/linux/net/dccp/ |
H A D | ipv6.h | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
H A D | minisocks.c | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
H A D | ipv6.c | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
/linux/include/net/ |
H A D | ip6_checksum.h | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
H A D | inet6_hashtables.h | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
H A D | inet_timewait_sock.h | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
/linux/security/ |
H A D | lsm_audit.c | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
/linux/net/l2tp/ |
H A D | l2tp_debugfs.c | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
H A D | l2tp_netlink.c | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
H A D | l2tp_ppp.c | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
H A D | l2tp_ip6.c | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
H A D | l2tp_core.c | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
/linux/net/netfilter/ |
H A D | xt_TPROXY.c | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
H A D | xt_socket.c | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
/linux/net/sctp/ |
H A D | ipv6.c | diff 661dbf34129cecd20879cb7b1cbe936911da0f02 Thu Feb 06 08:30:10 CET 2014 Matija Glavinic Pecotic <matija.glavinic-pecotic.ext@nsn.com> net: sctp: fix initialization of local source address on accepted ipv6 sockets
commit efe4208f47f907b86f528788da711e8ab9dea44d: 'ipv6: make lookups simpler and faster' broke initialization of local source address on accepted ipv6 sockets. Before the mentioned commit receive address was copied along with the contents of ipv6_pinfo in sctp_v6_create_accept_sk. Now when it is moved, it has to be copied separately.
This also fixes lksctp's ipv6 regression in a sense that test_getname_v6, TC5 - 'getsockname on a connected server socket' now passes.
Signed-off-by: Matija Glavinic Pecotic <matija.glavinic-pecotic.ext@nsn.com> Signed-off-by: David S. Miller <davem@davemloft.net> diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
/linux/net/ipv6/ |
H A D | inet6_connection_sock.c | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
H A D | ping.c | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
H A D | inet6_hashtables.c | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
H A D | datagram.c | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
H A D | ipv6_sockglue.c | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
/linux/net/ipv4/ |
H A D | tcp_metrics.c | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
H A D | ping.c | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
H A D | inet_diag.c | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
/linux/include/linux/ |
H A D | ipv6.h | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|
/linux/net/sunrpc/ |
H A D | svcsock.c | diff efe4208f47f907b86f528788da711e8ab9dea44d Fri Oct 04 00:42:29 CEST 2013 Eric Dumazet <edumazet@google.com> 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>
|