diff options
Diffstat (limited to 'include/net/tcp.h')
| -rw-r--r-- | include/net/tcp.h | 1058 |
1 files changed, 792 insertions, 266 deletions
diff --git a/include/net/tcp.h b/include/net/tcp.h index d4ef5bf94168..5078ad868fee 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -26,6 +26,7 @@ #include <linux/kref.h> #include <linux/ktime.h> #include <linux/indirect_call_wrapper.h> +#include <linux/bits.h> #include <net/inet_connection_sock.h> #include <net/inet_timewait_sock.h> @@ -37,9 +38,11 @@ #include <net/snmp.h> #include <net/ip.h> #include <net/tcp_states.h> +#include <net/tcp_ao.h> #include <net/inet_ecn.h> #include <net/dst.h> #include <net/mptcp.h> +#include <net/xfrm.h> #include <linux/seq_file.h> #include <linux/memcontrol.h> @@ -48,7 +51,11 @@ extern struct inet_hashinfo tcp_hashinfo; -extern struct percpu_counter tcp_orphan_count; +DECLARE_PER_CPU(unsigned int, tcp_orphan_count); +int tcp_orphan_count_sum(void); + +DECLARE_PER_CPU(u32, tcp_tw_isn); + void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_HEADER L1_CACHE_ALIGN(128 + MAX_HEADER) @@ -129,6 +136,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCP_FIN_TIMEOUT_MAX (120 * HZ) /* max TCP_LINGER2 value (two minutes) */ #define TCP_DELACK_MAX ((unsigned)(HZ/5)) /* maximal time to delay before sending an ACK */ +static_assert((1 << ATO_BITS) > TCP_DELACK_MAX); + #if HZ >= 100 #define TCP_DELACK_MIN ((unsigned)(HZ/25)) /* minimal time to delay before sending an ACK */ #define TCP_ATO_MIN ((unsigned)(HZ/25)) @@ -136,9 +145,13 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCP_DELACK_MIN 4U #define TCP_ATO_MIN 4U #endif -#define TCP_RTO_MAX ((unsigned)(120*HZ)) -#define TCP_RTO_MIN ((unsigned)(HZ/5)) +#define TCP_RTO_MAX_SEC 120 +#define TCP_RTO_MAX ((unsigned)(TCP_RTO_MAX_SEC * HZ)) +#define TCP_RTO_MIN ((unsigned)(HZ / 5)) #define TCP_TIMEOUT_MIN (2U) /* Min timeout for TCP timers in jiffies */ + +#define TCP_TIMEOUT_MIN_US (2*USEC_PER_MSEC) /* Min TCP timeout in microsecs */ + #define TCP_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */ #define TCP_TIMEOUT_FALLBACK ((unsigned)(3*HZ)) /* RFC 1122 initial RTO value, now * used as a fallback RTO for the @@ -159,9 +172,12 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_KEEPCNT 127 #define MAX_TCP_SYNCNT 127 -#define TCP_SYNQ_INTERVAL (HZ/5) /* Period of SYNACK timer */ +/* Ensure that TCP PAWS checks are relaxed after ~2147 seconds + * to avoid overflows. This assumes a clock smaller than 1 Mhz. + * Default clock is 1 Khz, tcp_usec_ts uses 1 Mhz. + */ +#define TCP_PAWS_WRAP (INT_MAX / USEC_PER_SEC) -#define TCP_PAWS_24DAYS (60 * 60 * 24 * 24) #define TCP_PAWS_MSL 60 /* Per-host timestamps are invalidated * after this time. It should be equal * (or greater than) TCP_TIMEWAIT_LEN @@ -184,6 +200,7 @@ 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_AO 29 /* Authentication Option (RFC5925) */ #define TCPOPT_MPTCP 30 /* Multipath TCP (RFC6824) */ #define TCPOPT_FASTOPEN 34 /* Fast open (RFC7413) */ #define TCPOPT_EXP 254 /* Experimental */ @@ -251,6 +268,8 @@ extern long sysctl_tcp_mem[3]; #define TCP_RACK_NO_DUPTHRESH 0x4 /* Do not use DUPACK threshold in RACK */ extern atomic_long_t tcp_memory_allocated; +DECLARE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc); + extern struct percpu_counter tcp_sockets_allocated; extern unsigned long tcp_memory_pressure; @@ -280,30 +299,19 @@ static inline bool between(__u32 seq1, __u32 seq2, __u32 seq3) return seq3 - seq2 >= seq1 - seq2; } -static inline bool tcp_out_of_memory(struct sock *sk) +static inline void tcp_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { - if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF && - sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2)) - return true; - return false; + sk_wmem_queued_add(sk, -skb->truesize); + if (!skb_zcopy_pure(skb)) + sk_mem_uncharge(sk, skb->truesize); + else + sk_mem_uncharge(sk, SKB_TRUESIZE(skb_end_offset(skb))); + __kfree_skb(skb); } 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; - int orphans = percpu_counter_read_positive(ocp); - - if (orphans << shift > sysctl_tcp_max_orphans) { - orphans = percpu_counter_sum_positive(ocp); - if (orphans << shift > sysctl_tcp_max_orphans) - return true; - } - return false; -} - -bool tcp_check_oom(struct sock *sk, int shift); +bool tcp_check_oom(const struct sock *sk, int shift); extern struct proto tcp_prot; @@ -322,39 +330,41 @@ void tcp_shutdown(struct sock *sk, int how); int 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); +void tcp_remove_empty_skb(struct sock *sk); int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_locked(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); -int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, - size_t size, int flags); -ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, - size_t size, int flags); +int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, + size_t size, struct ubuf_info *uarg); +void tcp_splice_eof(struct socket *sock); int tcp_send_mss(struct sock *sk, int *size_goal, int flags); +int tcp_wmem_schedule(struct sock *sk, int copy); void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle, int size_goal); 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); +int tcp_ioctl(struct sock *sk, int cmd, int *karg); +enum skb_drop_reason tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb); 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); +void tcp_twsk_purge(struct list_head *net_exit_list); ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); +struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp, + bool force_schedule); -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) +static inline void tcp_dec_quickack_mode(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ack.quick) { + /* How many ACKs S/ACKing new data have we sent? */ + const unsigned int pkts = inet_csk_ack_scheduled(sk) ? 1 : 0; + if (pkts >= icsk->icsk_ack.quick) { icsk->icsk_ack.quick = 0; /* Leaving quickack mode we deflate ATO. */ @@ -364,48 +374,99 @@ static inline void tcp_dec_quickack_mode(struct sock *sk, } } -#define TCP_ECN_OK 1 -#define TCP_ECN_QUEUE_CWR 2 -#define TCP_ECN_DEMAND_CWR 4 -#define TCP_ECN_SEEN 8 +#define TCP_ECN_MODE_RFC3168 BIT(0) +#define TCP_ECN_QUEUE_CWR BIT(1) +#define TCP_ECN_DEMAND_CWR BIT(2) +#define TCP_ECN_SEEN BIT(3) +#define TCP_ECN_MODE_ACCECN BIT(4) + +#define TCP_ECN_DISABLED 0 +#define TCP_ECN_MODE_PENDING (TCP_ECN_MODE_RFC3168 | TCP_ECN_MODE_ACCECN) +#define TCP_ECN_MODE_ANY (TCP_ECN_MODE_RFC3168 | TCP_ECN_MODE_ACCECN) + +static inline bool tcp_ecn_mode_any(const struct tcp_sock *tp) +{ + return tp->ecn_flags & TCP_ECN_MODE_ANY; +} + +static inline bool tcp_ecn_mode_rfc3168(const struct tcp_sock *tp) +{ + return (tp->ecn_flags & TCP_ECN_MODE_ANY) == TCP_ECN_MODE_RFC3168; +} + +static inline bool tcp_ecn_mode_accecn(const struct tcp_sock *tp) +{ + return (tp->ecn_flags & TCP_ECN_MODE_ANY) == TCP_ECN_MODE_ACCECN; +} + +static inline bool tcp_ecn_disabled(const struct tcp_sock *tp) +{ + return !tcp_ecn_mode_any(tp); +} + +static inline bool tcp_ecn_mode_pending(const struct tcp_sock *tp) +{ + return (tp->ecn_flags & TCP_ECN_MODE_PENDING) == TCP_ECN_MODE_PENDING; +} + +static inline void tcp_ecn_mode_set(struct tcp_sock *tp, u8 mode) +{ + tp->ecn_flags &= ~TCP_ECN_MODE_ANY; + tp->ecn_flags |= mode; +} enum tcp_tw_status { TCP_TW_SUCCESS = 0, TCP_TW_RST = 1, TCP_TW_ACK = 2, - TCP_TW_SYN = 3 + TCP_TW_SYN = 3, + TCP_TW_ACK_OOW = 4 }; enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, - const struct tcphdr *th); + const struct tcphdr *th, + u32 *tw_isn, + enum skb_drop_reason *drop_reason); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, bool fastopen, - bool *lost_race); -int tcp_child_process(struct sock *parent, struct sock *child, - struct sk_buff *skb); + bool *lost_race, enum skb_drop_reason *drop_reason); +enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child, + struct sk_buff *skb); void tcp_enter_loss(struct sock *sk); -void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag); +void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int newly_lost, int flag); 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); +void __tcp_close(struct sock *sk, long timeout); void tcp_close(struct sock *sk, long timeout); void tcp_init_sock(struct sock *sk); void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb); __poll_t tcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); +int do_tcp_getsockopt(struct sock *sk, int level, + int optname, sockptr_t optval, sockptr_t optlen); int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); +bool tcp_bpf_bypass_getsockopt(int level, int optname); +int do_tcp_setsockopt(struct sock *sk, int level, int optname, + sockptr_t optval, unsigned int optlen); int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); +void tcp_reset_keepalive_timer(struct sock *sk, unsigned long timeout); 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 tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len); int tcp_set_rcvlowat(struct sock *sk, int val); +int tcp_set_window_clamp(struct sock *sk, int val); +void tcp_update_recv_tstamps(struct sk_buff *skb, + struct scm_timestamping_internal *tss); +void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, + struct scm_timestamping_internal *tss); void tcp_data_ready(struct sock *sk); #ifdef CONFIG_MMU int tcp_mmap(struct file *file, struct socket *sock, @@ -414,7 +475,6 @@ int tcp_mmap(struct file *file, struct socket *sock, 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); -const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); /* * BPF SKB-less helpers @@ -423,6 +483,7 @@ u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, struct tcphdr *th, u32 *cookie); u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph, struct tcphdr *th, u32 *cookie); +u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss); u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct tcphdr *th); @@ -466,12 +527,30 @@ 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, u32 tsoff); -int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, - u32 cookie); + struct dst_entry *dst); +int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, - struct sock *sk, struct sk_buff *skb); + struct sock *sk, struct sk_buff *skb, + struct tcp_options_received *tcp_opt, + int mss, u32 tsoff); + +#if IS_ENABLED(CONFIG_BPF) +struct bpf_tcp_req_attrs { + u32 rcv_tsval; + u32 rcv_tsecr; + u16 mss; + u8 rcv_wscale; + u8 snd_wscale; + u8 ecn_ok; + u8 wscale_ok; + u8 sack_ok; + u8 tstamp_ok; + u8 usec_ts_ok; + u8 reserved[3]; +}; +#endif + #ifdef CONFIG_SYN_COOKIES /* Syncookies use a monotonic timer which increments every 60 seconds. @@ -509,7 +588,7 @@ static inline void tcp_synq_overflow(const struct sock *sk) last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp); if (!time_between32(now, last_overflow, last_overflow + HZ)) - WRITE_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp, now); + WRITE_ONCE(tcp_sk_rw(sk)->rx_opt.ts_recent_stamp, now); } /* syncookies: no recent synqueue overflow on this listening socket? */ @@ -551,18 +630,50 @@ static inline u32 tcp_cookie_time(void) return val; } +/* Convert one nsec 64bit timestamp to ts (ms or usec resolution) */ +static inline u64 tcp_ns_to_ts(bool usec_ts, u64 val) +{ + if (usec_ts) + return div_u64(val, NSEC_PER_USEC); + + return div_u64(val, NSEC_PER_MSEC); +} + u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, u16 *mssp); __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss); u64 cookie_init_timestamp(struct request_sock *req, u64 now); bool cookie_timestamp_decode(const struct net *net, struct tcp_options_received *opt); -bool cookie_ecn_ok(const struct tcp_options_received *opt, - const struct net *net, const struct dst_entry *dst); + +static inline bool cookie_ecn_ok(const struct net *net, const struct dst_entry *dst) +{ + return READ_ONCE(net->ipv4.sysctl_tcp_ecn) || + dst_feature(dst, RTAX_FEATURE_ECN); +} + +#if IS_ENABLED(CONFIG_BPF) +static inline bool cookie_bpf_ok(struct sk_buff *skb) +{ + return skb->sk; +} + +struct request_sock *cookie_bpf_check(struct sock *sk, struct sk_buff *skb); +#else +static inline bool cookie_bpf_ok(struct sk_buff *skb) +{ + return false; +} + +static inline struct request_sock *cookie_bpf_check(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + return NULL; +} +#endif /* From net/ipv6/syncookies.c */ -int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th, - u32 cookie); +int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th); struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb); u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, @@ -571,6 +682,8 @@ __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss); #endif /* tcp_output.c */ +void tcp_skb_entail(struct sock *sk, struct sk_buff *skb); +void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb); void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle); int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); @@ -589,13 +702,13 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, unsigned int mss_now, gfp_t gfp); void tcp_send_probe0(struct sock *); -void tcp_send_partial(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); +void tcp_send_active_reset(struct sock *sk, gfp_t priority, + enum sk_rst_reason reason); 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, u32 rcv_nxt, u16 flags); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); void tcp_send_loss_probe(struct sock *sk); @@ -606,9 +719,24 @@ void tcp_skb_collapse_tstamp(struct sk_buff *skb, /* tcp_input.c */ void tcp_rearm_rto(struct sock *sk); void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); -void tcp_reset(struct sock *sk); -void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb); +void tcp_done_with_error(struct sock *sk, int err); +void tcp_reset(struct sock *sk, struct sk_buff *skb); void tcp_fin(struct sock *sk); +void tcp_check_space(struct sock *sk); +void tcp_sack_compress_send_ack(struct sock *sk); + +static inline void tcp_cleanup_skb(struct sk_buff *skb) +{ + skb_dst_drop(skb); + secpath_reset(skb); +} + +static inline void tcp_add_receive_queue(struct sock *sk, struct sk_buff *skb) +{ + DEBUG_NET_WARN_ON_ONCE(skb_dst(skb)); + DEBUG_NET_WARN_ON_ONCE(secpath_exists(skb)); + __skb_queue_tail(&sk->sk_receive_queue, skb); +} /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); @@ -625,6 +753,7 @@ static inline void tcp_clear_xmit_timers(struct sock *sk) unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu); unsigned int tcp_current_mss(struct sock *sk); +u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when); /* 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) @@ -655,6 +784,12 @@ void tcp_get_info(struct sock *, struct tcp_info *); /* Read 'sendfile()'-style from a TCP socket */ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); +int tcp_read_sock_noack(struct sock *sk, read_descriptor_t *desc, + sk_read_actor_t recv_actor, bool noack, + u32 *copied_seq); +int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor); +struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off); +void tcp_read_done(struct sock *sk, size_t len); void tcp_initialize_rcv_mss(struct sock *sk); @@ -662,10 +797,14 @@ 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); -static inline void tcp_bound_rto(const struct sock *sk) +static inline unsigned int tcp_rto_max(const struct sock *sk) +{ + return READ_ONCE(inet_csk(sk)->icsk_rto_max); +} + +static inline void tcp_bound_rto(struct sock *sk) { - if (inet_csk(sk)->icsk_rto > TCP_RTO_MAX) - inet_csk(sk)->icsk_rto = TCP_RTO_MAX; + inet_csk(sk)->icsk_rto = min(inet_csk(sk)->icsk_rto, tcp_rto_max(sk)); } static inline u32 __tcp_set_rto(const struct tcp_sock *tp) @@ -675,6 +814,10 @@ static inline u32 __tcp_set_rto(const struct tcp_sock *tp) static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd) { + /* mptcp hooks are only on the slow path */ + if (sk_is_mptcp((struct sock *)tp)) + return; + tp->pred_flags = htonl((tp->tcp_header_len << 26) | ntohl(TCP_FLAG_ACK) | snd_wnd); @@ -696,18 +839,20 @@ static inline void tcp_fast_path_check(struct sock *sk) tcp_fast_path_on(tp); } +u32 tcp_delack_max(const struct sock *sk); + /* Compute the actual rto_min value */ -static inline u32 tcp_rto_min(struct sock *sk) +static inline u32 tcp_rto_min(const struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); - u32 rto_min = inet_csk(sk)->icsk_rto_min; + u32 rto_min = READ_ONCE(inet_csk(sk)->icsk_rto_min); if (dst && dst_metric_locked(dst, RTAX_RTO_MIN)) rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN); return rto_min; } -static inline u32 tcp_rto_min_us(struct sock *sk) +static inline u32 tcp_rto_min_us(const struct sock *sk) { return jiffies_to_usecs(tcp_rto_min(sk)); } @@ -767,22 +912,31 @@ static inline u64 tcp_clock_us(void) return div_u64(tcp_clock_ns(), NSEC_PER_USEC); } -/* This should only be used in contexts where tp->tcp_mstamp is up to date */ -static inline u32 tcp_time_stamp(const struct tcp_sock *tp) +static inline u64 tcp_clock_ms(void) +{ + return div_u64(tcp_clock_ns(), NSEC_PER_MSEC); +} + +/* TCP Timestamp included in TS option (RFC 1323) can either use ms + * or usec resolution. Each socket carries a flag to select one or other + * resolution, as the route attribute could change anytime. + * Each flow must stick to initial resolution. + */ +static inline u32 tcp_clock_ts(bool usec_ts) { - return div_u64(tp->tcp_mstamp, USEC_PER_SEC / TCP_TS_HZ); + return usec_ts ? tcp_clock_us() : tcp_clock_ms(); } -/* Convert a nsec timestamp into TCP TSval timestamp (ms based currently) */ -static inline u32 tcp_ns_to_ts(u64 ns) +static inline u32 tcp_time_stamp_ms(const struct tcp_sock *tp) { - return div_u64(ns, NSEC_PER_SEC / TCP_TS_HZ); + return div_u64(tp->tcp_mstamp, USEC_PER_MSEC); } -/* Could use tcp_clock_us() / 1000, but this version uses a single divide */ -static inline u32 tcp_time_stamp_raw(void) +static inline u32 tcp_time_stamp_ts(const struct tcp_sock *tp) { - return tcp_ns_to_ts(tcp_clock_ns()); + if (tp->tcp_usec_ts) + return tp->tcp_mstamp; + return tcp_time_stamp_ms(tp); } void tcp_mstamp_refresh(struct tcp_sock *tp); @@ -792,31 +946,64 @@ static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) return max_t(s64, t1 - t0, 0); } -static inline u32 tcp_skb_timestamp(const struct sk_buff *skb) -{ - return tcp_ns_to_ts(skb->skb_mstamp_ns); -} - /* provide the departure time in us unit */ static inline u64 tcp_skb_timestamp_us(const struct sk_buff *skb) { return div_u64(skb->skb_mstamp_ns, NSEC_PER_USEC); } +/* Provide skb TSval in usec or ms unit */ +static inline u32 tcp_skb_timestamp_ts(bool usec_ts, const struct sk_buff *skb) +{ + if (usec_ts) + return tcp_skb_timestamp_us(skb); -#define tcp_flag_byte(th) (((u_int8_t *)th)[13]) + return div_u64(skb->skb_mstamp_ns, NSEC_PER_MSEC); +} -#define TCPHDR_FIN 0x01 -#define TCPHDR_SYN 0x02 -#define TCPHDR_RST 0x04 -#define TCPHDR_PSH 0x08 -#define TCPHDR_ACK 0x10 -#define TCPHDR_URG 0x20 -#define TCPHDR_ECE 0x40 -#define TCPHDR_CWR 0x80 +static inline u32 tcp_tw_tsval(const struct tcp_timewait_sock *tcptw) +{ + return tcp_clock_ts(tcptw->tw_sk.tw_usec_ts) + tcptw->tw_ts_offset; +} +static inline u32 tcp_rsk_tsval(const struct tcp_request_sock *treq) +{ + return tcp_clock_ts(treq->req_usec_ts) + treq->ts_off; +} + +#define tcp_flag_byte(th) (((u_int8_t *)th)[13]) + +#define TCPHDR_FIN BIT(0) +#define TCPHDR_SYN BIT(1) +#define TCPHDR_RST BIT(2) +#define TCPHDR_PSH BIT(3) +#define TCPHDR_ACK BIT(4) +#define TCPHDR_URG BIT(5) +#define TCPHDR_ECE BIT(6) +#define TCPHDR_CWR BIT(7) +#define TCPHDR_AE BIT(8) +#define TCPHDR_FLAGS_MASK (TCPHDR_FIN | TCPHDR_SYN | TCPHDR_RST | \ + TCPHDR_PSH | TCPHDR_ACK | TCPHDR_URG | \ + TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE) +#define tcp_flags_ntohs(th) (ntohs(*(__be16 *)&tcp_flag_word(th)) & \ + TCPHDR_FLAGS_MASK) + +#define TCPHDR_ACE (TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE) #define TCPHDR_SYN_ECN (TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR) +/* State flags for sacked in struct tcp_skb_cb */ +enum tcp_skb_cb_sacked_flags { + TCPCB_SACKED_ACKED = (1 << 0), /* SKB ACK'd by a SACK block */ + TCPCB_SACKED_RETRANS = (1 << 1), /* SKB retransmitted */ + TCPCB_LOST = (1 << 2), /* SKB is lost */ + TCPCB_TAGBITS = (TCPCB_SACKED_ACKED | TCPCB_SACKED_RETRANS | + TCPCB_LOST), /* All tag bits */ + TCPCB_REPAIRED = (1 << 4), /* SKB repaired (no skb_mstamp_ns) */ + TCPCB_EVER_RETRANS = (1 << 7), /* Ever retransmitted frame */ + TCPCB_RETRANS = (TCPCB_SACKED_RETRANS | TCPCB_EVER_RETRANS | + TCPCB_REPAIRED), +}; + /* 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. @@ -827,42 +1014,33 @@ struct tcp_skb_cb { __u32 seq; /* Starting sequence number */ __u32 end_seq; /* SEQ + FIN + SYN + datalen */ union { - /* Note : tcp_tw_isn is used in input path only - * (isn chosen by tcp_timewait_state_process()) - * + /* Note : * tcp_gso_segs/size are used in write queue only, * cf tcp_skb_pcount()/tcp_skb_mss() */ - __u32 tcp_tw_isn; struct { u16 tcp_gso_segs; u16 tcp_gso_size; }; }; - __u8 tcp_flags; /* TCP header flags. (tcp[13]) */ + __u16 tcp_flags; /* TCP header flags (tcp[12-13])*/ __u8 sacked; /* State flags for SACK. */ -#define TCPCB_SACKED_ACKED 0x01 /* SKB ACK'd by a SACK block */ -#define TCPCB_SACKED_RETRANS 0x02 /* SKB retransmitted */ -#define TCPCB_LOST 0x04 /* SKB is lost */ -#define TCPCB_TAGBITS 0x07 /* All tag bits */ -#define TCPCB_REPAIRED 0x10 /* SKB repaired (no skb_mstamp_ns) */ -#define TCPCB_EVER_RETRANS 0x80 /* Ever retransmitted frame */ -#define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \ - TCPCB_REPAIRED) - __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */ - __u8 txstamp_ack:1, /* Record TX timestamp for ack? */ +#define TSTAMP_ACK_SK 0x1 +#define TSTAMP_ACK_BPF 0x2 + __u8 txstamp_ack:2, /* Record TX timestamp for ack? */ eor:1, /* Is skb MSG_EOR marked? */ has_rxtstamp:1, /* SKB has a RX timestamp */ - unused:5; + unused:4; __u32 ack_seq; /* Sequence number ACK'd */ union { struct { +#define TCPCB_DELIVERED_CE_MASK ((1U<<20) - 1) /* There is space for up to 24 bytes */ - __u32 in_flight:30,/* Bytes in flight at transmit */ - is_app_limited:1, /* cwnd not fully used? */ - unused:1; + __u32 is_app_limited:1, /* cwnd not fully used? */ + delivered_ce:20, + unused:11; /* pkts S/ACKed so far upon tx of skb, incl retrans: */ __u32 delivered; /* start of send pipeline phase */ @@ -876,36 +1054,11 @@ struct tcp_skb_cb { struct inet6_skb_parm h6; #endif } header; /* For incoming skbs */ - struct { - __u32 flags; - struct sock *sk_redir; - void *data_end; - } bpf; }; }; #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); -} - -static inline bool tcp_skb_bpf_ingress(const struct sk_buff *skb) -{ - return TCP_SKB_CB(skb)->bpf.flags & BPF_F_INGRESS; -} - -static inline struct sock *tcp_skb_bpf_redirect_fetch(struct sk_buff *skb) -{ - return TCP_SKB_CB(skb)->bpf.sk_redir; -} - -static inline void tcp_skb_bpf_redirect_clear(struct sk_buff *skb) -{ - TCP_SKB_CB(skb)->bpf.sk_redir = NULL; -} - extern const struct inet_connection_sock_af_ops ipv4_specific; #if IS_ENABLED(CONFIG_IPV6) @@ -938,7 +1091,7 @@ extern const struct inet_connection_sock_af_ops ipv6_specific; INDIRECT_CALLABLE_DECLARE(void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *skb)); -INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *skb)); +void tcp_v6_early_demux(struct sk_buff *skb); #endif @@ -984,8 +1137,18 @@ static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb) static inline bool tcp_skb_can_collapse(const struct sk_buff *to, const struct sk_buff *from) { + /* skb_cmp_decrypted() not needed, use tcp_write_collapse_fence() */ return likely(tcp_skb_can_collapse_to(to) && - mptcp_skb_can_collapse(to, from)); + mptcp_skb_can_collapse(to, from) && + skb_pure_zcopy_same(to, from) && + skb_frags_readable(to) == skb_frags_readable(from)); +} + +static inline bool tcp_skb_can_collapse_rx(const struct sk_buff *to, + const struct sk_buff *from) +{ + return likely(mptcp_skb_can_collapse(to, from) && + !skb_cmp_decrypted(to, from)); } /* Events passed to congestion control interface */ @@ -1015,9 +1178,9 @@ enum tcp_ca_ack_event_flags { #define TCP_CA_UNSPEC 0 /* Algorithm can be set on socket without CAP_NET_ADMIN privileges */ -#define TCP_CONG_NON_RESTRICTED 0x1 +#define TCP_CONG_NON_RESTRICTED BIT(0) /* Requires ECN/ECT set on all packets */ -#define TCP_CONG_NEEDS_ECN 0x2 +#define TCP_CONG_NEEDS_ECN BIT(1) #define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN) union tcp_cc_info; @@ -1039,7 +1202,9 @@ struct ack_sample { struct rate_sample { u64 prior_mstamp; /* starting timestamp for interval */ u32 prior_delivered; /* tp->delivered at "prior_mstamp" */ + u32 prior_delivered_ce;/* tp->delivered_ce at "prior_mstamp" */ s32 delivered; /* number of packets delivered over interval */ + s32 delivered_ce; /* number of packets delivered w/ CE marks*/ 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 */ @@ -1047,53 +1212,69 @@ struct rate_sample { int losses; /* number of packets marked lost upon ACK */ u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ u32 prior_in_flight; /* in flight before this ACK */ + u32 last_end_seq; /* end_seq of most recently ACKed packet */ bool is_app_limited; /* is sample from packet with bubble in pipe? */ bool is_retrans; /* is sample from retransmission? */ bool is_ack_delayed; /* is this (likely) a delayed ACK? */ }; struct tcp_congestion_ops { - struct list_head list; - u32 key; - u32 flags; - - /* initialize private data (optional) */ - void (*init)(struct sock *sk); - /* cleanup private data (optional) */ - void (*release)(struct sock *sk); +/* fast path fields are put first to fill one cache line */ /* return slow start threshold (required) */ u32 (*ssthresh)(struct sock *sk); + /* do new cwnd calculation (required) */ 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) */ void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev); + /* call when ack arrives (optional) */ void (*in_ack_event)(struct sock *sk, u32 flags); - /* new value of cwnd after loss (required) */ - u32 (*undo_cwnd)(struct sock *sk); + /* hook for packet ack accounting (optional) */ void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample); + /* override sysctl_tcp_min_tso_segs */ u32 (*min_tso_segs)(struct sock *sk); - /* returns the multiplier used in tcp_sndbuf_expand (optional) */ - u32 (*sndbuf_expand)(struct sock *sk); + /* call when packets are delivered to update cwnd and pacing rate, * after all the ca_state processing. (optional) */ - void (*cong_control)(struct sock *sk, const struct rate_sample *rs); + void (*cong_control)(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs); + + + /* new value of cwnd after loss (required) */ + u32 (*undo_cwnd)(struct sock *sk); + /* returns the multiplier used in tcp_sndbuf_expand (optional) */ + u32 (*sndbuf_expand)(struct sock *sk); + +/* control/slow paths put last */ /* get info for inet_diag (optional) */ 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; -}; + char name[TCP_CA_NAME_MAX]; + struct module *owner; + struct list_head list; + u32 key; + u32 flags; + + /* initialize private data (optional) */ + void (*init)(struct sock *sk); + /* cleanup private data (optional) */ + void (*release)(struct sock *sk); +} ____cacheline_aligned_in_smp; int tcp_register_congestion_control(struct tcp_congestion_ops *type); void tcp_unregister_congestion_control(struct tcp_congestion_ops *type); +int tcp_update_congestion_control(struct tcp_congestion_ops *type, + struct tcp_congestion_ops *old_type); +int tcp_validate_congestion_control(struct tcp_congestion_ops *ca); void tcp_assign_congestion_control(struct sock *sk); void tcp_init_congestion_control(struct sock *sk); @@ -1115,7 +1296,7 @@ extern struct tcp_congestion_ops tcp_reno; struct tcp_congestion_ops *tcp_ca_find(const char *name); struct tcp_congestion_ops *tcp_ca_find_key(u32 key); -u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca); +u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca); #ifdef CONFIG_INET char *tcp_ca_get_name_by_key(u32 key, char *buffer); #else @@ -1132,15 +1313,6 @@ static inline bool tcp_ca_needs_ecn(const struct sock *sk) return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN; } -static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - - if (icsk->icsk_ca_ops->set_state) - icsk->icsk_ca_ops->set_state(sk, ca_state); - icsk->icsk_ca_state = ca_state; -} - static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) { const struct inet_connection_sock *icsk = inet_csk(sk); @@ -1149,6 +1321,9 @@ static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) icsk->icsk_ca_ops->cwnd_event(sk, event); } +/* From tcp_cong.c */ +void tcp_set_ca_state(struct sock *sk, const u8 ca_state); + /* From tcp_rate.c */ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb); void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, @@ -1157,6 +1332,11 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, bool is_sack_reneg, struct rate_sample *rs); void tcp_rate_check_app_limited(struct sock *sk); +static inline bool tcp_skb_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) +{ + return t1 > t2 || (t1 == t2 && after(seq1, seq2)); +} + /* These functions determine how the current flow behaves in respect of SACK * handling. SACK is negotiated with the peer, and therefore it can vary * between different flows. @@ -1200,9 +1380,20 @@ static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp) #define TCP_INFINITE_SSTHRESH 0x7fffffff +static inline u32 tcp_snd_cwnd(const struct tcp_sock *tp) +{ + return tp->snd_cwnd; +} + +static inline void tcp_snd_cwnd_set(struct tcp_sock *tp, u32 val) +{ + WARN_ON_ONCE((int)val <= 0); + tp->snd_cwnd = val; +} + static inline bool tcp_in_slow_start(const struct tcp_sock *tp) { - return tp->snd_cwnd < tp->snd_ssthresh; + return tcp_snd_cwnd(tp) < tp->snd_ssthresh; } static inline bool tcp_in_initial_slowstart(const struct tcp_sock *tp) @@ -1228,8 +1419,8 @@ static inline __u32 tcp_current_ssthresh(const struct sock *sk) return tp->snd_ssthresh; else return max(tp->snd_ssthresh, - ((tp->snd_cwnd >> 1) + - (tp->snd_cwnd >> 2))); + ((tcp_snd_cwnd(tp) >> 1) + + (tcp_snd_cwnd(tp) >> 2))); } /* Use define here intentionally to get WARN_ON location shown at the caller */ @@ -1269,11 +1460,14 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); + if (tp->is_cwnd_limited) + return true; + /* If in slow start, ensure cwnd grows to twice what was ACKed. */ if (tcp_in_slow_start(tp)) - return tp->snd_cwnd < 2 * tp->max_packets_out; + return tcp_snd_cwnd(tp) < 2 * tp->max_packets_out; - return tp->is_cwnd_limited; + return false; } /* BBR congestion control needs pacing. @@ -1300,10 +1494,12 @@ static inline unsigned long tcp_pacing_delay(const struct sock *sk) static inline void tcp_reset_xmit_timer(struct sock *sk, const int what, unsigned long when, - const unsigned long max_when) + bool pace_delay) { - inet_csk_reset_xmit_timer(sk, what, when + tcp_pacing_delay(sk), - max_when); + if (pace_delay) + when += tcp_pacing_delay(sk); + inet_csk_reset_xmit_timer(sk, what, when, + tcp_rto_max(sk)); } /* Something is really bad, we could not queue an additional packet, @@ -1321,7 +1517,9 @@ static inline unsigned long tcp_probe0_base(const struct sock *sk) 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; + u8 backoff = min_t(u8, ilog2(TCP_RTO_MAX / TCP_RTO_MIN) + 1, + inet_csk(sk)->icsk_backoff); + u64 when = (u64)tcp_probe0_base(sk) << backoff; return (unsigned long)min_t(u64, when, max_when); } @@ -1330,7 +1528,7 @@ static inline void tcp_check_probe_timer(struct sock *sk) { if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending) tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, - tcp_probe0_base(sk), TCP_RTO_MAX); + tcp_probe0_base(sk), true); } static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq) @@ -1358,7 +1556,10 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb) __skb_checksum_complete(skb); } -bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb); +bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, + enum skb_drop_reason *reason); + + int tcp_filter(struct sock *sk, struct sk_buff *skb); void tcp_set_state(struct sock *sk, int state); void tcp_done(struct sock *sk); @@ -1378,8 +1579,8 @@ static inline void tcp_slow_start_after_idle_check(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); s32 delta; - if (!sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle || tp->packets_out || - ca_ops->cong_control) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) || + tp->packets_out || ca_ops->cong_control) return; delta = tcp_jiffies32 - tp->lsndtime; if (delta > inet_csk(sk)->icsk_rto) @@ -1392,13 +1593,40 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 *window_clamp, int wscale_ok, __u8 *rcv_wscale, __u32 init_rcv_wnd); +static inline int __tcp_win_from_space(u8 scaling_ratio, int space) +{ + s64 scaled_space = (s64)space * scaling_ratio; + + return scaled_space >> TCP_RMEM_TO_WIN_SCALE; +} + static inline int tcp_win_from_space(const struct sock *sk, int space) { - int tcp_adv_win_scale = sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale; + return __tcp_win_from_space(tcp_sk(sk)->scaling_ratio, space); +} + +/* inverse of __tcp_win_from_space() */ +static inline int __tcp_space_from_win(u8 scaling_ratio, int win) +{ + u64 val = (u64)win << TCP_RMEM_TO_WIN_SCALE; - return tcp_adv_win_scale <= 0 ? - (space>>(-tcp_adv_win_scale)) : - space - (space>>tcp_adv_win_scale); + do_div(val, scaling_ratio); + return val; +} + +static inline int tcp_space_from_win(const struct sock *sk, int win) +{ + return __tcp_space_from_win(tcp_sk(sk)->scaling_ratio, win); +} + +/* Assume a 50% default for skb->len/skb->truesize ratio. + * This may be adjusted later in tcp_measure_rcv_mss(). + */ +#define TCP_DEFAULT_SCALING_RATIO (1 << (TCP_RMEM_TO_WIN_SCALE - 1)) + +static inline void tcp_scaling_ratio_init(struct sock *sk) +{ + tcp_sk(sk)->scaling_ratio = TCP_DEFAULT_SCALING_RATIO; } /* Note: caller must be prepared to deal with negative returns */ @@ -1414,7 +1642,25 @@ static inline int tcp_full_space(const struct sock *sk) return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } +static inline void __tcp_adjust_rcv_ssthresh(struct sock *sk, u32 new_ssthresh) +{ + int unused_mem = sk_unused_reserved_mem(sk); + struct tcp_sock *tp = tcp_sk(sk); + + tp->rcv_ssthresh = min(tp->rcv_ssthresh, new_ssthresh); + if (unused_mem) + tp->rcv_ssthresh = max_t(u32, tp->rcv_ssthresh, + tcp_win_from_space(sk, unused_mem)); +} + +static inline void tcp_adjust_rcv_ssthresh(struct sock *sk) +{ + __tcp_adjust_rcv_ssthresh(sk, 4U * tcp_sk(sk)->advmss); +} + void tcp_cleanup_rbuf(struct sock *sk, int copied); +void __tcp_cleanup_rbuf(struct sock *sk, int copied); + /* We provision sk_rcvbuf around 200% of sk_rcvlowat. * If 87.5 % (7/8) of the space has been consumed, we want to override @@ -1423,12 +1669,29 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied); */ static inline bool tcp_rmem_pressure(const struct sock *sk) { - int rcvbuf = READ_ONCE(sk->sk_rcvbuf); - int threshold = rcvbuf - (rcvbuf >> 3); + int rcvbuf, threshold; + + if (tcp_under_memory_pressure(sk)) + return true; + + rcvbuf = READ_ONCE(sk->sk_rcvbuf); + threshold = rcvbuf - (rcvbuf >> 3); return atomic_read(&sk->sk_rmem_alloc) > threshold; } +static inline bool tcp_epollin_ready(const struct sock *sk, int target) +{ + const struct tcp_sock *tp = tcp_sk(sk); + int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq); + + if (avail <= 0) + return false; + + return (avail >= target) || tcp_rmem_pressure(sk) || + (tcp_receive_window(tp) <= inet_csk(sk)->icsk_ack.rcv_mss); +} + extern void tcp_openreq_init_rwin(struct request_sock *req, const struct sock *sk_listener, const struct dst_entry *dst); @@ -1439,22 +1702,38 @@ void tcp_leave_memory_pressure(struct sock *sk); static inline int keepalive_intvl_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); + int val; - return tp->keepalive_intvl ? : net->ipv4.sysctl_tcp_keepalive_intvl; + /* Paired with WRITE_ONCE() in tcp_sock_set_keepintvl() + * and do_tcp_setsockopt(). + */ + val = READ_ONCE(tp->keepalive_intvl); + + return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_intvl); } static inline int keepalive_time_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); + int val; + + /* Paired with WRITE_ONCE() in tcp_sock_set_keepidle_locked() */ + val = READ_ONCE(tp->keepalive_time); - return tp->keepalive_time ? : net->ipv4.sysctl_tcp_keepalive_time; + return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time); } static inline int keepalive_probes(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); + int val; - return tp->keepalive_probes ? : net->ipv4.sysctl_tcp_keepalive_probes; + /* Paired with WRITE_ONCE() in tcp_sock_set_keepcnt() + * and do_tcp_setsockopt(). + */ + val = READ_ONCE(tp->keepalive_probes); + + return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes); } static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) @@ -1467,7 +1746,8 @@ static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) static inline int tcp_fin_time(const struct sock *sk) { - int fin_timeout = tcp_sk(sk)->linger2 ? : sock_net(sk)->ipv4.sysctl_tcp_fin_timeout; + int fin_timeout = tcp_sk(sk)->linger2 ? : + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fin_timeout); const int rto = inet_csk(sk)->icsk_rto; if (fin_timeout < (rto << 2) - (rto >> 1)) @@ -1482,7 +1762,7 @@ 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(!time_before32(ktime_get_seconds(), - rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS))) + rx_opt->ts_recent_stamp + TCP_PAWS_WRAP))) return true; /* * Some OSes send SYN and SYNACK messages with tsval=0 tsecr=0, @@ -1542,12 +1822,7 @@ static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp) tp->retransmit_skb_hint = NULL; } -union tcp_md5_addr { - struct in_addr a4; -#if IS_ENABLED(CONFIG_IPV6) - struct in6_addr a6; -#endif -}; +#define tcp_md5_addr tcp_ao_addr /* - key database */ struct tcp_md5sig_key { @@ -1555,6 +1830,7 @@ struct tcp_md5sig_key { u8 keylen; u8 family; /* AF_INET or AF_INET6 */ u8 prefixlen; + u8 flags; union tcp_md5_addr addr; int l3index; /* set if key added with L3 scope */ u8 key[TCP_MD5SIG_MAXKEYLEN]; @@ -1590,36 +1866,75 @@ union tcp_md5sum_block { #endif }; -/* - pool: digest algorithm, hash description and scratch buffer */ -struct tcp_md5sig_pool { - struct ahash_request *md5_req; - void *scratch; +/* + * struct tcp_sigpool - per-CPU pool of ahash_requests + * @scratch: per-CPU temporary area, that can be used between + * tcp_sigpool_start() and tcp_sigpool_end() to perform + * crypto request + * @req: pre-allocated ahash request + */ +struct tcp_sigpool { + void *scratch; + struct ahash_request *req; }; +int tcp_sigpool_alloc_ahash(const char *alg, size_t scratch_size); +void tcp_sigpool_get(unsigned int id); +void tcp_sigpool_release(unsigned int id); +int tcp_sigpool_hash_skb_data(struct tcp_sigpool *hp, + const struct sk_buff *skb, + unsigned int header_len); + +/** + * tcp_sigpool_start - disable bh and start using tcp_sigpool_ahash + * @id: tcp_sigpool that was previously allocated by tcp_sigpool_alloc_ahash() + * @c: returned tcp_sigpool for usage (uninitialized on failure) + * + * Returns: 0 on success, error otherwise. + */ +int tcp_sigpool_start(unsigned int id, struct tcp_sigpool *c); +/** + * tcp_sigpool_end - enable bh and stop using tcp_sigpool + * @c: tcp_sigpool context that was returned by tcp_sigpool_start() + */ +void tcp_sigpool_end(struct tcp_sigpool *c); +size_t tcp_sigpool_algo(unsigned int id, char *buf, size_t buf_len); /* - functions */ 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, u8 prefixlen, int l3index, - const u8 *newkey, u8 newkeylen, gfp_t gfp); + int family, u8 prefixlen, int l3index, u8 flags, + const u8 *newkey, u8 newkeylen); +int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, + int family, u8 prefixlen, int l3index, + struct tcp_md5sig_key *key); + int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, - int family, u8 prefixlen, int l3index); + int family, u8 prefixlen, int l3index, u8 flags); +void tcp_clear_md5_list(struct sock *sk); struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk); #ifdef CONFIG_TCP_MD5SIG -#include <linux/jump_label.h> -extern struct static_key_false tcp_md5_needed; struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, - int family); + int family, bool any_l3index); static inline struct tcp_md5sig_key * tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family) { - if (!static_branch_unlikely(&tcp_md5_needed)) + if (!static_branch_unlikely(&tcp_md5_needed.key)) return NULL; - return __tcp_md5_do_lookup(sk, l3index, addr, family); + return __tcp_md5_do_lookup(sk, l3index, addr, family, false); +} + +static inline struct tcp_md5sig_key * +tcp_md5_do_lookup_any_l3index(const struct sock *sk, + const union tcp_md5_addr *addr, int family) +{ + if (!static_branch_unlikely(&tcp_md5_needed.key)) + return NULL; + return __tcp_md5_do_lookup(sk, 0, addr, family, true); } #define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_key) @@ -1630,20 +1945,23 @@ tcp_md5_do_lookup(const struct sock *sk, int l3index, { return NULL; } -#define tcp_twsk_md5_key(twsk) NULL -#endif -bool tcp_alloc_md5sig_pool(void); - -struct tcp_md5sig_pool *tcp_get_md5sig_pool(void); -static inline void tcp_put_md5sig_pool(void) +static inline struct tcp_md5sig_key * +tcp_md5_do_lookup_any_l3index(const struct sock *sk, + const union tcp_md5_addr *addr, int family) { - local_bh_enable(); + return NULL; } -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, +#define tcp_twsk_md5_key(twsk) NULL +#endif + +int tcp_md5_alloc_sigpool(void); +void tcp_md5_release_sigpool(void); +void tcp_md5_add_sigpool(void); +extern int tcp_md5_sigpool_id; + +int tcp_md5_hash_key(struct tcp_sigpool *hp, const struct tcp_md5sig_key *key); /* From tcp_fastopen.c */ @@ -1688,7 +2006,6 @@ struct tcp_fastopen_context { struct rcu_head rcu; }; -extern unsigned int sysctl_tcp_fastopen_blackhole_timeout; void tcp_fastopen_active_disable(struct sock *sk); bool tcp_fastopen_active_should_disable(struct sock *sk); void tcp_fastopen_active_disable_ofo_check(struct sock *sk); @@ -1766,11 +2083,6 @@ static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk) return skb_rb_last(&sk->tcp_rtx_queue); } -static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk) -{ - return skb_peek(&sk->sk_write_queue); -} - static inline struct sk_buff *tcp_write_queue_tail(const struct sock *sk) { return skb_peek_tail(&sk->sk_write_queue); @@ -1849,7 +2161,15 @@ static inline void tcp_rtx_queue_unlink_and_free(struct sk_buff *skb, struct soc { list_del(&skb->tcp_tsorted_anchor); tcp_rtx_queue_unlink(skb, sk); - sk_wmem_free_skb(sk, skb); + tcp_wmem_free_skb(sk, skb); +} + +static inline void tcp_write_collapse_fence(struct sock *sk) +{ + struct sk_buff *skb = tcp_write_queue_tail(sk); + + if (skb) + TCP_SKB_CB(skb)->eor = 1; } static inline void tcp_push_pending_frames(struct sock *sk) @@ -1909,7 +2229,7 @@ static inline bool inet_sk_transparent(const struct sock *sk) case TCP_NEW_SYN_RECV: return inet_rsk(inet_reqsk(sk))->no_srccheck; } - return inet_sk(sk)->transparent; + return inet_test_bit(TRANSPARENT, sk); } /* Determines whether this is a thin stream (which may suffer from @@ -1938,7 +2258,6 @@ struct tcp_iter_state { struct seq_net_private p; enum tcp_seq_states state; struct sock *syn_wait_sk; - struct tcp_seq_afinfo *bpf_seq_afinfo; int bucket, offset, sbucket, num; loff_t last_pos; }; @@ -1950,34 +2269,34 @@ 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 list_head *head, struct sk_buff *skb); +struct tcphdr *tcp_gro_pull_header(struct sk_buff *skb); +struct sk_buff *tcp_gro_lookup(struct list_head *head, struct tcphdr *th); +struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, + struct tcphdr *th); INDIRECT_CALLABLE_DECLARE(int tcp4_gro_complete(struct sk_buff *skb, int thoff)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(int tcp6_gro_complete(struct sk_buff *skb, int thoff)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb)); -int tcp_gro_complete(struct sk_buff *skb); +#ifdef CONFIG_INET +void tcp_gro_complete(struct sk_buff *skb); +#else +static inline void tcp_gro_complete(struct sk_buff *skb) { } +#endif void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); - return tp->notsent_lowat ?: net->ipv4.sysctl_tcp_notsent_lowat; -} + u32 val; -/* @wake is one when sk_stream_write_space() calls us. - * This sends EPOLLOUT only if notsent_bytes is half the limit. - * This mimics the strategy used in sock_def_write_space(). - */ -static inline bool tcp_stream_memory_free(const struct sock *sk, int wake) -{ - const struct tcp_sock *tp = tcp_sk(sk); - u32 notsent_bytes = READ_ONCE(tp->write_seq) - - READ_ONCE(tp->snd_nxt); + val = READ_ONCE(tp->notsent_lowat); - return (notsent_bytes << wake) < tcp_notsent_lowat(tp); + return val ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); } +bool tcp_stream_memory_free(const struct sock *sk, int wake); + #ifdef CONFIG_PROC_FS int tcp4_proc_init(void); void tcp4_proc_exit(void); @@ -2002,6 +2321,18 @@ struct tcp_sock_af_ops { sockptr_t optval, int optlen); #endif +#ifdef CONFIG_TCP_AO + int (*ao_parse)(struct sock *sk, int optname, sockptr_t optval, int optlen); + struct tcp_ao_key *(*ao_lookup)(const struct sock *sk, + struct sock *addr_sk, + int sndid, int rcvid); + int (*ao_calc_key_sk)(struct tcp_ao_key *mkt, u8 *key, + const struct sock *sk, + __be32 sisn, __be32 disn, bool send); + int (*calc_ao_hash)(char *location, struct tcp_ao_key *ao, + const struct sock *sk, const struct sk_buff *skb, + const u8 *tkey, int hash_offset, u32 sne); +#endif }; struct tcp_request_sock_ops { @@ -2014,15 +2345,24 @@ struct tcp_request_sock_ops { const struct sock *sk, const struct sk_buff *skb); #endif - void (*init_req)(struct request_sock *req, - const struct sock *sk_listener, - struct sk_buff *skb); +#ifdef CONFIG_TCP_AO + struct tcp_ao_key *(*ao_lookup)(const struct sock *sk, + struct request_sock *req, + int sndid, int rcvid); + int (*ao_calc_key)(struct tcp_ao_key *mkt, u8 *key, struct request_sock *sk); + int (*ao_synack_hash)(char *ao_hash, struct tcp_ao_key *mkt, + struct request_sock *req, const struct sk_buff *skb, + int hash_offset, u32 sne); +#endif #ifdef CONFIG_SYN_COOKIES __u32 (*cookie_init_seq)(const struct sk_buff *skb, __u16 *mss); #endif - struct dst_entry *(*route_req)(const struct sock *sk, struct flowi *fl, - const struct request_sock *req); + struct dst_entry *(*route_req)(const struct sock *sk, + struct sk_buff *skb, + struct flowi *fl, + struct request_sock *req, + u32 tw_isn); u32 (*init_seq)(const struct sk_buff *skb); u32 (*init_ts_off)(const struct net *net, const struct sk_buff *skb); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, @@ -2055,6 +2395,70 @@ static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, } #endif +struct tcp_key { + union { + struct { + struct tcp_ao_key *ao_key; + char *traffic_key; + u32 sne; + u8 rcv_next; + }; + struct tcp_md5sig_key *md5_key; + }; + enum { + TCP_KEY_NONE = 0, + TCP_KEY_MD5, + TCP_KEY_AO, + } type; +}; + +static inline void tcp_get_current_key(const struct sock *sk, + struct tcp_key *out) +{ +#if defined(CONFIG_TCP_AO) || defined(CONFIG_TCP_MD5SIG) + const struct tcp_sock *tp = tcp_sk(sk); +#endif + +#ifdef CONFIG_TCP_AO + if (static_branch_unlikely(&tcp_ao_needed.key)) { + struct tcp_ao_info *ao; + + ao = rcu_dereference_protected(tp->ao_info, + lockdep_sock_is_held(sk)); + if (ao) { + out->ao_key = READ_ONCE(ao->current_key); + out->type = TCP_KEY_AO; + return; + } + } +#endif +#ifdef CONFIG_TCP_MD5SIG + if (static_branch_unlikely(&tcp_md5_needed.key) && + rcu_access_pointer(tp->md5sig_info)) { + out->md5_key = tp->af_specific->md5_lookup(sk, sk); + if (out->md5_key) { + out->type = TCP_KEY_MD5; + return; + } + } +#endif + out->type = TCP_KEY_NONE; +} + +static inline bool tcp_key_is_md5(const struct tcp_key *key) +{ + if (static_branch_tcp_md5()) + return key->type == TCP_KEY_MD5; + return false; +} + +static inline bool tcp_key_is_ao(const struct tcp_key *key) +{ + if (static_branch_tcp_ao()) + return key->type == TCP_KEY_AO; + return false; +} + int tcpv4_offload_init(void); void tcp_v4_init(void); @@ -2065,20 +2469,69 @@ 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 bool tcp_rack_mark_lost(struct sock *sk); extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, u64 xmit_time); extern void tcp_rack_reo_timeout(struct sock *sk); extern void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs); +/* tcp_plb.c */ + +/* + * Scaling factor for fractions in PLB. For example, tcp_plb_update_state + * expects cong_ratio which represents fraction of traffic that experienced + * congestion over a single RTT. In order to avoid floating point operations, + * this fraction should be mapped to (1 << TCP_PLB_SCALE) and passed in. + */ +#define TCP_PLB_SCALE 8 + +/* State for PLB (Protective Load Balancing) for a single TCP connection. */ +struct tcp_plb_state { + u8 consec_cong_rounds:5, /* consecutive congested rounds */ + unused:3; + u32 pause_until; /* jiffies32 when PLB can resume rerouting */ +}; + +static inline void tcp_plb_init(const struct sock *sk, + struct tcp_plb_state *plb) +{ + plb->consec_cong_rounds = 0; + plb->pause_until = 0; +} +void tcp_plb_update_state(const struct sock *sk, struct tcp_plb_state *plb, + const int cong_ratio); +void tcp_plb_check_rehash(struct sock *sk, struct tcp_plb_state *plb); +void tcp_plb_update_state_upon_rto(struct sock *sk, struct tcp_plb_state *plb); + +static inline void tcp_warn_once(const struct sock *sk, bool cond, const char *str) +{ + WARN_ONCE(cond, + "%scwn:%u out:%u sacked:%u lost:%u retrans:%u tlp_high_seq:%u sk_state:%u ca_state:%u advmss:%u mss_cache:%u pmtu:%u\n", + str, + tcp_snd_cwnd(tcp_sk(sk)), + tcp_sk(sk)->packets_out, tcp_sk(sk)->sacked_out, + tcp_sk(sk)->lost_out, tcp_sk(sk)->retrans_out, + tcp_sk(sk)->tlp_high_seq, sk->sk_state, + inet_csk(sk)->icsk_ca_state, + tcp_sk(sk)->advmss, tcp_sk(sk)->mss_cache, + inet_csk(sk)->icsk_pmtu_cookie); +} + /* At how many usecs into the future should the RTO fire? */ static inline s64 tcp_rto_delta_us(const struct sock *sk) { const struct sk_buff *skb = tcp_rtx_queue_head(sk); u32 rto = inet_csk(sk)->icsk_rto; - u64 rto_time_stamp_us = tcp_skb_timestamp_us(skb) + jiffies_to_usecs(rto); - return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp; + if (likely(skb)) { + u64 rto_time_stamp_us = tcp_skb_timestamp_us(skb) + jiffies_to_usecs(rto); + + return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp; + } else { + tcp_warn_once(sk, 1, "rtx queue empty: "); + return jiffies_to_usecs(rto); + } + } /* @@ -2148,9 +2601,13 @@ static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb) u16 segs_in; segs_in = max_t(u16, 1, skb_shinfo(skb)->gso_segs); - tp->segs_in += segs_in; + + /* We update these fields while other threads might + * read them from tcp_get_info() + */ + WRITE_ONCE(tp->segs_in, tp->segs_in + segs_in); if (skb->len > tcp_hdrlen(skb)) - tp->data_segs_in += segs_in; + WRITE_ONCE(tp->data_segs_in, tp->data_segs_in + segs_in); } /* @@ -2187,8 +2644,8 @@ struct tcp_ulp_ops { /* cleanup ulp */ void (*release)(struct sock *sk); /* diagnostic */ - int (*get_info)(const struct sock *sk, struct sk_buff *skb); - size_t (*get_info_size)(const struct sock *sk); + int (*get_info)(struct sock *sk, struct sk_buff *skb, bool net_admin); + size_t (*get_info_size)(const struct sock *sk, bool net_admin); /* clone ulp */ void (*clone)(const struct request_sock *req, struct sock *newsk, const gfp_t priority); @@ -2208,25 +2665,38 @@ void tcp_update_ulp(struct sock *sk, struct proto *p, __MODULE_INFO(alias, alias_userspace, name); \ __MODULE_INFO(alias, alias_tcp_ulp, "tcp-ulp-" name) +#ifdef CONFIG_NET_SOCK_MSG struct sk_msg; struct sk_psock; -#ifdef CONFIG_BPF_STREAM_PARSER -struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock); +#ifdef CONFIG_BPF_SYSCALL +int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); +#ifdef CONFIG_BPF_STREAM_PARSER +struct strparser; +int tcp_bpf_strp_read_sock(struct strparser *strp, read_descriptor_t *desc, + sk_read_actor_t recv_actor); +#endif /* CONFIG_BPF_STREAM_PARSER */ +#endif /* CONFIG_BPF_SYSCALL */ + +#ifdef CONFIG_INET +void tcp_eat_skb(struct sock *sk, struct sk_buff *skb); #else -static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) +static inline void tcp_eat_skb(struct sock *sk, struct sk_buff *skb) { } -#endif /* CONFIG_BPF_STREAM_PARSER */ +#endif -#ifdef CONFIG_NET_SOCK_MSG -int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes, - int flags); -int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, - struct msghdr *msg, int len, int flags); +int tcp_bpf_sendmsg_redir(struct sock *sk, bool ingress, + struct sk_msg *msg, u32 bytes, int flags); #endif /* CONFIG_NET_SOCK_MSG */ +#if !defined(CONFIG_BPF_SYSCALL) || !defined(CONFIG_NET_SOCK_MSG) +static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) +{ +} +#endif + #ifdef CONFIG_CGROUP_BPF static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, struct sk_buff *skb, @@ -2257,6 +2727,7 @@ static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args) memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); if (sk_fullsock(sk)) { sock_ops.is_fullsock = 1; + sock_ops.is_locked_tcp_sock = 1; sock_owned_by_me(sk); } @@ -2315,7 +2786,7 @@ static inline u32 tcp_timeout_init(struct sock *sk) if (timeout <= 0) timeout = TCP_TIMEOUT_INIT; - return timeout; + return min_t(int, timeout, TCP_RTO_MAX); } static inline u32 tcp_rwnd_init_bpf(struct sock *sk) @@ -2334,10 +2805,10 @@ static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk) return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1); } -static inline void tcp_bpf_rtt(struct sock *sk) +static inline void tcp_bpf_rtt(struct sock *sk, long mrtt, u32 srtt) { if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_RTT_CB_FLAG)) - tcp_call_bpf(sk, BPF_SOCK_OPS_RTT_CB, 0, NULL); + tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_RTT_CB, mrtt, srtt); } #if IS_ENABLED(CONFIG_SMC) @@ -2345,9 +2816,9 @@ 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 clean_acked_data_enable(struct tcp_sock *tp, void (*cad)(struct sock *sk, u32 ack_seq)); -void clean_acked_data_disable(struct inet_connection_sock *icsk); +void clean_acked_data_disable(struct tcp_sock *tp); void clean_acked_data_flush(void); #endif @@ -2373,4 +2844,59 @@ static inline u64 tcp_transmit_time(const struct sock *sk) return 0; } +static inline int tcp_parse_auth_options(const struct tcphdr *th, + const u8 **md5_hash, const struct tcp_ao_hdr **aoh) +{ + const u8 *md5_tmp, *ao_tmp; + int ret; + + ret = tcp_do_parse_auth_options(th, &md5_tmp, &ao_tmp); + if (ret) + return ret; + + if (md5_hash) + *md5_hash = md5_tmp; + + if (aoh) { + if (!ao_tmp) + *aoh = NULL; + else + *aoh = (struct tcp_ao_hdr *)(ao_tmp - 2); + } + + return 0; +} + +static inline bool tcp_ao_required(struct sock *sk, const void *saddr, + int family, int l3index, bool stat_inc) +{ +#ifdef CONFIG_TCP_AO + struct tcp_ao_info *ao_info; + struct tcp_ao_key *ao_key; + + if (!static_branch_unlikely(&tcp_ao_needed.key)) + return false; + + ao_info = rcu_dereference_check(tcp_sk(sk)->ao_info, + lockdep_sock_is_held(sk)); + if (!ao_info) + return false; + + ao_key = tcp_ao_do_lookup(sk, l3index, saddr, family, -1, -1); + if (ao_info->ao_required || ao_key) { + if (stat_inc) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOREQUIRED); + atomic64_inc(&ao_info->counters.ao_required); + } + return true; + } +#endif + return false; +} + +enum skb_drop_reason tcp_inbound_hash(struct sock *sk, + const struct request_sock *req, const struct sk_buff *skb, + const void *saddr, const void *daddr, + int family, int dif, int sdif); + #endif /* _TCP_H */ |