remove useless blanks.

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
----
 include/net/inet_common.h |   55 ++++-------
 include/net/tcp.h         |  222 +++++++++++++++++-----------------------------
 include/net/udp.h         |   38 +++----
 3 files changed, 123 insertions(+), 192 deletions(-)
Signed-off-by: David S. Miller <davem@davemloft.net>

Reducing real_num_queues needs to flush the qdisc otherwise
skbs with queue_mappings greater then real_num_tx_queues can
be sent to the underlying driver.

The flow for this is,

dev_queue_xmit()
	dev_pick_tx()
		skb_tx_hash()  => hash using real_num_tx_queues
		skb_set_queue_mapping()
	...
	qdisc_enqueue_root() => enqueue skb on txq from hash
...
dev->real_num_tx_queues -= n
...
sch_direct_xmit()
	dev_hard_start_xmit()
		ndo_start_xmit(skb,dev) => skb queue set with old hash

skbs are enqueued on the qdisc with skb->queue_mapping set
0 < queue_mappings < real_num_tx_queues.  When the driver
decreases real_num_tx_queues skb's may be dequeued from the
qdisc with a queue_mapping greater then real_num_tx_queues.

This fixes a case in ixgbe where this was occurring with DCB
and FCoE. Because the driver is using queue_mapping to map
skbs to tx descriptor rings we can potentially map skbs to
rings that no longer exist.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Tested-by: Ross Brattain <ross.b.brattain@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

When calling qdisc_reset() the qdisc lock needs to be held.  In
this case there is at least one driver i4l which is using this
without holding the lock.  Add the locking here.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

add fast path for in-order fragments

As the fragments are sent in order in most of OSes, such as Windows, Darwin and
FreeBSD, it is likely the new fragments are at the end of the inet_frag_queue.
In the fast path, we check if the skb at the end of the inet_frag_queue is the
prev we expect.

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
----
 include/net/inet_frag.h |    1 +
 net/ipv4/ip_fragment.c  |   12 ++++++++++++
 net/ipv6/reassembly.c   |   11 +++++++++++
 3 files changed, 24 insertions(+)
Signed-off-by: David S. Miller <davem@davemloft.net>

/proc/net/snmp and /proc/net/netstat expose SNMP counters.

Width of these counters is either 32 or 64 bits, depending on the size
of "unsigned long" in kernel.

This means user program parsing these files must already be prepared to
deal with 64bit values, regardless of user program being 32 or 64 bit.

This patch introduces 64bit snmp values for IPSTAT mib, where some
counters can wrap pretty fast if they are 32bit wide.

# netstat -s|egrep "InOctets|OutOctets"
    InOctets: 244068329096
    OutOctets: 244069348848

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

'Shoul' must be 'should'.

Signed-off-by: Kulikov Vasiliy <segooon@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Determine the size of the xfrm_mark struct, not of its pointer.

Signed-off-by: Andreas Steffen <andreas.steffen@strongswan.org>
Acked-by: Jamal Hadi Salim <hadi@cyberus.ca>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch introduces the CAIF SPI Protocol Driver for
CAIF Link Layer.

This driver implements a platform driver to accommodate for a
platform specific SPI device. A general platform driver is not
possible as there are no SPI Slave side Kernel API defined.
A sample CAIF SPI Platform device can be found in
.../Documentation/networking/caif/spi_porting.txt

Signed-off-by: Sjur Braendeland <sjur.brandeland@stericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

don't clone skb when skb isn't shared

When the tcf_action is TC_ACT_STOLEN, and the skb isn't shared, we don't need
to clone a new skb. As the skb will be freed after this function returns, we
can use it freely once we get a reference to it.

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
----
 include/net/sch_generic.h |   11 +++++++++--
 net/sched/act_mirred.c    |    6 +++---
 2 files changed, 12 insertions(+), 5 deletions(-)
Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca>
Signed-off-by: David S. Miller <davem@davemloft.net>

Allows use of ECN when syncookies are in effect by encoding ecn_ok
into the syn-ack tcp timestamp.

While at it, remove a uneeded #ifdef CONFIG_SYN_COOKIES.
With CONFIG_SYN_COOKIES=nm want_cookie is ifdef'd to 0 and gcc
removes the "if (0)".

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

In preparation for 64bit snmp counters for some mibs,
add an 'align' parameter to snmp_mib_init(), instead
of assuming mibs only contain 'unsigned long' fields.

Callers can use __alignof__(type) to provide correct
alignment.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Herbert Xu <herbert@gondor.apana.org.au>
CC: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
CC: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
CC: Vlad Yasevich <vladislav.yasevich@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Check at rule install time that CT accounting is enabled. Force it
to be enabled if not while also emitting a warning since this is not
the default state.

This is in preparation for deprecating CONFIG_NF_CT_ACCT upon which
CONFIG_NETFILTER_XT_MATCH_CONNBYTES depended being set.

Added 2 CT accounting support functions:

nf_ct_acct_enabled() - Get CT accounting state.
nf_ct_set_acct() - Enable/disable CT accountuing.

Signed-off-by: Tim Gardner <tim.gardner@canonical.com>
Acked-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>

In preparation for a TX power setting interface in the nl80211, change the
.set_tx_power function to use mBm units instead of dBm for greater accuracy and
smaller power levels.

Also, already in advance move the tx_power_setting enumeration to nl80211.

This change affects the .tx_set_power function prototype. As a result, the
corresponding changes are needed to modules using it. These are mac80211,
iwmc3200wifi and rndis_wlan.

Cc: Samuel Ortiz <samuel.ortiz@intel.com>
Cc: Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
Signed-off-by: Juuso Oikarinen <juuso.oikarinen@nokia.com>
Acked-by: Samuel Ortiz <samuel.ortiz@intel.com>
Acked-by: Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
Signed-off-by: John W. Linville <linville@tuxdriver.com>

this patch is implementing IP_NODEFRAG option for IPv4 socket.
The reason is, there's no other way to send out the packet with user
customized header of the reassembly part.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Fix a typo in include/net/netlink.h
should be finalize instead of finanlize

Signed-off-by: Justin P. Mattock <justinmattock@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

commit aa2ea058 (tcp: fix outsegs stat for TSO segments) incorrectly
assumed SNMP_ADD_STATS() was used from BH context.

Fix this using mib[!in_softirq()] instead of mib[0]

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This mechanism introduced in this patch applies (at least) for hardware
designs using a single shared antenna for both WLAN and BT. In these designs,
the antenna must be toggled between WLAN and BT.

In those hardware, managing WLAN co-existence with Bluetooth requires WLAN
full power save whenever there is Bluetooth activity in order for WLAN to be
able to periodically relinquish the antenna to be used for BT. This is because
BT can only access the shared antenna when WLAN is idle or asleep.

Some hardware, for instance the wl1271, are able to indicate to the host
whenever there is BT traffic. In essence, the hardware will send an indication
to the host whenever there is, for example, SCO traffic or A2DP traffic, and
will send another indication when the traffic is over.

The hardware gets information of Bluetooth traffic via hardware co-existence
control lines - these lines are used to negotiate the shared antenna
ownership. The hardware will give the antenna to BT whenever WLAN is sleeping.

This patch adds the interface to mac80211 to facilitate temporarily disabling
of dynamic power save as per request of the WLAN driver. This interface will
immediately force WLAN to full powersave, hence allowing BT coexistence as
described above.

In these kind of shared antenna desings, when WLAN powersave is fully disabled,
Bluetooth will not work simultaneously with WLAN at all. This patch does not
address that problem. This interface will not change PSM state, so if PSM is
disabled it will remain so. Solving this problem requires knowledge about BT
state, and is best done in user-space.

Signed-off-by: Juuso Oikarinen <juuso.oikarinen@nokia.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>

Previously CAIF supported maximum transfer size of ~4050.
The transfer size is now calculated dynamically based on the
link layers mtu size.

Signed-off-by: Sjur <Braendeland@stericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

CAIF Remote File Manager may send or receive more than 4050 bytes.
Due to this The CAIF RFM service have to support segmentation.

Signed-off-by: Sjur <Braendeland@stericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Flow control is not used by all CAIF services.
The usage of flow control is now part of the gerneal
initialization function for CAIF Services.

Signed-off-by: Sjur <Braendeland@stericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2.6.34 introduced 'conntrack zones' to deal with cases where packets
from multiple identical networks are handled by conntrack/NAT. Packets
are looped through veth devices, during which they are NATed to private
addresses, after which they can continue normally through the stack
and possibly have NAT rules applied a second time.

This works well, but is needlessly complicated for cases where only
a single SNAT/DNAT mapping needs to be applied to these packets. In that
case, all that needs to be done is to assign each network to a seperate
zone and perform NAT as usual. However this doesn't work for packets
destined for the machine performing NAT itself since its corrently not
possible to configure SNAT mappings for the LOCAL_IN chain.

This patch adds a new INPUT chain to the NAT table and changes the
targets performing SNAT to be usable in that chain.

Example usage with two identical networks (192.168.0.0/24) on eth0/eth1:

iptables -t raw -A PREROUTING -i eth0 -j CT --zone 1
iptables -t raw -A PREROUTING -i eth0 -j MARK --set-mark 1
iptables -t raw -A PREROUTING -i eth1 -j CT --zone 2
iptabels -t raw -A PREROUTING -i eth1 -j MARK --set-mark 2

iptables -t nat -A INPUT       -m mark --mark 1 -j NETMAP --to 10.0.0.0/24
iptables -t nat -A POSTROUTING -m mark --mark 1 -j NETMAP --to 10.0.0.0/24
iptables -t nat -A INPUT       -m mark --mark 2 -j NETMAP --to 10.0.1.0/24
iptables -t nat -A POSTROUTING -m mark --mark 2 -j NETMAP --to 10.0.1.0/24

iptables -t raw -A PREROUTING -d 10.0.0.0/24 -j CT --zone 1
iptables -t raw -A OUTPUT     -d 10.0.0.0/24 -j CT --zone 1
iptables -t raw -A PREROUTING -d 10.0.1.0/24 -j CT --zone 2
iptables -t raw -A OUTPUT     -d 10.0.1.0/24 -j CT --zone 2

iptables -t nat -A PREROUTING -d 10.0.0.0/24 -j NETMAP --to 192.168.0.0/24
iptables -t nat -A OUTPUT     -d 10.0.0.0/24 -j NETMAP --to 192.168.0.0/24
iptables -t nat -A PREROUTING -d 10.0.1.0/24 -j NETMAP --to 192.168.0.0/24
iptables -t nat -A OUTPUT     -d 10.0.1.0/24 -j NETMAP --to 192.168.0.0/24

Signed-off-by: Patrick McHardy <kaber@trash.net>

In unix_skb_parms store pointers to struct pid and struct cred instead
of raw uid, gid, and pid values, then translate the credentials on
reception into values that are meaningful in the receiving processes
namespaces.

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Acked-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Start capturing not only the userspace pid, uid and gid values of the
sending process but also the struct pid and struct cred of the sending
process as well.

This is in preparation for properly supporting SCM_CREDENTIALS for
sockets that have different uid and/or pid namespaces at the different
ends.

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Acked-by: Serge E. Hallyn <serge@hallyn.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Use struct pid and struct cred to store the peer credentials on struct
sock.  This gives enough information to convert the peer credential
information to a value relative to whatever namespace the socket is in
at the time.

This removes nasty surprises when using SO_PEERCRED on socket
connetions where the processes on either side are in different pid and
user namespaces.

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Acked-by: Daniel Lezcano <daniel.lezcano@free.fr>
Acked-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Reorder the fields in scm_cookie so they pack better on 64bit.

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Acked-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Discard the ACK if we find options that do not match current sysctl
settings.

Previously it was possible to create a connection with sack, wscale,
etc. enabled even if the feature was disabled via sysctl.

Also remove an unneeded call to tcp_sack_reset() in
cookie_check_timestamp: Both call sites (cookie_v4_check,
cookie_v6_check) zero "struct tcp_options_received", hand it to
tcp_parse_options() (which does not change tcp_opt->num_sacks/dsack)
and then call cookie_check_timestamp().

Even if num_sacks/dsacks were changed, the structure is allocated on
the stack and after cookie_check_timestamp returns only a few selected
members are copied to the inet_request_sock.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

Addition of rcu_head to struct inet_peer added 16bytes on 64bit arches.

Thats a bit unfortunate, since old size was exactly 64 bytes.

This can be solved, using an union between this rcu_head an four fields,
that are normally used only when a refcount is taken on inet_peer.
rcu_head is used only when refcnt=-1, right before structure freeing.

Add a inet_peer_refcheck() function to check this assertion for a while.

We can bring back SLAB_HWCACHE_ALIGN qualifier in kmem cache creation.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

inetpeer currently uses an AVL tree protected by an rwlock.

It's possible to make most lookups use RCU

1) Add a struct rcu_head to struct inet_peer

2) add a lookup_rcu_bh() helper to perform lockless and opportunistic
lookup. This is a normal function, not a macro like lookup().

3) Add a limit to number of links followed by lookup_rcu_bh(). This is
needed in case we fall in a loop.

4) add an smp_wmb() in link_to_pool() right before node insert.

5) make unlink_from_pool() use atomic_cmpxchg() to make sure it can take
last reference to an inet_peer, since lockless readers could increase
refcount, even while we hold peers.lock.

6) Delay struct inet_peer freeing after rcu grace period so that
lookup_rcu_bh() cannot crash.

7) inet_getpeer() first attempts lockless lookup.
   Note this lookup can fail even if target is in AVL tree, but a
concurrent writer can let tree in a non correct form.
   If this attemps fails, lock is taken a regular lookup is performed
again.

8) convert peers.lock from rwlock to a spinlock

9) Remove SLAB_HWCACHE_ALIGN when peer_cachep is created, because
rcu_head adds 16 bytes on 64bit arches, doubling effective size (64 ->
128 bytes)
In a future patch, this is probably possible to revert this part, if rcu
field is put in an union to share space with rid, ip_id_count, tcp_ts &
tcp_ts_stamp. These fields being manipulated only with refcnt > 0.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The ps-qos latency handling is broken. It uses predetermined latency values
to select specific dynamic PS timeouts. With common AP configurations, these
values overlap with beacon interval and are therefore essentially useless
(for network latencies less than the beacon interval, PSM is disabled.)

This patch remedies the problem by replacing the predetermined network latency
values with one high value (1900ms) which is used to go trigger full psm. For
backwards compatibility, the value 2000ms is still mapped to a dynamic ps
timeout of 100ms.

Currently also the mac80211 internal value for storing user space configured
dynamic PSM values is incorrectly in the driver visible ieee80211_conf struct.
Move it to the ieee80211_local struct.

Signed-off-by: Juuso Oikarinen <juuso.oikarinen@nokia.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>

unify tcp flag macros: TCPHDR_FIN, TCPHDR_SYN, TCPHDR_RST, TCPHDR_PSH,
TCPHDR_ACK, TCPHDR_URG, TCPHDR_ECE and TCPHDR_CWR. TCBCB_FLAG_* are replaced
with the corresponding TCPHDR_*.

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
----
 include/net/tcp.h                      |   24 ++++++-------
 net/ipv4/tcp.c                         |    8 ++--
 net/ipv4/tcp_input.c                   |    2 -
 net/ipv4/tcp_output.c                  |   59 ++++++++++++++++-----------------
 net/netfilter/nf_conntrack_proto_tcp.c |   32 ++++++-----------
 net/netfilter/xt_TCPMSS.c              |    4 --
 6 files changed, 58 insertions(+), 71 deletions(-)
Signed-off-by: David S. Miller <davem@davemloft.net>

There is a circular locking dependency when configuring the
hardware ARP filters on association, occurring when flushing the mac80211
workqueue. This is what happens:

[   92.026800] =======================================================
[   92.030507] [ INFO: possible circular locking dependency detected ]
[   92.030507] 2.6.34-04781-g2b2c009 #85
[   92.030507] -------------------------------------------------------
[   92.030507] modprobe/5225 is trying to acquire lock:
[   92.030507]  ((wiphy_name(local->hw.wiphy))){+.+.+.}, at: [<ffffffff8105b5c0>] flush_workq
ueue+0x0/0xb0
[   92.030507]
[   92.030507] but task is already holding lock:
[   92.030507]  (rtnl_mutex){+.+.+.}, at: [<ffffffff812b9ce2>] rtnl_lock+0x12/0x20
[   92.030507]
[   92.030507] which lock already depends on the new lock.
[   92.030507]
[   92.030507]
[   92.030507] the existing dependency chain (in reverse order) is:
[   92.030507]
[   92.030507] -> #2 (rtnl_mutex){+.+.+.}:
[   92.030507]        [<ffffffff810761fb>] lock_acquire+0xdb/0x110
[   92.030507]        [<ffffffff81341754>] mutex_lock_nested+0x44/0x300
[   92.030507]        [<ffffffff812b9ce2>] rtnl_lock+0x12/0x20
[   92.030507]        [<ffffffffa022d47c>] ieee80211_assoc_done+0x6c/0xe0 [mac80211]
[   92.030507]        [<ffffffffa022f2ad>] ieee80211_work_work+0x31d/0x1280 [mac80211]

[   92.030507] -> #1 ((&local->work_work)){+.+.+.}:
[   92.030507]        [<ffffffff810761fb>] lock_acquire+0xdb/0x110
[   92.030507]        [<ffffffff8105a51a>] worker_thread+0x22a/0x370
[   92.030507]        [<ffffffff8105ecc6>] kthread+0x96/0xb0
[   92.030507]        [<ffffffff81003a94>] kernel_thread_helper+0x4/0x10
[   92.030507]
[   92.030507] -> #0 ((wiphy_name(local->hw.wiphy))){+.+.+.}:
[   92.030507]        [<ffffffff81075fdc>] __lock_acquire+0x1c0c/0x1d50
[   92.030507]        [<ffffffff810761fb>] lock_acquire+0xdb/0x110
[   92.030507]        [<ffffffff8105b60e>] flush_workqueue+0x4e/0xb0
[   92.030507]        [<ffffffffa023ff7b>] ieee80211_stop_device+0x2b/0xb0 [mac80211]
[   92.030507]        [<ffffffffa0231635>] ieee80211_stop+0x3e5/0x680 [mac80211]

The locking in this case is quite complex. Fix the problem by rewriting the
way the hardware ARP filter list is handled - i.e. make a copy of the address
list to the bss_conf struct, and provide that list to the hardware driver
when needed.

The current patch will enable filtering also in promiscuous mode. This may need
to be changed in the future.

Reported-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Juuso Oikarinen <juuso.oikarinen@nokia.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>

This patch adds support to nl80211 and mac80211 to set basic rates when
joining/creating ibss network.

Original patch was posted by Johannes Berg on the linux-wireless posting list.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Teemu Paasikivi <ext-teemu.3.paasikivi@nokia.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>

Allow drivers to sleep, and indicate this in
the documentation. ath9k has some locking I
don't understand, so keep it safe and disable
BHs in it, all other drivers look fine with
the context change.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>

The non-irqsafe aggregation start/stop done
callbacks are currently only used by ath9k_htc,
and can cause callbacks into the driver again.
This might lead to locking issues, which will
only get worse as we modify locking. To avoid
trouble, remove the non-irqsafe versions and
change ath9k_htc to use those instead.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>

gen_kill_estimator() API is incomplete or not well documented, since
caller should make sure an RCU grace period is respected before
freeing stats_lock.

This was partially addressed in commit 5d944c64
(gen_estimator: deadlock fix), but same problem exist for all
gen_kill_estimator() users, if lock they use is not already RCU
protected.

A code review shows xt_RATEEST.c, act_api.c, act_police.c have this
problem. Other are ok because they use qdisc lock, already RCU
protected.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

remove useless union keyword in rtable, rt6_info and dn_route.

Since there is only one member in a union, the union keyword isn't useful.

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

commit 66018506 (ip: Router Alert RCU conversion) introduced RCU
lookups to ip_call_ra_chain(). It missed proper deinit phase :
When ip_ra_control() deletes an ip_ra_chain, it should make sure
ip_call_ra_chain() users can not start to use socket during the rcu
grace period. It should also delay the sock_put() after the grace
period, or we risk a premature socket freeing and corruptions, as
raw sockets are not rcu protected yet.

This delay avoids using expensive atomic_inc_not_zero() in
ip_call_ra_chain().

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Use call_rcu rather than synchronize_rcu.

Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

NOTRACK makes all cpus share a cache line on nf_conntrack_untracked
twice per packet, slowing down performance.

This patch converts it to a per_cpu variable.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>

NOTRACK makes all cpus share a cache line on nf_conntrack_untracked
twice per packet. This is bad for performance.
__read_mostly annotation is also a bad choice.

This patch introduces IPS_UNTRACKED bit so that we can use later a
per_cpu untrack structure more easily.

A new helper, nf_ct_untracked_get() returns a pointer to
nf_conntrack_untracked.

Another one, nf_ct_untracked_status_or() is used by nf_nat_init() to add
IPS_NAT_DONE_MASK bits to untracked status.

nf_ct_is_untracked() prototype is changed to work on a nf_conn pointer.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>