This is the last step to be able to perform full RCU lookups
in __inet_lookup() : After established/timewait tables, we
add RCU lookups to listening hash table.
The only trick here is that a socket of a given type (TCP ipv4,
TCP ipv6, ...) can now flight between two different tables
(established and listening) during a RCU grace period, so we
must use different 'nulls' end-of-chain values for two tables.
We define a large value :
#define LISTENING_NULLS_BASE (1U << 29)
So that slots in listening table are guaranteed to have different
end-of-chain values than slots in established table. A reader can
still detect it finished its lookup in the right chain.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch prepares RCU migration of listening_hash table for
TCP/DCCP protocols.
listening_hash table being small (32 slots per protocol), we add
a spinlock for each slot, instead of a single rwlock for whole table.
This should reduce hold time of readers, and writers concurrency.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
RCU was added to UDP lookups, using a fast infrastructure :
- sockets kmem_cache use SLAB_DESTROY_BY_RCU and dont pay the
price of call_rcu() at freeing time.
- hlist_nulls permits to use few memory barriers.
This patch uses same infrastructure for TCP/DCCP established
and timewait sockets.
Thanks to SLAB_DESTROY_BY_RCU, no slowdown for applications
using short lived TCP connections. A followup patch, converting
rwlocks to spinlocks will even speedup this case.
__inet_lookup_established() is pretty fast now we dont have to
dirty a contended cache line (read_lock/read_unlock)
Only established and timewait hashtable are converted to RCU
(bind table and listen table are still using traditional locking)
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Some code here depends on CONFIG_KMOD to not try to load
protocol modules or similar, replace by CONFIG_MODULES
where more than just request_module depends on CONFIG_KMOD
and and also use try_then_request_module in ebtables.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch removes CVS keywords that weren't updated for a long time
from comments.
Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a net argument to inet6_lookup and propagate it further.
Actually, this is tcp-v6 implementation of what was done for
tcp-v4 sockets in a previous patch.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a net argument to inet_lookup and propagate it further
into lookup calls. Plus tune the __inet_check_established.
The dccp and inet_diag, which use that lookup functions
pass the init_net into them.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fixes: http://bugzilla.kernel.org/show_bug.cgi?id=9825
The inet_diag_lock_handler function uses ERR_PTR to encode errors but
its callers were testing against NULL.
This only happens when the only inet_diag modular user, DCCP, is not
built into the kernel or available as a module.
Also there was a problem with not dropping the mutex lock when a handler
was not found, also fixed in this patch.
This caused an OOPS and ss would then hang on subsequent calls, as
&inet_diag_table_mutex was being left locked.
Thanks to spike at ml.yaroslavl.ru for report it after trying 'ss -d'
on a kernel that doesn't have DCCP available.
This bug was introduced in cset
d523a328fb ("Fix inet_diag dead-lock
regression"), after 2.6.24-rc3, so just 2.6.24 seems to be affected.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Create a specific helper for netlink kernel socket disposal. This just
let the code look better and provides a ground for proper disposal
inside a namespace.
Signed-off-by: Denis V. Lunev <den@openvz.org>
Tested-by: Alexey Dobriyan <adobriyan@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The inet_diag register fix broke inet_diag module loading because the
loaded module had to take the same mutex that's already held by the
loader in order to register the new handler.
This patch fixes it by introducing a separate mutex to protect the
handling of handlers.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The following race is possible when one cpu unregisters the handler
while other one is trying to receive a message and call this one:
CPU1: CPU2:
inet_diag_rcv() inet_diag_unregister()
mutex_lock(&inet_diag_mutex);
netlink_rcv_skb(skb, &inet_diag_rcv_msg);
if (inet_diag_table[nlh->nlmsg_type] ==
NULL) /* false handler is still registered */
...
netlink_dump_start(idiagnl, skb, nlh,
inet_diag_dump, NULL);
cb = kzalloc(sizeof(*cb), GFP_KERNEL);
/* sleep here freeing memory
* or preempt
* or sleep later on nlk->cb_mutex
*/
spin_lock(&inet_diag_register_lock);
inet_diag_table[type] = NULL;
... spin_unlock(&inet_diag_register_lock);
synchronize_rcu();
/* CPU1 is sleeping - RCU quiescent
* state is passed
*/
return;
/* inet_diag_dump is finally called: */
inet_diag_dump()
handler = inet_diag_table[cb->nlh->nlmsg_type];
BUG_ON(handler == NULL);
/* OOPS! While we slept the unregister has set
* handler to NULL :(
*/
Grep showed, that the register/unregister functions are called
from init/fini module callbacks for tcp_/dccp_diag, so it's OK
to use the inet_diag_mutex to synchronize manipulations with the
inet_diag_table and the access to it.
Besides, as Herbert pointed out, asynchronous dumps should hold
this mutex as well, and thus, we provide the mutex as cb_mutex one.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
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>
By adding module aliases to inet_diag, tcp_diag and dccp_diag, we let
them load automatically as needed. This makes tools like "ss" run
faster.
Signed-off-by: Jean Delvare <jdelvare@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch make processing netlink user -> kernel messages synchronious.
This change was inspired by the talk with Alexey Kuznetsov about current
netlink messages processing. He says that he was badly wrong when introduced
asynchronious user -> kernel communication.
The call netlink_unicast is the only path to send message to the kernel
netlink socket. But, unfortunately, it is also used to send data to the
user.
Before this change the user message has been attached to the socket queue
and sk->sk_data_ready was called. The process has been blocked until all
pending messages were processed. The bad thing is that this processing
may occur in the arbitrary process context.
This patch changes nlk->data_ready callback to get 1 skb and force packet
processing right in the netlink_unicast.
Kernel -> user path in netlink_unicast remains untouched.
EINTR processing for in netlink_run_queue was changed. It forces rtnl_lock
drop, but the process remains in the cycle until the message will be fully
processed. So, there is no need to use this kludges now.
Signed-off-by: Denis V. Lunev <den@openvz.org>
Acked-by: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
I was looking at Patrick's fix to inet_diag and it occured
to me that we're using a pointer argument to return values
unnecessarily in netlink_run_queue. Changing it to return
the value will allow the compiler to generate better code
since the value won't have to be memory-backed.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Each netlink socket will live in exactly one network namespace,
this includes the controlling kernel sockets.
This patch updates all of the existing netlink protocols
to only support the initial network namespace. Request
by clients in other namespaces will get -ECONREFUSED.
As they would if the kernel did not have the support for
that netlink protocol compiled in.
As each netlink protocol is updated to be multiple network
namespace safe it can register multiple kernel sockets
to acquire a presence in the rest of the network namespaces.
The implementation in af_netlink is a simple filter implementation
at hash table insertion and hash table look up time.
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Hopefully captured all single statement cases under net/. I'm
not too sure if there is some policy about #includes that are
"guaranteed" (ie., in the current tree) to be available through
some other #included header, so I just added linux/kernel.h to
each changed file that didn't #include it previously.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
Switch cb_lock to mutex and allow netlink kernel users to override it
with a subsystem specific mutex for consistent locking in dump callbacks.
All netlink_dump_start users have been audited not to rely on any
side-effects of the previously used spinlock.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now that all users of netlink_dump_start() use netlink_run_queue()
to process the receive queue, it is possible to return -EINTR from
netlink_dump_start() directly, therefore simplying the callers.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Makes use of netlink_run_queue() to process the receive queue and
converts inet_diag_rcv_msg() to use the type safe netlink interface.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
For the common "(struct nlmsghdr *)skb->data" sequence, so that we reduce the
number of direct accesses to skb->data and for consistency with all the other
cast skb member helpers.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
So that it is also an offset from skb->head, reduces its size from 8 to 4 bytes
on 64bit architectures, allowing us to combine the 4 bytes hole left by the
layer headers conversion, reducing struct sk_buff size to 256 bytes, i.e. 4
64byte cachelines, and since the sk_buff slab cache is SLAB_HWCACHE_ALIGN...
:-)
Many calculations that previously required that skb->{transport,network,
mac}_header be first converted to a pointer now can be done directly, being
meaningful as offsets or pointers.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
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>
Currently netlink users BUG when the allocated skb for an event
notification is undersized. While this is certainly a kernel bug,
its not critical and crashing the kernel is too drastic, especially
when considering that these errors have appeared multiple times in
the past and it BUGs even if no listeners are present.
This patch replaces BUG by WARN_ON and changes the notification
functions to inform potential listeners of undersized allocations
using a unique error code (EMSGSIZE).
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
To be called from inet_diag_get_exact, also rename inet_diag_fill to
inet_csk_diag_fill, for consistency with inet_twsk_diag_fill.
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
To properly dump TIME_WAIT sockets and to reduce complexity a bit by
having per socket class accessor routines.
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The fields being accessed in inet_diag_dump are outside sock_common, the
common part of struct sock and struct inet_timewait_sock.
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Out of tcp6_timewait_sock, that now is just an aggregation of
inet_timewait_sock and inet6_timewait_sock, using tw_ipv6_offset in struct
inet_timewait_sock, that is common to the IPv6 transport protocols that use
timewait sockets, like DCCP and TCP.
tw_ipv6_offset plays the struct inet_sock pinfo6 role, i.e. for the generic
code to find the IPv6 area in a timewait sock.
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
And inet6_rsk_offset in inet_request_sock, for the same reasons as
inet_sock's pinfo6 member.
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Most netlink families make no use of the done() callback, making
it optional gets rid of all unnecessary dummy implementations.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
With this the previous setup is back, i.e. tcp_diag can be built as a module,
as dccp_diag and both share the infrastructure available in inet_diag.
If one selects CONFIG_INET_DIAG as module CONFIG_INET_TCP_DIAG will also be
built as a module, as will CONFIG_INET_DCCP_DIAG, if CONFIG_IP_DCCP was
selected static or as a module, if CONFIG_INET_DIAG is y, being statically
linked CONFIG_INET_TCP_DIAG will follow suit and CONFIG_INET_DCCP_DIAG will be
built in the same manner as CONFIG_IP_DCCP.
Now to aim at UDP, converting it to use inet_hashinfo, so that we can use
iproute2 for UDP sockets as well.
Ah, just to show an example of this new infrastructure working for DCCP :-)
[root@qemu ~]# ./ss -dane
State Recv-Q Send-Q Local Address:Port Peer Address:Port
LISTEN 0 0 *:5001 *:* ino:942 sk:cfd503a0
ESTAB 0 0 127.0.0.1:5001 127.0.0.1:32770 ino:943 sk:cfd50a60
ESTAB 0 0 127.0.0.1:32770 127.0.0.1:5001 ino:947 sk:cfd50700
TIME-WAIT 0 0 127.0.0.1:32769 127.0.0.1:5001 timer:(timewait,3.430ms,0) ino:0 sk:cf209620
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Next changeset will introduce net/ipv4/tcp_diag.c, moving the code that was put
transitioanlly in inet_diag.c.
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet
David S. Miller
Johannes Berg
Andi Kleen
Adrian Bunk
Pavel Emelyanov
Arnaldo Carvalho de Melo
Denis V. Lunev
Herbert Xu
Jean Delvare
Eric W. Biederman
Ilpo Järvinen
Patrick McHardy
Thomas Graf
YOSHIFUJI Hideaki
Al Viro
Panagiotis Issaris
Jörn Engel
Arnaldo Carvalho de Melo