David S. Miller says:

====================
net: Remove UDP Fragmentation Offload support

This is a patch series, based upon some discussions with various
developers, that removes UFO offloading.

Very few devices support this operation, it's usefullness is
quesitonable at best, and it adds a non-trivial amount of
complexity to our data paths.

v2: Delete more code thanks to feedback from Willem.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

No longer used.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Rename udp{4,6}_ufo_fragment() to udp{4,6}_tunnel_segment() and only
handle tunnel segmentation.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Such packets are no longer possible.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It is going away.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It is going away.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It is going away.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It is going away.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It is going away.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It is going away.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It is going away.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This driver doesn't actually support UFO explicitly yet
it advertises this in netdev->features.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

John Fastabend says:

====================
Implement XDP bpf_redirect

This series adds two new XDP helper routines bpf_redirect() and
bpf_redirect_map(). The first variant bpf_redirect() is meant
to be used the same way it is currently being used by the cls_bpf
classifier. An xdp packet will be redirected immediately when this
is called.

The other variant bpf_redirect_map(map, key, flags) uses a new
map type called devmap. A devmap uses integers as keys and
net_devices as values. The user provies key/ifindex pairs to
update the map with new net_devices. This provides two benefits
over the normal variant 'bpf_redirect()'. First the datapath
bpf program is abstracted away from using hard-coded ifindex
values. Allowing a single bpf program to be run any many different
environments. Second, and perhaps more important, the map enables
batching packet transmits. The map plus small driver changes
allows for batching all send requests across a NAPI poll loop.
This allows driver writers to optimize the driver xmit path
and only call expensive operations once for a batch of xdp_buffs.

The devmap was designed to support possible future work for
multicast and broadcast as follow-up patches.

To see, in more detail, how to leverage the new helpers and
map from the userspace side please review these two patches,

  xdp: sample program for new bpf_redirect helper
  xdp: bpf redirect with map sample program

Performance numbers provided by Jesper are the following, tested
using the ixgbe driver with CPU E5-1650 v4 @ 3.60GHz:

13,939,674 pkt/s = XDP_DROP without touching memory
14,290,650 pkt/s = xdp1: XDP_DROP with reading packet data
13,221,812 pkt/s = xdp2: XDP_TX   with swap mac (writes into pkt)
 7,596,576 pkt/s = xdp_redirect:    XDP_REDIRECT with swap mac (like XDP_TX)
13,058,435 pkt/s = xdp_redirect_map:XDP_REDIRECT with swap mac + devmap

A big thanks to everyone who helped with this series. Jesper
provided fixes, debugging, code review, performance benchmarks!
Daniel provided lots of useful feedback and code review. And last
but not least Andy provided useful feedback related to supporting
additional drivers, generic xdp implementation, testing, etc. Any
other feedback is welcome but I believe at this point these are
ready to be merged!

Whats left... get the rest of the drivers developers to implement
this in all the drivers.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NJohn Fastabend <john.fastabend@gmail.com>
Tested-by: NAndy Gospodarek <andy@greyhouse.net>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Acked-by: NJesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The BPF map devmap holds a refcnt on the net_device structure when
it is in the map. We need to do this to ensure on driver unload we
don't lose a dev reference.

However, its not very convenient to have to manually unload the map
when destroying a net device so add notifier handlers to do the cleanup
automatically. But this creates a race between update/destroy BPF
syscall and programs and the unregister netdev hook.

Unfortunately, the best I could come up with is either to live with
requiring manual removal of net devices from the map before removing
the net device OR to add a mutex in devmap to ensure the map is not
modified while we are removing a device. The fallout also requires
that BPF programs no longer update/delete the map from the BPF program
side because the mutex may sleep and this can not be done from inside
an rcu critical section.  This is not a real problem though because I
have not come up with any use cases where this is actually useful in
practice. If/when we come up with a compelling user for this we may
need to revisit this.
Signed-off-by: NJohn Fastabend <john.fastabend@gmail.com>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Acked-by: NJesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

For performance reasons we want to avoid updating the tail pointer in
the driver tx ring as much as possible. To accomplish this we add
batching support to the redirect path in XDP.

This adds another ndo op "xdp_flush" that is used to inform the driver
that it should bump the tail pointer on the TX ring.
Signed-off-by: NJohn Fastabend <john.fastabend@gmail.com>
Signed-off-by: NJesper Dangaard Brouer <brouer@redhat.com>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

BPF programs can use the devmap with a bpf_redirect_map() helper
routine to forward packets to netdevice in map.
Signed-off-by: NJohn Fastabend <john.fastabend@gmail.com>
Signed-off-by: NJesper Dangaard Brouer <brouer@redhat.com>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Device map (devmap) is a BPF map, primarily useful for networking
applications, that uses a key to lookup a reference to a netdevice.

The map provides a clean way for BPF programs to build virtual port
to physical port maps. Additionally, it provides a scoping function
for the redirect action itself allowing multiple optimizations. Future
patches will leverage the map to provide batching at the XDP layer.

Another optimization/feature, that is not yet implemented, would be
to support multiple netdevices per key to support efficient multicast
and broadcast support.
Signed-off-by: NJohn Fastabend <john.fastabend@gmail.com>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Acked-by: NJesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This adds a trace event for xdp redirect which may help when debugging
XDP programs that use redirect bpf commands.
Signed-off-by: NJohn Fastabend <john.fastabend@gmail.com>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Acked-by: NJesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There are optimizations we can add after the basic feature is
enabled. But, for now keep the patch simple.
Signed-off-by: NJohn Fastabend <john.fastabend@gmail.com>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Acked-by: NJesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add support for redirect to xdp generic creating a fall back for
devices that do not yet have support and allowing test infrastructure
using veth pairs to be built.
Signed-off-by: NJohn Fastabend <john.fastabend@gmail.com>
Tested-by: NAndy Gospodarek <andy@greyhouse.net>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Acked-by: NJesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This implements a sample program for testing bpf_redirect. It reports
the number of packets redirected per second and as input takes the
ifindex of the device to run the xdp program on and the ifindex of the
interface to redirect packets to.
Signed-off-by: NJohn Fastabend <john.fastabend@gmail.com>
Tested-by: NAndy Gospodarek <andy@greyhouse.net>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Acked-by: NJesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This adds support for a bpf_redirect helper function to the XDP
infrastructure. For now this only supports redirecting to the egress
path of a port.

In order to support drivers handling a xdp_buff natively this patches
uses a new ndo operation ndo_xdp_xmit() that takes pushes a xdp_buff
to the specified device.

If the program specifies either (a) an unknown device or (b) a device
that does not support the operation a BPF warning is thrown and the
XDP_ABORTED error code is returned.
Signed-off-by: NJohn Fastabend <john.fastabend@gmail.com>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Acked-by: NJesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

XDP generic allows users to test XDP programs and/or run them with
degraded performance on devices that do not yet support XDP. For
testing I typically test eBPF programs using a set of veth devices.
This allows testing topologies that would otherwise be difficult to
setup especially in the early stages of development.

This patch adds a xdp generic hook to the netif_rx_internal()
function which is called from dev_forward_skb(). With this addition
attaching XDP programs to veth devices works as expected! Also I
noticed multiple drivers using netif_rx(). These devices will also
benefit and generic XDP will work for them as well.
Signed-off-by: NJohn Fastabend <john.fastabend@gmail.com>
Tested-by: NAndy Gospodarek <andy@greyhouse.net>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Acked-by: NJesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

tx_rings and rx_rings are cleaned up on close paths in ixgbe driver
however, xdp_rings are not. Set the xdp_rings to NULL here so that
we can use the pointer to indicate if the XDP rings are initialized.
Signed-off-by: NJohn Fastabend <john.fastabend@gmail.com>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Acked-by: NJesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Jiri Pirko says:

====================
mlxsw: Traps enhancements

Ido says:

The first patch makes sure the driver marks packets that were trapped
in the router and might have already been flooded by the bridge, so that
the bridge driver won't flood them again. This isn't critical at this time
point, but will be when Neighbour Discovery traps are introduced as these
are multicast packets that are trapped in the router.

The second and third patches add new traps - for MLD and Router Alert
packets. The last patch takes advantage of that and floods IPv6
unregistered multicast packets only to mrouter ports instead of all ports.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Up until now IPv6 unregistered multicast traffic would be flooded like
broadcast, even when MLD snooping was enabled on the bridge. This was
intentional as MLD packet traps were missing, preventing the bridge
driver from programming MDB entries to the device.

Previous patch added these traps, so we can now finally flood IPv6
unregistered multicast packets to specific ports via the multicast table
instead of flooding them to all ports via the broadcast table.
Signed-off-by: NArkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add support for IPv6 MLDv1/2 packet trapping.
Signed-off-by: NArkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In case local sockets have the IP_ROUTER_ALERT socket option set, then
they expect to get packets with the Router Alert option.

Trap such packets, so that the kernel could inspect them and potentially
send them to interested sockets.
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In commit 1c6c6d22 ("mlxsw: spectrum: Mirror certain packets to
CPU") we marked packets that were mirrored to the CPU, so that they
won't be flooded again by the bridge driver.

However, certain packets are trapped in the device's router block, after
passing through the bridge block where they were potentially flooded.

Mark all packets coming from L3 traps, so that they won't be potentially
flooded again by the bridge driver.
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Jiri Pirko says:

====================
mlxsw: offloading matches on ip ttl and tos

Or says:

Support offloading matches on ip ttl and tos
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Support offloading rules that match on ip tos.
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add ecn and dscp fields to the ipv4 acl block.
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Define new element for ip tos (ecn, dscp) and place it into scratch area.
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Support offloading rules that match on ip ttl.
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add ttl field to the ipv4 acl block.
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Define new element for ip ttl and place it into scratch area.
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As discussed in Faro during Netfilter Workshop 2017, RB trees can be
used with RCU, using a seqlock.

Note that net/rxrpc/conn_service.c is already using this.

This patch converts inetpeer from AVL tree to RB tree, since it allows
to remove private AVL implementation in favor of shared RB code.

$ size net/ipv4/inetpeer.before net/ipv4/inetpeer.after
   text    data     bss     dec     hex filename
   3195      40     128    3363     d23 net/ipv4/inetpeer.before
   1562      24       0    1586     632 net/ipv4/inetpeer.after

The same technique can be used to speed up
net/netfilter/nft_set_rbtree.c (removing rwlock contention in fast path)
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>