#define tcp_flag_word(tp) ( ((union tcp_word_hdr *)(tp))->words [3])
enum {
- TCP_FLAG_CWR = __constant_htonl(0x00800000),
- TCP_FLAG_ECE = __constant_htonl(0x00400000),
- TCP_FLAG_URG = __constant_htonl(0x00200000),
- TCP_FLAG_ACK = __constant_htonl(0x00100000),
- TCP_FLAG_PSH = __constant_htonl(0x00080000),
- TCP_FLAG_RST = __constant_htonl(0x00040000),
- TCP_FLAG_SYN = __constant_htonl(0x00020000),
- TCP_FLAG_FIN = __constant_htonl(0x00010000),
- TCP_RESERVED_BITS = __constant_htonl(0x0F000000),
- TCP_DATA_OFFSET = __constant_htonl(0xF0000000)
+ TCP_FLAG_CWR = __constant_cpu_to_be32(0x00800000),
+ TCP_FLAG_ECE = __constant_cpu_to_be32(0x00400000),
+ TCP_FLAG_URG = __constant_cpu_to_be32(0x00200000),
+ TCP_FLAG_ACK = __constant_cpu_to_be32(0x00100000),
+ TCP_FLAG_PSH = __constant_cpu_to_be32(0x00080000),
+ TCP_FLAG_RST = __constant_cpu_to_be32(0x00040000),
+ TCP_FLAG_SYN = __constant_cpu_to_be32(0x00020000),
+ TCP_FLAG_FIN = __constant_cpu_to_be32(0x00010000),
+ TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0F000000),
+ TCP_DATA_OFFSET = __constant_cpu_to_be32(0xF0000000)
};
+/*
+ * TCP general constants
+ */
+#define TCP_MSS_DEFAULT 536U /* IPv4 (RFC1122, RFC2581) */
+#define TCP_MSS_DESIRED 1220U /* IPv6 (tunneled), EDNS0 (RFC3226) */
+
/* TCP socket options */
#define TCP_NODELAY 1 /* Turn off Nagle's algorithm. */
#define TCP_MAXSEG 2 /* Limit MSS */
#define TCP_QUICKACK 12 /* Block/reenable quick acks */
#define TCP_CONGESTION 13 /* Congestion control algorithm */
#define TCP_MD5SIG 14 /* TCP MD5 Signature (RFC2385) */
+#define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/
+#define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */
+#define TCP_USER_TIMEOUT 18 /* How long for loss retry before timeout */
+#define TCP_REPAIR 19 /* TCP sock is under repair right now */
+#define TCP_REPAIR_QUEUE 20
+#define TCP_QUEUE_SEQ 21
+#define TCP_REPAIR_OPTIONS 22
+#define TCP_FASTOPEN 23 /* Enable FastOpen on listeners */
+#define TCP_TIMESTAMP 24
+#define TCP_NOTSENT_LOWAT 25 /* limit number of unsent bytes in write queue */
+#define TCP_CC_INFO 26 /* Get Congestion Control (optional) info */
+#define TCP_SAVE_SYN 27 /* Record SYN headers for new connections */
+#define TCP_SAVED_SYN 28 /* Get SYN headers recorded for connection */
+
+struct tcp_repair_opt {
+ __u32 opt_code;
+ __u32 opt_val;
+};
+enum {
+ TCP_NO_QUEUE,
+ TCP_RECV_QUEUE,
+ TCP_SEND_QUEUE,
+ TCP_QUEUES_NR,
+};
+
+/* for TCP_INFO socket option */
#define TCPI_OPT_TIMESTAMPS 1
#define TCPI_OPT_SACK 2
#define TCPI_OPT_WSCALE 4
-#define TCPI_OPT_ECN 8
+#define TCPI_OPT_ECN 8 /* ECN was negociated at TCP session init */
+#define TCPI_OPT_ECN_SEEN 16 /* we received at least one packet with ECT */
+#define TCPI_OPT_SYN_DATA 32 /* SYN-ACK acked data in SYN sent or rcvd */
-enum tcp_ca_state
-{
+enum tcp_ca_state {
TCP_CA_Open = 0,
#define TCPF_CA_Open (1<<TCP_CA_Open)
TCP_CA_Disorder = 1,
#define TCPF_CA_Loss (1<<TCP_CA_Loss)
};
-struct tcp_info
-{
+struct tcp_info {
__u8 tcpi_state;
__u8 tcpi_ca_state;
__u8 tcpi_retransmits;
__u32 tcpi_rcv_space;
__u32 tcpi_total_retrans;
+
+ __u64 tcpi_pacing_rate;
+ __u64 tcpi_max_pacing_rate;
+ __u64 tcpi_bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked */
+ __u64 tcpi_bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived */
+ __u32 tcpi_segs_out; /* RFC4898 tcpEStatsPerfSegsOut */
+ __u32 tcpi_segs_in; /* RFC4898 tcpEStatsPerfSegsIn */
};
/* for TCP_MD5SIG socket option */
__u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN]; /* key (binary) */
};
-#ifdef __KERNEL__
-
-#include <linux/skbuff.h>
-#include <linux/dmaengine.h>
-#include <net/sock.h>
-#include <net/inet_connection_sock.h>
-#include <net/inet_timewait_sock.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 unsigned int tcp_optlen(const struct sk_buff *skb)
-{
- return (tcp_hdr(skb)->doff - 5) * 4;
-}
-
-/* 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;
-};
-
-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 */
-/* SACKs data */
- u8 eff_sacks; /* Size of SACK array to send with next packet */
- 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 */
-};
-
-/* This is the max number of SACKS that we'll generate and process. It's safe
- * to increse 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_request_sock {
- struct inet_request_sock req;
-#ifdef CONFIG_TCP_MD5SIG
- /* Only used by TCP MD5 Signature so far. */
- struct tcp_request_sock_ops *af_specific;
-#endif
- u32 rcv_isn;
- u32 snt_isn;
-};
-
-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; /* 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) */
-
- /* 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; /* Disable Nagle algorithm? */
-
-/* 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 urg_mode; /* In urgent mode */
- u8 ecn_flags; /* ECN status bits. */
-/*
- * 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 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;
- u32 bytes_acked; /* Appropriate Byte Counting - RFC3465 */
-
- /* 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 *forward_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_build_and_update_options) */
- 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; /* highest skb with SACK received
- * (validity guaranteed only if
- * sacked_out > 0)
- */
-
- int lost_cnt_hint;
- int retransmit_cnt_hint;
-
- u32 lost_retrans_low; /* Sent seq after any rxmit (lowest) */
-
- u8 reordering; /* Packet reordering metric. */
- u8 keepalive_probes; /* num of allowed keep alive probes */
- 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 */
- u32 snd_up; /* Urgent pointer */
-
- unsigned int keepalive_time; /* time before keep alive takes place */
- unsigned int keepalive_intvl; /* time interval between keep alive probes */
-
- unsigned long last_synq_overflow;
-
-/* 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;
-
-#ifdef CONFIG_TCP_MD5SIG
-/* TCP AF-Specific parts; only used by MD5 Signature support so far */
- struct tcp_sock_af_ops *af_specific;
-
-/* TCP MD5 Signagure Option information */
- struct tcp_md5sig_info *md5sig_info;
-#endif
-
- int linger2;
-};
-
-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_recent;
- long tw_ts_recent_stamp;
-#ifdef CONFIG_TCP_MD5SIG
- u16 tw_md5_keylen;
- u8 tw_md5_key[TCP_MD5SIG_MAXKEYLEN];
-#endif
-};
-
-static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk)
-{
- return (struct tcp_timewait_sock *)sk;
-}
-
-#endif
-
-#endif /* _LINUX_TCP_H */
+#endif /* _LINUX_TCP_H */
projects / l4.git / blobdiff