linux-sg2042/include/linux/tcp.h

558 lines
16 KiB
C
Raw Normal View History

/*
* 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_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_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 TCP_COOKIE_TRANSACTIONS 15 /* TCP Cookie Transactions */
#define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/
#define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */
tcp: Add TCP_USER_TIMEOUT socket option. This patch provides a "user timeout" support as described in RFC793. The socket option is also needed for the the local half of RFC5482 "TCP User Timeout Option". TCP_USER_TIMEOUT is a TCP level socket option that takes an unsigned int, when > 0, to specify the maximum amount of time in ms that transmitted data may remain unacknowledged before TCP will forcefully close the corresponding connection and return ETIMEDOUT to the application. If 0 is given, TCP will continue to use the system default. Increasing the user timeouts allows a TCP connection to survive extended periods without end-to-end connectivity. Decreasing the user timeouts allows applications to "fail fast" if so desired. Otherwise it may take upto 20 minutes with the current system defaults in a normal WAN environment. The socket option can be made during any state of a TCP connection, but is only effective during the synchronized states of a connection (ESTABLISHED, FIN-WAIT-1, FIN-WAIT-2, CLOSE-WAIT, CLOSING, or LAST-ACK). Moreover, when used with the TCP keepalive (SO_KEEPALIVE) option, TCP_USER_TIMEOUT will overtake keepalive to determine when to close a connection due to keepalive failure. The option does not change in anyway when TCP retransmits a packet, nor when a keepalive probe will be sent. This option, like many others, will be inherited by an acceptor from its listener. Signed-off-by: H.K. Jerry Chu <hkchu@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-08-28 03:13:28 +08:00
#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
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 /* ECN was negociated at TCP session init */
#define TCPI_OPT_ECN_SEEN 16 /* we received at least one packet with ECT */
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) */
};
/* for TCP_COOKIE_TRANSACTIONS (TCPCT) socket option */
#define TCP_COOKIE_MIN 8 /* 64-bits */
#define TCP_COOKIE_MAX 16 /* 128-bits */
#define TCP_COOKIE_PAIR_SIZE (2*TCP_COOKIE_MAX)
/* Flags for both getsockopt and setsockopt */
#define TCP_COOKIE_IN_ALWAYS (1 << 0) /* Discard SYN without cookie */
#define TCP_COOKIE_OUT_NEVER (1 << 1) /* Prohibit outgoing cookies,
* supercedes everything. */
/* Flags for getsockopt */
#define TCP_S_DATA_IN (1 << 2) /* Was data received? */
#define TCP_S_DATA_OUT (1 << 3) /* Was data sent? */
/* TCP_COOKIE_TRANSACTIONS data */
struct tcp_cookie_transactions {
__u16 tcpct_flags; /* see above */
__u8 __tcpct_pad1; /* zero */
__u8 tcpct_cookie_desired; /* bytes */
__u16 tcpct_s_data_desired; /* bytes of variable data */
__u16 tcpct_used; /* bytes in value */
__u8 tcpct_value[TCP_MSS_DEFAULT];
};
#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;
}
/* 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 */
/* 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 */
TCPCT part 1d: define TCP cookie option, extend existing struct's Data structures are carefully composed to require minimal additions. For example, the struct tcp_options_received cookie_plus variable fits between existing 16-bit and 8-bit variables, requiring no additional space (taking alignment into consideration). There are no additions to tcp_request_sock, and only 1 pointer in tcp_sock. This is a significantly revised implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 The principle difference is using a TCP option to carry the cookie nonce, instead of a user configured offset in the data. This is more flexible and less subject to user configuration error. Such a cookie option has been suggested for many years, and is also useful without SYN data, allowing several related concepts to use the same extension option. "Re: SYN floods (was: does history repeat itself?)", September 9, 1996. http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html "Re: what a new TCP header might look like", May 12, 1998. ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail These functions will also be used in subsequent patches that implement additional features. Requires: TCPCT part 1a: add request_values parameter for sending SYNACK TCPCT part 1b: generate Responder Cookie secret TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-03 02:17:05 +08:00
u8 cookie_plus:6, /* bytes in authenticator/cookie option */
cookie_out_never:1,
cookie_in_always:1;
u8 num_sacks; /* Number of SACK blocks */
TCPCT part 1d: define TCP cookie option, extend existing struct's Data structures are carefully composed to require minimal additions. For example, the struct tcp_options_received cookie_plus variable fits between existing 16-bit and 8-bit variables, requiring no additional space (taking alignment into consideration). There are no additions to tcp_request_sock, and only 1 pointer in tcp_sock. This is a significantly revised implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 The principle difference is using a TCP option to carry the cookie nonce, instead of a user configured offset in the data. This is more flexible and less subject to user configuration error. Such a cookie option has been suggested for many years, and is also useful without SYN data, allowing several related concepts to use the same extension option. "Re: SYN floods (was: does history repeat itself?)", September 9, 1996. http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html "Re: what a new TCP header might look like", May 12, 1998. ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail These functions will also be used in subsequent patches that implement additional features. Requires: TCPCT part 1a: add request_values parameter for sending SYNACK TCPCT part 1b: generate Responder Cookie secret TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-03 02:17:05 +08:00
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)
{
TCPCT part 1d: define TCP cookie option, extend existing struct's Data structures are carefully composed to require minimal additions. For example, the struct tcp_options_received cookie_plus variable fits between existing 16-bit and 8-bit variables, requiring no additional space (taking alignment into consideration). There are no additions to tcp_request_sock, and only 1 pointer in tcp_sock. This is a significantly revised implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 The principle difference is using a TCP option to carry the cookie nonce, instead of a user configured offset in the data. This is more flexible and less subject to user configuration error. Such a cookie option has been suggested for many years, and is also useful without SYN data, allowing several related concepts to use the same extension option. "Re: SYN floods (was: does history repeat itself?)", September 9, 1996. http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html "Re: what a new TCP header might look like", May 12, 1998. ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail These functions will also be used in subsequent patches that implement additional features. Requires: TCPCT part 1a: add request_values parameter for sending SYNACK TCPCT part 1b: generate Responder Cookie secret TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-03 02:17:05 +08:00
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
TCPCT part 1d: define TCP cookie option, extend existing struct's Data structures are carefully composed to require minimal additions. For example, the struct tcp_options_received cookie_plus variable fits between existing 16-bit and 8-bit variables, requiring no additional space (taking alignment into consideration). There are no additions to tcp_request_sock, and only 1 pointer in tcp_sock. This is a significantly revised implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 The principle difference is using a TCP option to carry the cookie nonce, instead of a user configured offset in the data. This is more flexible and less subject to user configuration error. Such a cookie option has been suggested for many years, and is also useful without SYN data, allowing several related concepts to use the same extension option. "Re: SYN floods (was: does history repeat itself?)", September 9, 1996. http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html "Re: what a new TCP header might look like", May 12, 1998. ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail These functions will also be used in subsequent patches that implement additional features. Requires: TCPCT part 1a: add request_values parameter for sending SYNACK TCPCT part 1b: generate Responder Cookie secret TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-03 02:17:05 +08:00
* 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
TCPCT part 1d: define TCP cookie option, extend existing struct's Data structures are carefully composed to require minimal additions. For example, the struct tcp_options_received cookie_plus variable fits between existing 16-bit and 8-bit variables, requiring no additional space (taking alignment into consideration). There are no additions to tcp_request_sock, and only 1 pointer in tcp_sock. This is a significantly revised implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 The principle difference is using a TCP option to carry the cookie nonce, instead of a user configured offset in the data. This is more flexible and less subject to user configuration error. Such a cookie option has been suggested for many years, and is also useful without SYN data, allowing several related concepts to use the same extension option. "Re: SYN floods (was: does history repeat itself?)", September 9, 1996. http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html "Re: what a new TCP header might look like", May 12, 1998. ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail These functions will also be used in subsequent patches that implement additional features. Requires: TCPCT part 1a: add request_values parameter for sending SYNACK TCPCT part 1b: generate Responder Cookie secret TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-03 02:17:05 +08:00
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
TCPCT part 1d: define TCP cookie option, extend existing struct's Data structures are carefully composed to require minimal additions. For example, the struct tcp_options_received cookie_plus variable fits between existing 16-bit and 8-bit variables, requiring no additional space (taking alignment into consideration). There are no additions to tcp_request_sock, and only 1 pointer in tcp_sock. This is a significantly revised implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 The principle difference is using a TCP option to carry the cookie nonce, instead of a user configured offset in the data. This is more flexible and less subject to user configuration error. Such a cookie option has been suggested for many years, and is also useful without SYN data, allowing several related concepts to use the same extension option. "Re: SYN floods (was: does history repeat itself?)", September 9, 1996. http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html "Re: what a new TCP header might look like", May 12, 1998. ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail These functions will also be used in subsequent patches that implement additional features. Requires: TCPCT part 1a: add request_values parameter for sending SYNACK TCPCT part 1b: generate Responder Cookie secret TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-03 02:17:05 +08:00
u32 rcv_isn;
u32 snt_isn;
u32 snt_synack; /* synack sent time */
};
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) */
tcp: TCP Small Queues This introduce TSQ (TCP Small Queues) TSQ goal is to reduce number of TCP packets in xmit queues (qdisc & device queues), to reduce RTT and cwnd bias, part of the bufferbloat problem. sk->sk_wmem_alloc not allowed to grow above a given limit, allowing no more than ~128KB [1] per tcp socket in qdisc/dev layers at a given time. TSO packets are sized/capped to half the limit, so that we have two TSO packets in flight, allowing better bandwidth use. As a side effect, setting the limit to 40000 automatically reduces the standard gso max limit (65536) to 40000/2 : It can help to reduce latencies of high prio packets, having smaller TSO packets. This means we divert sock_wfree() to a tcp_wfree() handler, to queue/send following frames when skb_orphan() [2] is called for the already queued skbs. Results on my dev machines (tg3/ixgbe nics) are really impressive, using standard pfifo_fast, and with or without TSO/GSO. Without reduction of nominal bandwidth, we have reduction of buffering per bulk sender : < 1ms on Gbit (instead of 50ms with TSO) < 8ms on 100Mbit (instead of 132 ms) I no longer have 4 MBytes backlogged in qdisc by a single netperf session, and both side socket autotuning no longer use 4 Mbytes. As skb destructor cannot restart xmit itself ( as qdisc lock might be taken at this point ), we delegate the work to a tasklet. We use one tasklest per cpu for performance reasons. If tasklet finds a socket owned by the user, it sets TSQ_OWNED flag. This flag is tested in a new protocol method called from release_sock(), to eventually send new segments. [1] New /proc/sys/net/ipv4/tcp_limit_output_bytes tunable [2] skb_orphan() is usually called at TX completion time, but some drivers call it in their start_xmit() handler. These drivers should at least use BQL, or else a single TCP session can still fill the whole NIC TX ring, since TSQ will have no effect. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Dave Taht <dave.taht@bufferbloat.net> Cc: Tom Herbert <therbert@google.com> Cc: Matt Mathis <mattmathis@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Nandita Dukkipati <nanditad@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-07-11 13:50:31 +08:00
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 */
tcp: Reorganize tcp_sock to fill 64-bit holes & improve locality I tried to group recovery related fields nearby (non-CA_Open related variables, to be more accurate) so that one to three cachelines would not be necessary in CA_Open. These are now contiguously deployed: struct sk_buff_head out_of_order_queue; /* 1968 80 */ /* --- cacheline 32 boundary (2048 bytes) --- */ struct tcp_sack_block duplicate_sack[1]; /* 2048 8 */ struct tcp_sack_block selective_acks[4]; /* 2056 32 */ struct tcp_sack_block recv_sack_cache[4]; /* 2088 32 */ /* --- cacheline 33 boundary (2112 bytes) was 8 bytes ago --- */ struct sk_buff * highest_sack; /* 2120 8 */ int lost_cnt_hint; /* 2128 4 */ int retransmit_cnt_hint; /* 2132 4 */ u32 lost_retrans_low; /* 2136 4 */ u8 reordering; /* 2140 1 */ u8 keepalive_probes; /* 2141 1 */ /* XXX 2 bytes hole, try to pack */ u32 prior_ssthresh; /* 2144 4 */ u32 high_seq; /* 2148 4 */ u32 retrans_stamp; /* 2152 4 */ u32 undo_marker; /* 2156 4 */ int undo_retrans; /* 2160 4 */ u32 total_retrans; /* 2164 4 */ ...and they're then followed by URG slowpath & keepalive related variables. Head of the out_of_order_queue always needed for empty checks, if that's empty (and TCP is in CA_Open), following ~200 bytes (in 64-bit) shouldn't be necessary for anything. If only OFO queue exists but TCP is in CA_Open, selective_acks (and possibly duplicate_sack) are necessary besides the out_of_order_queue but the rest of the block again shouldn't be (ie., the other direction had losses). As the cacheline boundaries depend on many factors in the preceeding stuff, trying to align considering them doesn't make too much sense. Commented one ordering hazard. There are number of low utilized u8/16s that could be combined get 2 bytes less in total so that the hole could be made to vanish (includes at least ecn_flags, urg_data, urg_mode, frto_counter, nonagle). Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Acked-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-05-29 18:25:23 +08:00
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 */
/* 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 */
tcp: Reorganize tcp_sock to fill 64-bit holes & improve locality I tried to group recovery related fields nearby (non-CA_Open related variables, to be more accurate) so that one to three cachelines would not be necessary in CA_Open. These are now contiguously deployed: struct sk_buff_head out_of_order_queue; /* 1968 80 */ /* --- cacheline 32 boundary (2048 bytes) --- */ struct tcp_sack_block duplicate_sack[1]; /* 2048 8 */ struct tcp_sack_block selective_acks[4]; /* 2056 32 */ struct tcp_sack_block recv_sack_cache[4]; /* 2088 32 */ /* --- cacheline 33 boundary (2112 bytes) was 8 bytes ago --- */ struct sk_buff * highest_sack; /* 2120 8 */ int lost_cnt_hint; /* 2128 4 */ int retransmit_cnt_hint; /* 2132 4 */ u32 lost_retrans_low; /* 2136 4 */ u8 reordering; /* 2140 1 */ u8 keepalive_probes; /* 2141 1 */ /* XXX 2 bytes hole, try to pack */ u32 prior_ssthresh; /* 2144 4 */ u32 high_seq; /* 2148 4 */ u32 retrans_stamp; /* 2152 4 */ u32 undo_marker; /* 2156 4 */ int undo_retrans; /* 2160 4 */ u32 total_retrans; /* 2164 4 */ ...and they're then followed by URG slowpath & keepalive related variables. Head of the out_of_order_queue always needed for empty checks, if that's empty (and TCP is in CA_Open), following ~200 bytes (in 64-bit) shouldn't be necessary for anything. If only OFO queue exists but TCP is in CA_Open, selective_acks (and possibly duplicate_sack) are necessary besides the out_of_order_queue but the rest of the block again shouldn't be (ie., the other direction had losses). As the cacheline boundaries depend on many factors in the preceeding stuff, trying to align considering them doesn't make too much sense. Commented one ordering hazard. There are number of low utilized u8/16s that could be combined get 2 bytes less in total so that the hole could be made to vanish (includes at least ecn_flags, urg_data, urg_mode, frto_counter, nonagle). Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Acked-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-05-29 18:25:23 +08:00
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;
Proportional Rate Reduction for TCP. This patch implements Proportional Rate Reduction (PRR) for TCP. PRR is an algorithm that determines TCP's sending rate in fast recovery. PRR avoids excessive window reductions and aims for the actual congestion window size at the end of recovery to be as close as possible to the window determined by the congestion control algorithm. PRR also improves accuracy of the amount of data sent during loss recovery. The patch implements the recommended flavor of PRR called PRR-SSRB (Proportional rate reduction with slow start reduction bound) and replaces the existing rate halving algorithm. PRR improves upon the existing Linux fast recovery under a number of conditions including: 1) burst losses where the losses implicitly reduce the amount of outstanding data (pipe) below the ssthresh value selected by the congestion control algorithm and, 2) losses near the end of short flows where application runs out of data to send. As an example, with the existing rate halving implementation a single loss event can cause a connection carrying short Web transactions to go into the slow start mode after the recovery. This is because during recovery Linux pulls the congestion window down to packets_in_flight+1 on every ACK. A short Web response often runs out of new data to send and its pipe reduces to zero by the end of recovery when all its packets are drained from the network. Subsequent HTTP responses using the same connection will have to slow start to raise cwnd to ssthresh. PRR on the other hand aims for the cwnd to be as close as possible to ssthresh by the end of recovery. A description of PRR and a discussion of its performance can be found at the following links: - IETF Draft: http://tools.ietf.org/html/draft-mathis-tcpm-proportional-rate-reduction-01 - IETF Slides: http://www.ietf.org/proceedings/80/slides/tcpm-6.pdf http://tools.ietf.org/agenda/81/slides/tcpm-2.pdf - Paper to appear in Internet Measurements Conference (IMC) 2011: Improving TCP Loss Recovery Nandita Dukkipati, Matt Mathis, Yuchung Cheng Signed-off-by: Nandita Dukkipati <nanditad@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-08-22 04:21:57 +08:00
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 */
tcp: Reorganize tcp_sock to fill 64-bit holes & improve locality I tried to group recovery related fields nearby (non-CA_Open related variables, to be more accurate) so that one to three cachelines would not be necessary in CA_Open. These are now contiguously deployed: struct sk_buff_head out_of_order_queue; /* 1968 80 */ /* --- cacheline 32 boundary (2048 bytes) --- */ struct tcp_sack_block duplicate_sack[1]; /* 2048 8 */ struct tcp_sack_block selective_acks[4]; /* 2056 32 */ struct tcp_sack_block recv_sack_cache[4]; /* 2088 32 */ /* --- cacheline 33 boundary (2112 bytes) was 8 bytes ago --- */ struct sk_buff * highest_sack; /* 2120 8 */ int lost_cnt_hint; /* 2128 4 */ int retransmit_cnt_hint; /* 2132 4 */ u32 lost_retrans_low; /* 2136 4 */ u8 reordering; /* 2140 1 */ u8 keepalive_probes; /* 2141 1 */ /* XXX 2 bytes hole, try to pack */ u32 prior_ssthresh; /* 2144 4 */ u32 high_seq; /* 2148 4 */ u32 retrans_stamp; /* 2152 4 */ u32 undo_marker; /* 2156 4 */ int undo_retrans; /* 2160 4 */ u32 total_retrans; /* 2164 4 */ ...and they're then followed by URG slowpath & keepalive related variables. Head of the out_of_order_queue always needed for empty checks, if that's empty (and TCP is in CA_Open), following ~200 bytes (in 64-bit) shouldn't be necessary for anything. If only OFO queue exists but TCP is in CA_Open, selective_acks (and possibly duplicate_sack) are necessary besides the out_of_order_queue but the rest of the block again shouldn't be (ie., the other direction had losses). As the cacheline boundaries depend on many factors in the preceeding stuff, trying to align considering them doesn't make too much sense. Commented one ordering hazard. There are number of low utilized u8/16s that could be combined get 2 bytes less in total so that the hole could be made to vanish (includes at least ecn_flags, urg_data, urg_mode, frto_counter, nonagle). Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Acked-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-05-29 18:25:23 +08:00
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 */
tcp: Reorganize tcp_sock to fill 64-bit holes & improve locality I tried to group recovery related fields nearby (non-CA_Open related variables, to be more accurate) so that one to three cachelines would not be necessary in CA_Open. These are now contiguously deployed: struct sk_buff_head out_of_order_queue; /* 1968 80 */ /* --- cacheline 32 boundary (2048 bytes) --- */ struct tcp_sack_block duplicate_sack[1]; /* 2048 8 */ struct tcp_sack_block selective_acks[4]; /* 2056 32 */ struct tcp_sack_block recv_sack_cache[4]; /* 2088 32 */ /* --- cacheline 33 boundary (2112 bytes) was 8 bytes ago --- */ struct sk_buff * highest_sack; /* 2120 8 */ int lost_cnt_hint; /* 2128 4 */ int retransmit_cnt_hint; /* 2132 4 */ u32 lost_retrans_low; /* 2136 4 */ u8 reordering; /* 2140 1 */ u8 keepalive_probes; /* 2141 1 */ /* XXX 2 bytes hole, try to pack */ u32 prior_ssthresh; /* 2144 4 */ u32 high_seq; /* 2148 4 */ u32 retrans_stamp; /* 2152 4 */ u32 undo_marker; /* 2156 4 */ int undo_retrans; /* 2160 4 */ u32 total_retrans; /* 2164 4 */ ...and they're then followed by URG slowpath & keepalive related variables. Head of the out_of_order_queue always needed for empty checks, if that's empty (and TCP is in CA_Open), following ~200 bytes (in 64-bit) shouldn't be necessary for anything. If only OFO queue exists but TCP is in CA_Open, selective_acks (and possibly duplicate_sack) are necessary besides the out_of_order_queue but the rest of the block again shouldn't be (ie., the other direction had losses). As the cacheline boundaries depend on many factors in the preceeding stuff, trying to align considering them doesn't make too much sense. Commented one ordering hazard. There are number of low utilized u8/16s that could be combined get 2 bytes less in total so that the hole could be made to vanish (includes at least ecn_flags, urg_data, urg_mode, frto_counter, nonagle). Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Acked-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-05-29 18:25:23 +08:00
/* 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. */
tcp: Reorganize tcp_sock to fill 64-bit holes & improve locality I tried to group recovery related fields nearby (non-CA_Open related variables, to be more accurate) so that one to three cachelines would not be necessary in CA_Open. These are now contiguously deployed: struct sk_buff_head out_of_order_queue; /* 1968 80 */ /* --- cacheline 32 boundary (2048 bytes) --- */ struct tcp_sack_block duplicate_sack[1]; /* 2048 8 */ struct tcp_sack_block selective_acks[4]; /* 2056 32 */ struct tcp_sack_block recv_sack_cache[4]; /* 2088 32 */ /* --- cacheline 33 boundary (2112 bytes) was 8 bytes ago --- */ struct sk_buff * highest_sack; /* 2120 8 */ int lost_cnt_hint; /* 2128 4 */ int retransmit_cnt_hint; /* 2132 4 */ u32 lost_retrans_low; /* 2136 4 */ u8 reordering; /* 2140 1 */ u8 keepalive_probes; /* 2141 1 */ /* XXX 2 bytes hole, try to pack */ u32 prior_ssthresh; /* 2144 4 */ u32 high_seq; /* 2148 4 */ u32 retrans_stamp; /* 2152 4 */ u32 undo_marker; /* 2156 4 */ int undo_retrans; /* 2160 4 */ u32 total_retrans; /* 2164 4 */ ...and they're then followed by URG slowpath & keepalive related variables. Head of the out_of_order_queue always needed for empty checks, if that's empty (and TCP is in CA_Open), following ~200 bytes (in 64-bit) shouldn't be necessary for anything. If only OFO queue exists but TCP is in CA_Open, selective_acks (and possibly duplicate_sack) are necessary besides the out_of_order_queue but the rest of the block again shouldn't be (ie., the other direction had losses). As the cacheline boundaries depend on many factors in the preceeding stuff, trying to align considering them doesn't make too much sense. Commented one ordering hazard. There are number of low utilized u8/16s that could be combined get 2 bytes less in total so that the hole could be made to vanish (includes at least ecn_flags, urg_data, urg_mode, frto_counter, nonagle). Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Acked-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-05-29 18:25:23 +08:00
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
TCPCT part 1d: define TCP cookie option, extend existing struct's Data structures are carefully composed to require minimal additions. For example, the struct tcp_options_received cookie_plus variable fits between existing 16-bit and 8-bit variables, requiring no additional space (taking alignment into consideration). There are no additions to tcp_request_sock, and only 1 pointer in tcp_sock. This is a significantly revised implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 The principle difference is using a TCP option to carry the cookie nonce, instead of a user configured offset in the data. This is more flexible and less subject to user configuration error. Such a cookie option has been suggested for many years, and is also useful without SYN data, allowing several related concepts to use the same extension option. "Re: SYN floods (was: does history repeat itself?)", September 9, 1996. http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html "Re: what a new TCP header might look like", May 12, 1998. ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail These functions will also be used in subsequent patches that implement additional features. Requires: TCPCT part 1a: add request_values parameter for sending SYNACK TCPCT part 1b: generate Responder Cookie secret TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-03 02:17:05 +08:00
/* TCP fastopen related information */
struct tcp_fastopen_request *fastopen_req;
TCPCT part 1d: define TCP cookie option, extend existing struct's Data structures are carefully composed to require minimal additions. For example, the struct tcp_options_received cookie_plus variable fits between existing 16-bit and 8-bit variables, requiring no additional space (taking alignment into consideration). There are no additions to tcp_request_sock, and only 1 pointer in tcp_sock. This is a significantly revised implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 The principle difference is using a TCP option to carry the cookie nonce, instead of a user configured offset in the data. This is more flexible and less subject to user configuration error. Such a cookie option has been suggested for many years, and is also useful without SYN data, allowing several related concepts to use the same extension option. "Re: SYN floods (was: does history repeat itself?)", September 9, 1996. http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html "Re: what a new TCP header might look like", May 12, 1998. ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail These functions will also be used in subsequent patches that implement additional features. Requires: TCPCT part 1a: add request_values parameter for sending SYNACK TCPCT part 1b: generate Responder Cookie secret TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-03 02:17:05 +08:00
/* 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: TCP Small Queues This introduce TSQ (TCP Small Queues) TSQ goal is to reduce number of TCP packets in xmit queues (qdisc & device queues), to reduce RTT and cwnd bias, part of the bufferbloat problem. sk->sk_wmem_alloc not allowed to grow above a given limit, allowing no more than ~128KB [1] per tcp socket in qdisc/dev layers at a given time. TSO packets are sized/capped to half the limit, so that we have two TSO packets in flight, allowing better bandwidth use. As a side effect, setting the limit to 40000 automatically reduces the standard gso max limit (65536) to 40000/2 : It can help to reduce latencies of high prio packets, having smaller TSO packets. This means we divert sock_wfree() to a tcp_wfree() handler, to queue/send following frames when skb_orphan() [2] is called for the already queued skbs. Results on my dev machines (tg3/ixgbe nics) are really impressive, using standard pfifo_fast, and with or without TSO/GSO. Without reduction of nominal bandwidth, we have reduction of buffering per bulk sender : < 1ms on Gbit (instead of 50ms with TSO) < 8ms on 100Mbit (instead of 132 ms) I no longer have 4 MBytes backlogged in qdisc by a single netperf session, and both side socket autotuning no longer use 4 Mbytes. As skb destructor cannot restart xmit itself ( as qdisc lock might be taken at this point ), we delegate the work to a tasklet. We use one tasklest per cpu for performance reasons. If tasklet finds a socket owned by the user, it sets TSQ_OWNED flag. This flag is tested in a new protocol method called from release_sock(), to eventually send new segments. [1] New /proc/sys/net/ipv4/tcp_limit_output_bytes tunable [2] skb_orphan() is usually called at TX completion time, but some drivers call it in their start_xmit() handler. These drivers should at least use BQL, or else a single TCP session can still fill the whole NIC TX ring, since TSQ will have no effect. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Dave Taht <dave.taht@bufferbloat.net> Cc: Tom Herbert <therbert@google.com> Cc: Matt Mathis <mattmathis@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Nandita Dukkipati <nanditad@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-07-11 13:50:31 +08:00
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()
*/
tcp: TCP Small Queues This introduce TSQ (TCP Small Queues) TSQ goal is to reduce number of TCP packets in xmit queues (qdisc & device queues), to reduce RTT and cwnd bias, part of the bufferbloat problem. sk->sk_wmem_alloc not allowed to grow above a given limit, allowing no more than ~128KB [1] per tcp socket in qdisc/dev layers at a given time. TSO packets are sized/capped to half the limit, so that we have two TSO packets in flight, allowing better bandwidth use. As a side effect, setting the limit to 40000 automatically reduces the standard gso max limit (65536) to 40000/2 : It can help to reduce latencies of high prio packets, having smaller TSO packets. This means we divert sock_wfree() to a tcp_wfree() handler, to queue/send following frames when skb_orphan() [2] is called for the already queued skbs. Results on my dev machines (tg3/ixgbe nics) are really impressive, using standard pfifo_fast, and with or without TSO/GSO. Without reduction of nominal bandwidth, we have reduction of buffering per bulk sender : < 1ms on Gbit (instead of 50ms with TSO) < 8ms on 100Mbit (instead of 132 ms) I no longer have 4 MBytes backlogged in qdisc by a single netperf session, and both side socket autotuning no longer use 4 Mbytes. As skb destructor cannot restart xmit itself ( as qdisc lock might be taken at this point ), we delegate the work to a tasklet. We use one tasklest per cpu for performance reasons. If tasklet finds a socket owned by the user, it sets TSQ_OWNED flag. This flag is tested in a new protocol method called from release_sock(), to eventually send new segments. [1] New /proc/sys/net/ipv4/tcp_limit_output_bytes tunable [2] skb_orphan() is usually called at TX completion time, but some drivers call it in their start_xmit() handler. These drivers should at least use BQL, or else a single TCP session can still fill the whole NIC TX ring, since TSQ will have no effect. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Dave Taht <dave.taht@bufferbloat.net> Cc: Tom Herbert <therbert@google.com> Cc: Matt Mathis <mattmathis@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Nandita Dukkipati <nanditad@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-07-11 13:50:31 +08:00
};
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
struct tcp_md5sig_key *tw_md5_key;
#endif
TCPCT part 1d: define TCP cookie option, extend existing struct's Data structures are carefully composed to require minimal additions. For example, the struct tcp_options_received cookie_plus variable fits between existing 16-bit and 8-bit variables, requiring no additional space (taking alignment into consideration). There are no additions to tcp_request_sock, and only 1 pointer in tcp_sock. This is a significantly revised implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 The principle difference is using a TCP option to carry the cookie nonce, instead of a user configured offset in the data. This is more flexible and less subject to user configuration error. Such a cookie option has been suggested for many years, and is also useful without SYN data, allowing several related concepts to use the same extension option. "Re: SYN floods (was: does history repeat itself?)", September 9, 1996. http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html "Re: what a new TCP header might look like", May 12, 1998. ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail These functions will also be used in subsequent patches that implement additional features. Requires: TCPCT part 1a: add request_values parameter for sending SYNACK TCPCT part 1b: generate Responder Cookie secret TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-03 02:17:05 +08:00
/* 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;
}
#endif /* __KERNEL__ */
#endif /* _LINUX_TCP_H */