linux_dsm_epyc7002/net/ipv4/xfrm4_mode_tunnel.c
Eric Dumazet 73f156a6e8 inetpeer: get rid of ip_id_count
Ideally, we would need to generate IP ID using a per destination IP
generator.

linux kernels used inet_peer cache for this purpose, but this had a huge
cost on servers disabling MTU discovery.

1) each inet_peer struct consumes 192 bytes

2) inetpeer cache uses a binary tree of inet_peer structs,
   with a nominal size of ~66000 elements under load.

3) lookups in this tree are hitting a lot of cache lines, as tree depth
   is about 20.

4) If server deals with many tcp flows, we have a high probability of
   not finding the inet_peer, allocating a fresh one, inserting it in
   the tree with same initial ip_id_count, (cf secure_ip_id())

5) We garbage collect inet_peer aggressively.

IP ID generation do not have to be 'perfect'

Goal is trying to avoid duplicates in a short period of time,
so that reassembly units have a chance to complete reassembly of
fragments belonging to one message before receiving other fragments
with a recycled ID.

We simply use an array of generators, and a Jenkin hash using the dst IP
as a key.

ipv6_select_ident() is put back into net/ipv6/ip6_output.c where it
belongs (it is only used from this file)

secure_ip_id() and secure_ipv6_id() no longer are needed.

Rename ip_select_ident_more() to ip_select_ident_segs() to avoid
unnecessary decrement/increment of the number of segments.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-02 11:00:41 -07:00

126 lines
2.9 KiB
C

/*
* xfrm4_mode_tunnel.c - Tunnel mode encapsulation for IPv4.
*
* Copyright (c) 2004-2006 Herbert Xu <herbert@gondor.apana.org.au>
*/
#include <linux/gfp.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/stringify.h>
#include <net/dst.h>
#include <net/inet_ecn.h>
#include <net/ip.h>
#include <net/xfrm.h>
static inline void ipip_ecn_decapsulate(struct sk_buff *skb)
{
struct iphdr *inner_iph = ipip_hdr(skb);
if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos))
IP_ECN_set_ce(inner_iph);
}
/* Add encapsulation header.
*
* The top IP header will be constructed per RFC 2401.
*/
static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct iphdr *top_iph;
int flags;
skb_set_network_header(skb, -x->props.header_len);
skb->mac_header = skb->network_header +
offsetof(struct iphdr, protocol);
skb->transport_header = skb->network_header + sizeof(*top_iph);
top_iph = ip_hdr(skb);
top_iph->ihl = 5;
top_iph->version = 4;
top_iph->protocol = xfrm_af2proto(skb_dst(skb)->ops->family);
/* DS disclosing depends on XFRM_SA_XFLAG_DONT_ENCAP_DSCP */
if (x->props.extra_flags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP)
top_iph->tos = 0;
else
top_iph->tos = XFRM_MODE_SKB_CB(skb)->tos;
top_iph->tos = INET_ECN_encapsulate(top_iph->tos,
XFRM_MODE_SKB_CB(skb)->tos);
flags = x->props.flags;
if (flags & XFRM_STATE_NOECN)
IP_ECN_clear(top_iph);
top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF));
top_iph->ttl = ip4_dst_hoplimit(dst->child);
top_iph->saddr = x->props.saddr.a4;
top_iph->daddr = x->id.daddr.a4;
ip_select_ident(skb, NULL);
return 0;
}
static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
{
int err = -EINVAL;
if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP)
goto out;
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto out;
err = skb_unclone(skb, GFP_ATOMIC);
if (err)
goto out;
if (x->props.flags & XFRM_STATE_DECAP_DSCP)
ipv4_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, ipip_hdr(skb));
if (!(x->props.flags & XFRM_STATE_NOECN))
ipip_ecn_decapsulate(skb);
skb_reset_network_header(skb);
skb_mac_header_rebuild(skb);
err = 0;
out:
return err;
}
static struct xfrm_mode xfrm4_tunnel_mode = {
.input2 = xfrm4_mode_tunnel_input,
.input = xfrm_prepare_input,
.output2 = xfrm4_mode_tunnel_output,
.output = xfrm4_prepare_output,
.owner = THIS_MODULE,
.encap = XFRM_MODE_TUNNEL,
.flags = XFRM_MODE_FLAG_TUNNEL,
};
static int __init xfrm4_mode_tunnel_init(void)
{
return xfrm_register_mode(&xfrm4_tunnel_mode, AF_INET);
}
static void __exit xfrm4_mode_tunnel_exit(void)
{
int err;
err = xfrm_unregister_mode(&xfrm4_tunnel_mode, AF_INET);
BUG_ON(err);
}
module_init(xfrm4_mode_tunnel_init);
module_exit(xfrm4_mode_tunnel_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS_XFRM_MODE(AF_INET, XFRM_MODE_TUNNEL);