tcp.h

linux 内核源代码

/* tcp_timer.c */
extern 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, int large);

/* tcp.c */
extern 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);
extern 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);

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);

static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
{
	tp->pred_flags = htonl((tp->tcp_header_len << 26) |
			       ntohl(TCP_FLAG_ACK) |
			       snd_wnd);
}

static inline void tcp_fast_path_on(struct tcp_sock *tp)
{
	__tcp_fast_path_on(tp, tp->snd_wnd >> tp->rx_opt.snd_wscale);
}

static inline void tcp_fast_path_check(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (skb_queue_empty(&tp->out_of_order_queue) &&
	    tp->rcv_wnd &&
	    atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
	    !tp->urg_data)
		tcp_fast_path_on(tp);
}

/* 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.
 */
static inline u32 tcp_receive_window(const struct tcp_sock *tp)
{
	s32 win = tp->rcv_wup + tp->rcv_wnd - tp->rcv_nxt;

	if (win < 0)
		win = 0;
	return (u32) win;
}

/* Choose a new window, without checks for shrinking, and without
 * 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);

/* TCP timestamps are only 32-bits, this causes a slight
 * complication on 64-bit systems since we store a snapshot
 * of jiffies in the buffer control blocks below.  We decided
 * to use only the low 32-bits of jiffies and hide the ugly
 * casts with the following macro.
 */
#define tcp_time_stamp		((__u32)(jiffies))

/* 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.  This is 36 bytes on 32-bit architectures,
 * 40 bytes on 64-bit machines, if this grows please adjust
 * skbuff.h:skbuff->cb[xxx] size appropriately.
 */
struct tcp_skb_cb {
	union {
		struct inet_skb_parm	h4;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
		struct inet6_skb_parm	h6;
#endif
	} header;	/* For incoming frames		*/
	__u32		seq;		/* Starting sequence number	*/
	__u32		end_seq;	/* SEQ + FIN + SYN + datalen	*/
	__u32		when;		/* used to compute rtt's	*/
	__u8		flags;		/* TCP header flags.		*/

	/* NOTE: These must match up to the flags byte in a
	 *       real TCP header.
	 */
#define TCPCB_FLAG_FIN		0x01
#define TCPCB_FLAG_SYN		0x02
#define TCPCB_FLAG_RST		0x04
#define TCPCB_FLAG_PSH		0x08
#define TCPCB_FLAG_ACK		0x10
#define TCPCB_FLAG_URG		0x20
#define TCPCB_FLAG_ECE		0x40
#define TCPCB_FLAG_CWR		0x80

	__u8		sacked;		/* State flags for SACK/FACK.	*/
#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_EVER_RETRANS	0x80	/* Ever retransmitted frame	*/
#define TCPCB_RETRANS		(TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS)

#define TCPCB_URG		0x20	/* Urgent pointer advanced here	*/

#define TCPCB_AT_TAIL		(TCPCB_URG)

	__u16		urg_ptr;	/* Valid w/URG flags is set.	*/
	__u32		ack_seq;	/* Sequence number ACK'd	*/
};

#define TCP_SKB_CB(__skb)	((struct tcp_skb_cb *)&((__skb)->cb[0]))

/* Due to TSO, an SKB can be composed of multiple actual
 * packets.  To keep these tracked properly, we use this.
 */
static inline int tcp_skb_pcount(const struct sk_buff *skb)
{
	return skb_shinfo(skb)->gso_segs;
}

/* This is valid iff tcp_skb_pcount() > 1. */
static inline int tcp_skb_mss(const struct sk_buff *skb)
{
	return skb_shinfo(skb)->gso_size;
}

static inline void tcp_dec_pcount_approx_int(__u32 *count, const int decr)
{
	if (*count) {
		*count -= decr;
		if ((int)*count < 0)
			*count = 0;
	}
}

static inline void tcp_dec_pcount_approx(__u32 *count,
					 const struct sk_buff *skb)
{
	tcp_dec_pcount_approx_int(count, tcp_skb_pcount(skb));
}

/* Events passed to congestion control interface */
enum tcp_ca_event {
	CA_EVENT_TX_START,	/* first transmit when no packets in flight */
	CA_EVENT_CWND_RESTART,	/* congestion window restart */
	CA_EVENT_COMPLETE_CWR,	/* end of congestion recovery */
	CA_EVENT_FRTO,		/* fast recovery timeout */
	CA_EVENT_LOSS,		/* loss timeout */
	CA_EVENT_FAST_ACK,	/* in sequence ack */
	CA_EVENT_SLOW_ACK,	/* other ack */
};

/*
 * Interface for adding new TCP congestion control handlers
 */
#define TCP_CA_NAME_MAX	16
#define TCP_CA_MAX	128
#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;
	unsigned long flags;

	/* initialize private data (optional) */
	void (*init)(struct sock *sk);
	/* cleanup private data  (optional) */
	void (*release)(struct sock *sk);

	/* 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, int good_ack);
	/* 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);
	/* new value of cwnd after loss (optional) */
	u32  (*undo_cwnd)(struct sock *sk);
	/* hook for packet ack accounting (optional) */
	void (*pkts_acked)(struct sock *sk, u32 num_acked, s32 rtt_us);
	/* get info for inet_diag (optional) */
	void (*get_info)(struct sock *sk, u32 ext, struct sk_buff *skb);

	char 		name[TCP_CA_NAME_MAX];
	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);

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 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, int flag);
extern u32 tcp_reno_min_cwnd(const struct sock *sk);
extern struct tcp_congestion_ops tcp_reno;

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);

	if (icsk->icsk_ca_ops->cwnd_event)
		icsk->icsk_ca_ops->cwnd_event(sk, event);
}

/* 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.
 *
 * tcp_is_sack - SACK enabled
 * tcp_is_reno - No SACK
 * tcp_is_fack - FACK enabled, implies SACK enabled
 */
static inline int tcp_is_sack(const struct tcp_sock *tp)
{
	return tp->rx_opt.sack_ok;
}

static inline int tcp_is_reno(const struct tcp_sock *tp)
{
	return !tcp_is_sack(tp);
}

static inline int tcp_is_fack(const struct tcp_sock *tp)
{
	return tp->rx_opt.sack_ok & 2;
}

static inline void tcp_enable_fack(struct tcp_sock *tp)
{
	tp->rx_opt.sack_ok |= 2;
}

static inline unsigned int tcp_left_out(const struct tcp_sock *tp)
{
	return tp->sacked_out + tp->lost_out;
}

/* This determines how many packets are "in the network" to the best
 * of our knowledge.  In many cases it is conservative, but where
 * detailed information is available from the receiver (via SACK
 * blocks etc.) we can make more aggressive calculations.
 *
 * Use this for decisions involving congestion control, use just
 * tp->packets_out to determine if the send queue is empty or not.
 *
 * Read this equation as:
 *
 *	"Packets sent once on transmission queue" MINUS
 *	"Packets left network, but not honestly ACKed yet" PLUS
 *	"Packets fast retransmitted"
 */
static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp)
{
	return tp->packets_out - tcp_left_out(tp) + tp->retrans_out;
}

/* If cwnd > ssthresh, we may raise ssthresh to be half-way to cwnd.
 * The exception is rate halving phase, when cwnd is decreasing towards
 * ssthresh.
 */
static inline __u32 tcp_current_ssthresh(const struct sock *sk)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	if ((1 << inet_csk(sk)->icsk_ca_state) & (TCPF_CA_CWR | TCPF_CA_Recovery))
		return tp->snd_ssthresh;
	else
		return max(tp->snd_ssthresh,
			   ((tp->snd_cwnd >> 1) +
			    (tp->snd_cwnd >> 2)));
}

/* 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(struct tcp_sock *tp, struct dst_entry *dst);

/* Slow start with delack produces 3 packets of burst, so that
 * it is safe "de facto".
 */
static __inline__ __u32 tcp_max_burst(const struct tcp_sock *tp)
{
	return 3;
}

/* RFC2861 Check whether we are limited by application or congestion window
 * This is the inverse of cwnd check in tcp_tso_should_defer
 */
static inline int tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	u32 left;

	if (in_flight >= tp->snd_cwnd)
		return 1;

	if (!sk_can_gso(sk))
		return 0;

	left = tp->snd_cwnd - in_flight;
	if (sysctl_tcp_tso_win_divisor)
		return left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd;
	else
		return left <= tcp_max_burst(tp);
}

static inline void tcp_minshall_update(struct tcp_sock *tp, unsigned int mss,
				       const struct sk_buff *skb)
{
	if (skb->len < mss)
		tp->snd_sml = TCP_SKB_CB(skb)->end_seq;
}

static inline void tcp_check_probe_timer(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	const struct inet_connection_sock *icsk = inet_csk(sk);

	if (!tp->packets_out && !icsk->icsk_pending)
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
					  icsk->icsk_rto, TCP_RTO_MAX);
}

static inline void tcp_push_pending_frames(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	__tcp_push_pending_frames(sk, tcp_current_mss(sk, 1), tp->nonagle);
}

static inline void tcp_init_wl(struct tcp_sock *tp, u32 ack, u32 seq)
{
	tp->snd_wl1 = seq;
}

static inline void tcp_update_wl(struct tcp_sock *tp, u32 ack, u32 seq)
{
	tp->snd_wl1 = seq;
}

/*
 * Calculate(/check) TCP checksum
 */
static inline __sum16 tcp_v4_check(int len, __be32 saddr,
				   __be32 daddr, __wsum base)
{
	return csum_tcpudp_magic(saddr,daddr,len,IPPROTO_TCP,base);
}

static inline __sum16 __tcp_checksum_complete(struct sk_buff *skb)
{
	return __skb_checksum_complete(skb);
}

static inline int tcp_checksum_complete(struct sk_buff *skb)
{
	return !skb_csum_unnecessary(skb) &&
		__tcp_checksum_complete(skb);
}

/* Prequeue for VJ style copy to user, combined with checksumming. */

static inline void tcp_prequeue_init(struct tcp_sock *tp)
{
	tp->ucopy.task = NULL;
	tp->ucopy.len = 0;
	tp->ucopy.memory = 0;
	skb_queue_head_init(&tp->ucopy.prequeue);
#ifdef CONFIG_NET_DMA
	tp->ucopy.dma_chan = NULL;
	tp->ucopy.wakeup = 0;
	tp->ucopy.pinned_list = NULL;
	tp->ucopy.dma_cookie = 0;
#endif
}

/* Packet is added to VJ-style prequeue for processing in process
 * context, if a reader task is waiting. Apparently, this exciting
 * idea (VJ's mail "Re: query about TCP header on tcp-ip" of 07 Sep 93)
 * failed somewhere. Latency? Burstiness? Well, at least now we will
 * see, why it failed. 8)8)				  --ANK
 *
 * NOTE: is this not too big to inline?
 */
static inline int tcp_prequeue(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (!sysctl_tcp_low_latency && tp->ucopy.task) {
		__skb_queue_tail(&tp->ucopy.prequeue, skb);
		tp->ucopy.memory += skb->truesize;
		if (tp->ucopy.memory > sk->sk_rcvbuf) {
			struct sk_buff *skb1;

			BUG_ON(sock_owned_by_user(sk));

			while ((skb1 = __skb_dequeue(&tp->ucopy.prequeue)) != NULL) {
				sk->sk_backlog_rcv(sk, skb1);
				NET_INC_STATS_BH(LINUX_MIB_TCPPREQUEUEDROPPED);
			}

			tp->ucopy.memory = 0;
		} else if (skb_queue_len(&tp->ucopy.prequeue) == 1) {
			wake_up_interruptible(sk->sk_sleep);
			if (!inet_csk_ack_scheduled(sk))
				inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
						          (3 * TCP_RTO_MIN) / 4,
							  TCP_RTO_MAX);
		}
		return 1;
	}
	return 0;
}


#undef STATE_TRACE

#ifdef STATE_TRACE
static const char *statename[]={
	"Unused","Established","Syn Sent","Syn Recv",
	"Fin Wait 1","Fin Wait 2","Time Wait", "Close",
	"Close Wait","Last ACK","Listen","Closing"
};
#endif