162,10 +175,10 @@ static inline char rt_tos2priority(u8 tos) return ip_tos2prio[IPTOS_TOS(tos)>>1]; } -static inline int ip_route_connect(struct rtable **rp, __be32 dst, - __be32 src, u32 tos, int oif, u8 protocol, - __be16 sport, __be16 dport, struct sock *sk, - int flags) +static inline struct rtable *ip_route_connect(__be32 dst, __be32 src, u32 tos, + int oif, u8 protocol, + __be16 sport, __be16 dport, + struct sock *sk, bool can_sleep) { struct flowi fl = { .oif = oif, .mark = sk->sk_mark, @@ -175,44 +188,52 @@ static inline int ip_route_connect(struct rtable **rp, __be32 dst, .proto = protocol, .fl_ip_sport = sport, .fl_ip_dport = dport }; - int err; struct net *net = sock_net(sk); + struct rtable *rt; if (inet_sk(sk)->transparent) fl.flags |= FLOWI_FLAG_ANYSRC; + if (protocol == IPPROTO_TCP) + fl.flags |= FLOWI_FLAG_PRECOW_METRICS; + if (can_sleep) + fl.flags |= FLOWI_FLAG_CAN_SLEEP; if (!dst || !src) { - err = __ip_route_output_key(net, rp, &fl); - if (err) - return err; - fl.fl4_dst = (*rp)->rt_dst; - fl.fl4_src = (*rp)->rt_src; - ip_rt_put(*rp); - *rp = NULL; + rt = __ip_route_output_key(net, &fl); + if (IS_ERR(rt)) + return rt; + fl.fl4_dst = rt->rt_dst; + fl.fl4_src = rt->rt_src; + ip_rt_put(rt); } security_sk_classify_flow(sk, &fl); - return ip_route_output_flow(net, rp, &fl, sk, flags); + return ip_route_output_flow(net, &fl, sk); } -static inline int ip_route_newports(struct rtable **rp, u8 protocol, - __be16 sport, __be16 dport, struct sock *sk) +static inline struct rtable *ip_route_newports(struct rtable *rt, + u8 protocol, __be16 orig_sport, + __be16 orig_dport, __be16 sport, + __be16 dport, struct sock *sk) { - if (sport != (*rp)->fl.fl_ip_sport || - dport != (*rp)->fl.fl_ip_dport) { - struct flowi fl; - - memcpy(&fl, &(*rp)->fl, sizeof(fl)); - fl.fl_ip_sport = sport; - fl.fl_ip_dport = dport; - fl.proto = protocol; + if (sport != orig_sport || dport != orig_dport) { + struct flowi fl = { .oif = rt->rt_oif, + .mark = rt->rt_mark, + .fl4_dst = rt->rt_key_dst, + .fl4_src = rt->rt_key_src, + .fl4_tos = rt->rt_tos, + .proto = protocol, + .fl_ip_sport = sport, + .fl_ip_dport = dport }; + if (inet_sk(sk)->transparent) fl.flags |= FLOWI_FLAG_ANYSRC; - ip_rt_put(*rp); - *rp = NULL; + if (protocol == IPPROTO_TCP) + fl.flags |= FLOWI_FLAG_PRECOW_METRICS; + ip_rt_put(rt); security_sk_classify_flow(sk, &fl); - return ip_route_output_flow(sock_net(sk), rp, &fl, sk, 0); + return ip_route_output_flow(sock_net(sk), &fl, sk); } - return 0; + return rt; } extern void rt_bind_peer(struct rtable *rt, int create); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index e9eee99..a9505b6 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 +79,44 @@ 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; + u32 limit; }; -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 { @@ -199,7 +219,7 @@ struct tcf_proto { struct qdisc_skb_cb { unsigned int pkt_len; - char data[]; + long data[]; }; static inline int qdisc_qlen(struct Qdisc *q) @@ -331,8 +351,8 @@ 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 +431,20 @@ 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); } @@ -445,7 +473,6 @@ static inline int __qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch, { __skb_queue_tail(list, skb); sch->qstats.backlog += qdisc_pkt_len(skb); - qdisc_bstats_update(sch, skb); return NET_XMIT_SUCCESS; } @@ -460,8 +487,10 @@ static inline struct sk_buff *__qdisc_dequeue_head(struct Qdisc *sch, { struct sk_buff *skb = __skb_dequeue(list); - if (likely(skb != NULL)) + if (likely(skb != NULL)) { sch->qstats.backlog -= qdisc_pkt_len(skb); + qdisc_bstats_update(sch, skb); + } return skb; } @@ -474,10 +503,11 @@ static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch) static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch, struct sk_buff_head *list) { - struct sk_buff *skb = __qdisc_dequeue_head(sch, list); + struct sk_buff *skb = __skb_dequeue(list); if (likely(skb != NULL)) { unsigned int len = qdisc_pkt_len(skb); + sch->qstats.backlog -= len; kfree_skb(skb); return len; } diff --git a/include/net/sctp/user.h b/include/net/sctp/user.h index 2a128c8..e73ebda 100644 --- a/include/net/sctp/user.h +++ b/include/net/sctp/user.h @@ -78,6 +78,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_GET_PEER_ADDR_INFO 15 #define SCTP_DELAYED_ACK_TIME 16 #define SCTP_DELAYED_ACK SCTP_DELAYED_ACK_TIME +#define SCTP_DELAYED_SACK SCTP_DELAYED_ACK_TIME #define SCTP_CONTEXT 17 #define SCTP_FRAGMENT_INTERLEAVE 18 #define SCTP_PARTIAL_DELIVERY_POINT 19 /* Set/Get partial delivery point */ diff --git a/include/net/sock.h b/include/net/sock.h index d884d26..da0534d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -281,7 +281,7 @@ struct sock { int sk_rcvbuf; struct sk_filter __rcu *sk_filter; - struct socket_wq *sk_wq; + struct socket_wq __rcu *sk_wq; #ifdef CONFIG_NET_DMA struct sk_buff_head sk_async_wait_queue; @@ -753,6 +753,8 @@ struct proto { int level, int optname, char __user *optval, int __user *option); + int (*compat_ioctl)(struct sock *sk, + unsigned int cmd, unsigned long arg); #endif int (*sendmsg)(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len); @@ -1189,7 +1191,7 @@ 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) @@ -1264,7 +1266,8 @@ static inline void sk_set_socket(struct sock *sk, struct socket *sock) static inline wait_queue_head_t *sk_sleep(struct sock *sk) { - return &sk->sk_wq->wait; + BUILD_BUG_ON(offsetof(struct socket_wq, wait) != 0); + return &rcu_dereference_raw(sk->sk_wq)->wait; } /* Detach socket from process context. * Announce socket dead, detach it from wait queue and inode. @@ -1285,7 +1288,7 @@ static inline void sock_orphan(struct sock *sk) static inline void sock_graft(struct sock *sk, struct socket *parent) { write_lock_bh(&sk->sk_callback_lock); - rcu_assign_pointer(sk->sk_wq, parent->wq); + sk->sk_wq = parent->wq; parent->sk = sk; sk_set_socket(sk, parent); security_sock_graft(sk, parent); diff --git a/include/net/tcp.h b/include/net/tcp.h index 38509f0..cda30ea 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -196,6 +196,9 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); /* TCP thin-stream limits */ #define TCP_THIN_LINEAR_RETRIES 6 /* After 6 linear retries, do exp. backoff */ +/* TCP initial congestion window as per draft-hkchu-tcpm-initcwnd-01 */ +#define TCP_INIT_CWND 10 + extern struct inet_timewait_death_row tcp_death_row; /* sysctl variables for tcp */ @@ -799,15 +802,6 @@ static inline __u32 tcp_current_ssthresh(const struct sock *sk) /* Use define here intentionally to get WARN_ON location shown at the caller */ #define tcp_verify_left_out(tp) WARN_ON(tcp_left_out(tp) > tp->packets_out) -/* - * Convert RFC 3390 larger initial window into an equivalent number of packets. - * This is based on the numbers specified in RFC 5681, 3.1. - */ -static inline u32 rfc3390_bytes_to_packets(const u32 smss) -{ - return smss <= 1095 ? 4 : (smss > 2190 ? 2 : 3); -} - extern void tcp_enter_cwr(struct sock *sk, const int set_ssthresh); extern __u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst); @@ -1074,8 +1068,6 @@ static inline int tcp_paws_reject(const struct tcp_options_received *rx_opt, return 1; } -#define TCP_CHECK_TIMER(sk) do { } while (0) - static inline void tcp_mib_init(struct net *net) { /* See RFC 2012 */ @@ -1404,7 +1396,7 @@ extern struct request_sock_ops tcp6_request_sock_ops; extern void tcp_v4_destroy_sock(struct sock *sk); extern int tcp_v4_gso_send_check(struct sk_buff *skb); -extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features); +extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, u32 features); extern struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb); extern struct sk_buff **tcp4_gro_receive(struct sk_buff **head, diff --git a/include/net/udp.h b/include/net/udp.h index bb967dd..67ea6fc 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -144,6 +144,17 @@ static inline __wsum udp_csum_outgoing(struct sock *sk, struct sk_buff *skb) return csum; } +static inline __wsum udp_csum(struct sk_buff *skb) +{ + __wsum csum = csum_partial(skb_transport_header(skb), + sizeof(struct udphdr), skb->csum); + + for (skb = skb_shinfo(skb)->frag_list; skb; skb = skb->next) { + csum = csum_add(csum, skb->csum); + } + return csum; +} + /* hash routines shared between UDPv4/6 and UDP-Litev4/6 */ static inline void udp_lib_hash(struct sock *sk) { @@ -245,5 +256,5 @@ extern void udp4_proc_exit(void); extern void udp_init(void); extern int udp4_ufo_send_check(struct sk_buff *skb); -extern struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, int features); +extern struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, u32 features); #endif /* _UDP_H */ diff --git a/include/net/udplite.h b/include/net/udplite.h index afdffe6..673a024 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -115,6 +115,18 @@ static inline __wsum udplite_csum_outgoing(struct sock *sk, struct sk_buff *skb) return csum; } +static inline __wsum udplite_csum(struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + int cscov = udplite_sender_cscov(udp_sk(sk), udp_hdr(skb)); + const int off = skb_transport_offset(skb); + const int len = skb->len - off; + + skb->ip_summed = CHECKSUM_NONE; /* no HW support for checksumming */ + + return skb_checksum(skb, off, min(cscov, len), 0); +} + extern void udplite4_register(void); extern int udplite_get_port(struct sock *sk, unsigned short snum, int (*scmp)(const struct sock *, const struct sock *)); diff --git a/include/net/xfrm.h b/include/net/xfrm.h index b9f385d..d5dcf39 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -36,6 +36,7 @@ #define XFRM_PROTO_ROUTING IPPROTO_ROUTING #define XFRM_PROTO_DSTOPTS IPPROTO_DSTOPTS +#define XFRM_ALIGN4(len) (((len) + 3) & ~3) #define XFRM_ALIGN8(len) (((len) + 7) & ~7) #define MODULE_ALIAS_XFRM_MODE(family, encap) \ MODULE_ALIAS("xfrm-mode-" __stringify(family) "-" __stringify(encap)) @@ -266,25 +267,26 @@ struct xfrm_policy_afinfo { struct dst_ops *dst_ops; void (*garbage_collect)(struct net *net); struct dst_entry *(*dst_lookup)(struct net *net, int tos, - xfrm_address_t *saddr, - xfrm_address_t *daddr); + const xfrm_address_t *saddr, + const xfrm_address_t *daddr); int (*get_saddr)(struct net *net, xfrm_address_t *saddr, xfrm_address_t *daddr); void (*decode_session)(struct sk_buff *skb, struct flowi *fl, int reverse); - int (*get_tos)(struct flowi *fl); + int (*get_tos)(const struct flowi *fl); int (*init_path)(struct xfrm_dst *path, struct dst_entry *dst, int nfheader_len); int (*fill_dst)(struct xfrm_dst *xdst, struct net_device *dev, - struct flowi *fl); + const struct flowi *fl); + struct dst_entry *(*blackhole_route)(struct net *net, struct dst_entry *orig); }; extern int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo); extern int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo); -extern void km_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c); -extern void km_state_notify(struct xfrm_state *x, struct km_event *c); +extern void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c); +extern void km_state_notify(struct xfrm_state *x, const struct km_event *c); struct xfrm_tmpl; extern int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); @@ -299,9 +301,12 @@ struct xfrm_state_afinfo { const struct xfrm_type *type_map[IPPROTO_MAX]; struct xfrm_mode *mode_map[XFRM_MODE_MAX]; int (*init_flags)(struct xfrm_state *x); - void (*init_tempsel)(struct xfrm_selector *sel, struct flowi *fl); - void (*init_temprop)(struct xfrm_state *x, struct xfrm_tmpl *tmpl, - xfrm_address_t *daddr, xfrm_address_t *saddr); + void (*init_tempsel)(struct xfrm_selector *sel, + const struct flowi *fl); + void (*init_temprop)(struct xfrm_state *x, + const struct xfrm_tmpl *tmpl, + const xfrm_address_t *daddr, + const xfrm_address_t *saddr); int (*tmpl_sort)(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n); int (*state_sort)(struct xfrm_state **dst, struct xfrm_state **src, int n); int (*output)(struct sk_buff *skb); @@ -332,7 +337,8 @@ struct xfrm_type { void (*destructor)(struct xfrm_state *); int (*input)(struct xfrm_state *, struct sk_buff *skb); int (*output)(struct xfrm_state *, struct sk_buff *pskb); - int (*reject)(struct xfrm_state *, struct sk_buff *, struct flowi *); + int (*reject)(struct xfrm_state *, struct sk_buff *, + const struct flowi *); int (*hdr_offset)(struct xfrm_state *, struct sk_buff *, u8 **); /* Estimate maximal size of result of transformation of a dgram */ u32 (*get_mtu)(struct xfrm_state *, int size); @@ -501,7 +507,7 @@ struct xfrm_policy { struct xfrm_tmpl xfrm_vec[XFRM_MAX_DEPTH]; }; -static inline struct net *xp_net(struct xfrm_policy *xp) +static inline struct net *xp_net(const struct xfrm_policy *xp) { return read_pnet(&xp->xp_net); } @@ -545,13 +551,17 @@ struct xfrm_migrate { struct xfrm_mgr { struct list_head list; char *id; - int (*notify)(struct xfrm_state *x, struct km_event *c); + int (*notify)(struct xfrm_state *x, const struct km_event *c); int (*acquire)(struct xfrm_state *x, struct xfrm_tmpl *, struct xfrm_policy *xp, int dir); struct xfrm_policy *(*compile_policy)(struct sock *sk, int opt, u8 *data, int len, int *dir); int (*new_mapping)(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport); - int (*notify_policy)(struct xfrm_policy *x, int dir, struct km_event *c); + int (*notify_policy)(struct xfrm_policy *x, int dir, const struct km_event *c); int (*report)(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr); - int (*migrate)(struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_bundles, struct xfrm_kmaddress *k); + int (*migrate)(const struct xfrm_selector *sel, + u8 dir, u8 type, + const struct xfrm_migrate *m, + int num_bundles, + const struct xfrm_kmaddress *k); }; extern int xfrm_register_km(struct xfrm_mgr *km); @@ -762,10 +772,11 @@ static inline void xfrm_state_hold(struct xfrm_state *x) atomic_inc(&x->refcnt); } -static __inline__ int addr_match(void *token1, void *token2, int prefixlen) +static inline bool addr_match(const void *token1, const void *token2, + int prefixlen) { - __be32 *a1 = token1; - __be32 *a2 = token2; + const __be32 *a1 = token1; + const __be32 *a2 = token2; int pdw; int pbi; @@ -774,7 +785,7 @@ static __inline__ int addr_match(void *token1, void *token2, int prefixlen) if (pdw) if (memcmp(a1, a2, pdw << 2)) - return 0; + return false; if (pbi) { __be32 mask; @@ -782,14 +793,14 @@ static __inline__ int addr_match(void *token1, void *token2, int prefixlen) mask = htonl((0xffffffff) << (32 - pbi)); if ((a1[pdw] ^ a2[pdw]) & mask) - return 0; + return false; } - return 1; + return true; } static __inline__ -__be16 xfrm_flowi_sport(struct flowi *fl) +__be16 xfrm_flowi_sport(const struct flowi *fl) { __be16 port; switch(fl->proto) { @@ -816,7 +827,7 @@ __be16 xfrm_flowi_sport(struct flowi *fl) } static __inline__ -__be16 xfrm_flowi_dport(struct flowi *fl) +__be16 xfrm_flowi_dport(const struct flowi *fl) { __be16 port; switch(fl->proto) { @@ -839,7 +850,8 @@ __be16 xfrm_flowi_dport(struct flowi *fl) return port; } -extern int xfrm_selector_match(struct xfrm_selector *sel, struct flowi *fl, +extern int xfrm_selector_match(const struct xfrm_selector *sel, + const struct flowi *fl, unsigned short family); #ifdef CONFIG_SECURITY_NETWORK_XFRM @@ -947,7 +959,7 @@ secpath_reset(struct sk_buff *skb) } static inline int -xfrm_addr_any(xfrm_address_t *addr, unsigned short family) +xfrm_addr_any(const xfrm_address_t *addr, unsigned short family) { switch (family) { case AF_INET: @@ -959,21 +971,21 @@ xfrm_addr_any(xfrm_address_t *addr, unsigned short family) } static inline int -__xfrm4_state_addr_cmp(struct xfrm_tmpl *tmpl, struct xfrm_state *x) +__xfrm4_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x) { return (tmpl->saddr.a4 && tmpl->saddr.a4 != x->props.saddr.a4); } static inline int -__xfrm6_state_addr_cmp(struct xfrm_tmpl *tmpl, struct xfrm_state *x) +__xfrm6_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x) { return (!ipv6_addr_any((struct in6_addr*)&tmpl->saddr) && ipv6_addr_cmp((struct in6_addr *)&tmpl->saddr, (struct in6_addr*)&x->props.saddr)); } static inline int -xfrm_state_addr_cmp(struct xfrm_tmpl *tmpl, struct xfrm_state *x, unsigned short family) +xfrm_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, unsigned short family) { switch (family) { case AF_INET: @@ -1126,7 +1138,7 @@ static inline int xfrm6_policy_check_reverse(struct sock *sk, int dir, #endif static __inline__ -xfrm_address_t *xfrm_flowi_daddr(struct flowi *fl, unsigned short family) +xfrm_address_t *xfrm_flowi_daddr(const struct flowi *fl, unsigned short family) { switch (family){ case AF_INET: @@ -1138,7 +1150,7 @@ xfrm_address_t *xfrm_flowi_daddr(struct flowi *fl, unsigned short family) } static __inline__ -xfrm_address_t *xfrm_flowi_saddr(struct flowi *fl, unsigned short family) +xfrm_address_t *xfrm_flowi_saddr(const struct flowi *fl, unsigned short family) { switch (family){ case AF_INET: @@ -1150,7 +1162,7 @@ xfrm_address_t *xfrm_flowi_saddr(struct flowi *fl, unsigned short family) } static __inline__ -void xfrm_flowi_addr_get(struct flowi *fl, +void xfrm_flowi_addr_get(const struct flowi *fl, xfrm_address_t *saddr, xfrm_address_t *daddr, unsigned short family) { @@ -1167,8 +1179,8 @@ void xfrm_flowi_addr_get(struct flowi *fl, } static __inline__ int -__xfrm4_state_addr_check(struct xfrm_state *x, - xfrm_address_t *daddr, xfrm_address_t *saddr) +__xfrm4_state_addr_check(const struct xfrm_state *x, + const xfrm_address_t *daddr, const xfrm_address_t *saddr) { if (daddr->a4 == x->id.daddr.a4 && (saddr->a4 == x->props.saddr.a4 || !saddr->a4 || !x->props.saddr.a4)) @@ -1177,8 +1189,8 @@ __xfrm4_state_addr_check(struct xfrm_state *x, } static __inline__ int -__xfrm6_state_addr_check(struct xfrm_state *x, - xfrm_address_t *daddr, xfrm_address_t *saddr) +__xfrm6_state_addr_check(const struct xfrm_state *x, + const xfrm_address_t *daddr, const xfrm_address_t *saddr) { if (!ipv6_addr_cmp((struct in6_addr *)daddr, (struct in6_addr *)&x->id.daddr) && (!ipv6_addr_cmp((struct in6_addr *)saddr, (struct in6_addr *)&x->props.saddr)|| @@ -1189,8 +1201,8 @@ __xfrm6_state_addr_check(struct xfrm_state *x, } static __inline__ int -xfrm_state_addr_check(struct xfrm_state *x, - xfrm_address_t *daddr, xfrm_address_t *saddr, +xfrm_state_addr_check(const struct xfrm_state *x, + const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family) { switch (family) { @@ -1203,23 +1215,23 @@ xfrm_state_addr_check(struct xfrm_state *x, } static __inline__ int -xfrm_state_addr_flow_check(struct xfrm_state *x, struct flowi *fl, +xfrm_state_addr_flow_check(const struct xfrm_state *x, const struct flowi *fl, unsigned short family) { switch (family) { case AF_INET: return __xfrm4_state_addr_check(x, - (xfrm_address_t *)&fl->fl4_dst, - (xfrm_address_t *)&fl->fl4_src); + (const xfrm_address_t *)&fl->fl4_dst, + (const xfrm_address_t *)&fl->fl4_src); case AF_INET6: return __xfrm6_state_addr_check(x, - (xfrm_address_t *)&fl->fl6_dst, - (xfrm_address_t *)&fl->fl6_src); + (const xfrm_address_t *)&fl->fl6_dst, + (const xfrm_address_t *)&fl->fl6_src); } return 0; } -static inline int xfrm_state_kern(struct xfrm_state *x) +static inline int xfrm_state_kern(const struct xfrm_state *x) { return atomic_read(&x->tunnel_users); } @@ -1323,8 +1335,10 @@ extern int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, int (*func)(struct xfrm_state *, int, void*), void *); extern void xfrm_state_walk_done(struct xfrm_state_walk *walk); extern struct xfrm_state *xfrm_state_alloc(struct net *net); -extern struct xfrm_state *xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, - struct flowi *fl, struct xfrm_tmpl *tmpl, +extern struct xfrm_state *xfrm_state_find(const xfrm_address_t *daddr, + const xfrm_address_t *saddr, + const struct flowi *fl, + struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, unsigned short family); extern struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark, @@ -1337,11 +1351,11 @@ extern void xfrm_state_insert(struct xfrm_state *x); extern int xfrm_state_add(struct xfrm_state *x); extern int xfrm_state_update(struct xfrm_state *x); extern struct xfrm_state *xfrm_state_lookup(struct net *net, u32 mark, - xfrm_address_t *daddr, __be32 spi, + const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family); extern struct xfrm_state *xfrm_state_lookup_byaddr(struct net *net, u32 mark, - xfrm_address_t *daddr, - xfrm_address_t *saddr, + const xfrm_address_t *daddr, + const xfrm_address_t *saddr, u8 proto, unsigned short family); #ifdef CONFIG_XFRM_SUB_POLICY @@ -1468,19 +1482,19 @@ u32 xfrm_get_acqseq(void); extern int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi); struct xfrm_state *xfrm_find_acq(struct net *net, struct xfrm_mark *mark, u8 mode, u32 reqid, u8 proto, - xfrm_address_t *daddr, - xfrm_address_t *saddr, int create, + const xfrm_address_t *daddr, + const xfrm_address_t *saddr, int create, unsigned short family); extern int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol); #ifdef CONFIG_XFRM_MIGRATE -extern int km_migrate(struct xfrm_selector *sel, u8 dir, u8 type, - struct xfrm_migrate *m, int num_bundles, - struct xfrm_kmaddress *k); +extern int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, + const struct xfrm_migrate *m, int num_bundles, + const struct xfrm_kmaddress *k); extern struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m); extern struct xfrm_state * xfrm_state_migrate(struct xfrm_state *x, struct xfrm_migrate *m); -extern int xfrm_migrate(struct xfrm_selector *sel, u8 dir, u8 type, +extern int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_bundles, struct xfrm_kmaddress *k); #endif @@ -1500,10 +1514,10 @@ extern struct xfrm_algo_desc *xfrm_ealg_get_byidx(unsigned int idx); extern struct xfrm_algo_desc *xfrm_aalg_get_byid(int alg_id); extern struct xfrm_algo_desc *xfrm_ealg_get_byid(int alg_id); extern struct xfrm_algo_desc *xfrm_calg_get_byid(int alg_id); -extern struct xfrm_algo_desc *xfrm_aalg_get_byname(char *name, int probe); -extern struct xfrm_algo_desc *xfrm_ealg_get_byname(char *name, int probe); -extern struct xfrm_algo_desc *xfrm_calg_get_byname(char *name, int probe); -extern struct xfrm_algo_desc *xfrm_aead_get_byname(char *name, int icv_len, +extern struct xfrm_algo_desc *xfrm_aalg_get_byname(const char *name, int probe); +extern struct xfrm_algo_desc *xfrm_ealg_get_byname(const char *name, int probe); +extern struct xfrm_algo_desc *xfrm_calg_get_byname(const char *name, int probe); +extern struct xfrm_algo_desc *xfrm_aead_get_byname(const char *name, int icv_len, int probe); struct hash_desc; @@ -1511,7 +1525,8 @@ struct scatterlist; typedef int (icv_update_fn_t)(struct hash_desc *, struct scatterlist *, unsigned int); -static inline int xfrm_addr_cmp(xfrm_address_t *a, xfrm_address_t *b, +static inline int xfrm_addr_cmp(const xfrm_address_t *a, + const xfrm_address_t *b, int family) { switch (family) { @@ -1544,12 +1559,12 @@ static inline int xfrm_aevent_is_on(struct net *net) } #endif -static inline int xfrm_alg_len(struct xfrm_algo *alg) +static inline int xfrm_alg_len(const struct xfrm_algo *alg) { return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); } -static inline int xfrm_alg_auth_len(struct xfrm_algo_auth *alg) +static inline int xfrm_alg_auth_len(const struct xfrm_algo_auth *alg) { return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); } @@ -1597,7 +1612,7 @@ static inline int xfrm_mark_get(struct nlattr **attrs, struct xfrm_mark *m) return m->v & m->m; } -static inline int xfrm_mark_put(struct sk_buff *skb, struct xfrm_mark *m) +static inline int xfrm_mark_put(struct sk_buff *skb, const struct xfrm_mark *m) { if (m->m | m->v) NLA_PUT(skb, XFRMA_MARK, sizeof(struct xfrm_mark), m); |