korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-11-18 09:44:18 +08:00
Code Issues Packages Projects Releases Wiki Activity
80b3671e93
linux/net/ipv6/sysctl_net_ipv6.c
Ahmed Abdelsalam b5facfdba1 ipv6: sr: Compute flowlabel for outer IPv6 header of seg6 encap mode 
ECMP (equal-cost multipath) hashes are typically computed on the packets'
5-tuple(src IP, dst IP, src port, dst port, L4 proto).

For encapsulated packets, the L4 data is not readily available and ECMP
hashing will often revert to (src IP, dst IP). This will lead to traffic
polarization on a single ECMP path, causing congestion and waste of network
capacity.

In IPv6, the 20-bit flow label field is also used as part of the ECMP hash.
In the lack of L4 data, the hashing will be on (src IP, dst IP, flow
label). Having a non-zero flow label is thus important for proper traffic
load balancing when L4 data is unavailable (i.e., when packets are
encapsulated).

Currently, the seg6_do_srh_encap() function extracts the original packet's
flow label and set it as the outer IPv6 flow label. There are two issues
with this behaviour:

a) There is no guarantee that the inner flow label is set by the source.
b) If the original packet is not IPv6, the flow label will be set to
zero (e.g., IPv4 or L2 encap).

This patch adds a function, named seg6_make_flowlabel(), that computes a
flow label from a given skb. It supports IPv6, IPv4 and L2 payloads, and
leverages the per namespace 'seg6_flowlabel" sysctl value.

The currently support behaviours are as follows:
-1 set flowlabel to zero.
0 copy flowlabel from Inner paceket in case of Inner IPv6
(Set flowlabel to 0 in case IPv4/L2)
1 Compute the flowlabel using seg6_make_flowlabel()

This patch has been tested for IPv6, IPv4, and L2 traffic.

Signed-off-by: Ahmed Abdelsalam <amsalam20@gmail.com>
Acked-by: David Lebrun <dlebrun@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-25 13:02:15 -04:00

317 lines
7.9 KiB
C
Raw Blame History

// SPDX-License-Identifier: GPL-2.0
/*
* sysctl_net_ipv6.c: sysctl interface to net IPV6 subsystem.
*
* Changes:
* YOSHIFUJI Hideaki @USAGI: added icmp sysctl table.
*/
#include <linux/mm.h>
#include <linux/sysctl.h>
#include <linux/in6.h>
#include <linux/ipv6.h>
#include <linux/slab.h>
#include <linux/export.h>
#include <net/ndisc.h>
#include <net/ipv6.h>
#include <net/addrconf.h>
#include <net/inet_frag.h>
#include <net/netevent.h>
#ifdef CONFIG_NETLABEL
#include <net/calipso.h>
#endif
static int zero;
static int one = 1;
static int auto_flowlabels_min;
static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX;
static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
struct net *net;
int ret;
net = container_of(table->data, struct net,
ipv6.sysctl.multipath_hash_policy);
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (write && ret == 0)
call_netevent_notifiers(NETEVENT_IPV6_MPATH_HASH_UPDATE, net);
return ret;
}
static struct ctl_table ipv6_table_template[] = {
{
.procname = "bindv6only",
.data = &init_net.ipv6.sysctl.bindv6only,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "anycast_src_echo_reply",
.data = &init_net.ipv6.sysctl.anycast_src_echo_reply,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "flowlabel_consistency",
.data = &init_net.ipv6.sysctl.flowlabel_consistency,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "auto_flowlabels",
.data = &init_net.ipv6.sysctl.auto_flowlabels,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &auto_flowlabels_min,
.extra2 = &auto_flowlabels_max
},
{
.procname = "fwmark_reflect",
.data = &init_net.ipv6.sysctl.fwmark_reflect,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "idgen_retries",
.data = &init_net.ipv6.sysctl.idgen_retries,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "idgen_delay",
.data = &init_net.ipv6.sysctl.idgen_delay,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "flowlabel_state_ranges",
.data = &init_net.ipv6.sysctl.flowlabel_state_ranges,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "ip_nonlocal_bind",
.data = &init_net.ipv6.sysctl.ip_nonlocal_bind,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "flowlabel_reflect",
.data = &init_net.ipv6.sysctl.flowlabel_reflect,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "max_dst_opts_number",
.data = &init_net.ipv6.sysctl.max_dst_opts_cnt,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "max_hbh_opts_number",
.data = &init_net.ipv6.sysctl.max_hbh_opts_cnt,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "max_dst_opts_length",
.data = &init_net.ipv6.sysctl.max_dst_opts_len,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "max_hbh_length",
.data = &init_net.ipv6.sysctl.max_hbh_opts_len,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "fib_multipath_hash_policy",
.data = &init_net.ipv6.sysctl.multipath_hash_policy,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_rt6_multipath_hash_policy,
.extra1 = &zero,
.extra2 = &one,
},
{
.procname = "seg6_flowlabel",
.data = &init_net.ipv6.sysctl.seg6_flowlabel,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{ }
};
static struct ctl_table ipv6_rotable[] = {
{
.procname = "mld_max_msf",
.data = &sysctl_mld_max_msf,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "mld_qrv",
.data = &sysctl_mld_qrv,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &one
},
#ifdef CONFIG_NETLABEL
{
.procname = "calipso_cache_enable",
.data = &calipso_cache_enabled,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "calipso_cache_bucket_size",
.data = &calipso_cache_bucketsize,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif /* CONFIG_NETLABEL */
{ }
};
static int __net_init ipv6_sysctl_net_init(struct net *net)
{
struct ctl_table *ipv6_table;
struct ctl_table *ipv6_route_table;
struct ctl_table *ipv6_icmp_table;
int err;
err = -ENOMEM;
ipv6_table = kmemdup(ipv6_table_template, sizeof(ipv6_table_template),
GFP_KERNEL);
if (!ipv6_table)
goto out;
ipv6_table[0].data = &net->ipv6.sysctl.bindv6only;
ipv6_table[1].data = &net->ipv6.sysctl.anycast_src_echo_reply;
ipv6_table[2].data = &net->ipv6.sysctl.flowlabel_consistency;
ipv6_table[3].data = &net->ipv6.sysctl.auto_flowlabels;
ipv6_table[4].data = &net->ipv6.sysctl.fwmark_reflect;
ipv6_table[5].data = &net->ipv6.sysctl.idgen_retries;
ipv6_table[6].data = &net->ipv6.sysctl.idgen_delay;
ipv6_table[7].data = &net->ipv6.sysctl.flowlabel_state_ranges;
ipv6_table[8].data = &net->ipv6.sysctl.ip_nonlocal_bind;
ipv6_table[9].data = &net->ipv6.sysctl.flowlabel_reflect;
ipv6_table[10].data = &net->ipv6.sysctl.max_dst_opts_cnt;
ipv6_table[11].data = &net->ipv6.sysctl.max_hbh_opts_cnt;
ipv6_table[12].data = &net->ipv6.sysctl.max_dst_opts_len;
ipv6_table[13].data = &net->ipv6.sysctl.max_hbh_opts_len;
ipv6_table[14].data = &net->ipv6.sysctl.multipath_hash_policy,
ipv6_table[15].data = &net->ipv6.sysctl.seg6_flowlabel;
ipv6_route_table = ipv6_route_sysctl_init(net);
if (!ipv6_route_table)
goto out_ipv6_table;
ipv6_icmp_table = ipv6_icmp_sysctl_init(net);
if (!ipv6_icmp_table)
goto out_ipv6_route_table;
net->ipv6.sysctl.hdr = register_net_sysctl(net, "net/ipv6", ipv6_table);
if (!net->ipv6.sysctl.hdr)
goto out_ipv6_icmp_table;
net->ipv6.sysctl.route_hdr =
register_net_sysctl(net, "net/ipv6/route", ipv6_route_table);
if (!net->ipv6.sysctl.route_hdr)
goto out_unregister_ipv6_table;
net->ipv6.sysctl.icmp_hdr =
register_net_sysctl(net, "net/ipv6/icmp", ipv6_icmp_table);
if (!net->ipv6.sysctl.icmp_hdr)
goto out_unregister_route_table;
err = 0;
out:
return err;
out_unregister_route_table:
unregister_net_sysctl_table(net->ipv6.sysctl.route_hdr);
out_unregister_ipv6_table:
unregister_net_sysctl_table(net->ipv6.sysctl.hdr);
out_ipv6_icmp_table:
kfree(ipv6_icmp_table);
out_ipv6_route_table:
kfree(ipv6_route_table);
out_ipv6_table:
kfree(ipv6_table);
goto out;
}
static void __net_exit ipv6_sysctl_net_exit(struct net *net)
{
struct ctl_table *ipv6_table;
struct ctl_table *ipv6_route_table;
struct ctl_table *ipv6_icmp_table;
ipv6_table = net->ipv6.sysctl.hdr->ctl_table_arg;
ipv6_route_table = net->ipv6.sysctl.route_hdr->ctl_table_arg;
ipv6_icmp_table = net->ipv6.sysctl.icmp_hdr->ctl_table_arg;
unregister_net_sysctl_table(net->ipv6.sysctl.icmp_hdr);
unregister_net_sysctl_table(net->ipv6.sysctl.route_hdr);
unregister_net_sysctl_table(net->ipv6.sysctl.hdr);
kfree(ipv6_table);
kfree(ipv6_route_table);
kfree(ipv6_icmp_table);
}
static struct pernet_operations ipv6_sysctl_net_ops = {
.init = ipv6_sysctl_net_init,
.exit = ipv6_sysctl_net_exit,
};
static struct ctl_table_header *ip6_header;
int ipv6_sysctl_register(void)
{
int err = -ENOMEM;
ip6_header = register_net_sysctl(&init_net, "net/ipv6", ipv6_rotable);
if (!ip6_header)
goto out;
err = register_pernet_subsys(&ipv6_sysctl_net_ops);
if (err)
goto err_pernet;
out:
return err;
err_pernet:
unregister_net_sysctl_table(ip6_header);
goto out;
}
void ipv6_sysctl_unregister(void)
{
unregister_net_sysctl_table(ip6_header);
unregister_pernet_subsys(&ipv6_sysctl_net_ops);
}
Reference in New Issue View Git Blame Copy Permalink