Make these compile without INET. tcp_input probably needs a lot more
work...

fix tcp/udp checksum test in the M_CSUM_NO_PSEUDOHDR case
(this can never have worked)
now I can use a "bge" gigabit interface with hw checksumming
ttcp-t: 2147483648 bytes in 18.31 real seconds = 11

fix tcp/udp checksum test in the M_CSUM_NO_PSEUDOHDR case
(this can never have worked)
now I can use a "bge" gigabit interface with hw checksumming
ttcp-t: 2147483648 bytes in 18.31 real seconds = 114527.11 KB/sec +++
woow!

show more ...

KNF

some corrections from markus@openbsd;
- callout_ack() was called with wrong argument
- no need for xor with timestamp as we are using arc4random()
- minor typo/cleanup

Footwork for fast-ipsec and IPv6: when compiling sys/netinet/tcp_input.c
for both FAST_IPSEC and INET6, include <netipsec/ipsec6.h>.

Fix the bug in the tcp transmit prediction code.
During testing the prediction counters show a hit-rate on about 85% for
packets sent on a local LAN, and better than 99% for intercontinental
high-spe

Fix the bug in the tcp transmit prediction code.
During testing the prediction counters show a hit-rate on about 85% for
packets sent on a local LAN, and better than 99% for intercontinental
high-speed bulk traffic (!).

show more ...

Remove all the code to maintain ia_inpcbs. This information was only used to
close sockets on address changes, which was deemed to be a bad idea and was
summarily removed, so there is no point in wa

Remove all the code to maintain ia_inpcbs. This information was only used to
close sockets on address changes, which was deemed to be a bad idea and was
summarily removed, so there is no point in wasting effort on maintaining it
any more.

show more ...

cut-and-paste error. Valeriy E. Ushakov

if IPsec inbound policy mismatches, respond to SYN with RST (instead of
just dropping it), allow client to react quickly.

clarify flowlabel handling

revamp inpcb/in6pcb so that they are more aligned with each other.
in6pcb lookup now uses hash(9).

make sure so is properly initialized

remove ipsec_set/getsocket. now we explicitly pass socket * to ip{,6}_output.

change the additional arg to be passed to ip{,6}_output to struct socket *.

this fixes KAME policy lookup which was broken by the previous commit.

Replace the set_socket() method of passing an extra struct socket*
argument to ip6_output() with a new explicit struct in6pcb* argument.
(The underlying socket can be obtained via in6pcb->inp6_socket

Replace the set_socket() method of passing an extra struct socket*
argument to ip6_output() with a new explicit struct in6pcb* argument.
(The underlying socket can be obtained via in6pcb->inp6_socket.)

In preparation for fast-ipsec. Reviewed by itojun.

show more ...

Honour the M_CSUM_NO_PSEUDOHDR, if set on inbound TCP and UDP packets.
Tested against bcm5700 with patched if_bge.c.

(fast-ipsec): Add hooks to pass IPv4 IPsec traffic into fast-ipsec, if
configured with ``options FAST_IPSEC''. Kernels with KAME IPsec or
with no IPsec should work as before.

All calls to ip_output

(fast-ipsec): Add hooks to pass IPv4 IPsec traffic into fast-ipsec, if
configured with ``options FAST_IPSEC''. Kernels with KAME IPsec or
with no IPsec should work as before.

All calls to ip_output() now always pass an additional compulsory
argument: the inpcb associated with the packet being sent,
or 0 if no inpcb is available.

Fast-ipsec tested with ICMP or UDP over ESP. TCP doesn't work, yet.

show more ...

Move UCB-licensed code from 4-clause to 3-clause licence.

Patches provided by Joel Baker in PR 22364, verified by myself.

As a temporary workaround, apply the fix from PR#20390, thereby
cooperating with the callout code in working around the race
condition caused by the TCP code's use of the callout facility.

Instead o

As a temporary workaround, apply the fix from PR#20390, thereby
cooperating with the callout code in working around the race
condition caused by the TCP code's use of the callout facility.

Instead of unconditionally releasing memory in tcp_close() and
SYN_CACHE_PUT(), check whether any of the related callout handlers
are about to be invoked (but have not yet done callout_ack()), and
if so, just mark the associated data structure (tcpcb or syn cache
entry) as "dead", and test for this (and release storage) in the
callout handler functions.

show more ...

Fix previous bug. Thanks to Enami for spotting the (obvious) error, and
to other people with much help with bug reports etc.
While fixing, change some of the code I added last time to make it
cleaner

Fix previous bug. Thanks to Enami for spotting the (obvious) error, and
to other people with much help with bug reports etc.
While fixing, change some of the code I added last time to make it
cleaner and simpler.

show more ...

Back out the lwp/ktrace changes. They contained a lot of colateral damage,
and need to be examined and discussed more.

Add code to remember where in the send queue of mbufs the last packet was
sent from. This change avoid a linear search through all mbufs when using
large TCP windows, and therefore permit high-speed

Add code to remember where in the send queue of mbufs the last packet was
sent from. This change avoid a linear search through all mbufs when using
large TCP windows, and therefore permit high-speed connections on long
distances.

Tested on a 1 Gigabit connection between Luleå and San Francisco, a distance
of about 15000km. With TCP windows of just over 20 Mbytes it could keep up
with 950Mbit/s.

After discussions with Matt Thomas and Jason Thorpe.

show more ...

Change the way multicasts are kept. They now use a hash table in the same
manner as the ifaddr hash table. By doing this, the mkludge code can go
away. At the same time, keep track of what pcbs ar

Change the way multicasts are kept. They now use a hash table in the same
manner as the ifaddr hash table. By doing this, the mkludge code can go
away. At the same time, keep track of what pcbs are using what ifaddr and
when an address is deleted from an interface, notify/abort all sockets
that have that address as a source. Switch IGMP and multicasts to use pools
for allocation. Fix a number of potential problems in the igmp code where
allocation failures could cause a trap/panic.

show more ...

inherit IPV6_V6ONLY from listening socket. PR 21713

no need for ip_v recovery in output path too
(tcp_template includes ip_v setting)