diff options
Diffstat (limited to 'include/net/tcp.h')
-rw-r--r-- | include/net/tcp.h | 224 |
1 files changed, 111 insertions, 113 deletions
diff --git a/include/net/tcp.h b/include/net/tcp.h index 8d6b983d5099..950cfecaad3c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -65,7 +65,13 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCP_MIN_MSS 88U /* The least MTU to use for probing */ -#define TCP_BASE_MSS 512 +#define TCP_BASE_MSS 1024 + +/* probing interval, default to 10 minutes as per RFC4821 */ +#define TCP_PROBE_INTERVAL 600 + +/* Specify interval when tcp mtu probing will stop */ +#define TCP_PROBE_THRESHOLD 8 /* After receiving this amount of duplicate ACKs fast retransmit starts. */ #define TCP_FASTRETRANS_THRESH 3 @@ -173,6 +179,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCPOPT_SACK 5 /* SACK Block */ #define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */ #define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */ +#define TCPOPT_FASTOPEN 34 /* Fast open (RFC7413) */ #define TCPOPT_EXP 254 /* Experimental */ /* Magic number to be after the option value for sharing TCP * experimental options. See draft-ietf-tcpm-experimental-options-00.txt @@ -188,6 +195,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCPOLEN_SACK_PERM 2 #define TCPOLEN_TIMESTAMP 10 #define TCPOLEN_MD5SIG 18 +#define TCPOLEN_FASTOPEN_BASE 2 #define TCPOLEN_EXP_FASTOPEN_BASE 4 /* But this is what stacks really send out. */ @@ -278,6 +286,14 @@ extern atomic_long_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; extern int tcp_memory_pressure; +/* optimized version of sk_under_memory_pressure() for TCP sockets */ +static inline bool tcp_under_memory_pressure(const struct sock *sk) +{ + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + return !!sk->sk_cgrp->memory_pressure; + + return tcp_memory_pressure; +} /* * The next routines deal with comparing 32 bit unsigned ints * and worry about wraparound (automatic with unsigned arithmetic). @@ -303,6 +319,8 @@ static inline bool tcp_out_of_memory(struct sock *sk) return false; } +void sk_forced_mem_schedule(struct sock *sk, int size); + static inline bool tcp_too_many_orphans(struct sock *sk, int shift) { struct percpu_counter *ocp = sk->sk_prot->orphan_count; @@ -318,18 +336,6 @@ static inline bool tcp_too_many_orphans(struct sock *sk, int shift) bool tcp_check_oom(struct sock *sk, int shift); -/* syncookies: remember time of last synqueue overflow */ -static inline void tcp_synq_overflow(struct sock *sk) -{ - tcp_sk(sk)->rx_opt.ts_recent_stamp = jiffies; -} - -/* syncookies: no recent synqueue overflow on this listening socket? */ -static inline bool tcp_synq_no_recent_overflow(const struct sock *sk) -{ - unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; - return time_after(jiffies, last_overflow + TCP_TIMEOUT_FALLBACK); -} extern struct proto tcp_prot; @@ -349,8 +355,7 @@ void tcp_v4_early_demux(struct sk_buff *skb); int tcp_v4_rcv(struct sk_buff *skb); int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); -int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t size); +int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); void tcp_release_cb(struct sock *sk); @@ -401,8 +406,7 @@ enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, const struct tcphdr *th); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, struct request_sock **prev, - bool fastopen); + struct request_sock *req, bool fastopen); int tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); void tcp_enter_loss(struct sock *sk); @@ -429,9 +433,9 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname, int compat_tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); void tcp_set_keepalive(struct sock *sk, int val); -void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req); -int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len, int nonblock, int flags, int *addr_len); +void tcp_syn_ack_timeout(const struct request_sock *req); +int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, + int flags, int *addr_len); void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab, struct tcp_fastopen_cookie *foc); @@ -443,6 +447,7 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); void tcp_v4_mtu_reduced(struct sock *sk); +void tcp_req_err(struct sock *sk, u32 seq); int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, @@ -464,6 +469,9 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size); void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb); /* From syncookies.c */ +struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct dst_entry *dst); int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, u32 cookie); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); @@ -476,13 +484,35 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); * i.e. a sent cookie is valid only at most for 2*60 seconds (or less if * the counter advances immediately after a cookie is generated). */ -#define MAX_SYNCOOKIE_AGE 2 +#define MAX_SYNCOOKIE_AGE 2 +#define TCP_SYNCOOKIE_PERIOD (60 * HZ) +#define TCP_SYNCOOKIE_VALID (MAX_SYNCOOKIE_AGE * TCP_SYNCOOKIE_PERIOD) + +/* syncookies: remember time of last synqueue overflow + * But do not dirty this field too often (once per second is enough) + */ +static inline void tcp_synq_overflow(struct sock *sk) +{ + unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; + unsigned long now = jiffies; + + if (time_after(now, last_overflow + HZ)) + tcp_sk(sk)->rx_opt.ts_recent_stamp = now; +} + +/* syncookies: no recent synqueue overflow on this listening socket? */ +static inline bool tcp_synq_no_recent_overflow(const struct sock *sk) +{ + unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; + + return time_after(jiffies, last_overflow + TCP_SYNCOOKIE_VALID); +} static inline u32 tcp_cookie_time(void) { u64 val = get_jiffies_64(); - do_div(val, 60 * HZ); + do_div(val, TCP_SYNCOOKIE_PERIOD); return val; } @@ -520,12 +550,10 @@ int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int, gfp_t); void tcp_send_probe0(struct sock *); void tcp_send_partial(struct sock *); -int tcp_write_wakeup(struct sock *); +int tcp_write_wakeup(struct sock *, int mib); void tcp_send_fin(struct sock *sk); void tcp_send_active_reset(struct sock *sk, gfp_t priority); int tcp_send_synack(struct sock *); -bool tcp_syn_flood_action(struct sock *sk, const struct sk_buff *skb, - const char *proto); void tcp_push_one(struct sock *, unsigned int mss_now); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); @@ -571,7 +599,7 @@ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize) } /* tcp.c */ -void tcp_get_info(const struct sock *, struct tcp_info *); +void tcp_get_info(struct sock *, struct tcp_info *); /* Read 'sendfile()'-style from a TCP socket */ typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, @@ -687,6 +715,8 @@ static inline u32 tcp_skb_timestamp(const struct sk_buff *skb) #define TCPHDR_ECE 0x40 #define TCPHDR_CWR 0x80 +#define TCPHDR_SYN_ECN (TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR) + /* This is what the send packet queuing engine uses to pass * TCP per-packet control information to the transmission code. * We also store the host-order sequence numbers in here too. @@ -700,11 +730,14 @@ struct tcp_skb_cb { /* Note : tcp_tw_isn is used in input path only * (isn chosen by tcp_timewait_state_process()) * - * tcp_gso_segs is used in write queue only, - * cf tcp_skb_pcount() + * tcp_gso_segs/size are used in write queue only, + * cf tcp_skb_pcount()/tcp_skb_mss() */ __u32 tcp_tw_isn; - __u32 tcp_gso_segs; + struct { + u16 tcp_gso_segs; + u16 tcp_gso_size; + }; }; __u8 tcp_flags; /* TCP header flags. (tcp[13]) */ @@ -760,10 +793,10 @@ static inline void tcp_skb_pcount_add(struct sk_buff *skb, int segs) TCP_SKB_CB(skb)->tcp_gso_segs += segs; } -/* This is valid iff tcp_skb_pcount() > 1. */ +/* This is valid iff skb is in write queue and tcp_skb_pcount() > 1. */ static inline int tcp_skb_mss(const struct sk_buff *skb) { - return skb_shinfo(skb)->gso_size; + return TCP_SKB_CB(skb)->tcp_gso_size; } /* Events passed to congestion control interface */ @@ -799,6 +832,8 @@ enum tcp_ca_ack_event_flags { /* Requires ECN/ECT set on all packets */ #define TCP_CONG_NEEDS_ECN 0x2 +union tcp_cc_info; + struct tcp_congestion_ops { struct list_head list; u32 key; @@ -824,7 +859,8 @@ struct tcp_congestion_ops { /* hook for packet ack accounting (optional) */ void (*pkts_acked)(struct sock *sk, u32 num_acked, s32 rtt_us); /* get info for inet_diag (optional) */ - void (*get_info)(struct sock *sk, u32 ext, struct sk_buff *skb); + size_t (*get_info)(struct sock *sk, u32 ext, int *attr, + union tcp_cc_info *info); char name[TCP_CA_NAME_MAX]; struct module *owner; @@ -1035,14 +1071,31 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk) return tp->is_cwnd_limited; } -static inline void tcp_check_probe_timer(struct sock *sk) +/* Something is really bad, we could not queue an additional packet, + * because qdisc is full or receiver sent a 0 window. + * We do not want to add fuel to the fire, or abort too early, + * so make sure the timer we arm now is at least 200ms in the future, + * regardless of current icsk_rto value (as it could be ~2ms) + */ +static inline unsigned long tcp_probe0_base(const struct sock *sk) { - const struct tcp_sock *tp = tcp_sk(sk); - const struct inet_connection_sock *icsk = inet_csk(sk); + return max_t(unsigned long, inet_csk(sk)->icsk_rto, TCP_RTO_MIN); +} + +/* Variant of inet_csk_rto_backoff() used for zero window probes */ +static inline unsigned long tcp_probe0_when(const struct sock *sk, + unsigned long max_when) +{ + u64 when = (u64)tcp_probe0_base(sk) << inet_csk(sk)->icsk_backoff; - if (!tp->packets_out && !icsk->icsk_pending) + return (unsigned long)min_t(u64, when, max_when); +} + +static inline void tcp_check_probe_timer(struct sock *sk) +{ + if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending) inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, - icsk->icsk_rto, TCP_RTO_MAX); + tcp_probe0_base(sk), TCP_RTO_MAX); } static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq) @@ -1132,31 +1185,6 @@ static inline int tcp_full_space(const struct sock *sk) return tcp_win_from_space(sk->sk_rcvbuf); } -static inline void tcp_openreq_init(struct request_sock *req, - struct tcp_options_received *rx_opt, - struct sk_buff *skb, struct sock *sk) -{ - struct inet_request_sock *ireq = inet_rsk(req); - - req->rcv_wnd = 0; /* So that tcp_send_synack() knows! */ - req->cookie_ts = 0; - tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; - tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; - tcp_rsk(req)->snt_synack = tcp_time_stamp; - tcp_rsk(req)->last_oow_ack_time = 0; - req->mss = rx_opt->mss_clamp; - req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0; - ireq->tstamp_ok = rx_opt->tstamp_ok; - ireq->sack_ok = rx_opt->sack_ok; - ireq->snd_wscale = rx_opt->snd_wscale; - ireq->wscale_ok = rx_opt->wscale_ok; - ireq->acked = 0; - ireq->ecn_ok = 0; - ireq->ir_rmt_port = tcp_hdr(skb)->source; - ireq->ir_num = ntohs(tcp_hdr(skb)->dest); - ireq->ir_mark = inet_request_mark(sk, skb); -} - extern void tcp_openreq_init_rwin(struct request_sock *req, struct sock *sk, struct dst_entry *dst); @@ -1236,36 +1264,8 @@ static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt, return true; } -/* Return true if we're currently rate-limiting out-of-window ACKs and - * thus shouldn't send a dupack right now. We rate-limit dupacks in - * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS - * attacks that send repeated SYNs or ACKs for the same connection. To - * do this, we do not send a duplicate SYNACK or ACK if the remote - * endpoint is sending out-of-window SYNs or pure ACKs at a high rate. - */ -static inline bool tcp_oow_rate_limited(struct net *net, - const struct sk_buff *skb, - int mib_idx, u32 *last_oow_ack_time) -{ - /* Data packets without SYNs are not likely part of an ACK loop. */ - if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) && - !tcp_hdr(skb)->syn) - goto not_rate_limited; - - if (*last_oow_ack_time) { - s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); - - if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { - NET_INC_STATS_BH(net, mib_idx); - return true; /* rate-limited: don't send yet! */ - } - } - - *last_oow_ack_time = tcp_time_stamp; - -not_rate_limited: - return false; /* not rate-limited: go ahead, send dupack now! */ -} +bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, + int mib_idx, u32 *last_oow_ack_time); static inline void tcp_mib_init(struct net *net) { @@ -1344,15 +1344,14 @@ struct tcp_md5sig_pool { }; /* - functions */ -int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, - const struct sock *sk, const struct request_sock *req, - const struct sk_buff *skb); +int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, + const struct sock *sk, const struct sk_buff *skb); int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, const u8 *newkey, u8 newkeylen, gfp_t gfp); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family); struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk, - struct sock *addr_sk); + const struct sock *addr_sk); #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, @@ -1388,7 +1387,8 @@ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie, int *syn_loss, unsigned long *last_syn_loss); void tcp_fastopen_cache_set(struct sock *sk, u16 mss, - struct tcp_fastopen_cookie *cookie, bool syn_lost); + struct tcp_fastopen_cookie *cookie, bool syn_lost, + u16 try_exp); struct tcp_fastopen_request { /* Fast Open cookie. Size 0 means a cookie request */ struct tcp_fastopen_cookie cookie; @@ -1663,28 +1663,26 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, struct tcp_sock_af_ops { #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *(*md5_lookup) (struct sock *sk, - struct sock *addr_sk); - int (*calc_md5_hash) (char *location, - struct tcp_md5sig_key *md5, - const struct sock *sk, - const struct request_sock *req, - const struct sk_buff *skb); - int (*md5_parse) (struct sock *sk, - char __user *optval, - int optlen); + const struct sock *addr_sk); + int (*calc_md5_hash)(char *location, + const struct tcp_md5sig_key *md5, + const struct sock *sk, + const struct sk_buff *skb); + int (*md5_parse)(struct sock *sk, + char __user *optval, + int optlen); #endif }; struct tcp_request_sock_ops { u16 mss_clamp; #ifdef CONFIG_TCP_MD5SIG - struct tcp_md5sig_key *(*md5_lookup) (struct sock *sk, - struct request_sock *req); - int (*calc_md5_hash) (char *location, - struct tcp_md5sig_key *md5, - const struct sock *sk, - const struct request_sock *req, - const struct sk_buff *skb); + struct tcp_md5sig_key *(*req_md5_lookup)(struct sock *sk, + const struct sock *addr_sk); + int (*calc_md5_hash) (char *location, + const struct tcp_md5sig_key *md5, + const struct sock *sk, + const struct sk_buff *skb); #endif void (*init_req)(struct request_sock *req, struct sock *sk, struct sk_buff *skb); |