Remove $FreeBSD$: two-line nroff pattern

Remove /^\.\\"\n\.\\"\s*\$FreeBSD\$$\n/

vxlan: correct interface MTU when using hw offloads

Otherwise it breaks when offloading like checksum or TSO are used,
because second (encapsulated) ip_output() processing passes fragments of
the en

vxlan: correct interface MTU when using hw offloads

Otherwise it breaks when offloading like checksum or TSO are used,
because second (encapsulated) ip_output() processing passes fragments of
the encapsulated packet down to the hardware interface.

Diagnosed by: hselasky
Reviewed by: np
Sponsored by: Nvidia Networking / Mellanox Technologies
MFC after: 1 week
Differential revision: https://reviews.freebsd.org/D29501

show more ...

if_vxlan(4): add support for hardware assisted checksumming, TSO, and RSS.

This lets a VXLAN pseudo-interface take advantage of hardware checksumming (tx
and rx), TSO, and RSS if the NIC is capable

if_vxlan(4): add support for hardware assisted checksumming, TSO, and RSS.

This lets a VXLAN pseudo-interface take advantage of hardware checksumming (tx
and rx), TSO, and RSS if the NIC is capable of performing these operations on
inner VXLAN traffic.

A VXLAN interface inherits the capabilities of its vxlandev interface if one is
specified or of the interface that hosts the vxlanlocal address. If other
interfaces will carry traffic for that VXLAN then they must have the same
hardware capabilities.

On transmit, if_vxlan verifies that the outbound interface has the required
capabilities and then translates the CSUM_ flags to their inner equivalents.
This tells the hardware ifnet that it needs to operate on the inner frame and
not the outer VXLAN headers.

An event is generated when a VXLAN ifnet starts. This allows hardware drivers to
configure their devices to expect VXLAN traffic on the specified incoming port.

On receive, the hardware does RSS and checksum verification on the inner frame.
if_vxlan now does a direct netisr dispatch to take full advantage of RSS. It is
not very clear why it didn't do this already.

Future work:
Rx: it should be possible to avoid the first trip up the protocol stack to get
the frame to if_vxlan just so it can decapsulate and requeue for a second trip
up the stack. The hardware NIC driver could directly call an if_vxlan receive
routine for VXLAN traffic instead.

Rx: LRO. depends on what happens with the previous item. There will have to to
be a mechanism to indicate that it's time for if_vxlan to flush its LRO state.

Reviewed by: kib@
Relnotes: Yes
Sponsored by: Chelsio Communications
Differential Revision: https://reviews.freebsd.org/D25873

show more ...

MFH

Sponsored by: Rubicon Communications, LLC (netgate.com)

vlan(4): Minor grammar corrections

Note: date not bumped because "content" was not changed, just inserted some
missing words.

PR: 248001
Submitted by: Jose Luis Duran <jlduran@gmail.com>
MFC after

vlan(4): Minor grammar corrections

Note: date not bumped because "content" was not changed, just inserted some
missing words.

PR: 248001
Submitted by: Jose Luis Duran <jlduran@gmail.com>
MFC after: 2 weeks
Sponsored by: Klara Inc.

show more ...

Merge ^/head r340918 through r341763.

Minor mandoc fixes.

Merge ^/head r327341 through r327623.

Add rc.conf vxlan example

PR: 206288
Submitted by: james@lodge.me.uk
MFC after: 2 weeks

MFH

Sponsored by: The FreeBSD Foundation

Fix bunch of .Xrs.

MFC after: 1 month
Sponsored by: The FreeBSD Foundation

Merge sync of head

Reintegrate head: r274132-r277384

Sponsored by: The FreeBSD Foundation

Reintegrate head revisions r273096-r277147

Sponsored by: The FreeBSD Foundation

MFhead @ r276594

Merge ^/head r274961 through r276301.

Fix various mdoc issues.

Found with: mandoc -Tlint

MFhead @ r275911 (also, sort out MK_* flags in BMAKE, etc on this branch)

Merge ^/head r275759 through r275911.

Prefix all the vxlan ifconfig commands so they are unique

And rehook ifvxlan back into the build.

Merge from head@274682

Sync to HEAD@r274095.

IFC @r273338

Add vxlan interface

vxlan creates a virtual LAN by encapsulating the inner Ethernet frame in
a UDP packet. This implementation is based on RFC7348.

Currently, the IPv6 support is not fully complian

Add vxlan interface

vxlan creates a virtual LAN by encapsulating the inner Ethernet frame in
a UDP packet. This implementation is based on RFC7348.

Currently, the IPv6 support is not fully compliant with the specification:
we should be able to receive UPDv6 packets with a zero checksum, but we
need to support RFC6935 first. Patches for this should come soon.

Encapsulation protocols such as vxlan emphasize the need for the FreeBSD
network stack to support batching, GRO, and GSO. Each frame has to make
two trips through the network stack, and each frame will be at most MTU
sized. Performance suffers accordingly.

Some latest generation NICs have begun to support vxlan HW offloads that
we should also take advantage of. VIMAGE support should also be added soon.

Differential Revision: https://reviews.freebsd.org/D384
Reviewed by: gnn
Relnotes: yes

show more ...