X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=include%2Fnet%2Fsock.h;h=1621935aad5bc5b3e69299c136c685dd42dbff92;hb=d43c36dc6b357fa1806800f18aa30123c747a6d1;hp=3f4897ab432e4e5bab8511bff5e774fa5cc45366;hpb=972692e0db9b0a62329ca394062b58917ddbd03c;p=safe%2Fjmp%2Flinux-2.6 diff --git a/include/net/sock.h b/include/net/sock.h index 3f4897a..1621935 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -42,6 +42,7 @@ #include #include +#include #include #include #include @@ -52,6 +53,8 @@ #include #include +#include +#include #include #include @@ -101,14 +104,15 @@ 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 UDP/UDP-Lite protocol + * @skc_refcnt: reference count + * @skc_hash: hash value used with various protocol 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_prot: protocol handlers inside a network family * @skc_net: reference to the network namespace of this socket * @@ -116,14 +120,21 @@ 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; + + unsigned int skc_hash; 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; struct proto *skc_prot; #ifdef CONFIG_NET_NS struct net *skc_net; @@ -152,7 +163,7 @@ 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_gso_type: GSO type (e.g. %SKB_GSO_TCPV4) @@ -201,19 +212,24 @@ 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_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 + kmemcheck_bitfield_begin(flags); unsigned char sk_shutdown : 2, sk_no_check : 2, sk_userlocks : 4; + kmemcheck_bitfield_end(flags); unsigned char sk_protocol; unsigned short sk_type; int sk_rcvbuf; @@ -229,7 +245,9 @@ struct sock { } sk_backlog; wait_queue_head_t *sk_sleep; struct dst_entry *sk_dst_cache; +#ifdef CONFIG_XFRM struct xfrm_policy *sk_policy[2]; +#endif rwlock_t sk_dst_lock; atomic_t sk_rmem_alloc; atomic_t sk_wmem_alloc; @@ -237,7 +255,9 @@ struct sock { 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; @@ -269,7 +289,9 @@ 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); @@ -294,12 +316,30 @@ 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); @@ -315,6 +355,11 @@ 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); @@ -361,6 +406,27 @@ static __inline__ int sk_del_node_init(struct sock *sk) return rc; } +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) { hlist_add_head(&sk->sk_node, list); @@ -372,6 +438,17 @@ static __inline__ void sk_add_node(struct sock *sk, struct hlist_head *list) __sk_add_node(sk, 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); @@ -385,9 +462,16 @@ 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_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) @@ -413,6 +497,13 @@ 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 */ }; static inline void sock_copy_flags(struct sock *nsk, struct sock *osk) @@ -482,6 +573,11 @@ static inline void sk_add_backlog(struct sock *sk, struct sk_buff *skb) skb->next = NULL; } +static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) +{ + return sk->sk_backlog_rcv(sk, skb); +} + #define sk_wait_event(__sk, __timeo, __condition) \ ({ int __rc; \ release_sock(__sk); \ @@ -528,18 +624,20 @@ struct proto { 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, @@ -565,9 +663,9 @@ struct proto { #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. @@ -580,17 +678,18 @@ 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; @@ -777,7 +876,6 @@ 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); @@ -808,7 +906,7 @@ 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, \ @@ -853,7 +951,7 @@ 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, @@ -862,6 +960,11 @@ 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); @@ -890,7 +993,7 @@ 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 *, @@ -912,11 +1015,11 @@ 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); @@ -929,7 +1032,6 @@ extern void sock_init_data(struct socket *sock, struct sock *sk); /** * sk_filter_release: Release a socket filter - * @sk: socket * @fp: filter to remove * * Remove a filter from a socket and release its resources. @@ -1113,6 +1215,107 @@ 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); +} + +/** + * sk_has_sleeper - check if there are any waiting processes + * @sk: socket + * + * Returns true if socket has waiting processes + * + * The purpose of the sk_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 ... + * if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + * wake_up_interruptible(sk->sk_sleep) + * ... + * } + * + * 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. + * + * The sk_has_sleeper is always called right after a call to read_lock, so we + * can use smp_mb__after_lock barrier. + */ +static inline int sk_has_sleeper(struct sock *sk) +{ + /* + * 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__after_lock(); + return sk->sk_sleep && waitqueue_active(sk->sk_sleep); +} + +/** + * 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 sk_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 sk_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 @@ -1124,14 +1327,20 @@ 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); @@ -1210,7 +1419,7 @@ 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; @@ -1226,7 +1435,7 @@ 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) @@ -1259,14 +1468,45 @@ 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; } /** + * 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 * @skb: socket buffer to eat @@ -1322,7 +1562,19 @@ static inline void sk_change_net(struct sock *sk, struct net *net) sock_net_set(sk, hold_net(net)); } -extern void sock_enable_timestamp(struct sock *sk); +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, int flag); extern int sock_get_timestamp(struct sock *, struct timeval __user *); extern int sock_get_timestampns(struct sock *, struct timespec __user *);