If we want to use ct packets expr, and add a rule like follows:
  # nft add rule filter input ct packets gt 1 counter

We will find that no packets will hit it, because
nf_conntrack_acct is disabled by default. So It will
not work until we enable it manually via
"echo 1 > /proc/sys/net/netfilter/nf_conntrack_acct".

This is not friendly, so like xt_connbytes do, if the user
want to use ct byte/packet expr, enable nf_conntrack_acct
automatically.
Signed-off-by: Liping Zhang <liping.zhang@spreadtrum.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

physdev_mt() will check skb->nf_bridge first, which was alloced in
br_nf_pre_routing. So if we want to use --physdev-out and physdev-is-out,
we need to match it in FORWARD or POSTROUTING chain. physdev_mt_check()
only checked physdev-out and missed physdev-is-out. Fix it and update the
debug message to make it clearer.
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Marcelo R Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

It did use a fixed-size bucket list plus single lock to protect add/del.

Unlike the main conntrack table we only need to add and remove keys.
Convert it to rhashtable to get table autosizing and per-bucket locking.

The maximum number of entries is -- as before -- tied to the number of
conntracks so we do not need another upperlimit.

The change does not handle rhashtable_remove_fast error, only possible
"error" is -ENOENT, and that is something that can happen legitimetely,
e.g. because nat module was inserted at a later time and no src manip
took place yet.

Tested with http-client-benchmark + httpterm with DNAT and SNAT rules
in place.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

The nat extension structure is 32bytes in size on x86_64:

struct nf_conn_nat {
        struct hlist_node          bysource;             /*     0    16 */
        struct nf_conn *           ct;                   /*    16     8 */
        union nf_conntrack_nat_help help;                /*    24     4 */
        int                        masq_index;           /*    28     4 */
        /* size: 32, cachelines: 1, members: 4 */
        /* last cacheline: 32 bytes */
};

The hlist is needed to quickly check for possible tuple collisions
when installing a new nat binding. Storing this in the extension
area has two drawbacks:

1. We need ct backpointer to get the conntrack struct from the extension.
2. When reallocation of extension area occurs we need to fixup the bysource
   hash head via hlist_replace_rcu.

We can avoid both by placing the hlist_head in nf_conn and place nf_conn in
the bysource hash rather than the extenstion.

We can also remove the ->move support; no other extension needs it.

Moving the entire nat extension into nf_conn would be possible as well but
then we have to add yet another callback for deletion from the bysource
hash table rather than just using nat extension ->destroy hook for this.

nf_conn size doesn't increase due to aligment, followup patch replaces
hlist_node with single pointer.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

We don't need to acquire the bucket lock during early drop, we can
use lockless traveral just like ____nf_conntrack_find.

The timer deletion serves as synchronization point, if another cpu
attempts to evict same entry, only one will succeed with timer deletion.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

From: Liping Zhang <liping.zhang@spreadtrum.com>

Similar to ctnl_untimeout, when hash resize happened, we should try
to do unhelp from the 0# bucket again.
Signed-off-by: Liping Zhang <liping.zhang@spreadtrum.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

Imagine such situation, nf_conntrack_htable_size now is 4096, we are doing
ctnl_untimeout, and iterate on 3000# bucket.

Meanwhile, another user try to reduce hash size to 2048, then all nf_conn
are removed to the new hashtable. When this hash resize operation finished,
we still try to itreate ct begin from 3000# bucket, find nothing to do and
just return.

We may miss unlinking some timeout objects. And later we will end up with
invalid references to timeout object that are already gone.

So when we find that hash resize happened, try to unlink timeout objects
from the 0# bucket again.
Signed-off-by: Liping Zhang <liping.zhang@spreadtrum.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

When we do "cat /proc/net/nf_conntrack", and meanwhile resize the conntrack
hash table via /sys/module/nf_conntrack/parameters/hashsize, race will
happen, because reader can observe a newly allocated hash but the old size
(or vice versa). So oops will happen like follows：

  BUG: unable to handle kernel NULL pointer dereference at 0000000000000017
  IP: [<ffffffffa0418e21>] seq_print_acct+0x11/0x50 [nf_conntrack]
  Call Trace:
  [<ffffffffa0412f4e>] ? ct_seq_show+0x14e/0x340 [nf_conntrack]
  [<ffffffff81261a1c>] seq_read+0x2cc/0x390
  [<ffffffff812a8d62>] proc_reg_read+0x42/0x70
  [<ffffffff8123bee7>] __vfs_read+0x37/0x130
  [<ffffffff81347980>] ? security_file_permission+0xa0/0xc0
  [<ffffffff8123cf75>] vfs_read+0x95/0x140
  [<ffffffff8123e475>] SyS_read+0x55/0xc0
  [<ffffffff817c2572>] entry_SYSCALL_64_fastpath+0x1a/0xa4

It is very easy to reproduce this kernel crash.
1. open one shell and input the following cmds:
  while : ; do
    echo $RANDOM > /sys/module/nf_conntrack/parameters/hashsize
  done
2. open more shells and input the following cmds:
  while : ; do
    cat /proc/net/nf_conntrack
  done
3. just wait a monent, oops will happen soon.

The solution in this patch is based on Florian's Commit 5e3c61f9
("netfilter: conntrack: fix lookup race during hash resize"). And
add a wrapper function nf_conntrack_get_ht to get hash and hsize
suggested by Florian Westphal.
Signed-off-by: Liping Zhang <liping.zhang@spreadtrum.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

Merge tag 'mac80211-next-for-davem-2016-07-06' of git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next

Johannes Berg says:

====================
One more set of new features:
 * beacon report (for radio measurement) support in cfg80211/mac80211
 * hwsim: allow wmediumd in namespaces
 * mac80211: extend 160MHz workaround to CSA IEs
 * mesh: properly encrypt group-addressed privacy action frames
 * mesh: allow setting peer AID
 * first steps for MU-MIMO monitor mode
 * along with various other cleanups and improvements
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Remove .owner field since calls to module_platform_driver() will
set it automatically.
Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>

Conflicts:
	drivers/net/ethernet/mellanox/mlx5/core/en.h
	drivers/net/ethernet/mellanox/mlx5/core/en_main.c
	drivers/net/usb/r8152.c

All three conflicts were overlapping changes.
Signed-off-by: David S. Miller <davem@davemloft.net>

Pull networking fixes from David Miller:

 1) All users of AF_PACKET's fanout feature want a symmetric packet
    header hash for load balancing purposes, so give it to them.

 2) Fix vlan state synchronization in e1000e, from Jarod Wilson.

 3) Use correct socket pointer in ip_skb_dst_mtu(), from Shmulik
    Ladkani.

 4) mlx5 bug fixes from Mohamad Haj Yahia, Daniel Jurgens, Matthew
    Finlay, Rana Shahout, and Shaker Daibes.  Mostly to do with
    operation timeouts and PCI error handling.

 5) Fix checksum handling in mirred packet action, from WANG Cong.

 6) Set skb->dev correctly when transmitting in !protect_frames case of
    macsec driver, from Daniel Borkmann.

 7) Fix MTU calculation in geneve driver, from Haishuang Yan.

 8) Missing netif_napi_del() in unregister path of qeth driver, from
    Ursula Braun.

 9) Handle malformed route netlink messages in decnet properly, from
    Vergard Nossum.

10) Memory leak of percpu data in ipv6 routing code, from Martin KaFai
    Lau.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (41 commits)
  ipv6: Fix mem leak in rt6i_pcpu
  net: fix decnet rtnexthop parsing
  cxgb4: update latest firmware version supported
  net/mlx5: Avoid setting unused var when modifying vport node GUID
  bonding: fix enslavement slave link notifications
  r8152: fix runtime function for RTL8152
  qeth: delete napi struct when removing a qeth device
  Revert "fsl/fman: fix error handling"
  fsl/fman: fix error handling
  cdc_ncm: workaround for EM7455 "silent" data interface
  RDS: fix rds_tcp_init() error path
  geneve: fix max_mtu setting
  net: phy: dp83867: Fix initialization of PHYCR register
  enc28j60: Fix race condition in enc28j60 driver
  net: stmmac: Fix null-function call in ISR on stmmac1000
  tipc: fix nl compat regression for link statistics
  net: bcmsysport: Device stats are unsigned long
  macsec: set actual real device for xmit when !protect_frames
  net_sched: fix mirrored packets checksum
  packet: Use symmetric hash for PACKET_FANOUT_HASH.
  ...

Pablo Neira Ayuso says:

====================
Netfilter updates for net-next

The following patchset contains Netfilter updates for net-next,
they are:

1) Don't use userspace datatypes in bridge netfilter code, from
   Tobin Harding.

2) Iterate only once over the expectation table when removing the
   helper module, instead of once per-netns, from Florian Westphal.

3) Extra sanitization in xt_hook_ops_alloc() to return error in case
   we ever pass zero hooks, xt_hook_ops_alloc():

4) Handle NFPROTO_INET from the logging core infrastructure, from
   Liping Zhang.

5) Autoload loggers when TRACE target is used from rules, this doesn't
   change the behaviour in case the user already selected nfnetlink_log
   as preferred way to print tracing logs, also from Liping Zhang.

6) Conntrack slabs with SLAB_HWCACHE_ALIGN to allow rearranging fields
   by cache lines, increases the size of entries in 11% per entry.
   From Florian Westphal.

7) Skip zone comparison if CONFIG_NF_CONNTRACK_ZONES=n, from Florian.

8) Remove useless defensive check in nf_logger_find_get() from Shivani
   Bhardwaj.

9) Remove zone extension as place it in the conntrack object, this is
   always include in the hashing and we expect more intensive use of
   zones since containers are in place. Also from Florian Westphal.

10) Owner match now works from any namespace, from Eric Bierdeman.

11) Make sure we only reply with TCP reset to TCP traffic from
    nf_reject_ipv4, patch from Liping Zhang.

12) Introduce --nflog-size to indicate amount of network packet bytes
    that are copied to userspace via log message, from Vishwanath Pai.
    This obsoletes --nflog-range that has never worked, it was designed
    to achieve this but it has never worked.

13) Introduce generic macros for nf_tables object generation masks.

14) Use generation mask in table, chain and set objects in nf_tables.
    This allows fixes interferences with ongoing preparation phase of
    the commit protocol and object listings going on at the same time.
    This update is introduced in three patches, one per object.

15) Check if the object is active in the next generation for element
    deactivation in the rbtree implementation, given that deactivation
    happens from the commit phase path we have to observe the future
    status of the object.

16) Support for deletion of just added elements in the hash set type.

17) Allow to resize hashtable from /proc entry, not only from the
    obscure /sys entry that maps to the module parameter, from Florian
    Westphal.

18) Get rid of NFT_BASECHAIN_DISABLED, this code is not exercised
    anymore since we tear down the ruleset whenever the netdevice
    goes away.

19) Support for matching inverted set lookups, from Arturo Borrero.

20) Simplify the iptables_mangle_hook() by removing a superfluous
    extra branch.

21) Introduce ether_addr_equal_masked() and use it from the netfilter
    codebase, from Joe Perches.

22) Remove references to "Use netfilter MARK value as routing key"
    from the Netfilter Kconfig description given that this toggle
    doesn't exists already for 10 years, from Moritz Sichert.

23) Introduce generic NF_INVF() and use it from the xtables codebase,
    from Joe Perches.

24) Setting logger to NONE via /proc was not working unless explicit
    nul-termination was included in the string. This fixes seems to
    leave the former behaviour there, so we don't break backward.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Pull sound fixes from Takashi Iwai:
 "Here are a collection of small fixes: at this time, we've got a
  slightly high amount, but all small and trivial fixes, and nothing
  scary can be seen there"

* tag 'sound-4.7-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound: (21 commits)
  ALSA: hda/realtek: Add Lenovo L460 to docking unit fixup
  ALSA: timer: Fix negative queue usage by racy accesses
  ASoC: rt5645: fix reg-2f default value.
  ASoC: fsl_ssi: Fix number of words per frame for I2S-slave mode
  ALSA: au88x0: Fix calculation in vortex_wtdma_bufshift()
  ALSA: hda - Add PCI ID for Kabylake-H
  ALSA: echoaudio: Fix memory allocation
  ASoC: Intel: atom: fix missing breaks that would cause the wrong operation to execute
  ALSA: hda - fix read before array start
  ASoC: cx20442: set tty->receiver_room in v253_open
  ASoC: ak4613: Enable cache usage to fix crashes on resume
  ASoC: wm8940: Enable cache usage to fix crashes on resume
  ASoC: Intel: Skylake: Initialize module list for Broxton
  ASoC: wm5102: Correct supported channels on trace compressed DAI
  ASoC: wm5110: Add missing route from OUT3R to SYSCLK
  ASoC: rt5670: fix HP Playback Volume control
  ASoC: hdmi-codec: select CONFIG_HDMI
  ASoC: davinci-mcasp: Fix dra7 DMA offset when using CFG port
  ASoC: hdac_hdmi: Fix potential NULL dereference
  ASoC: ak4613: Remove owner assignment from platform_driver
  ...

Pull chrome platform fix from Olof Johansson:
 "A single fix this time, closing a window where ioctl args are fetched
  twice"

* tag 'chrome-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/olof/chrome-platform:
  platform/chrome: cros_ec_dev - double fetch bug in ioctl

Previously, mesh power management functionality works only with kernel
MPM. Because user space MPM did not report mesh peer AID to kernel,
the kernel could not identify the bit in TIM element. So this patch
adds mesh peer AID setting API.
Signed-off-by: Masashi Honma <masashi.honma@gmail.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

Continuing the workaround implemented in commit 23665aaf
("mac80211: Interoperability workaround for 80+80 and 160 MHz channels")
use the same code to parse the Wide Bandwidth Channel Switch element
by converting to VHT Operation element since the spec also just refers
to that for parsing semantics, particularly with the workaround.

While at it, remove some dead code - the IEEE80211_STA_DISABLE_40MHZ
flag can never be set at this point since it's checked earlier and the
wide_bw_chansw_ie pointer is set to NULL if it's set.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

Rather than reporting the scan as having completed, report it as
being aborted.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

Add the following to support beacon report radio measurement
with the measurement mode field set to passive or active:
1. Propagate the required scan duration to the device
2. Report the scan start time (in terms of TSF)
3. Report each BSS's detection time (also in terms of TSF)

TSF times refer to the BSS that the interface that requested the
scan is connected to.
Signed-off-by: Assaf Krauss <assaf.krauss@intel.com>
Signed-off-by: Avraham Stern <avraham.stern@intel.com>
[changed ath9k/10k, at76c59x-usb, iwlegacy, wl1251 and wlcore to match
the new API]
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

Beacon report radio measurement requires reporting observed BSSs
on the channels specified in the beacon request. If the measurement
mode is set to passive or active, it requires actually performing a
scan (passive or active, accordingly), and reporting the time that
the scan was started and the time each beacon/probe was received
(both in terms of TSF of the BSS of the requesting AP). If the
request mode is table, this information is optional.
In addition, the radio measurement request specifies the channel
dwell time for the measurement.

In order to use scan for beacon report when the mode is active or
passive, add a parameter to scan request that specifies the
channel dwell time, and add scan start time and beacon received time
to scan results information.

Supporting beacon report is required for Multi Band Operation (MBO).
Signed-off-by: Assaf Krauss <assaf.krauss@intel.com>
Signed-off-by: David Spinadel <david.spinadel@intel.com>
Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

The API expects a pointer to a signed int so we should not use an
unsigned int for it.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

Add radar_detect_widths to the interface combination that allows
concurrent P2P Device dedicated interface and AP interfaces, to enable
testing of radar detection when P2P Device interface is used.

Clear the radar_detect_widths in case of multi channel contexts
as this is not currently supported.

As radar_detect_widths are now supported in all combinations,
remove the hwsim_if_dfs_limits definition since it is no longer
needed.
Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

add API to support VHT MU-MIMO air sniffer.
in MU-MIMO there are parallel frames on the air while the HW
has only one RX.
add the capability to sniff one of the MU-MIMO parallel frames by
giving the sniffer additional information so it'll know which
of the parallel frames it shall follow.

Add attribute - NL80211_ATTR_MU_MIMO_GROUP_DATA - for getting
a MU-MIMO groupID in order to monitor packets from that group
using VHT MU-MIMO.
And add attribute -NL80211_ATTR_MU_MIMO_FOLLOW_ADDR - for passing
MAC address to monitor mode.
that option will be used by VHT MU-MIMO air sniffer to follow a
station according to it's MAC address using VHT MU-MIMO.
Signed-off-by: Aviya Erenfeld <aviya.erenfeld@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

The current implementation of handling ADDBA Request while a session
is already active with the peer is wrong - in case the peer is using
the existing session's dialog token this should be treated as update
to the session, which can update the timeout value.

We don't really have a good way of supporting that, so reject, but
implement the required behaviour in the spec of "Even if the updated
ADDBA Request frame is not accepted, the original Block ACK setup
remains active." (802.11-2012 10.5.4)
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

It was first reported and reproduced by Petr (thanks!) in
https://bugzilla.kernel.org/show_bug.cgi?id=119581

free_percpu(rt->rt6i_pcpu) used to always happen in ip6_dst_destroy().

However, after fixing a deadlock bug in
commit 9c7370a1 ("ipv6: Fix a potential deadlock when creating pcpu rt"),
free_percpu() is not called before setting non_pcpu_rt->rt6i_pcpu to NULL.

It is worth to note that rt6i_pcpu is protected by table->tb6_lock.

kmemleak somehow did not report it.  We nailed it down by
observing the pcpu entries in /proc/vmallocinfo (first suggested
by Hannes, thanks!).
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Fixes: 9c7370a1 ("ipv6: Fix a potential deadlock when creating pcpu rt")
Reported-by: Petr Novopashenniy <pety@rusnet.ru>
Tested-by: Petr Novopashenniy <pety@rusnet.ru>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Cc: Petr Novopashenniy <pety@rusnet.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>

dn_fib_count_nhs() could enter an infinite loop if nhp->rtnh_len == 0
(i.e. if userspace passes a malformed netlink message).

Let's use the helpers from net/nexthop.h which take care of all this
stuff. We can do exactly the same as e.g. fib_count_nexthops() and
fib_get_nhs() from net/ipv4/fib_semantics.c.

This fixes the softlockup for me.

Cc: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

We verify "u_cmd.outsize" and "u_cmd.insize" but we need to make sure
that those values have not changed between the two copy_from_user()
calls.  Otherwise it could lead to a buffer overflow.

Additionally, cros_ec_cmd_xfer() can set s_cmd->insize to a lower value.
We should use the new smaller value so we don't copy too much data to
the user.
Reported-by: Pengfei Wang <wpengfeinudt@gmail.com>
Fixes: a8411784 ('mfd: cros_ec: Use a zero-length array for command data')
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Tested-by: Gwendal Grignou <gwendal@chromium.org>
Cc: <stable@vger.kernel.org> # v4.2+
Signed-off-by: Olof Johansson <olof@lixom.net>

Change t4fw_version.h to update latest firmware version number
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

GCC complains on unused-but-set-variable, clean this up.

Fixes: 23898c76 ('net/mlx5: E-Switch, Modify node guid on vf set MAC')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Currently, link notifications are not sent by
bond_set_slave_link_state() upon enslavement if
the slave is enslaved when up.

This happens because slave->link default init value
is 0, which is the same as BOND_LINK_UP, resulting
in bond_set_slave_link_state() ignoring this transition.

This patch sets the default value of slave->link to
BOND_LINK_NOCHANGE, assuring it will count as a state
transition and thus trigger notification logic.
Signed-off-by: Aviv Heller <avivh@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Add support for PREROUTING rules with skb->dev set to the vrf device.
INPUT rules are already allowed. Provides symmetry with the output path
which allows POSTROUTING rules.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The Kconfig controlling build of this code is currently:

drivers/connector/Kconfig:config PROC_EVENTS
drivers/connector/Kconfig:      bool "Report process events to userspace"

...meaning that it currently is not being built as a module by anyone.
Lets remove the two modular references, so that when reading the driver
there is no doubt it is builtin-only.

Since module_init translates to device_initcall in the non-modular
case, the init ordering remains unchanged with this commit.

Cc: Evgeniy Polyakov <zbr@ioremap.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The RTL8152 doesn't have U1U2 and U2P3 features, so use different
runtime functions for RTL812 and RTL8153 by adding autosuspend_en()
to rtl_ops.
Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

In case of error, function devm_ioremap_resource() returns ERR_PTR()
and never returns NULL. The NULL test in the return value check should
be replaced with IS_ERR().
Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>

Jiri Pirko says:

====================
mlxsw: Implement IPV4 unicast routing

This patchset enables IPv4 unicast routing in the Mellanox Spectrum ASIC
switch driver. This builds upon the work that was done by a couple of
previous patchsets.

Patches 1,2,6 add a couple of dependencies outside the driver. Namely, the
ability to propagate ndo_neigh_construct()/destroy() through stacked devices and
a notification whenever DELAY_PROBE_TIME changes. When propagated down, the
ndos allow drivers to add and remove neighbour entries from their private
neighbour table. The DELAY_PROBE_TIME notification gives drivers the ability to
correctly configure their polling interval for neighbour activity, so that
active neighbour won't be marked as STALE.

Patches 3-5,7-8 add the neighbour offloading infrastructure, where patch 7 uses
the DELAY_PROBE_TIME notification in order to correctly configure the device's
polling interval. Patch 8 finally programs neighbours to the device's table
based on NEIGH_UPDATE notifications, so that directly connected routes can
be used.

Patches 9-16 build upon the previous patches and extend the router with
remote routes (nexthop) support.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Now, the driver sends arp probes for all unresolved neighbours that are
currently a nexthop for some route on the system. The job is set
periodically every 5 seconds.
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

For nexthop neighbours we need to make kernel to think there is a traffic
flowing to them preventing it from going to stale state. Otherwise
kernel would stale it and eventually the neigh would be removed from HW
and nexthop as well. That would reduce ECMP group in HW.
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Implement next-hop routing offload including ECMP. To make it possible,
introduce next-hop group entity. This entity keeps track of resolved
neighbours and updates HW adjacency table accordingly. Note that HW
next-hops are stored in this adjacency table, in form of MAC.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The RALEU register is used to mass update remote action adjacency index
and ecmp size.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The RATR register is used to configure the Router Adjacency (next-hop)
Table.
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>