Currently small MSS values may require too many TSO descriptors for
the default queue size. This commit prevents this situation by fixing
the maximum supported TSO number of segments to 100 and by setting a
minimum Tx queue size. The minimum Tx queue size is set so that at
least 2 worst-case skb can be accommodated.

In addition, the queue stop and wake thresholds values are adjusted
accordingly. The queue is stopped when there's room for only 1 worst-case
skb and waked when the number of descriptors is half that value.
Signed-off-by: NEzequiel Garcia <ezequiel.garcia@free-electrons.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This driver has no need for a custom NAPI weigth. Use the default
one, which has the same value.
Signed-off-by: NEzequiel Garcia <ezequiel.garcia@free-electrons.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add netpoll support to macvlan devices. Based on the netpoll support in the 802.1q vlan code.

Tested and macvlan could work well with netconsole.
Signed-off-by: NDing Tianhong <dingtianhong@huawei.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Bjørn Mork says:

====================
cdc_ncm: fixes and conversion to sysfs API

After considering the comments received after the ethtool coalesce
support was commited, I have ended up concluding that we should
remove it again, while we can, before it hits a release. The idea
was not well enough thought through, and all comments received
pointed to advantages of using a sysfs based API instead.

This series removes the ethtool coalesce support and replaces it
with sysfs attributes in a driver specific group under the netdev.

The first 3 patches are unrelated fixes:

patch 1: reducing truesize as discussed
patch 2: fixing a potentional buffer overrun when changing tx_max
patch 3: prevent framing errors when changing rx_max

Changes v2:
 - minor editorial changes to patch 8, as suggested by Peter Stuge
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Adding documentation for all the driver specific sysfs attributes.

Cc: Peter Stuge <peter@stuge.se>
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The min_tx_pkt variable decides the cutoff point where the driver
will stop padding out NTBs to maximum size. The padding is a tradeoff
where we use some USB bus bandwidth to allow the device to receive
fixed size buffers. Different devices will have different optimal
settings, spanning from no padding at all to padding every NTB.
There is no way to automatically figure out which setting is best
for a specific device.

The default value is a reasonable tradeoff, calculated based on the
USB packet size and out NTB max size. This may have to be changed
along with any tx_max changes.
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The mandatory GetNtbParameters control request is an important part of
the host <-> device protocol negotiation in CDC NCM (and CDC MBIM). It
gives device limits which the host must obey when configuring the
protocol aggregation variables. The driver will enforce this by
rejecting attempts to set any of the tunable variables to a value
which is not supported by the device.  Exporting the parameter block
helps userspace decide which values are allowed without resorting
to trial and error.
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The ethtool coalesce API is not applicable for this driver. Forcing
it to fit the NCM aggregation redefined the API in a driver specific
way, which is much worse than defining a clean new API. These ethtool
coalesce functions have therefore been replaced by a new sysfs API.
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Attach a driver specific sysfs group to the netdev, and use it
for the rx/tx aggregation variables.

The datagram aggregation defined by the CDC NCM specification is
specific to this device class (including CDC MBIM). Using the
ethtool interrupt coalesce API as an interface to the aggregation
parameters redefined that API in a driver specific and confusing
way.  A sysfs group
 - makes it clear that this is a driver specific userspace API, and
 - allows us to export the real values instead of some translated
   version, and
 - lets us include more aggregation variables which were impossible
   to force into the ethtool API.

Additionally, using sysfs allows tuning the driver on space
constrained hosts where userspace tools like ethtool are undesired.
Suggested-by: NPeter Stuge <peter@stuge.se>
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It doesn't matter whether the buffer size goes up or down.  We have to
keep usbnet and device syncronized to be able to split transfers at the
correct boundaries. The spec allow skipping short packets when using
max sized transfers.  If we don't tell usbnet about our new expected rx
buffer size, then it will merge and/or split NTBs.  The driver does not
support this, and the result will be lots of framing errors.

Fix by always reallocating usbnet rx buffers when the rx_max value
changes.

Fixes: 68864abf ("net: cdc_ncm: support rx_max/tx_max updates when running")
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We are calling usbnet_start_xmit() to flush any remaining data,
depending on the side effect that tx_curr_skb is set to NULL,
ensuring a new allocation using the updated tx_max.  But this
side effect will only happen if there were any cached data ready
to transmit. If not, then an empty tx_curr_skb is still allocated
using the old tx_max size. Free it to avoid a buffer overrun.

Fixes: 68864abf ("net: cdc_ncm: support rx_max/tx_max updates when running")
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Cloning the big skbs we use for USB buffering chokes up TCP and
SCTP because the socket memory limits are hitting earlier than
they should. It is better to unconditionally copy the unwrapped
packets to freshly allocated skbs.
Reported-by: NJim Baxter <jim_baxter@mentor.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The macvlan dev should always have the same mac address like lowerdev
when in the passthru mode, change the mac address alone will break the
work mechanism, so when the lowerdev or macvlan mac address changes,
we should propagate the changes to another dev.

v1->v2: Allow macvlan dev to change mac address for passthru mode and propagate to
	lowerdev.

v2->v3: Don't set the mac address to the lower dev's unicast address for
	passthru mode when mac address changes.
Signed-off-by: NDing Tianhong <dingtianhong@huawei.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The following patch moved device tree interrupt resolution into
platform_get_irq_byname:

  ad69674e of/irq: do irq resolution in platform_get_irq_byname()

As a result, the function no longer only return -ENXIO on error.
This breaks DT based probing of stmmac, as seen in test runs of
linux-next next-20140526 cubie2-sunxi_defconfig:

  http://lists.linaro.org/pipermail/kernel-build-reports/2014-May/003659.html

This patch makes the stmmac_platform probe function properly handle
error codes, such as returning for deferred probing, and other codes
returned by of_irq_get_by_name.
Signed-off-by: NChen-Yu Tsai <wens@csie.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

John W. Linville says:

====================
pull request: wireless-next 2014-06-02

Please pull this remaining batch of updates intended for the 3.16 stream...

For the mac80211 bits, Johannes says:

"The remainder for -next right now is mostly fixes, and a handful of
small new things like some CSA infrastructure, the regdb script mW/dBm
conversion change and sending wiphy notifications."

For the bluetooth bits, Gustavo says:

"Some more patches for 3.16. There is nothing really special here, just a
bunch of clean ups, fixes plus some small improvements. Please pull."

For the nfc bits, Samuel says:

"We have:

- Felica (Type3) tags support for trf7970a
- Type 4b tags support for port100
- st21nfca DTS typo fix
- A few sparse warning fixes"

For the atheros bits, Kalle says:

"Ben added support for setting antenna configurations. Michal improved
warm reset so that we would not need to fall back to cold reset that
often, an issue where ath10k stripped protected flag while in monitor
mode and made module initialisation asynchronous to fix the problems
with firmware loading when the driver is linked to the kernel.

Luca removed unused channel_switch_beacon callbacks both from ath9k and
ath10k. Marek fixed Protected Management Frames (PMF) when using Action
Frames. Also we had other small fixes everywhere in the driver."

Along with that, there are a handful of updates to a variety
of drivers.  This includes updates to at76c50x-usb, ath9k, b43,
brcmfmac, mwifiex, rsi, rtlwifi, and wil6210.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Ideally, we would need to generate IP ID using a per destination IP
generator.

linux kernels used inet_peer cache for this purpose, but this had a huge
cost on servers disabling MTU discovery.

1) each inet_peer struct consumes 192 bytes

2) inetpeer cache uses a binary tree of inet_peer structs,
   with a nominal size of ~66000 elements under load.

3) lookups in this tree are hitting a lot of cache lines, as tree depth
   is about 20.

4) If server deals with many tcp flows, we have a high probability of
   not finding the inet_peer, allocating a fresh one, inserting it in
   the tree with same initial ip_id_count, (cf secure_ip_id())

5) We garbage collect inet_peer aggressively.

IP ID generation do not have to be 'perfect'

Goal is trying to avoid duplicates in a short period of time,
so that reassembly units have a chance to complete reassembly of
fragments belonging to one message before receiving other fragments
with a recycled ID.

We simply use an array of generators, and a Jenkin hash using the dst IP
as a key.

ipv6_select_ident() is put back into net/ipv6/ip6_output.c where it
belongs (it is only used from this file)

secure_ip_id() and secure_ipv6_id() no longer are needed.

Rename ip_select_ident_more() to ip_select_ident_segs() to avoid
unnecessary decrement/increment of the number of segments.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Make of_mdiobus_link_phydev externally available.
This fixes CONFIG_OF_MDIO=m.
Signed-off-by: NDaniel Mack <zonque@gmail.com>
Reported-by: NStephen Rothwell <sfr@canb.auug.org.au>
Fixes: 86f6cf41 ("net: of_mdio: add of_mdiobus_link_phydev()")
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use int rather than u32 to fix the following warning:

drivers/of/of_mdio.c:147 of_mdiobus_register() warn: unsigned 'addr' is
never less than zero.
Signed-off-by: NDaniel Mack <zonque@gmail.com>
Fixes: 8f838288 ("net: of_mdio: factor out code to parse a phy's 'reg' property")
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Alexander Duyck says:

====================
Provide common means for device address sync

The following series implements a means for synchronizing both unicast and
multicast addresses on a device interface.  The code is based on the original
implementation of dev_uc_sync that was available for syncing a VLAN to the
lower dev.

The original reason for coming up for this patch is a driver that is still in
the early stages of development.  The nearest driver I could find that
appeared to have the same limitations as the driver I was working on was the
Cisco enic driver.  For this reason I chose it as the first driver to make use
of this interface publicly.

However, I do not have a Cisco enic interface so I have only been able to
compile test any changes made to the driver.  I tried to keep this change as
simple as possible to avoid any issues.  Any help with testing would be
greatly appreciated.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change updates the enic driver to make use of __dev_uc_sync and
__dev_mc_sync calls.  Previously the driver was doing its own list
management by storing the mc_addr and uc_addr list in a 32 address array.
With this change the sync data is stored in the netdev_addr_list structures
and instead we just track how many addresses we have written to the device.
When we encounter 32 we stop and print a message as occurred previously with
the old approach.

Other than the core change the only other bit needed was to propagate the
constant attribute with the MAC address as there were several spots where
is twas only passed as a u8 * instead of a const u8 *.

This patch is meant to maintain the original functionality without the use
of the mc_addr and uc_addr arrays.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Acked-by: NGovindarajulu Varadarajan <_govind@gmx.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change provides a function to be used in order to break the
ndo_set_rx_mode call into a set of address add and remove calls.  The code
is based on the implementation of dev_uc_sync/dev_mc_sync.  Since they
essentially do the same thing but with only one dev I simply named my
functions __dev_uc_sync/__dev_mc_sync.

I also implemented an unsync version of the functions as well to allow for
cleanup on close.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Alexander Aring says:

====================
6lowpan: fragmentation fixes

This patch series fix the 6LoWPAN fragmentation which are in two cases broken.

The first case is if we have exactly two 6LoWPAN fragments only. This is fixed
by patch "6lowpan_rtnl: fix fragmentation with two fragments".
The second case is a off by one issue if we have payload which hits the fragment
boundary.

Both issues are introduced by commit d4b2816d
("6lowpan: fix fragmentation").
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch fix a off by one error while fragmentation. If the frag_cap
value is equal to skb_unprocessed value we need to stop the
fragmentation loop because the last fragment which has a size of
skb_unprocessed fits into the frag capability size.

This issue was introduced by commit d4b2816d
("6lowpan: fix fragmentation").
Signed-off-by: NAlexander Aring <alex.aring@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch fix the 6LoWPAN fragmentation for the case if we have exactly
two fragments. The problem is that the (skb_unprocessed >= frag_cap)
condition is always false on the second fragment after sending the first
fragment. A fragmentation with only one fragment doesn't make any sense.
The solution is that we use a do while loop here, that ensures we sending
always a minimum of two fragments if we need a fragmentation.

This issue was introduced by commit d4b2816d
("6lowpan: fix fragmentation").
Signed-off-by: NAlexander Aring <alex.aring@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The following patch removed unnecessary spin_lock/unlock calls
in ethtool_ops callback functions. In the second and final version
of the patch one spin_lock call was left behind.

commit cab6715c
Author: Yang Wei <Wei.Yang@windriver.com>
Date:   Sun May 25 09:53:44 2014 +0800

    net: driver: stmicro: Remove some useless the lock protection

This introduced the following sparse warning:

drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c:424:1: warning:
	context imbalance in 'stmmac_get_pauseparam' -
	different lock contexts for basic block
Signed-off-by: NEmil Goode <emilgoode@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

the local variable ops and n_ops were just read out from family,
and not changed, hence no need to assign back.

Validation functions should operate on const parameters and not
change anything.
Signed-off-by: NCheng Renquan <crquan@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-next into for-davem

This reverts commit 70a640d0.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We shouldn't be using regulator_get_optional() here. These
regulators are always present as part of the physical design and
there isn't any way to use an internal regulator or change the
source of the reference voltage via software. Given that the only
users of this driver in the kernel are DT based, this change
should be transparent to them even if they don't specify any
supplies because the regulator framework will insert dummy
supplies as needed.

Cc: Nishanth Menon <nm@ti.com>
Cc: Mark Brown <broonie@kernel.org>
Signed-off-by: NStephen Boyd <sboyd@codeaurora.org>
Reviewed-by: NMark Brown <broonie@linaro.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Daniel Borkmann says:

====================
BPF + test suite updates

These are the last bigger BPF changes that I had in my todo
queue for now. As the first two patches from this series
contain additional test cases for the test suite, I have
rebased them on top of current net-next with the set from [1]
applied to avoid introducing any unnecessary merge conflicts.

For details, please refer to the individual patches. Test
suite runs fine with the set applied.

 [1] http://patchwork.ozlabs.org/patch/352599/
     http://patchwork.ozlabs.org/patch/352600/
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit 9739eef1 ("net: filter: make BPF conversion more readable")
started to introduce helper macros similar to BPF_STMT()/BPF_JUMP()
macros from classic BPF.

However, quite some statements in the filter conversion functions
remained in the old style which gives a mixture of block macros and
non block macros in the code. This patch makes the block macros itself
more readable by using explicit member initialization, and converts
the remaining ones where possible to remain in a more consistent state.
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Acked-by: NAlexei Starovoitov <ast@plumgrid.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch finally allows us to get rid of the BPF_S_* enum.
Currently, the code performs unnecessary encode and decode
workarounds in seccomp and filter migration itself when a filter
is being attached in order to overcome BPF_S_* encoding which
is not used anymore by the new interpreter resp. JIT compilers.

Keeping it around would mean that also in future we would need
to extend and maintain this enum and related encoders/decoders.
We can get rid of all that and save us these operations during
filter attaching. Naturally, also JIT compilers need to be updated
by this.

Before JIT conversion is being done, each compiler checks if A
is being loaded at startup to obtain information if it needs to
emit instructions to clear A first. Since BPF extensions are a
subset of BPF_LD | BPF_{W,H,B} | BPF_ABS variants, case statements
for extensions can be removed at that point. To ease and minimalize
code changes in the classic JITs, we have introduced bpf_anc_helper().

Tested with test_bpf on x86_64 (JIT, int), s390x (JIT, int),
arm (JIT, int), i368 (int), ppc64 (JIT, int); for sparc we
unfortunately didn't have access, but changes are analogous to
the rest.

Joint work with Alexei Starovoitov.
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Signed-off-by: NAlexei Starovoitov <ast@plumgrid.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Mircea Gherzan <mgherzan@gmail.com>
Cc: Kees Cook <keescook@chromium.org>
Acked-by: NChema Gonzalez <chemag@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This check tests that overloading BPF_LD | BPF_ABS with an
always invalid BPF extension, that is SKF_AD_MAX, fails to
make sure classic BPF behaviour is correct in filter checker.

Also, we add a test for loading at packet offset SKF_AD_OFF-1
which should pass the filter, but later on fail during runtime.
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Acked-by: NAlexei Starovoitov <ast@plumgrid.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Also add a test for the scratch memory store that first fills
all slots and then sucessively reads all of them back adding
up to A, and eventually returning A. This and the previous
M[] test with alternating fill/spill will detect possible JIT
errors on M[].
Suggested-by: NAlexei Starovoitov <ast@plumgrid.com>
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Acked-by: NAlexei Starovoitov <ast@plumgrid.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As commit 2796d0c6 ("bridge: Automatically manage port
promiscuous mode."), make the add_if use dev_set_allmulti
instead of dev_set_promiscuous, so when add_if failed, we
should do dev_set_allmulti(dev, -1).
Signed-off-by: NWang Weidong <wangweidong1@huawei.com>
Reviewed-by: NAmos Kong <akong@redhat.com>
Acked-by: NVlad Yasevich <vyasevic@redhat.com>
Acked-by: NStephen Hemminger <stephen@networkplumber.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This reverts commit 70a640d0
("net/mlx4_en: Use affinity hint") and commit
c8865b64 ("cpumask: Utility function
to set n'th cpu - local cpu first") because these changes break
the build when SMP is disabled amongst other things.
Reported-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We shouldn't be using regulator_get_optional() here. These
regulators are always present as part of the physical design and
there isn't any way to use an internal regulator or change the
source of the reference voltage via software. Given that the only
users of this driver in the kernel are DT based, this change
should be transparent to them even if they don't specify any
supplies because the regulator framework will insert dummy
supplies as needed.

Cc: Nishanth Menon <nm@ti.com>
Cc: Mark Brown <broonie@kernel.org>
Signed-off-by: NStephen Boyd <sboyd@codeaurora.org>
Reviewed-by: NMark Brown <broonie@linaro.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Amir Vadai says:

====================
cpumask,net: Affinity hint helper function

This patchset will set affinity hint to influence IRQs to be allocated on the
same NUMA node as the one where the card resides. As discussed in
http://www.spinics.net/lists/netdev/msg271497.html

If the number of IRQs allocated is greater than the number of local NUMA cores, all
local cores will be used first, and the rest of the IRQs will be on a remote
NUMA node.
If no NUMA support - IRQ's and cores will be mapped 1:1

Since the utility function to calculate the mapping could be useful in other mq
drivers in the kernel, it was added to cpumask.[ch]

This patchset was tested and applied on top of net-next since the first
consumer is a network device (mlx4_en).  Over commit 506724c4: "tg3: Override
clock, link aware and link idle mode during NVRAM dump"

I couldn't find a maintainer for cpumask.c, so only added the kernel mailing
list

Amir

Changes from V5:
- Moved the utility function from kernel/irq/manage.c to lib/cpumask.c, and
  renamed it's name accordingly to cpumask_set_cpu_local_first()
- Added some comments as Thomas Gleixner suggested
- Changed -EINVAL to -EAGAIN, that describes the error situtation better.

Changes from V4:
- Patch 1/2: irq: Utility function to get affinity_hint by policy
  Thank you Ben for the great review:
  - Moved the function it kernel/irq/manage.c since it could be useful for
    block mq devices
  - Fixed Typo's
  - Use cpumask_t * instead of cpumask_var_t in function header
  - Restructured the function to remove NULL assignment in a cpumask_var_t
  - Fix for offline local CPU's

Changes from V3:
- Patch 2/2: net/mlx4_en: Use affinity hint
  - somehow patch file was corrupted

Changes from V2:
- Patch 1/2: net: Utility function to get affinity_hint by policy
  - Fixed style issues

Changes from V1:
- Patch 1/2: net: Utility function to get affinity_hint by policy
  - Fixed error flow to return -EINVAL on error (thanks govind)
- Patch 2/2: net/mlx4_en: Use affinity hint
  - Set ring->affinity_hint to NULL on error

Changes from V0:
- Fixed small style issues
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The “affinity hint” mechanism is used by the user space
daemon, irqbalancer, to indicate a preferred CPU mask for irqs.
Irqbalancer can use this hint to balance the irqs between the
cpus indicated by the mask.

We wish the HCA to preferentially map the IRQs it uses to numa cores
close to it.  To accomplish this, we use cpumask_set_cpu_local_first(), that
sets the affinity hint according the following policy:
First it maps IRQs to “close” numa cores.  If these are exhausted, the
remaining IRQs are mapped to “far” numa cores.
Signed-off-by: NYuval Atias <yuvala@mellanox.com>
Signed-off-by: NAmir Vadai <amirv@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This function sets the n'th cpu - local cpu's first.
For example: in a 16 cores server with even cpu's local, will get the
following values:
cpumask_set_cpu_local_first(0, numa, cpumask) => cpu 0 is set
cpumask_set_cpu_local_first(1, numa, cpumask) => cpu 2 is set
...
cpumask_set_cpu_local_first(7, numa, cpumask) => cpu 14 is set
cpumask_set_cpu_local_first(8, numa, cpumask) => cpu 1 is set
cpumask_set_cpu_local_first(9, numa, cpumask) => cpu 3 is set
...
cpumask_set_cpu_local_first(15, numa, cpumask) => cpu 15 is set

Curently this function will be used by multi queue networking devices to
calculate the irq affinity mask, such that as many local cpu's as
possible will be utilized to handle the mq device irq's.
Signed-off-by: NAmir Vadai <amirv@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>