The current definition of struct ocelot_stat_layout is long-winded (4
lines per entry, and we have hundreds of entries), so we could make an
effort to use the C preprocessor and reduce the line count.

Create an implicit correspondence between enum ocelot_reg, which tells
us the register address (SYS_COUNT_RX_OCTETS etc) and enum ocelot_stat
which allows us to index the ocelot->stats array (OCELOT_STAT_RX_OCTETS
etc), and don't require us to specify both when we define what stats
each switch family has.

Create an OCELOT_STAT() macro that pairs only an enum ocelot_stat to an
enum ocelot_reg, and an OCELOT_STAT_ETHTOOL() macro which also contains
a name exported to the unstructured ethtool -S stringset API. For now,
we define all counters as having the OCELOT_STAT_ETHTOOL() kind, but we
will add more counters in the future which are not exported to the
unstructured ethtool -S.
Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The hardware counter is called C_TX_AGED, so rename SYS_COUNT_TX_AGING
to SYS_COUNT_TX_AGED. This will become important since we want to
minimize the way in which we declare struct ocelot_stat_layout elements,
using the C preprocessor.
Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

DSA is integrated with the new standardized ethtool -S --groups option,
but the felix driver only exports unstructured statistics.

Reuse the array of 64-bit statistics collected by ocelot_check_stats_work(),
but just export select values from it.

Since ocelot_check_stats_work() runs periodically to avoid 32-bit
overflow, and the ethtool calling context is sleepable, we update the
64-bit stats one more time, to provide up-to-date values. The locking
scheme with a mutex followed by a spinlock is a bit hard to digest, so
we create and use a ocelot_port_stats_run() helper with a callback that
populates the ethool stats group the caller is interested in.

The exported stats are:
ethtool -S swp0 --groups eth-phy
ethtool -S swp0 --groups eth-mac
ethtool -S swp0 --groups eth-ctrl
ethtool -S swp0 --groups rmon
ethtool --include-statistics --show-pause swp0
Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Move the logic from the ocelot switchdev driver's ocelot_get_stats64()
method to the common switch lib and reuse it for the DSA driver.
Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The Felix PSFP counters suffer from the same problem as the ocelot
ndo_get_stats64 ones - they are 32-bit, so they can easily overflow and
this can easily go undetected.

Add a custom hook in ocelot_check_stats_work() through which driver
specific actions can be taken, and update the stats for the existing
PSFP filters from that hook.

Previously, vsc9959_psfp_filter_add() and vsc9959_psfp_filter_del() were
serialized with respect to each other via rtnl_lock(). However, with the
new entry point into &psfp->sfi_list coming from the periodic worker, we
now need an explicit mutex to serialize access to these lists.

We used to keep a struct felix_stream_filter_counters on stack, through
which vsc9959_psfp_stats_get() - a FLOW_CLS_STATS callback - would
retrieve data from vsc9959_psfp_counters_get(). We need to become
smarter about that in 3 ways:

- we need to keep a persistent set of counters for each stream instead
  of keeping them on stack

- we need to promote those counters from u32 to u64, and create a
  procedure that properly keeps 64-bit counters. Since we clear the
  hardware counters anyway, and we poll every 2 seconds, a simple
  increment of a u64 counter with a u32 value will perfectly do the job.

- FLOW_CLS_STATS also expect incremental counters, so we also need to
  zeroize our u64 counters every time sch_flower calls us
Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

To support SPI-controlled switches in the future, access to
SYS_STAT_CFG_STAT_VIEW needs to be done outside of any spinlock
protected region, but it still needs to be serialized (by a mutex).

Split the ocelot->stats_lock spinlock into a mutex that serializes
indirect access to hardware registers (ocelot->stat_view_lock) and a
spinlock that serializes access to the u64 ocelot->stats array.
Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

TSN stream (802.1Qci, 802.1CB) filters are also accessed through
STAT_VIEW, just like the port registers, but these counters are per
stream, rather than per port. So we don't keep them in
ocelot_port_update_stats().

What we can do, however, is we can create register definitions for them
just like we have for the port counters, and delete the last remaining
user of the SYS_CNT register + a group index (read_gix).
Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The read-modify-write of QSYS_TAG_CONFIG from vsc9959_sched_speed_set()
runs unlocked with respect to the other functions that access it, which
are vsc9959_tas_guard_bands_update(), vsc9959_qos_port_tas_set() and
vsc9959_tas_clock_adjust(). All the others are under ocelot->tas_lock,
so move the vsc9959_sched_speed_set() access under that lock as well, to
resolve the concurrency.

Fixes: 55a515b1 ("net: dsa: felix: drop oversized frames with tc-taprio instead of hanging the port")
Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Experimentally, it looks like when QSYS_QMAXSDU_CFG_7 is set to 605,
frames even way larger than 601 octets are transmitted even though these
should be considered as oversized, according to the documentation, and
dropped.

Since oversized frame dropping depends on frame size, which is only
known at the EOF stage, and therefore not at SOF when cut-through
forwarding begins, it means that the switch cannot take QSYS_QMAXSDU_CFG_*
into consideration for traffic classes that are cut-through.

Since cut-through forwarding has no UAPI to control it, and the driver
enables it based on the mantra "if we can, then why not", the strategy
is to alter vsc9959_cut_through_fwd() to take into consideration which
tc's have oversize frame dropping enabled, and disable cut-through for
them. Then, from vsc9959_tas_guard_bands_update(), we re-trigger the
cut-through determination process.

There are 2 strategies for vsc9959_cut_through_fwd() to determine
whether a tc has oversized dropping enabled or not. One is to keep a bit
mask of traffic classes per port, and the other is to read back from the
hardware registers (a non-zero value of QSYS_QMAXSDU_CFG_* means the
feature is enabled). We choose reading back from registers, because
struct ocelot_port is shared with drivers (ocelot, seville) that don't
support either cut-through nor tc-taprio, and we don't have a felix
specific extension of struct ocelot_port. Furthermore, reading registers
from the Felix hardware is quite cheap, since they are memory-mapped.

Fixes: 55a515b1 ("net: dsa: felix: drop oversized frames with tc-taprio instead of hanging the port")
Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The blamed commit broke tc-taprio schedules such as this one:

tc qdisc replace dev $swp1 root taprio \
        num_tc 8 \
        map 0 1 2 3 4 5 6 7 \
        queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 \
        base-time 0 \
        sched-entry S 0x7f 990000 \
        sched-entry S 0x80  10000 \
        flags 0x2

because the gate entry for TC 7 (S 0x80 10000 ns) now has a static guard
band added earlier than its 'gate close' event, such that packet
overruns won't occur in the worst case of the largest packet possible.

Since guard bands are statically determined based on the per-tc
QSYS_QMAXSDU_CFG_* with a fallback on the port-based QSYS_PORT_MAX_SDU,
we need to discuss what happens with TC 7 depending on kernel version,
since the driver, prior to commit 55a515b1 ("net: dsa: felix: drop
oversized frames with tc-taprio instead of hanging the port"), did not
touch QSYS_QMAXSDU_CFG_*, and therefore relied on QSYS_PORT_MAX_SDU.

1 (before vsc9959_tas_guard_bands_update): QSYS_PORT_MAX_SDU defaults to
  1518, and at gigabit this introduces a static guard band (independent
  of packet sizes) of 12144 ns, plus QSYS::HSCH_MISC_CFG.FRM_ADJ (bit
  time of 20 octets => 160 ns). But this is larger than the time window
  itself, of 10000 ns. So, the queue system never considers a frame with
  TC 7 as eligible for transmission, since the gate practically never
  opens, and these frames are forever stuck in the TX queues and hang
  the port.

2 (after vsc9959_tas_guard_bands_update): Under the sole goal of
  enabling oversized frame dropping, we make an effort to set
  QSYS_QMAXSDU_CFG_7 to 1230 bytes. But QSYS_QMAXSDU_CFG_7 plays
  one more role, which we did not take into account: per-tc static guard
  band, expressed in L2 byte time (auto-adjusted for FCS and L1 overhead).
  There is a discrepancy between what the driver thinks (that there is
  no guard band, and 100% of min_gate_len[tc] is available for egress
  scheduling) and what the hardware actually does (crops the equivalent
  of QSYS_QMAXSDU_CFG_7 ns out of min_gate_len[tc]). In practice, this
  means that the hardware thinks it has exactly 0 ns for scheduling tc 7.

In both cases, even minimum sized Ethernet frames are stuck on egress
rather than being considered for scheduling on TC 7, even if they would
fit given a proper configuration. Considering the current situation,
with vsc9959_tas_guard_bands_update(), frames between 60 octets and 1230
octets in size are not eligible for oversized dropping (because they are
smaller than QSYS_QMAXSDU_CFG_7), but won't be considered as eligible
for scheduling either, because the min_gate_len[7] (10000 ns) minus the
guard band determined by QSYS_QMAXSDU_CFG_7 (1230 octets * 8 ns per
octet == 9840 ns) minus the guard band auto-added for L1 overhead by
QSYS::HSCH_MISC_CFG.FRM_ADJ (20 octets * 8 ns per octet == 160 octets)
leaves 0 ns for scheduling in the queue system proper.

Investigating the hardware behavior, it becomes apparent that the queue
system needs precisely 33 ns of 'gate open' time in order to consider a
frame as eligible for scheduling to a tc. So the solution to this
problem is to amend vsc9959_tas_guard_bands_update(), by giving the
per-tc guard bands less space by exactly 33 ns, just enough for one
frame to be scheduled in that interval. This allows the queue system to
make forward progress for that port-tc, and prevents it from hanging.

Fixes: 297c4de6 ("net: dsa: felix: re-enable TAS guard band mode")
Reported-by: NXiaoliang Yang <xiaoliang.yang_1@nxp.com>
Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Adding support for the LAN9354 device by allowing it to use
the LAN9303 DSA driver.  These devices have the same underlying
access and control methods and from a feature set point of view
the LAN9354 is a superset of the LAN9303.

The MDIO access method has been tested on a SAMA5D3-EDS board
with a LAN9354 RMII daughter card.

While the SPI access method should also be the same, it has not
been tested and as such is not included at this time.
Signed-off-by: NJerry Ray <jerry.ray@microchip.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add initial BYTE_ORDER read to sync the 32-bit accesses over the 16-bit
mdio bus to improve driver robustness.

The lan9303 expects two mdio read transactions back-to-back to read a
32-bit register. The first read transaction causes the other half of the
32-bit register to get latched.  The subsequent read returns the latched
second half of the 32-bit read. The BYTE_ORDER register is an exception to
this rule. As it is a constant value, there is no need to latch the second
half. We read this register first in case there were reads during the boot
loader process that might have occurred prior to this driver taking over
ownership of accessing this device.

This patch has been tested on the SAMA5D3-EDS with a LAN9303 RMII daughter
card.
Signed-off-by: NJerry Ray <jerry.ray@microchip.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add register validation for KSZ9896.
Signed-off-by: NRomain Naour <romain.naour@skf.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

According to the KSZ9477S datasheet, there is no global register
at 0x033C and 0x033D addresses.
Signed-off-by: NRomain Naour <romain.naour@skf.com>
Cc: Oleksij Rempel <o.rempel@pengutronix.de>
Tested-by: NOleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add support for the KSZ9896 6-port Gigabit Ethernet Switch to the
ksz9477 driver. The KSZ9896 supports both SPI (already in) and I2C.
Signed-off-by: NRomain Naour <romain.naour@skf.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add support for the KSZ9896 6-port Gigabit Ethernet Switch to the
ksz9477 driver.

Although the KSZ9896 is already listed in the device tree binding
documentation since a1c0ed24 (dt-bindings: net: dsa: document
additional Microchip KSZ9477 family switches) the chip id
(0x00989600) is not recognized by ksz_switch_detect() and rejected
by the driver.

The KSZ9896 is similar to KSZ9897 but has only one configurable
MII/RMII/RGMII/GMII cpu port.
Signed-off-by: NRomain Naour <romain.naour@skf.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

of_device_get_match_data is called on priv->dev before priv->dev is
actually set. Move of_device_get_match_data after priv->dev is correctly
set to fix this kernel panic.

Fixes: 3bb0844e ("net: dsa: qca8k: cache match data to speed up access")
Signed-off-by: NChristian Marangi <ansuelsmth@gmail.com>
Reviewed-by: NVladimir Oltean <olteanv@gmail.com>
Link: https://lore.kernel.org/r/20220904215319.13070-1-ansuelsmth@gmail.comSigned-off-by: NPaolo Abeni <pabeni@redhat.com>

This patch enables the interrupts for internal phy link detection for
LAN937x. The interrupt enable bits are active low. There is global
interrupt mask for each port. And each port has the individual interrupt
mask for TAS. QCI, SGMII, PTP, PHY and ACL.
The first level of interrupt domain is registered for global port
interrupt and second level of interrupt domain for the individual port
interrupts. The phy interrupt is enabled in the lan937x_mdio_register
function. Interrupt from which port is raised will be detected based on
the interrupt host data.
Signed-off-by: NArun Ramadoss <arun.ramadoss@microchip.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In the lan937x_reset_switch(), it masks all the switch and port
registers. In the Global_Int_status register, POR ready bit is write 1
to clear bit and all other bits are read only. So, this patch clear the
por_ready_int status bit by writing 1.
Signed-off-by: NArun Ramadoss <arun.ramadoss@microchip.com>
Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

struct ksz_port doesn't have reference to ksz_device as of now. In order
to find out from which port interrupt has triggered, we need to pass the
struct ksz_port as a host data. When the interrupt is triggered, we can
get the port from which interrupt triggered, but to identify it is phy
interrupt we have to read status register. The regmap structure for
accessing the device register is present in the ksz_device struct. To
access the ksz_device from the ksz_port, the reference is added to it
with port number as well.
Signed-off-by: NArun Ramadoss <arun.ramadoss@microchip.com>
Reviewed-by: NAndrew Lunn <andrew@lunn.ch>
Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

After driver refactoring we was running ksz9477 specific CPU port
configuration on ksz8 family which ended with kernel oops. So, make sure
we run this code only on ksz9477 compatible devices.

Tested on KSZ8873 and KSZ9477.

Fixes: da8cd085 ("net: dsa: microchip: add support for common phylink mac link up")
Signed-off-by: NOleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Follow the advice of the below link and prefer 'strscpy' in this
subsystem. Conversion is 1:1 because the return value is not used.
Generated by a coccinelle script.

Link: https://lore.kernel.org/r/CAHk-=wgfRnXz0W3D37d01q3JFkr_i_uTL=V6A6G1oUZcprmknw@mail.gmail.com/Signed-off-by: NWolfram Sang <wsa+renesas@sang-engineering.com>
Acked-by: Marc Kleine-Budde <mkl@pengutronix.de> # for CAN
Link: https://lore.kernel.org/r/20220830201457.7984-1-wsa+renesas@sang-engineering.comSigned-off-by: NJakub Kicinski <kuba@kernel.org>

Use chip_id as other places of this code do it
Signed-off-by: NOleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: NVladimir Oltean <olteanv@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This variable is not used. So, remove it.
Signed-off-by: NOleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: NVladimir Oltean <olteanv@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This variable is not used on ksz9477 side. Remove it.
Signed-off-by: NOleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: NVladimir Oltean <olteanv@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This variable is unused. So, drop it.
Signed-off-by: NOleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: NVladimir Oltean <olteanv@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

With code refactoring was introduced new variable internal_phy. Let's
use it.
Signed-off-by: NOleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: NVladimir Oltean <olteanv@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add register validation for KSZ9477
Signed-off-by: NOleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: NVladimir Oltean <olteanv@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The reason why PHYlib may access MII_CTRL1000 on the chip without GBit
support is only if chip provides wrong information about extended caps
register. This issue is now handled by ksz9477_r_phy_quirks()

With proper regmap_ranges provided for all chips we will be able to
catch this kind of bugs any way. So, remove this sanity check.
Signed-off-by: NOleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: NVladimir Oltean <olteanv@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add register validation for KSZ8563.
Signed-off-by: NOleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: NVladimir Oltean <olteanv@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This is complex driver with support for different chips with different
layouts. To detect at least some bugs earlier, we should validate register
accesses by using regmap_access_table support.
Signed-off-by: NOleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: NVladimir Oltean <olteanv@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This issue was detected after adding regmap register access validation.
KSZ9893 compatible chips do not have "Output Clock Control Register
0x0103". So, avoid writing to it.
Signed-off-by: NOleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: NVladimir Oltean <olteanv@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now ksz_pread/ksz_pwrite can return error value. So, make use of it.
Signed-off-by: NOleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: NVladimir Oltean <olteanv@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now ksz_pread/ksz_pwrite can return error value. So, make use of it.
Signed-off-by: NOleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: NVladimir Oltean <olteanv@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

ksz_read*/ksz_write* are able to return errors, so forward it.
Signed-off-by: NOleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: NVladimir Oltean <olteanv@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

PHY access may end with errors on different levels. So, allow to forward
return values where possible.
Signed-off-by: NOleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: NVladimir Oltean <olteanv@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This issue was detected after adding support of regmap_ranges for KSZ8563R
chip. This chip is reporting extended registers support without having
actual extended registers. This made PHYlib request not existing
registers.
Signed-off-by: NOleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: NVladimir Oltean <olteanv@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

KSZ8563 has two 100Mbit PHYs and CPU port with RGMII support. Since
1000Mbit configuration for the RGMII capable MAC is present, we should
use per port validation.

As main part of migration to per-port validation we need to rework
ksz9477_switch_init() function. Which is using undocumented
REG_GLOBAL_OPTIONS register to detect per-chip Gbit support. So, it is
related to some sort of risk for regressions.

To reduce this risk I compared the code with publicly available
documentations. This function will executed on following currently
supported chips:
struct ksz_chip_data            OF compatible
KSZ9477				KSZ9477
KSZ9897				KSZ9897
KSZ9893				KSZ9893, KSZ9563
KSZ8563				KSZ8563
KSZ9567				KSZ9567

Only KSZ9893, KSZ9563, KSZ8563 document existence of 0xf ==
REG_GLOBAL_OPTIONS register with bit field description "SKU ID":
KSZ9893 0x0C
KSZ9563 0x1C
KSZ8563 0x3C

The existence of hidden flags is not documented.

KSZ9477, KSZ9897, KSZ9567 do not document this register at all.

Only KSZ8563 is documented as non Gbit chip: 100Mbit PHYs and RGMII CPU
port. So, this change should not introduce a regression for
configurations with properly used OF compatibles.
Signed-off-by: NOleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: NVladimir Oltean <olteanv@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add separate entry for the KSZ8563 chip. According to the documentation
it can support Gbit only on RGMII port. So, we will need to be able to
describe in the followup patch.
Signed-off-by: NOleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: NVladimir Oltean <olteanv@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

xrs700x_read_port_counters() updates the stats from a worker using the
u64_stats_update_begin() version. This is okay on 32-UP since on the
reader side preemption is disabled.
On 32bit-SMP the writer can be preempted by the reader at which point
the reader will spin on the seqcount until writer continues and
completes the update.

Assigning the mib_mutex mutex to the underlying seqcount would ensure
proper synchronisation. The API for that on the u64_stats_init() side
isn't available. Since it is the only user, just use disable interrupts
during the update.

Use u64_stats_update_begin_irqsave() on the writer side to ensure an
uninterrupted update.

Fixes: ee00b24f ("net: dsa: add Arrow SpeedChips XRS700x driver")
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: George McCollister <george.mccollister@gmail.com>
Cc: Vivien Didelot <vivien.didelot@gmail.com>
Cc: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: NSebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: NGeorge McCollister <george.mccollister@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>