82a584b7cd
This patch divides the IPv6 flow label space into two ranges: 0-7ffff is reserved for flow label manager, 80000-fffff will be used for creating auto flow labels (per RFC6438). This only affects how labels are set on transmit, it does not affect receive. This range split can be disbaled by systcl. Background: IPv6 flow labels have been an unmitigated disappointment thus far in the lifetime of IPv6. Support in HW devices to use them for ECMP is lacking, and OSes don't turn them on by default. If we had these we could get much better hashing in IPv6 networks without resorting to DPI, possibly eliminating some of the motivations to to define new encaps in UDP just for getting ECMP. Unfortunately, the initial specfications of IPv6 did not clarify how they are to be used. There has always been a vague concept that these can be used for ECMP, flow hashing, etc. and we do now have a good standard how to this in RFC6438. The problem is that flow labels can be either stateful or stateless (as in RFC6438), and we are presented with the possibility that a stateless label may collide with a stateful one. Attempts to split the flow label space were rejected in IETF. When we added support in Linux for RFC6438, we could not turn on flow labels by default due to this conflict. This patch splits the flow label space and should give us a path to enabling auto flow labels by default for all IPv6 packets. This is an API change so we need to consider compatibility with existing deployment. The stateful range is chosen to be the lower values in hopes that most uses would have chosen small numbers. Once we resolve the stateless/stateful issue, we can proceed to look at enabling RFC6438 flow labels by default (starting with scaled testing). Signed-off-by: Tom Herbert <tom@herbertland.com> Signed-off-by: David S. Miller <davem@davemloft.net>
94 lines
2.2 KiB
C
94 lines
2.2 KiB
C
/*
|
|
* ipv6 in net namespaces
|
|
*/
|
|
|
|
#include <net/inet_frag.h>
|
|
|
|
#ifndef __NETNS_IPV6_H__
|
|
#define __NETNS_IPV6_H__
|
|
#include <net/dst_ops.h>
|
|
|
|
struct ctl_table_header;
|
|
|
|
struct netns_sysctl_ipv6 {
|
|
#ifdef CONFIG_SYSCTL
|
|
struct ctl_table_header *hdr;
|
|
struct ctl_table_header *route_hdr;
|
|
struct ctl_table_header *icmp_hdr;
|
|
struct ctl_table_header *frags_hdr;
|
|
struct ctl_table_header *xfrm6_hdr;
|
|
#endif
|
|
int bindv6only;
|
|
int flush_delay;
|
|
int ip6_rt_max_size;
|
|
int ip6_rt_gc_min_interval;
|
|
int ip6_rt_gc_timeout;
|
|
int ip6_rt_gc_interval;
|
|
int ip6_rt_gc_elasticity;
|
|
int ip6_rt_mtu_expires;
|
|
int ip6_rt_min_advmss;
|
|
int flowlabel_consistency;
|
|
int auto_flowlabels;
|
|
int icmpv6_time;
|
|
int anycast_src_echo_reply;
|
|
int fwmark_reflect;
|
|
int idgen_retries;
|
|
int idgen_delay;
|
|
int flowlabel_state_ranges;
|
|
};
|
|
|
|
struct netns_ipv6 {
|
|
struct netns_sysctl_ipv6 sysctl;
|
|
struct ipv6_devconf *devconf_all;
|
|
struct ipv6_devconf *devconf_dflt;
|
|
struct inet_peer_base *peers;
|
|
struct netns_frags frags;
|
|
#ifdef CONFIG_NETFILTER
|
|
struct xt_table *ip6table_filter;
|
|
struct xt_table *ip6table_mangle;
|
|
struct xt_table *ip6table_raw;
|
|
#ifdef CONFIG_SECURITY
|
|
struct xt_table *ip6table_security;
|
|
#endif
|
|
struct xt_table *ip6table_nat;
|
|
#endif
|
|
struct rt6_info *ip6_null_entry;
|
|
struct rt6_statistics *rt6_stats;
|
|
struct timer_list ip6_fib_timer;
|
|
struct hlist_head *fib_table_hash;
|
|
struct fib6_table *fib6_main_tbl;
|
|
struct dst_ops ip6_dst_ops;
|
|
unsigned int ip6_rt_gc_expire;
|
|
unsigned long ip6_rt_last_gc;
|
|
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
|
|
struct rt6_info *ip6_prohibit_entry;
|
|
struct rt6_info *ip6_blk_hole_entry;
|
|
struct fib6_table *fib6_local_tbl;
|
|
struct fib_rules_ops *fib6_rules_ops;
|
|
#endif
|
|
struct sock **icmp_sk;
|
|
struct sock *ndisc_sk;
|
|
struct sock *tcp_sk;
|
|
struct sock *igmp_sk;
|
|
struct sock *mc_autojoin_sk;
|
|
#ifdef CONFIG_IPV6_MROUTE
|
|
#ifndef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
|
|
struct mr6_table *mrt6;
|
|
#else
|
|
struct list_head mr6_tables;
|
|
struct fib_rules_ops *mr6_rules_ops;
|
|
#endif
|
|
#endif
|
|
atomic_t dev_addr_genid;
|
|
atomic_t fib6_sernum;
|
|
};
|
|
|
|
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
|
|
struct netns_nf_frag {
|
|
struct netns_sysctl_ipv6 sysctl;
|
|
struct netns_frags frags;
|
|
};
|
|
#endif
|
|
|
|
#endif
|