Patrick McHardy [Thu, 30 Nov 2006 01:36:43 +0000 (17:36 -0800)]
[NET_SCHED]: Fix endless loops (part 3): HFSC
Convert HFSC to use qdisc_tree_decrease_len() and add a callback
for deactivating a class when its child queue becomes empty.
All queue purging goes through hfsc_purge_queue(), which is used in
three cases: grafting, class creation (when a leaf class is turned
into an intermediate class by attaching a new class) and class
deletion. In all cases qdisc_tree_decrease_len() is needed.
Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
There are multiple problems related to qlen adjustment that can lead
to an upper qdisc getting out of sync with the real number of packets
queued, leading to endless dequeueing attempts by the upper layer code.
All qdiscs must maintain an accurate q.qlen counter. There are basically
two groups of operations affecting the qlen: operations that propagate
down the tree (enqueue, dequeue, requeue, drop, reset) beginning at the
root qdisc and operations only affecting a subtree or single qdisc
(change, graft, delete class). Since qlen changes during operations from
the second group don't propagate to ancestor qdiscs, their qlen values
become desynchronized.
This patch adds a function to propagate qlen changes up the qdisc tree,
optionally calling a callback function to perform qdisc-internal
maintenance when the child qdisc becomes empty. The follow-up patches
will convert all qdiscs to use this function where necessary.
Noticed by Timo Steinbach <tsteinbach@astaro.com>.
Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
Patrick McHardy [Thu, 30 Nov 2006 01:34:50 +0000 (17:34 -0800)]
[NET_SCHED]: sch_htb: perform qlen adjustment immediately in ->delete
qlen adjustment should happen immediately in ->delete and not in the
class destroy function because the reference count will not hit zero in
->delete (sch_api holds a reference) but in ->put. Since the qdisc
lock is released between deletion of the class and final destruction
this creates an externally visible error in the qlen counter.
Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
James Morris [Wed, 29 Nov 2006 21:50:27 +0000 (16:50 -0500)]
Rename class_destroy to avoid namespace conflicts.
We're seeing increasing namespace conflicts between the global
class_destroy() function declared in linux/device.h, and the private
function in the SELinux core code. This patch renames the SELinux
function to cls_destroy() to avoid this conflict.
Acked-by: Stephen Smalley <sds@tycho.nsa.gov> Signed-off-by: James Morris <jmorris@namei.org>
Paul Moore [Wed, 29 Nov 2006 18:18:20 +0000 (13:18 -0500)]
NetLabel: add the ranged tag to the CIPSOv4 protocol
Add support for the ranged tag (tag type #5) to the CIPSOv4 protocol.
The ranged tag allows for seven, or eight if zero is the lowest category,
category ranges to be specified in a CIPSO option. Each range is specified by
two unsigned 16 bit fields, each with a maximum value of 65534. The two values
specify the start and end of the category range; if the start of the category
range is zero then it is omitted.
See Documentation/netlabel/draft-ietf-cipso-ipsecurity-01.txt for more details.
Signed-off-by: Paul Moore <paul.moore@hp.com> Signed-off-by: James Morris <jmorris@namei.org>
Paul Moore [Wed, 29 Nov 2006 18:18:19 +0000 (13:18 -0500)]
NetLabel: add the enumerated tag to the CIPSOv4 protocol
Add support for the enumerated tag (tag type #2) to the CIPSOv4 protocol.
The enumerated tag allows for 15 categories to be specified in a CIPSO option,
where each category is an unsigned 16 bit field with a maximum value of 65534.
See Documentation/netlabel/draft-ietf-cipso-ipsecurity-01.txt for more details.
Signed-off-by: Paul Moore <paul.moore@hp.com> Signed-off-by: James Morris <jmorris@namei.org>
Paul Moore [Wed, 29 Nov 2006 18:18:18 +0000 (13:18 -0500)]
NetLabel: convert to an extensibile/sparse category bitmap
The original NetLabel category bitmap was a straight char bitmap which worked
fine for the initial release as it only supported 240 bits due to limitations
in the CIPSO restricted bitmap tag (tag type 0x01). This patch converts that
straight char bitmap into an extensibile/sparse bitmap in order to lay the
foundation for other CIPSO tag types and protocols.
This patch also has a nice side effect in that all of the security attributes
passed by NetLabel into the LSM are now in a format which is in the host's
native byte/bit ordering which makes the LSM specific code much simpler; look
at the changes in security/selinux/ss/ebitmap.c as an example.
Signed-off-by: Paul Moore <paul.moore@hp.com> Signed-off-by: James Morris <jmorris@namei.org>
Bart De Schuymer [Wed, 29 Nov 2006 01:35:40 +0000 (02:35 +0100)]
[NETFILTER]: ebtables: add --snap-arp option
The attached patch adds --snat-arp support, which makes it possible to
change the source mac address in both the mac header and the arp header
with one rule.
Signed-off-by: Bart De Schuymer <bdschuym@pandora.be> Signed-off-by: Patrick McHardy <kaber@trash.net>
Patrick McHardy [Wed, 29 Nov 2006 01:35:38 +0000 (02:35 +0100)]
[NETFILTER]: x_tables: add NFLOG target
Add new NFLOG target to allow use of nfnetlink_log for both IPv4 and IPv6.
Currently we have two (unsupported by userspace) hacks in the LOG and ULOG
targets to optionally call to the nflog API. They lack a few features,
namely the IPv4 and IPv6 LOG targets can not specify a number of arguments
related to nfnetlink_log, while the ULOG target is only available for IPv4.
Remove those hacks and add a clean way to use nfnetlink_log.
[NETFILTER]: ctnetlink: rework conntrack fields dumping logic on events
| NEW | UPDATE | DESTROY |
----------------------------------------|
tuples | Y | Y | Y |
status | Y | Y | N |
timeout | Y | Y | N |
protoinfo | S | S | N |
helper | S | S | N |
mark | S | S | N |
counters | F | F | Y |
Leyend:
Y: yes
N: no
S: iif the field is set
F: iif overflow
This patch also replace IPCT_HELPINFO by IPCT_HELPER since we want to
track the helper assignation process, not the changes in the private
information held by the helper.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: Patrick McHardy <kaber@trash.net>
Patrick McHardy [Wed, 29 Nov 2006 01:35:30 +0000 (02:35 +0100)]
[NETFILTER]: sip conntrack: better NAT handling
The NAT handling of the SIP helper has a few problems:
- Request headers are only mangled in the reply direction, From/To headers
not at all, which can lead to authentication failures with DNAT in case
the authentication domain is the IP address
- Contact headers in responses are only mangled for REGISTER responses
- Headers may be mangled even though they contain addresses not
participating in the connection, like alternative addresses
- Packets are droppen when domain names are used where the helper expects
IP addresses
This patch takes a different approach, instead of fixed rules what field
to mangle to what content, it adds symetric mapping of From/To/Via/Contact
headers, which allows to deal properly with echoed addresses in responses
and foreign addresses not belonging to the connection.
Patrick McHardy [Wed, 29 Nov 2006 01:35:26 +0000 (02:35 +0100)]
[NETFILTER]: sip conntrack: minor cleanup
- Use enum for header field enumeration
- Use numerical value instead of pointer to header info structure to
identify headers, unexport ct_sip_hdrs
- group SIP and SDP entries in header info structure
- remove double forward declaration of ct_sip_get_info
The NAT helpr hooks are protected by RCU, but all of the
conntrack helpers test and use the global pointers instead
of copying them first using rcu_dereference()
Also replace synchronize_net() by synchronize_rcu() for clarity
since sychronizing only with packet receive processing is
insufficient to prevent races.
Patrick McHardy [Wed, 29 Nov 2006 01:35:17 +0000 (02:35 +0100)]
[NETFILTER]: nf_conntrack: automatic sysctl registation for conntrack protocols
Add helper functions for sysctl registration with optional instantiating
of common path elements (like net/netfilter) and use it for support for
automatic registation of conntrack protocol sysctls.
Martin Josefsson [Wed, 29 Nov 2006 01:35:12 +0000 (02:35 +0100)]
[NETFILTER]: nf_conntrack: reduce timer updates in __nf_ct_refresh_acct()
Only update the conntrack timer if there's been at least HZ jiffies since
the last update. Reduces the number of del_timer/add_timer cycles from one
per packet to one per connection per second (plus once for each state change
of a connection)
Should handle timer wraparounds and connection timeout changes.
Signed-off-by: Martin Josefsson <gandalf@wlug.westbo.se> Signed-off-by: Patrick McHardy <kaber@trash.net>
Rename 'struct nf_conntrack_protocol' to 'struct nf_conntrack_l4proto' in
order to help distinguish it from 'struct nf_conntrack_l3proto'. It gets
rather confusing with 'nf_conntrack_protocol'.
Signed-off-by: Martin Josefsson <gandalf@wlug.westbo.se> Signed-off-by: Patrick McHardy <kaber@trash.net>
Gerrit Renker [Tue, 28 Nov 2006 21:55:06 +0000 (19:55 -0200)]
[DCCP]: Use `unsigned' for packet lengths
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: 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@mandriva.com>
Gerrit Renker [Tue, 28 Nov 2006 21:51:42 +0000 (19:51 -0200)]
[DCCP] ccid3: Larger initial windows
This implements the larger-initial-windows feature for CCID 3, as described in
section 5 of RFC 4342. When the first feedback packet arrives, the sender can
send up to 2..4 packets per RTT, instead of just one.
The patch further
* reduces the number of timestamping calls by passing the timestamp value
(which is computed in one of the calling functions anyway) as argument
* renames one constant with a very long name into one which is shorter and
resembles the one in RFC 3448 (t_mbi)
* simplifies some of the min_t/max_t cases where both `x', `y' have the same
type
Commiter note: renamed TFRC_t_mbi to TFRC_T_MBI, to follow Linux coding style.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Gerrit Renker [Tue, 28 Nov 2006 21:33:36 +0000 (19:33 -0200)]
[DCCP]: Tidy up unused structures
This removes and cleans up unused variables and structures which have become
unnecessary following the introduction of the EWMA patch to automatically track
the CCID 3 receiver/sender packet sizes `s'.
It deprecates the PACKET_SIZE socket option by returning an error code and
printing a deprecation warning if an application tries to read or write this
socket option.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Gerrit Renker [Tue, 28 Nov 2006 20:34:34 +0000 (18:34 -0200)]
[DCCP] ccid3: Set NoFeedback Timeout according to RFC 3448
This corrects the setting of the nofeedback timer with regard to RFC
3448 - previously it was not set to max(4*R, 2*s/X) as specified. Using
the maximum of 1 second as upper bound (as it was done before) can have
detrimental effects, especially if R is small.
Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Gerrit Renker [Tue, 28 Nov 2006 20:14:10 +0000 (18:14 -0200)]
[DCCP]: Remove allocation of sysctl numbers
This is in response to a request sent earlier by Eric W. Biederman
and replaces all sysctl numbers for net.dccp.default with CTL_UNNUMBERED.
It has been tested to compile and to work.
Commiter note: I've removed the use of CTL_UNNUMBERED, not setting .ctl_name
sets it to 0, that is the what CTL_UNNUMBERED is, reason is
to avoid unneeded source code cluttering.
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@mandriva.com>
Gerrit Renker [Mon, 27 Nov 2006 22:32:37 +0000 (20:32 -0200)]
[DCCP] ccid3: Consolidate handling of t_RTO
This patch
* removes setting t_RTO in ccid3_hc_tx_init (per [RFC 3448, 4.2], t_RTO is
undefined until feedback has been received);
* makes some trivial changes (updates of comments);
* performs a small optimisation by exploiting that the feedback timeout
uses the value of t_ipi. The way it is done is safe, because the timeouts
appear after the changes to t_ipi, ensuring that up-to-date values are used;
* in ccid3_hc_tx_packet_recv, moves the t_rto statement closer to the calculation
of the next_tmout. This makes the code clearer to read and is also safe, since
t_rto is not updated until the next call of ccid3_hc_tx_packet_recv, and is not
read by the functions called via ccid_wait_for_ccid();
* removes a `max' statement in sk_reset_timer, this is not needed since the timeout
value is always greater than 1E6 microseconds.
* adds `XXX'es to highlight that currently the nofeedback timer is set
in a non-standard way
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
* consolidates updating of parameters (t_nom, t_ipi, t_delta) which
need to be updated at the same time, since they are inter-dependent
* removes two inline functions which are no longer needed as a result of
the above consolidation
* resolves a FIXME regarding the re-calculation of t_ipi within the nofeedback
timer, in the state where no feedback has previously been received
* ties updating these parameters to updating the sending rate X, exploiting
that all three parameters in turn depend on X; and using a small optimisation
which can reduce the number of required instructions: only update the three
parameters when X really changes
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Gerrit Renker [Mon, 27 Nov 2006 22:29:27 +0000 (20:29 -0200)]
[DCCP] ccid3: Consolidate timer resets
This patch concerns updating the value of the nofeedback timer when no feedback
has been received so far.
Since in this case the value of R is still undefined according to [RFC 3448,
4.2], we can not perform step (3) of [RFC 3448, 4.3]. A clarification is
provided in [RFC 4342, sec. 5], which states that in these cases the nofeedback
timer (still) expires "after two seconds".
Many thanks to Ian McDonald for pointing this out and providing the
clarification.
The patch
* implements [RFC 4342, sec. 5] with regard to the above case
* consolidates handling timer restart by
- adding an appropriate jump label and
- initialising the timeout value
Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Gerrit Renker [Mon, 27 Nov 2006 17:29:59 +0000 (09:29 -0800)]
[UDP(-Lite)]: consolidate v4 and v6 get|setsockopt code
This patch consolidates set/getsockopt code between UDP(-Lite) v4 and 6. The
justification is that UDP(-Lite) is a transport-layer protocol and therefore
the socket option code (at least in theory) should be AF-independent.
Furthermore, there is the following code reduplication:
* do_udp{,v6}_getsockopt is 100% identical between v4 and v6
* do_udp{,v6}_setsockopt is identical up to the following differerence
--v4 in contrast to v4 additionally allows the experimental encapsulation
types UDP_ENCAP_ESPINUDP and UDP_ENCAP_ESPINUDP_NON_IKE
--the remainder is identical between v4 and v6
I believe that this difference is of little relevance.
The advantages in not duplicating twice almost completely identical code.
The patch further simplifies the interface of udp{,v6}_push_pending_frames,
since for the second argument (struct udp_sock *up) it always holds that
up = udp_sk(sk); where sk is the first function argument.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
Gerrit Renker [Mon, 27 Nov 2006 14:27:55 +0000 (12:27 -0200)]
[DCCP] ccid3: Remove redundant statements in ccid3_hc_tx_packet_sent
This patch removes a switch statement which is redundant since,
* nothing is done in states TFRC_SSTATE_NO_SENT/TFRC_SSTATE_NO_FBACK
* it is impossible that the function is called in the state TFRC_SSTATE_TERM, since
--the function is called, in dccp_write_xmit, after ccid3_hc_tx_send_packet
--if ccid3_hc_tx_send_packet is called in state TFRC_SSTATE_TERM, it returns
-EINVAL, which means that ccid3_hc_tx_packet_sent will not be called
(compare dccp_write_xmit)
--> therefore, this case is logically impossible
* the remaining state is TFRC_SSTATE_FBACK which conditionally updates t_ipi, t_nom,
and t_delta. This is a no-op, since
--t_ipi only changes when feedback is received
--however, when feedback arrives via ccid3_hc_tx_packet_recv, there is an identical
code block which performs the same set of operations
--performing the same set of operations again in ccid3_hc_tx_packet_sent therefore
does not change anything, since between the time of receiving the last feedback
(and therefore update of t_ipi, t_nom, and t_delta), the value of t_ipi has not
changed
--since t_ipi has not changed, the values of t_delta and t_nom also do not change,
they depend fully on t_ipi
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Gerrit Renker [Mon, 27 Nov 2006 14:26:57 +0000 (12:26 -0200)]
[DCCP] ccid3: Avoid congestion control on zero-sized data packets
This resolves an `XXX' in ccid3_hc_tx_send_packet().
The function is only called on Data and DataAck packets and returns a negative
result on zero-sized messages. This is a reasonable policy since CCID 3 is a
congestion-control module and congestion control on zero-sized Data(Ack)
packets is in a way pathological.
The patch uses a more suitable error code for this case, it returns the Posix.1
code `EBADMSG' ("Not a data message") instead of `ENOTCONN'.
As a result of ignoring zero-sized packets, a the condition for a warning
"First packet is data" in ccid3_hc_tx_packet_sent is always satisfied; this
message has been removed since it will always be printed.
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@mandriva.com>
Gerrit Renker [Mon, 27 Nov 2006 14:22:48 +0000 (12:22 -0200)]
[DCCP] ccid3: Simplify control flow in the calculation of t_ipi
This patch performs a simplifying (performance) optimisation:
In each call of the inline function ccid3_calc_new_t_ipi(), the state is
tested against TFRC_SSTATE_NO_FBACK. This is expensive when the function
is called very often. A simpler solution, implemented by this patch, is
to adapt the control flow.
Andrea Bittau [Sun, 26 Nov 2006 03:04:40 +0000 (01:04 -0200)]
[DCCP] ackvec: Split long ack vectors across multiple options
Ack vectors grow proportional to the window size. If an ack vector does not fit
into a single option, it must be spread across multiple options. This patch
will allow for windows to grow larger.
Committer note: Simplified the patch a bit, original algorithm kept.
Signed-off-by: Andrea Bittau <a.bittau@cs.ucl.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Andrea Bittau [Fri, 24 Nov 2006 15:02:42 +0000 (13:02 -0200)]
[DCCP] ackvec: infrastructure for sending more than one ackvec per packet
Commiter note:
This was split from Andrea's original patch, in the process I changed the type
of the ackvec index fields to u16 instead of to int and haven't folded
dccp_ackvec_parse with dccp_ackvec_check_rcv_ackno.
Next patch will actually do the insertion of more than one ackvec per packet,
using, initially, up to a max of 2 ackvecs as per Andrea's original patch, then
I'll work on support for larger ackvecs, be it using a sysctl or using
setsockopt.
Signed-off-by: Andrea Bittau <a.bittau@cs.ucl.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Ville Nuorvala [Sat, 25 Nov 2006 01:06:27 +0000 (17:06 -0800)]
[IPV6]: Do mandatory IPv6 tunnel endpoint checks in realtime
Doing the mandatory tunnel endpoint checks when the tunnel is set up
isn't enough as interfaces can go up or down and addresses can be
added or deleted after this. The checks need to be done realtime when
the tunnel is processing a packet.
Signed-off-by: Ville Nuorvala <vnuorval@tcs.hut.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
projects / linux-2.6-omap-h63xx.git / log