In the SYN_RECV state, where the TCP connection is represented by
tcp_request_sock, we now rate-limit SYNACKs in response to a client's
retransmitted SYNs: we do not send a SYNACK in response to client SYN
if it has been less than sysctl_tcp_invalid_ratelimit (default 500ms)
since we last sent a SYNACK in response to a client's retransmitted
SYN.

This allows the vast majority of legitimate client connections to
proceed unimpeded, even for the most aggressive platforms, iOS and
MacOS, which actually retransmit SYNs 1-second intervals for several
times in a row. They use SYN RTO timeouts following the progression:
1,1,1,1,1,2,4,8,16,32.
Reported-by: NAvery Fay <avery@mixpanel.com>
Signed-off-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This work adds the possibility to define a per route/destination
congestion control algorithm. Generally, this opens up the possibility
for a machine with different links to enforce specific congestion
control algorithms with optimal strategies for each of them based
on their network characteristics, even transparently for a single
application listening on all links.

For our specific use case, this additionally facilitates deployment
of DCTCP, for example, applications can easily serve internal
traffic/dsts in DCTCP and external one with CUBIC. Other scenarios
would also allow for utilizing e.g. long living, low priority
background flows for certain destinations/routes while still being
able for normal traffic to utilize the default congestion control
algorithm. We also thought about a per netns setting (where different
defaults are possible), but given its actually a link specific
property, we argue that a per route/destination setting is the most
natural and flexible.

The administrator can utilize this through ip-route(8) by appending
"congctl [lock] <name>", where <name> denotes the name of a
congestion control algorithm and the optional lock parameter allows
to enforce the given algorithm so that applications in user space
would not be allowed to overwrite that algorithm for that destination.

The dst metric lookups are being done when a dst entry is already
available in order to avoid a costly lookup and still before the
algorithms are being initialized, thus overhead is very low when the
feature is not being used. While the client side would need to drop
the current reference on the module, on server side this can actually
even be avoided as we just got a flat-copied socket clone.

Joint work with Florian Westphal.
Suggested-by: NHannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Suggested by Stephen. Also drop inline keyword and let compiler decide.

gcc 4.7.3 decides to no longer inline tcp_ecn_check_ce, so split it up.
The actual evaluation is not inlined anymore while the ECN_OK test is.
Suggested-by: NStephen Hemminger <stephen@networkplumber.org>
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Split assignment and initialization from one into two functions.

This is required by followup patches that add Datacenter TCP
(DCTCP) congestion control algorithm - we need to be able to
determine if the connection is moderated by DCTCP before the
3WHS has finished.

As we walk the available congestion control list during the
assignment, we are always guaranteed to have Reno present as
it's fixed compiled-in. Therefore, since we're doing the
early assignment, we don't have a real use for the Reno alias
tcp_init_congestion_ops anymore and can thus remove it.

Actual usage of the congestion control operations are being
made after the 3WHS has finished, in some cases however we
can access get_info() via diag if implemented, therefore we
need to zero out the private area for those modules.

Joint work with Daniel Borkmann and Glenn Judd.
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Signed-off-by: NGlenn Judd <glenn.judd@morganstanley.com>
Acked-by: NStephen Hemminger <stephen@networkplumber.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

TCP_SKB_CB(skb)->when has different meaning in output and input paths.

In output path, it contains a timestamp.
In input path, it contains an ISN, chosen by tcp_timewait_state_process()

Lets add a different name to ease code comprehension.

Note that 'when' field will disappear in following patch,
as skb_mstamp already contains timestamp, the anonymous
union will promptly disappear as well.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Acked-by: NYuchung Cheng <ycheng@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When an UDP application switches from AF_INET to AF_INET6 sockets, we
have a small performance degradation for IPv4 communications because of
extra cache line misses to access ipv6only information.

This can also be noticed for TCP listeners, as ipv6_only_sock() is also
used from __inet_lookup_listener()->compute_score()

This is magnified when SO_REUSEPORT is used.

Move ipv6only into struct sock_common so that it is available at
no extra cost in lookups.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

To avoid large code duplication in IPv6, we need to first simplify
the complicate SYN-ACK sending code in tcp_v4_conn_request().

To use tcp_v4(6)_send_synack() to send all SYN-ACKs, we need to
initialize the mini socket's receive window before trying to
create the child socket and/or building the SYN-ACK packet. So we move
that initialization from tcp_make_synack() to tcp_v4_conn_request()
as a new function tcp_openreq_init_req_rwin().

After this refactoring the SYN-ACK sending code is simpler and easier
to implement Fast Open for IPv6.
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Signed-off-by: NDaniel Lee <longinus00@gmail.com>
Signed-off-by: NJerry Chu <hkchu@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Several spots in the kernel perform a sequence like:

	skb_queue_tail(&sk->s_receive_queue, skb);
	sk->sk_data_ready(sk, skb->len);

But at the moment we place the SKB onto the socket receive queue it
can be consumed and freed up.  So this skb->len access is potentially
to freed up memory.

Furthermore, the skb->len can be modified by the consumer so it is
possible that the value isn't accurate.

And finally, no actual implementation of this callback actually uses
the length argument.  And since nobody actually cared about it's
value, lots of call sites pass arbitrary values in such as '0' and
even '1'.

So just remove the length argument from the callback, that way there
is no confusion whatsoever and all of these use-after-free cases get
fixed as a side effect.

Based upon a patch by Eric Dumazet and his suggestion to audit this
issue tree-wide.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Upcoming congestion controls for TCP require usec resolution for RTT
estimations. Millisecond resolution is simply not enough these days.

FQ/pacing in DC environments also require this change for finer control
and removal of bimodal behavior due to the current hack in
tcp_update_pacing_rate() for 'small rtt'

TCP_CONG_RTT_STAMP is no longer needed.

As Julian Anastasov pointed out, we need to keep user compatibility :
tcp_metrics used to export RTT and RTTVAR in msec resolution,
so we added RTT_US and RTTVAR_US. An iproute2 patch is needed
to use the new attributes if provided by the kernel.

In this example ss command displays a srtt of 32 usecs (10Gbit link)

lpk51:~# ./ss -i dst lpk52
Netid  State      Recv-Q Send-Q   Local Address:Port       Peer
Address:Port
tcp    ESTAB      0      1         10.246.11.51:42959
10.246.11.52:64614
         cubic wscale:6,6 rto:201 rtt:0.032/0.001 ato:40 mss:1448
cwnd:10 send
3620.0Mbps pacing_rate 7240.0Mbps unacked:1 rcv_rtt:993 rcv_space:29559

Updated iproute2 ip command displays :

lpk51:~# ./ip tcp_metrics | grep 10.246.11.52
10.246.11.52 age 561.914sec cwnd 10 rtt 274us rttvar 213us source
10.246.11.51

Old binary displays :

lpk51:~# ip tcp_metrics | grep 10.246.11.52
10.246.11.52 age 561.914sec cwnd 10 rtt 250us rttvar 125us source
10.246.11.51

With help from Julian Anastasov, Stephen Hemminger and Yuchung Cheng
Signed-off-by: NEric Dumazet <edumazet@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Larry Brakmo <brakmo@google.com>
Cc: Julian Anastasov <ja@ssi.bg>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch is following the commit b903d324 (ipv6: tcp: fix TCLASS
value in ACK messages sent from TIME_WAIT).

For the same reason than tclass, we have to store the flow label in the
inet_timewait_sock to provide consistency of flow label on the last ACK.
Signed-off-by: NFlorent Fourcot <florent.fourcot@enst-bretagne.fr>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

TCP out_of_order_queue lock is not used, as queue manipulation
happens with socket lock held and we therefore use the lockless
skb queue routines (as __skb_queue_head())

We can use __skb_queue_head_init() instead of skb_queue_head_init()
to make this more consistent.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

TCP listener refactoring, part 4 :

To speed up inet lookups, we moved IPv4 addresses from inet to struct
sock_common

Now is time to do the same for IPv6, because it permits us to have fast
lookups for all kind of sockets, including upcoming SYN_RECV.

Getting IPv6 addresses in TCP lookups currently requires two extra cache
lines, plus a dereference (and memory stall).

inet6_sk(sk) does the dereference of inet_sk(__sk)->pinet6

This patch is way bigger than its IPv4 counter part, because for IPv4,
we could add aliases (inet_daddr, inet_rcv_saddr), while on IPv6,
it's not doable easily.

inet6_sk(sk)->daddr becomes sk->sk_v6_daddr
inet6_sk(sk)->rcv_saddr becomes sk->sk_v6_rcv_saddr

And timewait socket also have tw->tw_v6_daddr & tw->tw_v6_rcv_saddr
at the same offset.

We get rid of INET6_TW_MATCH() as INET6_MATCH() is now the generic
macro.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The first patch consolidates SYNACK and other RTT measurement to use a
central function tcp_ack_update_rtt(). A (small) bonus is now SYNACK
RTT measurement happens after PAWS check, potentially reducing the
impact of RTO seeding on bad TCP timestamps values.
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

TCP md5 code uses per cpu variables but protects access to them with
a shared spinlock, which is a contention point.

[ tcp_md5sig_pool_lock is locked twice per incoming packet ]

Makes things much simpler, by allocating crypto structures once, first
time a socket needs md5 keys, and not deallocating them as they are
really small.

Next step would be to allow crypto allocations being done in a NUMA
aware way.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Linux immediately returns SYNACK on (spurious) SYN retransmits, but
keeps the SYNACK timer running independently. Thus the timer may
fire right after the SYNACK retransmit and causes a SYN-SYNACK
cross-fire burst.

Adopt the fast retransmit/recovery idea in established state by
re-arming the SYNACK timer after the fast (SYNACK) retransmit. The
timer may fire late up to 500ms due to the current SYNACK timer wheel,
but it's OK to be conservative when network is congested. Eric's new
listener design should address this issue.
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The patch series refactor the F-RTO feature (RFC4138/5682).

This is to simplify the loss recovery processing. Existing F-RTO
was developed during the experimental stage (RFC4138) and has
many experimental features.  It takes a separate code path from
the traditional timeout processing by overloading CA_Disorder
instead of using CA_Loss state. This complicates CA_Disorder state
handling because it's also used for handling dubious ACKs and undos.
While the algorithm in the RFC does not change the congestion control,
the implementation intercepts congestion control in various places
(e.g., frto_cwnd in tcp_ack()).

The new code implements newer F-RTO RFC5682 using CA_Loss processing
path.  F-RTO becomes a small extension in the timeout processing
and interfaces with congestion control and Eifel undo modules.
It lets congestion control (module) determines how many to send
independently.  F-RTO only chooses what to send in order to detect
spurious retranmission. If timeout is found spurious it invokes
existing Eifel undo algorithms like DSACK or TCP timestamp based
detection.

The first patch removes all F-RTO code except the sysctl_tcp_frto is
left for the new implementation.  Since CA_EVENT_FRTO is removed, TCP
westwood now computes ssthresh on regular timeout CA_EVENT_LOSS event.
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

TCPCT uses option-number 253, reserved for experimental use and should
not be used in production environments.
Further, TCPCT does not fully implement RFC 6013.

As a nice side-effect, removing TCPCT increases TCP's performance for
very short flows:

Doing an apache-benchmark with -c 100 -n 100000, sending HTTP-requests
for files of 1KB size.

before this patch:
	average (among 7 runs) of 20845.5 Requests/Second
after:
	average (among 7 runs) of 21403.6 Requests/Second
Signed-off-by: NChristoph Paasch <christoph.paasch@uclouvain.be>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This is the second of the TLP patch series; it augments the basic TLP
algorithm with a loss detection scheme.

This patch implements a mechanism for loss detection when a Tail
loss probe retransmission plugs a hole thereby masking packet loss
from the sender. The loss detection algorithm relies on counting
TLP dupacks as outlined in Sec. 3 of:
http://tools.ietf.org/html/draft-dukkipati-tcpm-tcp-loss-probe-01

The basic idea is: Sender keeps track of TLP "episode" upon
retransmission of a TLP packet. An episode ends when the sender receives
an ACK above the SND.NXT (tracked by tlp_high_seq) at the time of the
episode. We want to make sure that before the episode ends the sender
receives a "TLP dupack", indicating that the TLP retransmission was
unnecessary, so there was no loss/hole that needed plugging. If the
sender gets no TLP dupack before the end of the episode, then it reduces
ssthresh and the congestion window, because the TLP packet arriving at
the receiver probably plugged a hole.
Signed-off-by: NNandita Dukkipati <nanditad@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

A socket timestamp is a sum of the global tcp_time_stamp and
a per-socket offset.

A socket offset is added in places where externally visible
tcp timestamp option is parsed/initialized.

Connections in the SYN_RECV state are not supported, global
tcp_time_stamp is used for them, because repair mode doesn't support
this state. In a future it can be implemented by the similar way
as for TIME_WAIT sockets.

Cc: "David S. Miller" <davem@davemloft.net>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Cc: James Morris <jmorris@namei.org>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: Patrick McHardy <kaber@trash.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: NAndrey Vagin <avagin@openvz.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This functionality is used for restoring tcp sockets. A tcp timestamp
depends on how long a system has been running, so it's differ for each
host. The solution is to set a per-socket offset.

A per-socket offset for a TIME_WAIT socket is inherited from a proper
tcp socket.

tcp_request_sock doesn't have a timestamp offset, because the repair
mode for them are not implemented.

Cc: "David S. Miller" <davem@davemloft.net>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Cc: James Morris <jmorris@namei.org>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: Patrick McHardy <kaber@trash.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: NAndrey Vagin <avagin@openvz.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

TCP Appropriate Byte Count was added by me, but later disabled.
There is no point in maintaining it since it is a potential source
of bugs and Linux already implements other better window protection
heuristics.
Signed-off-by: NStephen Hemminger <stephen@networkplumber.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

For passive TCP connections using TCP_DEFER_ACCEPT facility,
we incorrectly increment req->retrans each time timeout triggers
while no SYNACK is sent.

SYNACK are not sent for TCP_DEFER_ACCEPT that were established (for
which we received the ACK from client). Only the last SYNACK is sent
so that we can receive again an ACK from client, to move the req into
accept queue. We plan to change this later to avoid the useless
retransmit (and potential problem as this SYNACK could be lost)

TCP_INFO later gives wrong information to user, claiming imaginary
retransmits.

Decouple req->retrans field into two independent fields :

num_retrans : number of retransmit
num_timeout : number of timeouts

num_timeout is the counter that is incremented at each timeout,
regardless of actual SYNACK being sent or not, and used to
compute the exponential timeout.

Introduce inet_rtx_syn_ack() helper to increment num_retrans
only if ->rtx_syn_ack() succeeded.

Use inet_rtx_syn_ack() from tcp_check_req() to increment num_retrans
when we re-send a SYNACK in answer to a (retransmitted) SYN.
Prior to this patch, we were not counting these retransmits.

Change tcp_v[46]_rtx_synack() to increment TCP_MIB_RETRANSSEGS
only if a synack packet was successfully queued.
Reported-by: NYuchung Cheng <ycheng@google.com>
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Julian Anastasov <ja@ssi.bg>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Elliott Hughes <enh@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add a bit TCPI_OPT_SYN_DATA (32) to the socket option TCP_INFO:tcpi_options.
It's set if the data in SYN (sent or received) is acked by SYN-ACK. Server or
client application can use this information to check Fast Open success rate.
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Previously, when using TCP Fast Open a server would return from
tcp_check_req() before updating snt_synack based on TCP timestamp echo
replies and whether or not we've retransmitted the SYNACK. The result
was that (a) for TFO connections using timestamps we used an incorrect
baseline SYNACK send time (tcp_time_stamp of SYNACK send instead of
rcv_tsecr), and (b) for TFO connections that do not have TCP
timestamps but retransmit the SYNACK we took a SYNACK RTT sample when
we should not take a sample.

This fix merely moves the snt_synack update logic a bit earlier in the
function, so that connections using TCP Fast Open will properly do
these updates when the ACK for the SYNACK arrives.

Moving this snt_synack update logic means that with TCP_DEFER_ACCEPT
enabled we do a few instructions of wasted work on each bare ACK, but
that seems OK.
Signed-off-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Both tcp_timewait_state_process and tcp_check_req use the same basic
construct of

	struct tcp_options received tmp_opt;
	tmp_opt.saw_tstamp = 0;

then call

	tcp_parse_options

However if they are fed a frame containing a TCP_SACK then tbe code
behaviour is undefined because opt_rx->sack_ok is undefined data.

This ought to be documented if it is intentional.
Signed-off-by: NAlan Cox <alan@linux.intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch builds on top of the previous patch to add the support
for TFO listeners. This includes -

1. allocating, properly initializing, and managing the per listener
fastopen_queue structure when TFO is enabled

2. changes to the inet_csk_accept code to support TFO. E.g., the
request_sock can no longer be freed upon accept(), not until 3WHS
finishes

3. allowing a TCP_SYN_RECV socket to properly poll() and sendmsg()
if it's a TFO socket

4. properly closing a TFO listener, and a TFO socket before 3WHS
finishes

5. supporting TCP_FASTOPEN socket option

6. modifying tcp_check_req() to use to check a TFO socket as well
as request_sock

7. supporting TCP's TFO cookie option

8. adding a new SYN-ACK retransmit handler to use the timer directly
off the TFO socket rather than the listener socket. Note that TFO
server side will not retransmit anything other than SYN-ACK until
the 3WHS is completed.

The patch also contains an important function
"reqsk_fastopen_remove()" to manage the somewhat complex relation
between a listener, its request_sock, and the corresponding child
socket. See the comment above the function for the detail.
Signed-off-by: NH.K. Jerry Chu <hkchu@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Tom Herbert <therbert@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This commit removes the sk_rx_dst_set calls from
tcp_create_openreq_child(), because at that point the icsk_af_ops
field of ipv6_mapped TCP sockets has not been set to its proper final
value.

Instead, to make sure we get the right sk_rx_dst_set variant
appropriate for the address family of the new connection, we have
tcp_v{4,6}_syn_recv_sock() directly call the appropriate function
shortly after the call to tcp_create_openreq_child() returns.

This also moves inet6_sk_rx_dst_set() to avoid a forward declaration
with the new approach.
Signed-off-by: NNeal Cardwell <ncardwell@google.com>
Reported-by: NArtem Savkov <artem.savkov@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

IPv6 needs a cookie in dst_check() call.

We need to add rx_dst_cookie and provide a family independent
sk_rx_dst_set(sk, skb) method to properly support IPv6 TCP early demux.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

commit c6cffba4 (ipv4: Fix input route performance regression.)
added various fatal races with dst refcounts.

crashes happen on tcp workloads if routes are added/deleted at the same
time.

The dst_free() calls from free_fib_info_rcu() are clearly racy.

We need instead regular dst refcounting (dst_release()) and make
sure dst_release() is aware of RCU grace periods :

Add DST_RCU_FREE flag so that dst_release() respects an RCU grace period
before dst destruction for cached dst

Introduce a new inet_sk_rx_dst_set() helper, using atomic_inc_not_zero()
to make sure we dont increase a zero refcount (On a dst currently
waiting an rcu grace period before destruction)

rt_cache_route() must take a reference on the new cached route, and
release it if was not able to install it.

With this patch, my machines survive various benchmarks.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

commit 92101b3b (ipv4: Prepare for change of rt->rt_iif encoding.)
invalidated TCP early demux, because rx_dst_ifindex is not properly
initialized and checked.

Also remove the use of inet_iif(skb) in favor or skb->skb_iif
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch impelements the common code for both the client and server.

1. TCP Fast Open option processing. Since Fast Open does not have an
   option number assigned by IANA yet, it shares the experiment option
   code 254 by implementing draft-ietf-tcpm-experimental-options
   with a 16 bits magic number 0xF989. This enables global experiments
   without clashing the scarce(2) experimental options available for TCP.

   When the draft status becomes standard (maybe), the client should
   switch to the new option number assigned while the server supports
   both numbers for transistion.

2. The new sysctl tcp_fastopen

3. A place holder init function
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Acked-by: NEric Dumazet <edumazet@google.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>

No longer used.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

With help from Lin Ming.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Input packet processing for local sockets involves two major demuxes.
One for the route and one for the socket.

But we can optimize this down to one demux for certain kinds of local
sockets.

Currently we only do this for established TCP sockets, but it could
at least in theory be expanded to other kinds of connections.

If a TCP socket is established then it's identity is fully specified.

This means that whatever input route was used during the three-way
handshake must work equally well for the rest of the connection since
the keys will not change.

Once we move to established state, we cache the receive packet's input
route to use later.

Like the existing cached route in sk->sk_dst_cache used for output
packets, we have to check for route invalidations using dst->obsolete
and dst->ops->check().

Early demux occurs outside of a socket locked section, so when a route
invalidation occurs we defer the fixup of sk->sk_rx_dst until we are
actually inside of established state packet processing and thus have
the socket locked.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Since it's guarenteed that we will access the inetpeer if we're trying
to do timewait recycling and TCP options were enabled on the
connection, just cache the peer in the timewait socket.

In the future, inetpeer lookups will be context dependent (per routing
realm), and this helps facilitate that as well.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The get_peer method TCP uses is full of special cases that make no
sense accommodating, and it also gets in the way of doing more
reasonable things here.

First of all, if the socket doesn't have a usable cached route, there
is no sense in trying to optimize timewait recycling.

Likewise for the case where we have IP options, such as SRR enabled,
that make the IP header destination address (and thus the destination
address of the route key) differ from that of the connection's
destination address.

Just return a NULL peer in these cases, and thus we're also able to
get rid of the clumsy inetpeer release logic.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

bool conversions where possible.

__inline__ -> inline

space cleanups
Signed-off-by: NEric Dumazet <edumazet@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>

In order to be able to support proper RST messages for TCP MD5 flows, we
need to allow access to MD5 keys without locking listener socket.

This conversion is a nice cleanup, and shrinks size of timewait sockets
by 80 bytes.

IPv6 code reuses generic code found in IPv4 instead of duplicating it.

Control path uses GFP_KERNEL allocations instead of GFP_ATOMIC.
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Cc: Shawn Lu <shawn.lu@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>