diff options
Diffstat (limited to 'include/net/ip.h')
| -rw-r--r-- | include/net/ip.h | 362 |
1 files changed, 224 insertions, 138 deletions
diff --git a/include/net/ip.h b/include/net/ip.h index 86e2b182a0c..7596eb22e1c 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -28,6 +28,7 @@ #include <linux/skbuff.h> #include <net/inet_sock.h> +#include <net/route.h> #include <net/snmp.h> #include <net/flow.h> @@ -42,6 +43,8 @@ struct inet_skb_parm { #define IPSKB_XFRM_TRANSFORMED 4 #define IPSKB_FRAG_COMPLETE 8 #define IPSKB_REROUTED 16 + + u16 frag_max_size; }; static inline unsigned int ip_hdrlen(const struct sk_buff *skb) @@ -52,11 +55,15 @@ static inline unsigned int ip_hdrlen(const struct sk_buff *skb) struct ipcm_cookie { __be32 addr; int oif; - struct ip_options *opt; + struct ip_options_rcu *opt; __u8 tx_flags; + __u8 ttl; + __s16 tos; + char priority; }; #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb)) +#define PKTINFO_SKB_CB(skb) ((struct in_pktinfo *)((skb)->cb)) struct ip_ra_chain { struct ip_ra_chain __rcu *next; @@ -84,62 +91,77 @@ struct packet_type; struct rtable; struct sockaddr; -extern int igmp_mc_proc_init(void); +int igmp_mc_init(void); /* * Functions provided by ip.c */ -extern int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, - __be32 saddr, __be32 daddr, - struct ip_options *opt); -extern int ip_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev); -extern int ip_local_deliver(struct sk_buff *skb); -extern int ip_mr_input(struct sk_buff *skb); -extern int ip_output(struct sk_buff *skb); -extern int ip_mc_output(struct sk_buff *skb); -extern int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); -extern int ip_do_nat(struct sk_buff *skb); -extern void ip_send_check(struct iphdr *ip); -extern int __ip_local_out(struct sk_buff *skb); -extern int ip_local_out(struct sk_buff *skb); -extern int ip_queue_xmit(struct sk_buff *skb); -extern void ip_init(void); -extern int ip_append_data(struct sock *sk, - int getfrag(void *from, char *to, int offset, int len, - int odd, struct sk_buff *skb), - void *from, int len, int protolen, - struct ipcm_cookie *ipc, - struct rtable **rt, - unsigned int flags); -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 int ip_push_pending_frames(struct sock *sk); -extern void ip_flush_pending_frames(struct sock *sk); +int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, + __be32 saddr, __be32 daddr, + struct ip_options_rcu *opt); +int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, + struct net_device *orig_dev); +int ip_local_deliver(struct sk_buff *skb); +int ip_mr_input(struct sk_buff *skb); +int ip_output(struct sock *sk, struct sk_buff *skb); +int ip_mc_output(struct sock *sk, struct sk_buff *skb); +int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); +int ip_do_nat(struct sk_buff *skb); +void ip_send_check(struct iphdr *ip); +int __ip_local_out(struct sk_buff *skb); +int ip_local_out_sk(struct sock *sk, struct sk_buff *skb); +static inline int ip_local_out(struct sk_buff *skb) +{ + return ip_local_out_sk(skb->sk, skb); +} -/* datagram.c */ -extern int ip4_datagram_connect(struct sock *sk, - struct sockaddr *uaddr, int addr_len); +int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl); +void ip_init(void); +int ip_append_data(struct sock *sk, struct flowi4 *fl4, + int getfrag(void *from, char *to, int offset, int len, + int odd, struct sk_buff *skb), + void *from, int len, int protolen, + struct ipcm_cookie *ipc, + struct rtable **rt, + unsigned int flags); +int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, + struct sk_buff *skb); +ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, + int offset, size_t size, int flags); +struct sk_buff *__ip_make_skb(struct sock *sk, struct flowi4 *fl4, + struct sk_buff_head *queue, + struct inet_cork *cork); +int ip_send_skb(struct net *net, struct sk_buff *skb); +int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4); +void ip_flush_pending_frames(struct sock *sk); +struct sk_buff *ip_make_skb(struct sock *sk, struct flowi4 *fl4, + 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, struct flowi4 *fl4) +{ + return __ip_make_skb(sk, fl4, &sk->sk_write_queue, &inet_sk(sk)->cork.base); +} -/* - * Map a multicast IP onto multicast MAC for type Token Ring. - * This conforms to RFC1469 Option 2 Multicasting i.e. - * using a functional address to transmit / receive - * multicast packets. - */ +static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet) +{ + return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(inet->tos); +} -static inline void ip_tr_mc_map(__be32 addr, char *buf) +static inline __u8 get_rtconn_flags(struct ipcm_cookie* ipc, struct sock* sk) { - buf[0]=0xC0; - buf[1]=0x00; - buf[2]=0x00; - buf[3]=0x04; - buf[4]=0x00; - buf[5]=0x00; + return (ipc->tos != -1) ? RT_CONN_FLAGS_TOS(sk, ipc->tos) : RT_CONN_FLAGS(sk); } +/* datagram.c */ +int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); + +void ip4_datagram_release_cb(struct sock *sk); + struct ip_reply_arg { struct kvec iov[1]; int flags; @@ -147,6 +169,7 @@ struct ip_reply_arg { int csumoffset; /* u16 offset of csum in iov[0].iov_base */ /* -1 if not needed */ int bound_dev_if; + u8 tos; }; #define IP_REPLY_ARG_NOSRCCHECK 1 @@ -156,15 +179,10 @@ static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg) return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0; } -void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *arg, - unsigned int len); - -struct ipv4_config { - int log_martians; - int no_pmtu_disc; -}; +void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, + __be32 saddr, const struct ip_reply_arg *arg, + unsigned int len); -extern struct ipv4_config ipv4_config; #define IP_INC_STATS(net, field) SNMP_INC_STATS64((net)->mib.ip_statistics, field) #define IP_INC_STATS_BH(net, field) SNMP_INC_STATS64_BH((net)->mib.ip_statistics, field) #define IP_ADD_STATS(net, field, val) SNMP_ADD_STATS64((net)->mib.ip_statistics, field, val) @@ -174,52 +192,60 @@ extern struct ipv4_config ipv4_config; #define NET_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.net_statistics, field) #define NET_INC_STATS_BH(net, field) SNMP_INC_STATS_BH((net)->mib.net_statistics, field) #define NET_INC_STATS_USER(net, field) SNMP_INC_STATS_USER((net)->mib.net_statistics, field) +#define NET_ADD_STATS(net, field, adnd) SNMP_ADD_STATS((net)->mib.net_statistics, field, adnd) #define NET_ADD_STATS_BH(net, field, adnd) SNMP_ADD_STATS_BH((net)->mib.net_statistics, field, adnd) #define NET_ADD_STATS_USER(net, field, adnd) SNMP_ADD_STATS_USER((net)->mib.net_statistics, field, adnd) -extern unsigned long snmp_fold_field(void __percpu *mib[], int offt); +unsigned long snmp_fold_field(void __percpu *mib, int offt); #if BITS_PER_LONG==32 -extern u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t sync_off); +u64 snmp_fold_field64(void __percpu *mib, int offt, size_t sync_off); #else -static inline u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_off) +static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_off) { return snmp_fold_field(mib, offt); } #endif -extern int snmp_mib_init(void __percpu *ptr[2], size_t mibsize, size_t align); -extern void snmp_mib_free(void __percpu *ptr[2]); -extern struct local_ports { - seqlock_t lock; - int range[2]; -} sysctl_local_ports; -extern void inet_get_local_port_range(int *low, int *high); +void inet_get_local_port_range(struct net *net, int *low, int *high); -extern unsigned long *sysctl_local_reserved_ports; -static inline int inet_is_reserved_local_port(int port) +#ifdef CONFIG_SYSCTL +static inline int inet_is_local_reserved_port(struct net *net, int port) { - return test_bit(port, sysctl_local_reserved_ports); + if (!net->ipv4.sysctl_local_reserved_ports) + return 0; + return test_bit(port, net->ipv4.sysctl_local_reserved_ports); } +#else +static inline int inet_is_local_reserved_port(struct net *net, int port) +{ + return 0; +} +#endif -extern int sysctl_ip_default_ttl; extern int sysctl_ip_nonlocal_bind; -extern struct ctl_path net_core_path[]; -extern struct ctl_path net_ipv4_ctl_path[]; - /* From inetpeer.c */ extern int inet_peer_threshold; extern int inet_peer_minttl; extern int inet_peer_maxttl; -extern int inet_peer_gc_mintime; -extern int inet_peer_gc_maxtime; + +/* From ip_input.c */ +extern int sysctl_ip_early_demux; /* From ip_output.c */ extern int sysctl_ip_dynaddr; -extern void ipfrag_init(void); +void ipfrag_init(void); + +void ip_static_sysctl_init(void); -extern void ip_static_sysctl_init(void); +#define IP4_REPLY_MARK(net, mark) \ + ((net)->ipv4.sysctl_fwmark_reflect ? (mark) : 0) + +static inline bool ip_is_fragment(const struct iphdr *iph) +{ + return (iph->frag_off & htons(IP_MF | IP_OFFSET)) != 0; +} #ifdef CONFIG_INET #include <net/dst.h> @@ -243,32 +269,79 @@ int ip_dont_fragment(struct sock *sk, struct dst_entry *dst) !(dst_metric_locked(dst, RTAX_MTU))); } -extern void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more); +static inline bool ip_sk_accept_pmtu(const struct sock *sk) +{ + return inet_sk(sk)->pmtudisc != IP_PMTUDISC_INTERFACE && + inet_sk(sk)->pmtudisc != IP_PMTUDISC_OMIT; +} + +static inline bool ip_sk_use_pmtu(const struct sock *sk) +{ + return inet_sk(sk)->pmtudisc < IP_PMTUDISC_PROBE; +} -static inline void ip_select_ident(struct iphdr *iph, struct dst_entry *dst, struct sock *sk) +static inline bool ip_sk_ignore_df(const struct sock *sk) { - if (iph->frag_off & htons(IP_DF)) { + return inet_sk(sk)->pmtudisc < IP_PMTUDISC_DO || + inet_sk(sk)->pmtudisc == IP_PMTUDISC_OMIT; +} + +static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, + bool forwarding) +{ + struct net *net = dev_net(dst->dev); + + if (net->ipv4.sysctl_ip_fwd_use_pmtu || + dst_metric_locked(dst, RTAX_MTU) || + !forwarding) + return dst_mtu(dst); + + return min(dst->dev->mtu, IP_MAX_MTU); +} + +static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb) +{ + if (!skb->sk || ip_sk_use_pmtu(skb->sk)) { + bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED; + return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding); + } else { + return min(skb_dst(skb)->dev->mtu, IP_MAX_MTU); + } +} + +u32 ip_idents_reserve(u32 hash, int segs); +void __ip_select_ident(struct iphdr *iph, int segs); + +static inline void ip_select_ident_segs(struct sk_buff *skb, struct sock *sk, int segs) +{ + struct iphdr *iph = ip_hdr(skb); + + if ((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) { /* This is only to work around buggy Windows95/2000 * VJ compression implementations. If the ID field * does not change, they drop every other packet in * a TCP stream using header compression. */ - iph->id = (sk && inet_sk(sk)->inet_daddr) ? - htons(inet_sk(sk)->inet_id++) : 0; - } else - __ip_select_ident(iph, dst, 0); -} - -static inline void ip_select_ident_more(struct iphdr *iph, struct dst_entry *dst, struct sock *sk, int more) -{ - if (iph->frag_off & htons(IP_DF)) { if (sk && inet_sk(sk)->inet_daddr) { iph->id = htons(inet_sk(sk)->inet_id); - inet_sk(sk)->inet_id += 1 + more; - } else + inet_sk(sk)->inet_id += segs; + } else { iph->id = 0; - } else - __ip_select_ident(iph, dst, more); + } + } else { + __ip_select_ident(iph, segs); + } +} + +static inline void ip_select_ident(struct sk_buff *skb, struct sock *sk) +{ + ip_select_ident_segs(skb, sk, 1); +} + +static inline __wsum inet_compute_pseudo(struct sk_buff *skb, int proto) +{ + return csum_tcpudp_nofold(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, + skb->len, proto, 0); } /* @@ -324,19 +397,27 @@ static inline void ip_ib_mc_map(__be32 naddr, const unsigned char *broadcast, ch buf[16] = addr & 0x0f; } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +static inline void ip_ipgre_mc_map(__be32 naddr, const unsigned char *broadcast, char *buf) +{ + if ((broadcast[0] | broadcast[1] | broadcast[2] | broadcast[3]) != 0) + memcpy(buf, broadcast, 4); + else + memcpy(buf, &naddr, sizeof(naddr)); +} + +#if IS_ENABLED(CONFIG_IPV6) #include <linux/ipv6.h> #endif static __inline__ void inet_reset_saddr(struct sock *sk) { inet_sk(sk)->inet_rcv_saddr = inet_sk(sk)->inet_saddr = 0; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == PF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); memset(&np->saddr, 0, sizeof(np->saddr)); - memset(&np->rcv_saddr, 0, sizeof(np->rcv_saddr)); + memset(&sk->sk_v6_rcv_saddr, 0, sizeof(sk->sk_v6_rcv_saddr)); } #endif } @@ -350,7 +431,7 @@ static inline int sk_mc_loop(struct sock *sk) switch (sk->sk_family) { case AF_INET: return inet_sk(sk)->mc_loop; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) case AF_INET6: return inet6_sk(sk)->mc_loop; #endif @@ -359,7 +440,7 @@ static inline int sk_mc_loop(struct sock *sk) return 1; } -extern int ip_call_ra_chain(struct sk_buff *skb); +bool ip_call_ra_chain(struct sk_buff *skb); /* * Functions provided by ip_fragment.c @@ -376,10 +457,20 @@ enum ip_defrag_users { __IP_DEFRAG_CONNTRACK_BRIDGE_IN = IP_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX, IP_DEFRAG_VS_IN, IP_DEFRAG_VS_OUT, - IP_DEFRAG_VS_FWD + IP_DEFRAG_VS_FWD, + IP_DEFRAG_AF_PACKET, + IP_DEFRAG_MACVLAN, }; int ip_defrag(struct sk_buff *skb, u32 user); +#ifdef CONFIG_INET +struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user); +#else +static inline struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user) +{ + return skb; +} +#endif int ip_frag_mem(struct net *net); int ip_frag_nqueues(struct net *net); @@ -387,58 +478,53 @@ int ip_frag_nqueues(struct net *net); * Functions provided by ip_forward.c */ -extern int ip_forward(struct sk_buff *skb); +int ip_forward(struct sk_buff *skb); /* * Functions provided by ip_options.c */ -extern void ip_options_build(struct sk_buff *skb, struct ip_options *opt, __be32 daddr, struct rtable *rt, int is_frag); -extern int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb); -extern void ip_options_fragment(struct sk_buff *skb); -extern int ip_options_compile(struct net *net, - struct ip_options *opt, struct sk_buff *skb); -extern int ip_options_get(struct net *net, struct ip_options **optp, - unsigned char *data, int optlen); -extern int ip_options_get_from_user(struct net *net, struct ip_options **optp, - unsigned char __user *data, int optlen); -extern void ip_options_undo(struct ip_options * opt); -extern void ip_forward_options(struct sk_buff *skb); -extern int ip_options_rcv_srr(struct sk_buff *skb); +void ip_options_build(struct sk_buff *skb, struct ip_options *opt, + __be32 daddr, struct rtable *rt, int is_frag); +int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb); +void ip_options_fragment(struct sk_buff *skb); +int ip_options_compile(struct net *net, struct ip_options *opt, + struct sk_buff *skb); +int ip_options_get(struct net *net, struct ip_options_rcu **optp, + unsigned char *data, int optlen); +int ip_options_get_from_user(struct net *net, struct ip_options_rcu **optp, + unsigned char __user *data, int optlen); +void ip_options_undo(struct ip_options *opt); +void ip_forward_options(struct sk_buff *skb); +int ip_options_rcv_srr(struct sk_buff *skb); /* * Functions provided by ip_sockglue.c */ -extern int ip_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); -extern void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb); -extern int ip_cmsg_send(struct net *net, - struct msghdr *msg, struct ipcm_cookie *ipc); -extern int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); -extern int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); -extern int compat_ip_setsockopt(struct sock *sk, int level, - int optname, char __user *optval, unsigned int optlen); -extern int compat_ip_getsockopt(struct sock *sk, int level, - int optname, char __user *optval, int __user *optlen); -extern int ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct sock *)); - -extern int ip_recv_error(struct sock *sk, struct msghdr *msg, int len); -extern void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, - __be16 port, u32 info, u8 *payload); -extern void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport, - u32 info); - -/* sysctl helpers - any sysctl which holds a value that ends up being - * fed into the routing cache should use these handlers. - */ -int ipv4_doint_and_flush(ctl_table *ctl, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos); -int ipv4_doint_and_flush_strategy(ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen); +void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb); +void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb); +int ip_cmsg_send(struct net *net, struct msghdr *msg, + struct ipcm_cookie *ipc, bool allow_ipv6); +int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, + unsigned int optlen); +int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, + int __user *optlen); +int compat_ip_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, unsigned int optlen); +int compat_ip_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen); +int ip_ra_control(struct sock *sk, unsigned char on, + void (*destructor)(struct sock *)); + +int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len); +void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, + u32 info, u8 *payload); +void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport, + u32 info); + #ifdef CONFIG_PROC_FS -extern int ip_misc_proc_init(void); +int ip_misc_proc_init(void); #endif #endif /* _IP_H */ |
