X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=include%2Fnet%2Fsock.h;h=aed16eb9db4bc7e9196a829ce1531f9e6aef3dd7;hb=a465419b1febb603821f924805529cff89cafeed;hp=1c9d059223ee518a1934cf69b59b1eae76dc4ed4;hpb=f5aa23fd49063745f85644dd7a9330acd706add6;p=safe%2Fjmp%2Flinux-2.6 diff --git a/include/net/sock.h b/include/net/sock.h index 1c9d059..aed16eb 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -42,17 +42,20 @@ #include #include +#include #include #include #include #include #include -#include #include /* struct sk_buff */ #include #include +#include #include +#include +#include #include #include @@ -71,7 +74,7 @@ printk(KERN_DEBUG msg); } while (0) #else /* Validate arguments and do nothing */ -static void inline int __attribute__ ((format (printf, 2, 3))) +static inline void __attribute__ ((format (printf, 2, 3))) SOCK_DEBUG(struct sock *sk, const char *msg, ...) { } @@ -102,14 +105,18 @@ struct net; /** * struct sock_common - minimal network layer representation of sockets + * @skc_node: main hash linkage for various protocol lookup tables + * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol + * @skc_refcnt: reference count + * @skc_tx_queue_mapping: tx queue number for this connection + * @skc_hash: hash value used with various protocol lookup tables + * @skc_u16hashes: two u16 hash values used by UDP lookup tables * @skc_family: network address family * @skc_state: Connection state * @skc_reuse: %SO_REUSEADDR setting * @skc_bound_dev_if: bound device index if != 0 - * @skc_node: main hash linkage for various protocol lookup tables * @skc_bind_node: bind hash linkage for various protocol lookup tables - * @skc_refcnt: reference count - * @skc_hash: hash value used with various protocol lookup tables + * @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol * @skc_prot: protocol handlers inside a network family * @skc_net: reference to the network namespace of this socket * @@ -117,14 +124,28 @@ struct net; * for struct sock and struct inet_timewait_sock. */ struct sock_common { + /* + * first fields are not copied in sock_copy() + */ + union { + struct hlist_node skc_node; + struct hlist_nulls_node skc_nulls_node; + }; + atomic_t skc_refcnt; + int skc_tx_queue_mapping; + + union { + unsigned int skc_hash; + __u16 skc_u16hashes[2]; + }; unsigned short skc_family; volatile unsigned char skc_state; unsigned char skc_reuse; int skc_bound_dev_if; - struct hlist_node skc_node; - struct hlist_node skc_bind_node; - atomic_t skc_refcnt; - unsigned int skc_hash; + union { + struct hlist_node skc_bind_node; + struct hlist_nulls_node skc_portaddr_node; + }; struct proto *skc_prot; #ifdef CONFIG_NET_NS struct net *skc_net; @@ -138,7 +159,7 @@ struct sock_common { * @sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings * @sk_lock: synchronizer * @sk_rcvbuf: size of receive buffer in bytes - * @sk_sleep: sock wait queue + * @sk_wq: sock wait queue and async head * @sk_dst_cache: destination cache * @sk_dst_lock: destination cache lock * @sk_policy: flow policy @@ -153,9 +174,10 @@ struct sock_common { * @sk_allocation: allocation mode * @sk_sndbuf: size of send buffer in bytes * @sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, - * %SO_OOBINLINE settings + * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings * @sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) + * @sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK) * @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 @@ -167,7 +189,7 @@ 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 @@ -177,6 +199,7 @@ struct sock_common { * @sk_rcvlowat: %SO_RCVLOWAT setting * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting + * @sk_rxhash: flow hash received from netif layer * @sk_filter: socket filtering instructions * @sk_protinfo: private area, net family specific, when not using slab * @sk_timer: sock cleanup timer @@ -202,21 +225,27 @@ struct sock { * don't add nothing before this first member (__sk_common) --acme */ struct sock_common __sk_common; +#define sk_node __sk_common.skc_node +#define sk_nulls_node __sk_common.skc_nulls_node +#define sk_refcnt __sk_common.skc_refcnt +#define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping + +#define sk_copy_start __sk_common.skc_hash +#define sk_hash __sk_common.skc_hash #define sk_family __sk_common.skc_family #define sk_state __sk_common.skc_state #define sk_reuse __sk_common.skc_reuse #define sk_bound_dev_if __sk_common.skc_bound_dev_if -#define sk_node __sk_common.skc_node #define sk_bind_node __sk_common.skc_bind_node -#define sk_refcnt __sk_common.skc_refcnt -#define sk_hash __sk_common.skc_hash #define sk_prot __sk_common.skc_prot #define sk_net __sk_common.skc_net - unsigned char sk_shutdown : 2, - sk_no_check : 2, - sk_userlocks : 4; - unsigned char sk_protocol; - unsigned short sk_type; + kmemcheck_bitfield_begin(flags); + unsigned int sk_shutdown : 2, + sk_no_check : 2, + sk_userlocks : 4, + sk_protocol : 8, + sk_type : 16; + kmemcheck_bitfield_end(flags); int sk_rcvbuf; socket_lock_t sk_lock; /* @@ -227,25 +256,34 @@ struct sock { struct { struct sk_buff *head; struct sk_buff *tail; + int len; } sk_backlog; - wait_queue_head_t *sk_sleep; + struct socket_wq *sk_wq; struct dst_entry *sk_dst_cache; +#ifdef CONFIG_XFRM struct xfrm_policy *sk_policy[2]; - rwlock_t sk_dst_lock; +#endif + spinlock_t sk_dst_lock; atomic_t sk_rmem_alloc; atomic_t sk_wmem_alloc; atomic_t sk_omem_alloc; int sk_sndbuf; struct sk_buff_head sk_receive_queue; struct sk_buff_head sk_write_queue; +#ifdef CONFIG_NET_DMA struct sk_buff_head sk_async_wait_queue; +#endif int sk_wmem_queued; int sk_forward_alloc; gfp_t sk_allocation; int sk_route_caps; + int sk_route_nocaps; int sk_gso_type; unsigned int sk_gso_max_size; int sk_rcvlowat; +#ifdef CONFIG_RPS + __u32 sk_rxhash; +#endif unsigned long sk_flags; unsigned long sk_lingertime; struct sk_buff_head sk_error_queue; @@ -270,7 +308,9 @@ struct sock { struct sk_buff *sk_send_head; __u32 sk_sndmsg_off; int sk_write_pending; +#ifdef CONFIG_SECURITY void *sk_security; +#endif __u32 sk_mark; /* XXX 4 bytes hole on 64 bit */ void (*sk_state_change)(struct sock *sk); @@ -285,6 +325,11 @@ struct sock { /* * Hashed lists helper routines */ +static inline struct sock *sk_entry(const struct hlist_node *node) +{ + return hlist_entry(node, struct sock, sk_node); +} + static inline struct sock *__sk_head(const struct hlist_head *head) { return hlist_entry(head->first, struct sock, sk_node); @@ -295,12 +340,30 @@ static inline struct sock *sk_head(const struct hlist_head *head) return hlist_empty(head) ? NULL : __sk_head(head); } +static inline struct sock *__sk_nulls_head(const struct hlist_nulls_head *head) +{ + return hlist_nulls_entry(head->first, struct sock, sk_nulls_node); +} + +static inline struct sock *sk_nulls_head(const struct hlist_nulls_head *head) +{ + return hlist_nulls_empty(head) ? NULL : __sk_nulls_head(head); +} + static inline struct sock *sk_next(const struct sock *sk) { return sk->sk_node.next ? hlist_entry(sk->sk_node.next, struct sock, sk_node) : NULL; } +static inline struct sock *sk_nulls_next(const struct sock *sk) +{ + return (!is_a_nulls(sk->sk_nulls_node.next)) ? + hlist_nulls_entry(sk->sk_nulls_node.next, + struct sock, sk_nulls_node) : + NULL; +} + static inline int sk_unhashed(const struct sock *sk) { return hlist_unhashed(&sk->sk_node); @@ -316,11 +379,17 @@ static __inline__ void sk_node_init(struct hlist_node *node) node->pprev = NULL; } +static __inline__ void sk_nulls_node_init(struct hlist_nulls_node *node) +{ + node->pprev = NULL; +} + static __inline__ void __sk_del_node(struct sock *sk) { __hlist_del(&sk->sk_node); } +/* NB: equivalent to hlist_del_init_rcu */ static __inline__ int __sk_del_node_init(struct sock *sk) { if (sk_hashed(sk)) { @@ -361,6 +430,28 @@ static __inline__ int sk_del_node_init(struct sock *sk) } return rc; } +#define sk_del_node_init_rcu(sk) sk_del_node_init(sk) + +static __inline__ int __sk_nulls_del_node_init_rcu(struct sock *sk) +{ + if (sk_hashed(sk)) { + hlist_nulls_del_init_rcu(&sk->sk_nulls_node); + return 1; + } + return 0; +} + +static __inline__ int sk_nulls_del_node_init_rcu(struct sock *sk) +{ + int rc = __sk_nulls_del_node_init_rcu(sk); + + if (rc) { + /* paranoid for a while -acme */ + WARN_ON(atomic_read(&sk->sk_refcnt) == 1); + __sock_put(sk); + } + return rc; +} static __inline__ void __sk_add_node(struct sock *sk, struct hlist_head *list) { @@ -373,6 +464,23 @@ static __inline__ void sk_add_node(struct sock *sk, struct hlist_head *list) __sk_add_node(sk, list); } +static __inline__ void sk_add_node_rcu(struct sock *sk, struct hlist_head *list) +{ + sock_hold(sk); + hlist_add_head_rcu(&sk->sk_node, list); +} + +static __inline__ void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) +{ + hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list); +} + +static __inline__ void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) +{ + sock_hold(sk); + __sk_nulls_add_node_rcu(sk, list); +} + static __inline__ void __sk_del_bind_node(struct sock *sk) { __hlist_del(&sk->sk_bind_node); @@ -386,9 +494,18 @@ static __inline__ void sk_add_bind_node(struct sock *sk, #define sk_for_each(__sk, node, list) \ hlist_for_each_entry(__sk, node, list, sk_node) +#define sk_for_each_rcu(__sk, node, list) \ + hlist_for_each_entry_rcu(__sk, node, list, sk_node) +#define sk_nulls_for_each(__sk, node, list) \ + hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node) +#define sk_nulls_for_each_rcu(__sk, node, list) \ + hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node) #define sk_for_each_from(__sk, node) \ if (__sk && ({ node = &(__sk)->sk_node; 1; })) \ hlist_for_each_entry_from(__sk, node, sk_node) +#define sk_nulls_for_each_from(__sk, node) \ + if (__sk && ({ node = &(__sk)->sk_nulls_node; 1; })) \ + hlist_nulls_for_each_entry_from(__sk, node, sk_nulls_node) #define sk_for_each_continue(__sk, node) \ if (__sk && ({ node = &(__sk)->sk_node; 1; })) \ hlist_for_each_entry_continue(__sk, node, sk_node) @@ -414,6 +531,15 @@ enum sock_flags { SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */ SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */ SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */ + SOCK_TIMESTAMPING_TX_HARDWARE, /* %SOF_TIMESTAMPING_TX_HARDWARE */ + SOCK_TIMESTAMPING_TX_SOFTWARE, /* %SOF_TIMESTAMPING_TX_SOFTWARE */ + SOCK_TIMESTAMPING_RX_HARDWARE, /* %SOF_TIMESTAMPING_RX_HARDWARE */ + SOCK_TIMESTAMPING_RX_SOFTWARE, /* %SOF_TIMESTAMPING_RX_SOFTWARE */ + SOCK_TIMESTAMPING_SOFTWARE, /* %SOF_TIMESTAMPING_SOFTWARE */ + SOCK_TIMESTAMPING_RAW_HARDWARE, /* %SOF_TIMESTAMPING_RAW_HARDWARE */ + SOCK_TIMESTAMPING_SYS_HARDWARE, /* %SOF_TIMESTAMPING_SYS_HARDWARE */ + SOCK_FASYNC, /* fasync() active */ + SOCK_RXQ_OVFL, }; static inline void sock_copy_flags(struct sock *nsk, struct sock *osk) @@ -471,8 +597,8 @@ static inline int sk_stream_memory_free(struct sock *sk) return sk->sk_wmem_queued < sk->sk_sndbuf; } -/* The per-socket spinlock must be held here. */ -static inline void sk_add_backlog(struct sock *sk, struct sk_buff *skb) +/* OOB backlog add */ +static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) { if (!sk->sk_backlog.tail) { sk->sk_backlog.head = sk->sk_backlog.tail = skb; @@ -483,6 +609,66 @@ static inline void sk_add_backlog(struct sock *sk, struct sk_buff *skb) skb->next = NULL; } +/* + * Take into account size of receive queue and backlog queue + */ +static inline bool sk_rcvqueues_full(const struct sock *sk, const struct sk_buff *skb) +{ + unsigned int qsize = sk->sk_backlog.len + atomic_read(&sk->sk_rmem_alloc); + + return qsize + skb->truesize > sk->sk_rcvbuf; +} + +/* The per-socket spinlock must be held here. */ +static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *skb) +{ + if (sk_rcvqueues_full(sk, skb)) + return -ENOBUFS; + + __sk_add_backlog(sk, skb); + sk->sk_backlog.len += skb->truesize; + return 0; +} + +static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) +{ + return sk->sk_backlog_rcv(sk, skb); +} + +static inline void sock_rps_record_flow(const struct sock *sk) +{ +#ifdef CONFIG_RPS + struct rps_sock_flow_table *sock_flow_table; + + rcu_read_lock(); + sock_flow_table = rcu_dereference(rps_sock_flow_table); + rps_record_sock_flow(sock_flow_table, sk->sk_rxhash); + rcu_read_unlock(); +#endif +} + +static inline void sock_rps_reset_flow(const struct sock *sk) +{ +#ifdef CONFIG_RPS + struct rps_sock_flow_table *sock_flow_table; + + rcu_read_lock(); + sock_flow_table = rcu_dereference(rps_sock_flow_table); + rps_reset_sock_flow(sock_flow_table, sk->sk_rxhash); + rcu_read_unlock(); +#endif +} + +static inline void sock_rps_save_rxhash(struct sock *sk, u32 rxhash) +{ +#ifdef CONFIG_RPS + if (unlikely(sk->sk_rxhash != rxhash)) { + sock_rps_reset_flow(sk); + sk->sk_rxhash = rxhash; + } +#endif +} + #define sk_wait_event(__sk, __timeo, __condition) \ ({ int __rc; \ release_sock(__sk); \ @@ -525,22 +711,24 @@ 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, - int optlen); + unsigned int optlen); int (*getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *option); +#ifdef CONFIG_COMPAT int (*compat_setsockopt)(struct sock *sk, int level, int optname, char __user *optval, - int optlen); + unsigned int optlen); int (*compat_getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *option); +#endif int (*sendmsg)(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len); int (*recvmsg)(struct kiocb *iocb, struct sock *sk, @@ -562,13 +750,13 @@ struct proto { /* Keeping track of sockets in use */ #ifdef CONFIG_PROC_FS - struct pcounter inuse; + 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. */ + struct percpu_counter *sockets_allocated; /* Current number of sockets. */ /* * Pressure flag: try to collapse. * Technical note: it is used by multiple contexts non atomically. @@ -581,17 +769,18 @@ struct proto { int *sysctl_rmem; int max_header; - struct kmem_cache *slab; + struct kmem_cache *slab; unsigned int obj_size; + int slab_flags; - atomic_t *orphan_count; + struct percpu_counter *orphan_count; struct request_sock_ops *rsk_prot; struct timewait_sock_ops *twsk_prot; union { struct inet_hashinfo *hashinfo; - struct hlist_head *udp_hash; + struct udp_table *udp_table; struct raw_hashinfo *raw_hash; } h; @@ -635,36 +824,12 @@ static inline void sk_refcnt_debug_release(const struct sock *sk) #ifdef CONFIG_PROC_FS -# define DEFINE_PROTO_INUSE(NAME) DEFINE_PCOUNTER(NAME) -# define REF_PROTO_INUSE(NAME) PCOUNTER_MEMBER_INITIALIZER(NAME, .inuse) /* Called with local bh disabled */ -static inline void sock_prot_inuse_add(struct proto *prot, int inc) -{ - pcounter_add(&prot->inuse, inc); -} -static inline int sock_prot_inuse_init(struct proto *proto) -{ - return pcounter_alloc(&proto->inuse); -} -static inline int sock_prot_inuse_get(struct proto *proto) -{ - return pcounter_getval(&proto->inuse); -} -static inline void sock_prot_inuse_free(struct proto *proto) -{ - pcounter_free(&proto->inuse); -} +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 -# define DEFINE_PROTO_INUSE(NAME) -# define REF_PROTO_INUSE(NAME) -static void inline sock_prot_inuse_add(struct proto *prot, int inc) -{ -} -static int inline sock_prot_inuse_init(struct proto *proto) -{ - return 0; -} -static void inline sock_prot_inuse_free(struct proto *proto) +static void inline sock_prot_inuse_add(struct net *net, struct proto *prot, + int inc) { } #endif @@ -802,7 +967,6 @@ static inline void sk_mem_uncharge(struct sock *sk, int size) static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { - skb_truesize_check(skb); sock_set_flag(sk, SOCK_QUEUE_SHRUNK); sk->sk_wmem_queued -= skb->truesize; sk_mem_uncharge(sk, skb->truesize); @@ -833,7 +997,7 @@ static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb) */ #define sock_lock_init_class_and_name(sk, sname, skey, name, key) \ do { \ - sk->sk_lock.owned = 0; \ + sk->sk_lock.owned = 0; \ init_waitqueue_head(&sk->sk_lock.wq); \ spin_lock_init(&(sk)->sk_lock.slock); \ debug_check_no_locks_freed((void *)&(sk)->sk_lock, \ @@ -859,6 +1023,16 @@ extern void release_sock(struct sock *sk); SINGLE_DEPTH_NESTING) #define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock)) +static inline void lock_sock_bh(struct sock *sk) +{ + spin_lock_bh(&sk->sk_lock.slock); +} + +static inline void unlock_sock_bh(struct sock *sk) +{ + spin_unlock_bh(&sk->sk_lock.slock); +} + extern struct sock *sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot); @@ -878,7 +1052,7 @@ extern void sock_rfree(struct sk_buff *skb); extern int sock_setsockopt(struct socket *sock, int level, int op, char __user *optval, - int optlen); + unsigned int optlen); extern int sock_getsockopt(struct socket *sock, int level, int op, char __user *optval, @@ -887,6 +1061,11 @@ extern struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, int noblock, int *errcode); +extern struct sk_buff *sock_alloc_send_pskb(struct sock *sk, + unsigned long header_len, + unsigned long data_len, + int noblock, + int *errcode); extern void *sock_kmalloc(struct sock *sk, int size, gfp_t priority); extern void sock_kfree_s(struct sock *sk, void *mem, int size); @@ -915,7 +1094,7 @@ extern int sock_no_shutdown(struct socket *, int); extern int sock_no_getsockopt(struct socket *, int , int, char __user *, int __user *); extern int sock_no_setsockopt(struct socket *, int, int, - char __user *, int); + char __user *, unsigned int); extern int sock_no_sendmsg(struct kiocb *, struct socket *, struct msghdr *, size_t); extern int sock_no_recvmsg(struct kiocb *, struct socket *, @@ -937,11 +1116,11 @@ extern int sock_common_getsockopt(struct socket *sock, int level, int optname, extern int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size, int flags); extern int sock_common_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); extern int compat_sock_common_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); extern int compat_sock_common_setsockopt(struct socket *sock, int level, - int optname, char __user *optval, int optlen); + int optname, char __user *optval, unsigned int optlen); extern void sk_common_release(struct sock *sk); @@ -953,43 +1132,7 @@ 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 + * sk_filter_release - release a socket filter * @fp: filter to remove * * Remove a filter from a socket and release its resources. @@ -1050,6 +1193,36 @@ 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_tx_queue_set(struct sock *sk, int tx_queue) +{ + sk->sk_tx_queue_mapping = tx_queue; +} + +static inline void sk_tx_queue_clear(struct sock *sk) +{ + sk->sk_tx_queue_mapping = -1; +} + +static inline int sk_tx_queue_get(const struct sock *sk) +{ + return sk->sk_tx_queue_mapping; +} + +static inline bool sk_tx_queue_recorded(const struct sock *sk) +{ + return (sk && sk->sk_tx_queue_mapping >= 0); +} + +static inline void sk_set_socket(struct sock *sk, struct socket *sock) +{ + sk_tx_queue_clear(sk); + sk->sk_socket = sock; +} + +static inline wait_queue_head_t *sk_sleep(struct sock *sk) +{ + return &sk->sk_wq->wait; +} /* 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, @@ -1061,17 +1234,17 @@ 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->sk_sleep = NULL; + sk_set_socket(sk, NULL); + sk->sk_wq = NULL; write_unlock_bh(&sk->sk_callback_lock); } static inline void sock_graft(struct sock *sk, struct socket *parent) { write_lock_bh(&sk->sk_callback_lock); - sk->sk_sleep = &parent->wait; + rcu_assign_pointer(sk->sk_wq, parent->wq); parent->sk = sk; - sk->sk_socket = parent; + sk_set_socket(sk, parent); security_sock_graft(sk, parent); write_unlock_bh(&sk->sk_callback_lock); } @@ -1082,7 +1255,9 @@ extern unsigned long sock_i_ino(struct sock *sk); static inline struct dst_entry * __sk_dst_get(struct sock *sk) { - return sk->sk_dst_cache; + return rcu_dereference_check(sk->sk_dst_cache, rcu_read_lock_held() || + sock_owned_by_user(sk) || + lockdep_is_held(&sk->sk_lock.slock)); } static inline struct dst_entry * @@ -1090,48 +1265,65 @@ sk_dst_get(struct sock *sk) { struct dst_entry *dst; - read_lock(&sk->sk_dst_lock); - dst = sk->sk_dst_cache; + rcu_read_lock(); + dst = rcu_dereference(sk->sk_dst_cache); if (dst) dst_hold(dst); - read_unlock(&sk->sk_dst_lock); + rcu_read_unlock(); return dst; } +extern void sk_reset_txq(struct sock *sk); + +static inline void dst_negative_advice(struct sock *sk) +{ + struct dst_entry *ndst, *dst = __sk_dst_get(sk); + + if (dst && dst->ops->negative_advice) { + ndst = dst->ops->negative_advice(dst); + + if (ndst != dst) { + rcu_assign_pointer(sk->sk_dst_cache, ndst); + sk_reset_txq(sk); + } + } +} + static inline void __sk_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old_dst; - old_dst = sk->sk_dst_cache; - sk->sk_dst_cache = dst; + sk_tx_queue_clear(sk); + /* + * This can be called while sk is owned by the caller only, + * with no state that can be checked in a rcu_dereference_check() cond + */ + old_dst = rcu_dereference_raw(sk->sk_dst_cache); + rcu_assign_pointer(sk->sk_dst_cache, dst); dst_release(old_dst); } static inline void sk_dst_set(struct sock *sk, struct dst_entry *dst) { - write_lock(&sk->sk_dst_lock); + spin_lock(&sk->sk_dst_lock); __sk_dst_set(sk, dst); - write_unlock(&sk->sk_dst_lock); + spin_unlock(&sk->sk_dst_lock); } static inline void __sk_dst_reset(struct sock *sk) { - struct dst_entry *old_dst; - - old_dst = sk->sk_dst_cache; - sk->sk_dst_cache = NULL; - dst_release(old_dst); + __sk_dst_set(sk, NULL); } static inline void sk_dst_reset(struct sock *sk) { - write_lock(&sk->sk_dst_lock); + spin_lock(&sk->sk_dst_lock); __sk_dst_reset(sk); - write_unlock(&sk->sk_dst_lock); + spin_unlock(&sk->sk_dst_lock); } extern struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie); @@ -1145,6 +1337,12 @@ static inline int sk_can_gso(const struct sock *sk) extern void sk_setup_caps(struct sock *sk, struct dst_entry *dst); +static inline void sk_nocaps_add(struct sock *sk, int flags) +{ + sk->sk_route_nocaps |= flags; + sk->sk_route_caps &= ~flags; +} + static inline int skb_copy_to_page(struct sock *sk, char __user *from, struct sk_buff *skb, struct page *page, int off, int copy) @@ -1168,6 +1366,107 @@ static inline int skb_copy_to_page(struct sock *sk, char __user *from, return 0; } +/** + * sk_wmem_alloc_get - returns write allocations + * @sk: socket + * + * Returns sk_wmem_alloc minus initial offset of one + */ +static inline int sk_wmem_alloc_get(const struct sock *sk) +{ + return atomic_read(&sk->sk_wmem_alloc) - 1; +} + +/** + * sk_rmem_alloc_get - returns read allocations + * @sk: socket + * + * Returns sk_rmem_alloc + */ +static inline int sk_rmem_alloc_get(const struct sock *sk) +{ + return atomic_read(&sk->sk_rmem_alloc); +} + +/** + * sk_has_allocations - check if allocations are outstanding + * @sk: socket + * + * Returns true if socket has write or read allocations + */ +static inline int sk_has_allocations(const struct sock *sk) +{ + return sk_wmem_alloc_get(sk) || sk_rmem_alloc_get(sk); +} + +/** + * wq_has_sleeper - check if there are any waiting processes + * @sk: struct socket_wq + * + * Returns true if socket_wq has waiting processes + * + * The purpose of the wq_has_sleeper and sock_poll_wait is to wrap the memory + * barrier call. They were added due to the race found within the tcp code. + * + * Consider following tcp code paths: + * + * CPU1 CPU2 + * + * sys_select receive packet + * ... ... + * __add_wait_queue update tp->rcv_nxt + * ... ... + * tp->rcv_nxt check sock_def_readable + * ... { + * schedule rcu_read_lock(); + * wq = rcu_dereference(sk->sk_wq); + * if (wq && waitqueue_active(&wq->wait)) + * wake_up_interruptible(&wq->wait) + * ... + * } + * + * The race for tcp fires when the __add_wait_queue changes done by CPU1 stay + * in its cache, and so does the tp->rcv_nxt update on CPU2 side. The CPU1 + * could then endup calling schedule and sleep forever if there are no more + * data on the socket. + * + */ +static inline bool wq_has_sleeper(struct socket_wq *wq) +{ + + /* + * We need to be sure we are in sync with the + * add_wait_queue modifications to the wait queue. + * + * This memory barrier is paired in the sock_poll_wait. + */ + smp_mb(); + return wq && waitqueue_active(&wq->wait); +} + +/** + * sock_poll_wait - place memory barrier behind the poll_wait call. + * @filp: file + * @wait_address: socket wait queue + * @p: poll_table + * + * See the comments in the wq_has_sleeper function. + */ +static inline void sock_poll_wait(struct file *filp, + wait_queue_head_t *wait_address, poll_table *p) +{ + if (p && wait_address) { + poll_wait(filp, wait_address, p); + /* + * We need to be sure we are in sync with the + * socket flags modification. + * + * This memory barrier is paired in the wq_has_sleeper. + */ + smp_mb(); + } +} + /* * Queue a received datagram if it will fit. Stream and sequenced * protocols can't normally use this as they need to fit buffers in @@ -1179,14 +1478,20 @@ static inline int skb_copy_to_page(struct sock *sk, char __user *from, static inline void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) { - sock_hold(sk); + skb_orphan(skb); skb->sk = sk; skb->destructor = sock_wfree; + /* + * We used to take a refcount on sk, but following operation + * is enough to guarantee sk_free() wont free this sock until + * all in-flight packets are completed + */ atomic_add(skb->truesize, &sk->sk_wmem_alloc); } static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk) { + skb_orphan(skb); skb->sk = sk; skb->destructor = sock_rfree; atomic_add(skb->truesize, &sk->sk_rmem_alloc); @@ -1242,7 +1547,7 @@ static inline unsigned long sock_wspace(struct sock *sk) static inline void sk_wake_async(struct sock *sk, int how, int band) { - if (sk->sk_socket && sk->sk_socket->fasync_list) + if (sock_flag(sk, SOCK_FASYNC)) sock_wake_async(sk->sk_socket, how, band); } @@ -1265,7 +1570,7 @@ 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; @@ -1281,7 +1586,7 @@ static inline int sock_writeable(const struct sock *sk) static inline gfp_t gfp_any(void) { - return in_atomic() ? GFP_ATOMIC : GFP_KERNEL; + return in_softirq() ? GFP_ATOMIC : GFP_KERNEL; } static inline long sock_rcvtimeo(const struct sock *sk, int noblock) @@ -1314,13 +1619,63 @@ static __inline__ void sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { ktime_t kt = skb->tstamp; + struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb); - if (sock_flag(sk, SOCK_RCVTSTAMP)) + /* + * generate control messages if + * - receive time stamping in software requested (SOCK_RCVTSTAMP + * or SOCK_TIMESTAMPING_RX_SOFTWARE) + * - software time stamp available and wanted + * (SOCK_TIMESTAMPING_SOFTWARE) + * - hardware time stamps available and wanted + * (SOCK_TIMESTAMPING_SYS_HARDWARE or + * SOCK_TIMESTAMPING_RAW_HARDWARE) + */ + if (sock_flag(sk, SOCK_RCVTSTAMP) || + sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE) || + (kt.tv64 && sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE)) || + (hwtstamps->hwtstamp.tv64 && + sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE)) || + (hwtstamps->syststamp.tv64 && + sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE))) __sock_recv_timestamp(msg, sk, skb); else sk->sk_stamp = kt; } +extern void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb); + +static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) +{ +#define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL) | \ + (1UL << SOCK_RCVTSTAMP) | \ + (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE) | \ + (1UL << SOCK_TIMESTAMPING_SOFTWARE) | \ + (1UL << SOCK_TIMESTAMPING_RAW_HARDWARE) | \ + (1UL << SOCK_TIMESTAMPING_SYS_HARDWARE)) + + if (sk->sk_flags & FLAGS_TS_OR_DROPS) + __sock_recv_ts_and_drops(msg, sk, skb); + else + sk->sk_stamp = skb->tstamp; +} + +/** + * sock_tx_timestamp - checks whether the outgoing packet is to be time stamped + * @msg: outgoing packet + * @sk: socket sending this packet + * @shtx: filled with instructions for time stamping + * + * Currently only depends on SOCK_TIMESTAMPING* flags. Returns error code if + * parameters are invalid. + */ +extern int sock_tx_timestamp(struct msghdr *msg, + struct sock *sk, + union skb_shared_tx *shtx); + + /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from @@ -1374,10 +1729,22 @@ void sock_net_set(struct sock *sk, struct net *net) static inline void sk_change_net(struct sock *sk, struct net *net) { put_net(sock_net(sk)); - sock_net_set(sk, net); + sock_net_set(sk, hold_net(net)); +} + +static inline struct sock *skb_steal_sock(struct sk_buff *skb) +{ + if (unlikely(skb->sk)) { + struct sock *sk = skb->sk; + + skb->destructor = NULL; + skb->sk = NULL; + return sk; + } + return NULL; } -extern void sock_enable_timestamp(struct sock *sk); +extern void sock_enable_timestamp(struct sock *sk, int flag); extern int sock_get_timestamp(struct sock *, struct timeval __user *); extern int sock_get_timestampns(struct sock *, struct timespec __user *); @@ -1391,30 +1758,6 @@ 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;