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
to control the packets injected while in sack recovery (for both
retransmissions and new data).
- Cleanups to the sack codepaths in tcp_output.c and tcp_sack.c.
- Add a new sysctl (net.inet.tcp.sack.initburst) that controls the
number of sack retransmissions done upon initiation of sack recovery.
Submitted by: Mohan Srinivasan <mohans@yahoo-inc.com>
- 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>
for the SYN|ACK packet and then letting in6_pcbconnect set the
flowlabel later. Arange for the syncache/syncookie code to set and
recall the flow label so that the flowlabel used for the SYN|ACK
is consistent. This is done by using some of the cookie (when tcp
cookies are enabeled) and by stashing the flowlabel in syncache.
Tested and Discovered by: Orla McGann <orly@cnri.dit.ie>
Approved by: ume, silby
MFC after: 1 month
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)
possible while maintaining compatibility with the widest range of TCP stacks.
The algorithm is as follows:
---
For connections in the ESTABLISHED state, only resets with
sequence numbers exactly matching last_ack_sent will cause a reset,
all other segments will be silently dropped.
For connections in all other states, a reset anywhere in the window
will cause the connection to be reset. All other segments will be
silently dropped.
---
The necessity of accepting all in-window resets was discovered
by jayanth and jlemon, both of whom have seen TCP stacks that
will respond to FIN-ACK packets with resets not meeting the
strict last_ack_sent check.
Idea by: Darren Reed
Reviewed by: truckman, jlemon, others(?)
TIME_WAIT recycling cases I was able to generate with http testing tools.
In short, as the old algorithm relied on ticks to create the time offset
component of an ISN, two connections with the exact same host, port pair
that were generated between timer ticks would have the exact same sequence
number. As a result, the second connection would fail to pass the TIME_WAIT
check on the server side, and the SYN would never be acknowledged.
I've "fixed" this by adding random positive increments to the time component
between clock ticks so that ISNs will *always* be increasing, no matter how
quickly the port is recycled.
Except in such contrived benchmarking situations, this problem should never
come up in normal usage... until networks get faster.
No MFC planned, 4.x is missing other optimizations that are needed to even
create the situation in which such quick port recycling will occur.
increased <netinet/tcp_var>'s already large set of prerequisites, and
this was handled badly. Just don't declare the complete syncache struct
unless <netinet/pcb.h> is included before <netinet/tcp_var.h>.
Approved by: jlemon (years ago, for a more invasive fix)
amount of segments it will hold.
The following tuneables and sysctls control the behaviour of the tcp
segment reassembly queue:
net.inet.tcp.reass.maxsegments (loader tuneable)
specifies the maximum number of segments all tcp reassemly queues can
hold (defaults to 1/16 of nmbclusters).
net.inet.tcp.reass.maxqlen
specifies the maximum number of segments any individual tcp session queue
can hold (defaults to 48).
net.inet.tcp.reass.cursegments (readonly)
counts the number of segments currently in all reassembly queues.
net.inet.tcp.reass.overflows (readonly)
counts how often either the global or local queue limit has been reached.
Tested by: bms, silby
Reviewed by: bms, silby
This is the first of two commits; bringing in the kernel support first.
This can be enabled by compiling a kernel with options TCP_SIGNATURE
and FAST_IPSEC.
For the uninitiated, this is a TCP option which provides for a means of
authenticating TCP sessions which came into being before IPSEC. It is
still relevant today, however, as it is used by many commercial router
vendors, particularly with BGP, and as such has become a requirement for
interconnect at many major Internet points of presence.
Several parts of the TCP and IP headers, including the segment payload,
are digested with MD5, including a shared secret. The PF_KEY interface
is used to manage the secrets using security associations in the SADB.
There is a limitation here in that as there is no way to map a TCP flow
per-port back to an SPI without polluting tcpcb or using the SPD; the
code to do the latter is unstable at this time. Therefore this code only
supports per-host keying granularity.
Whilst FAST_IPSEC is mutually exclusive with KAME IPSEC (and thus IPv6),
TCP_SIGNATURE applies only to IPv4. For the vast majority of prospective
users of this feature, this will not pose any problem.
This implementation is output-only; that is, the option is honoured when
responding to a host initiating a TCP session, but no effort is made
[yet] to authenticate inbound traffic. This is, however, sufficient to
interwork with Cisco equipment.
Tested with a Cisco 2501 running IOS 12.0(27), and Quagga 0.96.4 with
local patches. Patches for tcpdump to validate TCP-MD5 sessions are also
available from me upon request.
Sponsored by: sentex.net
resource exhaustion attacks.
For network link optimization TCP can adjust its MSS and thus
packet size according to the observed path MTU. This is done
dynamically based on feedback from the remote host and network
components along the packet path. This information can be
abused to pretend an extremely low path MTU.
The resource exhaustion works in two ways:
o during tcp connection setup the advertized local MSS is
exchanged between the endpoints. The remote endpoint can
set this arbitrarily low (except for a minimum MTU of 64
octets enforced in the BSD code). When the local host is
sending data it is forced to send many small IP packets
instead of a large one.
For example instead of the normal TCP payload size of 1448
it forces TCP payload size of 12 (MTU 64) and thus we have
a 120 times increase in workload and packets. On fast links
this quickly saturates the local CPU and may also hit pps
processing limites of network components along the path.
This type of attack is particularly effective for servers
where the attacker can download large files (WWW and FTP).
We mitigate it by enforcing a minimum MTU settable by sysctl
net.inet.tcp.minmss defaulting to 256 octets.
o the local host is reveiving data on a TCP connection from
the remote host. The local host has no control over the
packet size the remote host is sending. The remote host
may chose to do what is described in the first attack and
send the data in packets with an TCP payload of at least
one byte. For each packet the tcp_input() function will
be entered, the packet is processed and a sowakeup() is
signalled to the connected process.
For example an attack with 2 Mbit/s gives 4716 packets per
second and the same amount of sowakeup()s to the process
(and context switches).
This type of attack is particularly effective for servers
where the attacker can upload large amounts of data.
Normally this is the case with WWW server where large POSTs
can be made.
We mitigate this by calculating the average MSS payload per
second. If it goes below 'net.inet.tcp.minmss' and the pps
rate is above 'net.inet.tcp.minmssoverload' defaulting to
1000 this particular TCP connection is resetted and dropped.
MITRE CVE: CAN-2004-0002
Reviewed by: sam (mentor)
MFC after: 1 day
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)
previously only considered the send sequence space. Unfortunately,
some OSes (windows) still use a random positive increments scheme for
their syn-ack ISNs, so I must consider receive sequence space as well.
The value of 250000 bytes / second for Microsoft's ISN rate of increase
was determined by testing with an XP machine.
we will generate for a given ip/port tuple has advanced far enough
for the time_wait socket in question to be safely recycled.
- Have in_pcblookup_local use tcp_twrecycleable to determine if
time_Wait sockets which are hogging local ports can be safely
freed.
This change preserves proper TIME_WAIT behavior under normal
circumstances while allowing for safe and fast recycling whenever
ephemeral port space is scarce.
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]
sure that the MAC label on TCP responses during TIMEWAIT is
properly set from either the socket (if available), or the mbuf
that it's responding to.
Unfortunately, this is made somewhat difficult by the TCP code,
as tcp_twstart() calls tcp_twrespond() after discarding the socket
but without a reference to the mbuf that causes the "response".
Passing both the socket and the mbuf works arounds this--eventually
it might be good to make sure the mbuf always gets passed in in
"response" scenarios but working through this provided to
complicate things too much.
Approved by: re (scottl)
Reviewed by: hsu
Obtained from: TrustedBSD Project
Sponsored by: DARPA, Network Associates Laboratories
doing Limited Transmit. Only artificially inflate the congestion
window by 1 segment instead of the usual 3 to take into account
the 2 already sent by Limited Transmit.
Approved in principle by: Mark Allman <mallman@grc.nasa.gov>,
Hari Balakrishnan <hari@nms.lcs.mit.edu>, Sally Floyd <floyd@icir.org>
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
not meant to duplicate) TCP/Vegas. Add four sysctls and default the
implementation to 'off'.
net.inet.tcp.inflight_enable enable algorithm (defaults to 0=off)
net.inet.tcp.inflight_debug debugging (defaults to 1=on)
net.inet.tcp.inflight_min minimum window limit
net.inet.tcp.inflight_max maximum window limit
MFC after: 1 week
indication of whether this happenned so the calling function
knows whether or not to unlock the pcb.
Submitted by: Jennifer Yang (yangjihui@yahoo.com)
Bug reported by: Sid Carter (sidcarter@symonds.net)
Ensure that the syn cache's syn-ack packets contain the same
ip_tos, ip_ttl, and DF bits as all other tcp packets.
PR: 39141
MFC after: 2 weeks
This time, make sure that ipv4 specific code (aka all of the above)
is only run in the ipv4 case.
receiver was not sending an immediate ack with delayed acks turned on
when the input buffer is drained, preventing the transmitter from
restarting immediately.
Propogate the TCP_NODELAY option to accept()ed sockets. (Helps tbench and
is a good idea anyway).
Some cleanup. Identify additonal issues in comments.
MFC after: 1 day
to send all its data, especially when the data is less than one MSS.
This fixes an issue where the stack was delaying the sending
of data, eventhough there was enough window to send all the data and
the sending of data was emptying the socket buffer.
Problem found by Yoshihiro Tsuchiya (tsuchiya@flab.fujitsu.co.jp)
Submitted by: Jayanth Vijayaraghavan
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
For TCP, verify that the sequence number in the ICMP packet falls within
the tcp receive window before performing any actions indicated by the
icmp packet.
Clean up some layering violations (access to tcp internals from in_pcb)
Add new PRC_UNREACH_ADMIN_PROHIB in sys/sys/protosw.h
Remove condition on TCP in src/sys/netinet/ip_icmp.c:icmp_input
In src/sys/netinet/ip_icmp.c:icmp_input set code = PRC_UNREACH_ADMIN_PROHIB
or PRC_UNREACH_HOST for all unreachables except ICMP_UNREACH_NEEDFRAG
Rename sysctl icmp_admin_prohib_like_rst to icmp_unreach_like_rst
to reflect the fact that we also react on ICMP unreachables that
are not administrative prohibited. Also update the comments to
reflect this.
In sys/netinet/tcp_subr.c:tcp_ctlinput add code to treat
PRC_UNREACH_ADMIN_PROHIB and PRC_UNREACH_HOST different.
PR: 23986
Submitted by: Jesper Skriver <jesper@skriver.dk>
messages send by routers when they deny our traffic, this causes
a timeout when trying to connect to TCP ports/services on a remote
host, which is blocked by routers or firewalls.
rfc1122 (Requirements for Internet Hosts) section 3.2.2.1 actually
requi re that we treat such a message for a TCP session, that we
treat it like if we had recieved a RST.
quote begin.
A Destination Unreachable message that is received MUST be
reported to the transport layer. The transport layer SHOULD
use the information appropriately; for example, see Sections
4.1.3.3, 4.2.3.9, and 4.2.4 below. A transport protocol
that has its own mechanism for notifying the sender that a
port is unreachable (e.g., TCP, which sends RST segments)
MUST nevertheless accept an ICMP Port Unreachable for the
same purpose.
quote end.
I've written a small extension that implement this, it also create
a sysctl "net.inet.tcp.icmp_admin_prohib_like_rst" to control if
this new behaviour is activated.
When it's activated (set to 1) we'll treat a ICMP administratively
prohibited message (icmp type 3 code 9, 10 and 13) for a TCP
sessions, as if we recived a TCP RST, but only if the TCP session
is in SYN_SENT state.
The reason for only reacting when in SYN_SENT state, is that this
will solve the problem, and at the same time minimize the risk of
this being abused.
I suggest that we enable this new behaviour by default, but it
would be a change of current behaviour, so if people prefer to
leave it disabled by default, at least for now, this would be ok
for me, the attached diff actually have the sysctl set to 0 by
default.
PR: 23086
Submitted by: Jesper Skriver <jesper@skriver.dk>
delete the cloned route that is associated with the connection.
This does not exhaust the routing table memory when the system
is under a SYN flood attack. The route entry is not deleted if there
is any prior information cached in it.
Reviewed by: Peter Wemm,asmodai
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>
is an application space macro and the applications are supposed to be free
to use it as they please (but cannot). This is consistant with the other
BSD's who made this change quite some time ago. More commits to come.
pr_input() routines prototype is also changed to support IPSEC and IPV6
chained protocol headers.
Reviewed by: freebsd-arch, cvs-committers
Obtained from: KAME project
- 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
This makes it possible to change the sysctl tree at runtime.
* Change KLD to find and register any sysctl nodes contained in the loaded
file and to unregister them when the file is unloaded.
Reviewed by: Archie Cobbs <archie@whistle.com>,
Peter Wemm <peter@netplex.com.au> (well they looked at it anyway)
flag means that there is more data to be put into the socket buffer.
Use it in TCP to reduce the interaction between mbuf sizes and the
Nagle algorithm.
Based on: "Justin C. Walker" <justin@apple.com>'s description of Apple's
fix for this problem.
another specialized mbuf type in the process. Also clean up some
of the cruft surrounding IPFW, multicast routing, RSVP, and other
ill-explored corners.
mismatches exposed by this (the prototype for tcp_respond() didn't
match the function definition lexically, and still depends on a
gcc feature to match if ints have more than 32 bits).
Define a parameter which indicates the maximum number of sockets in a
system, and use this to size the zone allocators used for sockets and
for certain PCBs.
Convert PF_LOCAL PCB structures to be type-stable and add a version number.
Define an external format for infomation about socket structures and use
it in several places.
Define a mechanism to get all PF_LOCAL and PF_INET PCB lists through
sysctl(3) without blocking network interrupts for an unreasonable
length of time. This probably still has some bugs and/or race
conditions, but it seems to work well enough on my machines.
It is now possible for `netstat' to get almost all of its information
via the sysctl(3) interface rather than reading kmem (changes to follow).
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
a hashed port list. In the new scheme, in_pcblookup() goes away and is
replaced by a new routine, in_pcblookup_local() for doing the local port
check. Note that this implementation is space inefficient in that the PCB
struct is now too large to fit into 128 bytes. I might deal with this in the
future by using the new zone allocator, but I wanted these changes to be
extensively tested in their current form first.
Also:
1) Fixed off-by-one errors in the port lookup loops in in_pcbbind().
2) Got rid of some unneeded rehashing. Adding a new routine, in_pcbinshash()
to do the initialial hash insertion.
3) Renamed in_pcblookuphash() to in_pcblookup_hash() for easier readability.
4) Added a new routine, in_pcbremlists() to remove the PCB from the various
hash lists.
5) Added/deleted comments where appropriate.
6) Removed unnecessary splnet() locking. In general, the PCB functions should
be called at splnet()...there are unfortunately a few exceptions, however.
7) Reorganized a few structs for better cache line behavior.
8) Killed my TCP_ACK_HACK kludge. It may come back in a different form in
the future, however.
These changes have been tested on wcarchive for more than a month. In tests
done here, connection establishment overhead is reduced by more than 50
times, thus getting rid of one of the major networking scalability problems.
Still to do: make tcp_fastimo/tcp_slowtimo scale well for systems with a
large number of connections. tcp_fastimo is easy; tcp_slowtimo is difficult.
WARNING: Anything that knows about inpcb and tcpcb structs will have to be
recompiled; at the very least, this includes netstat(1).
This commit includes the following changes:
1) Old-style (pr_usrreq()) protocols are no longer supported, the compatibility
glue for them is deleted, and the kernel will panic on boot if any are compiled
in.
2) Certain protocol entry points are modified to take a process structure,
so they they can easily tell whether or not it is possible to sleep, and
also to access credentials.
3) SS_PRIV is no more, and with it goes the SO_PRIVSTATE setsockopt()
call. Protocols should use the process pointer they are now passed.
4) The PF_LOCAL and PF_ROUTE families have been updated to use the new
style, as has the `raw' skeleton family.
5) PF_LOCAL sockets now obey the process's umask when creating a socket
in the filesystem.
As a result, LINT is now broken. I'm hoping that some enterprising hacker
with a bit more time will either make the broken bits work (should be
easy for netipx) or dike them out.
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.
from Larry Peterson &co. at Arizona:
- Header prediction for ACKs did not exclude Fast Retransmit/Recovery.
- srtt calculation tended to get ``stuck'' and could never decrease
when below 8. It still can't, but the scaling factors are adjusted
so that this artifact does not cause as bad an effect on the RTO
value as it used to.
The paper also points out the incr/8 error that has been long since fixed,
and the problems with ACKing frequency resulting from the use of options
which I suspect to be fixed already as well (as part of the T/TCP work).
Obtained from: Brakmo & Peterson, ``Performance Problems in BSD4.4 TCP''
*' instead of caddr_t and it isn't optional (it never was). Most of the
netipx (and netns) pr_ctlinput functions abuse the second arg instead of
using the third arg but fixing this is beyond the scope of this round
of changes.
have to decide whether to send a CC or CCnew option in our SYN segment
depending on the contents of our TAO cache. This decision has to be
made once when the connection starts. The earlier code delayed this
decision until the segment was assembled in tcp_output() and
retransmitted SYN segments could have different CC options.
Reviewed by: Richard Stevens, davidg, wollman
a few new wrinkles for MTU discovery which tcp_output() had better
be prepared to handle. ip_output() is also modified to do something
helpful in this case, since it has already calculated the information
we need.
turned out not to be necessary; simply watching for MTU decreases (which
we already did) automagically eliminates all the cases we were trying to
protect against.
middle of a fully-open window. Also, keep track of how many retransmits
we do as a result of MTU discovery. This may actually do more work than
necessary, but it's an unusual condition...
Suggested by: Janey Hoe <janey@lcs.mit.edu>
to be no ill effects, and so far as Iknow none of the variables in
question depend on 16-bit wraparound behavior. (The sizes are in
many cases relics from when a PCB had to fit inside a 128-byte mbuf. PCBs
are no longer stored in that way, and the old structure would not have
fit, either.)
time ago. I left in Garrett's one, because his was in the 4.4-Lite-2
location, making any diffs just that little bit smaller.
I presume this choice means that netstat needs to be recompiled before
"netstat -s" will give a meaningful answer on tcp stats.
or ssthresh that we were able to use
tcp_var.h - declare tcpstat entries for above; declare tcp_{send,recv}space
in_rmx.c - fill in the MTU and pipe sizes with the defaults TCP would have
used anyway in the absence of values here
know better when to cache values in the route, rather than relying on a
heuristic involving sequence numbers that broke when tcp_sendspace
was increased to 16k.
its connection parameters, we want to keep statistics on how often this
actually happens to see whether there is any work that needs to be done in
TCP itself.
Suggested by: John Wroclawski <jtw@lcs.mit.edu>
