Reordering detection fails to take account that the reordered
skb may have pcount larger than 1. In such case the lowest of
them had the largest reordering, the old formula used the
highest of them which is pcount - 1 packets less reordered.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit ed6dcf4a in the history.git tree broke netlink_unicast timeouts
by moving the schedule_timeout() call to a new function that doesn't
propagate the remaining timeout back to the caller. This means on each
retry we start with the full timeout again.
ipc/mqueue.c seems to actually want to wait indefinitely so this
behaviour is retained.
Signed-off-by: Patrick McHardy <kaber@trash.net>
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>
This patch makes the master daemon to sync the connection when it is about
to close. This makes the connections on the backup to close or timeout
according their state. Before the sync was performed only if the
connection is in ESTABLISHED state which always made the connections to
timeout in the hard coded 3 minutes. However the Andy Gospodarek's patch
([IPVS]: use proper timeout instead of fixed value) effectively did nothing
more than increasing this to 15 minutes (Established state timeout). So
this patch makes use of proper timeout since it syncs the connections on
status changes to FIN_WAIT (2min timeout) and CLOSE (10sec timeout).
However if the backup misses CLOSE hopefully it did not miss FIN_WAIT.
Otherwise we will just have to wait for the ESTABLISHED state timeout. As
it is without this patch. This way the number of the hanging connections
on the backup is kept to minimum. And very few of them will be left to
timeout with a long timeout.
This is important if we want to make use of the fix for the real server
overcommit on master/backup fail-over.
Signed-off-by: Rumen G. Bogdanovski <rumen@voicecho.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes the problem with node overload on director fail-over.
Given the scenario: 2 nodes each accepting 3 connections at a time and 2
directors, director failover occurs when the nodes are fully loaded (6
connections to the cluster) in this case the new director will assign
another 6 connections to the cluster, If the same real servers exist
there.
The problem turned to be in not binding the inherited connections to
the real servers (destinations) on the backup director. Therefore:
"ipvsadm -l" reports 0 connections:
root@test2:~# ipvsadm -l
IP Virtual Server version 1.2.1 (size=4096)
Prot LocalAddress:Port Scheduler Flags
-> RemoteAddress:Port Forward Weight ActiveConn InActConn
TCP test2.local:5999 wlc
-> node473.local:5999 Route 1000 0 0
-> node484.local:5999 Route 1000 0 0
while "ipvs -lnc" is right
root@test2:~# ipvsadm -lnc
IPVS connection entries
pro expire state source virtual destination
TCP 14:56 ESTABLISHED 192.168.0.10:39164 192.168.0.222:5999
192.168.0.51:5999
TCP 14:59 ESTABLISHED 192.168.0.10:39165 192.168.0.222:5999
192.168.0.52:5999
So the patch I am sending fixes the problem by binding the received
connections to the appropriate service on the backup director, if it
exists, else the connection will be handled the old way. So if the
master and the backup directors are synchronized in terms of real
services there will be no problem with server over-committing since
new connections will not be created on the nonexistent real services
on the backup. However if the service is created later on the backup,
the binding will be performed when the next connection update is
received. With this patch the inherited connections will show as
inactive on the backup:
root@test2:~# ipvsadm -l
IP Virtual Server version 1.2.1 (size=4096)
Prot LocalAddress:Port Scheduler Flags
-> RemoteAddress:Port Forward Weight ActiveConn InActConn
TCP test2.local:5999 wlc
-> node473.local:5999 Route 1000 0 1
-> node484.local:5999 Route 1000 0 1
rumen@test2:~$ cat /proc/net/ip_vs
IP Virtual Server version 1.2.1 (size=4096)
Prot LocalAddress:Port Scheduler Flags
-> RemoteAddress:Port Forward Weight ActiveConn InActConn
TCP C0A800DE:176F wlc
-> C0A80033:176F Route 1000 0 1
-> C0A80032:176F Route 1000 0 1
Regards,
Rumen Bogdanovski
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Rumen G. Bogdanovski <rumen@voicecho.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
The struct proto has the per-cpu "inuse" counter, which is handled
with a special care. All the handling code hides under the ifdef
CONFIG_SMP and it introduces some code duplication and makes it
look worse than it could.
Clean this.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The function crypto_alloc_comp returns an errno instead of NULL
to indicate error. So it needs to be tested with IS_ERR.
This is based on a patch by Vicenç Beltran Querol.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Based on report and patch by Doug Kehn <rdkehn@yahoo.com>:
vconfig returns the following error when attempting to execute the
set_ingress_map command:
vconfig: socket or ioctl error for set_ingress_map: Operation not permitted
In vlan.c, vlan_ioctl_handler for SET_VLAN_INGRESS_PRIORITY_CMD
sets err = -EPERM and calls vlan_dev_set_ingress_priority.
vlan_dev_set_ingress_priority is a void function so err remains
at -EPERM and results in the vconfig error (even though the ingress
map was set).
Fix by setting err = 0 after the vlan_dev_set_ingress_priority call.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Because net_free is called by copy_net_ns before its declaration, the
compiler gives an error. This patch puts net_free before copy_net_ns
to fix this.
The compiler error:
net/core/net_namespace.c: In function 'copy_net_ns':
net/core/net_namespace.c:97: error: implicit declaration of function 'net_free'
net/core/net_namespace.c: At top level:
net/core/net_namespace.c:104: warning: conflicting types for 'net_free'
net/core/net_namespace.c:104: error: static declaration of 'net_free' follows non-static declaration
net/core/net_namespace.c:97: error: previous implicit declaration of 'net_free' was here
The error was introduced by the '[NET]: Hide the dead code in the
net_namespace.c' patch (6a1a3b9f68).
Signed-off-by: Johann Felix Soden <johfel@users.sourceforge.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
While trying to implement u32 hashes in my shaping machine I ran into
a possible bug in the u32 hash/bucket computing algorithm
(net/sched/cls_u32.c).
The problem occurs only with hash masks that extend over the octet
boundary, on little endian machines (where htonl() actually does
something).
Let's say that I would like to use 0x3fc0 as the hash mask. This means
8 contiguous "1" bits starting at b6. With such a mask, the expected
(and logical) behavior is to hash any address in, for instance,
192.168.0.0/26 in bucket 0, then any address in 192.168.0.64/26 in
bucket 1, then 192.168.0.128/26 in bucket 2 and so on.
This is exactly what would happen on a big endian machine, but on
little endian machines, what would actually happen with current
implementation is 0x3fc0 being reversed (into 0xc03f0000) by htonl()
in the userspace tool and then applied to 192.168.x.x in the u32
classifier. When shifting right by 16 bits (rank of first "1" bit in
the reversed mask) and applying the divisor mask (0xff for divisor
256), what would actually remain is 0x3f applied on the "168" octet of
the address.
One could say is this can be easily worked around by taking endianness
into account in userspace and supplying an appropriate mask (0xfc03)
that would be turned into contiguous "1" bits when reversed
(0x03fc0000). But the actual problem is the network address (inside
the packet) not being converted to host order, but used as a
host-order value when computing the bucket.
Let's say the network address is written as n31 n30 ... n0, with n0
being the least significant bit. When used directly (without any
conversion) on a little endian machine, it becomes n7 ... n0 n8 ..n15
etc in the machine's registers. Thus bits n7 and n8 would no longer be
adjacent and 192.168.64.0/26 and 192.168.128.0/26 would no longer be
consecutive.
The fix is to apply ntohl() on the hmask before computing fshift,
and in u32_hash_fold() convert the packet data to host order before
shifting down by fshift.
With helpful feedback from Jamal Hadi Salim and Jarek Poplawski.
Signed-off-by: David S. Miller <davem@davemloft.net>
There are places that check for CONFIG_IP_MULTIPLE_TABLES
twice in the same file, but the internals of these #ifdefs
can be merged.
As a side effect - remove one ifdef from inside a function.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This removes last proc_net_create() user. Kudos to Benjamin Thery and
Stephen Hemminger for comments on previous version.
Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
tecl_reset() is called from deactivate and qdisc is set to noop already,
but subsequent teql_xmit does not know about it and dereference private
data as teql qdisc and thus oopses.
not catch it first :)
Signed-off-by: Evgeniy Polyakov <johnpol@2ka.mipt.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
Trivial patch to make "sctcp,sctpv6" protocols uses the fast "inuse
sockets" infrastructure
Each protocol use then a static percpu var, instead of a dynamic one.
This saves some ram and some cpu cycles
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Trivial patch to make "tcpv6,udpv6,udplitev6,rawv6" protocols uses the
fast "inuse sockets" infrastructure
Each protocol use then a static percpu var, instead of a dynamic one.
This saves some ram and some cpu cycles
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Trivial patch to make "tcp,udp,udplite,raw" protocols uses the fast
"inuse sockets" infrastructure
Each protocol use then a static percpu var, instead of a dynamic one.
This saves some ram and some cpu cycles
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
"struct proto" currently uses an array stats[NR_CPUS] to track change on
'inuse' sockets per protocol.
If NR_CPUS is big, this means we use a big memory area for this.
Moreover, all this memory area is located on a single node on NUMA
machines, increasing memory pressure on the boot node.
In this patch, I tried to :
- Keep a fast !CONFIG_SMP implementation
- Keep a fast CONFIG_SMP implementation for often used protocols
(tcp,udp,raw,...)
- Introduce a NUMA efficient implementation
Some helper macros are defined in include/net/sock.h
These macros take into account CONFIG_SMP
If a "struct proto" is declared without using DEFINE_PROTO_INUSE /
REF_PROTO_INUSE
macros, it will automatically use a default implementation, using a
dynamically allocated percpu zone.
This default implementation will be NUMA efficient, but might use 32/64
bytes per possible cpu
because of current alloc_percpu() implementation.
However it still should be better than previous implementation based on
stats[NR_CPUS] field.
When a "struct proto" is changed to use the new macros, we use a single
static "int" percpu variable,
lowering the memory and cpu costs, still preserving NUMA efficiency.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The #idfed CONFIG_IP_MROUTE is sometimes places inside the if-s,
which looks completely bad. Similar ifdefs inside the functions
looks a bit better, but they are also not recommended to be used.
Provide an ifdef-ed ip_mroute_opt() helper to cleanup the code.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
As the checksum verification is postponed till user calls recv or poll,
the inrementation of Udp6InErrors counter should be also postponed.
Currently, it is postponed in non-blocking operation case. However it
should be postponed in all case like the IPv4 code.
Signed-off-by: Mitsuru Chinen <mitch@linux.vnet.ibm.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
The ip6_push_pending_frames and ip6_flush_pending_frames do the
same things to flush the sock's cork. Move this into a separate
function and save ~100 bytes from the .text
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The ip_push_pending_frames and ip_flush_pending_frames do the
same things to flush the sock's cork. Move this into a separate
function and save ~80 bytes from the .text
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix --arp-gratuitous matching dependence on --arp-ip-{src,dst}
Signed-off-by: Bart De Schuymer <bdschuym@pandora.be>
Signed-off-by: Lutz Preßler <Lutz.Pressler@SerNet.DE>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Code is using knowledge that nf_sockopt_ops::list list_head is first
field in structure by using casts. Switch to list_for_each_entry()
itetators while I am at it.
Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
As noticed by Paul McKenney, the rcu_dereference calls in the init path
of NAT modules are unneeded, remove them.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Sort matches and targets in the NF makefiles.
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>
Transfer all my copyright over to our company.
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>
I plan to kill ->get_info which means killing proc_net_create().
Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
The list of options that the fd transport accepts is missing end-of-options
marker. This patch adds it.
Signed-off-by: Latchesar Ionkov <lucho@ionkov.net>
Acked-by: Eric Van Hensbergen <ericvh@gmail.com>
v9fs_match_trans function returns arbitrary transport module instead of NULL
when the requested transport is not registered. This patch modifies the
function to return NULL in that case.
Signed-off-by: Latchesar Ionkov <lucho@ionkov.net>
Acked-by: Eric Van Hensbergen <ericvh@gmail.com>
sg_mark_end() overwrites the page_link information, but all users want
__sg_mark_end() behaviour where we just set the end bit. That is the most
natural way to use the sg list, since you'll fill it in and then mark the
end point.
So change sg_mark_end() to only set the termination bit. Add a sg_magic
debug check as well, and clear a chain pointer if it is set.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Not architecture specific code should not #include <asm/scatterlist.h>.
This patch therefore either replaces them with
#include <linux/scatterlist.h> or simply removes them if they were
unused.
Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Documentation updates for network interfaces.
1. Add doc for netif_napi_add
2. Remove doc for unused returns from netif_rx
3. Add doc for netif_receive_skb
[ Incorporated minor mods from Randy Dunlap -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This cache is only required to create new namespaces,
but we won't have them in CONFIG_NET_NS=n case.
Hide it under the appropriate ifdef.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The setup_net is called for the init net namespace
only (int the CONFIG_NET_NS=n of course) from the __init
function, so mark it as __net_init to disappear with the
caller after the boot.
Yet again, in the perfect world this has to be under
#ifdef CONFIG_NET_NS, but it isn't guaranteed that every
subsystem is registered *after* the init_net_ns is set
up. After we are sure, that we don't start registering
them before the init net setup, we'll be able to move
this code under the ifdef.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The namespace creation/destruction code is never called
if the CONFIG_NET_NS is n, so it's OK to move it under
appropriate ifdef.
The copy_net_ns() in the "n" case checks for flags and
returns -EINVAL when new net ns is requested. In a perfect
world this stub must be in net_namespace.h, but this
function need to know the CLONE_NEWNET value and thus
requires sched.h. On the other hand this header is to be
injected into almost every .c file in the networking code,
and making all this code depend on the sched.h is a
suicidal attempt.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
When the new pernet something (subsys, device or operations) is
being registered, the init callback is to be called for each
namespace, that currently exitst in the system. During the
unregister, the same is to be done with the exit callback.
However, not every pernet something has both calls, but the
check for the appropriate pointer to be not NULL is performed
inside the for_each_net() loop.
This is (at least) strange, so tune this.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Finally, the zero_it argument can be completely removed from
the callers and from the function prototype.
Besides, fix the checkpatch.pl warnings about using the
assignments inside if-s.
This patch is rather big, and it is a part of the previous one.
I splitted it wishing to make the patches more readable. Hope
this particular split helped.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
At this point nobody calls the sk_alloc(() with zero_it == 0,
so remove unneeded checks from it.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The sk_prot_alloc() already performs all the stuff needed by the
sk_clone(). Besides, the sk_prot_alloc() requires almost twice
less arguments than the sk_alloc() does, so call the sk_prot_alloc()
saving the stack a bit.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The security_sk_alloc() and the module_get is a part of the
object allocations - move it in the proper place.
Note, that since we do not reset the newly allocated sock
in the sk_alloc() (memset() is removed with the previous
patch) we can safely do this.
Also fix the error path in sk_prot_alloc() - release the security
context if needed.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
We have a __GFP_ZERO flag that allocates a zeroed chunk of memory.
Use it in the sk_alloc() and avoid a hand-made memset().
This is a temporary patch that will help us in the nearest future :)
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The sock object is allocated either from the generic cache with
the kmalloc, or from the proc->slab cache.
Move this logic into an isolated set of helpers and make the
sk_alloc/sk_free look a bit nicer.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The sock_copy() is supposed to just clone the socket. In a perfect
world it has to be just memcpy, but we have to handle the security
mark correctly. All the extra setup must be performed in sk_clone()
call, so move the get_net() into more proper place.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The sock_copy() call is not used outside the sock.c file,
so just move it into a sock.c
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Similar to commit 3eec0047d9, point of this is to avoid
skipping R-bit skbs.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ilpo Järvinen