nf_conntrack_lock is a monolithic lock and suffers from huge contention
on current generation servers (8 or more core/threads).

Perf locking congestion is clear on base kernel:

-  72.56%  ksoftirqd/6  [kernel.kallsyms]    [k] _raw_spin_lock_bh
   - _raw_spin_lock_bh
      + 25.33% init_conntrack
      + 24.86% nf_ct_delete_from_lists
      + 24.62% __nf_conntrack_confirm
      + 24.38% destroy_conntrack
      + 0.70% tcp_packet
+   2.21%  ksoftirqd/6  [kernel.kallsyms]    [k] fib_table_lookup
+   1.15%  ksoftirqd/6  [kernel.kallsyms]    [k] __slab_free
+   0.77%  ksoftirqd/6  [kernel.kallsyms]    [k] inet_getpeer
+   0.70%  ksoftirqd/6  [nf_conntrack]       [k] nf_ct_delete
+   0.55%  ksoftirqd/6  [ip_tables]          [k] ipt_do_table

This patch change conntrack locking and provides a huge performance
improvement.  SYN-flood attack tested on a 24-core E5-2695v2(ES) with
10Gbit/s ixgbe (with tool trafgen):

 Base kernel:   810.405 new conntrack/sec
 After patch: 2.233.876 new conntrack/sec

Notice other floods attack (SYN+ACK or ACK) can easily be deflected using:
 # iptables -A INPUT -m state --state INVALID -j DROP
 # sysctl -w net/netfilter/nf_conntrack_tcp_loose=0

Use an array of hashed spinlocks to protect insertions/deletions of
conntracks into the hash table. 1024 spinlocks seem to give good
results, at minimal cost (4KB memory). Due to lockdep max depth,
1024 becomes 8 if CONFIG_LOCKDEP=y

The hash resize is a bit tricky, because we need to take all locks in
the array. A seqcount_t is used to synchronize the hash table users
with the resizing process.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

Netfilter expectations are protected with the same lock as conntrack
entries (nf_conntrack_lock).  This patch split out expectations locking
to use it's own lock (nf_conntrack_expect_lock).
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

Preparation for disconnecting the nf_conntrack_lock from the
expectations code.  Once the nf_conntrack_lock is lifted, a race
condition is exposed.

The expectations master conntrack exp->master, can race with
delete operations, as the refcnt increment happens too late in
init_conntrack().  Race is against other CPUs invoking
->destroy() (destroy_conntrack()), or nf_ct_delete() (via timeout
or early_drop()).

Avoid this race in nf_ct_find_expectation() by using atomic_inc_not_zero(),
and checking if nf_ct_is_dying() (path via nf_ct_delete()).
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

One spinlock per cpu to protect dying/unconfirmed/template special lists.
(These lists are now per cpu, a bit like the untracked ct)
Add a @cpu field to nf_conn, to make sure we hold the appropriate
spinlock at removal time.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

Changes while reading through the netfilter code.

Added hint about how conntrack nf_conn refcnt is accessed.
And renamed repl_hash to reply_hash for readability
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

Via Simon Horman:

====================
* Whitespace cleanup spotted by checkpatch.pl from Tingwei Liu.
* Section conflict cleanup, basically removal of one wrong __read_mostly,
  from Andi Kleen.
====================
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

Add whitespace after operator and put open brace { on the previous line

Cc: Tingwei Liu <liutingwei@hisense.com>
Cc: lvs-devel@vger.kernel.org
Signed-off-by: Tingwei Liu <tingw.liu@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>

const __read_mostly does not make any sense, because const
data is already read-only. Remove the __read_mostly
for the ipvs genl_ops. This avoids a LTO
section conflict compile problem.

Cc: Wensong Zhang <wensong@linux-vs.org>
Cc: Simon Horman <horms@verge.net.au>
Cc: Patrick McHardy <kaber@trash.net>
Cc: lvs-devel@vger.kernel.org
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Simon Horman <horms@verge.net.au>

Adds a new property for hash set types, where if a set is created
with the 'forceadd' option and the set becomes full the next addition
to the set may succeed and evict a random entry from the set.

To keep overhead low eviction is done very simply. It checks to see
which bucket the new entry would be added. If the bucket's pos value
is non-zero (meaning there's at least one entry in the bucket) it
replaces the first entry in the bucket. If pos is zero, then it continues
down the normal add process.

This property is useful if you have a set for 'ban' lists where it may
not matter if you release some entries from the set early.
Signed-off-by: Josh Hunt <johunt@akamai.com>
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>

Commit 1785e8f4 ("netfiler: ipset: Add net namespace for ipset") moved
the initialization print into net_init, which can get called a lot due
to namespaces. Move it back into init, reduce to pr_info.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>

commit 2dfb973c0dcc6d2211 (add markmask for hash:ip,mark data type)
inserted IPSET_ATTR_MARKMASK in-between other enum values, i.e.
changing values of all further attributes.  This causes 'ipset list'
segfault on existing kernels since ipset no longer finds
IPSET_ATTR_MEMSIZE (it has a different value on kernel side).

Jozsef points out it should be moved below IPSET_ATTR_MARK which
works since there is some extra reserved space after that value.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>

Introduce packet mark mask for hash:ip,mark data type. This allows to
set mark bit filter for the ip set.

Change-Id: Id8dd9ca7e64477c4f7b022a1d9c1a5b187f1c96e
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>

Introduce packet mark support with new ip,mark hash set. This includes
userspace and kernelspace code, hash:ip,mark set tests and man page
updates.

The intended use of ip,mark set is similar to the ip:port type, but for
protocols which don't use a predictable port number. Instead of port
number it matches a firewall mark determined by a layer 7 filtering
program like opendpi.

As well as allowing or blocking traffic it will also be used for
accounting packets and bytes sent for each protocol.
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>

net/netfilter/ipset/ip_set_hash_netnet.c:115:8-9: WARNING: return of 0/1 in function 'hash_netnet4_data_list' with return type bool
/c/kernel-tests/src/cocci/net/netfilter/ipset/ip_set_hash_netnet.c:338:8-9: WARNING: return of 0/1 in function 'hash_netnet6_data_list' with return type bool

Return statements in functions returning bool should use
true/false instead of 1/0.
Generated by: coccinelle/misc/boolreturn.cocci
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>

ipset(8) for list:set says:
  The match will try to find a matching entry in the sets and the
  target will try to add an entry to the first set to which it can
  be added.

However real behavior is bit differ from described. Consider example:

 # ipset create test-1-v4 hash:ip family inet
 # ipset create test-1-v6 hash:ip family inet6
 # ipset create test-1 list:set
 # ipset add test-1 test-1-v4
 # ipset add test-1 test-1-v6

 # iptables  -A INPUT -p tcp --destination-port 25 -j SET --add-set test-1 src
 # ip6tables -A INPUT -p tcp --destination-port 25 -j SET --add-set test-1 src

And then when iptables/ip6tables rule matches packet IPSET target
tries to add src from packet to the list:set test-1 where first
entry is test-1-v4 and the second one is test-1-v6.

For IPv4, as it first entry in test-1 src added to test-1-v4
correctly, but for IPv6 src not added!

Placing test-1-v6 to the first element of list:set makes behavior
correct for IPv6, but brokes for IPv4.

This is due to result, returned from ip_set_add() and ip_set_del() from
net/netfilter/ipset/ip_set_core.c when set in list:set equires more
parameters than given or address families do not match (which is this
case).

It seems wrong returning 0 from ip_set_add() and ip_set_del() in
this case, as 0 should be returned only when an element successfuly
added/deleted to/from the set, contrary to ip_set_test() which
returns 0 when no entry exists and >0 when entry found in set.
Signed-off-by: Sergey Popovich <popovich_sergei@mail.ru>
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>

This allows us to store user comment strings, but it could be also
used to store any kind of information that the user application needs
to link to the rule.

Scratch 8 bits for the new ulen field that indicates the length the
user data area. 4 bits from the handle (so it's 42 bits long, according
to Patrick, it would last 139 years with 1000 new rules per second)
and 4 bits from dlen (so the expression data area is 4K, which seems
sufficient by now even considering the compatibility layer).
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: Patrick McHardy <kaber@trash.net>

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

Allow userspace to specify the queue number or the errno code for QUEUE
and DROP verdicts.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

Add a lockdep_nfnl_is_held() function and a nfnl_dereference() macro for
RCU dereferences protected by a NFNL subsystem mutex.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

The next patch will introduce a nfnl_dereference() macro that actually
checks that the appropriate mutex is held and therefore needs a
subsystem argument.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

This also adds NF_CT_LABELS_MAX_SIZE so it can be re-used
as BUILD_BUG_ON in nft_ct.

At this time, nft doesn't yet support writing to the label area;
when this changes the label->words handling needs to be moved
out of xt_connlabel.c into nf_conntrack_labels.c.

Also removes a useless run-time check: words cannot grow beyond
4 (32 bit) or 2 (64bit) since xt_connlabel enforces a maximum of
128 labels.
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

0-DAY kernel build testing backend reported:

sparse warnings: (new ones prefixed by >>)

 >> >> net/netfilter/xt_ipcomp.c:63:26: sparse: restricted __be16 degrades to integer
 >> >> net/netfilter/xt_ipcomp.c:63:26: sparse: cast to restricted __be32

Fix this by using ntohs without shifting.

Tested with: make C=1 CF=-D__CHECK_ENDIAN__
Signed-off-by: Fan Du <fan.du@windriver.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

This is C not shell script
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

Conflicts:
	drivers/net/bonding/bond_3ad.h
	drivers/net/bonding/bond_main.c

Two minor conflicts in bonding, both of which were overlapping
changes.
Signed-off-by: David S. Miller <davem@davemloft.net>

Pull drm fixes from Dave Airlie:
 "Lots of little small things, nothing too major: nouveau regression
  fixes, vmware fixes for the new hw support, memory leaks in error path
  fixes"

* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux: (31 commits)
  drm/radeon/ni: fix typo in dpm sq ramping setup
  drm/radeon/si: fix typo in dpm sq ramping setup
  drm/radeon: fix CP semaphores on CIK
  drm/radeon: delete a stray tab
  drm/radeon: fix display tiling setup on SI
  drm/radeon/dpm: reduce r7xx vblank mclk threshold to 200
  drm/radeon: fill in DRM_CAPs for cursor size
  drm: add DRM_CAPs for cursor size
  drm/radeon: unify bpc handling
  drm/ttm: Fix memory leak in ttm_agp_backend.c
  drm/ttm: declare 'struct device' in ttm_page_alloc.h
  drm/nouveau: fix TTM_PL_TT memtype on pre-nv50
  drm/nv50/disp: use correct register to determine DP display bpp
  drm/nouveau/fb: use correct ram oclass for nv1a hardware
  drm/nv50/gr: add missing nv_error parameter priv
  drm/nouveau: fix ENG_RUNLIST register address
  drm/nv4c/bios: disallow retrieving from prom on nv4x igp's
  drm/nv4c/vga: decode register is in a different place on nv4x igp's
  drm/nv4c/mc: nv4x igp's have a different msi rearm register
  drm/nouveau: set irq_enabled manually
  ...

Pull HID update from Jiri Kosina:

 - fixes for several bugs in incorrect allocations of buffers by David
   Herrmann and Benjamin Tissoires.

 - support for a few new device IDs by Archana Patni, Benjamin
   Tissoires, Huei-Horng Yo, Reyad Attiyat and Yufeng Shen

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid:
  HID: hyperv: make sure input buffer is big enough
  HID: Bluetooth: hidp: make sure input buffers are big enough
  HID: hid-sensor-hub: quirk for STM Sensor hub
  HID: apple: add Apple wireless keyboard 2011 JIS model support
  HID: fix buffer allocations
  HID: multitouch: add FocalTech FTxxxx support
  HID: microsoft: Add ID's for Surface Type/Touch Cover 2
  HID: usbhid: quirk for CY-TM75 75 inch Touch Overlay

Pull networking fixes from David Miller:

 1) kvaser CAN driver has fixed limits of some of it's table, validate
    that we won't exceed those limits at probe time.  Fix from Olivier
    Sobrie.

 2) Fix rtl8192ce disabling interrupts for too long, from Olivier
    Langlois.

 3) Fix botched shift in ath5k driver, from Dan Carpenter.

 4) Fix corruption of deferred packets in TIPC, from Erik Hugne.

 5) Fix newlink error path in macvlan driver, from Cong Wang.

 6) Fix netpoll deadlock in bonding, from Ding Tianhong.

 7) Handle GSO packets properly in forwarding path when fragmentation is
    necessary on egress, from Florian Westphal.

 8) Fix axienet build errors, from Michal Simek.

 9) Fix refcounting of ubufs on tx in vhost net driver, from Michael S
    Tsirkin.

10) Carrier status isn't set properly in hyperv driver, from Haiyang
    Zhang.

11) Missing pci_disable_device() in tulip_remove_one), from Ingo Molnar.

12) AF_PACKET qdisc bypass mode doesn't adhere to driver provided TX
    queue selection method.  Add a fallback method mechanism to fix this
    bug, from Daniel Borkmann.

13) Fix regression in link local route handling on GRE tunnels, from
    Nicolas Dichtel.

14) Bonding can assign dup aggregator IDs in some sequences of
    configuration, fix by making the allocation counter per-bond instead
    of global.  From Jiri Bohac.

15) sctp_connectx() needs compat translations, from Daniel Borkmann.

16) Fix of_mdio PHY interrupt parsing, from Ben Dooks

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (62 commits)
  MAINTAINERS: add entry for the PHY library
  of_mdio: fix phy interrupt passing
  net: ethernet: update dependency and help text of mvneta
  NET: fec: only enable napi if we are successful
  af_packet: remove a stray tab in packet_set_ring()
  net: sctp: fix sctp_connectx abi for ia32 emulation/compat mode
  ipv4: fix counter in_slow_tot
  irtty-sir.c: Do not set_termios() on irtty_close()
  bonding: 802.3ad: make aggregator_identifier bond-private
  usbnet: remove generic hard_header_len check
  gre: add link local route when local addr is any
  batman-adv: fix potential kernel paging error for unicast transmissions
  batman-adv: avoid double free when orig_node initialization fails
  batman-adv: free skb on TVLV parsing success
  batman-adv: fix TT CRC computation by ensuring byte order
  batman-adv: fix potential orig_node reference leak
  batman-adv: avoid potential race condition when adding a new neighbour
  batman-adv: properly check pskb_may_pull return value
  batman-adv: release vlan object after checking the CRC
  batman-adv: fix TT-TVLV parsing on OGM reception
  ...

Pull ARM fixes from Russell King:
 "A range of ARM fixes.  Biggest change is the stage-2 attributes used
  for for hyp mode which were wrong.  I've killed some bits in a couple
  of DT files which turned out not to be required, and a few other
  fixes.

  One fix touches code outside of arch/arm, which is related to sorting
  out the DMA masks correctly.  There is a long standing issue with the
  conversion from PFNs to addresses where people assume that shifting an
  unsigned long left by PAGE_SHIFT results in a correct address.  This
  is not the case with C: the integer promotion happens at assignment
  after evaluation.  This fixes the recently introduced dma_max_pfn()
  function, but there's a number of other places where we try this
  directly on an unsigned long in the mm code"

* 'fixes' of git://ftp.arm.linux.org.uk/~rmk/linux-arm:
  ARM: 7957/1: add DSB after icache flush in __flush_icache_all()
  Fix uses of dma_max_pfn() when converting to a limiting address
  ARM: 7955/1: spinlock: ensure we have a compiler barrier before sev
  ARM: 7953/1: mm: ensure TLB invalidation is complete before enabling MMU
  ARM: 7952/1: mm: Fix the memblock allocation for LPAE machines
  ARM: 7950/1: mm: Fix stage-2 device memory attributes
  ARM: dts: fix spdif pinmux configuration

Pull jfs fix from David Kleikamp:
 "Another ACL regression. This one more subtle"

* tag 'jfs-3.14-rc4' of git://github.com/kleikamp/linux-shaggy:
  jfs: set i_ctime when setting ACL

The only place this is used outside rtnetlink.c is veth. So provide
wrapper function for this usage.
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>

It's slightly smaller/faster for some architectures.
Make sure def_multicast_addr is __aligned(2)
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The PHY library has been subject to some changes, new drivers and DT
interactions over the past few months. Add myself as a maintainer for
the core PHY library parts and drivers. Make sure the PHY library entry
also covers the Device Tree files which have a close interaction with
the MDIO bus, PHY connection and Ethernet PHY mode parsing.

CC: Grant Likely <grant.likely@linaro.org>
CC: Shaohui Xie <shaohui.xie@freescale.com>
CC: Andy Fleming <afleming@gmail.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The of_mdiobus_register_phy() is not setting phy->irq thus causing
some drivers to incorrectly assume that the PHY does not have an
IRQ associated with it. Not only do some drivers report no IRQ
they do not install an interrupt handler for the PHY.

Simplify the code setting irq and set the phy->irq at the same
time so that we cover the following issues, which should cover
all the cases the code will find:

- Set phy->irq if node has irq property and mdio->irq is NULL
- Set phy->irq if node has no irq and mdio->irq is not NULL
- Leave phy->irq as PHY_POLL default if none of the above

This fixes the issue:
 net eth0: attached PHY 1 (IRQ -1) to driver Micrel KSZ8041RNLI

to the correct:
 net eth0: attached PHY 1 (IRQ 416) to driver Micrel KSZ8041RNLI
Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>

These include are here since kernel 2.2.7, but probably never used.
Signed-off-by: Florent Fourcot <florent.fourcot@enst-bretagne.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>

phy_set_csma_params has a redundant (and impossible) check for
"retries", found by smatch. The check was supposed to be for
frame_retries, but wasn't moved during development when
phy_set_frame_retries was introduced. Also, maxBE >= 3 as required by
the standard is not enforced.

Remove the redundant check, assure max_be >= 3 and check -1 <=
frame_retries <= 7 in the correct function.
Signed-off-by: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

With the introduction of the support for Armada 375 and Armada 38x,
the hidden Kconfig option MACH_ARMADA_370_XP is being renamed to
MACH_MVEBU_V7. Therefore, the dependency that was used for the mvneta
driver can no longer work. This commit replaces this dependency by a
dependency on PLAT_ORION, which is used similarly for the mv643xx_eth
driver.

In addition to this, it takes this opportunity to adjust the
description and help text to indicate that the driver can is also used
for Armada 38x. Note that Armada 375 cannot use this driver as it has
a completely different networking unit, which will require a separate
driver.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Acked-by: Jason Cooper <jason@lakedaemon.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

If napi is left enabled after a failed attempt to bring the interface
up, we BUG:

fec 2188000.ethernet eth0: no PHY, assuming direct connection to switch
libphy: PHY fixed-0:00 not found
fec 2188000.ethernet eth0: could not attach to PHY
------------[ cut here ]------------
kernel BUG at include/linux/netdevice.h:502!
Internal error: Oops - BUG: 0 [#1] SMP ARM
...
PC is at fec_enet_open+0x4d0/0x500
LR is at __dev_open+0xa4/0xfc

Only enable napi after we are past all the failure paths.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>

At first glance it looks like there is a missing curly brace but
actually the code works the same either way.  I have adjusted the
indenting but left the code the same.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>