Commit Graph

4524 Commits

Author SHA1 Message Date
Michael Tuexen
cca6f4a8f3 Get it compiling without INET and INET6 support (mainly userland stack).
MFC after: 2 weeks
2012-12-08 15:11:09 +00:00
Pawel Jakub Dawidek
6acd596efb More warnings for zones that depend on the kern.ipc.maxsockets limit.
Obtained from:	WHEEL Systems
2012-12-08 12:51:06 +00:00
Michael Tuexen
b11f07d86c Use correct padding of the ABORT chunk in case of an user initiated
abort cause is used.

MFC after: 2 weeks
2012-12-08 09:50:38 +00:00
Michael Tuexen
3fb7827628 Ensure that the padding of the last parameter of an INIT chunk
is not included in the chunk length as required by RFC 4960.
While there, cleanup sctp_send_initiate().

MFC after: 2 weeks
2012-12-08 08:22:33 +00:00
Gleb Smirnoff
eb1b1807af Mechanically substitute flags from historic mbuf allocator with
malloc(9) flags within sys.

Exceptions:

- sys/contrib not touched
- sys/mbuf.h edited manually
2012-12-05 08:04:20 +00:00
Andre Oppermann
da2299c5c7 Remove unused and unnecessary CSUM_IP_FRAGS checksumming capability.
Checksumming the IP header of fragments is no different from doing
normal IP headers.

Discussed with:	yongari
MFC after:	1 week
2012-11-27 19:31:49 +00:00
Andre Oppermann
13feab8286 Add DELACK to list of timers.
MFC after:	1 week
2012-11-27 19:07:28 +00:00
Navdeep Parhar
825fd1e437 Make sure that tcp_timer_activate() correctly sees TCP_OFFLOAD (or not). 2012-11-27 06:42:44 +00:00
Alfred Perlstein
08373e0bc4 Auto size the tcbhashsize structure based on max sockets.
While here, also make the code that enforces power-of-two more
forgiving, instead of just resetting to 512, graciously round-down
to the next lower power of two.
2012-11-27 03:04:24 +00:00
Michael Tuexen
a50f0e3152 Add support for sctp_peeloff() also in the front states of the
association.

MFC after: 3 days
2012-11-26 16:44:03 +00:00
Michael Tuexen
e3976bb8d7 Find the endpoint for an incoming packet also if the endpoint
comes from sctp_peeloff().

MFC after: 3 days
2012-11-26 16:43:32 +00:00
Michael Tuexen
440da2d35b Allow shutdown() to be used on fds returned from sctp_peeloff().
MFC after: 3 days
2012-11-26 08:50:00 +00:00
Michael Tuexen
a3158782c2 Remove unused function.
MFC after: 1 week
2012-11-25 14:25:08 +00:00
Michael Tuexen
3a51a2647a Add support for SCTP/UDP/IPV6.
This completes the support of
http://tools.ietf.org/html/draft-ietf-tsvwg-sctp-udp-encaps

MFC after: 1 week
2012-11-17 20:04:04 +00:00
Michael Tuexen
325c8c46b1 Get the accounting working. We now have counters how many
chunks for each SCTP outgoing stream are in the send and
sent queue.
While there, improve the naming of NR-SACK related constants
recently introduced.

MFC after: 1 week
2012-11-16 19:39:10 +00:00
Roman Divacky
8252626fb4 Initialize hdrlen to 0 to avoid clang warning in NOINET case. 2012-11-10 10:41:00 +00:00
Bjoern A. Zeeb
ec89d0398b Cleanup some whitspace in this file to get it out of an upcoming patch.
MFC after:	10 days
2012-11-08 03:29:55 +00:00
Michael Tuexen
a7ad6026e0 Add per outgoing stream accounting for chunks in the send
and sent queue. This provides no functional change, but is
a preparation for an upcoming stream reset improvement.
Done with rrs@.

MFC after: 1 week
2012-11-07 22:11:38 +00:00
Michael Tuexen
2a4985847a Add some missing changes missed in the last commit.
MFC after: 1 week
X-MFC with: 242708
2012-11-07 21:25:32 +00:00
Michael Tuexen
98f2956c11 Improve PR-SCTP if used in combination with NR-SACK.
Based on work done by Mohammad Rajiullah.

MFC after: 1 week
2012-11-07 20:59:00 +00:00
Kevin Lo
0f5e7edc14 Fix typo; s/ouput/output 2012-11-07 07:00:59 +00:00
Mateusz Guzik
8e1e6e5f4a Fix possible spurious sbunlock in sctp_sorecvmsg.
Reviewed by:	tuexen
Approved by:	trasz (mentor)
MFC after:	3 days
2012-11-06 23:04:23 +00:00
Michael Tuexen
f3b05218ea Move from early SSN assignment to late SSN assignment.
This doesn't change functionality, but makes upcoming change
much easier.
Developed with rrs@ at the IETF 85.

MFC after: 1 week
2012-11-05 20:55:17 +00:00
Andre Oppermann
60ee3bb213 Back out r242262. The simplified window change/update logic wasn't
complete and ready for production use.

PR:	kern/173309
2012-11-05 09:13:06 +00:00
Andrey V. Elsukov
ffdbf9da3b Remove the recently added sysctl variable net.pfil.forward.
Instead, add protocol specific mbuf flags M_IP_NEXTHOP and
M_IP6_NEXTHOP. Use them to indicate that the mbuf's chain
contains the PACKET_TAG_IPFORWARD tag. And do a tag lookup
only when this flag is set.

Suggested by:	andre
2012-11-02 01:20:55 +00:00
Michael Tuexen
21f67da7c4 Whitespace changes due to upstream integration of SCTP changes in the
FreeBSD code base.
2012-10-29 20:47:32 +00:00
Michael Tuexen
24d4ce2c87 Add braces (as used elsewhere in the SCTP code). 2012-10-29 20:44:29 +00:00
Michael Tuexen
09c1c8563a Use ntohs() and htons() in correct order. However, this doesn't change
functionality.
2012-10-29 20:42:48 +00:00
Andre Oppermann
78f59b4bfd Forced commit to provide the correct commit message to r242251:
Defer sending an independent window update if a delayed ACK is pending
  saving a packet.  The window update then gets piggy-backed on the next
  already scheduled ACK.

Added grammar fixes as well.

MFC after:	2 weeks
2012-10-29 13:16:33 +00:00
Andre Oppermann
8d045dbdf3 Define the delayed ACK timeout value directly as hz/10 instead of
obfuscating it by going through PR_FASTHZ.  No functional change.

MFC after:	2 weeks
2012-10-29 12:17:02 +00:00
Andre Oppermann
322181c98e If the user has closed the socket then drop a persisting connection
after a much reduced timeout.

Typically web servers close their sockets quickly under the assumption
that the TCP connections goes away as well.  That is not entirely true
however.  If the peer closed the window we're going to wait for a long
time with lots of data in the send buffer.

MFC after:	2 weeks
2012-10-28 19:58:20 +00:00
Andre Oppermann
09440655fe Increase the initial CWND to 10 segments as defined in IETF TCPM
draft-ietf-tcpm-initcwnd-05. It explains why the increased initial
window improves the overall performance of many web services without
risking congestion collapse.

As long as it remains a draft it is placed under a sysctl marking it
as experimental:
 net.inet.tcp.experimental.initcwnd10 = 1
When it becomes an official RFC soon the sysctl will be changed to
the RFC number and moved to net.inet.tcp.

This implementation differs from the RFC draft in that it is a bit
more conservative in the case of packet loss on SYN or SYN|ACK because
we haven't reduced the default RTO to 1 second yet.  Also the restart
window isn't yet increased as allowed.  Both will be adjusted with
upcoming changes.

Is is enabled by default.  In Linux it is enabled since kernel 3.0.

MFC after:	2 weeks
2012-10-28 19:47:46 +00:00
Andre Oppermann
77339e1cdc Update comment to reflect the change made in r242263.
MFC after:	2 weeks
2012-10-28 19:22:18 +00:00
Andre Oppermann
c4ab59c1a1 Add SACK_PERMIT to the list of TCP options that are switched off after
retransmitting a SYN three times.

MFC after:	2 weeks
2012-10-28 19:20:23 +00:00
Andre Oppermann
79ce26a08c Simplify and enhance the window change/update acceptance logic,
especially in the presence of bi-directional data transfers.

snd_wl1 tracks the right edge, including data in the reassembly
queue, of valid incoming data.  This makes it like rcv_nxt plus
reassembly.  It never goes backwards to prevent older, possibly
reordered segments from updating the window.

snd_wl2 tracks the left edge of sent data.  This makes it a duplicate
of snd_una.  However joining them right now is difficult due to
separate update dependencies in different places in the code flow.

snd_wnd tracks the current advertized send window by the peer.  In
tcp_output() the effective window is calculated by subtracting the
already in-flight data, snd_nxt less snd_una, from it.

ACK's become the main clock of window updates and will always update
the window when the left edge of what we sent is advanced.  The ACK
clock is the primary signaling mechanism in ongoing data transfers.
This works reliably even in the presence of reordering, reassembly
and retransmitted segments.  The ACK clock is most important because
it determines how much data we are allowed to inject into the network.

Zero window updates get us out of persistence mode are crucial.  Here
a segment that neither moves ACK nor SEQ but enlarges WND is accepted.

When the ACK clock is not active (that is we're not or no longer
sending any data) any segment that moves the extended right SEQ edge,
including out-of-order segments, updates the window.  This gives us
updates especially during ping-pong transfers where the peer isn't
done consuming the already acknowledged data from the receive buffer
while responding with data.

The SSH protocol is a prime candidate to benefit from the improved
bi-directional window update logic as it has its own windowing
mechanism on top of TCP and is frequently sending back protocol ACK's.

Tcpdump provided by:	darrenr
Tested by:	darrenr
MFC after:	2 weeks
2012-10-28 19:16:22 +00:00
Andre Oppermann
024fd5b6bb For retransmits of SYN|ACK from the syncache use the slightly more
aggressive special tcp_syn_backoff[] retransmit schedule instead of
the normal tcp_backoff[] schedule for established connections.

MFC after:	2 weeks
2012-10-28 19:02:07 +00:00
Andre Oppermann
f4748ef5fb When retransmitting SYN in TCPS_SYN_SENT state use TCPTV_RTOBASE,
the default retransmit timeout, as base to calculate the backoff
time until next try instead of the TCP_REXMTVAL() macro which only
works correctly when we already have measured an actual RTT+RTTVAR.

Before it would cause the first retransmit at RTOBASE, the next
four at the same time (!) about 200ms later, and then another one
again RTOBASE later.

MFC after:	2 weeks
2012-10-28 18:56:57 +00:00
Andre Oppermann
602e8e45ee Remove bogus 'else' in #ifdef that prevented the rttvar from being reset
tcp_timer_rexmt() on retransmit for IPv6 sessions.

MFC after:	2 weeks
2012-10-28 18:45:04 +00:00
Andre Oppermann
4faaea5505 Allow arbitrary MSS sizes and don't mind about the cluster size anymore.
We've got more cluster sizes for quite some time now and the orginally
imposed limits and the previously codified thoughts on efficiency gains
are no longer true.

MFC after:	2 weeks
2012-10-28 18:33:52 +00:00
Andre Oppermann
f3a10d7954 Change the syncache count reporting the current number of entries
from an unprotected u_int that reports garbage on SMP to a function
based sysctl obtaining the current value from UMA.

Also read back the actual cache_limit after page size rounding by UMA.

PR:		kern/165879
MFC after:	2 weeks
2012-10-28 18:07:34 +00:00
Andre Oppermann
aafa0b4164 Simplify implementation of net.inet.tcp.reass.maxsegments and
net.inet.tcp.reass.cursegments.

MFC after:	2 weeks
2012-10-28 17:59:46 +00:00
Andre Oppermann
f62563d33c Prevent a flurry of forced window updates when an application is
doing small reads on a (partially) filled receive socket buffer.

Normally one would a send a window update every time the available
space in the socket buffer increases by two times MSS.  This leads
to a flurry of window updates that do not provide any meaningful
new information to the sender.  There still is available space in
the window and the sender can continue sending data.  All window
updates then get carried by the regular ACKs.  Only when the socket
buffer was (almost) full and the window closed accordingly a window
updates delivery new information and allows the sender to start
sending more data again.

Send window updates only every two MSS when the socket buffer
has less than 1/8 space available, or the available space in the
socket buffer increased by 1/4 its full capacity, or the socket
buffer is very small.  The next regular data ACK will carry and
report the exact window size again.

Reported by:	sbruno
Tested by:	darrenr
Tested by:	Darren Baginski
PR:		kern/116335
MFC after:	2 weeks
2012-10-28 17:40:35 +00:00
Andre Oppermann
4249614cb0 When SYN or SYN/ACK had to be retransmitted RFC5681 requires us to
reduce the initial CWND to one segment.  This reduction got lost
some time ago due to a change in initialization ordering.

Additionally in tcp_timer_rexmt() avoid entering fast recovery when
we're still in TCPS_SYN_SENT state.

MFC after:	2 weeks
2012-10-28 17:30:28 +00:00
Andre Oppermann
cf8f04f4c0 When SYN or SYN/ACK had to be retransmitted RFC5681 requires us to
reduce the initial CWND to one segment.  This reduction got lost
some time ago due to a change in initialization ordering.

Additionally in tcp_timer_rexmt() avoid entering fast recovery when
we're still in TCPS_SYN_SENT state.

MFC after:	2 weeks
2012-10-28 17:25:08 +00:00
Andre Oppermann
22efabd40c Adjust the initial default CWND upon connection establishment to the
new and increased values specified by RFC5681 Section 3.1.

The even larger initial CWND per RFC3390, if enabled, is not affected.

MFC after:	2 weeks
2012-10-28 17:16:09 +00:00
Gleb Smirnoff
078468ede4 o Remove last argument to ip_fragment(), and obtain all needed information
on checksums directly from mbuf flags. This simplifies code.
o Clear CSUM_IP from the mbuf in ip_fragment() if we did checksums in
  hardware. Some driver may not announce CSUM_IP in theur if_hwassist,
  although try to do checksums if CSUM_IP set on mbuf. Example is em(4).
o While here, consistently use CSUM_IP instead of its alias CSUM_DELAY_IP.
  After this change CSUM_DELAY_IP vanishes from the stack.

Submitted by:	Sebastian Kuzminsky <seb lineratesystems.com>
2012-10-26 21:06:33 +00:00
Andrey V. Elsukov
c1de64a495 Remove the IPFIREWALL_FORWARD kernel option and make possible to turn
on the related functionality in the runtime via the sysctl variable
net.pfil.forward. It is turned off by default.

Sponsored by:	Yandex LLC
Discussed with:	net@
MFC after:	2 weeks
2012-10-25 09:39:14 +00:00
Gleb Smirnoff
a7f707cd37 After r241923 the updated ip_len no longer needed. 2012-10-25 09:02:21 +00:00
Gleb Smirnoff
b6fcf6f9f5 Fix error in r241913 that had broken fragment reassembly. 2012-10-25 09:00:57 +00:00
Gleb Smirnoff
9e2a372fd2 Use ip_stripoptions() instead of handrolled version. 2012-10-23 10:30:09 +00:00