xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

inetpeer: get rid of ip_id_count

Browse Source 
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>
This commit is contained in:
Eric Dumazet
2014-06-02 05:26:03 -07:00
committed by David S. Miller
parent e067ee336a
commit 73f156a6e8
17 changed files with 66 additions and 156 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
include/net/ip.h
View File

@@ -309,9 +309,19 @@ static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb)
}
}
void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more);
#define IP_IDENTS_SZ 2048u
extern atomic_t *ip_idents;
static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk)
static inline u32 ip_idents_reserve(u32 hash, int segs)
{
atomic_t *id_ptr = ip_idents + hash % IP_IDENTS_SZ;
return atomic_add_return(segs, id_ptr) - segs;
}
void __ip_select_ident(struct iphdr *iph, int segs);
static inline void ip_select_ident_segs(struct sk_buff *skb, struct sock *sk, int segs)
{
struct iphdr *iph = ip_hdr(skb);
@@ -321,24 +331,20 @@ static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, s
* does not change, they drop every other packet in
* a TCP stream using header compression.
*/
iph->id = (sk && inet_sk(sk)->inet_daddr) ?
htons(inet_sk(sk)->inet_id++) : 0;
} else
__ip_select_ident(iph, dst, 0);
}
static inline void ip_select_ident_more(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk, int more)
{
struct iphdr *iph = ip_hdr(skb);
if ((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) {
if (sk && inet_sk(sk)->inet_daddr) {
iph->id = htons(inet_sk(sk)->inet_id);
inet_sk(sk)->inet_id += 1 + more;
} else
inet_sk(sk)->inet_id += segs;
} else {
iph->id = 0;
} else
__ip_select_ident(iph, dst, more);
}
} else {
__ip_select_ident(iph, segs);
}
}
static inline void ip_select_ident(struct sk_buff *skb, struct sock *sk)
{
ip_select_ident_segs(skb, sk, 1);
}
static inline __wsum inet_compute_pseudo(struct sk_buff *skb, int proto)