linux/net/ipv6/output_core.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

99 lines
2.1 KiB
C

/*
* IPv6 library code, needed by static components when full IPv6 support is
* not configured or static. These functions are needed by GSO/GRO implementation.
*/
#include <linux/export.h>
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/addrconf.h>
#include <net/secure_seq.h>
int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
{
u16 offset = sizeof(struct ipv6hdr);
struct ipv6_opt_hdr *exthdr =
(struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1);
unsigned int packet_len = skb_tail_pointer(skb) -
skb_network_header(skb);
int found_rhdr = 0;
*nexthdr = &ipv6_hdr(skb)->nexthdr;
while (offset + 1 <= packet_len) {
switch (**nexthdr) {
case NEXTHDR_HOP:
break;
case NEXTHDR_ROUTING:
found_rhdr = 1;
break;
case NEXTHDR_DEST:
#if IS_ENABLED(CONFIG_IPV6_MIP6)
if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0)
break;
#endif
if (found_rhdr)
return offset;
break;
default :
return offset;
}
offset += ipv6_optlen(exthdr);
*nexthdr = &exthdr->nexthdr;
exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) +
offset);
}
return offset;
}
EXPORT_SYMBOL(ip6_find_1stfragopt);
#if IS_ENABLED(CONFIG_IPV6)
int ip6_dst_hoplimit(struct dst_entry *dst)
{
int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT);
if (hoplimit == 0) {
struct net_device *dev = dst->dev;
struct inet6_dev *idev;
rcu_read_lock();
idev = __in6_dev_get(dev);
if (idev)
hoplimit = idev->cnf.hop_limit;
else
hoplimit = dev_net(dev)->ipv6.devconf_all->hop_limit;
rcu_read_unlock();
}
return hoplimit;
}
EXPORT_SYMBOL(ip6_dst_hoplimit);
#endif
int __ip6_local_out(struct sk_buff *skb)
{
int len;
len = skb->len - sizeof(struct ipv6hdr);
if (len > IPV6_MAXPLEN)
len = 0;
ipv6_hdr(skb)->payload_len = htons(len);
return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL,
skb_dst(skb)->dev, dst_output);
}
EXPORT_SYMBOL_GPL(__ip6_local_out);
int ip6_local_out(struct sk_buff *skb)
{
int err;
err = __ip6_local_out(skb);
if (likely(err == 1))
err = dst_output(skb);
return err;
}
EXPORT_SYMBOL_GPL(ip6_local_out);