linux-stable/include/linux/tcp.h
Paolo Abeni cfde141ea3 mptcp: move option parsing into mptcp_incoming_options()
The mptcp_options_received structure carries several per
packet flags (mp_capable, mp_join, etc.). Such fields must
be cleared on each packet, even on dropped ones or packet
not carrying any MPTCP options, but the current mptcp
code clears them only on TCP option reset.

On several races/corner cases we end-up with stray bits in
incoming options, leading to WARN_ON splats. e.g.:

[  171.164906] Bad mapping: ssn=32714 map_seq=1 map_data_len=32713
[  171.165006] WARNING: CPU: 1 PID: 5026 at net/mptcp/subflow.c:533 warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531)
[  171.167632] Modules linked in: ip6_vti ip_vti ip_gre ipip sit tunnel4 ip_tunnel geneve ip6_udp_tunnel udp_tunnel macsec macvtap tap ipvlan macvlan 8021q garp mrp xfrm_interface veth netdevsim nlmon dummy team bonding vcan bridge stp llc ip6_gre gre ip6_tunnel tunnel6 tun binfmt_misc intel_rapl_msr intel_rapl_common rfkill kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel joydev virtio_balloon pcspkr i2c_piix4 sunrpc ip_tables xfs libcrc32c crc32c_intel serio_raw virtio_console ata_generic virtio_blk virtio_net net_failover failover ata_piix libata
[  171.199464] CPU: 1 PID: 5026 Comm: repro Not tainted 5.7.0-rc1.mptcp_f227fdf5d388+ #95
[  171.200886] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014
[  171.202546] RIP: 0010:warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531)
[  171.206537] Code: c1 ea 03 0f b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 04 84 d2 75 1d 8b 55 3c 44 89 e6 48 c7 c7 20 51 13 95 e8 37 8b 22 fe <0f> 0b 48 83 c4 08 5b 5d 41 5c c3 89 4c 24 04 e8 db d6 94 fe 8b 4c
[  171.220473] RSP: 0018:ffffc90000150560 EFLAGS: 00010282
[  171.221639] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
[  171.223108] RDX: 0000000000000000 RSI: 0000000000000008 RDI: fffff5200002a09e
[  171.224388] RBP: ffff8880aa6e3c00 R08: 0000000000000001 R09: fffffbfff2ec9955
[  171.225706] R10: ffffffff9764caa7 R11: fffffbfff2ec9954 R12: 0000000000007fca
[  171.227211] R13: ffff8881066f4a7f R14: ffff8880aa6e3c00 R15: 0000000000000020
[  171.228460] FS:  00007f8623719740(0000) GS:ffff88810be00000(0000) knlGS:0000000000000000
[  171.230065] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  171.231303] CR2: 00007ffdab190a50 CR3: 00000001038ea006 CR4: 0000000000160ee0
[  171.232586] Call Trace:
[  171.233109]  <IRQ>
[  171.233531] get_mapping_status (linux-mptcp/net/mptcp/subflow.c:691)
[  171.234371] mptcp_subflow_data_available (linux-mptcp/net/mptcp/subflow.c:736 linux-mptcp/net/mptcp/subflow.c:832)
[  171.238181] subflow_state_change (linux-mptcp/net/mptcp/subflow.c:1085 (discriminator 1))
[  171.239066] tcp_fin (linux-mptcp/net/ipv4/tcp_input.c:4217)
[  171.240123] tcp_data_queue (linux-mptcp/./include/linux/compiler.h:199 linux-mptcp/net/ipv4/tcp_input.c:4822)
[  171.245083] tcp_rcv_established (linux-mptcp/./include/linux/skbuff.h:1785 linux-mptcp/./include/net/tcp.h:1774 linux-mptcp/./include/net/tcp.h:1847 linux-mptcp/net/ipv4/tcp_input.c:5238 linux-mptcp/net/ipv4/tcp_input.c:5730)
[  171.254089] tcp_v4_rcv (linux-mptcp/./include/linux/spinlock.h:393 linux-mptcp/net/ipv4/tcp_ipv4.c:2009)
[  171.258969] ip_protocol_deliver_rcu (linux-mptcp/net/ipv4/ip_input.c:204 (discriminator 1))
[  171.260214] ip_local_deliver_finish (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/ipv4/ip_input.c:232)
[  171.261389] ip_local_deliver (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:252)
[  171.265884] ip_rcv (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:539)
[  171.273666] process_backlog (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/core/dev.c:6135)
[  171.275328] net_rx_action (linux-mptcp/net/core/dev.c:6572 linux-mptcp/net/core/dev.c:6640)
[  171.280472] __do_softirq (linux-mptcp/./arch/x86/include/asm/jump_label.h:25 linux-mptcp/./include/linux/jump_label.h:200 linux-mptcp/./include/trace/events/irq.h:142 linux-mptcp/kernel/softirq.c:293)
[  171.281379] do_softirq_own_stack (linux-mptcp/arch/x86/entry/entry_64.S:1083)
[  171.282358]  </IRQ>

We could address the issue clearing explicitly the relevant fields
in several places - tcp_parse_option, tcp_fast_parse_options,
possibly others.

Instead we move the MPTCP option parsing into the already existing
mptcp ingress hook, so that we need to clear the fields in a single
place.

This allows us dropping an MPTCP hook from the TCP code and
removing the quite large mptcp_options_received from the tcp_sock
struct. On the flip side, the MPTCP sockets will traverse the
option space twice (in tcp_parse_option() and in
mptcp_incoming_options(). That looks acceptable: we already
do that for syn and 3rd ack packets, plain TCP socket will
benefit from it, and even MPTCP sockets will experience better
code locality, reducing the jumps between TCP and MPTCP code.

v1 -> v2:
 - rebased on current '-net' tree

Fixes: 648ef4b886 ("mptcp: Implement MPTCP receive path")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 12:23:22 -07:00

496 lines
16 KiB
C

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* 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>
*/
#ifndef _LINUX_TCP_H
#define _LINUX_TCP_H
#include <linux/skbuff.h>
#include <linux/win_minmax.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 tcphdr *th)
{
return th->doff * 4;
}
static inline unsigned int tcp_hdrlen(const struct sk_buff *skb)
{
return __tcp_hdrlen(tcp_hdr(skb));
}
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 {
__le64 val[DIV_ROUND_UP(TCP_FASTOPEN_COOKIE_MAX, sizeof(u64))];
s8 len;
bool exp; /* In RFC6994 experimental option format */
};
/* 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_DSACK_SEEN (1 << 2) /*1 = DSACK was received from peer*/
struct tcp_options_received {
/* PAWS/RTTM data */
int 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 : 3, /* SACK seen on SYN packet */
smc_ok : 1, /* SMC seen on SYN packet */
snd_wscale : 4, /* Window scaling received from sender */
rcv_wscale : 4; /* Window scaling to send to receiver */
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;
#if IS_ENABLED(CONFIG_SMC)
rx_opt->smc_ok = 0;
#endif
}
/* 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_request_sock_ops;
struct tcp_request_sock {
struct inet_request_sock req;
const struct tcp_request_sock_ops *af_specific;
u64 snt_synack; /* first SYNACK sent time */
bool tfo_listener;
bool is_mptcp;
u32 txhash;
u32 rcv_isn;
u32 snt_isn;
u32 ts_off;
u32 last_oow_ack_time; /* last SYNACK */
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 gso_segs; /* Max number of segs per GSO packet */
/*
* 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.
*/
u64 bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived
* sum(delta(rcv_nxt)), or how many bytes
* were acked.
*/
u32 segs_in; /* RFC4898 tcpEStatsPerfSegsIn
* total number of segments in.
*/
u32 data_segs_in; /* RFC4898 tcpEStatsPerfDataSegsIn
* total number of data segments in.
*/
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 segs_out; /* RFC4898 tcpEStatsPerfSegsOut
* The total number of segments sent.
*/
u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut
* total number of data segments sent.
*/
u64 bytes_sent; /* RFC4898 tcpEStatsPerfHCDataOctetsOut
* total number of data bytes sent.
*/
u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked
* sum(delta(snd_una)), or how many bytes
* were acked.
*/
u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups
* total number of DSACK blocks received
*/
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 last_oow_ack_time; /* timestamp of last out-of-window ACK */
u32 compressed_ack_rcv_nxt;
u32 tsoffset; /* timestamp offset */
struct list_head tsq_node; /* anchor in tsq_tasklet.head list */
struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */
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 */
/* Information of the most recently (s)acked skb */
struct tcp_rack {
u64 mstamp; /* (Re)sent time of the skb */
u32 rtt_us; /* Associated RTT */
u32 end_seq; /* Ending TCP sequence of the skb */
u32 last_delivered; /* tp->delivered at last reo_wnd adj */
u8 reo_wnd_steps; /* Allowed reordering window */
#define TCP_RACK_RECOVERY_THRESH 16
u8 reo_wnd_persist:5, /* No. of recovery since last adj */
dsack_seen:1, /* Whether DSACK seen after last adj */
advanced:1; /* mstamp advanced since last lost marking */
} rack;
u16 advmss; /* Advertised MSS */
u8 compressed_ack;
u32 chrono_start; /* Start time in jiffies of a TCP chrono */
u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */
u8 chrono_type:2, /* current chronograph type */
rate_app_limited:1, /* rate_{delivered,interval_us} limited? */
fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */
fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */
is_sack_reneg:1, /* in recovery from loss with SACK reneg? */
fastopen_client_fail:2; /* reason why fastopen failed */
u8 nonagle : 4,/* Disable Nagle algorithm? */
thin_lto : 1,/* Use linear timeouts for thin streams */
recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */
repair : 1,
frto : 1;/* F-RTO (RFC5682) activated in CA_Loss */
u8 repair_queue;
u8 syn_data:1, /* SYN includes data */
syn_fastopen:1, /* SYN includes Fast Open option */
syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */
syn_fastopen_ch:1, /* Active TFO re-enabling probe */
syn_data_acked:1,/* data in SYN is acked by SYN-ACK */
save_syn:1, /* Save headers of SYN packet */
is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */
syn_smc:1; /* SYN includes SMC */
u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */
u32 tcp_tx_delay; /* delay (in usec) added to TX packets */
u64 tcp_wstamp_ns; /* departure time for next sent data packet */
u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */
/* RTT measurement */
u64 tcp_mstamp; /* most recent packet received/sent */
u32 srtt_us; /* smoothed round trip time << 3 in usecs */
u32 mdev_us; /* medium deviation */
u32 mdev_max_us; /* maximal mdev for the last rtt period */
u32 rttvar_us; /* smoothed mdev_max */
u32 rtt_seq; /* sequence number to update rttvar */
struct minmax rtt_min;
u32 packets_out; /* Packets which are "in flight" */
u32 retrans_out; /* Retransmitted packets out */
u32 max_packets_out; /* max packets_out in last window */
u32 max_packets_seq; /* right edge of max_packets_out flight */
u16 urg_data; /* Saved octet of OOB data and control flags */
u8 ecn_flags; /* ECN status bits. */
u8 keepalive_probes; /* num of allowed keep alive probes */
u32 reordering; /* Packet reordering metric. */
u32 reord_seen; /* number of data packet reordering events */
u32 snd_up; /* Urgent pointer */
/*
* 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; /* cwnd right before starting loss recovery */
u32 prr_delivered; /* Number of newly delivered packets to
* receiver in Recovery. */
u32 prr_out; /* Total number of pkts sent during Recovery. */
u32 delivered; /* Total data packets delivered incl. rexmits */
u32 delivered_ce; /* Like the above but only ECE marked packets */
u32 lost; /* Total data packets lost incl. rexmits */
u32 app_limited; /* limited until "delivered" reaches this val */
u64 first_tx_mstamp; /* start of window send phase */
u64 delivered_mstamp; /* time we reached "delivered" */
u32 rate_delivered; /* saved rate sample: packets delivered */
u32 rate_interval_us; /* saved rate sample: time elapsed */
u32 rcv_wnd; /* Current receiver window */
u32 write_seq; /* Tail(+1) of data held in tcp send buffer */
u32 notsent_lowat; /* TCP_NOTSENT_LOWAT */
u32 pushed_seq; /* Last pushed seq, required to talk to windows */
u32 lost_out; /* Lost packets */
u32 sacked_out; /* SACK'd packets */
struct hrtimer pacing_timer;
struct hrtimer compressed_ack_timer;
/* from STCP, retrans queue hinting */
struct sk_buff* lost_skb_hint;
struct sk_buff *retransmit_skb_hint;
/* OOO segments go in this rbtree. Socket lock must be held. */
struct rb_root out_of_order_queue;
struct sk_buff *ooo_last_skb; /* cache rb_last(out_of_order_queue) */
/* 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 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; /* snd_una upon a new recovery episode. */
int undo_retrans; /* number of undoable retransmissions. */
u64 bytes_retrans; /* RFC4898 tcpEStatsPerfOctetsRetrans
* Total data bytes retransmitted
*/
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;
/* Sock_ops bpf program related variables */
#ifdef CONFIG_BPF
u8 bpf_sock_ops_cb_flags; /* Control calling BPF programs
* values defined in uapi/linux/tcp.h
*/
#define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) (TP->bpf_sock_ops_cb_flags & ARG)
#else
#define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) 0
#endif
u16 timeout_rehash; /* Timeout-triggered rehash attempts */
u32 rcv_ooopack; /* Received out-of-order packets, for tcpinfo */
/* Receiver side RTT estimation */
u32 rcv_rtt_last_tsecr;
struct {
u32 rtt_us;
u32 seq;
u64 time;
} rcv_rtt_est;
/* Receiver queue space */
struct {
u32 space;
u32 seq;
u64 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.
*/
#if IS_ENABLED(CONFIG_MPTCP)
bool is_mptcp;
#endif
#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
/* 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 __rcu *fastopen_rsk;
u32 *saved_syn;
};
enum tsq_enum {
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()
*/
};
enum tsq_flags {
TSQF_THROTTLED = (1UL << TSQ_THROTTLED),
TSQF_QUEUED = (1UL << TSQ_QUEUED),
TCPF_TSQ_DEFERRED = (1UL << TCP_TSQ_DEFERRED),
TCPF_WRITE_TIMER_DEFERRED = (1UL << TCP_WRITE_TIMER_DEFERRED),
TCPF_DELACK_TIMER_DEFERRED = (1UL << TCP_DELACK_TIMER_DEFERRED),
TCPF_MTU_REDUCED_DEFERRED = (1UL << TCP_MTU_REDUCED_DEFERRED),
};
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;
#define tw_rcv_nxt tw_sk.__tw_common.skc_tw_rcv_nxt
#define tw_snd_nxt tw_sk.__tw_common.skc_tw_snd_nxt
u32 tw_rcv_wnd;
u32 tw_ts_offset;
u32 tw_ts_recent;
/* The time we sent the last out-of-window ACK: */
u32 tw_last_oow_ack_time;
int tw_ts_recent_stamp;
u32 tw_tx_delay;
#ifdef CONFIG_TCP_MD5SIG
struct tcp_md5sig_key *tw_md5_key;
#endif
};
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 &&
rcu_access_pointer(tcp_sk(sk)->fastopen_rsk) != NULL;
}
static inline void fastopen_queue_tune(struct sock *sk, int backlog)
{
struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
int somaxconn = READ_ONCE(sock_net(sk)->core.sysctl_somaxconn);
queue->fastopenq.max_qlen = min_t(unsigned int, backlog, somaxconn);
}
static inline void tcp_move_syn(struct tcp_sock *tp,
struct request_sock *req)
{
tp->saved_syn = req->saved_syn;
req->saved_syn = NULL;
}
static inline void tcp_saved_syn_free(struct tcp_sock *tp)
{
kfree(tp->saved_syn);
tp->saved_syn = NULL;
}
struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk);
static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss)
{
/* We use READ_ONCE() here because socket might not be locked.
* This happens for listeners.
*/
u16 user_mss = READ_ONCE(tp->rx_opt.user_mss);
return (user_mss && user_mss < mss) ? user_mss : mss;
}
int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount,
int shiftlen);
#endif /* _LINUX_TCP_H */