diff options
Diffstat (limited to 'include/net/tcp.h')
-rw-r--r-- | include/net/tcp.h | 116 |
1 files changed, 93 insertions, 23 deletions
diff --git a/include/net/tcp.h b/include/net/tcp.h index 9c9b3768b350..770917d0caa7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -36,6 +36,7 @@ #include <net/inet_hashtables.h> #include <net/checksum.h> #include <net/request_sock.h> +#include <net/sock_reuseport.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ip.h> @@ -245,6 +246,7 @@ extern long sysctl_tcp_mem[3]; #define TCP_RACK_LOSS_DETECTION 0x1 /* Use RACK to detect losses */ #define TCP_RACK_STATIC_REO_WND 0x2 /* Use static RACK reo wnd */ +#define TCP_RACK_NO_DUPTHRESH 0x4 /* Do not use DUPACK threshold in RACK */ extern atomic_long_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; @@ -333,8 +335,7 @@ 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); -void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, - const struct tcphdr *th); +void tcp_rcv_established(struct sock *sk, struct sk_buff *skb); void tcp_rcv_space_adjust(struct sock *sk); int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp); void tcp_twsk_destructor(struct sock *sk); @@ -342,6 +343,7 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); +void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks); static inline void tcp_dec_quickack_mode(struct sock *sk, const unsigned int pkts) { @@ -402,6 +404,10 @@ void tcp_set_keepalive(struct sock *sk, int val); 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); +int tcp_set_rcvlowat(struct sock *sk, int val); +void tcp_data_ready(struct sock *sk); +int tcp_mmap(struct file *file, struct socket *sock, + struct vm_area_struct *vma); void tcp_parse_options(const struct net *net, const struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab, struct tcp_fastopen_cookie *foc); @@ -468,19 +474,45 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); */ static inline void tcp_synq_overflow(const struct sock *sk) { - unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; - unsigned long now = jiffies; + unsigned int last_overflow; + unsigned int now = jiffies; - if (time_after(now, last_overflow + HZ)) + if (sk->sk_reuseport) { + struct sock_reuseport *reuse; + + reuse = rcu_dereference(sk->sk_reuseport_cb); + if (likely(reuse)) { + last_overflow = READ_ONCE(reuse->synq_overflow_ts); + if (time_after32(now, last_overflow + HZ)) + WRITE_ONCE(reuse->synq_overflow_ts, now); + return; + } + } + + last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; + if (time_after32(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; + unsigned int last_overflow; + unsigned int now = jiffies; - return time_after(jiffies, last_overflow + TCP_SYNCOOKIE_VALID); + if (sk->sk_reuseport) { + struct sock_reuseport *reuse; + + reuse = rcu_dereference(sk->sk_reuseport_cb); + if (likely(reuse)) { + last_overflow = READ_ONCE(reuse->synq_overflow_ts); + return time_after32(now, last_overflow + + TCP_SYNCOOKIE_VALID); + } + } + + last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; + return time_after32(now, last_overflow + TCP_SYNCOOKIE_VALID); } static inline u32 tcp_cookie_time(void) @@ -535,6 +567,7 @@ void tcp_send_fin(struct sock *sk); void tcp_send_active_reset(struct sock *sk, gfp_t priority); int tcp_send_synack(struct sock *); void tcp_push_one(struct sock *, unsigned int mss_now); +void __tcp_send_ack(struct sock *sk, u32 rcv_nxt); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); void tcp_send_loss_probe(struct sock *sk); @@ -553,7 +586,12 @@ void tcp_fin(struct sock *sk); void tcp_init_xmit_timers(struct sock *); static inline void tcp_clear_xmit_timers(struct sock *sk) { - hrtimer_cancel(&tcp_sk(sk)->pacing_timer); + if (hrtimer_try_to_cancel(&tcp_sk(sk)->pacing_timer) == 1) + __sock_put(sk); + + if (hrtimer_try_to_cancel(&tcp_sk(sk)->compressed_ack_timer) == 1) + __sock_put(sk); + inet_csk_clear_xmit_timers(sk); } @@ -810,9 +848,8 @@ struct tcp_skb_cb { #endif } header; /* For incoming skbs */ struct { - __u32 key; __u32 flags; - struct bpf_map *map; + struct sock *sk_redir; void *data_end; } bpf; }; @@ -820,6 +857,10 @@ struct tcp_skb_cb { #define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0])) +static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb) +{ + TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb); +} #if IS_ENABLED(CONFIG_IPV6) /* This is the variant of inet6_iif() that must be used by TCP, @@ -827,6 +868,11 @@ struct tcp_skb_cb { */ static inline int tcp_v6_iif(const struct sk_buff *skb) { + return TCP_SKB_CB(skb)->header.h6.iif; +} + +static inline int tcp_v6_iif_l3_slave(const struct sk_buff *skb) +{ bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags); return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif; @@ -900,8 +946,6 @@ enum tcp_ca_event { CA_EVENT_LOSS, /* loss timeout */ CA_EVENT_ECN_NO_CE, /* ECT set, but not CE marked */ CA_EVENT_ECN_IS_CE, /* received CE marked IP packet */ - CA_EVENT_DELAYED_ACK, /* Delayed ack is sent */ - CA_EVENT_NON_DELAYED_ACK, }; /* Information about inbound ACK, passed to cong_ops->in_ack_event() */ @@ -946,6 +990,8 @@ struct rate_sample { u32 prior_delivered; /* tp->delivered at "prior_mstamp" */ s32 delivered; /* number of packets delivered over interval */ long interval_us; /* time for tp->delivered to incr "delivered" */ + u32 snd_interval_us; /* snd interval for delivered packets */ + u32 rcv_interval_us; /* rcv interval for delivered packets */ long rtt_us; /* RTT of last (S)ACKed packet (or -1) */ int losses; /* number of packets marked lost upon ACK */ u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ @@ -1177,6 +1223,17 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk) return tp->is_cwnd_limited; } +/* BBR congestion control needs pacing. + * Same remark for SO_MAX_PACING_RATE. + * sch_fq packet scheduler is efficiently handling pacing, + * but is not always installed/used. + * Return true if TCP stack should pace packets itself. + */ +static inline bool tcp_needs_internal_pacing(const struct sock *sk) +{ + return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED; +} + /* 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, @@ -1354,7 +1411,8 @@ static inline bool tcp_paws_check(const struct tcp_options_received *rx_opt, { if ((s32)(rx_opt->ts_recent - rx_opt->rcv_tsval) <= paws_win) return true; - if (unlikely(get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS)) + if (unlikely(!time_before32(ktime_get_seconds(), + rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS))) return true; /* * Some OSes send SYN and SYNACK messages with tsval=0 tsecr=0, @@ -1384,7 +1442,8 @@ static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt, However, we can relax time bounds for RST segments to MSL. */ - if (rst && get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_MSL) + if (rst && !time_before32(ktime_get_seconds(), + rx_opt->ts_recent_stamp + TCP_PAWS_MSL)) return false; return true; } @@ -1747,27 +1806,22 @@ enum tcp_seq_states { TCP_SEQ_STATE_ESTABLISHED, }; -int tcp_seq_open(struct inode *inode, struct file *file); +void *tcp_seq_start(struct seq_file *seq, loff_t *pos); +void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos); +void tcp_seq_stop(struct seq_file *seq, void *v); struct tcp_seq_afinfo { - char *name; sa_family_t family; - const struct file_operations *seq_fops; - struct seq_operations seq_ops; }; struct tcp_iter_state { struct seq_net_private p; - sa_family_t family; enum tcp_seq_states state; struct sock *syn_wait_sk; int bucket, offset, sbucket, num; loff_t last_pos; }; -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; @@ -1775,7 +1829,7 @@ void tcp_v4_destroy_sock(struct sock *sk); 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); +struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb); int tcp_gro_complete(struct sk_buff *skb); void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); @@ -1871,6 +1925,10 @@ void tcp_v4_init(void); void tcp_init(void); /* tcp_recovery.c */ +void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb); +void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced); +extern s32 tcp_rack_skb_timeout(struct tcp_sock *tp, struct sk_buff *skb, + u32 reo_wnd); extern void tcp_rack_mark_lost(struct sock *sk); extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, u64 xmit_time); @@ -2007,6 +2065,10 @@ int tcp_set_ulp_id(struct sock *sk, const int ulp); void tcp_get_available_ulp(char *buf, size_t len); void tcp_cleanup_ulp(struct sock *sk); +#define MODULE_ALIAS_TCP_ULP(name) \ + __MODULE_INFO(alias, alias_userspace, name); \ + __MODULE_INFO(alias, alias_tcp_ulp, "tcp-ulp-" name) + /* Call BPF_SOCK_OPS program that returns an int. If the return value * is < 0, then the BPF op failed (for example if the loaded BPF * program does not support the chosen operation or there is no BPF @@ -2101,4 +2163,12 @@ static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk) #if IS_ENABLED(CONFIG_SMC) extern struct static_key_false tcp_have_smc; #endif + +#if IS_ENABLED(CONFIG_TLS_DEVICE) +void clean_acked_data_enable(struct inet_connection_sock *icsk, + void (*cad)(struct sock *sk, u32 ack_seq)); +void clean_acked_data_disable(struct inet_connection_sock *icsk); + +#endif + #endif /* _TCP_H */ |