One of my x86_64 (linux 2.6.13) server log is filled with :

schedule_timeout: wrong timeout value ffffffffffffff06 from ffffffff802e63ca
schedule_timeout: wrong timeout value ffffffffffffff06 from ffffffff802e63ca
schedule_timeout: wrong timeout value ffffffffffffff06 from ffffffff802e63ca
schedule_timeout: wrong timeout value ffffffffffffff06 from ffffffff802e63ca
schedule_timeout: wrong timeout value ffffffffffffff06 from ffffffff802e63ca

This is because some application does a

struct linger li;
li.l_onoff = 1;
li.l_linger = -1;
setsockopt(sock, SOL_SOCKET, SO_LINGER, &li, sizeof(li));

And unfortunatly l_linger is defined as a 'signed int' in
include/linux/socket.h:

struct linger {
         int             l_onoff;        /* Linger active                */
         int             l_linger;       /* How long to linger for       */
};

I dont know if it's safe to change l_linger to 'unsigned int' in the
include file (It might be defined as int in ABI specs)
Signed-off-by: NEric Dumazet <dada1@cosmosbay.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Patrick McHardy says:

  Never mind, I got it, we never fall through to the second switch
  statement anymore. I think we could simply break when load_pointer
  returns NULL. The switch statement will fall through to the default
  case and return 0 for all cases but 0 > k >= SKF_AD_OFF.

Here's a patch to do just that.

I left BPF_MSH alone because it's really a hack to calculate the IP
header length, which makes no sense when applied to the special data.
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The ipv4 and ipv6 protocols need to access it unconditionally.
SYSCTL=n build failure reported by Russell King.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NJeff Garzik <jgarzik@pobox.com>

This patch puts mostly read only data in the right section
(read_mostly), to help sharing of these data between CPUS without
memory ping pongs.

On one of my production machine, tcp_statistics was sitting in a
heavily modified cache line, so *every* SNMP update had to force a
reload.
Signed-off-by: NEric Dumazet <dada1@cosmosbay.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds a new field to net device to hold the permanent
hardware address, and adds a new generic ethtool_op function to
get that address.
Signed-off-by: NJon Wetzel <jon_wetzel@dell.com>
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Protocols that make extensive use of SKB cloning,
for example TCP, eat at least 2 allocations per
packet sent as a result.

To cut the kmalloc() count in half, we implement
a pre-allocation scheme wherein we allocate
2 sk_buff objects in advance, then use a simple
reference count to free up the memory at the
correct time.

Based upon an initial patch by Thomas Graf and
suggestions from Herbert Xu.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Of this type, mostly:

CHECK   net/ipv6/netfilter.c
net/ipv6/netfilter.c:96:12: warning: symbol 'ipv6_netfilter_init' was not declared. Should it be static?
net/ipv6/netfilter.c:101:6: warning: symbol 'ipv6_netfilter_fini' was not declared. Should it be static?
Signed-off-by: NArnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NPatrick McHardy <kaber@trash.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NPatrick McHardy <kaber@trash.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Reduces skb size by 8 bytes on 64-bit.
Signed-off-by: NPatrick McHardy <kaber@trash.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch doesn't introduce any code changes, but merely splits the
core netfilter code into four separate files.  It also moves it from
it's old location in net/core/ to the recently-created net/netfilter/
directory.
Signed-off-by: NHarald Welte <laforge@netfilter.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

With this we're very close to getting all of the current TCP
refactorings in my dccp-2.6 tree merged, next changeset will export
some functions needed by the current DCCP code and then dccp-2.6.git
will be born!
Signed-off-by: NArnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Out of tcp_create_openreq_child, will be used in
dccp_create_openreq_child, and is a nice sock function anyway.
Signed-off-by: NArnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This paves the way to generalise the rest of the sock ID lookup
routines and saves some bytes in TCPv4 TIME_WAIT sockets on distro
kernels (where IPv6 is always built as a module):

[root@qemu ~]# grep tw_sock /proc/slabinfo
tw_sock_TCPv6  0  0  128  31  1
tw_sock_TCP    0  0   96  41  1
[root@qemu ~]#

Now if a protocol wants to use the TIME_WAIT generic infrastructure it
only has to set the sk_prot->twsk_obj_size field with the size of its
inet_timewait_sock derived sock and proto_register will create
sk_prot->twsk_slab, for now its only for INET sockets, but we can
introduce timewait_sock later if some non INET transport protocolo
wants to use this stuff.

Next changesets will take advantage of this new infrastructure to
generalise even more TCP code.

[acme@toy net-2.6.14]$ grep built-in /tmp/before.size /tmp/after.size
/tmp/before.size: 188646   11764    5068  205478   322a6 net/ipv4/built-in.o
/tmp/after.size:  188144   11764    5068  204976   320b0 net/ipv4/built-in.o
[acme@toy net-2.6.14]$

Tested with both IPv4 & IPv6 (::1 (localhost) & ::ffff:172.20.0.1
(qemu host)).
Signed-off-by: NArnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Lots of places just needs the states, not even linux/tcp.h, where this
enum was, needs it.

This speeds up development of the refactorings as less sources are
rebuilt when things get moved from net/tcp.h.
Signed-off-by: NArnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch is in preparation to nfnetlink_log:
- loggers now have to register struct nf_logger instead of nf_logfn
- nf_log_unregister() replaced by nf_log_unregister_pf() and
  nf_log_unregister_logger()
- add comment to ip[6]t_LOG.h to assure nobody redefines flags
- add /proc/net/netfilter/nf_log to tell user which logger is currently
  registered for which address family
- if user has configured logging, but no logging backend (logger) is
  available, always spit a message to syslog, not just the first time.
- split ip[6]t_LOG.c into two parts:
  Backend: Always try to register as logger for the respective address family
  Frontend: Always log via nf_log_packet() API
- modify all users of nf_log_packet() to accomodate additional argument
Signed-off-by: NHarald Welte <laforge@netfilter.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NArnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

- split netfiler verdict in 16bit verdict and 16bit queue number
- add 'queuenum' argument to nf_queue_outfn_t and its users ip[6]_queue
- move NFNL_SUBSYS_ definitions from enum to #define
- introduce autoloading for nfnetlink subsystem modules
- add MODULE_ALIAS_NFNL_SUBSYS macro
- add nf_unregister_queue_handlers() to register all handlers for a given
  nf_queue_outfn_t
- add more verbose DEBUGP macro definition to nfnetlink.c
- make nfnetlink_subsys_register fail if subsys already exists
- add some more comments and debug statements to nfnetlink.c
Signed-off-by: NHarald Welte <laforge@netfilter.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The rerouting functionality is required by the core, therefore it has
to be implemented by the core and not in individual queue handlers.
Signed-off-by: NHarald Welte <laforge@netfilter.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

- Remove bogus code for compiling netlink as module
- Add module refcounting support for modules implementing a netlink
  protocol
- Add support for autoloading modules that implement a netlink protocol
  as soon as someone opens a socket for that protocol
Signed-off-by: NHarald Welte <laforge@netfilter.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Netfilter cleanup
- Move ipv4 code from net/core/netfilter.c to net/ipv4/netfilter.c
- Move ipv6 netfilter code from net/ipv6/ip6_output.c to net/ipv6/netfilter.c
Signed-off-by: NHarald Welte <laforge@netfilter.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There is nothing IPv4-specific in it.  In fact, it was already used by
IPv6, too...  Upcoming nfnetlink_queue code will use it for any kind
of packet.
Signed-off-by: NHarald Welte <laforge@netfilter.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Instead, set it in one place, namely the beginning of
netif_receive_skb().

Based upon suggestions from Jamal Hadi Salim.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch contains the following possible cleanups:
- make needlessly global code static
- #if 0 the following unused global function:
  - xfrm4_state.c: xfrm4_state_fini
- remove the following unneeded EXPORT_SYMBOL's:
  - ip_output.c: ip_finish_output
  - ip_output.c: sysctl_ip_default_ttl
  - fib_frontend.c: ip_dev_find
  - inetpeer.c: inet_peer_idlock
  - ip_options.c: ip_options_compile
  - ip_options.c: ip_options_undo
  - net/core/request_sock.c: sysctl_max_syn_backlog
Signed-off-by: NAdrian Bunk <bunk@stusta.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Bonding just wants the device before the skb_bond()
decapsulation occurs, so simply pass that original
device into packet_type->func() as an argument.

It remains to be seen whether we can use this same
exact thing to get rid of skb->input_dev as well.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NArnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This removes the private element from skbuff, that is only used by
HIPPI. Instead it uses skb->cb[] to hold the additional data that is
needed in the output path from hard_header to device driver.

PS: The only qdisc that might potentially corrupt this cb[] is if
netem was used over HIPPI. I will take care of that by fixing netem
to use skb->stamp. I don't expect many users of netem over HIPPI
Signed-off-by: NStephen Hemminger <shemminger@osdl.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Allows overriding of sysctl_{wmem,rmrm}_max
Signed-off-by: NPatrick McHardy <kaber@trash.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NPatrick McHardy <kaber@trash.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Remove the "list" member of struct sk_buff, as it is entirely
redundant.  All SKB list removal callers know which list the
SKB is on, so storing this in sk_buff does nothing other than
taking up some space.

Two tricky bits were SCTP, which I took care of, and two ATM
drivers which Francois Romieu <romieu@fr.zoreil.com> fixed
up.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
Signed-off-by: NFrancois Romieu <romieu@fr.zoreil.com>

As discussed at netconf'05, we're trying to save every bit in sk_buff.
The patch below makes sk_buff 8 bytes smaller.  I did some basic
testing on my notebook and it seems to work.

The only real in-tree user of nfcache was IPVS, who only needs a
single bit.  Unfortunately I couldn't find some other free bit in
sk_buff to stuff that bit into, so I introduced a separate field for
them.  Maybe the IPVS guys can resolve that to further save space.

Initially I wanted to shrink pkt_type to three bits (PACKET_HOST and
alike are only 6 values defined), but unfortunately the bluetooth code
overloads pkt_type :(

The conntrack-event-api (out-of-tree) uses nfcache, but Rusty just
came up with a way how to do it without any skb fields, so it's safe
to remove it.

- remove all never-implemented 'nfcache' code
- don't have ipvs code abuse 'nfcache' field. currently get's their own
  compile-conditional skb->ipvs_property field.  IPVS maintainers can
  decide to move this bit elswhere, but nfcache needs to die.
- remove skb->nfcache field to save 4 bytes
- move skb->nfctinfo into three unused bits to save further 4 bytes
Signed-off-by: NHarald Welte <laforge@netfilter.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Remove unused variable
Signed-off-by: NMatt Mackall <mpm@selenic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This fixes a race during initialization with the NAPI softirq
processing by using an RCU approach.

This race was discovered when refill_skbs() was added to
the setup code.
Signed-off-by: NMatt Mackall <mpm@selenic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

we could do one thing (see the patch below): i think it would be useful 
to fill up the netlogging skb queue straight at initialization time.  
Especially if netpoll is used for dumping alone, the system might not be 
in a situation to fill up the queue at the point of crash, so better be 
a bit more prepared and keep the pipeline filled.

[ I've modified this to be called earlier - mpm ]
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NMatt Mackall <mpm@selenic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add limited retry logic to netpoll_send_skb

Each time we attempt to send, decrement our per-device retry counter.
On every successful send, we reset the counter. 

We delay 50us between attempts with up to 20000 retries for a total of
1 second. After we've exhausted our retries, subsequent failed
attempts will try only once until reset by success.
Signed-off-by: NMatt Mackall <mpm@selenic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Minor netpoll_send_skb restructuring

Restructure to avoid confusing goto and move some bits out of the
retry loop.
Signed-off-by: NMatt Mackall <mpm@selenic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This fixes an obvious deadlock in the netpoll code.  netpoll_rx takes the
npinfo->rx_lock.  netpoll_rx is also the only caller of arp_reply (through
__netpoll_rx).  As such, it is not necessary to take this lock.
Signed-off-by: NJeff Moyer <jmoyer@redhat.com>
Signed-off-by: NMatt Mackall <mpm@selenic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Initialize npinfo->rx_flags.  The way it stands now, this will have random
garbage, and so will incur a locking penalty even when an rx_hook isn't
registered and we are not active in the netpoll polling code.
Signed-off-by: NJeff Moyer <jmoyer@redhat.com>
Signed-off-by: NMatt Mackall <mpm@selenic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The bug is evident when it is seen once. dst gc timer was backed off,
when gc queue is not empty. But this means that timer quickly backs off,
if at least one destination remains in use. Normally, the bug is invisible,
because adding new dst entry to queue cancels the backoff. But it shots
deadly with destination cache overflow when new destinations are not released
for long time f.e. after an interface goes down.

The fix is to cancel backoff when something was released.
Signed-off-by: NDenis Lunev <den@sw.ru>
Signed-off-by: NAlexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>