mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-03 01:16:40 +07:00
ae8064ac32
This patch limits the amount of time you will defer sending a TSO segment to less than two clock ticks, or the time between two acks, whichever is longer. On slow links, deferring causes significant bursts. See attached plots, which show RTT through a 1 Mbps link with a 100 ms RTT and ~100 ms queue for (a) non-TSO, (b) currnet TSO, and (c) patched TSO. This burstiness causes significant jitter, tends to overflow queues early (bad for short queues), and makes delay-based congestion control more difficult. Deferring by a couple clock ticks I believe will have a relatively small impact on performance. Signed-off-by: John Heffner <jheffner@psc.edu> Signed-off-by: David S. Miller <davem@davemloft.net>
390 lines
11 KiB
C
390 lines
11 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>
|
|
|
|
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;
|
|
__be16 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 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;
|
|
};
|
|
|
|
#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>
|
|
|
|
/* 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;
|
|
__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;
|
|
int tcp_header_len; /* Bytes of tcp header to send */
|
|
|
|
/*
|
|
* 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 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 */
|
|
__u16 xmit_size_goal; /* Goal for segmenting output packets */
|
|
/* XXX Two bytes hole, try to pack */
|
|
|
|
__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 left_out; /* Packets which leaved network */
|
|
__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 */
|
|
__u16 snd_cwnd_cnt; /* Linear increase counter */
|
|
__u16 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 rcv_wup; /* rcv_nxt on last window update sent */
|
|
__u32 write_seq; /* Tail(+1) of data held in tcp send buffer */
|
|
__u32 pushed_seq; /* Last pushed seq, required to talk to windows */
|
|
__u32 copied_seq; /* Head of yet unread data */
|
|
|
|
/* 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];
|
|
|
|
/* 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 *fastpath_skb_hint;
|
|
|
|
int fastpath_cnt_hint;
|
|
int lost_cnt_hint;
|
|
int retransmit_cnt_hint;
|
|
int forward_cnt_hint;
|
|
|
|
__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;
|
|
};
|
|
|
|
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;
|
|
};
|
|
|
|
static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk)
|
|
{
|
|
return (struct tcp_timewait_sock *)sk;
|
|
}
|
|
|
|
#endif
|
|
|
|
#endif /* _LINUX_TCP_H */
|