This gets rid of a warning caused by the test in rcu_assign_pointer.
I tried to fix rcu_assign_pointer, but that devolved into a long set
of discussions about doing it right that came to no real solution.
Since the test in rcu_assign_pointer for constant NULL would never
succeed in fib_trie, just open code instead.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While testing the virtio-net driver on KVM with TSO I noticed
that TSO performance with a 1500 MTU is significantly worse
compared to the performance of non-TSO with a 16436 MTU. The
packet dump shows that most of the packets sent are smaller
than a page.
Looking at the code this actually is quite obvious as it always
stop extending the packet if it's the first packet yet to be
sent and if it's larger than the MSS. Since each extension is
bound by the page size, this means that (given a 1500 MTU) we're
very unlikely to construct packets greater than a page, provided
that the receiver and the path is fast enough so that packets can
always be sent immediately.
The fix is also quite obvious. The push calls inside the loop
is just an optimisation so that we don't end up doing all the
sending at the end of the loop. Therefore there is no specific
reason why it has to do so at MSS boundaries. For TSO, the
most natural extension of this optimisation is to do the pushing
once the skb exceeds the TSO size goal.
This is what the patch does and testing with KVM shows that the
TSO performance with a 1500 MTU easily surpasses that of a 16436
MTU and indeed the packet sizes sent are generally larger than
16436.
I don't see any obvious downsides for slower peers or connections,
but it would be prudent to test this extensively to ensure that
those cases don't regress.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is a narrow pedantry :) but the dlci_ioctl_hook check and call
should not be parted with the mutex lock.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Been seeing occasional panics in my testing of 2.6.25-rc in ip_defrag.
Offending line in ip_defrag is here:
net = skb->dev->nd_net
where dev is NULL. Bisected the problem down to commit
ac18e7509e ([NETNS][FRAGS]: Make the
inet_frag_queue lookup work in namespaces).
Below patch (idea from Patrick McHardy) fixes the problem for me.
Signed-off-by: Phil Oester <kernel@linuxace.com>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Based on notice from "Colin" <colins@sjtu.edu.cn>.
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
When selecting a new window, tcp_select_window() tries not to shrink
the offered window by using the maximum of the remaining offered window
size and the newly calculated window size. The newly calculated window
size is always a multiple of the window scaling factor, the remaining
window size however might not be since it depends on rcv_wup/rcv_nxt.
This means we're effectively shrinking the window when scaling it down.
The dump below shows the problem (scaling factor 2^7):
- Window size of 557 (71296) is advertised, up to 3111907257:
IP 172.2.2.3.33000 > 172.2.2.2.33000: . ack 3111835961 win 557 <...>
- New window size of 514 (65792) is advertised, up to 3111907217, 40 bytes
below the last end:
IP 172.2.2.3.33000 > 172.2.2.2.33000: . 3113575668:3113577116(1448) ack 3111841425 win 514 <...>
The number 40 results from downscaling the remaining window:
3111907257 - 3111841425 = 65832
65832 / 2^7 = 514
65832 % 2^7 = 40
If the sender uses up the entire window before it is shrunk, this can have
chaotic effects on the connection. When sending ACKs, tcp_acceptable_seq()
will notice that the window has been shrunk since tcp_wnd_end() is before
tp->snd_nxt, which makes it choose tcp_wnd_end() as sequence number.
This will fail the receivers checks in tcp_sequence() however since it
is before it's tp->rcv_wup, making it respond with a dupack.
If both sides are in this condition, this leads to a constant flood of
ACKs until the connection times out.
Make sure the window is never shrunk by aligning the remaining window to
the window scaling factor.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
zap_completion_queue() retrieves skbs from completion_queue where they have
zero skb->users counter. Before dev_kfree_skb_any() it should be non-zero
yet, so it's increased now.
Reported-and-tested-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Jarek Poplawski <jarkao2@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
In br_fdb_cleanup() next_timer and this_timer are in jiffies, so they
should be compared using the time_after() macro.
Signed-off-by: Fabio Checconi <fabio@gandalf.sssup.it>
Signed-off-by: Stephen Hemminger <stephen.hemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is a race is SCTP between the loading of the module
and the access by the socket layer to the protocol functions.
In particular, a list of addresss that SCTP maintains is
not initialized prior to the registration with the protosw.
Thus it is possible for a user application to gain access
to SCTP functions before everything has been initialized.
The problem shows up as odd crashes during connection
initializtion when we try to access the SCTP address list.
The solution is to refactor how we do registration and
initialize the lists prior to registering with the protosw.
Care must be taken since the address list initialization
depends on some other pieces of SCTP initialization. Also
the clean-up in case of failure now also needs to be refactored.
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>
Acked-by: Sridhar Samudrala <sri@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If a rule using ipt_recent is created with a hit count greater than
ip_pkt_list_tot, the rule will never match as it cannot keep track
of enough timestamps. This patch makes ipt_recent refuse to create such
rules.
With ip_pkt_list_tot's default value of 20, the following can be used
to reproduce the problem.
nc -u -l 0.0.0.0 1234 &
for i in `seq 1 100`; do echo $i | nc -w 1 -u 127.0.0.1 1234; done
This limits it to 20 packets:
iptables -A OUTPUT -p udp --dport 1234 -m recent --set --name test \
--rsource
iptables -A OUTPUT -p udp --dport 1234 -m recent --update --seconds \
60 --hitcount 20 --name test --rsource -j DROP
While this is unlimited:
iptables -A OUTPUT -p udp --dport 1234 -m recent --set --name test \
--rsource
iptables -A OUTPUT -p udp --dport 1234 -m recent --update --seconds \
60 --hitcount 21 --name test --rsource -j DROP
With the patch the second rule-set will throw an EINVAL.
Reported-by: Sean Kennedy <skennedy@vcn.com>
Signed-off-by: Daniel Hokka Zakrisson <daniel@hozac.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
logical-bitwise & confusion
Signed-off-by: Roel Kluin <12o3l@tiscali.nl>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (47 commits)
[SCTP]: Fix local_addr deletions during list traversals.
net: fix build with CONFIG_NET=n
[TCP]: Prevent sending past receiver window with TSO (at last skb)
rt2x00: Add new D-Link USB ID
rt2x00: never disable multicast because it disables broadcast too
libertas: fix the 'compare command with itself' properly
drivers/net/Kconfig: fix whitespace for GELIC_WIRELESS entry
[NETFILTER]: nf_queue: don't return error when unregistering a non-existant handler
[NETFILTER]: nfnetlink_queue: fix EPERM when binding/unbinding and instance 0 exists
[NETFILTER]: nfnetlink_log: fix EPERM when binding/unbinding and instance 0 exists
[NETFILTER]: nf_conntrack: replace horrible hack with ksize()
[NETFILTER]: nf_conntrack: add \n to "expectation table full" message
[NETFILTER]: xt_time: fix failure to match on Sundays
[NETFILTER]: nfnetlink_log: fix computation of netlink skb size
[NETFILTER]: nfnetlink_queue: fix computation of allocated size for netlink skb.
[NETFILTER]: nfnetlink: fix ifdef in nfnetlink_compat.h
[NET]: include <linux/types.h> into linux/ethtool.h for __u* typedef
[NET]: Make /proc/net a symlink on /proc/self/net (v3)
RxRPC: fix rxrpc_recvmsg()'s returning of msg_name
net/enc28j60: oops fix
...
The assertion that checks for sge context overflow is
incorrectly hard-coded to 32. This causes a kernel bug
check when using big-data mounts. Changed the BUG_ON to
use the computed value RPCSVC_MAXPAGES.
Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
RDMA connection shutdown on an SMP machine can cause a kernel crash due
to the transport close path racing with the I/O tasklet.
Additional transport references were added as follows:
- A reference when on the DTO Q to avoid having the transport
deleted while queued for I/O.
- A reference while there is a QP able to generate events.
- A reference until the DISCONNECTED event is received on the CM ID
Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Since the lists are circular, we need to explicitely tag
the address to be deleted since we might end up freeing
the list head instead. This fixes some interesting SCTP
crashes.
Signed-off-by: Chidambar 'ilLogict' Zinnoury <illogict@online.fr>
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With TSO it was possible to send past the receiver window when the skb
to be sent was the last in the write queue while the receiver window
is the limiting factor. One can notice that there's a loophole in the
tcp_mss_split_point that lacked a receiver window check for the
tcp_write_queue_tail() if also cwnd was smaller than the full skb.
Noticed by Thomas Gleixner <tglx@linutronix.de> in form of "Treason
uncloaked! Peer ... shrinks window .... Repaired." messages (the peer
didn't actually shrink its window as the message suggests, we had just
sent something past it without a permission to do so).
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Tested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit ce7663d84:
[NETFILTER]: nfnetlink_queue: don't unregister handler of other subsystem
changed nf_unregister_queue_handler to return an error when attempting to
unregister a queue handler that is not identical to the one passed in.
This is correct in case we really do have a different queue handler already
registered, but some existing userspace code always does an unbind before
bind and aborts if that fails, so try to be nice and return success in
that case.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Similar to the nfnetlink_log problem, nfnetlink_queue incorrectly
returns -EPERM when binding or unbinding to an address family and
queueing instance 0 exists and is owned by a different process. Unlike
nfnetlink_log it previously completes the operation, but it is still
incorrect.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
When binding or unbinding to an address family, the res_id is usually set
to zero. When logging instance 0 already exists and is owned by a different
process, this makes nfunl_recv_config return -EPERM without performing
the bind operation.
Since no operation on the foreign logging instance itself was requested,
this is incorrect. Move bind/unbind commands before the queue instance
permissions checks.
Also remove an incorrect comment.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
There's a horrible slab abuse in net/netfilter/nf_conntrack_extend.c
that can be replaced with a call to ksize().
Cc: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
From: Andrew Schulman <andrex@alumni.utexas.net>
xt_time_match() in net/netfilter/xt_time.c in kernel 2.6.24 never
matches on Sundays. On my host I have a rule like
iptables -A OUTPUT -m time --weekdays Sun -j REJECT
and it never matches. The problem is in localtime_2(), which uses
r->weekday = (4 + r->dse) % 7;
to map the epoch day onto a weekday in {0,...,6}. In particular this
gives 0 for Sundays. But 0 has to be wrong; a weekday of 0 can never
match. xt_time_match() has
if (!(info->weekdays_match & (1 << current_time.weekday)))
return false;
and when current_time.weekday = 0, the result of the & is always
zero, even when info->weekdays_match = XT_TIME_ALL_WEEKDAYS = 0xFE.
Signed-off-by: Jan Engelhardt <jengelh@computergmbh.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch is similar to nfnetlink_queue fixes. It fixes the computation
of skb size by using NLMSG_SPACE instead of NLMSG_ALIGN.
Signed-off-by: Eric Leblond <eric@inl.fr>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Size of the netlink skb was wrongly computed because the formula was using
NLMSG_ALIGN instead of NLMSG_SPACE. NLMSG_ALIGN does not add the room for
netlink header as NLMSG_SPACE does. This was causing a failure of message
building in some cases.
On my test system, all messages for packets in range [8*k+41, 8*k+48] where k
is an integer were invalid and the corresponding packets were dropped.
Signed-off-by: Eric Leblond <eric@inl.fr>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
* 'hotfixes' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6:
NFS: Fix dentry revalidation for NFSv4 referrals and mountpoint crossings
NFS: Fix the fsid revalidation in nfs_update_inode()
SUNRPC: Fix a nfs4 over rdma transport oops
NFS: Fix an f_mode/f_flags confusion in fs/nfs/write.c
Prevent an RPC oops when freeing a dynamically allocated RDMA
buffer, used in certain special-case large metadata operations.
Signed-off-by: Tom Talpey <tmt@netapp.com>
Signed-off-by: James Lentini <jlentini@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Fix rxrpc_recvmsg() to return msg_name correctly. We shouldn't
overwrite the *msg struct, but should rather write into msg->msg_name
(there's a '&' unary operator that shouldn't be there).
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
bnep_sock_cleanup() always returns 0 and its return value isn't used
anywhere in the code.
Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
hci_sock_cleanup() always returns 0 and its return value isn't used
anywhere in the code.
Compile-tested with 'make allyesconfig && make net/bluetooth/bluetooth.ko'
Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Brings max_burst socket option set/get into line with the latest ietf
socket extensions api draft, while maintaining backwards
compatibility.
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If an address family is not listed in "Supported Address Types"
parameter(INIT Chunk), but the packet is sent by that family, this
address family should be considered as supported by peer. Otherwise,
an error condition will occur. For instance, if kernel receives an
IPV6 SCTP INIT chunk with "Support Address Types" parameter which
indicates just supporting IPV4 Address family. Kernel will reply an
IPV6 SCTP INIT ACK packet, but the source ipv6 address in ipv6 header
will be vacant. This is not correct.
refer to RFC4460 as following:
IMPLEMENTATION NOTE: If an SCTP endpoint lists in the 'Supported
Address Types' parameter either IPv4 or IPv6, but uses the other
family for sending the packet containing the INIT chunk, or if it
also lists addresses of the other family in the INIT chunk, then
the address family that is not listed in the 'Supported Address
Types' parameter SHOULD also be considered as supported by the
receiver of the INIT chunk. The receiver of the INIT chunk SHOULD
NOT respond with any kind of error indication.
Here is a fix to comply to RFC.
Signed-off-by: Gui Jianfeng <guijianfeng@cn.fujitsu.com>
Acked-by: Vlad Yasevich <vladislav.yasevich@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
From: Stephen Hemminger <shemminger@linux-foundation.org>
Based upon a patch by Marcel Wappler:
This patch fixes a DHCP issue of the kernel: some DHCP servers
(i.e. in the Linksys WRT54Gv5) are very strict about the contents
of the DHCPDISCOVER packet they receive from clients.
Table 5 in RFC2131 page 36 requests the fields 'ciaddr' and
'siaddr' MUST be set to '0'. These DHCP servers ignore Linux
kernel's DHCP discovery packets with these two fields set to
'255.255.255.255' (in contrast to popular DHCP clients, such as
'dhclient' or 'udhcpc'). This leads to a not booting system.
Signed-off-by: David S. Miller <davem@davemloft.net>
Merge rate_control_pid_shift_adjust() to rate_control_pid_adjust_rate()
in order to make the learning algorithm aware of constraints on rates. Also
add some comments and rename variables.
This fixes a bug which prevented 802.11b/g non-AP STAs from working with
802.11b only AP STAs.
This patch was originally destined for 2.6.26, and is being backported
to fix a user reported problem in post-2.6.24 kernels.
Signed-off-by: Stefano Brivio <stefano.brivio@polimi.it>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Now the ESP uses the AEAD interface even for algorithms which are
not combined mode, we need to select CONFIG_CRYPTO_AUTHENC as
otherwise only combined mode algorithms will work.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Based upon a report by Andrew Morton and code analysis done
by Jarek Poplawski.
This reverts 33f807ba0d ("[NETPOLL]:
Kill NETPOLL_RX_DROP, set but never tested.") and
c7b6ea24b4 ("[NETPOLL]: Don't need
rx_flags.").
The rx_flags did get tested for zero vs. non-zero and therefore we do
need those tests and that code which sets NETPOLL_RX_DROP et al.
Signed-off-by: David S. Miller <davem@davemloft.net>
When the l2cap info_timer is active the info_state will be set to
L2CAP_INFO_FEAT_MASK_REQ_SENT, and it will be unset after the timer is
deleted or timeout triggered.
Here in l2cap_conn_del only call del_timer_sync when the info_state is
set to L2CAP_INFO_FEAT_MASK_REQ_SENT.
Signed-off-by: Dave Young <hidave.darkstar@gmail.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
neigh_update sends skb from neigh->arp_queue while neigh_timer_handler
has increased skbs refcount and calls solicit with the
skb. neigh_timer_handler should not increase skbs refcount but make a
copy of the skb and do solicit with the copy.
Signed-off-by: Frank Blaschka <frank.blaschka@de.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since a5fbb6d106
"KVM: fix !SMP build error" smp_call_function isn't a define anymore
that folds into nothing but a define that calls up_smp_call_function
with all parameters. Hence we cannot #ifdef out the unused code
anymore...
This seems to be the preferred method, so do this for s390 as well.
net/iucv/iucv.c: In function 'iucv_cleanup_queue':
net/iucv/iucv.c:657: error: '__iucv_cleanup_queue' undeclared
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Josef 'Jeff' Sipek <jeffpc@josefsipek.net>
Signed-off-by: Ursula Braun <braunu@de.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It makes fackets_out to grow too slowly compared with the
real write queue.
This shouldn't cause those BUG_TRAP(packets <= tp->packets_out)
to trigger but how knows how such inconsistent fackets_out
affects here and there around TCP when everything is nowadays
assuming accurate fackets_out. So lets see if this silences
them all.
Reported by Guillaume Chazarain <guichaz@gmail.com>.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
In addition to commit 160f17 ("[SCTP]: Use proc_create() to setup
->proc_fops first") use proc_create in two more places.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use proc_create() to make sure that ->proc_fops be setup before gluing
PDE to main tree.
Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>