diff options
Diffstat (limited to 'include/net/tcp.h')
| -rw-r--r-- | include/net/tcp.h | 91 |
1 files changed, 65 insertions, 26 deletions
diff --git a/include/net/tcp.h b/include/net/tcp.h index 770917d0caa7..a18914d20486 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -732,7 +732,7 @@ void tcp_send_window_probe(struct sock *sk); static inline u64 tcp_clock_ns(void) { - return local_clock(); + return ktime_get_ns(); } static inline u64 tcp_clock_us(void) @@ -752,17 +752,7 @@ static inline u32 tcp_time_stamp_raw(void) return div_u64(tcp_clock_ns(), NSEC_PER_SEC / TCP_TS_HZ); } - -/* Refresh 1us clock of a TCP socket, - * ensuring monotically increasing values. - */ -static inline void tcp_mstamp_refresh(struct tcp_sock *tp) -{ - u64 val = tcp_clock_us(); - - if (val > tp->tcp_mstamp) - tp->tcp_mstamp = val; -} +void tcp_mstamp_refresh(struct tcp_sock *tp); static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) { @@ -771,7 +761,13 @@ static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) static inline u32 tcp_skb_timestamp(const struct sk_buff *skb) { - return div_u64(skb->skb_mstamp, USEC_PER_SEC / TCP_TS_HZ); + return div_u64(skb->skb_mstamp_ns, NSEC_PER_SEC / TCP_TS_HZ); +} + +/* 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); } @@ -817,7 +813,7 @@ struct tcp_skb_cb { #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) */ +#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) @@ -862,6 +858,21 @@ 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; +} + #if IS_ENABLED(CONFIG_IPV6) /* This is the variant of inet6_iif() that must be used by TCP, * as TCP moves IP6CB into a different location in skb->cb[] @@ -1234,8 +1245,31 @@ static inline bool tcp_needs_internal_pacing(const struct sock *sk) return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED; } +/* Return in jiffies the delay before one skb is sent. + * If @skb is NULL, we look at EDT for next packet being sent on the socket. + */ +static inline unsigned long tcp_pacing_delay(const struct sock *sk, + const struct sk_buff *skb) +{ + s64 pacing_delay = skb ? skb->tstamp : tcp_sk(sk)->tcp_wstamp_ns; + + pacing_delay -= tcp_sk(sk)->tcp_clock_cache; + + return pacing_delay > 0 ? nsecs_to_jiffies(pacing_delay) : 0; +} + +static inline void tcp_reset_xmit_timer(struct sock *sk, + const int what, + unsigned long when, + const unsigned long max_when, + const struct sk_buff *skb) +{ + inet_csk_reset_xmit_timer(sk, what, when + tcp_pacing_delay(sk, skb), + max_when); +} + /* Something is really bad, we could not queue an additional packet, - * because qdisc is full or receiver sent a 0 window. + * because qdisc is full or receiver sent a 0 window, or we are paced. * We do not want to add fuel to the fire, or abort too early, * so make sure the timer we arm now is at least 200ms in the future, * regardless of current icsk_rto value (as it could be ~2ms) @@ -1257,8 +1291,9 @@ static inline unsigned long tcp_probe0_when(const struct sock *sk, static inline void tcp_check_probe_timer(struct sock *sk) { if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending) - inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, - tcp_probe0_base(sk), TCP_RTO_MAX); + tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, + tcp_probe0_base(sk), TCP_RTO_MAX, + NULL); } static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq) @@ -1940,7 +1975,7 @@ 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 = skb->skb_mstamp + jiffies_to_usecs(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; } @@ -2040,11 +2075,6 @@ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer); #define TCP_ULP_MAX 128 #define TCP_ULP_BUF_MAX (TCP_ULP_NAME_MAX*TCP_ULP_MAX) -enum { - TCP_ULP_TLS, - TCP_ULP_BPF, -}; - struct tcp_ulp_ops { struct list_head list; @@ -2053,15 +2083,12 @@ struct tcp_ulp_ops { /* cleanup ulp */ void (*release)(struct sock *sk); - int uid; char name[TCP_ULP_NAME_MAX]; - bool user_visible; struct module *owner; }; int tcp_register_ulp(struct tcp_ulp_ops *type); void tcp_unregister_ulp(struct tcp_ulp_ops *type); int tcp_set_ulp(struct sock *sk, const char *name); -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); @@ -2069,6 +2096,18 @@ void tcp_cleanup_ulp(struct sock *sk); __MODULE_INFO(alias, alias_userspace, name); \ __MODULE_INFO(alias, alias_tcp_ulp, "tcp-ulp-" name) +struct sk_msg; +struct sk_psock; + +int tcp_bpf_init(struct sock *sk); +void tcp_bpf_reinit(struct sock *sk); +int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes, + int flags); +int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int nonblock, int flags, int *addr_len); +int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, + struct msghdr *msg, int len, int flags); + /* 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 |