#define TFO_SERVER_COOKIE_NOT_REQD 0x200
/* Force enable TFO on all listeners, i.e., not requiring the
- * TCP_FASTOPEN socket option. SOCKOPT1/2 determine how to set max_qlen.
+ * TCP_FASTOPEN socket option.
*/
#define TFO_SERVER_WO_SOCKOPT1 0x400
-#define TFO_SERVER_WO_SOCKOPT2 0x800
extern struct inet_timewait_death_row tcp_death_row;
#endif
/* tcp_output.c */
+u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
+ int min_tso_segs);
void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
int nonagle);
bool tcp_may_send_now(struct sock *sk);
void tcp_get_info(struct sock *, struct tcp_info *);
/* Read 'sendfile()'-style from a TCP socket */
-typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *,
- unsigned int, size_t);
int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
sk_read_actor_t recv_actor);
{
struct tcp_sock *tp = tcp_sk(sk);
- if (skb_queue_empty(&tp->out_of_order_queue) &&
+ if (RB_EMPTY_ROOT(&tp->out_of_order_queue) &&
tp->rcv_wnd &&
atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
!tp->urg_data)
/* Minimum RTT in usec. ~0 means not available. */
static inline u32 tcp_min_rtt(const struct tcp_sock *tp)
{
- return tp->rtt_min[0].rtt;
+ return minmax_get(&tp->rtt_min);
}
/* Compute the actual receive window we are currently advertising.
__u32 ack_seq; /* Sequence number ACK'd */
union {
struct {
- /* There is space for up to 20 bytes */
- __u32 in_flight;/* Bytes in flight when packet sent */
+ /* 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;
+ /* pkts S/ACKed so far upon tx of skb, incl retrans: */
+ __u32 delivered;
+ /* start of send pipeline phase */
+ struct skb_mstamp first_tx_mstamp;
+ /* when we reached the "delivered" count */
+ struct skb_mstamp delivered_mstamp;
} tx; /* only used for outgoing skbs */
union {
struct inet_skb_parm h4;
*/
static inline int tcp_v6_iif(const struct sk_buff *skb)
{
- bool l3_slave = skb_l3mdev_slave(TCP_SKB_CB(skb)->header.h6.flags);
+ 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;
}
#endif
+/* TCP_SKB_CB reference means this can not be used from early demux */
+static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+ if (!net->ipv4.sysctl_tcp_l3mdev_accept &&
+ ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags))
+ return true;
+#endif
+ return false;
+}
+
/* Due to TSO, an SKB can be composed of multiple actual
* packets. To keep these tracked properly, we use this.
*/
u32 in_flight;
};
+/* A rate sample measures the number of (original/retransmitted) data
+ * packets delivered "delivered" over an interval of time "interval_us".
+ * The tcp_rate.c code fills in the rate sample, and congestion
+ * control modules that define a cong_control function to run at the end
+ * of ACK processing can optionally chose to consult this sample when
+ * setting cwnd and pacing rate.
+ * A sample is invalid if "delivered" or "interval_us" is negative.
+ */
+struct rate_sample {
+ struct skb_mstamp prior_mstamp; /* starting timestamp for interval */
+ 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" */
+ 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 */
+ u32 prior_in_flight; /* in flight before this ACK */
+ bool is_app_limited; /* is sample from packet with bubble in pipe? */
+ bool is_retrans; /* is sample from retransmission? */
+};
+
struct tcp_congestion_ops {
struct list_head list;
u32 key;
u32 (*undo_cwnd)(struct sock *sk);
/* hook for packet ack accounting (optional) */
void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample);
+ /* suggest number of segments for each skb to transmit (optional) */
+ u32 (*tso_segs_goal)(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);
/* get info for inet_diag (optional) */
size_t (*get_info)(struct sock *sk, u32 ext, int *attr,
union tcp_cc_info *info);
icsk->icsk_ca_ops->cwnd_event(sk, event);
}
+/* 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,
+ struct rate_sample *rs);
+void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
+ struct skb_mstamp *now, struct rate_sample *rs);
+void tcp_rate_check_app_limited(struct sock *sk);
+
/* 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.
}
bool tcp_prequeue(struct sock *sk, struct sk_buff *skb);
+bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb);
#undef STATE_TRACE
return answ;
}
+int tcp_peek_len(struct socket *sock);
+
static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb)
{
u16 segs_in;
projects / cascardo / linux.git / blobdiff