sendmsg() (or sendto()) with MSG_FASTOPEN is a combo of connect(2)
and write(2). The application should replace connect() with it to
send data in the opening SYN packet.

For blocking socket, sendmsg() blocks until all the data are buffered
locally and the handshake is completed like connect() call. It
returns similar errno like connect() if the TCP handshake fails.

For non-blocking socket, it returns the number of bytes queued (and
transmitted in the SYN-data packet) if cookie is available. If cookie
is not available, it transmits a data-less SYN packet with Fast Open
cookie request option and returns -EINPROGRESS like connect().

Using MSG_FASTOPEN on connecting or connected socket will result in
simlar errno like repeating connect() calls. Therefore the application
should only use this flag on new sockets.

The buffer size of sendmsg() is independent of the MSS of the connection.
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Update the references to bridge utilities and web pages
to current locations
Signed-off-by: NStephen Hemminger <shemminger@vyatta.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Implement the RFC 5691 mitigation against Blind
Reset attack using RST bit.

Idea is to validate incoming RST sequence,
to match RCV.NXT value, instead of previouly accepted
window : (RCV.NXT <= SEG.SEQ < RCV.NXT+RCV.WND)

If sequence is in window but not an exact match, send
a "challenge ACK", so that the other part can resend an
RST with the appropriate sequence.

Add a new sysctl, tcp_challenge_ack_limit, to limit
number of challenge ACK sent per second.

Add a new SNMP counter to count number of challenge acks sent.
(netstat -s | grep TCPChallengeACK)
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Kiran Kumar Kella <kkiran@broadcom.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This introduce TSQ (TCP Small Queues)

TSQ goal is to reduce number of TCP packets in xmit queues (qdisc &
device queues), to reduce RTT and cwnd bias, part of the bufferbloat
problem.

sk->sk_wmem_alloc not allowed to grow above a given limit,
allowing no more than ~128KB [1] per tcp socket in qdisc/dev layers at a
given time.

TSO packets are sized/capped to half the limit, so that we have two
TSO packets in flight, allowing better bandwidth use.

As a side effect, setting the limit to 40000 automatically reduces the
standard gso max limit (65536) to 40000/2 : It can help to reduce
latencies of high prio packets, having smaller TSO packets.

This means we divert sock_wfree() to a tcp_wfree() handler, to
queue/send following frames when skb_orphan() [2] is called for the
already queued skbs.

Results on my dev machines (tg3/ixgbe nics) are really impressive,
using standard pfifo_fast, and with or without TSO/GSO.

Without reduction of nominal bandwidth, we have reduction of buffering
per bulk sender :
< 1ms on Gbit (instead of 50ms with TSO)
< 8ms on 100Mbit (instead of 132 ms)

I no longer have 4 MBytes backlogged in qdisc by a single netperf
session, and both side socket autotuning no longer use 4 Mbytes.

As skb destructor cannot restart xmit itself ( as qdisc lock might be
taken at this point ), we delegate the work to a tasklet. We use one
tasklest per cpu for performance reasons.

If tasklet finds a socket owned by the user, it sets TSQ_OWNED flag.
This flag is tested in a new protocol method called from release_sock(),
to eventually send new segments.

[1] New /proc/sys/net/ipv4/tcp_limit_output_bytes tunable
[2] skb_orphan() is usually called at TX completion time,
  but some drivers call it in their start_xmit() handler.
  These drivers should at least use BQL, or else a single TCP
  session can still fill the whole NIC TX ring, since TSQ will
  have no effect.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Dave Taht <dave.taht@bufferbloat.net>
Cc: Tom Herbert <therbert@google.com>
Cc: Matt Mathis <mattmathis@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Nandita Dukkipati <nanditad@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

URLs to neterion.com and s2io.com no longer resolve.  Remove all references to
these URLs in the driver source and documentation.
Signed-off-by: NJon Mason <jdmason@kudzu.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch updates the stmmac's documentation adding
some missing files in the section used to describe the
internal driver's structure.

Also the patch adds a new section to describe the EEE support.
Signed-off-by: NGiuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Update drawing and remove description of old features.
Add HSI and USB link layers to the drawing.
Reported-by: NJoerg Reisenweber <joerg.reisenweber@stericssion.com>
Signed-off-by: NSjur Brændeland <sjur.brandeland@stericssion.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NOliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: NMarc Kleine-Budde <mkl@pengutronix.de>

Added additional counters in a bat_stats structure, which are exported
through the ethtool api. The counters are specific to batman-adv and
includes:
 forwarded packets and bytes
 management packets and bytes (aggregated OGMs at this point)
 translation table packets

New counters are added by extending "enum bat_counters" in types.h and
adding corresponding  descriptive string(s) to bat_counters_strings in
soft-iface.c.

Counters are increased by calling batadv_add_counter() and incremented
by one by calling batadv_inc_counter().
Signed-off-by: NMartin Hundebøll <martin@hundeboll.net>
Signed-off-by: NSven Eckelmann <sven@narfation.org>

Routing of 127/8 is tradtionally forbidden, we consider
packets from that address block martian when routing and do
not process corresponding ARP requests.

This is a sane default but renders a huge address space
practically unuseable.

The RFC states that no address within the 127/8 block should
ever appear on any network anywhere but it does not forbid
the use of such addresses outside of the loopback device in
particular. For example to address a pool of virtual guests
behind a load balancer.

This patch adds a new interface option 'route_localnet'
enabling routing of the 127/8 address block and processing
of ARP requests on a specific interface.

Note that for the feature to work, the default local route
covering 127/8 dev lo needs to be removed.

Example:
  $ sysctl -w net.ipv4.conf.eth0.route_localnet=1
  $ ip route del 127.0.0.0/8 dev lo table local
  $ ip addr add 127.1.0.1/16 dev eth0
  $ ip route flush cache

V2: Fix invalid check to auto flush cache (thanks davem)
Signed-off-by: NThomas Graf <tgraf@suug.ch>
Acked-by: NNeil Horman <nhorman@tuxdriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fixed the driver's documentation that was obsolete and didn't
report new platform fields (recently added).
Signed-off-by: NGiuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As Heinz-Juergen Oertel pointed out 'CAN error frames' are a already defined
term for the CAN protocol violation indication on the wire.

To avoid confusion with the error messages created by CAN drivers available
via CAN RAW sockets update the documentation and change the naming from
'error frames' to 'error messages' or 'error message frames'.
Signed-off-by: NOliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: NMarc Kleine-Budde <mkl@pengutronix.de>

The support for CONFIG_MCA is being removed, since the 20
year old hardware simply isn't capable of meeting today's
software demands on CPU and memory resources.

This commit removes any MCA specific net drivers, and removes
any MCA specific probe/support code from drivers that were
doing a dual ISA/MCA role.

Cc: "David S. Miller" <davem@davemloft.net>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: netdev@vger.kernel.org
Signed-off-by: NPaul Gortmaker <paul.gortmaker@windriver.com>

Update the documentation according to latest changes.
Signed-off-by: NAlexander Smirnov <alex.bluesman.smirnov@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This represents the mass deletion of the of the tokenring support.

It gets rid of:
  - the net/tr.c which the drivers depended on
  - the drivers/net component
  - the Kbuild infrastructure around it
  - any tokenring related CONFIG_ settings in any defconfigs
  - the tokenring headers in the include/linux dir
  - the firmware associated with the tokenring drivers.
  - any associated token ring documentation.
Signed-off-by: NPaul Gortmaker <paul.gortmaker@windriver.com>

- Add routing_algo

- Remove date from README:
The date has to be updated when a patch touches the README. Therefore, nearly
every feature will modify this date. It can happens quite often that not only
one feature is currently in development or waiting on the mailinglist. This
creates merge conflicts when applying a patchset.

The date itself doesn't provide any additional information when this file is
only available in a release tarball or as part of a SCM repository.
Signed-off-by: NSven Eckelmann <sven@narfation.org>
Signed-off-by: NAntonio Quartulli <ordex@autistici.org>

if net.bridge.bridge-nf-filter-vlan-tagged sysctl is enabled, bridge
netfilter removes the vlan header temporarily and then feeds the packet
to ip(6)tables.

When the new "bridge-nf-pass-vlan-input-device" sysctl is on
(default off), then bridge netfilter will also set the
in-interface to the vlan interface; if such an interface exists.

This is needed to make iptables REDIRECT target work with
"vlan-on-top-of-bridge" setups and to allow use of "iptables -i" to
match the vlan device name.

Also update Documentation with current brnf default settings.
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Acked-by: NBart De Schuymer <bdschuym@pandora.be>
Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>

tcp_adv_win_scale default value is 2, meaning we expect a good citizen
skb to have skb->len / skb->truesize ratio of 75% (3/4)

In 2.6 kernels we (mis)accounted for typical MSS=1460 frame :
1536 + 64 + 256 = 1856 'estimated truesize', and 1856 * 3/4 = 1392.
So these skbs were considered as not bloated.

With recent truesize fixes, a typical MSS=1460 frame truesize is now the
more precise :
2048 + 256 = 2304. But 2304 * 3/4 = 1728.
So these skb are not good citizen anymore, because 1460 < 1728

(GRO can escape this problem because it build skbs with a too low
truesize.)

This also means tcp advertises a too optimistic window for a given
allocated rcvspace : When receiving frames, sk_rmem_alloc can hit
sk_rcvbuf limit and we call tcp_prune_queue()/tcp_collapse() too often,
especially when application is slow to drain its receive queue or in
case of losses (netperf is fast, scp is slow). This is a major latency
source.

We should adjust the len/truesize ratio to 50% instead of 75%

This patch :

1) changes tcp_adv_win_scale default to 1 instead of 2

2) increase tcp_rmem[2] limit from 4MB to 6MB to take into account
better truesize tracking and to allow autotuning tcp receive window to
reach same value than before. Note that same amount of kernel memory is
consumed compared to 2.6 kernels.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Tom Herbert <therbert@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch implements RFC 5827 early retransmit (ER) for TCP.
It reduces DUPACK threshold (dupthresh) if outstanding packets are
less than 4 to recover losses by fast recovery instead of timeout.

While the algorithm is simple, small but frequent network reordering
makes this feature dangerous: the connection repeatedly enter
false recovery and degrade performance. Therefore we implement
a mitigation suggested in the appendix of the RFC that delays
entering fast recovery by a small interval, i.e., RTT/4. Currently
ER is conservative and is disabled for the rest of the connection
after the first reordering event. A large scale web server
experiment on the performance impact of ER is summarized in
section 6 of the paper "Proportional Rate Reduction for TCP”,
IMC 2011. http://conferences.sigcomm.org/imc/2011/docs/p155.pdf

Note that Linux has a similar feature called THIN_DUPACK. The
differences are THIN_DUPACK do not mitigate reorderings and is only
used after slow start. Currently ER is disabled if THIN_DUPACK is
enabled. I would be happy to merge THIN_DUPACK feature with ER if
people think it's a good idea.

ER is enabled by sysctl_tcp_early_retrans:
  0: Disables ER

  1: Reduce dupthresh to packets_out - 1 when outstanding packets < 4.

  2: (Default) reduce dupthresh like mode 1. In addition, delay
     entering fast recovery by RTT/4.

Note: mode 2 is implemented in the third part of this patch series.
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

All parameter descriptions in /proc/sys/net/core/* now is separated
two places. So, merge them into Documentation/sysctl/net.txt.
Signed-off-by: NShan Wei <davidshan@tencent.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Correct multiple spelling typo in Documentation.
Signed-off-by: NMasanari Iida <standby24x7@gmail.com>
Acked-by: NRob Landley <rob@landley.net>
Reported-by: NAnders Larsen <al@alarsen.net>
Signed-off-by: NJiri Kosina <jkosina@suse.cz>

Signed-off-by: NSimon Wunderlich <siwu@hrz.tu-chemnitz.de>
Signed-off-by: NAntonio Quartulli <ordex@autistici.org>

This second version of the bridge loop avoidance for batman-adv
avoids loops between the mesh and a backbone (usually a LAN).

By connecting multiple batman-adv mesh nodes to the same ethernet
segment a loop can be created when the soft-interface is bridged
into that ethernet segment. A simple visualization of the loop
involving the most common case - a LAN as ethernet segment:

node1  <-- LAN  -->  node2
  |                   |
wifi   <-- mesh -->  wifi

Packets from the LAN (e.g. ARP broadcasts) will circle forever from
node1 or node2 over the mesh back into the LAN.

With this patch, batman recognizes backbone gateways, nodes which are
part of the mesh and backbone/LAN at the same time. Each backbone
gateway "claims" clients from within the mesh to handle them
exclusively. By restricting that only responsible backbone gateways
may handle their claimed clients traffic, loops are effectively
avoided.
Signed-off-by: NSimon Wunderlich <siwu@hrz.tu-chemnitz.de>
Signed-off-by: NAntonio Quartulli <ordex@autistici.org>

Changing the channel type during operation is
confusing to some drivers and will be hard to
handle in multi-channel scenarios. Instead of
changing the channel, set it to the right HT
channel before authenticating/associating and
don't change it -- just update the 20/40 MHz
restrictions in rate control as needed when
changed by the AP.

This also fixes a problem that Paul missed in
his fix for the "regulatory makes us deaf"
issue -- when we couldn't use 40 MHz we still
associated saying we were using 40 MHz, which
could in similarly broken APs make us never
even connect successfully.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>

Commit dc1f8bf6 ('netdev: change
transmit to limited range type') changed the required return type and
9a1654ba ('net: Optimize
hard_start_xmit() return checking') changed the valid numerical
return values.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit 08baf561 ('net:
txq_trans_update() helper') made it unnecessary for most drivers to
set net_device::trans_start (or netdev_queue::trans_start).
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commits d314774c ('netdev: network
device operations infrastructure') and
00829823 ('netdev: add more functions
to netdevice ops') moved and renamed net device operation pointers.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commits e308a5d8 ('netdev: Add
netdev->addr_list_lock protection.') and
e8a0464c ('netdev: Allocate multiple
queues for TX.') introduced more fine-grained locks.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit bea3348e ('[NET]: Make NAPI
polling independent of struct net_device objects.') removed the
automatic disabling of NAPI polling by dev_close(), and drivers
must now do this themselves.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If a specific clk_csr value is passed from the platform
this means that the CSR Clock Range selection cannot be
changed at run-time and it is fixed (as reported in the driver
documentation). Viceversa the driver will try to set the MDC
clock dynamically according to the actual clock input.
Signed-off-by: NDeepak Sikri <deepak.sikri@st.com>
Signed-off-by: NGiuseppe Cavallaro <peppe.cavallaro@st.com>
Reviewed-by: NFrancesco Virlinzi <francesco.virlinzi@st.com>
Reviewed-by: NDavid Laight <david.laight@aculab.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch re-works the internal GMAC DMA parameters
passed from the platform.
In the past, we only passed the pbl but, with new core,
other parameters can be passed and are mandatory on some
platforms.

New parameters are documented in stmmac.txt because this
patch has an impact for many platforms.
Signed-off-by: NShiraz Hashim <shiraz.hashim@st.com>
Signed-off-by: NVikas Manocha <vikas.manocha@st.com>
Signed-off-by: NDeepak Sikri <deepak.sikri@st.com>
Hacked-by: NGiuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch explicitly defines the CSUM offload engine type which need
(not mandatory) to be passed from the platform code.
STMMAC core supports two check sum offload engine types- Type-1 & Type-2.
Also, there are STMMAC cores that do not have the check sum offload
capabilities.

The behaviour of Type-1 & Type-2 cores related to provision of checksum
increases the packet length for Type-1 cores by 2, as the checksum is appended
at the end of data packet and the same is made accountable in the DMA status.
The STMMAC cores beyond Version-3.5 provide HW interface registers which allows
the user to read the HW capabilities, while to support the previous cores the
information related to HW capabilities has to be provided from the platform
code.

The Type-1 cores which do not have the HW register interface need this
information.

This patch also updates the driver's doc.
Signed-off-by: NDeepak Sikri <deepak.sikri@st.com>
Hacked-by: NGiuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The explanation of ip_local_port_range in
Documentation/networking/ip-sysctl.txt contains several factual
errors:

- The default value of ip_local_port_range does not depend on the
  amount of memory available in the system.
- tcp_tw_recycle is not enabled by default.
- 1024-4999 is not the default value.
- Etc.

Clean up the mess.
Signed-off-by: NFernando Luis Vazquez Cao <fernando@oss.ntt.co.jp>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Install commands should not be used to specify soft dependencies among
modules. When loading modules it's much better to have a softdep that
modprobe knows what's being done than having to fork/exec another
instance of modprobe to load the other module.

By using a softdep user has also an option to remove the dependencies
when removing the module (and if its refcount dropped to 0)
Signed-off-by: NLucas De Marchi <lucas.demarchi@profusion.mobi>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Usage of /etc/modprobe.conf file was deprecated by module-init-tools and
is no longer parsed by new kmod tool. References to this file are
replaced in Documentation, comments and Kconfig according to the
context.

There are also some references to the old /etc/modules.conf from 2.4
kernels that are being removed.
Signed-off-by: NLucas De Marchi <lucas.demarchi@profusion.mobi>
Acked-by: NTakashi Iwai <tiwai@suse.de>
Acked-by: NMauro Carvalho Chehab <mchehab@redhat.com>
Signed-off-by: NRandy Dunlap <rdunlap@xenotime.net>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Signed-off-by: NYegor Yefremov <yegorslists@googlemail.com>
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>

I've been working on some documentation, so let's
add this diagram to the kernel tree where at least
it has a chance of being maintained :-)
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>

Signed-off-by: NMasanari Iida <standby24x7@gmail.com>
Acked-by: NRandy Dunlap <rdunlap@xenotime.net>
Signed-off-by: NJiri Kosina <jkosina@suse.cz>

Since all that include/linux/if_ppp.h does is #include <linux/ppp-ioctl.h>,
this replaces the occurrences of #include <linux/if_ppp.h> with
#include <linux/ppp-ioctl.h>.

It also corrects an error in Documentation/networking/l2tp.txt, where
it referenced include/linux/if_ppp.h as the source of some definitions
that are actually now defined in include/linux/if_pppol2tp.h.
Signed-off-by: NPaul Mackerras <paulus@samba.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>