diff options
Diffstat (limited to 'include/net/sock.h')
| -rw-r--r-- | include/net/sock.h | 121 |
1 files changed, 105 insertions, 16 deletions
diff --git a/include/net/sock.h b/include/net/sock.h index 02162b0378f7..6d84784d33fa 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -117,19 +117,26 @@ typedef __u64 __bitwise __addrpair; * struct sock_common - minimal network layer representation of sockets * @skc_daddr: Foreign IPv4 addr * @skc_rcv_saddr: Bound local IPv4 addr + * @skc_addrpair: 8-byte-aligned __u64 union of @skc_daddr & @skc_rcv_saddr * @skc_hash: hash value used with various protocol lookup tables * @skc_u16hashes: two u16 hash values used by UDP lookup tables * @skc_dport: placeholder for inet_dport/tw_dport * @skc_num: placeholder for inet_num/tw_num + * @skc_portpair: __u32 union of @skc_dport & @skc_num * @skc_family: network address family * @skc_state: Connection state * @skc_reuse: %SO_REUSEADDR setting * @skc_reuseport: %SO_REUSEPORT setting + * @skc_ipv6only: socket is IPV6 only + * @skc_net_refcnt: socket is using net ref counting * @skc_bound_dev_if: bound device index if != 0 * @skc_bind_node: bind hash linkage for 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 + * @skc_v6_daddr: IPV6 destination address + * @skc_v6_rcv_saddr: IPV6 source address + * @skc_cookie: socket's cookie value * @skc_node: main hash linkage for various protocol lookup tables * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol * @skc_tx_queue_mapping: tx queue number for this connection @@ -137,7 +144,15 @@ typedef __u64 __bitwise __addrpair; * @skc_flags: place holder for sk_flags * %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings + * @skc_listener: connection request listener socket (aka rsk_listener) + * [union with @skc_flags] + * @skc_tw_dr: (aka tw_dr) ptr to &struct inet_timewait_death_row + * [union with @skc_flags] * @skc_incoming_cpu: record/match cpu processing incoming packets + * @skc_rcv_wnd: (aka rsk_rcv_wnd) TCP receive window size (possibly scaled) + * [union with @skc_incoming_cpu] + * @skc_tw_rcv_nxt: (aka tw_rcv_nxt) TCP window next expected seq number + * [union with @skc_incoming_cpu] * @skc_refcnt: reference count * * This is the minimal network layer representation of sockets, the header @@ -245,6 +260,7 @@ struct bpf_sk_storage; * @sk_dst_cache: destination cache * @sk_dst_pending_confirm: need to confirm neighbour * @sk_policy: flow policy + * @sk_rx_skb_cache: cache copy of recently accessed RX skb * @sk_receive_queue: incoming packets * @sk_wmem_alloc: transmit queue bytes committed * @sk_tsq_flags: TCP Small Queues flags @@ -265,6 +281,8 @@ struct bpf_sk_storage; * @sk_no_check_rx: allow zero checksum in RX packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) * @sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK) + * @sk_route_forced_caps: static, forced route capabilities + * (set in tcp_init_sock()) * @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4) * @sk_gso_max_size: Maximum GSO segment size to build * @sk_gso_max_segs: Maximum number of GSO segments @@ -303,6 +321,8 @@ struct bpf_sk_storage; * @sk_frag: cached page frag * @sk_peek_off: current peek_offset value * @sk_send_head: front of stuff to transmit + * @tcp_rtx_queue: TCP re-transmit queue [union with @sk_send_head] + * @sk_tx_skb_cache: cache copy of recently accessed TX skb * @sk_security: used by security modules * @sk_mark: generic packet mark * @sk_cgrp_data: cgroup data for this cgroup @@ -313,11 +333,14 @@ struct bpf_sk_storage; * @sk_write_space: callback to indicate there is bf sending space available * @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE) * @sk_backlog_rcv: callback to process the backlog + * @sk_validate_xmit_skb: ptr to an optional validate function * @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0 * @sk_reuseport_cb: reuseport group container + * @sk_bpf_storage: ptr to cache and control for bpf_sk_storage * @sk_rcu: used during RCU grace period * @sk_clockid: clockid used by time-based scheduling (SO_TXTIME) * @sk_txtime_deadline_mode: set deadline mode for SO_TXTIME + * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags */ struct sock { @@ -393,7 +416,9 @@ struct sock { struct sk_filter __rcu *sk_filter; union { struct socket_wq __rcu *sk_wq; + /* private: */ struct socket_wq *sk_wq_raw; + /* public: */ }; #ifdef CONFIG_XFRM struct xfrm_policy __rcu *sk_policy[2]; @@ -502,10 +527,43 @@ enum sk_pacing { SK_PACING_FQ = 2, }; +/* Pointer stored in sk_user_data might not be suitable for copying + * when cloning the socket. For instance, it can point to a reference + * counted object. sk_user_data bottom bit is set if pointer must not + * be copied. + */ +#define SK_USER_DATA_NOCOPY 1UL +#define SK_USER_DATA_PTRMASK ~(SK_USER_DATA_NOCOPY) + +/** + * sk_user_data_is_nocopy - Test if sk_user_data pointer must not be copied + * @sk: socket + */ +static inline bool sk_user_data_is_nocopy(const struct sock *sk) +{ + return ((uintptr_t)sk->sk_user_data & SK_USER_DATA_NOCOPY); +} + #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data))) -#define rcu_dereference_sk_user_data(sk) rcu_dereference(__sk_user_data((sk))) -#define rcu_assign_sk_user_data(sk, ptr) rcu_assign_pointer(__sk_user_data((sk)), ptr) +#define rcu_dereference_sk_user_data(sk) \ +({ \ + void *__tmp = rcu_dereference(__sk_user_data((sk))); \ + (void *)((uintptr_t)__tmp & SK_USER_DATA_PTRMASK); \ +}) +#define rcu_assign_sk_user_data(sk, ptr) \ +({ \ + uintptr_t __tmp = (uintptr_t)(ptr); \ + WARN_ON_ONCE(__tmp & ~SK_USER_DATA_PTRMASK); \ + rcu_assign_pointer(__sk_user_data((sk)), __tmp); \ +}) +#define rcu_assign_sk_user_data_nocopy(sk, ptr) \ +({ \ + uintptr_t __tmp = (uintptr_t)(ptr); \ + WARN_ON_ONCE(__tmp & ~SK_USER_DATA_PTRMASK); \ + rcu_assign_pointer(__sk_user_data((sk)), \ + __tmp | SK_USER_DATA_NOCOPY); \ +}) /* * SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK @@ -1601,6 +1659,7 @@ void sock_rfree(struct sk_buff *skb); void sock_efree(struct sk_buff *skb); #ifdef CONFIG_INET void sock_edemux(struct sk_buff *skb); +void sock_pfree(struct sk_buff *skb); #else #define sock_edemux sock_efree #endif @@ -2017,7 +2076,7 @@ static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *fro * sk_wmem_alloc_get - returns write allocations * @sk: socket * - * Returns sk_wmem_alloc minus initial offset of one + * Return: sk_wmem_alloc minus initial offset of one */ static inline int sk_wmem_alloc_get(const struct sock *sk) { @@ -2028,7 +2087,7 @@ static inline int sk_wmem_alloc_get(const struct sock *sk) * sk_rmem_alloc_get - returns read allocations * @sk: socket * - * Returns sk_rmem_alloc + * Return: sk_rmem_alloc */ static inline int sk_rmem_alloc_get(const struct sock *sk) { @@ -2039,7 +2098,7 @@ static inline int sk_rmem_alloc_get(const struct sock *sk) * sk_has_allocations - check if allocations are outstanding * @sk: socket * - * Returns true if socket has write or read allocations + * Return: true if socket has write or read allocations */ static inline bool sk_has_allocations(const struct sock *sk) { @@ -2050,7 +2109,7 @@ static inline bool sk_has_allocations(const struct sock *sk) * skwq_has_sleeper - check if there are any waiting processes * @wq: struct socket_wq * - * Returns true if socket_wq has waiting processes + * Return: true if socket_wq has waiting processes * * The purpose of the skwq_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. @@ -2238,6 +2297,9 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, * gfpflags_allow_blocking() isn't enough here as direct reclaim may nest * inside other socket operations and end up recursing into sk_page_frag() * while it's already in use. + * + * Return: a per task page_frag if context allows that, + * otherwise a per socket one. */ static inline struct page_frag *sk_page_frag(struct sock *sk) { @@ -2432,6 +2494,7 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) &skb_shinfo(skb)->tskey); } +DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key); /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from @@ -2440,7 +2503,6 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) * This routine must be called with interrupts disabled or with the socket * locked so that the sk_buff queue operation is ok. */ -DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key); static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb) { __skb_unlink(skb, &sk->sk_receive_queue); @@ -2465,16 +2527,14 @@ void sock_net_set(struct sock *sk, struct net *net) write_pnet(&sk->sk_net, net); } -static inline struct sock *skb_steal_sock(struct sk_buff *skb) +static inline bool +skb_sk_is_prefetched(struct sk_buff *skb) { - if (skb->sk) { - struct sock *sk = skb->sk; - - skb->destructor = NULL; - skb->sk = NULL; - return sk; - } - return NULL; +#ifdef CONFIG_INET + return skb->destructor == sock_pfree; +#else + return false; +#endif /* CONFIG_INET */ } /* This helper checks if a socket is a full socket, @@ -2485,6 +2545,35 @@ static inline bool sk_fullsock(const struct sock *sk) return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV); } +static inline bool +sk_is_refcounted(struct sock *sk) +{ + /* Only full sockets have sk->sk_flags. */ + return !sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE); +} + +/** + * skb_steal_sock + * @skb to steal the socket from + * @refcounted is set to true if the socket is reference-counted + */ +static inline struct sock * +skb_steal_sock(struct sk_buff *skb, bool *refcounted) +{ + if (skb->sk) { + struct sock *sk = skb->sk; + + *refcounted = true; + if (skb_sk_is_prefetched(skb)) + *refcounted = sk_is_refcounted(sk); + skb->destructor = NULL; + skb->sk = NULL; + return sk; + } + *refcounted = false; + return NULL; +} + /* Checks if this SKB belongs to an HW offloaded socket * and whether any SW fallbacks are required based on dev. * Check decrypted mark in case skb_orphan() cleared socket. |