MFC 328608: Export tcp_always_keepalive for use by the Chelsio TOM module.

This used to work by accident with ld.bfd even though always_keepalive
was marked as static. LLD honors static more correctly, so export this
variable properly (including moving it into the tcp_* namespace).

Relative to HEAD the MFC includes two additional changes:
- The t3_tom module used for cxgb(4) is also patched.
- A strong reference from the new name (tcp_always_keepalive) to the old
name (always_keepalive) has been added to preserve the KBI for existing
modules.

Suggested by: kib (strong reference)
Sponsored by: Chelsio Communications

MFC r286227, r286443:

r286227:

Decompose TCP INP_INFO lock to increase short-lived TCP connections scalability:

- The existing TCP INP_INFO lock continues to protect the global inpcb list
stability during full list traversal (e.g. tcp_pcblist()).

- A new INP_LIST lock protects inpcb list actual modifications (inp allocation
and free) and inpcb global counters.

It allows to use TCP INP_INFO_RLOCK lock in critical paths (e.g. tcp_input())
and INP_INFO_WLOCK only in occasional operations that walk all connections.

PR: 183659
Differential Revision: https://reviews.freebsd.org/D2599
Reviewed by: jhb, adrian
Tested by: adrian, nitroboost-gmail.com
Sponsored by: Verisign, Inc.

r286443:

Fix a kernel assertion issue introduced with r286227:
Avoid too strict INP_INFO_RLOCK_ASSERT checks due to
tcp_notify() being called from in6_pcbnotify().

Reported by: Larry Rosenman <ler@lerctr.org>
Submitted by: markj, jch

MFC r286873:

Make clear that TIME_WAIT timeout expiration is managed solely by
tcp_tw_2msl_scan().

Sponsored by: Verisign, Inc.

MFC r294840

Persist timers TCPTV_PERSMIN and TCPTV_PERSMAX are hardcoded with 5 seconds and
60 seconds, respectively. Turn them into sysctls that can be tuned live. The
default values of 5 seconds and 60 seconds have been retained.

MFC r292706:

Implementation of server-side TCP Fast Open (TFO) [RFC7413].

TFO is disabled by default in the kernel build. See the top comment
in sys/netinet/tcp_fastopen.c for implementation particulars.

Differential Revision: https://reviews.freebsd.org/D4350
Sponsored by: Verisign, Inc.

MFC r289293

Fix an unnecessarily aggressive behavior where mtu clamping begins on first
retransmission timeout (rto) when blackhole detection is enabled. Make
sure it only happens when the second attempt to send the same segment also fails
with rto.

Also make sure that each mtu probing stage (usually 1448 -> 1188 -> 524) follows
the same pattern and gets 2 chances (rto) before further clamping down.

Note: RFC4821 doesn't specify implementation details on how this situation
should be handled.

MFC r284245:
Fix a callout race condition introduced in TCP timers callouts with r281599.
In TCP timer context, it is not enough to check callout_stop() return value
to decide if a callout is still running or not, previous callout_reset()
return values have also to be checked.

MFC: r280904, r280990, r281599

r280904:
Use appropriate timeout_t* instead of void* in tcp_timer_activate()

Suggested by: imp
Differential Revision: https://reviews.freebsd.org/D2154
Reviewed by: imp, jhb
Approved by: jhb

r280990:
Provide better debugging information in tcp_timer_activate() and
tcp_timer_active()

Differential Revision: https://reviews.freebsd.org/D2179
Suggested by: bz
Reviewed by: jhb
Approved by: jhb

r281599:
Fix an old and well-documented use-after-free race condition in
TCP timers:
- Add a reference from tcpcb to its inpcb
- Defer tcpcb deletion until TCP timers have finished

Differential Revision: https://reviews.freebsd.org/D2079
Submitted by: jch, Marc De La Gueronniere <mdelagueronniere@verisign.com>
Reviewed by: imp, rrs, adrian, jhb, bz
Approved by: jhb
Sponsored by: Verisign, Inc.

MFC r264321, r264342, r264351, r264356, r273850, r274629:

Currently, the TCP slow timer can starve TCP input processing while it
walks the list of connections in TIME_WAIT closing expired connections
due to contention on the global TCP pcbinfo lock.

To remediate, introduce a new global lock to protect the list of
connections in TIME_WAIT. Only acquire the TCP pcbinfo lock when
closing an expired connection. This limits the window of time when
TCP input processing is stopped to the amount of time needed to close
a single connection.

Approved by: jhb (mentor)

MFC r272720, 273061, 273062, 273063, 273064

Implement PLPMTUD blackhole detection (RFC 4821), inspired by code
from xnu sources. If we encounter a network where ICMP is blocked
the Needs Frag indicator may not propagate back to us. Attempt to
downshift the mss once to a preconfigured value.

Note, this is turned off by default.

MFC r284245:
Fix a callout race condition introduced in TCP timers callouts with r281599.
In TCP timer context, it is not enough to check callout_stop() return value
to decide if a callout is still running or not, previous callout_reset()
return values have also to be checked.

MFC: r280904, r280990, r281599

r280904:
Use appropriate timeout_t* instead of void* in tcp_timer_activate()

Suggested by: imp
Differential Revision: https://reviews.freebsd.org/D2154
Reviewed by: imp, jhb
Approved by: jhb

r280990:
Provide better debugging information in tcp_timer_activate() and
tcp_timer_active()

Differential Revision: https://reviews.freebsd.org/D2179
Suggested by: bz
Reviewed by: jhb
Approved by: jhb

r281599:
Fix an old and well-documented use-after-free race condition in
TCP timers:
- Add a reference from tcpcb to its inpcb
- Defer tcpcb deletion until TCP timers have finished

Differential Revision: https://reviews.freebsd.org/D2079
Submitted by: jch, Marc De La Gueronniere <mdelagueronniere@verisign.com>
Reviewed by: imp, rrs, adrian, jhb, bz
Approved by: jhb
Sponsored by: Verisign, Inc.

MFC r264321, r264342, r264351, r264356, r273850, r274629:

Currently, the TCP slow timer can starve TCP input processing while it
walks the list of connections in TIME_WAIT closing expired connections
due to contention on the global TCP pcbinfo lock.

To remediate, introduce a new global lock to protect the list of
connections in TIME_WAIT. Only acquire the TCP pcbinfo lock when
closing an expired connection. This limits the window of time when
TCP input processing is stopped to the amount of time needed to close
a single connection.

Approved by: jhb (mentor)

MFC r272720, 273061, 273062, 273063, 273064

Implement PLPMTUD blackhole detection (RFC 4821), inspired by code
from xnu sources. If we encounter a network where ICMP is blocked
the Needs Frag indicator may not propagate back to us. Attempt to
downshift the mss once to a preconfigured value.

Note, this is turned off by default.