ipv6: make lookups simpler and faster

TCP listener refactoring, part 4 :

To speed up inet lookups, we moved IPv4 addresses from inet to struct
sock_common

Now is time to do the same for IPv6, because it permits us to have fast
lookups for all kind of sockets, including upcoming SYN_RECV.

Getting IPv6 addresses in TCP lookups currently requires two extra cache
lines, plus a dereference (and memory stall).

inet6_sk(sk) does the dereference of inet_sk(__sk)->pinet6

This patch is way bigger than its IPv4 counter part, because for IPv4,
we could add aliases (inet_daddr, inet_rcv_saddr), while on IPv6,
it's not doable easily.

inet6_sk(sk)->daddr becomes sk->sk_v6_daddr
inet6_sk(sk)->rcv_saddr becomes sk->sk_v6_rcv_saddr

And timewait socket also have tw->tw_v6_daddr & tw->tw_v6_rcv_saddr
at the same offset.

We get rid of INET6_TW_MATCH() as INET6_MATCH() is now the generic
macro.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Eric Dumazet 2013-10-03 15:42:29 -07:00 committed by David S. Miller
parent 05dbc7b594
commit efe4208f47
35 changed files with 213 additions and 288 deletions

View file

@ -55,11 +55,10 @@
int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
{
const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr;
const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2);
int sk_ipv6only = ipv6_only_sock(sk);
int sk2_ipv6only = inet_v6_ipv6only(sk2);
int addr_type = ipv6_addr_type(sk_rcv_saddr6);
int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr);
int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
/* if both are mapped, treat as IPv4 */
@ -77,7 +76,7 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
return 1;
if (sk2_rcv_saddr6 &&
ipv6_addr_equal(sk_rcv_saddr6, sk2_rcv_saddr6))
ipv6_addr_equal(&sk->sk_v6_rcv_saddr, sk2_rcv_saddr6))
return 1;
return 0;
@ -105,7 +104,7 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum)
unsigned int hash2_nulladdr =
udp6_portaddr_hash(sock_net(sk), &in6addr_any, snum);
unsigned int hash2_partial =
udp6_portaddr_hash(sock_net(sk), &inet6_sk(sk)->rcv_saddr, 0);
udp6_portaddr_hash(sock_net(sk), &sk->sk_v6_rcv_saddr, 0);
/* precompute partial secondary hash */
udp_sk(sk)->udp_portaddr_hash = hash2_partial;
@ -115,7 +114,7 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum)
static void udp_v6_rehash(struct sock *sk)
{
u16 new_hash = udp6_portaddr_hash(sock_net(sk),
&inet6_sk(sk)->rcv_saddr,
&sk->sk_v6_rcv_saddr,
inet_sk(sk)->inet_num);
udp_lib_rehash(sk, new_hash);
@ -131,7 +130,6 @@ static inline int compute_score(struct sock *sk, struct net *net,
if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum &&
sk->sk_family == PF_INET6) {
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet_sock *inet = inet_sk(sk);
score = 0;
@ -140,13 +138,13 @@ static inline int compute_score(struct sock *sk, struct net *net,
return -1;
score++;
}
if (!ipv6_addr_any(&np->rcv_saddr)) {
if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
return -1;
score++;
}
if (!ipv6_addr_any(&np->daddr)) {
if (!ipv6_addr_equal(&np->daddr, saddr))
if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
return -1;
score++;
}
@ -169,10 +167,9 @@ static inline int compute_score2(struct sock *sk, struct net *net,
if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum &&
sk->sk_family == PF_INET6) {
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet_sock *inet = inet_sk(sk);
if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
return -1;
score = 0;
if (inet->inet_dport) {
@ -180,8 +177,8 @@ static inline int compute_score2(struct sock *sk, struct net *net,
return -1;
score++;
}
if (!ipv6_addr_any(&np->daddr)) {
if (!ipv6_addr_equal(&np->daddr, saddr))
if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
return -1;
score++;
}
@ -549,7 +546,7 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
int rc;
if (!ipv6_addr_any(&inet6_sk(sk)->daddr)) {
if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
sock_rps_save_rxhash(sk, skb);
sk_mark_napi_id(sk, skb);
}
@ -690,20 +687,19 @@ static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk,
if (udp_sk(s)->udp_port_hash == num &&
s->sk_family == PF_INET6) {
struct ipv6_pinfo *np = inet6_sk(s);
if (inet->inet_dport) {
if (inet->inet_dport != rmt_port)
continue;
}
if (!ipv6_addr_any(&np->daddr) &&
!ipv6_addr_equal(&np->daddr, rmt_addr))
if (!ipv6_addr_any(&sk->sk_v6_daddr) &&
!ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr))
continue;
if (s->sk_bound_dev_if && s->sk_bound_dev_if != dif)
continue;
if (!ipv6_addr_any(&np->rcv_saddr)) {
if (!ipv6_addr_equal(&np->rcv_saddr, loc_addr))
if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr))
continue;
}
if (!inet6_mc_check(s, loc_addr, rmt_addr))
@ -1063,7 +1059,7 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk,
} else if (!up->pending) {
if (sk->sk_state != TCP_ESTABLISHED)
return -EDESTADDRREQ;
daddr = &np->daddr;
daddr = &sk->sk_v6_daddr;
} else
daddr = NULL;
@ -1133,8 +1129,8 @@ do_udp_sendmsg:
* sk->sk_dst_cache.
*/
if (sk->sk_state == TCP_ESTABLISHED &&
ipv6_addr_equal(daddr, &np->daddr))
daddr = &np->daddr;
ipv6_addr_equal(daddr, &sk->sk_v6_daddr))
daddr = &sk->sk_v6_daddr;
if (addr_len >= sizeof(struct sockaddr_in6) &&
sin6->sin6_scope_id &&
@ -1145,7 +1141,7 @@ do_udp_sendmsg:
return -EDESTADDRREQ;
fl6.fl6_dport = inet->inet_dport;
daddr = &np->daddr;
daddr = &sk->sk_v6_daddr;
fl6.flowlabel = np->flow_label;
connected = 1;
}
@ -1261,8 +1257,8 @@ do_append_data:
if (dst) {
if (connected) {
ip6_dst_store(sk, dst,
ipv6_addr_equal(&fl6.daddr, &np->daddr) ?
&np->daddr : NULL,
ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ?
&sk->sk_v6_daddr : NULL,
#ifdef CONFIG_IPV6_SUBTREES
ipv6_addr_equal(&fl6.saddr, &np->saddr) ?
&np->saddr :