X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=include%2Fnet%2Fsock.h;h=06c5259aff30354dc1005444734441796fc895db;hb=ad0e9e01da4ece70ff524b49c77c5e850d5dd53e;hp=3d938f6c672558bab4ef59e52c491ff481f07385;hpb=3ab224be6d69de912ee21302745ea45a99274dbc;p=safe%2Fjmp%2Flinux-2.6 diff --git a/include/net/sock.h b/include/net/sock.h index 3d938f6..06c5259 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -47,7 +47,6 @@ #include #include #include -#include #include /* struct sk_buff */ #include #include @@ -70,7 +69,11 @@ #define SOCK_DEBUG(sk, msg...) do { if ((sk) && sock_flag((sk), SOCK_DBG)) \ printk(KERN_DEBUG msg); } while (0) #else -#define SOCK_DEBUG(sk, msg...) do { } while (0) +/* Validate arguments and do nothing */ +static void inline int __attribute__ ((format (printf, 2, 3))) +SOCK_DEBUG(struct sock *sk, const char *msg, ...) +{ +} #endif /* This is the per-socket lock. The spinlock provides a synchronization @@ -122,7 +125,9 @@ struct sock_common { atomic_t skc_refcnt; unsigned int skc_hash; struct proto *skc_prot; +#ifdef CONFIG_NET_NS struct net *skc_net; +#endif }; /** @@ -151,6 +156,7 @@ struct sock_common { * @sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) * @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4) + * @sk_gso_max_size: Maximum GSO segment size to build * @sk_lingertime: %SO_LINGER l_linger setting * @sk_backlog: always used with the per-socket spinlock held * @sk_callback_lock: used with the callbacks in the end of this struct @@ -160,7 +166,7 @@ struct sock_common { * @sk_err: last error * @sk_err_soft: errors that don't cause failure but are the cause of a * persistent failure not just 'timed out' - * @sk_drops: raw drops counter + * @sk_drops: raw/udp drops counter * @sk_ack_backlog: current listen backlog * @sk_max_ack_backlog: listen backlog set in listen() * @sk_priority: %SO_PRIORITY setting @@ -180,6 +186,7 @@ struct sock_common { * @sk_sndmsg_off: cached offset for sendmsg * @sk_send_head: front of stuff to transmit * @sk_security: used by security modules + * @sk_mark: generic packet mark * @sk_write_pending: a write to stream socket waits to start * @sk_state_change: callback to indicate change in the state of the sock * @sk_data_ready: callback to indicate there is data to be processed @@ -236,6 +243,7 @@ struct sock { gfp_t sk_allocation; int sk_route_caps; int sk_gso_type; + unsigned int sk_gso_max_size; int sk_rcvlowat; unsigned long sk_flags; unsigned long sk_lingertime; @@ -262,6 +270,8 @@ struct sock { __u32 sk_sndmsg_off; int sk_write_pending; void *sk_security; + __u32 sk_mark; + /* XXX 4 bytes hole on 64 bit */ void (*sk_state_change)(struct sock *sk); void (*sk_data_ready)(struct sock *sk, int bytes); void (*sk_write_space)(struct sock *sk); @@ -494,6 +504,8 @@ extern int sk_wait_data(struct sock *sk, long *timeo); struct request_sock_ops; struct timewait_sock_ops; +struct inet_hashinfo; +struct raw_hashinfo; /* Networking protocol blocks we attach to sockets. * socket layer -> transport layer interface @@ -512,7 +524,7 @@ struct proto { int (*ioctl)(struct sock *sk, int cmd, unsigned long arg); int (*init)(struct sock *sk); - int (*destroy)(struct sock *sk); + void (*destroy)(struct sock *sk); void (*shutdown)(struct sock *sk, int how); int (*setsockopt)(struct sock *sk, int level, int optname, char __user *optval, @@ -548,10 +560,12 @@ struct proto { int (*get_port)(struct sock *sk, unsigned short snum); /* Keeping track of sockets in use */ - struct pcounter inuse; +#ifdef CONFIG_PROC_FS + unsigned int inuse_idx; +#endif /* Memory pressure */ - void (*enter_memory_pressure)(void); + void (*enter_memory_pressure)(struct sock *sk); atomic_t *memory_allocated; /* Current allocated memory. */ atomic_t *sockets_allocated; /* Current number of sockets. */ /* @@ -574,6 +588,12 @@ struct proto { struct request_sock_ops *rsk_prot; struct timewait_sock_ops *twsk_prot; + union { + struct inet_hashinfo *hashinfo; + struct hlist_head *udp_hash; + struct raw_hashinfo *raw_hash; + } h; + struct module *owner; char name[32]; @@ -584,9 +604,6 @@ struct proto { #endif }; -#define DEFINE_PROTO_INUSE(NAME) DEFINE_PCOUNTER(NAME) -#define REF_PROTO_INUSE(NAME) PCOUNTER_MEMBER_INITIALIZER(NAME, .inuse) - extern int proto_register(struct proto *prot, int alloc_slab); extern void proto_unregister(struct proto *prot); @@ -615,21 +632,18 @@ static inline void sk_refcnt_debug_release(const struct sock *sk) #define sk_refcnt_debug_release(sk) do { } while (0) #endif /* SOCK_REFCNT_DEBUG */ -/* Called with local bh disabled */ -static __inline__ void sock_prot_inc_use(struct proto *prot) -{ - pcounter_add(&prot->inuse, 1); -} -static __inline__ void sock_prot_dec_use(struct proto *prot) +#ifdef CONFIG_PROC_FS +/* Called with local bh disabled */ +extern void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc); +extern int sock_prot_inuse_get(struct net *net, struct proto *proto); +#else +static void inline sock_prot_inuse_add(struct net *net, struct proto *prot, + int inc) { - pcounter_add(&prot->inuse, -1); } +#endif -static __inline__ int sock_prot_inuse(struct proto *proto) -{ - return pcounter_getval(&proto->inuse); -} /* With per-bucket locks this operation is not-atomic, so that * this version is not worse. @@ -739,6 +753,14 @@ static inline void sk_mem_reclaim(struct sock *sk) __sk_mem_reclaim(sk); } +static inline void sk_mem_reclaim_partial(struct sock *sk) +{ + if (!sk_has_account(sk)) + return; + if (sk->sk_forward_alloc > SK_MEM_QUANTUM) + __sk_mem_reclaim(sk); +} + static inline void sk_mem_charge(struct sock *sk, int size) { if (!sk_has_account(sk)) @@ -816,6 +838,7 @@ extern struct sock *sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot); extern void sk_free(struct sock *sk); +extern void sk_release_kernel(struct sock *sk); extern struct sock *sk_clone(const struct sock *sk, const gfp_t priority); @@ -905,41 +928,6 @@ extern void sk_common_release(struct sock *sk); extern void sock_init_data(struct socket *sock, struct sock *sk); /** - * sk_filter - run a packet through a socket filter - * @sk: sock associated with &sk_buff - * @skb: buffer to filter - * @needlock: set to 1 if the sock is not locked by caller. - * - * Run the filter code and then cut skb->data to correct size returned by - * sk_run_filter. If pkt_len is 0 we toss packet. If skb->len is smaller - * than pkt_len we keep whole skb->data. This is the socket level - * wrapper to sk_run_filter. It returns 0 if the packet should - * be accepted or -EPERM if the packet should be tossed. - * - */ - -static inline int sk_filter(struct sock *sk, struct sk_buff *skb) -{ - int err; - struct sk_filter *filter; - - err = security_sock_rcv_skb(sk, skb); - if (err) - return err; - - rcu_read_lock_bh(); - filter = rcu_dereference(sk->sk_filter); - if (filter) { - unsigned int pkt_len = sk_run_filter(skb, filter->insns, - filter->len); - err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM; - } - rcu_read_unlock_bh(); - - return err; -} - -/** * sk_filter_release: Release a socket filter * @sk: socket * @fp: filter to remove @@ -1002,6 +990,11 @@ static inline void sock_put(struct sock *sk) extern int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested); +static inline void sk_set_socket(struct sock *sk, struct socket *sock) +{ + sk->sk_socket = sock; +} + /* Detach socket from process context. * Announce socket dead, detach it from wait queue and inode. * Note that parent inode held reference count on this struct sock, @@ -1013,7 +1006,7 @@ static inline void sock_orphan(struct sock *sk) { write_lock_bh(&sk->sk_callback_lock); sock_set_flag(sk, SOCK_DEAD); - sk->sk_socket = NULL; + sk_set_socket(sk, NULL); sk->sk_sleep = NULL; write_unlock_bh(&sk->sk_callback_lock); } @@ -1023,7 +1016,7 @@ static inline void sock_graft(struct sock *sk, struct socket *parent) write_lock_bh(&sk->sk_callback_lock); sk->sk_sleep = &parent->wait; parent->sk = sk; - sk->sk_socket = parent; + sk_set_socket(sk, parent); security_sock_graft(sk, parent); write_unlock_bh(&sk->sk_callback_lock); } @@ -1217,7 +1210,7 @@ static inline struct page *sk_stream_alloc_page(struct sock *sk) page = alloc_pages(sk->sk_allocation, 0); if (!page) { - sk->sk_prot->enter_memory_pressure(); + sk->sk_prot->enter_memory_pressure(sk); sk_stream_moderate_sndbuf(sk); } return page; @@ -1299,6 +1292,36 @@ static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb, int copied_e } #endif +static inline +struct net *sock_net(const struct sock *sk) +{ +#ifdef CONFIG_NET_NS + return sk->sk_net; +#else + return &init_net; +#endif +} + +static inline +void sock_net_set(struct sock *sk, struct net *net) +{ +#ifdef CONFIG_NET_NS + sk->sk_net = net; +#endif +} + +/* + * Kernel sockets, f.e. rtnl or icmp_socket, are a part of a namespace. + * They should not hold a referrence to a namespace in order to allow + * to stop it. + * Sockets after sk_change_net should be released using sk_release_kernel + */ +static inline void sk_change_net(struct sock *sk, struct net *net) +{ + put_net(sock_net(sk)); + sock_net_set(sk, hold_net(net)); +} + extern void sock_enable_timestamp(struct sock *sk); extern int sock_get_timestamp(struct sock *, struct timeval __user *); extern int sock_get_timestampns(struct sock *, struct timespec __user *); @@ -1313,30 +1336,6 @@ extern int net_msg_warn; #define LIMIT_NETDEBUG(fmt, args...) \ do { if (net_msg_warn && net_ratelimit()) printk(fmt,##args); } while(0) -/* - * Macros for sleeping on a socket. Use them like this: - * - * SOCK_SLEEP_PRE(sk) - * if (condition) - * schedule(); - * SOCK_SLEEP_POST(sk) - * - * N.B. These are now obsolete and were, afaik, only ever used in DECnet - * and when the last use of them in DECnet has gone, I'm intending to - * remove them. - */ - -#define SOCK_SLEEP_PRE(sk) { struct task_struct *tsk = current; \ - DECLARE_WAITQUEUE(wait, tsk); \ - tsk->state = TASK_INTERRUPTIBLE; \ - add_wait_queue((sk)->sk_sleep, &wait); \ - release_sock(sk); - -#define SOCK_SLEEP_POST(sk) tsk->state = TASK_RUNNING; \ - remove_wait_queue((sk)->sk_sleep, &wait); \ - lock_sock(sk); \ - } - extern __u32 sysctl_wmem_max; extern __u32 sysctl_rmem_max;