After commit 3a927bc7 ("ovs: propagate per dp max headroom to
all vports") the need_headroom for the internal vport is updated
accordingly to the max needed headroom in its datapath.

That avoids the pskb_expand_head() costs when sending/forwarding
packets towards tunnel devices, at least for some scenarios.

We still require such copy when using the ovs-preferred configuration
for vxlan tunnels:

    br_int
  /       \
tap      vxlan
           (remote_ip:X)

br_phy
     \
    NIC

where the route towards the IP 'X' is via 'br_phy'.

When forwarding traffic from the tap towards the vxlan device, we
will call pskb_expand_head() in vxlan_build_skb() because
br-phy->needed_headroom is equal to tun->needed_headroom.

With this change we avoid updating the internal vport needed_headroom,
so that in the above scenario no head copy is needed, giving 5%
performance improvement in UDP throughput test.

As a trade-off, packets sent from the internal port towards a tunnel
device will now experience the head copy overhead. The rationale is
that the latter use-case is less relevant performance-wise.
Signed-off-by: NPaolo Abeni <pabeni@redhat.com>
Acked-by: NPravin B Shelar <pshelar@ovn.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Network devices can allocate reasources and private memory using
netdev_ops->ndo_init().  However, the release of these resources
can occur in one of two different places.

Either netdev_ops->ndo_uninit() or netdev->destructor().

The decision of which operation frees the resources depends upon
whether it is necessary for all netdev refs to be released before it
is safe to perform the freeing.

netdev_ops->ndo_uninit() presumably can occur right after the
NETDEV_UNREGISTER notifier completes and the unicast and multicast
address lists are flushed.

netdev->destructor(), on the other hand, does not run until the
netdev references all go away.

Further complicating the situation is that netdev->destructor()
almost universally does also a free_netdev().

This creates a problem for the logic in register_netdevice().
Because all callers of register_netdevice() manage the freeing
of the netdev, and invoke free_netdev(dev) if register_netdevice()
fails.

If netdev_ops->ndo_init() succeeds, but something else fails inside
of register_netdevice(), it does call ndo_ops->ndo_uninit().  But
it is not able to invoke netdev->destructor().

This is because netdev->destructor() will do a free_netdev() and
then the caller of register_netdevice() will do the same.

However, this means that the resources that would normally be released
by netdev->destructor() will not be.

Over the years drivers have added local hacks to deal with this, by
invoking their destructor parts by hand when register_netdevice()
fails.

Many drivers do not try to deal with this, and instead we have leaks.

Let's close this hole by formalizing the distinction between what
private things need to be freed up by netdev->destructor() and whether
the driver needs unregister_netdevice() to perform the free_netdev().

netdev->priv_destructor() performs all actions to free up the private
resources that used to be freed by netdev->destructor(), except for
free_netdev().

netdev->needs_free_netdev is a boolean that indicates whether
free_netdev() should be done at the end of unregister_netdevice().

Now, register_netdevice() can sanely release all resources after
ndo_ops->ndo_init() succeeds, by invoking both ndo_ops->ndo_uninit()
and netdev->priv_destructor().

And at the end of unregister_netdevice(), we invoke
netdev->priv_destructor() and optionally call free_netdev().
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit 91572088 ("net: use core MTU range checking in core net
infra") changed the openvswitch internal device to use the core net
infra for controlling the MTU range, but failed to actually set the
max_mtu as described in the commit message, which now defaults to
ETH_DATA_LEN.

This patch fixes this by setting max_mtu to ETH_MAX_MTU after
ether_setup() call.

Fixes: 91572088 ("net: use core MTU range checking in core net infra")
Signed-off-by: NJarno Rajahalme <jarno@ovn.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The network device operation for reading statistics is only called
in one place, and it ignores the return value. Having a structure
return value is potentially confusing because some future driver could
incorrectly assume that the return value was used.

Fix all drivers with ndo_get_stats64 to have a void function.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

geneve:
- Merge __geneve_change_mtu back into geneve_change_mtu, set max_mtu
- This one isn't quite as straight-forward as others, could use some
  closer inspection and testing

macvlan:
- set min/max_mtu

tun:
- set min/max_mtu, remove tun_net_change_mtu

vxlan:
- Merge __vxlan_change_mtu back into vxlan_change_mtu
- Set max_mtu to IP_MAX_MTU and retain dynamic MTU range checks in
  change_mtu function
- This one is also not as straight-forward and could use closer inspection
  and testing from vxlan folks

bridge:
- set max_mtu of IP_MAX_MTU and retain dynamic MTU range checks in
  change_mtu function

openvswitch:
- set min/max_mtu, remove internal_dev_change_mtu
- note: max_mtu wasn't checked previously, it's been set to 65535, which
  is the largest possible size supported

sch_teql:
- set min/max_mtu (note: max_mtu previously unchecked, used max of 65535)

macsec:
- min_mtu = 0, max_mtu = 65535

macvlan:
- min_mtu = 0, max_mtu = 65535

ntb_netdev:
- min_mtu = 0, max_mtu = 65535

veth:
- min_mtu = 68, max_mtu = 65535

8021q:
- min_mtu = 0, max_mtu = 65535

CC: netdev@vger.kernel.org
CC: Nicolas Dichtel <nicolas.dichtel@6wind.com>
CC: Hannes Frederic Sowa <hannes@stressinduktion.org>
CC: Tom Herbert <tom@herbertland.com>
CC: Daniel Borkmann <daniel@iogearbox.net>
CC: Alexander Duyck <alexander.h.duyck@intel.com>
CC: Paolo Abeni <pabeni@redhat.com>
CC: Jiri Benc <jbenc@redhat.com>
CC: WANG Cong <xiyou.wangcong@gmail.com>
CC: Roopa Prabhu <roopa@cumulusnetworks.com>
CC: Pravin B Shelar <pshelar@ovn.org>
CC: Sabrina Dubroca <sd@queasysnail.net>
CC: Patrick McHardy <kaber@trash.net>
CC: Stephen Hemminger <stephen@networkplumber.org>
CC: Pravin Shelar <pshelar@nicira.com>
CC: Maxim Krasnyansky <maxk@qti.qualcomm.com>
Signed-off-by: NJarod Wilson <jarod@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The internal device does support 802.1AD offloading since 018c1dda
("openvswitch: 802.1AD Flow handling, actions, vlan parsing, netlink
attributes").
Signed-off-by: NJiri Benc <jbenc@redhat.com>
Acked-by: NPravin B Shelar <pshelar@ovn.org>
Acked-by: NEric Garver <e@erig.me>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

net_device->ndo_set_rx_headroom (introduced in
871b642a) says

  "Setting a negtaive value reset the rx headroom
   to the default value".

It seems that the OVS implementation in
3a927bc7 overlooked this and sets
dev->needed_headroom unconditionally.

This doesn't have an immediate effect, but can mess up later
LL_RESERVED_SPACE calculations, such as done in
net/ipv6/mcast.c:mld_newpack.  For reference, this issue was found
from a skb_panic raised there after the length calculations had given
the wrong result.

Note the other current users of this interface
(drivers/net/tun.c:tun_set_headroom and
drivers/net/veth.c:veth_set_rx_headroom) are both checking this
correctly thus need no modification.

Thanks to Ben for some pointers from the crash dumps!

Cc: Benjamin Poirier <bpoirier@suse.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1361414Signed-off-by: NIan Wienand <iwienand@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Set name_assign_type of internal port to NET_NAME_USER.
Signed-off-by: NZhang Shengju <zhangshengju@cmss.chinamobile.com>
Acked-by: NPravin B Shelar <pshelar@ovn.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Cc: Pravin Shelar <pshelar@nicira.com>
Signed-off-by: NPhil Sutter <phil@nwl.cc>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NFengguang Wu <fengguang.wu@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch implements bookkeeping support to compute the maximum
headroom for all the devices in each datapath. When said value
changes, the underlying devs are notified via the
ndo_set_rx_headroom method.

This also increases the internal vports xmit performance.
Signed-off-by: NPaolo Abeni <pabeni@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

With use of lwtunnel, we can directly call dev_queue_xmit()
rather than calling netdev vport send operation.
Following change make tunnel vport code bit cleaner.
Signed-off-by: NPravin B Shelar <pshelar@nicira.com>
Acked-by: NThomas Graf <tgraf@suug.ch>
Acked-by: NJiri Benc <jbenc@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

"openvswitch: Remove vport stats" removed the per-vport statistics, in
order to use the netdev's statistics fields.
"openvswitch: Fix ovs_vport_get_stats()" fixed the export of these stats
to user-space, by using the provided netdev_ops to collate them - but ovs
internal devices still use an unallocated dev->tstats field to count
packets, which are no longer exported by this api.

Allocate the dev->tstats field for ovs internal devices, and wire up
ndo_get_stats64 with the original implementation of
ovs_vport_get_stats().

On its own, "openvswitch: Fix ovs_vport_get_stats()" fixes the OOPs,
unmasking a full-on panic on arm64:

=============%<==============
[<ffffffbffc00ce4c>] internal_dev_recv+0xa8/0x170 [openvswitch]
[<ffffffbffc0008b4>] do_output.isra.31+0x60/0x19c [openvswitch]
[<ffffffbffc000bf8>] do_execute_actions+0x208/0x11c0 [openvswitch]
[<ffffffbffc001c78>] ovs_execute_actions+0xc8/0x238 [openvswitch]
[<ffffffbffc003dfc>] ovs_packet_cmd_execute+0x21c/0x288 [openvswitch]
[<ffffffc0005e8c5c>] genl_family_rcv_msg+0x1b0/0x310
[<ffffffc0005e8e60>] genl_rcv_msg+0xa4/0xe4
[<ffffffc0005e7ddc>] netlink_rcv_skb+0xb0/0xdc
[<ffffffc0005e8a94>] genl_rcv+0x38/0x50
[<ffffffc0005e76c0>] netlink_unicast+0x164/0x210
[<ffffffc0005e7b70>] netlink_sendmsg+0x304/0x368
[<ffffffc0005a21c0>] sock_sendmsg+0x30/0x4c
[SNIP]
Kernel panic - not syncing: Fatal exception in interrupt
=============%<==============

Fixes: 8c876639 ("openvswitch: Remove vport stats.")
Signed-off-by: NJames Morse <james.morse@arm.com>
Acked-by: NPravin B Shelar <pshelar@nicira.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Since all vport types are now backed by netdev, we can directly
use netdev stats. Following patch removes redundant stat
from vport.
Signed-off-by: NPravin B Shelar <pshelar@nicira.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add this helper so code can easily figure out if netdev is openswitch.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This allows to get rid of the get_name() vport ops later on.
Signed-off-by: NThomas Graf <tgraf@suug.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This is the first step in representing all OVS vports as regular
struct net_devices. Move the net_device pointer into the vport
structure itself to get rid of struct vport_netdev.
Signed-off-by: NThomas Graf <tgraf@suug.ch>
Signed-off-by: NPravin B Shelar <pshelar@nicira.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If the internal device is not up, it should drop received
packets. Sometimes it receive the broadcast or multicast
packets, and the ip protocol stack will casue more cpu
usage wasted.
Signed-off-by: NChunhe Li <lichunhe@huawei.com>
Signed-off-by: NPravin B Shelar <pshelar@nicira.com>

The internal and netdev vport remain part of openvswitch.ko. Encap
vports including vxlan, gre, and geneve can be built as separate
modules and are loaded on demand. Modules can be unloaded after use.
Datapath ports keep a reference to the vport module during their
lifetime.

Allows to remove the error prone maintenance of the global list
vport_ops_list.
Signed-off-by: NThomas Graf <tgraf@suug.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Following patch enables all available tunnel GSO features for OVS
bridge device so that ovs can use hardware offloads available to
underling device.
Signed-off-by: NPravin B Shelar <pshelar@nicira.com>
Acked-by: NAndy Zhou <azhou@nicira.com>

Extend alloc_netdev{,_mq{,s}}() to take name_assign_type as argument, and convert
all users to pass NET_NAME_UNKNOWN.

Coccinelle patch:

@@
expression sizeof_priv, name, setup, txqs, rxqs, count;
@@

(
-alloc_netdev_mqs(sizeof_priv, name, setup, txqs, rxqs)
+alloc_netdev_mqs(sizeof_priv, name, NET_NAME_UNKNOWN, setup, txqs, rxqs)
|
-alloc_netdev_mq(sizeof_priv, name, setup, count)
+alloc_netdev_mq(sizeof_priv, name, NET_NAME_UNKNOWN, setup, count)
|
-alloc_netdev(sizeof_priv, name, setup)
+alloc_netdev(sizeof_priv, name, NET_NAME_UNKNOWN, setup)
)

v9: move comments here from the wrong commit
Signed-off-by: NTom Gundersen <teg@jklm.no>
Reviewed-by: NDavid Herrmann <dh.herrmann@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This stub now allows userspace to see IFLA_INFO_KIND for ovs master and
IFLA_INFO_SLAVE_KIND for slave.
Signed-off-by: NJiri Pirko <jiri@resnulli.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

net: get rid of SET_ETHTOOL_OPS

Dave Miller mentioned he'd like to see SET_ETHTOOL_OPS gone.
This does that.

Mostly done via coccinelle script:
@@
struct ethtool_ops *ops;
struct net_device *dev;
@@
-       SET_ETHTOOL_OPS(dev, ops);
+       dev->ethtool_ops = ops;

Compile tested only, but I'd seriously wonder if this broke anything.
Suggested-by: NDave Miller <davem@davemloft.net>
Signed-off-by: NWilfried Klaebe <w-lkml@lebenslange-mailadresse.de>
Acked-by: NFelipe Balbi <balbi@ti.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

OVS already can handle all types of segmentation offloads that
are supported by the kernel.
Following patch specifically enables UDP and IPV6 segmentation
offloads.
Signed-off-by: NPravin B Shelar <pshelar@nicira.com>
Signed-off-by: NJesse Gross <jesse@nicira.com>

Add ovs tunnel interface for set tunnel action for userspace.
Signed-off-by: NPravin B Shelar <pshelar@nicira.com>
Acked-by: NJesse Gross <jesse@nicira.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Following patch keeps skb->csum correct across ovs.
Signed-off-by: NPravin B Shelar <pshelar@nicira.com>
Signed-off-by: NJesse Gross <jesse@nicira.com>

The only user is get_dpifindex(), no need to redirect via the port
operations.
Signed-off-by: NThomas Graf <tgraf@suug.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Rename the hardware VLAN acceleration features to include "CTAG" to indicate
that they only support CTAGs. Follow up patches will introduce 802.1ad
server provider tagging (STAGs) and require the distinction for hardware not
supporting acclerating both.
Signed-off-by: NPatrick McHardy <kaber@trash.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently OVS uses combination of genl and rtnl lock to protect
datapath state.  This was done due to networking stack locking.
But this has complicated locking and there are few lock ordering
issues with new tunneling protocols.
Following patch simplifies locking by introducing new ovs mutex
and now this lock is used to protect entire ovs state.
Signed-off-by: NPravin B Shelar <pshelar@nicira.com>
Signed-off-by: NJesse Gross <jesse@nicira.com>

Use strlcpy where possible to ensure the string is \0 terminated.
Use always sizeof(string) instead of 32, ETHTOOL_BUSINFO_LEN
and custom defines.
Use snprintf instead of sprint.
Remove unnecessary inits of ->fw_version
Remove unnecessary inits of drvinfo struct.
Signed-off-by: NJiri Pirko <jiri@resnulli.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

NET_ADDR_SET is set in dev_set_mac_address() no need to alter
dev->addr_assign_type value in drivers.
Signed-off-by: NJiri Pirko <jiri@resnulli.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

bonus: if we ever are to use IFF_LIVE_ADDR_CHANGE for
anything further than to check availability in eth_mac_addr(),
Open vSwitch will be ready for that.
Signed-off-by: NThomas Graf <tgraf@redhat.com>
Signed-off-by: NJesse Gross <jesse@nicira.com>

Following patch adds support for network namespace to openvswitch.
Since it must release devices when namespaces are destroyed, a
side effect of this patch is that the module no longer keeps a
refcount but instead cleans up any state when it is unloaded.
Signed-off-by: NPravin B Shelar <pshelar@nicira.com>
Signed-off-by: NJesse Gross <jesse@nicira.com>

It's possible that packets that are sent on internal devices (from
the OVS perspective) have already traversed the local IP stack.
After they go through the internal device, they will again travel
through the IP stack which may get confused by the presence of
existing information in the skb. The problem can be observed
when switching between namespaces. This clears out that information
to avoid problems but deliberately leaves other metadata alone.
This is to provide maximum flexibility in chaining together OVS
and other Linux components.
Signed-off-by: NJesse Gross <jesse@nicira.com>

Replaced all instances of Nicira Networks(, Inc) to Nicira, Inc.
Signed-off-by: NRaju Subramanian <rsubramanian@nicira.com>
Signed-off-by: NBen Pfaff <blp@nicira.com>
Signed-off-by: NJesse Gross <jesse@nicira.com>

Use eth_hw_addr_random() instead of calling random_ether_addr()
to set addr_assign_type correctly to NET_ADDR_RANDOM.

Reset the state to NET_ADDR_PERM as soon as the MAC get
changed via .ndo_set_mac_address.

v2: adapt to renamed eth_hw_addr_random()
Signed-off-by: NDanny Kukawka <danny.kukawka@bisect.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

remove version.h includes in net/openswitch/ as reported by make versioncheck.
Signed-off-by: NDevendra Naga <devendra.aaru@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Open vSwitch is a multilayer Ethernet switch targeted at virtualized
environments.  In addition to supporting a variety of features
expected in a traditional hardware switch, it enables fine-grained
programmatic extension and flow-based control of the network.
This control is useful in a wide variety of applications but is
particularly important in multi-server virtualization deployments,
which are often characterized by highly dynamic endpoints and the need
to maintain logical abstractions for multiple tenants.

The Open vSwitch datapath provides an in-kernel fast path for packet
forwarding.  It is complemented by a userspace daemon, ovs-vswitchd,
which is able to accept configuration from a variety of sources and
translate it into packet processing rules.

See http://openvswitch.org for more information and userspace
utilities.
Signed-off-by: NJesse Gross <jesse@nicira.com>