diff options
Diffstat (limited to 'include/net/sock.h')
| -rw-r--r-- | include/net/sock.h | 97 |
1 files changed, 63 insertions, 34 deletions
diff --git a/include/net/sock.h b/include/net/sock.h index 7aa78440559a..bbf7c2cf15b4 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -150,6 +150,10 @@ typedef __u64 __bitwise __addrpair; * @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 + * @skc_flags: place holder for sk_flags + * %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, + * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings + * @skc_incoming_cpu: record/match cpu processing incoming packets * @skc_refcnt: reference count * * This is the minimal network layer representation of sockets, the header @@ -200,6 +204,16 @@ struct sock_common { atomic64_t skc_cookie; + /* following fields are padding to force + * offset(struct sock, sk_refcnt) == 128 on 64bit arches + * assuming IPV6 is enabled. We use this padding differently + * for different kind of 'sockets' + */ + union { + unsigned long skc_flags; + struct sock *skc_listener; /* request_sock */ + struct inet_timewait_death_row *skc_tw_dr; /* inet_timewait_sock */ + }; /* * fields between dontcopy_begin/dontcopy_end * are not copied in sock_copy() @@ -212,9 +226,20 @@ struct sock_common { struct hlist_nulls_node skc_nulls_node; }; int skc_tx_queue_mapping; + union { + int skc_incoming_cpu; + u32 skc_rcv_wnd; + u32 skc_tw_rcv_nxt; /* struct tcp_timewait_sock */ + }; + atomic_t skc_refcnt; /* private: */ int skc_dontcopy_end[0]; + union { + u32 skc_rxhash; + u32 skc_window_clamp; + u32 skc_tw_snd_nxt; /* struct tcp_timewait_sock */ + }; /* public: */ }; @@ -243,8 +268,6 @@ struct cg_proto; * @sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler) * @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE) * @sk_sndbuf: size of send buffer in bytes - * @sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, - * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings * @sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets * @sk_no_check_rx: allow zero checksum in RX packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) @@ -273,8 +296,6 @@ struct cg_proto; * @sk_rcvlowat: %SO_RCVLOWAT setting * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting - * @sk_rxhash: flow hash received from netif layer - * @sk_incoming_cpu: record cpu processing incoming packets * @sk_txhash: computed flow hash for use on transmit * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer @@ -331,6 +352,9 @@ struct sock { #define sk_v6_daddr __sk_common.skc_v6_daddr #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr #define sk_cookie __sk_common.skc_cookie +#define sk_incoming_cpu __sk_common.skc_incoming_cpu +#define sk_flags __sk_common.skc_flags +#define sk_rxhash __sk_common.skc_rxhash socket_lock_t sk_lock; struct sk_buff_head sk_receive_queue; @@ -350,14 +374,6 @@ struct sock { } sk_backlog; #define sk_rmem_alloc sk_backlog.rmem_alloc int sk_forward_alloc; -#ifdef CONFIG_RPS - __u32 sk_rxhash; -#endif - u16 sk_incoming_cpu; - /* 16bit hole - * Warned : sk_incoming_cpu can be set from softirq, - * Do not use this hole without fully understanding possible issues. - */ __u32 sk_txhash; #ifdef CONFIG_NET_RX_BUSY_POLL @@ -373,7 +389,6 @@ struct sock { #ifdef CONFIG_XFRM struct xfrm_policy *sk_policy[2]; #endif - unsigned long sk_flags; struct dst_entry *sk_rx_dst; struct dst_entry __rcu *sk_dst_cache; spinlock_t sk_dst_lock; @@ -759,7 +774,7 @@ static inline int sk_memalloc_socks(void) #endif -static inline gfp_t sk_gfp_atomic(struct sock *sk, gfp_t gfp_mask) +static inline gfp_t sk_gfp_atomic(const struct sock *sk, gfp_t gfp_mask) { return GFP_ATOMIC | (sk->sk_allocation & __GFP_MEMALLOC); } @@ -828,6 +843,14 @@ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *s if (sk_rcvqueues_full(sk, limit)) return -ENOBUFS; + /* + * If the skb was allocated from pfmemalloc reserves, only + * allow SOCK_MEMALLOC sockets to use it as this socket is + * helping free memory + */ + if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) + return -ENOMEM; + __sk_add_backlog(sk, skb); sk->sk_backlog.len += skb->truesize; return 0; @@ -1514,6 +1537,13 @@ void sock_kfree_s(struct sock *sk, void *mem, int size); void sock_kzfree_s(struct sock *sk, void *mem, int size); void sk_send_sigurg(struct sock *sk); +struct sockcm_cookie { + u32 mark; +}; + +int sock_cmsg_send(struct sock *sk, struct msghdr *msg, + struct sockcm_cookie *sockc); + /* * Functions to fill in entries in struct proto_ops when a protocol * does not implement a particular function. @@ -1654,12 +1684,16 @@ static inline void sock_graft(struct sock *sk, struct socket *parent) kuid_t sock_i_uid(struct sock *sk); unsigned long sock_i_ino(struct sock *sk); -static inline void sk_set_txhash(struct sock *sk) +static inline u32 net_tx_rndhash(void) { - sk->sk_txhash = prandom_u32(); + u32 v = prandom_u32(); - if (unlikely(!sk->sk_txhash)) - sk->sk_txhash = 1; + return v ?: 1; +} + +static inline void sk_set_txhash(struct sock *sk) +{ + sk->sk_txhash = net_tx_rndhash(); } static inline void sk_rethink_txhash(struct sock *sk) @@ -1917,6 +1951,8 @@ static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk) } } +void skb_set_owner_w(struct sk_buff *skb, struct sock *sk); + /* * Queue a received datagram if it will fit. Stream and sequenced * protocols can't normally use this as they need to fit buffers in @@ -1925,21 +1961,6 @@ static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk) * Inlined as it's very short and called for pretty much every * packet ever received. */ - -static inline void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) -{ - skb_orphan(skb); - skb->sk = sk; - skb->destructor = sock_wfree; - skb_set_hash_from_sk(skb, sk); - /* - * 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); @@ -2020,7 +2041,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, */ static inline struct page_frag *sk_page_frag(struct sock *sk) { - if (sk->sk_allocation & __GFP_WAIT) + if (gfpflags_allow_blocking(sk->sk_allocation)) return ¤t->task_frag; return &sk->sk_frag; @@ -2197,6 +2218,14 @@ static inline bool sk_fullsock(const struct sock *sk) return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV); } +/* This helper checks if a socket is a LISTEN or NEW_SYN_RECV + * SYNACK messages can be attached to either ones (depending on SYNCOOKIE) + */ +static inline bool sk_listener(const struct sock *sk) +{ + return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV); +} + void sock_enable_timestamp(struct sock *sk, int flag); int sock_get_timestamp(struct sock *, struct timeval __user *); int sock_get_timestampns(struct sock *, struct timespec __user *); |