This patch removes a bug in the current code. I agree with Andrea's comment
that there is a problem here but the way it is treated does not fix it.

The problem is that whenever Ack Ratio > cwnd, starvation/deadlock occurs:
 * the receiver will not send an Ack until (Ack Ratio - cwnd) data packets
   have arrived;
 * the sender will not send any data packet before the receipt of an Ack
   advances the send window.
The only way that the connection then progresses was via RTO timeout. In one
extreme case (bulk transfer), it was observed that this happened for every single
packet; i.e. hundreds of packets, each a RTO timeout of 1..3 seconds apart:
a transfer which normally would take a fraction of a second thus grew to
several minutes.

The solution taken by this approach is to observe the relation

                   "Ack Ratio <= cwnd"

by using the constraint (1) from RFC 4341, 6.1.2; i.e. set

                 Ack Ratio = ceil(cwnd / 2)

and update it whenever either Ack Ratio or cwnd change. This ensures that
the deadlock problem can not arise.
Signed-off-by: NGerrit Renker <gerrit@erg.abdn.ac.uk>
Acked-by: NIan McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Since it makes not sense to assign negative values to Ack Ratio, this
patch disallows this possibility.

As a consequence, a Bug test for negative Ack Ratio values becomes obsolete.

Furthermore, a check against overflow (as Ack Ratio may not exceed 2 bytes,
due to RFC 4340, 11.3) has been added.
Signed-off-by: NGerrit Renker <gerrit@erg.abdn.ac.uk>
Acked-by: NIan McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This replaces use of normal subtraction with modulo-48 subtraction.
Signed-off-by: NGerrit Renker <gerrit@erg.abdn.ac.uk>
Acked-by: NIan McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In CCID2 the receiver-history is sorted in ascending order of sequence number,
but the processing of received Ack Vectors requires the list traversal in the
opposite direction.

The current code has a bug in this regard: the list traversal is upwards. As a
consequence, only Ack Vectors with a run length of 1 will pass, in all other
Ack Vectors the remaining (acked) sequence numbers are missed, and may later
falsely be identified as lost.

Note: This bug is only visible when Ack Ratio > 1, since otherwise the run
      lengths of Ack Vectors are 0.
Signed-off-by: NGerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: NIan McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Many-many code in the kernel initialized the timer->function
and  timer->data together with calling init_timer(timer). There
is already a helper for this. Use it for networking code.

The patch is HUGE, but makes the code 130 lines shorter
(98 insertions(+), 228 deletions(-)).
Signed-off-by: NPavel Emelyanov <xemul@openvz.org>
Acked-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Assigning initial values of `0' is redundant when loading a new CCID structure,
since in net/dccp/ccid.c the entire CCID structure is zeroed out prior to
initialisation in ccid_new():

    	struct ccid {
    		struct ccid_operations *ccid_ops;
    		char		       ccid_priv[0];
    	};

    	// ...
    	if (rx) {
    		memset(ccid + 1, 0, ccid_ops->ccid_hc_rx_obj_size);
    		if (ccid->ccid_ops->ccid_hc_rx_init != NULL &&
    		    ccid->ccid_ops->ccid_hc_rx_init(ccid, sk) != 0)
    			goto out_free_ccid;
    	} else {
    		memset(ccid + 1, 0, ccid_ops->ccid_hc_tx_obj_size);
    		/* analogous to the rx case */
    	}

This patch therefore removes the redundant assignments. Thanks to Arnaldo for
the inspiration.
Signed-off-by: NGerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: NIan McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

This replaces several uses of standard arithmetic with the DCCP
sequence number arithmetic functions. The problem here is that the
sequence number wrap-around was not taken into consideration.

 * Condition "seqp->ccid2s_seq <= prev->ccid2s_seq" has been replaced
   by

   	dccp_delta_seqno(seqp->ccid2s_seq, prev->ccid2s_seq) >= 0

   since if seqp is `before' prev, then the delta_seqno() is positive.

 * The test whether sequence numbers `a' and `b' are consecutive has
   the form

   	dccp_delta_seqno(a, b) == 1

 * Increment of ccid2hctx_rpseq could be done using dccp_inc_seqno(),
   but since here the incremented ccid2hctx_rpseq == seqno, used
   assignment instead.
Signed-off-by: NGerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

skb's passed to ccid2_hc_tx_send_packet() are headerless, the packet
type is decided later, in dccp_write_xmit(). Therefore the first test
of the switch/case block is always true, the others are never reached.
Signed-off-by: NGerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This removes a test for `val < 1' which would only have been triggered
when val < 0, due to a preceding test for 0.  Fixed by using an
unsigned type for cwnd (as in TCP) instead.
Signed-off-by: NGerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This removes an ugly BUG_ON which has been pointed out by Arnaldo.

Instead of freezing up the machine, a `critical' message is now issued
to the system log.

There is potential of doing this more gracefully (eg. there are a few
internal variables which could be updated despite the lack of memory),
but that requires more complicated changes to the algorithm; thus a
`FIXME' has been added.
Signed-off-by: NGerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch simplifies the interface of ccid2_hc_tx_alloc_seq():

   * ccid2_hc_tx_alloc_seq() is always called with an argument of
     CCID2_SEQBUF_LEN;

   * other code - ccid2_hc_tx_check_sanity() - even depends on the
     assumption that ccid2_hc_tx_alloc_seq() has been called with this
     particular size;

   * passing the `gfp_t' argument to ccid2_hc_tx_alloc_seq() is
     redundant with gfp_any().
Signed-off-by: NGerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This just sets the parameter to bool, since debugging messages are
either on or off.
Signed-off-by: NGerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: NIan McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This fixes the following bug reported in syslog:

[ 4039.051658] BUG: sleeping function called from invalid context at /usr/src/davem-2.6/mm/slab.c:3032
[ 4039.051668] in_atomic():1, irqs_disabled():0
[ 4039.051670] INFO: lockdep is turned off.
[ 4039.051674]  [<c0104c0f>] show_trace_log_lvl+0x1a/0x30
[ 4039.051687]  [<c0104d4d>] show_trace+0x12/0x14
[ 4039.051691]  [<c0104d65>] dump_stack+0x16/0x18
[ 4039.051695]  [<c011371e>] __might_sleep+0xaf/0xbe
[ 4039.051700]  [<c0157b66>] __kmalloc+0xb1/0xd0
[ 4039.051706]  [<f090416f>] ccid2_hc_tx_alloc_seq+0x35/0xc3 [dccp_ccid2]
[ 4039.051717]  [<f09048d6>] ccid2_hc_tx_packet_sent+0x27f/0x2d9 [dccp_ccid2]
[ 4039.051723]  [<f085486b>] dccp_write_xmit+0x1eb/0x338 [dccp]
[ 4039.051741]  [<f085603d>] dccp_sendmsg+0x113/0x18f [dccp]
[ 4039.051750]  [<c03907fc>] inet_sendmsg+0x2e/0x4c
[ 4039.051758]  [<c033a47d>] sock_aio_write+0xd5/0x107
[ 4039.051766]  [<c015abc1>] do_sync_write+0xcd/0x11c
[ 4039.051772]  [<c015b296>] vfs_write+0x118/0x11f
[ 4039.051840]  [<c015b932>] sys_write+0x3d/0x64
[ 4039.051845]  [<c0103e7c>] syscall_call+0x7/0xb
[ 4039.051848]  =======================

The problem was that GFP_KERNEL was used; fixed by using gfp_any().
Signed-off-by: NGerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: NArnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NYOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

That accumulated over the last months hackaton, shame on me for not
using git-apply whitespace helping hand, will do that from now on.
Signed-off-by: NArnaldo Carvalho de Melo <acme@mandriva.com>

This patch implements a suggestion by Ian McDonald and

 1) Avoids tests against negative packet lengths by using unsigned int
    for packet payload lengths in the CCID send_packet()/packet_sent() routines

 2) As a consequence, it removes an now unnecessary test with regard to `len > 0'
    in ccid3_hc_tx_packet_sent: that condition is always true, since
      * negative packet lengths are avoided
      * ccid3_hc_tx_send_packet flags an error whenever the payload length is 0.
        As a consequence, ccid3_hc_tx_packet_sent is never called as all errors
        returned by ccid_hc_tx_send_packet are caught in dccp_write_xmit

 3) Removes the third argument of ccid_hc_tx_send_packet (the `len' parameter),
    since it is currently always set to skb->len. The code is updated with regard
    to this parameter change.
Signed-off-by: NGerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: NIan McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: NArnaldo Carvalho de Melo <acme@mandriva.com>

This reaps the benefit of the earlier patch, which changed the type of
CCID 3 states to use enums, in that many conditions are now simplified
and the number of possible (unexpected) values is greatly reduced.

In a few instances, this also allowed to simplify pre-conditions; where
care has been taken to retain logical equivalence.

[DCCP]: Introduce a consistent BUG/WARN message scheme

This refines the existing set of DCCP messages so that
 * BUG(), BUG_ON(), WARN_ON() have meaningful DCCP-specific counterparts
 * DCCP_CRIT (for severe warnings) is not rate-limited
 * DCCP_WARN() is introduced as rate-limited wrapper

Using these allows a faster and cleaner transition to their original
counterparts once the code has matured into a full DCCP implementation.
Signed-off-by: NGerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: NArnaldo Carvalho de Melo <acme@mandriva.com>

This patch
  * makes debugging (when configured) work both for static / module build
  * provides generic debugging macros for use in other DCCP / CCID modules
  * adds missing information about debug parameters to Kconfig
  * performs some code tidy-up
Signed-off-by: NGerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: NArnaldo Carvalho de Melo <acme@mandriva.com>

These are code optimizations which are relevant when dealing with large
windows.  They are not coded the way I would like to, but they do the job for
the short-term.  This patch should be more neat.

Commiter note: Changed the seqno comparisions to use {after,before}48 to handle
               wrapping.
Signed-off-by: NAndrea Bittau <a.bittau@cs.ucl.ac.uk>
Signed-off-by: NArnaldo Carvalho de Melo <acme@mandriva.com>

Fix printk format warnings:
build2.out:net/dccp/ccids/ccid2.c:355: warning: long long unsigned int format, u64 arg (arg 3)
build2.out:net/dccp/ccids/ccid2.c:360: warning: long long unsigned int format, u64 arg (arg 3)
build2.out:net/dccp/ccids/ccid2.c:482: warning: long long unsigned int format, u64 arg (arg 5)
build2.out:net/dccp/ccids/ccid2.c:639: warning: long long unsigned int format, u64 arg (arg 3)
build2.out:net/dccp/ccids/ccid2.c:639: warning: long long unsigned int format, u64 arg (arg 4)
build2.out:net/dccp/ccids/ccid2.c:674: warning: long long unsigned int format, u64 arg (arg 3)
build2.out:net/dccp/ccids/ccid2.c:720: warning: long long unsigned int format, u64 arg (arg 3)
Signed-off-by: NRandy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Updates the references to spec documents throughout the code, taking into
account that

* the DCCP, CCID 2, and CCID 3 drafts all became RFCs in March this year

* RFC 1063 was obsoleted by RFC 1191

* draft-ietf-tcpimpl-pmtud-0x.txt was published as an Informational
  RFC, RFC 2923 on 2000-09-22.

All references verified.
Signed-off-by: NGerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: NArnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

With constants for CCID numbers this now uses them in some places.
Signed-off-by: NIan McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: NArnaldo Carvalho de Melo <acme@mandriva.com>

Introduce methods which manipulate interesting congestion control
state such as pipe and rtt estimate.  This is useful for people
wishing to monitor the variables of CCID and instrument the code
[perhaps using Kprobes].  Personally, I am a fan of
encapsulation---that justifies this change =D.
Signed-off-by: NAndrea Bittau <a.bittau@cs.ucl.ac.uk>
Signed-off-by: NArnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When multiple losses occur in one RTT, the window should be halved
only once [a single "congestion event"].  This is now implemented,
although not perfectly.  Slightly changed the interface for changing
the cwnd: pass hctx instead of dp.  This is required in order to allow
for change_cwnd to be called from _init().
Signed-off-by: NAndrea Bittau <a.bittau@cs.ucl.ac.uk>
Signed-off-by: NArnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Allocate more sequence state on demand.  Each time a packet is sent
out by CCID2, a record of it needs to be kept.  This list of records
grows proportionally to cwnd.  Previously, the length of this list was
hardcored and therefore the cwnd could only grow to this value (of
128).  Now, records are allocated on demand as necessary---cwnd may
grow as it wishes.  The exceptional case of when memory is not
available is not handled gracefully.  Perhaps, cwnd should be capped
at that point.
Signed-off-by: NAndrea Bittau <a.bittau@cs.ucl.ac.uk>
Signed-off-by: NArnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Allow the user to choose whether or not to enable CCID2 debugging via
Kconfig.
Signed-off-by: NAndrea Bittau <a.bittau@cs.ucl.ac.uk>
Signed-off-by: NArnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If not enough cwnd is available, tell the sender to check again as
soon as possible.  This will increase CPU utilization (polling
frequently for cwnd) but will improve network performance.  That is,
the sender will need to wait less before detecting the increase of
cwnd.  A better architecture would be for the CCID to call-back (or
dequeue) from DCCP when it is able to transmit traffic -- not the
other way around as it currently occurs.
Signed-off-by: NAndrea Bittau <a.bittau@cs.ucl.ac.uk>
Signed-off-by: NArnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Initialize the slow-start threshold to infinity.  This way, upon connection
initiation, slow-start will be exited only upon a packet loss.  This patch will
allow connections to quickly gain speed.
Signed-off-by: NAndrea Bittau <a.bittau@cs.ucl.ac.uk>
Signed-off-by: NArnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Jiffies are now handled correctly (I hope) in CCID2.  If they wrap, no
problem.
Signed-off-by: NAndrea Bittau <a.bittau@cs.ucl.ac.uk>
Signed-off-by: NArnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fix the way state is masked out.  DCCP_ACKVEC_STATE_NOT_RECEIVED is
defined as appears in the packet, therefore bit shifting is not
required.  This fix allows CCID2 to correctly detect losses.
Signed-off-by: NAndrea Bittau <a.bittau@cs.ucl.ac.uk>
Signed-off-by: NArnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NJörn Engel <joern@wohnheim.fh-wedel.de>
Signed-off-by: NAdrian Bunk <bunk@stusta.de>

No changes in the logic where made.
Signed-off-by: NArnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

1. No need for ->ccid_init nor ->ccid_exit, this is what module_{init,exit}
   does and anynways neither ccid2 nor ccid3 were using it.

2. Rename struct ccid to struct ccid_operations and introduce struct ccid
   with a pointer to ccid_operations and rigth after it the rx or tx
   private state.

3. Remove the pointer to the state of the half connections from struct
   dccp_sock, now its derived thru ccid_priv() from the ccid pointer.

Now we also can implement the setsockopt for changing the CCID easily as
no ccid init routines can affect struct dccp_sock in any way that prevents
other CCIDs from working if a CCID switch operation is asked by apps.
Signed-off-by: NArnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There was a hybrid use of standard timers and sk_timers.  This caused
the reference count of the sock to be incorrect when resetting the RTO
timer.  The sock reference count should now be correct, enabling its
destruction, and allowing the DCCP module to be unloaded.
Signed-off-by: NAndrea Bittau <a.bittau@cs.ucl.ac.uk>
Signed-off-by: NArnaldo Carvalho de Melo <acme@mandriva.com>

Original work by Andrea Bittau, Arnaldo Melo cleaned up and fixed several
issues on the merge process.

For now CCID2 was turned the default for all SOCK_DCCP connections, but this
will be remedied soon with the merge of the feature negotiation code.
Signed-off-by: NAndrea Bittau <a.bittau@cs.ucl.ac.uk>
Signed-off-by: NArnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>