summaryrefslogtreecommitdiff
path: root/net/ipv4/ip_output.c
diff options
context:
space:
mode:
authorEric Dumazet <edumazet@google.com>2014-06-02 16:26:03 +0400
committerDavid S. Miller <davem@davemloft.net>2014-06-02 22:00:41 +0400
commit73f156a6e8c1074ac6327e0abd1169e95eb66463 (patch)
tree2c8b222f21784e738c397ba95dee70a8f256ea64 /net/ipv4/ip_output.c
parente067ee336a9d3f038ffa9699c59f2abec3376bf7 (diff)
downloadlinux-73f156a6e8c1074ac6327e0abd1169e95eb66463.tar.xz
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>
Diffstat (limited to 'net/ipv4/ip_output.c')
-rw-r--r--net/ipv4/ip_output.c7
1 files changed, 3 insertions, 4 deletions
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 6e231ab58d65..8d3b6b0e9857 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -148,7 +148,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
iph->saddr = saddr;
iph->protocol = sk->sk_protocol;
- ip_select_ident(skb, &rt->dst, sk);
+ ip_select_ident(skb, sk);
if (opt && opt->opt.optlen) {
iph->ihl += opt->opt.optlen>>2;
@@ -430,8 +430,7 @@ packet_routed:
ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0);
}
- ip_select_ident_more(skb, &rt->dst, sk,
- (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+ ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1);
/* TODO : should we use skb->sk here instead of sk ? */
skb->priority = sk->sk_priority;
@@ -1379,7 +1378,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
iph->ttl = ttl;
iph->protocol = sk->sk_protocol;
ip_copy_addrs(iph, fl4);
- ip_select_ident(skb, &rt->dst, sk);
+ ip_select_ident(skb, sk);
if (opt) {
iph->ihl += opt->optlen>>2;