This migrates more TFRC-related code into the dccp_tfrc_lib:
* sampling of the packet size `s' (which is only needed until the first
loss interval is computed (ccid3_first_li));
* updating the byte-counter `bytes_recvd' in between sending feedbacks.
The result is a better separation of CCID-3 specific and TFRC specific
code, which aids future integration with ECN and e.g. CCID-4.
Further changes:
----------------
* replaced magic number of 536 with equivalent constant TCP_MIN_RCVMSS;
(this constant is also used when no estimate for `s' is available).
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Ensure that cmsg->cmsg_type value is valid for qpolicy
that is currently in use.
Signed-off-by: Tomasz Grobelny <tomasz@grobelny.oswiecenia.net>
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
This patch adds a generic infrastructure for policy-based dequeueing of
TX packets and provides two policies:
* a simple FIFO policy (which is the default) and
* a priority based policy (set via socket options).
Both policies honour the tx_qlen sysctl for the maximum size of the write
queue (can be overridden via socket options).
The priority policy uses skb->priority internally to assign an u32 priority
identifier, using the same ranking as SO_PRIORITY. The skb->priority field
is set to 0 when the packet leaves DCCP. The priority is supplied as ancillary
data using cmsg(3), the patch also provides the requisite parsing routines.
Signed-off-by: Tomasz Grobelny <tomasz@grobelny.oswiecenia.net>
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
This extends the existing wait-for-ccid routine so that it may be used with
different types of CCID. It further addresses the problems listed below.
The code looks if the write queue is non-empty and grants the TX CCID up to
`timeout' jiffies to drain the queue. It will instead purge that queue if
* the delay suggested by the CCID exceeds the time budget;
* a socket error occurred while waiting for the CCID;
* there is a signal pending (eg. annoyed user pressed Control-C);
* the CCID does not support delays (we don't know how long it will take).
D e t a i l s [can be removed]
-------------------------------
DCCP's sending mechanism functions a bit like non-blocking I/O: dccp_sendmsg()
will enqueue up to net.dccp.default.tx_qlen packets (default=5), without waiting
for them to be released to the network.
Rate-based CCIDs, such as CCID3/4, can impose sending delays of up to maximally
64 seconds (t_mbi in RFC 3448). Hence the write queue may still contain packets
when the application closes. Since the write queue is congestion-controlled by
the CCID, draining the queue is also under control of the CCID.
There are several problems that needed to be addressed:
1) The queue-drain mechanism only works with rate-based CCIDs. If CCID2 for
example has a full TX queue and becomes network-limited just as the
application wants to close, then waiting for CCID2 to become unblocked could
lead to an indefinite delay (i.e., application "hangs").
2) Since each TX CCID in turn uses a feedback mechanism, there may be changes
in its sending policy while the queue is being drained. This can lead to
further delays during which the application will not be able to terminate.
3) The minimum wait time for CCID3/4 can be expected to be the queue length
times the current inter-packet delay. For example if tx_qlen=100 and a delay
of 15 ms is used for each packet, then the application would have to wait
for a minimum of 1.5 seconds before being allowed to exit.
4) There is no way for the user/application to control this behaviour. It would
be good to use the timeout argument of dccp_close() as an upper bound. Then
the maximum time that an application is willing to wait for its CCIDs to can
be set via the SO_LINGER option.
These problems are addressed by giving the CCID a grace period of up to the
`timeout' value.
The wait-for-ccid function is, as before, used when the application
(a) has read all the data in its receive buffer and
(b) if SO_LINGER was set with a non-zero linger time, or
(c) the socket is either in the OPEN (active close) or in the PASSIVE_CLOSEREQ
state (client application closes after receiving CloseReq).
In addition, there is a catch-all case by calling __skb_queue_purge() after
waiting for the CCID. This is necessary since the write queue may still have
data when
(a) the host has been passively-closed,
(b) abnormal termination (unread data, zero linger time),
(c) wait-for-ccid could not finish within the given time limit.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
This uses the new feature-negotiation framework to signal Ack Ratio changes,
as required by RFC 4341, sec. 6.1.2.
This raises some problems for CCID-2 since it can at the moment not cope
gracefully with Ack Ratio of e.g. 2. A FIXME has thus been added which
reverts to the existing policy of bypassing the Ack Ratio sysctl.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
This adds full support for local/remote Sequence Window feature, from which the
* sequence-number-validity (W) and
* acknowledgment-number-validity (W') windows
derive as specified in RFC 4340, 7.5.3.
Specifically, the following changes are introduced:
* integrated new socket fields into dccp_sk;
* updated the update_gsr/gss routines with regard to these fields;
* updated handler code: the Sequence Window feature is located at the TX side,
so the local feature is meant if the handler-rx flag is false;
* the initialisation of `rcv_wnd' in reqsk is removed, since
- rcv_wnd is not used by the code anywhere;
- sequence number checks are not done in the LISTEN state (cf. 7.5.3);
- dccp_check_req checks the Ack number validity more rigorously;
* the `struct dccp_minisock' became empty and is now removed.
Until the handshake completes with activating negotiated values, the local/remote
Sequence-Window values are undefined and thus can not reliably be estimated.
This issue is addressed in a separate patch.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
This removes the use of the sysctl and the minisock variable for the Send Ack
Vector feature, which is now handled fully dynamically via feature negotiation;
i.e. when CCID2 is enabled, Ack Vectors are automatically enabled (as per
RFC 4341, 4.).
Using a sysctl in parallel to this implementation would open the door to
crashes, since much of the code relies on tests of the boolean minisock /
sysctl variable. Thus, this patch replaces all tests of type
if (dccp_msk(sk)->dccpms_send_ack_vector)
/* ... */
with
if (dp->dccps_hc_rx_ackvec != NULL)
/* ... */
The dccps_hc_rx_ackvec is allocated by the dccp_hdlr_ackvec() when feature
negotiation concluded that Ack Vectors are to be used on the half-connection.
Otherwise, it is NULL (due to dccp_init_sock/dccp_create_openreq_child),
so that the test is a valid one.
The activation handler for Ack Vectors is called as soon as the feature
negotiation has concluded at the
* server when the Ack marking the transition RESPOND => OPEN arrives;
* client after it has sent its ACK, marking the transition REQUEST => PARTOPEN.
Adding the sequence number of the Response packet to the Ack Vector has been
removed, since
(a) connection establishment implies that the Response has been received;
(b) the CCIDs only look at packets received in the (PART)OPEN state, i.e.
this entry will always be ignored;
(c) it can not be used for anything useful - to detect loss for instance, only
packets received after the loss can serve as pseudo-dupacks.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
This first patch out of three replaces the hardcoded default settings with
initialisation code for the dynamic feature negotiation.
Note on retransmitting Confirm options:
---------------------------------------
This patch also defers flushing the client feature-negotiation queue,
due to the following considerations.
As long as the client is in PARTOPEN, it needs to retransmit the Confirm
options for the Change options received on the DCCP-Response from the server.
Otherwise, if the packet containing the Confirm options gets dropped in the
network, the connection aborts due to undefined feature negotiation state.
Thanks to Leandro Melo de Sales who reported a bug in an earlier revision
of the patch set, resulting from not retransmitting the Confirm options.
The patch now ensures that the client feature-negotiation queue is flushed only
when entering the OPEN state. Since confirmed Change options are removed as
soon as they are confirmed (in the DCCP-Response), this ensures that Confirm
options are retransmitted.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
This provides function to query the current TX/RX CCID dynamically, without
reliance on the minisock value, using dynamic information available in the
currently loaded CCID module.
This query function is then used to
(a) provide the getsockopt part for getting/setting CCIDs via sockopts;
(b) replace the current test for "which CCID is in use" in probe.c.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
With this patch, TX/RX CCIDs can now be changed on a per-connection basis, which
overrides the defaults set by the global sysctl variables for TX/RX CCIDs.
To make full use of this facility, the remaining patches of this patch set are
needed, which track dependencies and activate negotiated feature values.
Note on the maximum number of CCIDs that can be registered:
-----------------------------------------------------------
The maximum number of CCIDs that can be registered on the socket is constrained
by the space in a Confirm/Change feature negotiation option.
The space in these in turn depends on the size of header options as defined
in RFC 4340, 5.8. Since this is a recurring constant, it has been moved from
ackvec.h into linux/dccp.h, clarifying its purpose.
Relative to this size, the maximum number of CCID identifiers that can be
present in a Confirm option (which always consumes 1 byte more than a Change
option, cf. 6.1) is 2 bytes less than the maximum TLV size: one for the
CCID-feature-type and one for the selected value.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
This splits the setsockopt calls into two groups, depending on whether an
integer argument (val) is required and whether routines being called do
their own locking.
Some options (such as setting the CCID) use u8 rather than int, so that for
these the test with regard to integer-sizeof can not be used.
The second switch-case statement now only has those statements which need
locking and which make use of `val'.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Reviewed-by: Eugene Teo <eugeneteo@kernel.sg>
This provides feature negotiation for server minimum checksum coverage
which so far has been missing.
Since sender/receiver coverage values range only from 0...15, their
type has also been reduced in size from u16 to u4.
Feature-negotiation options are now generated for both sender and receiver
coverage, i.e. when the peer has `forgotten' to enable partial coverage
then feature negotiation will automatically enable (negotiate) the partial
coverage value for this connection.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
The previous setsockopt interface, which passed socket options via struct
dccp_so_feat, is complicated/difficult to use. Continuing to support it leads to
ugly code since the old approach did not distinguish between NN and SP values.
This patch removes the old setsockopt interface and replaces it with two new
functions to register NN/SP values for feature negotiation. These are
essentially wrappers around the internal __feat_register functions, with
checking added to avoid
* wrong usage (type);
* changing values while the connection is in progress.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
This provides a missing link in the code chain, as several features implicitly
depend and/or rely on the choice of CCID. Most notably, this is the Send Ack Vector
feature, but also Ack Ratio and Send Loss Event Rate (also taken care of).
For Send Ack Vector, the situation is as follows:
* since CCID2 mandates the use of Ack Vectors, there is no point in allowing
endpoints which use CCID2 to disable Ack Vector features such a connection;
* a peer with a TX CCID of CCID2 will always expect Ack Vectors, and a peer
with a RX CCID of CCID2 must always send Ack Vectors (RFC 4341, sec. 4);
* for all other CCIDs, the use of (Send) Ack Vector is optional and thus
negotiable. However, this implies that the code negotiating the use of Ack
Vectors also supports it (i.e. is able to supply and to either parse or
ignore received Ack Vectors). Since this is not the case (CCID-3 has no Ack
Vector support), the use of Ack Vectors is here disabled, with a comment
in the source code.
An analogous consideration arises for the Send Loss Event Rate feature,
since the CCID-3 implementation does not support the loss interval options
of RFC 4342. To make such use explicit, corresponding feature-negotiation
options are inserted which signal the use of the loss event rate option,
as it is used by the CCID3 code.
Lastly, the values of the Ack Ratio feature are matched to the choice of CCID.
The patch implements this as a function which is called after the user has
made all other registrations for changing default values of features.
The table is variable-length, the reserved (and hence for feature-negotiation
invalid, confirmed by considering section 19.4 of RFC 4340) feature number `0'
is used to mark the end of the table.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
This provides a data structure to record which CCIDs are locally supported
and three accessor functions:
- a test function for internal use which is used to validate CCID requests
made by the user;
- a copy function so that the list can be used for feature-negotiation;
- documented getsockopt() support so that the user can query capabilities.
The data structure is a table which is filled in at compile-time with the
list of available CCIDs (which in turn depends on the Kconfig choices).
Using the copy function for cloning the list of supported CCIDs is useful for
feature negotiation, since the negotiation is now with the full list of available
CCIDs (e.g. {2, 3}) instead of the default value {2}. This means negotiation
will not fail if the peer requests to use CCID3 instead of CCID2.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
Two registration routines, for SP and NN features, are provided by this patch,
replacing a previous routine which was used for both feature types.
These are internal-only routines and therefore start with `__feat_register'.
It further exports the known limits of Sequence Window and Ack Ratio as symbolic
constants.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
This inserts the required de-allocation routines for memory allocated by
feature negotiation in the socket destructors, replacing dccp_feat_clean()
in one instance.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
This provides feature-negotiation initialisation for both DCCP sockets and
DCCP request_sockets, to support feature negotiation during connection setup.
It also resolves a FIXME regarding the congestion control initialisation.
Thanks to Wei Yongjun for help with the IPv6 side of this patch.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
This sets the sysfs permissions so that root can toggle the `debug'
parameter available for nearly every DCCP module. This is useful
since there are various module inter-dependencies. The debug flag
can now be toggled at runtime using
echo 1 > /sys/module/dccp/parameters/dccp_debug
echo 1 > /sys/module/dccp_ccid2/parameters/ccid2_debug
echo 1 > /sys/module/dccp_ccid3/parameters/ccid3_debug
echo 1 > /sys/module/dccp_tfrc_lib/parameters/tfrc_debug
The last is not very useful yet, since no code at the moment calls
the tfrc_debug() macro.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
dccp_disconnect() can be called due to several reasons:
1. when the connection setup failed (inet_stream_connect());
2. when shutting down (inet_shutdown(), inet_csk_listen_stop());
3. when aborting the connection (dccp_close() with 0 linger time).
In case (1) the write queue is empty. This patch empties the write queue,
if in case (2) or (3) it was not yet empty.
This avoids triggering the write-queue BUG_TRAP in sk_stream_kill_queues()
later on.
It also seems natural to do: when breaking an association, to delete all
packets that were originally intended for the soon-disconnected end (compare
with call to tcp_write_queue_purge in tcp_disconnect()).
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Thanks to Eugene Teo for reporting this problem.
Signed-off-by: Eugene Teo <eugenete@kernel.sg>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
Removes legacy reinvent-the-wheel type thing. The generic
machinery integrates much better to automated debugging aids
such as kerneloops.org (and others), and is unambiguous due to
better naming. Non-intuively BUG_TRAP() is actually equal to
WARN_ON() rather than BUG_ON() though some might actually be
promoted to BUG_ON() but I left that to future.
I could make at least one BUILD_BUG_ON conversion.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
Change struct proto destroy function pointer to return void. Noticed
by Al Viro.
Signed-off-by: Brian Haley <brian.haley@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
None of these files use any of the functionality promised by
asm/semaphore.h. It's possible that they rely on it dragging in some
unrelated header file, but I can't build all these files, so we'll have
fix any build failures as they come up.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
dev_queue_xmit() and the other IP output functions expect to get a skb
with clear or properly initialized skb->cb. Unlike TCP and UDP, the
dccp_skb_cb doesn't contain a struct inet_skb_parm at the beginning,
so the DCCP-specific data is interpreted by the IP output functions.
This can cause false negatives for the conditional POST_ROUTING hook
invocation, making the packet bypass the hook.
Add a inet_skb_parm/inet6_skb_parm union to the beginning of
dccp_skb_cb to avoid clashes. Also add a BUILD_BUG_ON to make
sure it fits in the cb.
[ Combined with patch from Gerrit Renker to remove two now unnecessary
memsets of IPCB(skb)->opt ]
Signed-off-by: Patrick McHardy <kaber@trash.net>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This way we can remove TCP and DCCP specific versions of
sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port
sk->sk_prot->hash: inet_hash is directly used, only v6 need
a specific version to deal with mapped sockets
sk->sk_prot->unhash: both v4 and v6 use inet_hash directly
struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so
that inet_csk_get_port can find the per family routine.
Now only the lookup routines receive as a parameter a struct inet_hashtable.
With this we further reuse code, reducing the difference among INET transport
protocols.
Eventually work has to be done on UDP and SCTP to make them share this
infrastructure and get as a bonus inet_diag interfaces so that iproute can be
used with these protocols.
net-2.6/net/ipv4/inet_hashtables.c:
struct proto | +8
struct inet_connection_sock_af_ops | +8
2 structs changed
__inet_hash_nolisten | +18
__inet_hash | -210
inet_put_port | +8
inet_bind_bucket_create | +1
__inet_hash_connect | -8
5 functions changed, 27 bytes added, 218 bytes removed, diff: -191
net-2.6/net/core/sock.c:
proto_seq_show | +3
1 function changed, 3 bytes added, diff: +3
net-2.6/net/ipv4/inet_connection_sock.c:
inet_csk_get_port | +15
1 function changed, 15 bytes added, diff: +15
net-2.6/net/ipv4/tcp.c:
tcp_set_state | -7
1 function changed, 7 bytes removed, diff: -7
net-2.6/net/ipv4/tcp_ipv4.c:
tcp_v4_get_port | -31
tcp_v4_hash | -48
tcp_v4_destroy_sock | -7
tcp_v4_syn_recv_sock | -2
tcp_unhash | -179
5 functions changed, 267 bytes removed, diff: -267
net-2.6/net/ipv6/inet6_hashtables.c:
__inet6_hash | +8
1 function changed, 8 bytes added, diff: +8
net-2.6/net/ipv4/inet_hashtables.c:
inet_unhash | +190
inet_hash | +242
2 functions changed, 432 bytes added, diff: +432
vmlinux:
16 functions changed, 485 bytes added, 492 bytes removed, diff: -7
/home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c:
tcp_v6_get_port | -31
tcp_v6_hash | -7
tcp_v6_syn_recv_sock | -9
3 functions changed, 47 bytes removed, diff: -47
/home/acme/git/net-2.6/net/dccp/proto.c:
dccp_destroy_sock | -7
dccp_unhash | -179
dccp_hash | -49
dccp_set_state | -7
dccp_done | +1
5 functions changed, 1 bytes added, 242 bytes removed, diff: -241
/home/acme/git/net-2.6/net/dccp/ipv4.c:
dccp_v4_get_port | -31
dccp_v4_request_recv_sock | -2
2 functions changed, 33 bytes removed, diff: -33
/home/acme/git/net-2.6/net/dccp/ipv6.c:
dccp_v6_get_port | -31
dccp_v6_hash | -7
dccp_v6_request_recv_sock | +5
3 functions changed, 5 bytes added, 38 bytes removed, diff: -33
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This replaces 4 individual assignments for `len' with a single
one, placed where the control flow of those 4 leads to.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This adds a socket option and signalling support for the case where the server
holds timewait state on closing the connection, as described in RFC 4340, 8.3.
Since holding timewait state at the server is the non-usual case, it is enabled
via a socket option. Documentation for this socket option has been added.
The setsockopt statement has been made resilient against different possible cases
of expressing boolean `true' values using a suggestion by Ian McDonald.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When performing active close, RFC 4340, 8.3. requires to retransmit the
Close/CloseReq with a backoff-retransmit timer starting at intially 2 RTTs.
This patch shifts the existing code for active-close retransmit timer
into output.c, so that the retransmit timer is started when the first
Close/CloseReq is sent. Previously, the timer was started when, after
releasing the socket in dccp_close(), the actively-closing side had not yet
reached the CLOSED/TIMEWAIT state.
The patch further reduces the initial timeout from 3 seconds to the required
2 RTTs, where - in absence of a known RTT - the fallback value specified in
RFC 4340, 3.4 is used.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This adds the necessary state transitions for the two forms of passive-close
* PASSIVE_CLOSE - which is entered when a host receives a Close;
* PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq.
Here is a detailed account of what the patch does in each state.
1) Receiving CloseReq
The pseudo-code in 8.5 says:
Step 13: Process CloseReq
If P.type == CloseReq and S.state < CLOSEREQ,
Generate Close
S.state := CLOSING
Set CLOSING timer.
This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN.
* CLOSED: silently ignore - it may be a late or duplicate CloseReq;
* LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client);
* REQUEST: perform Step 13 directly (no need to enqueue packet);
* OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data.
When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored.
I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where
the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it
gets the Reset, so ignoring the CloseReq while in state CLOSING is sane.
2) Receiving Close
The code below from 8.5 is unconditional.
Step 14: Process Close
If P.type == Close,
Generate Reset(Closed)
Tear down connection
Drop packet and return
Thus we need to consider all states:
* CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives;
* LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection");
* REQUEST: perform Step 14 directly (no need to enqueue packet);
* RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that;
* OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data;
* CLOSEREQ: server performed active-close -- perform Step 14;
* CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment);
* PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close);
* TIMEWAIT: packet is ignored.
Note that the condition of receiving a packet in state CLOSED here is different from the condition "there
is no socket for such a connection": the socket still exists, but its state indicates it is unusable.
Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that
sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED).
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This adds two auxiliary states to deal with passive closes:
* PASSIVE_CLOSE (reached from OPEN via reception of Close) and
* PASSIVE_CLOSEREQ (reached from OPEN via reception of CloseReq)
as internal intermediate states.
These states are used to allow a receiver to process unread data before
acknowledging the received connection-termination-request (the Close/CloseReq).
Without such support, it will happen that passively-closed sockets enter CLOSED
state while there is still unprocessed data in the queue; leading to unexpected
and erratic API behaviour.
PASSIVE_CLOSE has been mapped into TCPF_CLOSE_WAIT, so that the code will
seamlessly work with inet_accept() (which tests for this state).
The state names are thanks to Arnaldo, who suggested this naming scheme
following an earlier revision of this patch.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This continues from the previous patch and adds support for actively aborting
a DCCP connection, using a Reset Code 2, "Aborted" to inform the peer of an
abortive release.
I have tried this in various client/server settings and it works as expected.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This removes one FIXME with regard to close when there is still unread data.
The mechanism is implemented similar to TCP: with regard to DCCP-specifics,
a Reset with Code 2, "Aborted" is sent to the peer.
This corresponds in part to RFC 4340, 8.1.1 and 8.1.5.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is because in the next patch CCID2 will assume that dccps_mss_cache is
non-zero.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This extends the DCCP socket API by honouring any shutdown(2) option set by the user.
The behaviour is, as much as possible, made consistent with the API for TCP's shutdown.
This patch exploits the information provided by the user via the socket API to reduce
processing costs:
* if the read end is closed (SHUT_RD), it is not necessary to deliver to input CCID;
* if the write end is closed (SHUT_WR), the same idea applies, but with a difference -
as long as the TX queue has not been drained, we need to receive feedback to keep
congestion-control rates up to date. Hence SHUT_WR is honoured only after the last
packet (under congestion control) has been sent;
* although SHUT_RDWR seems nonsensical, it is nevertheless supported in the same manner
as for TCP (and agrees with test for SHUTDOWN_MASK in dccp_poll() in net/dccp/proto.c).
Furthermore, most of the code already honours the sk_shutdown flags (dccp_recvmsg() for
instance sets the read length to 0 if SHUT_RD had been called); CCID handling is now added
to this by the present patch.
There will also no longer be any delivery when the socket is in the final stages, i.e. when
one of dccp_close(), dccp_fin(), or dccp_done() has been called - which is fine since at
that stage the connection is its final stages.
Motivation and background are on http://www.erg.abdn.ac.uk/users/gerrit/dccp/notes/shutdown
A FIXME has been added to notify the other end if SHUT_RD has been set (RFC 4340, 11.7).
Note: There is a comment in inet_shutdown() in net/ipv4/af_inet.c which asks to "make
sure the socket is a TCP socket". This should probably be extended to mean
`TCP or DCCP socket' (the code is also used by UDP and raw sockets).
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As done two years ago on IP route cache table (commit
22c047ccbc) , we can avoid using one
lock per hash bucket for the huge TCP/DCCP hash tables.
On a typical x86_64 platform, this saves about 2MB or 4MB of ram, for
litle performance differences. (we hit a different cache line for the
rwlock, but then the bucket cache line have a better sharing factor
among cpus, since we dirty it less often). For netstat or ss commands
that want a full scan of hash table, we perform fewer memory accesses.
Using a 'small' table of hashed rwlocks should be more than enough to
provide correct SMP concurrency between different buckets, without
using too much memory. Sizing of this table depends on
num_possible_cpus() and various CONFIG settings.
This patch provides some locking abstraction that may ease a future
work using a different model for TCP/DCCP table.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Just like UDP.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Leandro Melo de Sales <leandroal@gmail.com>
Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: David S. Miller <davem@davemloft.net>
This just sets the parameter to bool, since debugging messages are
either on or off.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This enables applications to query the current value of the Maximum
Packet Size via a socket option, suggested as a SHOULD in (RFC 4340,
p. 102).
This socket option is useful to avoid the annoying bail-out via
`-EMSGSIZE'. In particular, as fragmentation is not currently
supported (and its use is partly discouraged in RFC 4340).
With this option, it is possible to size buffers accordingly, e.g.
int buflen = dccp_get_cur_mps(sockfd);
/* or */
if (msgsize > dccp_get_cur_mps(sockfd))
die("message is too large for this path");
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since DCCP requires to close both ends of a connection simultaneously,
permission to write in state DCCP_CLOSING is removed in dccp_sendmsg():
* if the sending end closed, it would encounter a write error anyhow;
* if the other end has closed the connection, it accepts no more data.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
This implements a SHOULD from RFC 4340, 7.5.4:
"To protect against denial-of-service attacks, DCCP implementations SHOULD
impose a rate limit on DCCP-Syncs sent in response to sequence-invalid packets,
such as not more than eight DCCP-Syncs per second."
The rate-limit is maintained on a per-socket basis. This is a more stringent
policy than enforcing the rate-limit on a per-source-address basis and
protects against attacks with forged source addresses.
Moreover, the mechanism is deliberately kept simple. In contrast to
xrlim_allow(), bursts of Sync packets in reply to sequence-invalid packets
are not supported. This foils such attacks where the receipt of a Sync
triggers further sequence-invalid packets. (I have tested this mechanism against
xrlim_allow algorithm for Syncs, permitting bursts just increases the problems.)
In order to keep flexibility, the timeout parameter can be set via sysctl; and
the whole mechanism can even be disabled (which is however not recommended).
The algorithm in this patch has been improved with regard to wrapping issues
thanks to a suggestion by Arnaldo.
Commiter note: Rate limited the step 6 DCCP_WARN too, as it says we're
sending a sync.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
This provides a timesource, conveniently used for DCCP timestamps, which
returns the elapsed time in 10s of microseconds since initialisation.
This makes for a wrap-around time of about 11.9 hours, which should be
sufficient for most applications.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Slab destructors were no longer supported after Christoph's
c59def9f22 change. They've been
BUGs for both slab and slub, and slob never supported them
either.
This rips out support for the dtor pointer from kmem_cache_create()
completely and fixes up every single callsite in the kernel (there were
about 224, not including the slab allocator definitions themselves,
or the documentation references).
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
We were only checking if there was enough space to put the int, but
left len as specified by the (malicious) user, sigh, fix it by setting
len to sizeof(val) and transfering just one int worth of data, the one
asked for.
Also check for negative len values.
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
ehash table layout is currently this one :
First half of this table is used by sockets not in TIME_WAIT state
Second half of it is used by sockets in TIME_WAIT state.
This is non optimal because of for a given hash or socket, the two chain heads
are located in separate cache lines.
Moreover the locks of the second half are never used.
If instead of this halving, we use two list heads in inet_ehash_bucket instead
of only one, we probably can avoid one cache miss, and reduce ram usage,
particularly if sizeof(rwlock_t) is big (various CONFIG_DEBUG_SPINLOCK,
CONFIG_DEBUG_LOCK_ALLOC settings). So we still halves the table but we keep
together related chains to speedup lookups and socket state change.
In this patch I did not try to align struct inet_ehash_bucket, but a future
patch could try to make this structure have a convenient size (a power of two
or a multiple of L1_CACHE_SIZE).
I guess rwlock will just vanish as soon as RCU is plugged into ehash :) , so
maybe we dont need to scratch our heads to align the bucket...
Note : In case struct inet_ehash_bucket is not a power of two, we could
probably change alloc_large_system_hash() (in case it use __get_free_pages())
to free the unused space. It currently allocates a big zone, but the last
quarter of it could be freed. Again, this should be a temporary 'problem'.
Patch tested on ipv4 tcp only, but should be OK for IPV6 and DCCP.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Gerrit Renker