/openbmc/linux/net/dccp/ |
H A D | ipv6.h | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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 | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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 | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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>
|
/openbmc/linux/include/net/ |
H A D | ip6_checksum.h | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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 | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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 | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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>
|
/openbmc/linux/net/l2tp/ |
H A D | l2tp_debugfs.c | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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 | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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 | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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 | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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 | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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>
|
/openbmc/linux/net/netfilter/ |
H A D | xt_TPROXY.c | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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 | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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>
|
/openbmc/linux/security/ |
H A D | lsm_audit.c | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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>
|
/openbmc/linux/net/ipv6/ |
H A D | inet6_connection_sock.c | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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 | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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 | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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 | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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 | raw.c | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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>
|
/openbmc/linux/net/ipv4/ |
H A D | tcp_metrics.c | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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 | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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 | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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 | tcp_timer.c | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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>
|
/openbmc/linux/include/linux/ |
H A D | ipv6.h | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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>
|
/openbmc/linux/net/sctp/ |
H A D | ipv6.c | efe4208f Thu Oct 03 17:42:29 CDT 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> efe4208f Thu Oct 03 17:42:29 CDT 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>
|