ixgbevf_alloc_q_vectors() calls netif_napi_add for each qvector
where qvectors is determined by the number of msix vectors. This
makes perfect sense.

However on cleanup when ixgbevf_free_q_vectors() is called and
for each qvector we should call netif_napi_del there is some
extra logic to add a dependency on RX queues. This patch makes
the add/del operations symmetric by removing the RX queues
dependency.

Without this if  free_netdev() is called we see the general
protection fault below in netif_napi_del when list_del_init()
is called.

# addr2line -e ./vmlinux ffffffff8140810c
net-next/include/linux/list.h:88

general protection fault: 0000 [#1] SMP
Modules linked in: bonding ixgbevf ixgbe(-) mdio libfc scsi_transport_fc scsi_tgt 8021q garp stp llc cpufreq_ondemand acpi_cpufreq freq_table mperf ipv6 uinput coretemp lpc_ich i2c_i801 shpchp hwmon i2c_core serio_raw crc32c_intel mfd_core joydev pcspkr microcode ioatdma igb dca pata_acpi ata_generic usb_storage pata_jmicron [last unloaded: bonding]
CPU 10
Pid: 4174, comm: rmmod Tainted: G        W    3.6.0-rc3jk-net-next+ #104 Supermicro X8DTN/X8DTN
RIP: 0010:[<ffffffff8140810c>]  [<ffffffff8140810c>] netif_napi_del+0x24/0x87
RSP: 0018:ffff88027f5e9b48  EFLAGS: 00010293
RAX: ffff8806224b4768 RBX: ffff8806224b46e8 RCX: 6b6b6b6b6b6b6b6b
RDX: 6b6b6b6b6b6b6b6b RSI: ffffffff810bf6c5 RDI: ffff8806224b46e8
RBP: ffff88027f5e9b58 R08: ffff88033200b180 R09: ffff88027f5e98a8
R10: ffff88033320b000 R11: ffff88027f5e9ae8 R12: 6b6b6b6b6b6b6aeb
R13: ffff8806221d11c0 R14: 0000000000000000 R15: ffff88027f5e9cf8
FS:  00007f5e58b9b700(0000) GS:ffff880333200000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 00000000010ef2b8 CR3: 0000000281fff000 CR4: 00000000000007e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process rmmod (pid: 4174, threadinfo ffff88027f5e8000, task ffff88032f888000)
Stack:
 ffff8806221d1160 6b6b6b6b6b6b6aeb ffff88027f5e9b88 ffffffff81408e46
 ffff8806221d1160 ffff8806221d1160 ffff8806221d1ae0 ffff8806221d5668
 ffff88027f5e9bb8 ffffffffa009153c ffffffffa0092a30 ffff8806221d5700
Call Trace:
 [<ffffffff81408e46>] free_netdev+0x64/0xd7
 [<ffffffffa009153c>] ixgbevf_remove+0xa6/0xbc [ixgbevf]
 [<ffffffff8127a7a1>] pci_device_remove+0x2d/0x51
 [<ffffffff8131f503>] __device_release_driver+0x6c/0xc2
 [<ffffffff8131f640>] device_release_driver+0x25/0x32
 [<ffffffff8131e821>] bus_remove_device+0x148/0x15d
 [<ffffffff8131cb6b>] device_del+0x130/0x1a4
 [<ffffffff8131cc2a>] device_unregister+0x4b/0x57
 [<ffffffff81275c27>] pci_stop_bus_device+0x63/0x85
 [...]
Signed-off-by: NJohn Fastabend <john.r.fastabend@intel.com>
Acked-by: NGreg Rose <gregory.v.rose@intel.com>
Acked-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NSibai Li <sibai.li@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch updates the igb driver version to 4.0.17.
Signed-off-by: NCarolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

There was a problem in the initial implementation of the get cable length
function for i210 and it did not work properly.  This patch fixes that
problem for i210/i211 devices.
Signed-off-by: NCarolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Add an official link which is designed to guide the user to the appropriate
support resource (be it community, OEM, Intel phone, Intel email, etc)

Add the current e1000 maintainer to the list of Intel maintainers.
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This is a HW requirement. Although a buffer as short as 1 byte is allowed,
the total length of packet before, padding and CRC insertion, must be at
least 17 bytes.  So pad all small packets manually up to 17 bytes before
delivering them to HW.
Signed-off-by: NTushar Dave <tushar.n.dave@intel.com>
Tested-by: NJeff Pieper <jeffrey.e.pieper@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Jeff Kirsher says:

====================
This series contains updates to ixgbe only.  Only change to this series
is I dropped the "ixgbe: Add support for pipeline reset" due to
change requested by Martin Josefsson.

Alexander Duyck (7):
  ixgbe: Add support for IPv6 and UDP to ixgbe_get_headlen
  ixgbe: Add support for tracking the default user priority to SR-IOV
  ixgbe: Add support for GET_QUEUES message to get DCB configuration
  ixgbe: Enable support for VF API version 1.1 in the PF.
  ixgbevf: Add VF DCB + SR-IOV support
  ixgbe: Drop unnecessary addition from ixgbe_set_rx_buffer_len
  ixgbe: Fix possible memory leak in ixgbe_set_ringparam

Don Skidmore (1):
  ixgbe: Add function ixgbe_reset_pipeline_82599

Emil Tantilov (1):
  ixgbe: add WOL support for new subdevice id

Jacob Keller (1):
  ixgbe: (PTP) refactor init, cyclecounter and reset

Tushar Dave (1):
  ixgbe: Correcting small packet padding

Wei Yongjun (1):
  ixgbe: using is_zero_ether_addr() to simplify the code
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

MBIM devices can support up to 256 generic streams called
Device Service Streams (DSS). The MBIM spec says

   The format of the Device Service Stream payload depends
   on the device service (as identified by the corresponding
   UUID) that is used when opening the data stream.

Example use cases are serial AT command interfaces and NMEA
data streams. We cannot make any assumptions about these
device services.

Adding support for Device Service Stream by extending
the MBIM session to VLAN mapping scheme, allocating
VLAN IDs 256 to 511 for DSS, using the DSS SessionID
as the lower 8bit of the VLAN ID.

Using a netdev for DSS keeps the device framing intact and
allows userspace to do whatever it want with the streams.
For example, exporting an AT command interface using DSS
session #0 to a PTY for use with a terminal application like
minicom:

  vconfig add wwan0 256
  ip link set dev wwan0 up
  ip link set dev wwan0.256 up
  socat INTERFACE:wwan0.256,type=2 PTY:,echo=0,link=/tmp/modem

Device configuration must be done using MBIM control commands
over the /dev/cdc-wdmx device. The userspace management
application should coordinate host VLAN configuration and the
device MBIM configuration using the device capabilities to
find out if it needs to set up PTY mappings etc.
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

MBIM devices can support up to 256 independent IP Streams.
The main network device will only handle SessionID 0. Mapping
SessionIDs 1 to 255 to VLANs using the SessionID as VLAN ID
allow userspace to use these streams with traditional tools
like vconfig.
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The MBIM specification allows a MBIM device to disguise
itself as NCM for backwards compatibility, using additional
altsettings with different subclass (control) or protocol
(data):

C:* #Ifs= 2 Cfg#= 1 Atr=80 MxPwr=100mA
I:  If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0d Prot=00 Driver=cdc_mbim
E:  Ad=81(I) Atr=03(Int.) MxPS=  64 Ivl=7ms
I:* If#= 0 Alt= 1 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim
E:  Ad=81(I) Atr=03(Int.) MxPS=  64 Ivl=7ms
I:  If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=01 Driver=cdc_mbim
I:  If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=01 Driver=cdc_mbim
E:  Ad=81(I) Atr=02(Bulk) MxPS=  64 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS=  64 Ivl=0ms
I:* If#= 1 Alt= 2 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
E:  Ad=81(I) Atr=02(Bulk) MxPS=  64 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS=  64 Ivl=0ms

If the MBIM driver is enabled then that should have priority
for devices providing such a NCM 1.0 backward compatibility
mode.
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NGreg Suarez <gsuarez@smithmicro.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The CDC Mobile Broadband Interface Model (MBIM) specification
extends CDC NCM by
 - removing the redundant ethernet header from the point-to-point
   USB channel
 - adding support for multiple IP (v4 and/or v6) sessions multiplexed
   on the same USB channel
 - adding a MBIM control channel encapsulated in CDC
 - adding Device Service Streams (DSS), which are non IP generic data
   streams multiplexed on the same USB channel as the IP sessions

MBIM devices are managed using the dedicated control channel, and no
data will flow on the data channel until a control session has been
established.  This driver has no knowledge of MBIM control messages.
It just exports the control channel to a /dev/cdc-wdmX character
device for userspace management applications. Such an application is
therefore required to use this driver.

This patch implements basic MBIM support, reusing the NCM and WDM driver
APIs, currently limited to IP sessions with SessionID 0. DSS and
multiplexed IP sessions are not yet supported.
Signed-off-by: NGreg Suarez <gsuarez@smithmicro.com>
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Move symbols and definitons which can be shared with a
MBIM driver in a new header.
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Adding multiplexed NDP support to cdc_ncm_fill_tx_frame, allowing
transmissions of multiple independent sessions within the same NTB.

Refactoring the code quite a bit to avoid having to store copies
of multiple NDPs being prepared for tx. The old code would still
reserve enough room for a maximum sized NDP in the skb so we might
as well keep them in the skb while they are being prepared.
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Verifying and handling received MBIM and NCM frames will need
to be different in three areas:
 - verifying the NDP signature
 - checking valid datagram length
 - datagram header manipulation

This makes it inconvenient to share rx_fixup in whole.  But
some verification parts are common.  Split these out in separate
functions.
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The NCM 1.0 spefication makes provisions for linking more than
one NDP into a single NTB. This is important for MBIM support,
where these NDPs might be of different types.

Following the chain of NDPs is also correct for NCM, and will
not change anything in the common case where there is only
one NDP
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

NCM and MBIM can share most of the bind function.  Split
out the shareable part and add MBIM functional descriptor
parsing.
Signed-off-by: NGreg Suarez <gsuarez@smithmicro.com>
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

MBIM and NCM are very similar, so we can reuse most of the
setup and bind logic in cdc_ncm for CDC MBIM devices.  Handle
a few minor differences in ncm_setup.
Signed-off-by: NGreg Suarez <gsuarez@smithmicro.com>
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Based on revision 1.0 of "Universal Serial Bus Communications
Class Subclass Specification for Mobile Broadband Interface
Model" available from www.usb.org
Signed-off-by: NGreg Suarez <gsuarez@smithmicro.com>
[bmork: added DSS defines]
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Acked-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Some devices do not support the 8 byte variants of the NTB input
size control messages despite announcing such support in their
NCM or MBIM functional descriptor.

According to the NCM specification, all devices must support the
4 byte variant regardless of whether or not the flag is set:

  If bit D5 is set in the bmNetworkCapabilities field of
  function’s NCM Functional Descriptor, the host may
  set wLength either to 4 or to 8. If wLength is 4, the
  function shall assume that wNtbInMaxDatagrams is to be
  set to zero. If wLength is 8, then the function shall
  use the provided value as the limit. The function shall
  return an error response (a STALL PID) if wLength is set
  to any other value.

We do not set wNtbInMaxDatagrams in any case, so we can just as
well unconditionally use the 4 byte variant without losing any
functionality.  This works around the known firmware bug, and
simplifies the code considerably.
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This will allow us to remove the last mach include from at91_ether
and also make it easier to share address setup with macb.
Signed-off-by: NJoachim Eastwood <manabian@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now that HAVE_NET_MACB is gone let's just select MACB to
satisfy the dependecies in at91_ether.
Signed-off-by: NJoachim Eastwood <manabian@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

macb is a platform driver and there is nothing that prevents
this driver from being built on non-ARM/AVR32 platforms.
Signed-off-by: NJoachim Eastwood <manabian@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When building macb on x86_64 the following warnings show up:
  drivers/net/ethernet/cadence/macb.c: In function macb_interrupt:
  drivers/net/ethernet/cadence/macb.c:556:4: warning: large integer implicitly truncated to unsigned type [-Woverflow]
  drivers/net/ethernet/cadence/macb.c: In function macb_reset_hw:
  drivers/net/ethernet/cadence/macb.c:792:2: warning: large integer implicitly truncated to unsigned type [-Woverflow]
  drivers/net/ethernet/cadence/macb.c:793:2: warning: large integer implicitly truncated to unsigned type [-Woverflow]
  drivers/net/ethernet/cadence/macb.c:796:2: warning: large integer implicitly truncated to unsigned type [-Woverflow]

Use -1 insted of ~0UL, as done in other places in the driver,
to silence these warnings.
Signed-off-by: NJoachim Eastwood <manabian@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Each nexthop is added like a single route in the routing table. All routes
that have the same metric/weight and destination but not the same gateway
are considering as ECMP routes. They are linked together, through a list called
rt6i_siblings.

ECMP routes can be added in one shot, with RTA_MULTIPATH attribute or one after
the other (in both case, the flag NLM_F_EXCL should not be set).

The patch is based on a previous work from
Luc Saillard <luc.saillard@6wind.com>.
Signed-off-by: NNicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We were not correctly freeing the temporary rings on error in
ixgbe_set_ring_param.  In order to correct this I am unwinding a number of
changes that were made in order to get things back to the original working
form with modification for the current ring layouts.

This approach has multiple advantages including a smaller memory footprint,
and the fact that the interface is stopped while we are allocating the rings
meaning that there is less potential for some sort of memory corruption on the
ring.

The only disadvantage I see with this approach is that on a Rx allocation
failure we will report an error and only update the Tx rings.  However the
adapter should be fully functional in this state and the likelihood of such
an error is very low.  In addition it is not unreasonable to expect the
user to need to recheck the ring configuration should they experience an
error setting the ring sizes.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NPhil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch adds a function that forces a full pipeline reset.  This
function will be used in following patches to completely reset the PHY
during resets.
Signed-off-by: NDon Skidmore <donald.c.skidmore@intel.com>
Tested-by: NPhil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

We still had some code floating around from the old single buffer receive
path.  As a result we were adding VLAN_HLEN to max_frame although the
resultant value was never used.  Since that is the case we can drop this from
the function.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NPhil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Driver pad skb up to 17 bytes because of the HW requirement. However, that code
implementation mess up the skb tail pointer after padding. This patch sets
skb->tail correctly.
Signed-off-by: NTushar Dave <tushar.n.dave@intel.com>
Tested-by: NPhil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Using is_zero_ether_addr() to simplify the code.
Signed-off-by: NWei Yongjun <yongjun_wei@trendmicro.com.cn>
Tested-by: NPhil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch modifies when and where PTP registers and data are set. Previously
a work-around was used inside cyclecounter_start in order to reset some of the
time registers. This patch creates a new ixgbe_ptp_reset specifically for this
purpose. The cyclecounter configuration has trimmed down to only modify what
is necessary. Due to hardware conditions after probe and before open, PTP init
has now moved into the ixgbe_open call. This allows the ptp device name in the
sysfs to be the ethernet device name instead of the MAC address.

The cyclecounter check flag is renamed to PTP_ENABLED and is used to prevent
PTP init from happening when PTP has not been enabled.

CC: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NJacob Keller <jacob.e.keller@intel.com>
Tested-by: NPhil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch adds a subdevice id for new 82599 device. The define is needed
to allow enabling WOL support.
Signed-off-by: NEmil Tantilov <emil.s.tantilov@intel.com>
Tested-by: NPhil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This change adds support for DCB and SR-IOV from the VF.  With this change
in place the VF will correctly use a traffic class other than 0 in the case
that the PF is configured with the default user priority belonging to a
traffic class other than 0.

Cc: Greg Rose <gregory.v.rose@intel.com>
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NSibai Li <sibai.li@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This change switches on the last few bits for us enabling version 1.1 VF
support in the PF.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NPhil Schmitt <phillip.j.schmitt@intel.com>
Tested-by: NRobert Garrett <RobertX.Garrett@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch addresses several issues in regards to the combination of DCB
and SR-IOV. Specifically it allows us to send information to the VF on
which queues it should be using.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NPhil Schmitt <phillip.j.schmitt@intel.com>
Tested-by: NRoss Brattain <ross.b.brattain@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

It is necessary to track the default user priority in the PF so that we can
force it upon the VFs.  The motivation behind this is to keep the VFs from
getting access to user priorities meant for things like storage.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NPhil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This change adds support for IPv6 and UDP to ixgbe_get_headlen. The
advantage to this is that we can now handle ipv4/UDP, ipv6/TCP, and
ipv6/UDP with a single memcpy instead of having to do them in multiple
pskb_may_pull calls.

A quick bit of testing shows that we increase throughput for a single
session of netperf from 8800Mpbs to about 9300Mpbs in the case of ipv6/TCP.
As such overall ipv6 performance should improve with this change.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NStephen Ko  <stephen.s.ko@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

A small host typically needs ~10 fib_info structures, so create initial
hash table with 16 slots instead of only one. This removes potential
false sharing and reallocs/rehashes (1->2->4->8->16)
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

SIOCINQ can use the lock_sock_fast() version to avoid double acquisition
of socket lock.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation]

  All TCP stacks MAY implement the following mitigation.  TCP stacks
  that implement this mitigation MUST add an additional input check to
  any incoming segment.  The ACK value is considered acceptable only if
  it is in the range of ((SND.UNA - MAX.SND.WND) <= SEG.ACK <=
  SND.NXT).  All incoming segments whose ACK value doesn't satisfy the
  above condition MUST be discarded and an ACK sent back.

Move tcp_send_challenge_ack() before tcp_ack() to avoid a forward
declaration.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Jerry Chu <hkchu@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

ns_to_ktime() seems better than ktime_set() + ktime_add_ns()
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>