From 304a16180fb6d2b153b45f6fbbcec1fa814496e5 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 19:59:20 -0700 Subject: [INET]: Move the TCP ehash functions to include/net/inet_hashtables.h To be shared with DCCP (and others), this is the start of a series of patches that will expose the already generic TCP hash table routines. The few changes noticed when calling gcc -S before/after on a pentium4 were of this type: movl 40(%esp), %edx cmpl %esi, 472(%edx) je .L168 - pushl $291 + pushl $272 pushl $.LC0 pushl $.LC1 pushl $.LC2 [acme@toy net-2.6.14]$ size net/ipv4/tcp_ipv4.before.o net/ipv4/tcp_ipv4.after.o text data bss dec hex filename 17804 516 140 18460 481c net/ipv4/tcp_ipv4.before.o 17804 516 140 18460 481c net/ipv4/tcp_ipv4.after.o Holler if some weird architecture has issues with things like this 8) Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) create mode 100644 include/net/inet_hashtables.h (limited to 'include/net/inet_hashtables.h') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h new file mode 100644 index 000000000000..c4c9e39f4505 --- /dev/null +++ b/include/net/inet_hashtables.h @@ -0,0 +1,40 @@ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * Authors: Lotsa people, from code originally in tcp + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _INET_HASHTABLES_H +#define _INET_HASHTABLES_H + +#include + +static inline int inet_ehashfn(const __u32 laddr, const __u16 lport, + const __u32 faddr, const __u16 fport, + const int ehash_size) +{ + int h = (laddr ^ lport) ^ (faddr ^ fport); + h ^= h >> 16; + h ^= h >> 8; + return h & (ehash_size - 1); +} + +static inline int inet_sk_ehashfn(const struct sock *sk, const int ehash_size) +{ + const struct inet_sock *inet = inet_sk(sk); + const __u32 laddr = inet->rcv_saddr; + const __u16 lport = inet->num; + const __u32 faddr = inet->daddr; + const __u16 fport = inet->dport; + + return inet_ehashfn(laddr, lport, faddr, fport, ehash_size); +} + +#endif /* _INET_HASHTABLES_H */ -- cgit v1.2.2 From 77d8bf9c6208eb535f05718168ffcc476be0ca8c Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:00:51 -0700 Subject: [INET]: Move the TCP hashtable functions/structs to inet_hashtables.[ch] Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 122 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 122 insertions(+) (limited to 'include/net/inet_hashtables.h') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index c4c9e39f4505..3a6c11ca421d 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -14,8 +14,107 @@ #ifndef _INET_HASHTABLES_H #define _INET_HASHTABLES_H +#include +#include +#include +#include #include +/* This is for all connections with a full identity, no wildcards. + * New scheme, half the table is for TIME_WAIT, the other half is + * for the rest. I'll experiment with dynamic table growth later. + */ +struct inet_ehash_bucket { + rwlock_t lock; + struct hlist_head chain; +} __attribute__((__aligned__(8))); + +/* There are a few simple rules, which allow for local port reuse by + * an application. In essence: + * + * 1) Sockets bound to different interfaces may share a local port. + * Failing that, goto test 2. + * 2) If all sockets have sk->sk_reuse set, and none of them are in + * TCP_LISTEN state, the port may be shared. + * Failing that, goto test 3. + * 3) If all sockets are bound to a specific inet_sk(sk)->rcv_saddr local + * address, and none of them are the same, the port may be + * shared. + * Failing this, the port cannot be shared. + * + * The interesting point, is test #2. This is what an FTP server does + * all day. To optimize this case we use a specific flag bit defined + * below. As we add sockets to a bind bucket list, we perform a + * check of: (newsk->sk_reuse && (newsk->sk_state != TCP_LISTEN)) + * As long as all sockets added to a bind bucket pass this test, + * the flag bit will be set. + * The resulting situation is that tcp_v[46]_verify_bind() can just check + * for this flag bit, if it is set and the socket trying to bind has + * sk->sk_reuse set, we don't even have to walk the owners list at all, + * we return that it is ok to bind this socket to the requested local port. + * + * Sounds like a lot of work, but it is worth it. In a more naive + * implementation (ie. current FreeBSD etc.) the entire list of ports + * must be walked for each data port opened by an ftp server. Needless + * to say, this does not scale at all. With a couple thousand FTP + * users logged onto your box, isn't it nice to know that new data + * ports are created in O(1) time? I thought so. ;-) -DaveM + */ +struct inet_bind_bucket { + unsigned short port; + signed short fastreuse; + struct hlist_node node; + struct hlist_head owners; +}; + +#define inet_bind_bucket_for_each(tb, node, head) \ + hlist_for_each_entry(tb, node, head, node) + +struct inet_bind_hashbucket { + spinlock_t lock; + struct hlist_head chain; +}; + +/* This is for listening sockets, thus all sockets which possess wildcards. */ +#define INET_LHTABLE_SIZE 32 /* Yes, really, this is all you need. */ + +struct inet_hashinfo { + /* This is for sockets with full identity only. Sockets here will + * always be without wildcards and will have the following invariant: + * + * TCP_ESTABLISHED <= sk->sk_state < TCP_CLOSE + * + * First half of the table is for sockets not in TIME_WAIT, second half + * is for TIME_WAIT sockets only. + */ + struct inet_ehash_bucket *ehash; + + /* Ok, let's try this, I give up, we do need a local binding + * TCP hash as well as the others for fast bind/connect. + */ + struct inet_bind_hashbucket *bhash; + + int bhash_size; + int ehash_size; + + /* All sockets in TCP_LISTEN state will be in here. This is the only + * table where wildcard'd TCP sockets can exist. Hash function here + * is just local port number. + */ + struct hlist_head listening_hash[INET_LHTABLE_SIZE]; + + /* All the above members are written once at bootup and + * never written again _or_ are predominantly read-access. + * + * Now align to a new cache line as all the following members + * are often dirty. + */ + rwlock_t lhash_lock ____cacheline_aligned; + atomic_t lhash_users; + wait_queue_head_t lhash_wait; + spinlock_t portalloc_lock; +}; + static inline int inet_ehashfn(const __u32 laddr, const __u16 lport, const __u32 faddr, const __u16 fport, const int ehash_size) @@ -37,4 +136,27 @@ static inline int inet_sk_ehashfn(const struct sock *sk, const int ehash_size) return inet_ehashfn(laddr, lport, faddr, fport, ehash_size); } +extern struct inet_bind_bucket * + inet_bind_bucket_create(kmem_cache_t *cachep, + struct inet_bind_hashbucket *head, + const unsigned short snum); +extern void inet_bind_bucket_destroy(kmem_cache_t *cachep, + struct inet_bind_bucket *tb); + +static inline int inet_bhashfn(const __u16 lport, const int bhash_size) +{ + return lport & (bhash_size - 1); +} + +/* These can have wildcards, don't try too hard. */ +static inline int inet_lhashfn(const unsigned short num) +{ + return num & (INET_LHTABLE_SIZE - 1); +} + +static inline int inet_sk_listen_hashfn(const struct sock *sk) +{ + return inet_lhashfn(inet_sk(sk)->num); +} + #endif /* _INET_HASHTABLES_H */ -- cgit v1.2.2 From 2d8c4ce51903636ce0f60addc8134aa50ab8fa76 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:07:13 -0700 Subject: [INET]: Generalise tcp_bind_hash & tcp_inherit_port This required moving tcp_bucket_cachep to inet_hashinfo. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include/net/inet_hashtables.h') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 3a6c11ca421d..da9705525f15 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -14,12 +14,15 @@ #ifndef _INET_HASHTABLES_H #define _INET_HASHTABLES_H +#include #include #include #include #include #include +#include + /* This is for all connections with a full identity, no wildcards. * New scheme, half the table is for TIME_WAIT, the other half is * for the rest. I'll experiment with dynamic table growth later. @@ -113,6 +116,7 @@ struct inet_hashinfo { atomic_t lhash_users; wait_queue_head_t lhash_wait; spinlock_t portalloc_lock; + kmem_cache_t *bind_bucket_cachep; }; static inline int inet_ehashfn(const __u32 laddr, const __u16 lport, @@ -148,6 +152,9 @@ static inline int inet_bhashfn(const __u16 lport, const int bhash_size) return lport & (bhash_size - 1); } +extern void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, + const unsigned short snum); + /* These can have wildcards, don't try too hard. */ static inline int inet_lhashfn(const unsigned short num) { @@ -159,4 +166,29 @@ static inline int inet_sk_listen_hashfn(const struct sock *sk) return inet_lhashfn(inet_sk(sk)->num); } +/* Caller must disable local BH processing. */ +static inline void __inet_inherit_port(struct inet_hashinfo *table, + struct sock *sk, struct sock *child) +{ + const int bhash = inet_bhashfn(inet_sk(child)->num, table->bhash_size); + struct inet_bind_hashbucket *head = &table->bhash[bhash]; + struct inet_bind_bucket *tb; + + spin_lock(&head->lock); + tb = inet_sk(sk)->bind_hash; + sk_add_bind_node(child, &tb->owners); + inet_sk(child)->bind_hash = tb; + spin_unlock(&head->lock); +} + +static inline void inet_inherit_port(struct inet_hashinfo *table, + struct sock *sk, struct sock *child) +{ + local_bh_disable(); + __inet_inherit_port(table, sk, child); + local_bh_enable(); +} + +extern void inet_put_port(struct inet_hashinfo *table, struct sock *sk); + #endif /* _INET_HASHTABLES_H */ -- cgit v1.2.2 From 6e04e02165a7209a71db553b7bc48d68421e5ebf Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:07:35 -0700 Subject: [INET]: Move tcp_port_rover to inet_hashinfo Also expose all of the tcp_hashinfo members, i.e. killing those tcp_ehash, etc macros, this will more clearly expose already generic functions and some that need just a bit of work to become generic, as we'll see in the upcoming changesets. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net/inet_hashtables.h') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index da9705525f15..da07411b36d2 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -117,6 +117,7 @@ struct inet_hashinfo { wait_queue_head_t lhash_wait; spinlock_t portalloc_lock; kmem_cache_t *bind_bucket_cachep; + int port_rover; }; static inline int inet_ehashfn(const __u32 laddr, const __u16 lport, -- cgit v1.2.2 From f3f05f7046e7c85b04af390d95a82a27160dd5d0 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:08:09 -0700 Subject: [INET]: Generalise the tcp_listen_ lock routines Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 48 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) (limited to 'include/net/inet_hashtables.h') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index da07411b36d2..f5d65121f7b7 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -19,10 +19,14 @@ #include #include #include +#include /* only for TCP_LISTEN, damn :-( */ #include +#include #include +#include + /* This is for all connections with a full identity, no wildcards. * New scheme, half the table is for TIME_WAIT, the other half is * for the rest. I'll experiment with dynamic table growth later. @@ -192,4 +196,48 @@ static inline void inet_inherit_port(struct inet_hashinfo *table, extern void inet_put_port(struct inet_hashinfo *table, struct sock *sk); +extern void inet_listen_wlock(struct inet_hashinfo *hashinfo); + +/* + * - We may sleep inside this lock. + * - If sleeping is not required (or called from BH), + * use plain read_(un)lock(&inet_hashinfo.lhash_lock). + */ +static inline void inet_listen_lock(struct inet_hashinfo *hashinfo) +{ + /* read_lock synchronizes to candidates to writers */ + read_lock(&hashinfo->lhash_lock); + atomic_inc(&hashinfo->lhash_users); + read_unlock(&hashinfo->lhash_lock); +} + +static inline void inet_listen_unlock(struct inet_hashinfo *hashinfo) +{ + if (atomic_dec_and_test(&hashinfo->lhash_users)) + wake_up(&hashinfo->lhash_wait); +} + +static inline void __inet_hash(struct inet_hashinfo *hashinfo, + struct sock *sk, const int listen_possible) +{ + struct hlist_head *list; + rwlock_t *lock; + + BUG_TRAP(sk_unhashed(sk)); + if (listen_possible && sk->sk_state == TCP_LISTEN) { + list = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; + lock = &hashinfo->lhash_lock; + inet_listen_wlock(hashinfo); + } else { + sk->sk_hashent = inet_sk_ehashfn(sk, hashinfo->ehash_size); + list = &hashinfo->ehash[sk->sk_hashent].chain; + lock = &hashinfo->ehash[sk->sk_hashent].lock; + write_lock(lock); + } + __sk_add_node(sk, list); + sock_prot_inc_use(sk->sk_prot); + write_unlock(lock); + if (listen_possible && sk->sk_state == TCP_LISTEN) + wake_up(&hashinfo->lhash_wait); +} #endif /* _INET_HASHTABLES_H */ -- cgit v1.2.2 From c752f0739f09b803aed191c4765a3b6650a08653 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:08:28 -0700 Subject: [TCP]: Move the tcp sock states to net/tcp_states.h Lots of places just needs the states, not even linux/tcp.h, where this enum was, needs it. This speeds up development of the refactorings as less sources are rebuilt when things get moved from net/tcp.h. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net/inet_hashtables.h') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index f5d65121f7b7..c816708fa556 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -19,11 +19,11 @@ #include #include #include -#include /* only for TCP_LISTEN, damn :-( */ #include #include #include +#include #include -- cgit v1.2.2 From 81849d106b1fb97f8e2d311c0c4d36347def55b8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:08:50 -0700 Subject: [INET]: Generalise tcp_v4_hash & tcp_unhash It really just makes the existing code be a helper function that tcp_v4_hash and tcp_unhash uses, specifying the right inet_hashinfo, tcp_hashinfo. One thing I'll investigate at some point is to have the inet_hashinfo pointer in sk_prot, so that we get all the hashtable information from the sk pointer, this can lead to some extra indirections that may well hurt performance/code size, we'll see. Ultimate idea would be that sk_prot would provide _all_ the information about a protocol implementation. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/net/inet_hashtables.h') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index c816708fa556..6731df2cea67 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -240,4 +240,38 @@ static inline void __inet_hash(struct inet_hashinfo *hashinfo, if (listen_possible && sk->sk_state == TCP_LISTEN) wake_up(&hashinfo->lhash_wait); } + +static inline void inet_hash(struct inet_hashinfo *hashinfo, struct sock *sk) +{ + if (sk->sk_state != TCP_CLOSE) { + local_bh_disable(); + __inet_hash(hashinfo, sk, 1); + local_bh_enable(); + } +} + +static inline void inet_unhash(struct inet_hashinfo *hashinfo, struct sock *sk) +{ + rwlock_t *lock; + + if (sk_unhashed(sk)) + goto out; + + if (sk->sk_state == TCP_LISTEN) { + local_bh_disable(); + inet_listen_wlock(hashinfo); + lock = &hashinfo->lhash_lock; + } else { + struct inet_ehash_bucket *head = &hashinfo->ehash[sk->sk_hashent]; + lock = &head->lock; + write_lock_bh(&head->lock); + } + + if (__sk_del_node_init(sk)) + sock_prot_dec_use(sk->sk_prot); + write_unlock_bh(lock); +out: + if (sk->sk_state == TCP_LISTEN) + wake_up(&hashinfo->lhash_wait); +} #endif /* _INET_HASHTABLES_H */ -- cgit v1.2.2 From 33b62231908c58ae04185e4f1063d1e35a7c8576 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:09:06 -0700 Subject: [INET]: Generalise tcp_v4_lookup_listener [acme@toy net-2.6.14]$ grep built-in /tmp/before /tmp/after /tmp/before: 282560 13122 9312 304994 4a762 net/ipv4/built-in.o /tmp/after: 282560 13122 9312 304994 4a762 net/ipv4/built-in.o Will be used in DCCP, not exporting it right now not to get in Adrian Bunk's exported-but-not-used-on-modules radar 8) Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/net/inet_hashtables.h') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 6731df2cea67..1c4fa0065a8e 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -16,8 +16,10 @@ #include #include +#include #include #include +#include #include #include #include @@ -274,4 +276,38 @@ out: if (sk->sk_state == TCP_LISTEN) wake_up(&hashinfo->lhash_wait); } + +extern struct sock *__inet_lookup_listener(const struct hlist_head *head, + const u32 daddr, + const unsigned short hnum, + const int dif); + +/* Optimize the common listener case. */ +static inline struct sock *inet_lookup_listener(struct inet_hashinfo *hashinfo, + const u32 daddr, + const unsigned short hnum, + const int dif) +{ + struct sock *sk = NULL; + struct hlist_head *head; + + read_lock(&hashinfo->lhash_lock); + head = &hashinfo->listening_hash[inet_lhashfn(hnum)]; + if (!hlist_empty(head)) { + const struct inet_sock *inet = inet_sk((sk = __sk_head(head))); + + if (inet->num == hnum && !sk->sk_node.next && + (!inet->rcv_saddr || inet->rcv_saddr == daddr) && + (sk->sk_family == PF_INET || !ipv6_only_sock(sk)) && + !sk->sk_bound_dev_if) + goto sherry_cache; + sk = __inet_lookup_listener(head, daddr, hnum, dif); + } + if (sk) { +sherry_cache: + sock_hold(sk); + } + read_unlock(&hashinfo->lhash_lock); + return sk; +} #endif /* _INET_HASHTABLES_H */ -- cgit v1.2.2 From 8feaf0c0a5488b3d898a9c207eb6678f44ba3f26 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:09:30 -0700 Subject: [INET]: Generalise tcp_tw_bucket, aka TIME_WAIT sockets This paves the way to generalise the rest of the sock ID lookup routines and saves some bytes in TCPv4 TIME_WAIT sockets on distro kernels (where IPv6 is always built as a module): [root@qemu ~]# grep tw_sock /proc/slabinfo tw_sock_TCPv6 0 0 128 31 1 tw_sock_TCP 0 0 96 41 1 [root@qemu ~]# Now if a protocol wants to use the TIME_WAIT generic infrastructure it only has to set the sk_prot->twsk_obj_size field with the size of its inet_timewait_sock derived sock and proto_register will create sk_prot->twsk_slab, for now its only for INET sockets, but we can introduce timewait_sock later if some non INET transport protocolo wants to use this stuff. Next changesets will take advantage of this new infrastructure to generalise even more TCP code. [acme@toy net-2.6.14]$ grep built-in /tmp/before.size /tmp/after.size /tmp/before.size: 188646 11764 5068 205478 322a6 net/ipv4/built-in.o /tmp/after.size: 188144 11764 5068 204976 320b0 net/ipv4/built-in.o [acme@toy net-2.6.14]$ Tested with both IPv4 & IPv6 (::1 (localhost) & ::ffff:172.20.0.1 (qemu host)). Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'include/net/inet_hashtables.h') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 1c4fa0065a8e..c38c637e0734 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -14,6 +14,8 @@ #ifndef _INET_HASHTABLES_H #define _INET_HASHTABLES_H +#include + #include #include #include @@ -310,4 +312,43 @@ sherry_cache: read_unlock(&hashinfo->lhash_lock); return sk; } + +/* Socket demux engine toys. */ +#ifdef __BIG_ENDIAN +#define INET_COMBINED_PORTS(__sport, __dport) \ + (((__u32)(__sport) << 16) | (__u32)(__dport)) +#else /* __LITTLE_ENDIAN */ +#define INET_COMBINED_PORTS(__sport, __dport) \ + (((__u32)(__dport) << 16) | (__u32)(__sport)) +#endif + +#if (BITS_PER_LONG == 64) +#ifdef __BIG_ENDIAN +#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \ + const __u64 __name = (((__u64)(__saddr)) << 32) | ((__u64)(__daddr)); +#else /* __LITTLE_ENDIAN */ +#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \ + const __u64 __name = (((__u64)(__daddr)) << 32) | ((__u64)(__saddr)); +#endif /* __BIG_ENDIAN */ +#define INET_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\ + (((*((__u64 *)&(inet_sk(__sk)->daddr))) == (__cookie)) && \ + ((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports)) && \ + (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) +#define INET_TW_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\ + (((*((__u64 *)&(inet_twsk(__sk)->tw_daddr))) == (__cookie)) && \ + ((*((__u32 *)&(inet_twsk(__sk)->tw_dport))) == (__ports)) && \ + (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) +#else /* 32-bit arch */ +#define INET_ADDR_COOKIE(__name, __saddr, __daddr) +#define INET_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif) \ + ((inet_sk(__sk)->daddr == (__saddr)) && \ + (inet_sk(__sk)->rcv_saddr == (__daddr)) && \ + ((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports)) && \ + (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) +#define INET_TW_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif) \ + ((inet_twsk(__sk)->tw_daddr == (__saddr)) && \ + (inet_twsk(__sk)->tw_rcv_saddr == (__daddr)) && \ + ((*((__u32 *)&(inet_twsk(__sk)->tw_dport))) == (__ports)) && \ + (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) +#endif /* 64-bit arch */ #endif /* _INET_HASHTABLES_H */ -- cgit v1.2.2 From e48c414ee61f4ac8d5cff2973e66a7cbc8a93aa5 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:09:46 -0700 Subject: [INET]: Generalise the TCP sock ID lookup routines And also some TIME_WAIT functions. [acme@toy net-2.6.14]$ grep built-in /tmp/before.size /tmp/after.size /tmp/before.size: 282955 13122 9312 305389 4a8ed net/ipv4/built-in.o /tmp/after.size: 281566 13122 9312 304000 4a380 net/ipv4/built-in.o [acme@toy net-2.6.14]$ I kept them still inlined, will uninline at some point to see what would be the performance difference. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 77 ++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 72 insertions(+), 5 deletions(-) (limited to 'include/net/inet_hashtables.h') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index c38c637e0734..b5c0d64ea741 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -30,6 +30,7 @@ #include #include +#include /* This is for all connections with a full identity, no wildcards. * New scheme, half the table is for TIME_WAIT, the other half is @@ -285,13 +286,13 @@ extern struct sock *__inet_lookup_listener(const struct hlist_head *head, const int dif); /* Optimize the common listener case. */ -static inline struct sock *inet_lookup_listener(struct inet_hashinfo *hashinfo, - const u32 daddr, - const unsigned short hnum, - const int dif) +static inline struct sock * + inet_lookup_listener(struct inet_hashinfo *hashinfo, + const u32 daddr, + const unsigned short hnum, const int dif) { struct sock *sk = NULL; - struct hlist_head *head; + const struct hlist_head *head; read_lock(&hashinfo->lhash_lock); head = &hashinfo->listening_hash[inet_lhashfn(hnum)]; @@ -351,4 +352,70 @@ sherry_cache: ((*((__u32 *)&(inet_twsk(__sk)->tw_dport))) == (__ports)) && \ (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) #endif /* 64-bit arch */ + +/* + * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need + * not check it for lookups anymore, thanks Alexey. -DaveM + * + * Local BH must be disabled here. + */ +static inline struct sock * + __inet_lookup_established(struct inet_hashinfo *hashinfo, + const u32 saddr, const u16 sport, + const u32 daddr, const u16 hnum, + const int dif) +{ + INET_ADDR_COOKIE(acookie, saddr, daddr) + const __u32 ports = INET_COMBINED_PORTS(sport, hnum); + struct sock *sk; + const struct hlist_node *node; + /* Optimize here for direct hit, only listening connections can + * have wildcards anyways. + */ + const int hash = inet_ehashfn(daddr, hnum, saddr, sport, hashinfo->ehash_size); + struct inet_ehash_bucket *head = &hashinfo->ehash[hash]; + + read_lock(&head->lock); + sk_for_each(sk, node, &head->chain) { + if (INET_MATCH(sk, acookie, saddr, daddr, ports, dif)) + goto hit; /* You sunk my battleship! */ + } + + /* Must check for a TIME_WAIT'er before going to listener hash. */ + sk_for_each(sk, node, &(head + hashinfo->ehash_size)->chain) { + if (INET_TW_MATCH(sk, acookie, saddr, daddr, ports, dif)) + goto hit; + } + sk = NULL; +out: + read_unlock(&head->lock); + return sk; +hit: + sock_hold(sk); + goto out; +} + +static inline struct sock *__inet_lookup(struct inet_hashinfo *hashinfo, + const u32 saddr, const u16 sport, + const u32 daddr, const u16 hnum, + const int dif) +{ + struct sock *sk = __inet_lookup_established(hashinfo, saddr, sport, daddr, + hnum, dif); + return sk ? : inet_lookup_listener(hashinfo, daddr, hnum, dif); +} + +static inline struct sock *inet_lookup(struct inet_hashinfo *hashinfo, + const u32 saddr, const u16 sport, + const u32 daddr, const u16 dport, + const int dif) +{ + struct sock *sk; + + local_bh_disable(); + sk = __inet_lookup(hashinfo, saddr, sport, daddr, ntohs(dport), dif); + local_bh_enable(); + + return sk; +} #endif /* _INET_HASHTABLES_H */ -- cgit v1.2.2 From 463c84b97f24010a67cd871746d6a7e4c925a5f9 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:10:42 -0700 Subject: [NET]: Introduce inet_connection_sock This creates struct inet_connection_sock, moving members out of struct tcp_sock that are shareable with other INET connection oriented protocols, such as DCCP, that in my private tree already uses most of these members. The functions that operate on these members were renamed, using a inet_csk_ prefix while not being moved yet to a new file, so as to ease the review of these changes. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/net/inet_hashtables.h') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index b5c0d64ea741..f0c21c07f894 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -17,7 +17,6 @@ #include #include -#include #include #include #include @@ -26,6 +25,7 @@ #include #include +#include #include #include @@ -185,9 +185,9 @@ static inline void __inet_inherit_port(struct inet_hashinfo *table, struct inet_bind_bucket *tb; spin_lock(&head->lock); - tb = inet_sk(sk)->bind_hash; + tb = inet_csk(sk)->icsk_bind_hash; sk_add_bind_node(child, &tb->owners); - inet_sk(child)->bind_hash = tb; + inet_csk(child)->icsk_bind_hash = tb; spin_unlock(&head->lock); } -- cgit v1.2.2 From 0a5578cf8e5e045aaa68643c17ce885426697c6b Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2005 20:11:41 -0700 Subject: [ICSK]: Generalise tcp_listen_{start,stop} This also moved inet_iif from tcp to inet_hashtables.h, as it is needed by the inet_lookup callers, perhaps this needs a bit of polishing, but for now seems fine. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/net/inet_hashtables.h') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index f0c21c07f894..646b6ea7fe26 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -26,6 +26,7 @@ #include #include +#include #include #include @@ -280,6 +281,11 @@ out: wake_up(&hashinfo->lhash_wait); } +static inline int inet_iif(const struct sk_buff *skb) +{ + return ((struct rtable *)skb->dst)->rt_iif; +} + extern struct sock *__inet_lookup_listener(const struct hlist_head *head, const u32 daddr, const unsigned short hnum, -- cgit v1.2.2