directly to a merged model where only one callout, the next to fire,
is registered.
Instead of callout_reset(9) and callout_stop(9) the new function
tcp_timer_activate() is used which then internally manages the callout.
The single new callout is a mutex callout on inpcb simplifying the
locking a bit.
tcp_timer() is the called function which handles all race conditions
in one place and then dispatches the individual timer functions.
Reviewed by: rwatson (earlier version)
potential issues where the peer does not close, potentially leaving
thousands of connections in FIN_WAIT_2. This is controlled by a new sysctl
fast_finwait2_recycle, which is disabled by default.
Reviewed by: gnn, silby.
timeouts for TCP and T/TCP connections in the TIME_WAIT
state, and we had two separate timed wait queues for them.
Now that is has gone, the timeout is always 2*MSL again,
and there is no reason to keep two queues (the first was
unused anyway!).
Also, reimplement the remaining queue using a TAILQ (it
was technically impossible before, with two queues).
bad under high load. For example with 40k sockets and 25k tcptw
entries, connect() syscall can run for seconds. Debugging showed
that it iterates the cycle millions times and purges thousands of
tcptw entries at a time.
Besides practical unusability this change is architecturally
wrong. First, in_pcblookup_local() is used in connect() and bind()
syscalls. No stale entries purging shouldn't be done here. Second,
it is a layering violation.
o Return back the tcptw purging cycle to tcp_timer_2msl_tw(),
that was removed in rev. 1.78 by rwatson. The commit log of this
revision tells nothing about the reason cycle was removed. Now
we need this cycle, since major cleaner of stale tcptw structures
is removed.
o Disable probably necessary, but now unused
tcp_twrecycleable() function.
Reviewed by: ru
dropped. This prevents a bug introduced during the socket/pcb refcounting
work from occuring, in which occasionally the retransmit timer may fire
after a connection has been reset, resulting in the resulting R|A TCP
packet having a source port of 0, as the port reservation has been
released.
While here, fixing up some RUNLOCK->WUNLOCK bugs.
MFC after: 1 month
return NULL. In principle this shouldn't change the behavior, but
avoids returning a potentially invalid/inappropriate pointer to
the caller.
Found with: Coverity Prevent (tm)
Submitted by: pjd
MFC after: 3 months
pru_abort(), pru_detach(), and in_pcbdetach():
- Universally support and enforce the invariant that so_pcb is
never NULL, converting dozens of unnecessary NULL checks into
assertions, and eliminating dozens of unnecessary error handling
cases in protocol code.
- In some cases, eliminate unnecessary pcbinfo locking, as it is no
longer required to ensure so_pcb != NULL. For example, the receive
code no longer requires the pcbinfo lock, and the send code only
requires it if building a new connection on an otherwise unconnected
socket triggered via sendto() with an address. This should
significnatly reduce tcbinfo lock contention in the receive and send
cases.
- In order to support the invariant that so_pcb != NULL, it is now
necessary for the TCP code to not discard the tcpcb any time a
connection is dropped, but instead leave the tcpcb until the socket
is shutdown. This case is handled by setting INP_DROPPED, to
substitute for using a NULL so_pcb to indicate that the connection
has been dropped. This requires the inpcb lock, but not the pcbinfo
lock.
- Unlike all other protocols in the tree, TCP may need to retain access
to the socket after the file descriptor has been closed. Set
SS_PROTOREF in tcp_detach() in order to prevent the socket from being
freed, and add a flag, INP_SOCKREF, so that the TCP code knows whether
or not it needs to free the socket when the connection finally does
close. The typical case where this occurs is if close() is called on
a TCP socket before all sent data in the send socket buffer has been
transmitted or acknowledged. If INP_SOCKREF is found when the
connection is dropped, we release the inpcb, tcpcb, and socket instead
of flagging INP_DROPPED.
- Abort and detach protocol switch methods no longer return failures,
nor attempt to free sockets, as the socket layer does this.
- Annotate the existence of a long-standing race in the TCP timer code,
in which timers are stopped but not drained when the socket is freed,
as waiting for drain may lead to deadlocks, or have to occur in a
context where waiting is not permitted. This race has been handled
by testing to see if the tcpcb pointer in the inpcb is NULL (and vice
versa), which is not normally permitted, but may be true of a inpcb
and tcpcb have been freed. Add a counter to test how often this race
has actually occurred, and a large comment for each instance where
we compare potentially freed memory with NULL. This will have to be
fixed in the near future, but requires is to further address how to
handle the timer shutdown shutdown issue.
- Several TCP calls no longer potentially free the passed inpcb/tcpcb,
so no longer need to return a pointer to indicate whether the argument
passed in is still valid.
- Un-macroize debugging and locking setup for various protocol switch
methods for TCP, as it lead to more obscurity, and as locking becomes
more customized to the methods, offers less benefit.
- Assert copyright on tcp_usrreq.c due to significant modifications that
have been made as part of this work.
These changes significantly modify the memory management and connection
logic of our TCP implementation, and are (as such) High Risk Changes,
and likely to contain serious bugs. Please report problems to the
current@ mailing list ASAP, ideally with simple test cases, and
optionally, packet traces.
MFC after: 3 months
multiple MIB entries using sysctl in short order, which might
result in unexpected values for tcp_maxidle being generated by
tcp_slowtimo. In practice, this will not happen, or at least,
doesn't require an explicit comment.
MFC after: 2 weeks
structure, so assert the inpcb lock associated with the tcptw.
Also assert the tcbinfo lock, as tcp_timewait() may call
tcp_twclose() or tcp_2msl_rest(), which require it. Since
tcp_timewait() is already called with that lock from tcp_input(),
this doesn't change current locking, merely documents reasons for
it.
In tcp_twstart(), assert the tcbinfo lock, as tcp_timer_2msl_rest()
is called, which requires that lock.
In tcp_twclose(), assert the tcbinfo lock, as tcp_timer_2msl_stop()
is called, which requires that lock.
Document the locking strategy for the time wait queues in tcp_timer.c,
which consists of protecting the time wait queues in the same manner
as the tcbinfo structure (using the tcbinfo lock).
In tcp_timer_2msl_reset(), assert the tcbinfo lock, as the time wait
queues are modified.
In tcp_timer_2msl_stop(), assert the tcbinfo lock, as the time wait
queues may be modified.
In tcp_timer_2msl_tw(), assert the tcbinfo lock, as the time wait
queues may be modified.
MFC after: 2 weeks
but unlikely races that could be corrected by having tcp_keepcnt
and tcp_keepintvl modifications go through handler functions via
sysctl, but probably is not worth doing. Updates to multiple
sysctls within evaluation of a single addition are unlikely.
Annotate that tcp_canceltimers() is currently unused.
De-spl tcp_timer_delack().
De-spl tcp_timer_2msl().
MFC after: 2 weeks
A complete rationale and discussion is given in this message
and the resulting discussion:
http://docs.freebsd.org/cgi/mid.cgi?4177C8AD.6060706
Note that this commit removes only the functional part of T/TCP
from the tcp_* related functions in the kernel. Other features
introduced with RFC1644 are left intact (socket layer changes,
sendmsg(2) on connection oriented protocols) and are meant to
be reused by a simpler and less intrusive reimplemention of the
previous T/TCP functionality.
Discussed on: -arch
- Trailing tab/space cleanup
- Remove spurious spaces between or before tabs
This change avoids touching files that Andre likely has in his working
set for PFIL hooks changes for IPFW/DUMMYNET.
Approved by: re (scottl)
Submitted by: Xin LI <delphij@frontfree.net>
originated on RELENG_4 and was ported to -CURRENT.
The scoreboarding code was obtained from OpenBSD, and many
of the remaining changes were inspired by OpenBSD, but not
taken directly from there.
You can enable/disable sack using net.inet.tcp.do_sack. You can
also limit the number of sack holes that all senders can have in
the scoreboard with net.inet.tcp.sackhole_limit.
Reviewed by: gnn
Obtained from: Yahoo! (Mohan Srinivasan, Jayanth Vijayaraghavan)
the routing table. Move all usage and references in the tcp stack
from the routing table metrics to the tcp hostcache.
It caches measured parameters of past tcp sessions to provide better
initial start values for following connections from or to the same
source or destination. Depending on the network parameters to/from
the remote host this can lead to significant speedups for new tcp
connections after the first one because they inherit and shortcut
the learning curve.
tcp_hostcache is designed for multiple concurrent access in SMP
environments with high contention and is hash indexed by remote
ip address.
It removes significant locking requirements from the tcp stack with
regard to the routing table.
Reviewed by: sam (mentor), bms
Reviewed by: -net, -current, core@kame.net (IPv6 parts)
Approved by: re (scottl)
lastest rev of the spec. Use an explicit flag for Fast Recovery. [1]
Fix bug with exiting Fast Recovery on a retransmit timeout
diagnosed by Lu Guohan. [2]
Reviewed by: Thomas Henderson <thomas.r.henderson@boeing.com>
Reported and tested by: Lu Guohan <lguohan00@mails.tsinghua.edu.cn> [2]
Approved by: Thomas Henderson <thomas.r.henderson@boeing.com>,
Sally Floyd <floyd@acm.org> [1]
control block. Allow the socket and tcpcb structures to be freed
earlier than inpcb. Update code to understand an inp w/o a socket.
Reviewed by: hsu, silby, jayanth
Sponsored by: DARPA, NAI Labs
routine does not require a tcpcb to operate. Since we no longer keep
template mbufs around, move pseudo checksum out of this routine, and
merge it with the length update.
Sponsored by: DARPA, NAI Labs
net.inet.tcp.rexmit_min (default 3 ticks equiv)
This sysctl is the retransmit timer RTO minimum,
specified in milliseconds. This value is
designed for algorithmic stability only.
net.inet.tcp.rexmit_slop (default 200ms)
This sysctl is the retransmit timer RTO slop
which is added to every retransmit timeout and
is designed to handle protocol stack overheads
and delayed ack issues.
Note that the *original* code applied a 1-second
RTO minimum but never applied real slop to the RTO
calculation, so any RTO calculation over one second
would have no slop and thus not account for
protocol stack overheads (TCP timestamps are not
a measure of protocol turnaround!). Essentially,
the original code made the RTO calculation almost
completely irrelevant.
Please note that the 200ms slop is debateable.
This commit is not meant to be a line in the sand,
and if the community winds up deciding that increasing
it is the correct solution then it's easy to do.
Note that larger values will destroy performance
on lossy networks while smaller values may result in
a greater number of unnecessary retransmits.
o Add a mutex (sb_mtx) to struct sockbuf. This protects the data in a
socket buffer. The mutex in the receive buffer also protects the data
in struct socket.
o Determine the lock strategy for each members in struct socket.
o Lock down the following members:
- so_count
- so_options
- so_linger
- so_state
o Remove *_locked() socket APIs. Make the following socket APIs
touching the members above now require a locked socket:
- sodisconnect()
- soisconnected()
- soisconnecting()
- soisdisconnected()
- soisdisconnecting()
- sofree()
- soref()
- sorele()
- sorwakeup()
- sotryfree()
- sowakeup()
- sowwakeup()
Reviewed by: alfred
In order to ensure security and functionality, RFC 1948 style
initial sequence number generation has been implemented. Barring
any major crypographic breakthroughs, this algorithm should be
unbreakable. In addition, the problems with TIME_WAIT recycling
which affect our currently used algorithm are not present.
Reviewed by: jesper
generation scheme. Users may now select between the currently used
OpenBSD algorithm and the older random positive increment method.
While the OpenBSD algorithm is more secure, it also breaks TIME_WAIT
handling; this is causing trouble for an increasing number of folks.
To switch between generation schemes, one sets the sysctl
net.inet.tcp.tcp_seq_genscheme. 0 = random positive increments,
1 = the OpenBSD algorithm. 1 is still the default.
Once a secure _and_ compatible algorithm is implemented, this sysctl
will be removed.
Reviewed by: jlemon
Tested by: numerous subscribers of -net
connection. The information contained in a tcptemp can be
reconstructed from a tcpcb when needed.
Previously, tcp templates required the allocation of one
mbuf per connection. On large systems, this change should
free up a large number of mbufs.
Reviewed by: bmilekic, jlemon, ru
MFC after: 2 weeks
any response to our third SYN to work-around some broken
terminal servers (most of which have hopefully been retired)
that have bad VJ header compression code which trashes TCP
segments containing unknown-to-them TCP options.
PR: kern/1689
Submitted by: jesper
Reviewed by: wollman
MFC after: 2 weeks
but have a network interrupt arrive and deactivate the timeout before
the callout routine runs. Check for this case in the callout routine;
it should only run if the callout is active and not on the wheel.
better recovery for multiple packet losses in a single window.
The algorithm can be toggled via the sysctl net.inet.tcp.newreno,
which defaults to "on".
Submitted by: Jayanth Vijayaraghavan <jayanth@yahoo-inc.com>
- eliminate the fast/slow timeout lists for TCP and instead use a
callout entry for each timer.
- increase the TCP timer granularity to HZ
- implement "bad retransmit" recovery, as presented in
"On Estimating End-to-End Network Path Properties", by Allman and Paxson.
Submitted by: jlemon, wollmann
is believed to have been broken with the Brakmo/Peterson srtt
calculation changes. The result of this bug is that TCP connections
could time out extremely quickly (in 12 seconds).
Also backed out jdp's partial fix for this problem in rev 1.17 of
tcp_timer.c as it is obsoleted by this commit.
Bug was pointed out by Kevin Lehey <kml@roller.nas.nasa.gov>.
PR: 6068
This will make a number of things easier in the future, as well as (finally!)
avoiding the Id-smashing problem which has plagued developers for so long.
Boy, I'm glad we're not using sup anymore. This update would have been
insane otherwise.
time, in seconds, that state for non-established TCP sessions stays about)
a sysctl modifyable variable.
[part 1 of two commits, I just realized I can't play with the indices as
I was typing this commit message.]
pr_usrreq mechanism which was poorly designed and error-prone. This
commit renames pr_usrreq to pr_ousrreq so that old code which depended on it
would break in an obvious manner. This commit also implements the new
interface for TCP, although the old function is left as an example
(#ifdef'ed out). This commit ALSO fixes a longstanding bug in the
TCP timer processing (introduced by davidg on 1995/04/12) which caused
timer processing on a TCB to always stop after a single timer had
expired (because it misinterpreted the return value from tcp_usrreq()
to indicate that the TCB had been deleted). Finally, some code
related to polling has been deleted from if.c because it is not
relevant t -current and doesn't look at all like my current code.
circumstances, caused perfectly good connections to be dropped. This
happened for connections over a LAN, where the retransmit timer
calculation TCP_REXMTVAL(tp) returned 0. If sending was blocked by flow
control for long enough, the old code dropped the connection, even
though timely replies were being received for all window probes.
Reviewed by: W. Richard Stevens <rstevens@noao.edu>
1) Set the persist timer to help time-out connections in the CLOSING state.
2) Honor the keep-alive timer in the CLOSING state.
This fixes problems with connections getting "stuck" due to incompletion
of the final connection shutdown which can be a BIG problem on busy WWW
servers.
keepalive on all tcp sessions. Setsockopt(2) cannot override this setting.
Maybe another one is needed that just changes the default for SO_KEEPALIVE ?
Requested by: Joe Greco <jgreco@brasil.moneng.mei.com>
Bob Braden <braden@isi.edu>.
NB: This has not had David's TCP ACK hack re-integrated. It is not clear
what the correct solution to this problem is, if any. If a better solution
doesn't pop up in response to this message, I'll put David's code back in
(or he's welcome to do so himself).
