It was once upon time so that snd_sthresh was a 16-bit quantity.
...That has not been true for long period of time. I run across
some ancient compares which still seem to trust such legacy.
Put all that magic into a single place, I hopefully found all
of them.

Compile tested, though linking of allyesconfig is ridiculous
nowadays it seems.
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Here, an ICMP host/network unreachable message, whose payload fits to
TCP's SND.UNA, is taken as an indication that the RTO retransmission has
not been lost due to congestion, but because of a route failure
somewhere along the path.
With true congestion, a router won't trigger such a message and the
patched TCP will operate as standard TCP.

This patch reverts one RTO backoff, if an ICMP host/network unreachable
message, whose payload fits to TCP's SND.UNA, arrives.
Based on the new RTO, the retransmission timer is reset to reflect the
remaining time, or - if the revert clocked out the timer - a retransmission
is sent out immediately.
Backoffs are only reverted, if TCP is in RTO loss recovery, i.e. if
there have been retransmissions and reversible backoffs, already.

Changes from v2:
1) Renaming of skb in tcp_v4_err() moved to another patch.
2) Reintroduced tcp_bound_rto() and __tcp_set_rto().
3) Fixed code comments.
Signed-off-by: NDamian Lukowski <damian@tvk.rwth-aachen.de>
Acked-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Somewhat luckily, I was looking into these parts with very fine
comb because I've made somewhat similar changes on the same
area (conflicts that arose weren't that lucky though). The loop
was very much overengineered recently in commit 91521944
(tcp: Use SKB queue and list helpers instead of doing it
by-hand), while it basically just wants to know if there are
skbs after 'skb'.

Also it got broken because skb1 = skb->next got translated into
skb1 = skb1->next (though abstracted) improperly. Note that
'skb1' is pointing to previous sk_buff than skb or NULL if at
head. Two things went wrong:
- We'll kfree 'skb' on the first iteration instead of the
  skbuff following 'skb' (it would require required SACK reneging
  to recover I think).
- The list head case where 'skb1' is NULL is checked too early
  and the loop won't execute whereas it previously did.

Conclusion, mostly revert the recent changes which makes the
cset very messy looking but using proper accessor in the
previous-like version.

The effective changes against the original can be viewed with:
  git-diff 91521944^ \
		net/ipv4/tcp_input.c | sed -n -e '57,70 p'
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

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

tcp_prequeue() refers to the constant value (TCP_RTO_MIN) regardless of
the actual value might be tuned. The following patches fix this and make
tcp_prequeue get the actual value returns from tcp_rto_min().
Signed-off-by: NSatoru SATOH <satoru.satoh@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This should be very safe compared with full enabled, so I see
no reason why it shouldn't be done right away. As ECN can only
be negotiated if the SYN sending party is also supporting it,
somebody in the loop probably knows what he/she is doing. If
SYN does not ask for ECN, the server side SYN-ACK is identical
to what it is without ECN. Thus it's quite safe.

The chosen value is safe w.r.t to existing configs which
choose to currently set manually either 0 or 1 but
silently upgrades those who have not explicitly requested
ECN off.

Whether to just enable both sides comes up time to time but
unless that gets done now we can at least make the servers
aware of ECN already. As there are some known problems to occur
if ECN is enabled, it's currently questionable whether there's
any real gain from enabling clients as servers mostly won't
support it anyway (so we'd hit just the negative sides). After
enabling the servers and getting that deployed, the client end
enable really has some potential gain too.
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

A long-standing feature in tcp_init_metrics() is such that
any of its goto reset prevents call to tcp_init_cwnd().
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Discard incoming packets whose ack field iincludes data not yet sent.
This is consistent with RFC 793 Section 3.9.

Change tcp_ack() to distinguish between too-small and too-large ack
field values.  Keep segments with too-large ack fields out of the fast
path, and change slow path to discard them.
Reported-by: NOliver Zheng <mailinglists+netdev@oliverzheng.com>
Signed-off-by: NJohn Dykstra <john.dykstra1@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

tcp_sack_swap seems unnecessary so I pushed swap to the caller.
Also removed comment that seemed then pointless, and added include
when not already there. Compile tested.
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There's very little need for most of the callsites to get
tp->xmit_goal_size updated. That will cost us divide as is,
so slice the function in two. Also, the only users of the
tp->xmit_goal_size are directly behind tcp_current_mss(),
so there's no need to store that variable into tcp_sock
at all! The drop of xmit_goal_size currently leaves 16-bit
hole and some reorganization would again be necessary to
change that (but I'm aiming to fill that hole with u16
xmit_goal_size_segs to cache the results of the remaining
divide to get that tso on regression).

Bring xmit_goal_size parts into tcp.c
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Cc: Evgeniy Polyakov <zbr@ioremap.net>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It seems that no variables clash such that we couldn't do
the check just once later on. Therefore move it.

Also kill dead obvious comment, dead argument and add
unlikely since this mtu probe does not happen too often.
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Wow, it was quite tricky to merge that stream of negations
but I think I finally got it right:

check & replace_ts_recent:
(s32)(rcv_tsval - ts_recent) >= 0                  => 0
(s32)(ts_recent - rcv_tsval) <= 0                  => 0

discard:
(s32)(ts_recent - rcv_tsval)  > TCP_PAWS_WINDOW    => 1
(s32)(ts_recent - rcv_tsval) <= TCP_PAWS_WINDOW    => 0

I toggled the return values of tcp_paws_check around since
the old encoding added yet-another negation making tracking
of truth-values really complicated.
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

I've already forgotten what for this was necessary, anyway
it's no longer used (if it ever was).
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In the pure assignment case, the earlier zeroing is
still in effect.

David S. Miller raised concerns if the ifs are there to avoid
dirtying cachelines. I came to these conclusions:

> We'll be dirty it anyway (now that I check), the first "real" statement
> in tcp_rcv_established is:
>
>       tp->rx_opt.saw_tstamp = 0;
>
> ...that'll land on the same dword. :-/
>
> I suppose the blocks are there just because they had more complexity
> inside when they had to calculate the eff_sacks too (maybe it would
> have been better to just remove them in that drop-patch so you would
> have had less head-ache :-)).
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The above functions from include/net/tcp.h have been defined with an
argument that they never use. The argument is 'u32 ack' which is never
used inside the function body, and thus it can be removed. The rest of
the patch involves the necessary changes to the function callers of the
above two functions.
Signed-off-by: NHantzis Fotis <xantzis@ceid.upatras.gr>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Also fixes insignificant bug that would cause sending of stale
SACK block (would occur in some corner cases).
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Some comment about its current state added. So far I have
seen very few cases where the thing is actually useful,
usually just marginally (though admittedly I don't usually
see top of window losses where it seems possible that there
could be some gain), instead, more often the cases suffer
from L-marking spike which is certainly not desirable
(I'll bury improving it to my todo list, but on a low
prio position).
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Arnd Hannemann <hannemann@nets.rwth-aachen.de> noticed and was
puzzled by the fact that !tcp_is_fack(tp) leads to early return
near the beginning and the later on tcp_is_fack(tp) was still
used in an if condition. The later check was a left-over from
RFC3517 SACK stuff (== !tcp_is_fack(tp) behavior nowadays) as
there wasn't clear way how to handle this particular check
cheaply in the spirit of RFC3517 (using only SACK blocks, not
holes + SACK blocks as with FACK). I sort of left it there as
a reminder but since it's confusing other people just remove
it and comment the missing-feature stuff instead.
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Cc: Arnd Hannemann <hannemann@nets.rwth-aachen.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It is possible that lost_cnt_hint gets underflow in
tcp_clean_rtx_queue because the cumulative ACK can cover
the segment where lost_skb_hint points to only partially,
which means that the hint is not cleared, opposite to what
my (earlier) comment claimed.

Also I don't agree what I ended up writing about non-trivial
case there to be what I intented to say. It was not supposed
to happen that the hint won't get cleared and we underflow
in any scenario.

In general, this is quite hard to trigger in practice.
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There's conflicting assumptions in shifting, the caller assumes
that dupsack results in S'ed skbs (or a part of it) for sure but
never gave a hint to tcp_sacktag_one when dsack is actually in
use. Thus DSACK retrans_out -= pcount was not taken and the
counter became out of sync. Remove obstacle from that information
flow to get DSACKs accounted in tcp_sacktag_one as expected.
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Tested-by: NDenys Fedoryshchenko <denys@visp.net.lb>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use the general-purpose channel allocation provided by dmaengine.
Reviewed-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Both are called by the same sites.
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There are just too many args to some sacktag functions. This
idea was first proposed by David S. Miller around a year ago,
and the current situation is much worse that what it was back
then.

tcp_sacktag_one can be made a bit simpler by returning the
new sacked (it can be achieved with a single variable though
the previous code "caching" sacked into a local variable and
therefore it is not exactly equal but the results will be the
same).

codiff on x86_64
  tcp_sacktag_one         |  -15
  tcp_shifted_skb         |  -50
  tcp_match_skb_to_sack   |   -1
  tcp_sacktag_walk        |  -64
  tcp_sacktag_write_queue |  -59
  tcp_urg                 |   +1
  tcp_event_data_recv     |   -1
 7 functions changed, 1 bytes added, 190 bytes removed, diff: -189
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

I noticed that since skb->len has nothing to do with actual segment
length with gso, we need to figure it out separately, reuse
a function from the recent shifting stuff (generalize it).
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

S|R won't result in S if just SACK is received. DSACK is
another story (but it is covered correctly already).
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Also make if-goto forest nicer looking.
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The earlier version was just very basic one which is "playing
safe" by always clearing the hints. However, clearing of a hint
is extremely costly operation with large windows, so it must be
avoided at all cost whenever possible, there is a way with
shifting too achieve not-clearing.
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

During SACK processing, most of the benefits of TSO are eaten by
the SACK blocks that one-by-one fragment SKBs to MSS sized chunks.
Then we're in problems when cleanup work for them has to be done
when a large cumulative ACK comes. Try to return back to pre-split
state already while more and more SACK info gets discovered by
combining newly discovered SACK areas with the previous skb if
that's SACKed as well.

This approach has a number of benefits:

1) The processing overhead is spread more equally over the RTT
2) Write queue has less skbs to process (affect everything
   which has to walk in the queue past the sacked areas)
3) Write queue is consistent whole the time, so no other parts
   of TCP has to be aware of this (this was not the case with
   some other approach that was, well, quite intrusive all
   around).
4) Clean_rtx_queue can release most of the pages using single
   put_page instead of previous PAGE_SIZE/mss+1 calls

In case a hole is fully filled by the new SACK block, we attempt
to combine the next skb too which allows construction of skbs
that are even larger than what tso split them to and it handles
hole per on every nth patterns that often occur during slow start
overshoot pretty nicely. Though this to be really useful also
a retransmission would have to get lost since cumulative ACKs
advance one hole at a time in the most typical case.

TODO: handle upwards only merging. That should be rather easy
when segment is fully sacked but I'm leaving that as future
work item (it won't make very large difference anyway since
this current approach already covers quite a lot of normal
cases).

I was earlier thinking of some sophisticated way of tracking
timestamps of the first and the last segment but later on
realized that it won't be that necessary at all to store the
timestamp of the last segment. The cases that can occur are
basically either:
  1) ambiguous => no sensible measurement can be taken anyway
  2) non-ambiguous is due to reordering => having the timestamp
     of the last segment there is just skewing things more off
     than does some good since the ack got triggered by one of
     the holes (besides some substle issues that would make
     determining right hole/skb even harder problem). Anyway,
     it has nothing to do with this change then.

I choose to route some abnormal looking cases with goto noop,
some could be handled differently (eg., by stopping the
walking at that skb but again). In general, they either
shouldn't happen at all or are rare enough to make no difference
in practice.

In theory this change (as whole) could cause some macroscale
regression (global) because of cache misses that are taken over
the round-trip time but it gets very likely better because of much
less (local) cache misses per other write queue walkers and the
big recovery clearing cumulative ack.

Worth to note that these benefits would be very easy to get also
without TSO/GSO being on as long as the data is in pages so that
we can merge them. Currently I won't let that happen because
DSACK splitting at fragment that would mess up pcounts due to
sk_can_gso in tcp_set_skb_tso_segs. Once DSACKs fragments gets
avoided, we have some conditions that can be made less strict.

TODO: I will probably have to convert the excessive pointer
passing to struct sacktag_state... :-)

My testing revealed that considerable amount of skbs couldn't
be shifted because they were cloned (most likely still awaiting
tx reclaim)...

[The rest is considering future work instead since I got
repeatably EFAULT to tcpdump's recvfrom when I added
pskb_expand_head to deal with clones, so I separated that
into another, later patch]

...To counter that, I gave up on the fifth advantage:

5) When growing previous SACK block, less allocs for new skbs
   are done, basically a new alloc is needed only when new hole
   is detected and when the previous skb runs out of frags space

...which now only happens of if reclaim is fast enough to dispose
the clone before the SACK block comes in (the window is RTT long),
otherwise we'll have to alloc some.

With clones being handled I got these numbers (will be somewhat
worse without that), taken with fine-grained mibs:

                  TCPSackShifted 398
                   TCPSackMerged 877
            TCPSackShiftFallback 320
      TCPSACKCOLLAPSEFALLBACKGSO 0
  TCPSACKCOLLAPSEFALLBACKSKBBITS 0
  TCPSACKCOLLAPSEFALLBACKSKBDATA 0
    TCPSACKCOLLAPSEFALLBACKBELOW 0
    TCPSACKCOLLAPSEFALLBACKFIRST 1
 TCPSACKCOLLAPSEFALLBACKPREVBITS 318
      TCPSACKCOLLAPSEFALLBACKMSS 1
   TCPSACKCOLLAPSEFALLBACKNOHEAD 0
    TCPSACKCOLLAPSEFALLBACKSHIFT 0
          TCPSACKCOLLAPSENOOPSEQ 0
  TCPSACKCOLLAPSENOOPSMALLPCOUNT 0
     TCPSACKCOLLAPSENOOPSMALLLEN 0
             TCPSACKCOLLAPSEHOLE 12
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This is preparatory work for SACK combiner patch which may
have to count TCP state changes for only a part of the skb
because it will intentionally avoids splitting skb to SACKed
and not sacked parts.
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Sadly enough, this adds possible divide though we try to avoid
it by checking one mss as common case.
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

I knew already when rewriting the sacktag that this condition
was too conservative, change it now since it prevent lot of
useless work (especially in the sack shifter decision code
that is being added by a later patch). This shouldn't change
anything really, just save some processing regardless of the
shifter.
Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Using NIPQUAD() with NIPQUAD_FMT, %d.%d.%d.%d or %u.%u.%u.%u
can be replaced with %pI4
Signed-off-by: NHarvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NHarvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NHarvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

From: Ali Saidi <saidi@engin.umich.edu>

When TCP receive copy offload is enabled it's possible that
tcp_rcv_established() will cause two acks to be sent for a single
packet. In the case that a tcp_dma_early_copy() is successful,
copied_early is set to true which causes tcp_cleanup_rbuf() to be
called early which can send an ack. Further along in
tcp_rcv_established(), __tcp_ack_snd_check() is called and will
schedule a delayed ACK. If no packets are processed before the delayed
ack timer expires the packet will be acked twice.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>