kernel-ark/include/linux/tcp.h
Ilpo Järvinen 68f8353b48 [TCP]: Rewrite SACK block processing & sack_recv_cache use
Key points of this patch are:

  - In case new SACK information is advance only type, no skb
    processing below previously discovered highest point is done
  - Optimize cases below highest point too since there's no need
    to always go up to highest point (which is very likely still
    present in that SACK), this is not entirely true though
    because I'm dropping the fastpath_skb_hint which could
    previously optimize those cases even better. Whether that's
    significant, I'm not too sure.

Currently it will provide skipping by walking. Combined with
RB-tree, all skipping would become fast too regardless of window
size (can be done incrementally later).

Previously a number of cases in TCP SACK processing fails to
take advantage of costly stored information in sack_recv_cache,
most importantly, expected events such as cumulative ACK and new
hole ACKs. Processing on such ACKs result in rather long walks
building up latencies (which easily gets nasty when window is
huge). Those latencies are often completely unnecessary
compared with the amount of _new_ information received, usually
for cumulative ACK there's no new information at all, yet TCP
walks whole queue unnecessary potentially taking a number of
costly cache misses on the way, etc.!

Since the inclusion of highest_sack, there's a lot information
that is very likely redundant (SACK fastpath hint stuff,
fackets_out, highest_sack), though there's no ultimate guarantee
that they'll remain the same whole the time (in all unearthly
scenarios). Take advantage of this knowledge here and drop
fastpath hint and use direct access to highest SACKed skb as
a replacement.

Effectively "special cased" fastpath is dropped. This change
adds some complexity to introduce better coveraged "fastpath",
though the added complexity should make TCP behave more cache
friendly.

The current ACK's SACK blocks are compared against each cached
block individially and only ranges that are new are then scanned
by the high constant walk. For other parts of write queue, even
when in previously known part of the SACK blocks, a faster skip
function is used (if necessary at all). In addition, whenever
possible, TCP fast-forwards to highest_sack skb that was made
available by an earlier patch. In typical case, no other things
but this fast-forward and mandatory markings after that occur
making the access pattern quite similar to the former fastpath
"special case".

DSACKs are special case that must always be walked.

The local to recv_sack_cache copying could be more intelligent
w.r.t DSACKs which are likely to be there only once but that
is left to a separate patch.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-28 14:54:07 -08:00

436 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/types.h>
#include <asm/byteorder.h>
#include <linux/socket.h>
struct tcphdr {
__be16 source;
__be16 dest;
__be32 seq;
__be32 ack_seq;
#if defined(__LITTLE_ENDIAN_BITFIELD)
__u16 res1:4,
doff:4,
fin:1,
syn:1,
rst:1,
psh:1,
ack:1,
urg:1,
ece:1,
cwr:1;
#elif defined(__BIG_ENDIAN_BITFIELD)
__u16 doff:4,
res1:4,
cwr:1,
ece:1,
urg:1,
ack:1,
psh:1,
rst:1,
syn:1,
fin:1;
#else
#error "Adjust your <asm/byteorder.h> defines"
#endif
__be16 window;
__sum16 check;
__be16 urg_ptr;
};
/*
* The union cast uses a gcc extension to avoid aliasing problems
* (union is compatible to any of its members)
* This means this part of the code is -fstrict-aliasing safe now.
*/
union tcp_word_hdr {
struct tcphdr hdr;
__be32 words[5];
};
#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 socket options */
#define TCP_NODELAY 1 /* Turn off Nagle's algorithm. */
#define TCP_MAXSEG 2 /* Limit MSS */
#define TCP_CORK 3 /* Never send partially complete segments */
#define TCP_KEEPIDLE 4 /* Start keeplives after this period */
#define TCP_KEEPINTVL 5 /* Interval between keepalives */
#define TCP_KEEPCNT 6 /* Number of keepalives before death */
#define TCP_SYNCNT 7 /* Number of SYN retransmits */
#define TCP_LINGER2 8 /* Life time of orphaned FIN-WAIT-2 state */
#define TCP_DEFER_ACCEPT 9 /* Wake up listener only when data arrive */
#define TCP_WINDOW_CLAMP 10 /* Bound advertised window */
#define TCP_INFO 11 /* Information about this connection. */
#define TCP_QUICKACK 12 /* Block/reenable quick acks */
#define TCP_CONGESTION 13 /* Congestion control algorithm */
#define TCP_MD5SIG 14 /* TCP MD5 Signature (RFC2385) */
#define TCPI_OPT_TIMESTAMPS 1
#define TCPI_OPT_SACK 2
#define TCPI_OPT_WSCALE 4
#define TCPI_OPT_ECN 8
enum tcp_ca_state
{
TCP_CA_Open = 0,
#define TCPF_CA_Open (1<<TCP_CA_Open)
TCP_CA_Disorder = 1,
#define TCPF_CA_Disorder (1<<TCP_CA_Disorder)
TCP_CA_CWR = 2,
#define TCPF_CA_CWR (1<<TCP_CA_CWR)
TCP_CA_Recovery = 3,
#define TCPF_CA_Recovery (1<<TCP_CA_Recovery)
TCP_CA_Loss = 4
#define TCPF_CA_Loss (1<<TCP_CA_Loss)
};
struct tcp_info
{
__u8 tcpi_state;
__u8 tcpi_ca_state;
__u8 tcpi_retransmits;
__u8 tcpi_probes;
__u8 tcpi_backoff;
__u8 tcpi_options;
__u8 tcpi_snd_wscale : 4, tcpi_rcv_wscale : 4;
__u32 tcpi_rto;
__u32 tcpi_ato;
__u32 tcpi_snd_mss;
__u32 tcpi_rcv_mss;
__u32 tcpi_unacked;
__u32 tcpi_sacked;
__u32 tcpi_lost;
__u32 tcpi_retrans;
__u32 tcpi_fackets;
/* Times. */
__u32 tcpi_last_data_sent;
__u32 tcpi_last_ack_sent; /* Not remembered, sorry. */
__u32 tcpi_last_data_recv;
__u32 tcpi_last_ack_recv;
/* Metrics. */
__u32 tcpi_pmtu;
__u32 tcpi_rcv_ssthresh;
__u32 tcpi_rtt;
__u32 tcpi_rttvar;
__u32 tcpi_snd_ssthresh;
__u32 tcpi_snd_cwnd;
__u32 tcpi_advmss;
__u32 tcpi_reordering;
__u32 tcpi_rcv_rtt;
__u32 tcpi_rcv_space;
__u32 tcpi_total_retrans;
};
/* for TCP_MD5SIG socket option */
#define TCP_MD5SIG_MAXKEYLEN 80
struct tcp_md5sig {
struct __kernel_sockaddr_storage tcpm_addr; /* address associated */
__u16 __tcpm_pad1; /* zero */
__u16 tcpm_keylen; /* key length */
__u32 __tcpm_pad2; /* zero */
__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 */
};
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 */
u8 reordering; /* Packet reordering metric. */
u8 frto_counter; /* Number of new acks after RTO */
u8 nonagle; /* Disable Nagle algorithm? */
u8 keepalive_probes; /* num of allowed keep alive probes */
/* 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 */
/*
* 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;
struct sk_buff_head out_of_order_queue; /* Out of order segments go here */
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 */
/* SACKs data */
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)
*/
/* 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;
int lost_cnt_hint;
int retransmit_cnt_hint;
u32 lost_retrans_low; /* Sent seq after any rxmit (lowest) */
u16 advmss; /* Advertised MSS */
u16 prior_ssthresh; /* ssthresh saved at recovery start */
u32 lost_out; /* Lost packets */
u32 sacked_out; /* SACK'd packets */
u32 fackets_out; /* FACK'd packets */
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 urg_seq; /* Seq of received urgent pointer */
u16 urg_data; /* Saved octet of OOB data and control flags */
u8 urg_mode; /* In urgent mode */
u8 ecn_flags; /* ECN status bits. */
u32 snd_up; /* Urgent pointer */
u32 total_retrans; /* Total retransmits for entire connection */
u32 bytes_acked; /* Appropriate Byte Counting - RFC3465 */
unsigned int keepalive_time; /* time before keep alive takes place */
unsigned int keepalive_intvl; /* time interval between keep alive probes */
int linger2;
unsigned long last_synq_overflow;
u32 tso_deferred;
/* 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
};
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 */