diff options
Diffstat (limited to 'include/net/tcp.h')
| -rw-r--r-- | include/net/tcp.h | 503 |
1 files changed, 262 insertions, 241 deletions
diff --git a/include/net/tcp.h b/include/net/tcp.h index b1aa324c5e6..7286db80e8b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -31,6 +31,7 @@ #include <linux/crypto.h> #include <linux/cryptohash.h> #include <linux/kref.h> +#include <linux/ktime.h> #include <net/inet_connection_sock.h> #include <net/inet_timewait_sock.h> @@ -50,7 +51,7 @@ extern struct inet_hashinfo tcp_hashinfo; extern struct percpu_counter tcp_orphan_count; -extern void tcp_time_wait(struct sock *sk, int state, int timeo); +void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_HEADER (128 + MAX_HEADER) #define MAX_TCP_OPTION_SPACE 40 @@ -219,8 +220,6 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); #define TFO_SERVER_ENABLE 2 #define TFO_CLIENT_NO_COOKIE 4 /* Data in SYN w/o cookie option */ -/* Process SYN data but skip cookie validation */ -#define TFO_SERVER_COOKIE_NOT_CHKED 0x100 /* Accept SYN data w/o any cookie option */ #define TFO_SERVER_COOKIE_NOT_REQD 0x200 @@ -229,10 +228,6 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); */ #define TFO_SERVER_WO_SOCKOPT1 0x400 #define TFO_SERVER_WO_SOCKOPT2 0x800 -/* Always create TFO child sockets on a TFO listener even when - * cookie/data not present. (For testing purpose!) - */ -#define TFO_SERVER_ALWAYS 0x1000 extern struct inet_timewait_death_row tcp_death_row; @@ -259,6 +254,7 @@ extern int sysctl_tcp_max_orphans; extern int sysctl_tcp_fack; extern int sysctl_tcp_reordering; extern int sysctl_tcp_dsack; +extern long sysctl_tcp_mem[3]; extern int sysctl_tcp_wmem[3]; extern int sysctl_tcp_rmem[3]; extern int sysctl_tcp_app_win; @@ -274,7 +270,6 @@ extern int sysctl_tcp_mtu_probing; extern int sysctl_tcp_base_mss; extern int sysctl_tcp_workaround_signed_windows; extern int sysctl_tcp_slow_start_after_idle; -extern int sysctl_tcp_max_ssthresh; extern int sysctl_tcp_thin_linear_timeouts; extern int sysctl_tcp_thin_dupack; extern int sysctl_tcp_early_retrans; @@ -282,6 +277,7 @@ extern int sysctl_tcp_limit_output_bytes; extern int sysctl_tcp_challenge_ack_limit; extern unsigned int sysctl_tcp_notsent_lowat; extern int sysctl_tcp_min_tso_segs; +extern int sysctl_tcp_autocorking; extern atomic_long_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; @@ -325,7 +321,7 @@ static inline bool tcp_too_many_orphans(struct sock *sk, int shift) return false; } -extern bool tcp_check_oom(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) @@ -348,38 +344,36 @@ extern struct proto tcp_prot; #define TCP_ADD_STATS_USER(net, field, val) SNMP_ADD_STATS_USER((net)->mib.tcp_statistics, field, val) #define TCP_ADD_STATS(net, field, val) SNMP_ADD_STATS((net)->mib.tcp_statistics, field, val) -extern void tcp_init_mem(struct net *net); - -extern void tcp_tasklet_init(void); - -extern void tcp_v4_err(struct sk_buff *skb, u32); - -extern void tcp_shutdown (struct sock *sk, int how); - -extern void tcp_v4_early_demux(struct sk_buff *skb); -extern int tcp_v4_rcv(struct sk_buff *skb); - -extern int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); -extern int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t size); -extern int tcp_sendpage(struct sock *sk, struct page *page, int offset, - size_t size, int flags); -extern void tcp_release_cb(struct sock *sk); -extern void tcp_wfree(struct sk_buff *skb); -extern void tcp_write_timer_handler(struct sock *sk); -extern void tcp_delack_timer_handler(struct sock *sk); -extern int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg); -extern int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, - const struct tcphdr *th, unsigned int len); -extern void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, - const struct tcphdr *th, unsigned int len); -extern void tcp_rcv_space_adjust(struct sock *sk); -extern void tcp_cleanup_rbuf(struct sock *sk, int copied); -extern int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp); -extern void tcp_twsk_destructor(struct sock *sk); -extern ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, - struct pipe_inode_info *pipe, size_t len, - unsigned int flags); +void tcp_tasklet_init(void); + +void tcp_v4_err(struct sk_buff *skb, u32); + +void tcp_shutdown(struct sock *sk, int how); + +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_sendpage(struct sock *sk, struct page *page, int offset, size_t size, + int flags); +void tcp_release_cb(struct sock *sk); +void tcp_wfree(struct sk_buff *skb); +void tcp_write_timer_handler(struct sock *sk); +void tcp_delack_timer_handler(struct sock *sk); +int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg); +int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, + const struct tcphdr *th, unsigned int len); +void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, + const struct tcphdr *th, unsigned int len); +void tcp_rcv_space_adjust(struct sock *sk); +void tcp_cleanup_rbuf(struct sock *sk, int copied); +int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp); +void tcp_twsk_destructor(struct sock *sk); +ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags); static inline void tcp_dec_quickack_mode(struct sock *sk, const unsigned int pkts) @@ -409,83 +403,97 @@ enum tcp_tw_status { }; -extern enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, - struct sk_buff *skb, - const struct tcphdr *th); -extern struct sock * tcp_check_req(struct sock *sk,struct sk_buff *skb, - struct request_sock *req, - struct request_sock **prev, - bool fastopen); -extern int tcp_child_process(struct sock *parent, struct sock *child, - struct sk_buff *skb); -extern void tcp_enter_loss(struct sock *sk, int how); -extern void tcp_clear_retrans(struct tcp_sock *tp); -extern void tcp_update_metrics(struct sock *sk); -extern void tcp_init_metrics(struct sock *sk); -extern void tcp_metrics_init(void); -extern bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, bool paws_check); -extern bool tcp_remember_stamp(struct sock *sk); -extern bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw); -extern void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst); -extern void tcp_disable_fack(struct tcp_sock *tp); -extern void tcp_close(struct sock *sk, long timeout); -extern void tcp_init_sock(struct sock *sk); -extern unsigned int tcp_poll(struct file * file, struct socket *sock, - struct poll_table_struct *wait); -extern int tcp_getsockopt(struct sock *sk, int level, int optname, +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); +int tcp_child_process(struct sock *parent, struct sock *child, + struct sk_buff *skb); +void tcp_enter_loss(struct sock *sk, int how); +void tcp_clear_retrans(struct tcp_sock *tp); +void tcp_update_metrics(struct sock *sk); +void tcp_init_metrics(struct sock *sk); +void tcp_metrics_init(void); +bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, + bool paws_check); +bool tcp_remember_stamp(struct sock *sk); +bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw); +void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst); +void tcp_disable_fack(struct tcp_sock *tp); +void tcp_close(struct sock *sk, long timeout); +void tcp_init_sock(struct sock *sk); +unsigned int tcp_poll(struct file *file, struct socket *sock, + struct poll_table_struct *wait); +int tcp_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen); +int tcp_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, unsigned int optlen); +int compat_tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); -extern int tcp_setsockopt(struct sock *sk, int level, int optname, +int compat_tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); -extern int compat_tcp_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen); -extern int compat_tcp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen); -extern void tcp_set_keepalive(struct sock *sk, int val); -extern void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req); -extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len, int nonblock, int flags, int *addr_len); -extern void tcp_parse_options(const struct sk_buff *skb, - struct tcp_options_received *opt_rx, - int estab, struct tcp_fastopen_cookie *foc); -extern const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); +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_parse_options(const struct sk_buff *skb, + struct tcp_options_received *opt_rx, + int estab, struct tcp_fastopen_cookie *foc); +const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); /* * TCP v4 functions exported for the inet6 API */ -extern void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); -extern int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); -extern struct sock * tcp_create_openreq_child(struct sock *sk, - struct request_sock *req, - struct sk_buff *skb); -extern struct sock * tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct dst_entry *dst); -extern int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); -extern int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, - int addr_len); -extern int tcp_connect(struct sock *sk); -extern struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst, - struct request_sock *req, - struct tcp_fastopen_cookie *foc); -extern int tcp_disconnect(struct sock *sk, int flags); - -void tcp_connect_init(struct sock *sk); +void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); +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, + struct sk_buff *skb); +struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct dst_entry *dst); +int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); +int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); +int tcp_connect(struct sock *sk); +struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, + struct request_sock *req, + struct tcp_fastopen_cookie *foc); +int tcp_disconnect(struct sock *sk, int flags); + void tcp_finish_connect(struct sock *sk, struct sk_buff *skb); 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 */ -extern __u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS]; -extern int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, - u32 cookie); -extern struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, - struct ip_options *opt); +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, + struct ip_options *opt); #ifdef CONFIG_SYN_COOKIES -extern u32 __cookie_v4_init_sequence(const struct iphdr *iph, - const struct tcphdr *th, u16 *mssp); -extern __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, - __u16 *mss); + +/* Syncookies use a monotonic timer which increments every 60 seconds. + * This counter is used both as a hash input and partially encoded into + * the cookie value. A cookie is only validated further if the delta + * between the current counter value and the encoded one is less than this, + * 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 + +static inline u32 tcp_cookie_time(void) +{ + u64 val = get_jiffies_64(); + + do_div(val, 60 * HZ); + return val; +} + +u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, + u16 *mssp); +__u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mss); #else static inline __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, @@ -495,19 +503,19 @@ static inline __u32 cookie_v4_init_sequence(struct sock *sk, } #endif -extern __u32 cookie_init_timestamp(struct request_sock *req); -extern bool cookie_check_timestamp(struct tcp_options_received *opt, - struct net *net, bool *ecn_ok); +__u32 cookie_init_timestamp(struct request_sock *req); +bool cookie_check_timestamp(struct tcp_options_received *opt, struct net *net, + bool *ecn_ok); /* From net/ipv6/syncookies.c */ -extern int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th, - u32 cookie); -extern struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb); +int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th, + u32 cookie); +struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb); #ifdef CONFIG_SYN_COOKIES -extern u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, - const struct tcphdr *th, u16 *mssp); -extern __u32 cookie_v6_init_sequence(struct sock *sk, const struct sk_buff *skb, - __u16 *mss); +u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, + const struct tcphdr *th, u16 *mssp); +__u32 cookie_v6_init_sequence(struct sock *sk, const struct sk_buff *skb, + __u16 *mss); #else static inline __u32 cookie_v6_init_sequence(struct sock *sk, struct sk_buff *skb, @@ -518,47 +526,45 @@ static inline __u32 cookie_v6_init_sequence(struct sock *sk, #endif /* tcp_output.c */ -extern void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, - int nonagle); -extern bool tcp_may_send_now(struct sock *sk); -extern int __tcp_retransmit_skb(struct sock *, struct sk_buff *); -extern int tcp_retransmit_skb(struct sock *, struct sk_buff *); -extern void tcp_retransmit_timer(struct sock *sk); -extern void tcp_xmit_retransmit_queue(struct sock *); -extern void tcp_simple_retransmit(struct sock *); -extern int tcp_trim_head(struct sock *, struct sk_buff *, u32); -extern int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int); - -extern void tcp_send_probe0(struct sock *); -extern void tcp_send_partial(struct sock *); -extern int tcp_write_wakeup(struct sock *); -extern void tcp_send_fin(struct sock *sk); -extern void tcp_send_active_reset(struct sock *sk, gfp_t priority); -extern int tcp_send_synack(struct sock *); -extern bool tcp_syn_flood_action(struct sock *sk, - const struct sk_buff *skb, - const char *proto); -extern void tcp_push_one(struct sock *, unsigned int mss_now); -extern void tcp_send_ack(struct sock *sk); -extern void tcp_send_delayed_ack(struct sock *sk); -extern void tcp_send_loss_probe(struct sock *sk); -extern bool tcp_schedule_loss_probe(struct sock *sk); +void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, + int nonagle); +bool tcp_may_send_now(struct sock *sk); +int __tcp_retransmit_skb(struct sock *, struct sk_buff *); +int tcp_retransmit_skb(struct sock *, struct sk_buff *); +void tcp_retransmit_timer(struct sock *sk); +void tcp_xmit_retransmit_queue(struct sock *); +void tcp_simple_retransmit(struct sock *); +int tcp_trim_head(struct sock *, struct sk_buff *, u32); +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 *); +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); +void tcp_send_loss_probe(struct sock *sk); +bool tcp_schedule_loss_probe(struct sock *sk); /* tcp_input.c */ -extern void tcp_cwnd_application_limited(struct sock *sk); -extern void tcp_resume_early_retransmit(struct sock *sk); -extern void tcp_rearm_rto(struct sock *sk); -extern void tcp_reset(struct sock *sk); +void tcp_resume_early_retransmit(struct sock *sk); +void tcp_rearm_rto(struct sock *sk); +void tcp_reset(struct sock *sk); /* tcp_timer.c */ -extern void tcp_init_xmit_timers(struct sock *); +void tcp_init_xmit_timers(struct sock *); static inline void tcp_clear_xmit_timers(struct sock *sk) { inet_csk_clear_xmit_timers(sk); } -extern unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu); -extern unsigned int tcp_current_mss(struct sock *sk); +unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu); +unsigned int tcp_current_mss(struct sock *sk); /* Bound MSS / TSO packet size with the half of the window */ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize) @@ -584,20 +590,20 @@ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize) } /* tcp.c */ -extern void tcp_get_info(const struct sock *, struct tcp_info *); +void tcp_get_info(const struct sock *, struct tcp_info *); /* Read 'sendfile()'-style from a TCP socket */ typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, unsigned int, size_t); -extern int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, - sk_read_actor_t recv_actor); +int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, + sk_read_actor_t recv_actor); -extern void tcp_initialize_rcv_mss(struct sock *sk); +void tcp_initialize_rcv_mss(struct sock *sk); -extern int tcp_mtu_to_mss(struct sock *sk, int pmtu); -extern int tcp_mss_to_mtu(struct sock *sk, int mss); -extern void tcp_mtup_init(struct sock *sk); -extern void tcp_init_buffer_space(struct sock *sk); +int tcp_mtu_to_mss(struct sock *sk, int pmtu); +int tcp_mss_to_mtu(struct sock *sk, int mss); +void tcp_mtup_init(struct sock *sk); +void tcp_init_buffer_space(struct sock *sk); static inline void tcp_bound_rto(const struct sock *sk) { @@ -607,11 +613,9 @@ static inline void tcp_bound_rto(const struct sock *sk) static inline u32 __tcp_set_rto(const struct tcp_sock *tp) { - return (tp->srtt >> 3) + tp->rttvar; + return usecs_to_jiffies((tp->srtt_us >> 3) + tp->rttvar_us); } -extern void tcp_set_rto(struct sock *sk); - static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd) { tp->pred_flags = htonl((tp->tcp_header_len << 26) | @@ -646,6 +650,11 @@ static inline u32 tcp_rto_min(struct sock *sk) return rto_min; } +static inline u32 tcp_rto_min_us(struct sock *sk) +{ + return jiffies_to_usecs(tcp_rto_min(sk)); +} + /* Compute the actual receive window we are currently advertising. * Rcv_nxt can be after the window if our peer push more data * than the offered window. @@ -663,7 +672,7 @@ static inline u32 tcp_receive_window(const struct tcp_sock *tp) * scaling applied to the result. The caller does these things * if necessary. This is a "raw" window selection. */ -extern u32 __tcp_select_window(struct sock *sk); +u32 __tcp_select_window(struct sock *sk); void tcp_send_window_probe(struct sock *sk); @@ -768,7 +777,6 @@ enum tcp_ca_event { #define TCP_CA_BUF_MAX (TCP_CA_NAME_MAX*TCP_CA_MAX) #define TCP_CONG_NON_RESTRICTED 0x1 -#define TCP_CONG_RTT_STAMP 0x2 struct tcp_congestion_ops { struct list_head list; @@ -781,10 +789,8 @@ struct tcp_congestion_ops { /* return slow start threshold (required) */ u32 (*ssthresh)(struct sock *sk); - /* lower bound for congestion window (optional) */ - u32 (*min_cwnd)(const struct sock *sk); /* do new cwnd calculation (required) */ - void (*cong_avoid)(struct sock *sk, u32 ack, u32 in_flight); + void (*cong_avoid)(struct sock *sk, u32 ack, u32 acked); /* call before changing ca_state (optional) */ void (*set_state)(struct sock *sk, u8 new_state); /* call when cwnd event occurs (optional) */ @@ -800,24 +806,23 @@ struct tcp_congestion_ops { struct module *owner; }; -extern int tcp_register_congestion_control(struct tcp_congestion_ops *type); -extern void tcp_unregister_congestion_control(struct tcp_congestion_ops *type); +int tcp_register_congestion_control(struct tcp_congestion_ops *type); +void tcp_unregister_congestion_control(struct tcp_congestion_ops *type); -extern void tcp_init_congestion_control(struct sock *sk); -extern void tcp_cleanup_congestion_control(struct sock *sk); -extern int tcp_set_default_congestion_control(const char *name); -extern void tcp_get_default_congestion_control(char *name); -extern void tcp_get_available_congestion_control(char *buf, size_t len); -extern void tcp_get_allowed_congestion_control(char *buf, size_t len); -extern int tcp_set_allowed_congestion_control(char *allowed); -extern int tcp_set_congestion_control(struct sock *sk, const char *name); -extern void tcp_slow_start(struct tcp_sock *tp); -extern void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w); +void tcp_init_congestion_control(struct sock *sk); +void tcp_cleanup_congestion_control(struct sock *sk); +int tcp_set_default_congestion_control(const char *name); +void tcp_get_default_congestion_control(char *name); +void tcp_get_available_congestion_control(char *buf, size_t len); +void tcp_get_allowed_congestion_control(char *buf, size_t len); +int tcp_set_allowed_congestion_control(char *allowed); +int tcp_set_congestion_control(struct sock *sk, const char *name); +int tcp_slow_start(struct tcp_sock *tp, u32 acked); +void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w); extern struct tcp_congestion_ops tcp_init_congestion_ops; -extern u32 tcp_reno_ssthresh(struct sock *sk); -extern void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight); -extern u32 tcp_reno_min_cwnd(const struct sock *sk); +u32 tcp_reno_ssthresh(struct sock *sk); +void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked); extern struct tcp_congestion_ops tcp_reno; static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state) @@ -936,8 +941,8 @@ static inline __u32 tcp_current_ssthresh(const struct sock *sk) /* Use define here intentionally to get WARN_ON location shown at the caller */ #define tcp_verify_left_out(tp) WARN_ON(tcp_left_out(tp) > tp->packets_out) -extern void tcp_enter_cwr(struct sock *sk, const int set_ssthresh); -extern __u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst); +void tcp_enter_cwr(struct sock *sk, const int set_ssthresh); +__u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst); /* The maximum number of MSS of available cwnd for which TSO defers * sending if not using sysctl_tcp_tso_win_divisor. @@ -963,13 +968,29 @@ static inline u32 tcp_wnd_end(const struct tcp_sock *tp) { return tp->snd_una + tp->snd_wnd; } -extern bool tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight); -static inline void tcp_minshall_update(struct tcp_sock *tp, unsigned int mss, - const struct sk_buff *skb) +/* We follow the spirit of RFC2861 to validate cwnd but implement a more + * flexible approach. The RFC suggests cwnd should not be raised unless + * it was fully used previously. And that's exactly what we do in + * congestion avoidance mode. But in slow start we allow cwnd to grow + * as long as the application has used half the cwnd. + * Example : + * cwnd is 10 (IW10), but application sends 9 frames. + * We allow cwnd to reach 18 when all frames are ACKed. + * This check is safe because it's as aggressive as slow start which already + * risks 100% overshoot. The advantage is that we discourage application to + * either send more filler packets or data to artificially blow up the cwnd + * usage, and allow application-limited process to probe bw more aggressively. + */ +static inline bool tcp_is_cwnd_limited(const struct sock *sk) { - if (skb->len < mss) - tp->snd_sml = TCP_SKB_CB(skb)->end_seq; + const struct tcp_sock *tp = tcp_sk(sk); + + /* If in slow start, ensure cwnd grows to twice what was ACKed. */ + if (tp->snd_cwnd <= tp->snd_ssthresh) + return tp->snd_cwnd < 2 * tp->max_packets_out; + + return tp->is_cwnd_limited; } static inline void tcp_check_probe_timer(struct sock *sk) @@ -1028,7 +1049,7 @@ static inline void tcp_prequeue_init(struct tcp_sock *tp) #endif } -extern bool tcp_prequeue(struct sock *sk, struct sk_buff *skb); +bool tcp_prequeue(struct sock *sk, struct sk_buff *skb); #undef STATE_TRACE @@ -1039,9 +1060,9 @@ static const char *statename[]={ "Close Wait","Last ACK","Listen","Closing" }; #endif -extern void tcp_set_state(struct sock *sk, int state); +void tcp_set_state(struct sock *sk, int state); -extern void tcp_done(struct sock *sk); +void tcp_done(struct sock *sk); static inline void tcp_sack_reset(struct tcp_options_received *rx_opt) { @@ -1049,13 +1070,12 @@ static inline void tcp_sack_reset(struct tcp_options_received *rx_opt) rx_opt->num_sacks = 0; } -extern u32 tcp_default_init_rwnd(u32 mss); +u32 tcp_default_init_rwnd(u32 mss); /* Determine a window scaling and initial window to offer. */ -extern void tcp_select_initial_window(int __space, __u32 mss, - __u32 *rcv_wnd, __u32 *window_clamp, - int wscale_ok, __u8 *rcv_wscale, - __u32 init_rcv_wnd); +void tcp_select_initial_window(int __space, __u32 mss, __u32 *rcv_wnd, + __u32 *window_clamp, int wscale_ok, + __u8 *rcv_wscale, __u32 init_rcv_wnd); static inline int tcp_win_from_space(int space) { @@ -1095,11 +1115,14 @@ static inline void tcp_openreq_init(struct request_sock *req, ireq->wscale_ok = rx_opt->wscale_ok; ireq->acked = 0; ireq->ecn_ok = 0; - ireq->rmt_port = tcp_hdr(skb)->source; - ireq->loc_port = tcp_hdr(skb)->dest; + ireq->ir_rmt_port = tcp_hdr(skb)->source; + ireq->ir_num = ntohs(tcp_hdr(skb)->dest); } -extern void tcp_enter_memory_pressure(struct sock *sk); +extern void tcp_openreq_init_rwin(struct request_sock *req, + struct sock *sk, struct dst_entry *dst); + +void tcp_enter_memory_pressure(struct sock *sk); static inline int keepalive_intvl_when(const struct tcp_sock *tp) { @@ -1252,21 +1275,20 @@ struct tcp_md5sig_pool { }; /* - functions */ -extern 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); -extern int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, - int family, const u8 *newkey, - u8 newkeylen, gfp_t gfp); -extern int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, - int family); -extern struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk, +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_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); #ifdef CONFIG_TCP_MD5SIG -extern struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, - const union tcp_md5_addr *addr, int family); +struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, + const union tcp_md5_addr *addr, + int family); #define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_key) #else static inline struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, @@ -1278,40 +1300,42 @@ static inline struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, #define tcp_twsk_md5_key(twsk) NULL #endif -extern bool tcp_alloc_md5sig_pool(void); +bool tcp_alloc_md5sig_pool(void); -extern struct tcp_md5sig_pool *tcp_get_md5sig_pool(void); +struct tcp_md5sig_pool *tcp_get_md5sig_pool(void); static inline void tcp_put_md5sig_pool(void) { local_bh_enable(); } -extern int tcp_md5_hash_header(struct tcp_md5sig_pool *, const struct tcphdr *); -extern int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, const struct sk_buff *, - unsigned int header_len); -extern int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, - const struct tcp_md5sig_key *key); +int tcp_md5_hash_header(struct tcp_md5sig_pool *, const struct tcphdr *); +int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, const struct sk_buff *, + unsigned int header_len); +int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, + const struct tcp_md5sig_key *key); /* From tcp_fastopen.c */ -extern void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, - struct tcp_fastopen_cookie *cookie, - int *syn_loss, unsigned long *last_syn_loss); -extern void tcp_fastopen_cache_set(struct sock *sk, u16 mss, - struct tcp_fastopen_cookie *cookie, - bool syn_lost); +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_request { /* Fast Open cookie. Size 0 means a cookie request */ struct tcp_fastopen_cookie cookie; struct msghdr *data; /* data in MSG_FASTOPEN */ - u16 copied; /* queued in tcp_connect() */ + size_t size; + int copied; /* queued in tcp_connect() */ }; void tcp_free_fastopen_req(struct tcp_sock *tp); extern struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; int tcp_fastopen_reset_cipher(void *key, unsigned int len); -extern void tcp_fastopen_cookie_gen(__be32 src, __be32 dst, - struct tcp_fastopen_cookie *foc); - +bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct tcp_fastopen_cookie *foc, + struct dst_entry *dst); +void tcp_fastopen_init_key_once(bool publish); #define TCP_FASTOPEN_KEY_LENGTH 16 /* Fastopen key context */ @@ -1507,7 +1531,6 @@ enum tcp_seq_states { TCP_SEQ_STATE_LISTENING, TCP_SEQ_STATE_OPENREQ, TCP_SEQ_STATE_ESTABLISHED, - TCP_SEQ_STATE_TIME_WAIT, }; int tcp_seq_open(struct inode *inode, struct file *file); @@ -1529,22 +1552,20 @@ struct tcp_iter_state { loff_t last_pos; }; -extern int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo); -extern void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo); +int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo); +void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo); extern struct request_sock_ops tcp_request_sock_ops; extern struct request_sock_ops tcp6_request_sock_ops; -extern void tcp_v4_destroy_sock(struct sock *sk); +void tcp_v4_destroy_sock(struct sock *sk); -extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, - netdev_features_t features); -extern struct sk_buff **tcp_gro_receive(struct sk_buff **head, - struct sk_buff *skb); -extern int tcp_gro_complete(struct sk_buff *skb); +struct sk_buff *tcp_gso_segment(struct sk_buff *skb, + netdev_features_t features); +struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb); +int tcp_gro_complete(struct sk_buff *skb); -extern void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, - __be32 daddr); +void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) { @@ -1560,8 +1581,8 @@ static inline bool tcp_stream_memory_free(const struct sock *sk) } #ifdef CONFIG_PROC_FS -extern int tcp4_proc_init(void); -extern void tcp4_proc_exit(void); +int tcp4_proc_init(void); +void tcp4_proc_exit(void); #endif /* TCP af-specific functions */ @@ -1592,9 +1613,9 @@ struct tcp_request_sock_ops { #endif }; -extern int tcpv4_offload_init(void); +int tcpv4_offload_init(void); -extern void tcp_v4_init(void); -extern void tcp_init(void); +void tcp_v4_init(void); +void tcp_init(void); #endif /* _TCP_H */ |