Now when the packet is scrubbed early, the metadata_dst can be assigned to
the skb as soon as it is allocated. This simplifies the error cleanup path,
as the dst will be freed by kfree_skb. It is also not necessary to pass it
as a parameter to functions anymore.
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Now when both vxlan_udp_encap_recv and vxlan_rcv are much shorter, combine
them into a single function.
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

It simplifies the vxlan_rcv function.
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This code will be different for VXLAN-GPE, so move it to a separate
function. It will also make the rx path less spaghetti-like.
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Now when the packet is scrubbed early, skb->mark can be set in the GBP
handling code.
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Cong Wang says:

====================
net_sched: add network namespace support for tc actions

This patchset adds network namespace support for tc actions.

v2:
* pull the first patch into net-next
* reduce code duplication by introducing more helper functions
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Currently tc actions are stored in a per-module hashtable,
therefore are visible to all network namespaces. This is
probably the last part of the tc subsystem which is not
aware of netns now. This patch makes them per-netns,
several tc action API's need to be adjusted for this.

The tc action API code is ugly due to historical reasons,
we need to refactor that code in the future.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

We only release the memory of the hashtable itself, not its
entries inside. This is not a problem yet since we only call
it in module release path, and module is refcount'ed by
actions. This would be a problem after we move the per module
hinfo into per netns in the latter patch.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

* Split big conditional statement.
  * Check (data.length <= CCP_MAX_OPTION_LENGTH) only once.
  * Don't read ccp_option[1] if not initialised.

Reading uninitialised ccp_option[1] was harmless, because this could
only happen when data.length was 0 or 1. So even then, we couldn't pass
the (ccp_option[1] < 2 || ccp_option[1] > data.length) test anyway.
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>

When CONFIG_GENEVE is built as a loadable module, and bnx2x is built-in,
we get this link error:

drivers/net/built-in.o: In function `bnx2x_open':
:(.text+0x33322): undefined reference to `geneve_get_rx_port'
drivers/net/built-in.o: In function `bnx2x_sp_rtnl_task':
:(.text+0x3e632): undefined reference to `geneve_get_rx_port'

This avoids the problem by adding a separate Kconfig symbol named
CONFIG_BNX2X_GENEVE that is only enabled when the code is
reachable from the driver.

This is the same trick that BNX2X does for VXLAN support, and
is similar to how I40E handles both.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Fixes: 883ce97d ("bnx2x: Add Geneve inner-RSS support")
Acked-By: Yuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Claudiu Manoil says:

====================
gianfar: xmit() improvements

Remove redundant operations, improve code locality and maintainability.
Thanks.

V2: Updated first patch to not touch existing wmb().
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Timestamp BD status updates that can be merged into the
same "do_tstamp" block, no need for extra save/restore
to the BD area.  The code is more readable too.
Signed-off-by: Claudiu Manoil <claudiu.manoil@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: Claudiu Manoil <claudiu.manoil@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Move the mapping of the head BD before the mapping of fragments.
The TOE (h/w offload) decision logic block can be also moved up
(as the TOE flag belongs to the head BD), resulting in more
localized code (TOE logic vs BD mapping code blocks).
Note that, for this h/w, the R (status) bit for the head BD of a S/G
frame needs to be written last for a reliable transmission.
For the fragmented skb case, a local variable is used to temporarily
store the status info of the first BD, replacing a BD status read.
A merge of 2 "if(do_tstamp)" blocks was also possible.
Signed-off-by: Claudiu Manoil <claudiu.manoil@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

It needs very similar workarounds to the one on BCM4707. It was tested
on D-Link DIR-885L home router.
Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Ajit Khaparde says:

====================
be2net patches

Please consider applying to net-next
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

In QnQ configurations like Flex-10 where the VLANs are inserted by the
ASIC, on rare occasions the HW is encountering a scenario where the
final frame length ends to be greater than what the ASIC can support.

This is because when the TXULP pulls the TX WRB to check the length
of the frame to be transmitted it also adds the size of VLANs to be
inserted by the HW to the length of the frame indicated in the WRB,
which in some cases fails the range check.  This causes a UE.

Avoid this by trimming the skb length to accommodate the VLAN insertion.
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

When 16-bit integers are loaded on CPUs with high order native
register sizes, the CPU could use some extra ops before using them.
And currently some of the frequently used fields in the driver like
the producer and consumer indices of the queues are declared as u16.

This patch declares such fields as u32.  With this change we see the
64-byte packets per second numbers improve by about 4%.
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Alexander Duyck says:

====================
Flow dissector fixes and improvements

This patch series is meant to fix and/or improve a number of items within
the flow dissector code.  The main change out of all of this is that IPv4
and IPv6 fragmentation should now be handled better than it was.  As a
result we should see an improvement when handling things like IP fragment
reassembly as the skbs should now only have header data in the linear
portion of the buffer while the fragments will only hold payload data.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

We want to try and pull the L4 header in if it is available in the first
fragment.  As such add the flag to indicate we want to pull the headers on
the first fragment in.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Acked-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The IPv6 parsing was using a local pointer when it could use the same
pointer as the IPv4 portion of the code since the key_addrs can support
both IPv4 and IPv6 as it is just a pointer.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Acked-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The flow dissector bits handling FCoE didn't bother to actually validate
that the space there was enough for the FCoE header.  So we need to update
things so that if there is room we add the header and report a good result,
otherwise we do not add the header, and report the bad result.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Acked-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

It turns out that for IPv4 we were reporting the ip_proto of the fragment,
and for IPv6 we were not.  This patch updates that behavior so that we
always report the IP protocol of the fragment.  In addition it takes the
steps of updating the payload offset code so that we will determine the
start of the payload not including the L4 header for any fragment after the
first.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Acked-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch corrects the logic for the IPv4 parsing so that it is consistent
with how we handle IPv6.  Specifically if we do not have the flow key
indicating we want the addresses we still may need to take a look at the IP
fragmentation bits and to see if we should stop after we have recognized
the L3 header.

Fixes: 807e165d ("flow_dissector: Add control/reporting of fragmentation")
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Acked-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Saeed Mahameed says:

====================
QoS and VxLAN offloads support for Mellanox 100G mlx5 driver

This patch series introduces QoS IEEE dcbnl support for
PFC, ETS and max rate.

In addition we added VxLAN support and introduced a patch
that modifies the driver to report checksum complete in RX path
for all IP (tunneled and non-tunneled) traffic which is non HW LRO.

This series is applied on top of the latest mlx5_ifc and NDO fixes
we sent to the net tree:
	net/mlx5e: Use static constant netdevice ndos
	net/mlx5e: Remove select queue ndo initialization
	net/mlx5: Use offset based reserved field names in the IFC header file

The QoS patches depend on the IFC change since they expose new fields in
the driver/firmware API. Both QoS and VxLAN patches depend on the NDO changes,
since they add new ndo entries.

Changes from V1:
	- Fixed the S.O.B from "Matt" to "Matthew" to be aligned with the committer title.
	- Don't populate VxLAN/dcbnl ndos for virtual functions.
	- Addressed John comment on mlx5_setup_tc to be aligned with latest API changes.
	- Added device ETS capability check prior query/modify ets configuration.
	- Call mlx5e_dcbnl_ieee_setets_core at the end of mlx5e_create_netdev and don't
fail netdev creation in case it failed or ETS was not supported.

The series where applied on top of: ("5270c4da Merge branch 'vxlan-cleanups'") +
	latest mlx5 ifc and ndo fixes from net tree.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Add TSO and TX checksum counters for tunneled, inner packets
Signed-off-by: Matthew Finlay <matt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Add support for TSO and TX checksum when using hw assisted,
tunneled offloads.
Signed-off-by: Matthew Finlay <matt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

If a VXLAN udp dport is added to device it will:

   - Configure the hardware to offload the port (up to the max
     supported).
   - Advertise NETIF_F_GSO_UDP_TUNNEL and supported hw_enc_features.
Signed-off-by: Matthew Finlay <matt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

add ifndef to en.h. needed for upcoming vxlan patchset.
Signed-off-by: Matthew Finlay <matt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Use checksum complete for all IP packets, unless they are HW LRO,
in which case, use checksum unnecessary.
Signed-off-by: Matthew Finlay <matt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Implement set/get WOL by ethtool and added the needed
device commands and structures to mlx5_ifc.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Rana Shahout <ranas@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Add support for DCBNL IEEE get/set max rate.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Implement the set/get DCBNL IEEE PFC callbacks.
Signed-off-by: Achiad Shochat <achiad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Support the ndo_setup_tc callback and the needed methods
for multi TC/UP support, and removed the default_vlan_prio
from mlx5e_priv which is always 0, it was replaced with
hardcoded "0" in the new select queue method.

For that we now create MAX_NUM_TC num of TISs (one per prio)
on netdevice creation instead of priv->params.num_tc which
was always 1.

So far each channel had a single TXQ, Now each channel has a
TXQ per TC (Traffic Class).

Added en_dcbnl.c which implements the set/get DCBNL IEEE ETS,
set/get dcbx and registers the mlx5e dcbnl ops.

We still use the kernel's default TXQ selection method to select the
channel to transmit through but now we use our own method to select
the TXQ inside the channel based on VLAN priority.

In mlx5, as opposed to mlx4, tc group N gets lower priority than
tc group N+1.

CC: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Rana Shahout <ranas@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Add access functions to set and query a physical port TC groups
and prio parameters.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Add access functions to set and query a physical port PFC
(Priority Flow Control) parameters.
Signed-off-by: Achiad Shochat <achiad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

All the device physical port access functions are implemented in the
port.c file.
We just extract the exposure of these functions from driver.h into a
dedicated header file called port.h.
Signed-off-by: Achiad Shochat <achiad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

One of the validation checks for the new array-based TCP SO_REUSEPORT
validation was unintentionally dropped in ea8add2b.  This adds it back.

Lack of this check allows the user to allocate multiple sock_reuseport
structures (leaking all but the first).

Fixes: ea8add2b ("tcp/dccp: better use of ephemeral ports in bind()")
Signed-off-by: Craig Gallek <kraig@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Vivien Didelot says:

====================
net: dsa: pass bridge device to drivers

This patchset simplifies the DSA layer.

A switch may support multiple bridges with the same hardware VLAN. Thus a check
such as dsa_bridge_check_vlan_range must be moved from the DSA layer to the
concerned driver.

The first purpose of this patchset is to help moving this check to the
mv88e6xxx driver, which is the only one affected at the moment.

To do that, pass directly the bridge net_device structure down to the DSA
drivers, instead of calculating a bitmask of bridge members.

The second purpose is to prepare the replacement of the complex
port_vlan_getnext approach. A second patchset is ready to follow, implementing
port_vlan_dump and thus simplifying the DSA slave code one more time.

Note that this patchset applies on top of https://lkml.org/lkml/2016/2/5/532.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

DSA drivers may support multiple bridge groups with the same hardware
VLAN. The mv88e6xxx driver which cannot yet, already has its own check
for overlapping bridges. Thus remove the check from the DSA layer.
Signed-off-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>