ceaa1fef65
This functionality is used for restoring tcp sockets. A tcp timestamp depends on how long a system has been running, so it's differ for each host. The solution is to set a per-socket offset. A per-socket offset for a TIME_WAIT socket is inherited from a proper tcp socket. tcp_request_sock doesn't have a timestamp offset, because the repair mode for them are not implemented. Cc: "David S. Miller" <davem@davemloft.net> Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> Cc: James Morris <jmorris@namei.org> Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> Cc: Patrick McHardy <kaber@trash.net> Cc: Eric Dumazet <edumazet@google.com> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrey Vagin <avagin@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
407 lines
12 KiB
C
407 lines
12 KiB
C
/*
|
|
* INET An implementation of the TCP/IP protocol suite for the LINUX
|
|
* operating system. INET is implemented using the BSD Socket
|
|
* interface as the means of communication with the user level.
|
|
*
|
|
* Definitions for the TCP protocol.
|
|
*
|
|
* Version: @(#)tcp.h 1.0.2 04/28/93
|
|
*
|
|
* Author: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; either version
|
|
* 2 of the License, or (at your option) any later version.
|
|
*/
|
|
#ifndef _LINUX_TCP_H
|
|
#define _LINUX_TCP_H
|
|
|
|
|
|
#include <linux/skbuff.h>
|
|
#include <linux/dmaengine.h>
|
|
#include <net/sock.h>
|
|
#include <net/inet_connection_sock.h>
|
|
#include <net/inet_timewait_sock.h>
|
|
#include <uapi/linux/tcp.h>
|
|
|
|
static inline struct tcphdr *tcp_hdr(const struct sk_buff *skb)
|
|
{
|
|
return (struct tcphdr *)skb_transport_header(skb);
|
|
}
|
|
|
|
static inline unsigned int tcp_hdrlen(const struct sk_buff *skb)
|
|
{
|
|
return tcp_hdr(skb)->doff * 4;
|
|
}
|
|
|
|
static inline struct tcphdr *inner_tcp_hdr(const struct sk_buff *skb)
|
|
{
|
|
return (struct tcphdr *)skb_inner_transport_header(skb);
|
|
}
|
|
|
|
static inline unsigned int inner_tcp_hdrlen(const struct sk_buff *skb)
|
|
{
|
|
return inner_tcp_hdr(skb)->doff * 4;
|
|
}
|
|
|
|
static inline unsigned int tcp_optlen(const struct sk_buff *skb)
|
|
{
|
|
return (tcp_hdr(skb)->doff - 5) * 4;
|
|
}
|
|
|
|
/* TCP Fast Open */
|
|
#define TCP_FASTOPEN_COOKIE_MIN 4 /* Min Fast Open Cookie size in bytes */
|
|
#define TCP_FASTOPEN_COOKIE_MAX 16 /* Max Fast Open Cookie size in bytes */
|
|
#define TCP_FASTOPEN_COOKIE_SIZE 8 /* the size employed by this impl. */
|
|
|
|
/* TCP Fast Open Cookie as stored in memory */
|
|
struct tcp_fastopen_cookie {
|
|
s8 len;
|
|
u8 val[TCP_FASTOPEN_COOKIE_MAX];
|
|
};
|
|
|
|
/* This defines a selective acknowledgement block. */
|
|
struct tcp_sack_block_wire {
|
|
__be32 start_seq;
|
|
__be32 end_seq;
|
|
};
|
|
|
|
struct tcp_sack_block {
|
|
u32 start_seq;
|
|
u32 end_seq;
|
|
};
|
|
|
|
/*These are used to set the sack_ok field in struct tcp_options_received */
|
|
#define TCP_SACK_SEEN (1 << 0) /*1 = peer is SACK capable, */
|
|
#define TCP_FACK_ENABLED (1 << 1) /*1 = FACK is enabled locally*/
|
|
#define TCP_DSACK_SEEN (1 << 2) /*1 = DSACK was received from peer*/
|
|
|
|
struct tcp_options_received {
|
|
/* PAWS/RTTM data */
|
|
long ts_recent_stamp;/* Time we stored ts_recent (for aging) */
|
|
u32 ts_recent; /* Time stamp to echo next */
|
|
u32 rcv_tsval; /* Time stamp value */
|
|
u32 rcv_tsecr; /* Time stamp echo reply */
|
|
u16 saw_tstamp : 1, /* Saw TIMESTAMP on last packet */
|
|
tstamp_ok : 1, /* TIMESTAMP seen on SYN packet */
|
|
dsack : 1, /* D-SACK is scheduled */
|
|
wscale_ok : 1, /* Wscale seen on SYN packet */
|
|
sack_ok : 4, /* SACK seen on SYN packet */
|
|
snd_wscale : 4, /* Window scaling received from sender */
|
|
rcv_wscale : 4; /* Window scaling to send to receiver */
|
|
u8 cookie_plus:6, /* bytes in authenticator/cookie option */
|
|
cookie_out_never:1,
|
|
cookie_in_always:1;
|
|
u8 num_sacks; /* Number of SACK blocks */
|
|
u16 user_mss; /* mss requested by user in ioctl */
|
|
u16 mss_clamp; /* Maximal mss, negotiated at connection setup */
|
|
};
|
|
|
|
static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
|
|
{
|
|
rx_opt->tstamp_ok = rx_opt->sack_ok = 0;
|
|
rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
|
|
rx_opt->cookie_plus = 0;
|
|
}
|
|
|
|
/* This is the max number of SACKS that we'll generate and process. It's safe
|
|
* to increase this, although since:
|
|
* size = TCPOLEN_SACK_BASE_ALIGNED (4) + n * TCPOLEN_SACK_PERBLOCK (8)
|
|
* only four options will fit in a standard TCP header */
|
|
#define TCP_NUM_SACKS 4
|
|
|
|
struct tcp_cookie_values;
|
|
struct tcp_request_sock_ops;
|
|
|
|
struct tcp_request_sock {
|
|
struct inet_request_sock req;
|
|
#ifdef CONFIG_TCP_MD5SIG
|
|
/* Only used by TCP MD5 Signature so far. */
|
|
const struct tcp_request_sock_ops *af_specific;
|
|
#endif
|
|
struct sock *listener; /* needed for TFO */
|
|
u32 rcv_isn;
|
|
u32 snt_isn;
|
|
u32 snt_synack; /* synack sent time */
|
|
u32 rcv_nxt; /* the ack # by SYNACK. For
|
|
* FastOpen it's the seq#
|
|
* after data-in-SYN.
|
|
*/
|
|
};
|
|
|
|
static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)
|
|
{
|
|
return (struct tcp_request_sock *)req;
|
|
}
|
|
|
|
struct tcp_sock {
|
|
/* inet_connection_sock has to be the first member of tcp_sock */
|
|
struct inet_connection_sock inet_conn;
|
|
u16 tcp_header_len; /* Bytes of tcp header to send */
|
|
u16 xmit_size_goal_segs; /* Goal for segmenting output packets */
|
|
|
|
/*
|
|
* Header prediction flags
|
|
* 0x5?10 << 16 + snd_wnd in net byte order
|
|
*/
|
|
__be32 pred_flags;
|
|
|
|
/*
|
|
* RFC793 variables by their proper names. This means you can
|
|
* read the code and the spec side by side (and laugh ...)
|
|
* See RFC793 and RFC1122. The RFC writes these in capitals.
|
|
*/
|
|
u32 rcv_nxt; /* What we want to receive next */
|
|
u32 copied_seq; /* Head of yet unread data */
|
|
u32 rcv_wup; /* rcv_nxt on last window update sent */
|
|
u32 snd_nxt; /* Next sequence we send */
|
|
|
|
u32 snd_una; /* First byte we want an ack for */
|
|
u32 snd_sml; /* Last byte of the most recently transmitted small packet */
|
|
u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */
|
|
u32 lsndtime; /* timestamp of last sent data packet (for restart window) */
|
|
|
|
u32 tsoffset; /* timestamp offset */
|
|
|
|
struct list_head tsq_node; /* anchor in tsq_tasklet.head list */
|
|
unsigned long tsq_flags;
|
|
|
|
/* Data for direct copy to user */
|
|
struct {
|
|
struct sk_buff_head prequeue;
|
|
struct task_struct *task;
|
|
struct iovec *iov;
|
|
int memory;
|
|
int len;
|
|
#ifdef CONFIG_NET_DMA
|
|
/* members for async copy */
|
|
struct dma_chan *dma_chan;
|
|
int wakeup;
|
|
struct dma_pinned_list *pinned_list;
|
|
dma_cookie_t dma_cookie;
|
|
#endif
|
|
} ucopy;
|
|
|
|
u32 snd_wl1; /* Sequence for window update */
|
|
u32 snd_wnd; /* The window we expect to receive */
|
|
u32 max_window; /* Maximal window ever seen from peer */
|
|
u32 mss_cache; /* Cached effective mss, not including SACKS */
|
|
|
|
u32 window_clamp; /* Maximal window to advertise */
|
|
u32 rcv_ssthresh; /* Current window clamp */
|
|
|
|
u32 frto_highmark; /* snd_nxt when RTO occurred */
|
|
u16 advmss; /* Advertised MSS */
|
|
u8 frto_counter; /* Number of new acks after RTO */
|
|
u8 nonagle : 4,/* Disable Nagle algorithm? */
|
|
thin_lto : 1,/* Use linear timeouts for thin streams */
|
|
thin_dupack : 1,/* Fast retransmit on first dupack */
|
|
repair : 1,
|
|
unused : 1;
|
|
u8 repair_queue;
|
|
u8 do_early_retrans:1,/* Enable RFC5827 early-retransmit */
|
|
early_retrans_delayed:1, /* Delayed ER timer installed */
|
|
syn_data:1, /* SYN includes data */
|
|
syn_fastopen:1, /* SYN includes Fast Open option */
|
|
syn_data_acked:1;/* data in SYN is acked by SYN-ACK */
|
|
|
|
/* RTT measurement */
|
|
u32 srtt; /* smoothed round trip time << 3 */
|
|
u32 mdev; /* medium deviation */
|
|
u32 mdev_max; /* maximal mdev for the last rtt period */
|
|
u32 rttvar; /* smoothed mdev_max */
|
|
u32 rtt_seq; /* sequence number to update rttvar */
|
|
|
|
u32 packets_out; /* Packets which are "in flight" */
|
|
u32 retrans_out; /* Retransmitted packets out */
|
|
|
|
u16 urg_data; /* Saved octet of OOB data and control flags */
|
|
u8 ecn_flags; /* ECN status bits. */
|
|
u8 reordering; /* Packet reordering metric. */
|
|
u32 snd_up; /* Urgent pointer */
|
|
|
|
u8 keepalive_probes; /* num of allowed keep alive probes */
|
|
/*
|
|
* Options received (usually on last packet, some only on SYN packets).
|
|
*/
|
|
struct tcp_options_received rx_opt;
|
|
|
|
/*
|
|
* Slow start and congestion control (see also Nagle, and Karn & Partridge)
|
|
*/
|
|
u32 snd_ssthresh; /* Slow start size threshold */
|
|
u32 snd_cwnd; /* Sending congestion window */
|
|
u32 snd_cwnd_cnt; /* Linear increase counter */
|
|
u32 snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */
|
|
u32 snd_cwnd_used;
|
|
u32 snd_cwnd_stamp;
|
|
u32 prior_cwnd; /* Congestion window at start of Recovery. */
|
|
u32 prr_delivered; /* Number of newly delivered packets to
|
|
* receiver in Recovery. */
|
|
u32 prr_out; /* Total number of pkts sent during Recovery. */
|
|
|
|
u32 rcv_wnd; /* Current receiver window */
|
|
u32 write_seq; /* Tail(+1) of data held in tcp send buffer */
|
|
u32 pushed_seq; /* Last pushed seq, required to talk to windows */
|
|
u32 lost_out; /* Lost packets */
|
|
u32 sacked_out; /* SACK'd packets */
|
|
u32 fackets_out; /* FACK'd packets */
|
|
u32 tso_deferred;
|
|
|
|
/* from STCP, retrans queue hinting */
|
|
struct sk_buff* lost_skb_hint;
|
|
struct sk_buff *scoreboard_skb_hint;
|
|
struct sk_buff *retransmit_skb_hint;
|
|
|
|
struct sk_buff_head out_of_order_queue; /* Out of order segments go here */
|
|
|
|
/* SACKs data, these 2 need to be together (see tcp_options_write) */
|
|
struct tcp_sack_block duplicate_sack[1]; /* D-SACK block */
|
|
struct tcp_sack_block selective_acks[4]; /* The SACKS themselves*/
|
|
|
|
struct tcp_sack_block recv_sack_cache[4];
|
|
|
|
struct sk_buff *highest_sack; /* skb just after the highest
|
|
* skb with SACKed bit set
|
|
* (validity guaranteed only if
|
|
* sacked_out > 0)
|
|
*/
|
|
|
|
int lost_cnt_hint;
|
|
u32 retransmit_high; /* L-bits may be on up to this seqno */
|
|
|
|
u32 lost_retrans_low; /* Sent seq after any rxmit (lowest) */
|
|
|
|
u32 prior_ssthresh; /* ssthresh saved at recovery start */
|
|
u32 high_seq; /* snd_nxt at onset of congestion */
|
|
|
|
u32 retrans_stamp; /* Timestamp of the last retransmit,
|
|
* also used in SYN-SENT to remember stamp of
|
|
* the first SYN. */
|
|
u32 undo_marker; /* tracking retrans started here. */
|
|
int undo_retrans; /* number of undoable retransmissions. */
|
|
u32 total_retrans; /* Total retransmits for entire connection */
|
|
|
|
u32 urg_seq; /* Seq of received urgent pointer */
|
|
unsigned int keepalive_time; /* time before keep alive takes place */
|
|
unsigned int keepalive_intvl; /* time interval between keep alive probes */
|
|
|
|
int linger2;
|
|
|
|
/* Receiver side RTT estimation */
|
|
struct {
|
|
u32 rtt;
|
|
u32 seq;
|
|
u32 time;
|
|
} rcv_rtt_est;
|
|
|
|
/* Receiver queue space */
|
|
struct {
|
|
int space;
|
|
u32 seq;
|
|
u32 time;
|
|
} rcvq_space;
|
|
|
|
/* TCP-specific MTU probe information. */
|
|
struct {
|
|
u32 probe_seq_start;
|
|
u32 probe_seq_end;
|
|
} mtu_probe;
|
|
u32 mtu_info; /* We received an ICMP_FRAG_NEEDED / ICMPV6_PKT_TOOBIG
|
|
* while socket was owned by user.
|
|
*/
|
|
|
|
#ifdef CONFIG_TCP_MD5SIG
|
|
/* TCP AF-Specific parts; only used by MD5 Signature support so far */
|
|
const struct tcp_sock_af_ops *af_specific;
|
|
|
|
/* TCP MD5 Signature Option information */
|
|
struct tcp_md5sig_info __rcu *md5sig_info;
|
|
#endif
|
|
|
|
/* When the cookie options are generated and exchanged, then this
|
|
* object holds a reference to them (cookie_values->kref). Also
|
|
* contains related tcp_cookie_transactions fields.
|
|
*/
|
|
struct tcp_cookie_values *cookie_values;
|
|
|
|
/* TCP fastopen related information */
|
|
struct tcp_fastopen_request *fastopen_req;
|
|
/* fastopen_rsk points to request_sock that resulted in this big
|
|
* socket. Used to retransmit SYNACKs etc.
|
|
*/
|
|
struct request_sock *fastopen_rsk;
|
|
};
|
|
|
|
enum tsq_flags {
|
|
TSQ_THROTTLED,
|
|
TSQ_QUEUED,
|
|
TCP_TSQ_DEFERRED, /* tcp_tasklet_func() found socket was owned */
|
|
TCP_WRITE_TIMER_DEFERRED, /* tcp_write_timer() found socket was owned */
|
|
TCP_DELACK_TIMER_DEFERRED, /* tcp_delack_timer() found socket was owned */
|
|
TCP_MTU_REDUCED_DEFERRED, /* tcp_v{4|6}_err() could not call
|
|
* tcp_v{4|6}_mtu_reduced()
|
|
*/
|
|
};
|
|
|
|
static inline struct tcp_sock *tcp_sk(const struct sock *sk)
|
|
{
|
|
return (struct tcp_sock *)sk;
|
|
}
|
|
|
|
struct tcp_timewait_sock {
|
|
struct inet_timewait_sock tw_sk;
|
|
u32 tw_rcv_nxt;
|
|
u32 tw_snd_nxt;
|
|
u32 tw_rcv_wnd;
|
|
u32 tw_ts_offset;
|
|
u32 tw_ts_recent;
|
|
long tw_ts_recent_stamp;
|
|
#ifdef CONFIG_TCP_MD5SIG
|
|
struct tcp_md5sig_key *tw_md5_key;
|
|
#endif
|
|
/* Few sockets in timewait have cookies; in that case, then this
|
|
* object holds a reference to them (tw_cookie_values->kref).
|
|
*/
|
|
struct tcp_cookie_values *tw_cookie_values;
|
|
};
|
|
|
|
static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk)
|
|
{
|
|
return (struct tcp_timewait_sock *)sk;
|
|
}
|
|
|
|
static inline bool tcp_passive_fastopen(const struct sock *sk)
|
|
{
|
|
return (sk->sk_state == TCP_SYN_RECV &&
|
|
tcp_sk(sk)->fastopen_rsk != NULL);
|
|
}
|
|
|
|
static inline bool fastopen_cookie_present(struct tcp_fastopen_cookie *foc)
|
|
{
|
|
return foc->len != -1;
|
|
}
|
|
|
|
extern void tcp_sock_destruct(struct sock *sk);
|
|
|
|
static inline int fastopen_init_queue(struct sock *sk, int backlog)
|
|
{
|
|
struct request_sock_queue *queue =
|
|
&inet_csk(sk)->icsk_accept_queue;
|
|
|
|
if (queue->fastopenq == NULL) {
|
|
queue->fastopenq = kzalloc(
|
|
sizeof(struct fastopen_queue),
|
|
sk->sk_allocation);
|
|
if (queue->fastopenq == NULL)
|
|
return -ENOMEM;
|
|
|
|
sk->sk_destruct = tcp_sock_destruct;
|
|
spin_lock_init(&queue->fastopenq->lock);
|
|
}
|
|
queue->fastopenq->max_qlen = backlog;
|
|
return 0;
|
|
}
|
|
|
|
#endif /* _LINUX_TCP_H */
|