kernel-ark/include/linux/ipv6.h

334 lines
7.5 KiB
C
Raw Normal View History

#ifndef _IPV6_H
#define _IPV6_H
#include <uapi/linux/ipv6.h>
#define ipv6_optlen(p) (((p)->hdrlen+1) << 3)
#define ipv6_authlen(p) (((p)->hdrlen+2) << 2)
/*
* This structure contains configuration options per IPv6 link.
*/
struct ipv6_devconf {
__s32 forwarding;
__s32 hop_limit;
__s32 mtu6;
__s32 accept_ra;
__s32 accept_redirects;
__s32 autoconf;
__s32 dad_transmits;
__s32 rtr_solicits;
__s32 rtr_solicit_interval;
__s32 rtr_solicit_delay;
__s32 force_mld_version;
__s32 mldv1_unsolicited_report_interval;
__s32 mldv2_unsolicited_report_interval;
__s32 use_tempaddr;
__s32 temp_valid_lft;
__s32 temp_prefered_lft;
__s32 regen_max_retry;
__s32 max_desync_factor;
__s32 max_addresses;
__s32 accept_ra_defrtr;
__s32 accept_ra_pinfo;
#ifdef CONFIG_IPV6_ROUTER_PREF
__s32 accept_ra_rtr_pref;
__s32 rtr_probe_interval;
#ifdef CONFIG_IPV6_ROUTE_INFO
__s32 accept_ra_rt_info_max_plen;
#endif
#endif
__s32 proxy_ndp;
__s32 accept_source_route;
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
__s32 optimistic_dad;
#endif
#ifdef CONFIG_IPV6_MROUTE
__s32 mc_forwarding;
#endif
__s32 disable_ipv6;
__s32 accept_dad;
__s32 force_tllao;
__s32 ndisc_notify;
__s32 suppress_frag_ndisc;
void *sysctl;
};
struct ipv6_params {
__s32 disable_ipv6;
__s32 autoconf;
};
extern struct ipv6_params ipv6_defaults;
#include <linux/icmpv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <net/inet_sock.h>
static inline struct ipv6hdr *ipv6_hdr(const struct sk_buff *skb)
{
return (struct ipv6hdr *)skb_network_header(skb);
}
static inline struct ipv6hdr *inner_ipv6_hdr(const struct sk_buff *skb)
{
return (struct ipv6hdr *)skb_inner_network_header(skb);
}
static inline struct ipv6hdr *ipipv6_hdr(const struct sk_buff *skb)
{
return (struct ipv6hdr *)skb_transport_header(skb);
}
/*
This structure contains results of exthdrs parsing
as offsets from skb->nh.
*/
struct inet6_skb_parm {
int iif;
__be16 ra;
__u16 hop;
__u16 dst0;
__u16 srcrt;
__u16 dst1;
__u16 lastopt;
__u16 nhoff;
__u16 flags;
#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
__u16 dsthao;
#endif
netfilter: nf_conntrack_ipv6: improve fragmentation handling The IPv6 conntrack fragmentation currently has a couple of shortcomings. Fragmentes are collected in PREROUTING/OUTPUT, are defragmented, the defragmented packet is then passed to conntrack, the resulting conntrack information is attached to each original fragment and the fragments then continue their way through the stack. Helper invocation occurs in the POSTROUTING hook, at which point only the original fragments are available. The result of this is that fragmented packets are never passed to helpers. This patch improves the situation in the following way: - If a reassembled packet belongs to a connection that has a helper assigned, the reassembled packet is passed through the stack instead of the original fragments. - During defragmentation, the largest received fragment size is stored. On output, the packet is refragmented if required. If the largest received fragment size exceeds the outgoing MTU, a "packet too big" message is generated, thus behaving as if the original fragments were passed through the stack from an outside point of view. - The ipv6_helper() hook function can't receive fragments anymore for connections using a helper, so it is switched to use ipv6_skip_exthdr() instead of the netfilter specific nf_ct_ipv6_skip_exthdr() and the reassembled packets are passed to connection tracking helpers. The result of this is that we can properly track fragmented packets, but still generate ICMPv6 Packet too big messages if we would have before. This patch is also required as a precondition for IPv6 NAT, where NAT helpers might enlarge packets up to a point that they require fragmentation. In that case we can't generate Packet too big messages since the proper MTU can't be calculated in all cases (f.i. when changing textual representation of a variable amount of addresses), so the packet is transparently fragmented iff the original packet or fragments would have fit the outgoing MTU. IPVS parts by Jesper Dangaard Brouer <brouer@redhat.com>. Signed-off-by: Patrick McHardy <kaber@trash.net>
2012-08-26 17:13:58 +00:00
__u16 frag_max_size;
#define IP6SKB_XFRM_TRANSFORMED 1
#define IP6SKB_FORWARDED 2
#define IP6SKB_REROUTED 4
#define IP6SKB_ROUTERALERT 8
#define IP6SKB_FRAGMENTED 16
};
#define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb))
#define IP6CBMTU(skb) ((struct ip6_mtuinfo *)((skb)->cb))
static inline int inet6_iif(const struct sk_buff *skb)
{
return IP6CB(skb)->iif;
}
struct tcp6_request_sock {
struct tcp_request_sock tcp6rsk_tcp;
};
struct ipv6_mc_socklist;
struct ipv6_ac_socklist;
struct ipv6_fl_socklist;
/**
* struct ipv6_pinfo - ipv6 private area
*
* In the struct sock hierarchy (tcp6_sock, upd6_sock, etc)
* this _must_ be the last member, so that inet6_sk_generic
* is able to calculate its offset from the base struct sock
* by using the struct proto->slab_obj_size member. -acme
*/
struct ipv6_pinfo {
struct in6_addr saddr;
struct in6_pktinfo sticky_pktinfo;
const struct in6_addr *daddr_cache;
#ifdef CONFIG_IPV6_SUBTREES
const struct in6_addr *saddr_cache;
#endif
__be32 flow_label;
__u32 frag_size;
/*
* Packed in 16bits.
* Omit one shift by by putting the signed field at MSB.
*/
#if defined(__BIG_ENDIAN_BITFIELD)
__s16 hop_limit:9;
__u16 __unused_1:7;
#else
__u16 __unused_1:7;
__s16 hop_limit:9;
#endif
#if defined(__BIG_ENDIAN_BITFIELD)
/* Packed in 16bits. */
__s16 mcast_hops:9;
__u16 __unused_2:6,
mc_loop:1;
#else
__u16 mc_loop:1,
__unused_2:6;
__s16 mcast_hops:9;
#endif
int ucast_oif;
int mcast_oif;
/* pktoption flags */
union {
struct {
__u16 srcrt:1,
osrcrt:1,
rxinfo:1,
rxoinfo:1,
rxhlim:1,
rxohlim:1,
hopopts:1,
ohopopts:1,
dstopts:1,
odstopts:1,
rxflow:1,
rxtclass:1,
rxpmtu:1,
rxorigdstaddr:1;
/* 2 bits hole */
} bits;
__u16 all;
} rxopt;
/* sockopt flags */
__u16 recverr:1,
sndflow:1,
pmtudisc:2,
ipv6only:1,
srcprefs:3, /* 001: prefer temporary address
* 010: prefer public address
* 100: prefer care-of address
*/
dontfrag:1;
__u8 min_hopcount;
__u8 tclass;
__u8 rcv_tclass;
__u32 dst_cookie;
__u32 rx_dst_cookie;
struct ipv6_mc_socklist __rcu *ipv6_mc_list;
struct ipv6_ac_socklist *ipv6_ac_list;
struct ipv6_fl_socklist __rcu *ipv6_fl_list;
struct ipv6_txoptions *opt;
struct sk_buff *pktoptions;
struct sk_buff *rxpmtu;
struct {
struct ipv6_txoptions *opt;
u8 hop_limit;
u8 tclass;
} cork;
};
/* WARNING: don't change the layout of the members in {raw,udp,tcp}6_sock! */
struct raw6_sock {
/* inet_sock has to be the first member of raw6_sock */
struct inet_sock inet;
__u32 checksum; /* perform checksum */
__u32 offset; /* checksum offset */
struct icmp6_filter filter;
__u32 ip6mr_table;
/* ipv6_pinfo has to be the last member of raw6_sock, see inet6_sk_generic */
struct ipv6_pinfo inet6;
};
struct udp6_sock {
struct udp_sock udp;
/* ipv6_pinfo has to be the last member of udp6_sock, see inet6_sk_generic */
struct ipv6_pinfo inet6;
};
struct tcp6_sock {
struct tcp_sock tcp;
/* ipv6_pinfo has to be the last member of tcp6_sock, see inet6_sk_generic */
struct ipv6_pinfo inet6;
};
extern int inet6_sk_rebuild_header(struct sock *sk);
struct tcp6_timewait_sock {
struct tcp_timewait_sock tcp6tw_tcp;
};
#if IS_ENABLED(CONFIG_IPV6)
static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk)
{
return inet_sk(__sk)->pinet6;
}
static inline struct request_sock *inet6_reqsk_alloc(struct request_sock_ops *ops)
{
struct request_sock *req = reqsk_alloc(ops);
if (req)
inet_rsk(req)->pktopts = NULL;
return req;
}
static inline struct raw6_sock *raw6_sk(const struct sock *sk)
{
return (struct raw6_sock *)sk;
}
static inline void inet_sk_copy_descendant(struct sock *sk_to,
const struct sock *sk_from)
{
int ancestor_size = sizeof(struct inet_sock);
if (sk_from->sk_family == PF_INET6)
ancestor_size += sizeof(struct ipv6_pinfo);
__inet_sk_copy_descendant(sk_to, sk_from, ancestor_size);
}
#define __ipv6_only_sock(sk) (inet6_sk(sk)->ipv6only)
#define ipv6_only_sock(sk) ((sk)->sk_family == PF_INET6 && __ipv6_only_sock(sk))
static inline const struct in6_addr *inet6_rcv_saddr(const struct sock *sk)
{
if (sk->sk_family == AF_INET6)
return &sk->sk_v6_rcv_saddr;
return NULL;
}
static inline int inet_v6_ipv6only(const struct sock *sk)
{
return likely(sk->sk_state != TCP_TIME_WAIT) ?
ipv6_only_sock(sk) : inet_twsk(sk)->tw_ipv6only;
}
#else
#define __ipv6_only_sock(sk) 0
#define ipv6_only_sock(sk) 0
static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk)
{
return NULL;
}
static inline struct inet6_request_sock *
inet6_rsk(const struct request_sock *rsk)
{
return NULL;
}
static inline struct raw6_sock *raw6_sk(const struct sock *sk)
{
return NULL;
}
#define inet6_rcv_saddr(__sk) NULL
#define tcp_twsk_ipv6only(__sk) 0
#define inet_v6_ipv6only(__sk) 0
#endif /* IS_ENABLED(CONFIG_IPV6) */
net: move inet_dport/inet_num in sock_common commit 68835aba4d9b (net: optimize INET input path further) moved some fields used for tcp/udp sockets lookup in the first cache line of struct sock_common. This patch moves inet_dport/inet_num as well, filling a 32bit hole on 64 bit arches and reducing number of cache line misses in lookups. Also change INET_MATCH()/INET_TW_MATCH() to perform the ports match before addresses match, as this check is more discriminant. Remove the hash check from MATCH() macros because we dont need to re validate the hash value after taking a refcount on socket, and use likely/unlikely compiler hints, as the sk_hash/hash check makes the following conditional tests 100% predicted by cpu. Introduce skc_addrpair/skc_portpair pair values to better document the alignment requirements of the port/addr pairs used in the various MATCH() macros, and remove some casts. The namespace check can also be done at last. This slightly improves TCP/UDP lookup times. IP/TCP early demux needs inet->rx_dst_ifindex and TCP needs inet->min_ttl, lets group them together in same cache line. With help from Ben Hutchings & Joe Perches. Idea of this patch came after Ling Ma proposal to move skc_hash to the beginning of struct sock_common, and should allow him to submit a final version of his patch. My tests show an improvement doing so. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Joe Perches <joe@perches.com> Cc: Ling Ma <ling.ma.program@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-30 09:49:27 +00:00
#define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif) \
(((__sk)->sk_portpair == (__ports)) && \
net: move inet_dport/inet_num in sock_common commit 68835aba4d9b (net: optimize INET input path further) moved some fields used for tcp/udp sockets lookup in the first cache line of struct sock_common. This patch moves inet_dport/inet_num as well, filling a 32bit hole on 64 bit arches and reducing number of cache line misses in lookups. Also change INET_MATCH()/INET_TW_MATCH() to perform the ports match before addresses match, as this check is more discriminant. Remove the hash check from MATCH() macros because we dont need to re validate the hash value after taking a refcount on socket, and use likely/unlikely compiler hints, as the sk_hash/hash check makes the following conditional tests 100% predicted by cpu. Introduce skc_addrpair/skc_portpair pair values to better document the alignment requirements of the port/addr pairs used in the various MATCH() macros, and remove some casts. The namespace check can also be done at last. This slightly improves TCP/UDP lookup times. IP/TCP early demux needs inet->rx_dst_ifindex and TCP needs inet->min_ttl, lets group them together in same cache line. With help from Ben Hutchings & Joe Perches. Idea of this patch came after Ling Ma proposal to move skc_hash to the beginning of struct sock_common, and should allow him to submit a final version of his patch. My tests show an improvement doing so. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Joe Perches <joe@perches.com> Cc: Ling Ma <ling.ma.program@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-30 09:49:27 +00:00
((__sk)->sk_family == AF_INET6) && \
ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr)) && \
ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr)) && \
net: move inet_dport/inet_num in sock_common commit 68835aba4d9b (net: optimize INET input path further) moved some fields used for tcp/udp sockets lookup in the first cache line of struct sock_common. This patch moves inet_dport/inet_num as well, filling a 32bit hole on 64 bit arches and reducing number of cache line misses in lookups. Also change INET_MATCH()/INET_TW_MATCH() to perform the ports match before addresses match, as this check is more discriminant. Remove the hash check from MATCH() macros because we dont need to re validate the hash value after taking a refcount on socket, and use likely/unlikely compiler hints, as the sk_hash/hash check makes the following conditional tests 100% predicted by cpu. Introduce skc_addrpair/skc_portpair pair values to better document the alignment requirements of the port/addr pairs used in the various MATCH() macros, and remove some casts. The namespace check can also be done at last. This slightly improves TCP/UDP lookup times. IP/TCP early demux needs inet->rx_dst_ifindex and TCP needs inet->min_ttl, lets group them together in same cache line. With help from Ben Hutchings & Joe Perches. Idea of this patch came after Ling Ma proposal to move skc_hash to the beginning of struct sock_common, and should allow him to submit a final version of his patch. My tests show an improvement doing so. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Joe Perches <joe@perches.com> Cc: Ling Ma <ling.ma.program@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-30 09:49:27 +00:00
(!(__sk)->sk_bound_dev_if || \
((__sk)->sk_bound_dev_if == (__dif))) && \
net_eq(sock_net(__sk), (__net)))
#endif /* _IPV6_H */