diff options
Diffstat (limited to 'include/net/sock.h')
| -rw-r--r-- | include/net/sock.h | 159 |
1 files changed, 113 insertions, 46 deletions
diff --git a/include/net/sock.h b/include/net/sock.h index 8741988e6880..c4f5e6fca17c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -252,6 +252,7 @@ struct sock_common { * @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_padding: unused element for alignment * @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) @@ -302,7 +303,8 @@ struct sock_common { * @sk_backlog_rcv: callback to process the backlog * @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0 * @sk_reuseport_cb: reuseport group container - */ + * @sk_rcu: used during RCU grace period + */ struct sock { /* * Now struct inet_timewait_sock also uses sock_common, so please just @@ -341,6 +343,9 @@ struct sock { #define sk_rxhash __sk_common.skc_rxhash socket_lock_t sk_lock; + atomic_t sk_drops; + int sk_rcvlowat; + struct sk_buff_head sk_error_queue; struct sk_buff_head sk_receive_queue; /* * The backlog queue is special, it is always used with @@ -357,14 +362,13 @@ struct sock { struct sk_buff *tail; } sk_backlog; #define sk_rmem_alloc sk_backlog.rmem_alloc - int sk_forward_alloc; - __u32 sk_txhash; + int sk_forward_alloc; #ifdef CONFIG_NET_RX_BUSY_POLL - unsigned int sk_napi_id; unsigned int sk_ll_usec; + /* ===== mostly read cache line ===== */ + unsigned int sk_napi_id; #endif - atomic_t sk_drops; int sk_rcvbuf; struct sk_filter __rcu *sk_filter; @@ -377,16 +381,50 @@ struct sock { #endif struct dst_entry *sk_rx_dst; struct dst_entry __rcu *sk_dst_cache; - /* Note: 32bit hole on 64bit arches */ - atomic_t sk_wmem_alloc; atomic_t sk_omem_alloc; int sk_sndbuf; + + /* ===== cache line for TX ===== */ + int sk_wmem_queued; + atomic_t sk_wmem_alloc; + unsigned long sk_tsq_flags; + struct sk_buff *sk_send_head; struct sk_buff_head sk_write_queue; + __s32 sk_peek_off; + int sk_write_pending; + long sk_sndtimeo; + struct timer_list sk_timer; + __u32 sk_priority; + __u32 sk_mark; + u32 sk_pacing_rate; /* bytes per second */ + u32 sk_max_pacing_rate; + struct page_frag sk_frag; + netdev_features_t sk_route_caps; + netdev_features_t sk_route_nocaps; + int sk_gso_type; + unsigned int sk_gso_max_size; + gfp_t sk_allocation; + __u32 sk_txhash; /* * Because of non atomicity rules, all * changes are protected by socket lock. */ + unsigned int __sk_flags_offset[0]; +#ifdef __BIG_ENDIAN_BITFIELD +#define SK_FL_PROTO_SHIFT 16 +#define SK_FL_PROTO_MASK 0x00ff0000 + +#define SK_FL_TYPE_SHIFT 0 +#define SK_FL_TYPE_MASK 0x0000ffff +#else +#define SK_FL_PROTO_SHIFT 8 +#define SK_FL_PROTO_MASK 0x0000ff00 + +#define SK_FL_TYPE_SHIFT 16 +#define SK_FL_TYPE_MASK 0xffff0000 +#endif + kmemcheck_bitfield_begin(flags); unsigned int sk_padding : 2, sk_no_check_tx : 1, @@ -397,41 +435,24 @@ struct sock { #define SK_PROTOCOL_MAX U8_MAX kmemcheck_bitfield_end(flags); - int sk_wmem_queued; - gfp_t sk_allocation; - u32 sk_pacing_rate; /* bytes per second */ - u32 sk_max_pacing_rate; - netdev_features_t sk_route_caps; - netdev_features_t sk_route_nocaps; - int sk_gso_type; - unsigned int sk_gso_max_size; u16 sk_gso_max_segs; - int sk_rcvlowat; unsigned long sk_lingertime; - struct sk_buff_head sk_error_queue; struct proto *sk_prot_creator; rwlock_t sk_callback_lock; int sk_err, sk_err_soft; u32 sk_ack_backlog; u32 sk_max_ack_backlog; - __u32 sk_priority; - __u32 sk_mark; + kuid_t sk_uid; struct pid *sk_peer_pid; const struct cred *sk_peer_cred; long sk_rcvtimeo; - long sk_sndtimeo; - struct timer_list sk_timer; ktime_t sk_stamp; u16 sk_tsflags; u8 sk_shutdown; u32 sk_tskey; struct socket *sk_socket; void *sk_user_data; - struct page_frag sk_frag; - struct sk_buff *sk_send_head; - __s32 sk_peek_off; - int sk_write_pending; #ifdef CONFIG_SECURITY void *sk_security; #endif @@ -892,7 +913,20 @@ static inline void sock_rps_record_flow_hash(__u32 hash) static inline void sock_rps_record_flow(const struct sock *sk) { #ifdef CONFIG_RPS - sock_rps_record_flow_hash(sk->sk_rxhash); + if (static_key_false(&rfs_needed)) { + /* Reading sk->sk_rxhash might incur an expensive cache line + * miss. + * + * TCP_ESTABLISHED does cover almost all states where RFS + * might be useful, and is cheaper [1] than testing : + * IPv4: inet_sk(sk)->inet_daddr + * IPv6: ipv6_addr_any(&sk->sk_v6_daddr) + * OR an additional socket flag + * [1] : sk_state and sk_prot are in the same cache line. + */ + if (sk->sk_state == TCP_ESTABLISHED) + sock_rps_record_flow_hash(sk->sk_rxhash); + } #endif } @@ -912,14 +946,16 @@ static inline void sock_rps_reset_rxhash(struct sock *sk) #endif } -#define sk_wait_event(__sk, __timeo, __condition) \ +#define sk_wait_event(__sk, __timeo, __condition, __wait) \ ({ int __rc; \ release_sock(__sk); \ __rc = __condition; \ if (!__rc) { \ - *(__timeo) = schedule_timeout(*(__timeo)); \ + *(__timeo) = wait_woken(__wait, \ + TASK_INTERRUPTIBLE, \ + *(__timeo)); \ } \ - sched_annotate_sleep(); \ + sched_annotate_sleep(); \ lock_sock(__sk); \ __rc = __condition; \ __rc; \ @@ -1020,7 +1056,6 @@ struct proto { void (*unhash)(struct sock *sk); void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); - void (*clear_sk)(struct sock *sk, int size); /* Keeping track of sockets in use */ #ifdef CONFIG_PROC_FS @@ -1114,6 +1149,16 @@ static inline bool sk_stream_is_writeable(const struct sock *sk) sk_stream_memory_free(sk); } +static inline int sk_under_cgroup_hierarchy(struct sock *sk, + struct cgroup *ancestor) +{ +#ifdef CONFIG_SOCK_CGROUP_DATA + return cgroup_is_descendant(sock_cgroup_ptr(&sk->sk_cgrp_data), + ancestor); +#else + return -ENOTSUPP; +#endif +} static inline bool sk_has_memory_pressure(const struct sock *sk) { @@ -1151,11 +1196,6 @@ static inline void sk_enter_memory_pressure(struct sock *sk) sk->sk_prot->enter_memory_pressure(sk); } -static inline long sk_prot_mem_limits(const struct sock *sk, int index) -{ - return sk->sk_prot->sysctl_mem[index]; -} - static inline long sk_memory_allocated(const struct sock *sk) { @@ -1232,8 +1272,6 @@ static inline int __sk_prot_rehash(struct sock *sk) return sk->sk_prot->hash(sk); } -void sk_prot_clear_portaddr_nulls(struct sock *sk, int size); - /* About 10 seconds */ #define SOCK_DESTROY_TIME (10*HZ) @@ -1267,14 +1305,32 @@ static inline struct inode *SOCK_INODE(struct socket *socket) /* * Functions for memory accounting */ +int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind); int __sk_mem_schedule(struct sock *sk, int size, int kind); +void __sk_mem_reduce_allocated(struct sock *sk, int amount); void __sk_mem_reclaim(struct sock *sk, int amount); -#define SK_MEM_QUANTUM ((int)PAGE_SIZE) +/* We used to have PAGE_SIZE here, but systems with 64KB pages + * do not necessarily have 16x time more memory than 4KB ones. + */ +#define SK_MEM_QUANTUM 4096 #define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM) #define SK_MEM_SEND 0 #define SK_MEM_RECV 1 +/* sysctl_mem values are in pages, we convert them in SK_MEM_QUANTUM units */ +static inline long sk_prot_mem_limits(const struct sock *sk, int index) +{ + long val = sk->sk_prot->sysctl_mem[index]; + +#if PAGE_SIZE > SK_MEM_QUANTUM + val <<= PAGE_SHIFT - SK_MEM_QUANTUM_SHIFT; +#elif PAGE_SIZE < SK_MEM_QUANTUM + val >>= SK_MEM_QUANTUM_SHIFT - PAGE_SHIFT; +#endif + return val; +} + static inline int sk_mem_pages(int amt) { return (amt + SK_MEM_QUANTUM - 1) >> SK_MEM_QUANTUM_SHIFT; @@ -1587,11 +1643,11 @@ static inline void sock_put(struct sock *sk) void sock_gen_put(struct sock *sk); int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, - unsigned int trim_cap); + unsigned int trim_cap, bool refcounted); static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) { - return __sk_receive_skb(sk, skb, nested, 1); + return __sk_receive_skb(sk, skb, nested, 1, true); } static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) @@ -1642,6 +1698,7 @@ static inline void sock_graft(struct sock *sk, struct socket *parent) sk->sk_wq = parent->wq; parent->sk = sk; sk_set_socket(sk, parent); + sk->sk_uid = SOCK_INODE(parent)->i_uid; security_sock_graft(sk, parent); write_unlock_bh(&sk->sk_callback_lock); } @@ -1649,6 +1706,11 @@ 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 kuid_t sock_net_uid(const struct net *net, const struct sock *sk) +{ + return sk ? sk->sk_uid : make_kuid(net->user_ns, 0); +} + static inline u32 net_tx_rndhash(void) { u32 v = prandom_u32(); @@ -1774,13 +1836,13 @@ static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb, { if (skb->ip_summed == CHECKSUM_NONE) { __wsum csum = 0; - if (csum_and_copy_from_iter(to, copy, &csum, from) != copy) + if (!csum_and_copy_from_iter_full(to, copy, &csum, from)) return -EFAULT; skb->csum = csum_block_add(skb->csum, csum, offset); } else if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) { - if (copy_from_iter_nocache(to, copy, from) != copy) + if (!copy_from_iter_full_nocache(to, copy, from)) return -EFAULT; - } else if (copy_from_iter(to, copy, from) != copy) + } else if (!copy_from_iter_full(to, copy, from)) return -EFAULT; return 0; @@ -1943,6 +2005,10 @@ void sk_reset_timer(struct sock *sk, struct timer_list *timer, void sk_stop_timer(struct sock *sk, struct timer_list *timer); +int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb, + unsigned int flags, + void (*destructor)(struct sock *sk, + struct sk_buff *skb)); int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); @@ -2099,7 +2165,8 @@ struct sock_skb_cb { static inline void sock_skb_set_dropcount(const struct sock *sk, struct sk_buff *skb) { - SOCK_SKB_CB(skb)->dropcount = atomic_read(&sk->sk_drops); + SOCK_SKB_CB(skb)->dropcount = sock_flag(sk, SOCK_RXQ_OVFL) ? + atomic_read(&sk->sk_drops) : 0; } static inline void sk_drops_add(struct sock *sk, const struct sk_buff *skb) @@ -2128,8 +2195,8 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) */ if (sock_flag(sk, SOCK_RCVTSTAMP) || (sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) || - (kt.tv64 && sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) || - (hwtstamps->hwtstamp.tv64 && + (kt && sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) || + (hwtstamps->hwtstamp && (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE))) __sock_recv_timestamp(msg, sk, skb); else |