By separating the freeing code from the refcounting decrementing.
Probably reducing icache pressure when we still have reference counts to
go.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
v5 -> v6 (current):
-removed so far unused static functions
-corrected dev_addr_del_multiple to call del instead of add
v4 -> v5:
-added device address type (suggested by davem)
-removed refcounting (better to have simplier code then safe potentially few
bytes)
v3 -> v4:
-changed kzalloc to kmalloc in __hw_addr_add_ii()
-ASSERT_RTNL() avoided in dev_addr_flush() and dev_addr_init()
v2 -> v3:
-removed unnecessary rcu read locking
-moved dev_addr_flush() calling to ensure no null dereference of dev_addr
v1 -> v2:
-added forgotten ASSERT_RTNL to dev_addr_init and dev_addr_flush
-removed unnecessary rcu_read locking in dev_addr_init
-use compare_ether_addr_64bits instead of compare_ether_addr
-use L1_CACHE_BYTES as size for allocating struct netdev_hw_addr
-use call_rcu instead of rcu_synchronize
-moved is_etherdev_addr into __KERNEL__ ifdef
This patch introduces a new list in struct net_device and brings a set of
functions to handle the work with device address list. The list is a replacement
for the original dev_addr field and because in some situations there is need to
carry several device addresses with the net device. To be backward compatible,
dev_addr is made to point to the first member of the list so original drivers
sees no difference.
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
net_create() will be used by C/R to create fresh netns on restart.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Acked-by: Serge Hallyn <serue@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
copy_net_ns() doesn't copy anything, it creates fresh netns, so
get/put of old netns isn't needed.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Acked-by: Serge Hallyn <serue@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This should be very safe compared with full enabled, so I see
no reason why it shouldn't be done right away. As ECN can only
be negotiated if the SYN sending party is also supporting it,
somebody in the loop probably knows what he/she is doing. If
SYN does not ask for ECN, the server side SYN-ACK is identical
to what it is without ECN. Thus it's quite safe.
The chosen value is safe w.r.t to existing configs which
choose to currently set manually either 0 or 1 but
silently upgrades those who have not explicitly requested
ECN off.
Whether to just enable both sides comes up time to time but
unless that gets done now we can at least make the servers
aware of ECN already. As there are some known problems to occur
if ECN is enabled, it's currently questionable whether there's
any real gain from enabling clients as servers mostly won't
support it anyway (so we'd hit just the negative sides). After
enabling the servers and getting that deployed, the client end
enable really has some potential gain too.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
Based almost entirely upon a patch by Eric Dumazet.
The common case is to have num-tx-queues <= num_rx_queues
and even if num_tx_queues is larger it will not be significantly
larger.
Therefore, a subtraction loop is always going to be faster than
modulus.
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 0ba25ff4c6 ("br2684: convert to
net_device_ops") inadvertently deleted the initialization of the net_dev
pointer in the br2684_dev structure, leading to crashes. This patch
adds it back.
Reported-by: Mikko Vinni <mmvinni@yahoo.com>
Tested-by: Mikko Vinni <mmvinni@yahoo.com>
Signed-off-by: Rabin Vincent <rabin@rab.in>
Signed-off-by: David S. Miller <davem@davemloft.net>
The kernel should only be using the high 16 bits of a kernel
generated priority. Filter priorities in all other cases only
use the upper 16 bits of the u32 'prio' field of 'struct tcf_proto',
but when the kernel generates the priority of a filter is saves all
32 bits which can result in incorrect lookup failures when a filter
needs to be deleted or modified.
Signed-off-by: Robert Love <robert.w.love@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
xt_socket can use connection tracking, and checks whether it is a module.
Signed-off-by: Laszlo Attila Toth <panther@balabit.hu>
Signed-off-by: David S. Miller <davem@davemloft.net>
When skb_rx_queue_recorded() is true, we dont want to use jash distribution
as the device driver exactly told us which queue was selected at RX time.
jhash makes a statistical shuffle, but this wont work with 8 static inputs.
Later improvements would be to compute reciprocal value of real_num_tx_queues
to avoid a divide here. But this computation should be done once,
when real_num_tx_queues is set. This needs a separate patch, and a new
field in struct net_device.
Reported-by: Andrew Dickinson <andrew@whydna.net>
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Lennert Buytenhek wrote:
> Since 4fb6699481 ("net: Optimize memory
> usage when splicing from sockets.") I'm seeing this oops (e.g. in
> 2.6.30-rc3) when splicing from a TCP socket to /dev/null on a driver
> (mv643xx_eth) that uses LRO in the skb mode (lro_receive_skb) rather
> than the frag mode:
My patch incorrectly assumed skb->sk was always valid, but for
"frag_listed" skbs we can only use skb->sk of their parent.
Reported-by: Lennert Buytenhek <buytenh@wantstofly.org>
Debugged-by: Lennert Buytenhek <buytenh@wantstofly.org>
Tested-by: Lennert Buytenhek <buytenh@wantstofly.org>
Signed-off-by: Jarek Poplawski <jarkao2@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In "mac80211: correct wext transmit power handler"
I fixed the wext handler, but forgot to make the default of the
user_power_level -1 (aka "auto"), so that now the transmit power
is always set to 0, causing associations to time out and similar
problems since we're transmitting with very little power. Correct
this by correcting the default user_power_level to -1.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Bisected-by: Niel Lambrechts <niel.lambrechts@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
- ieee80211_wep_init(), which is called with rtnl_lock held, blocks in
request_module() [waiting for modprobe to load a crypto module].
- modprobe blocks in a call to flush_workqueue(), when it closes a TTY
[presumably when it exits].
- The workqueue item linkwatch_event() blocks on rtnl_lock.
There's no reason for wep_init() to be called with rtnl_lock held, so
just move it outside the critical section.
Signed-off-by: Alan Jenkins <alan-jenkins@tuffmail.co.uk>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
The x_tables are organized with a table structure and a per-cpu copies
of the counters and rules. On older kernels there was a reader/writer
lock per table which was a performance bottleneck. In 2.6.30-rc, this
was converted to use RCU and the counters/rules which solved the performance
problems for do_table but made replacing rules much slower because of
the necessary RCU grace period.
This version uses a per-cpu set of spinlocks and counters to allow to
table processing to proceed without the cache thrashing of a global
reader lock and keeps the same performance for table updates.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The Bluetooth 2.1 specification introduced four different security modes
that can be mapped using Legacy Pairing and Simple Pairing. With the
usage of Simple Pairing it is required that all connections (except
the ones for SDP) are encrypted. So even the low security requirement
mandates an encrypted connection when using Simple Pairing. When using
Legacy Pairing (for Bluetooth 2.0 devices and older) this is not required
since it causes interoperability issues.
To support this properly the low security requirement translates into
different host controller transactions depending if Simple Pairing is
supported or not. However in case of Simple Pairing the command to
switch on encryption after a successful authentication is not triggered
for the low security mode. This patch fixes this and actually makes
the logic to differentiate between Simple Pairing and Legacy Pairing
a lot simpler.
Based on a report by Ville Tervo <ville.tervo@nokia.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
The Bluetooth stack uses a reference counting for all established ACL
links and if no user (L2CAP connection) is present, the link will be
terminated to save power. The problem part is the dedicated pairing
when using Legacy Pairing (Bluetooth 2.0 and before). At that point
no user is present and pairing attempts will be disconnected within
10 seconds or less. In previous kernel version this was not a problem
since the disconnect timeout wasn't triggered on incoming connections
for the first time. However this caused issues with broken host stacks
that kept the connections around after dedicated pairing. When the
support for Simple Pairing got added, the link establishment procedure
needed to be changed and now causes issues when using Legacy Pairing
When using Simple Pairing it is possible to do a proper reference
counting of ACL link users. With Legacy Pairing this is not possible
since the specification is unclear in some areas and too many broken
Bluetooth devices have already been deployed. So instead of trying to
deal with all the broken devices, a special pairing timeout will be
introduced that increases the timeout to 60 seconds when pairing is
triggered.
If a broken devices now puts the stack into an unforeseen state, the
worst that happens is the disconnect timeout triggers after 120 seconds
instead of 4 seconds. This allows successful pairings with legacy and
broken devices now.
Based on a report by Johan Hedberg <johan.hedberg@nokia.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
These are later assigned to other values without being used meanwhile.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In 2.6.25 we added UDP mem accounting.
This unfortunatly added a penalty when a frame is transmitted, since
we have at TX completion time to call sock_wfree() to perform necessary
memory accounting. This calls sock_def_write_space() and utimately
scheduler if any thread is waiting on the socket.
Thread(s) waiting for an incoming frame was scheduled, then had to sleep
again as event was meaningless.
(All threads waiting on a socket are using same sk_sleep anchor)
This adds lot of extra wakeups and increases latencies, as noted
by Christoph Lameter, and slows down softirq handler.
Reference : http://marc.info/?l=linux-netdev&m=124060437012283&w=2
Fortunatly, Davide Libenzi recently added concept of keyed wakeups
into kernel, and particularly for sockets (see commit
37e5540b3c
epoll keyed wakeups: make sockets use keyed wakeups)
Davide goal was to optimize epoll, but this new wakeup infrastructure
can help non epoll users as well, if they care to setup an appropriate
handler.
This patch introduces new DEFINE_WAIT_FUNC() helper and uses it
in wait_for_packet(), so that only relevant event can wakeup a thread
blocked in this function.
Trace of function calls from bnx2 TX completion bnx2_poll_work() is :
__kfree_skb()
skb_release_head_state()
sock_wfree()
sock_def_write_space()
__wake_up_sync_key()
__wake_up_common()
receiver_wake_function() : Stops here since thread is waiting for an INPUT
Reported-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
this is the sctp code to enable hardware crc32c offload for
adapters that support it.
Originally by: Vlad Yasevich <vladislav.yasevich@hp.com>
modified by Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
On a brand new GRO skb, we cannot call ip_hdr since the header
may lie in the non-linear area. This patch adds the helper
skb_gro_network_header to handle this.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
The skb_gro_* code fails to handle the case where a header starts
in the linear area but ends in the frags area. Since the goal
of skb_gro_* is to optimise the case of completely non-linear
packets, we can simply bail out if we have anything in the linear
area.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Right now we have no upper limit on the size of the route cache hash table.
On a 128GB POWER6 box it ends up as 32MB:
IP route cache hash table entries: 4194304 (order: 9, 33554432 bytes)
It would be nice to cap this for memory consumption reasons, but a massive
hashtable also causes a significant spike when measuring OS jitter.
With a 32MB hashtable and 4 million entries, rt_worker_func is taking
5 ms to complete. On another system with more memory it's taking 14 ms.
Even though rt_worker_func does call cond_sched() to limit its impact,
in an HPC environment we want to keep all sources of OS jitter to a minimum.
With the patch applied we limit the number of entries to 512k which
can still be overriden by using the rt_entries boot option:
IP route cache hash table entries: 524288 (order: 6, 4194304 bytes)
With this patch rt_worker_func now takes 0.460 ms on the same system.
Signed-off-by: Anton Blanchard <anton@samba.org>
Acked-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When I initially implemented this protocol, I disregarded the use of netlink
attribute headers, thinking for my purposes they weren't needed. I've come to
find out that, as I'm starting to work with sending down messages with
associated data (like config messages), the kernel code spits out warnings about
trailing data in a netlink skb that doesn't have an associated header on it. As
such, I'm going to start including attribute headers in my netlink transaction,
and so for completeness, I should likely include them on messages bound from the
kernel to user space. This patch adds that header to the kernel, and bumps the
protocol version accordingly
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When kernel inserts a temporary SA for IKE, it uses the wrong hash
value for dst list. Two hash values were calcultated before: one with
source address and one with a wildcard source address.
Bug hinted by Junwei Zhang <junwei.zhang@6wind.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The IP MIB (RFC 4293) defines stats for InOctets, OutOctets, InMcastOctets and
OutMcastOctets:
http://tools.ietf.org/html/rfc4293
But it seems we don't track those in any way that easy to separate from other
protocols. This patch adds those missing counters to the stats file. Tested
successfully by me
With help from Eric Dumazet.
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, the VLAN event handler does not adjust the VLAN
device's carrier state when the real device or the VLAN device is set
administratively up or down.
The following patch adds a transfer of operating state from the
real device to the VLAN device when the real device is administratively
set up or down, and sets the carrier state up or down during init, open
and close of the VLAN device.
This permits observers above the VLAN device that care about the
carrier state (bonding's link monitor, for example) to receive updates
for administrative changes by more closely mimicing the behavior of real
devices.
Signed-off-by: Jay Vosburgh <fubar@us.ibm.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
net/mac80211/tx.c: In function ‘ieee80211_tx_h_select_key’:
net/mac80211/tx.c:448: warning: ‘key’ may be used uninitialized in this function
drivers/net/wireless/ath/ath9k/rc.c: In function ‘ath_rc_rate_getidx’:
drivers/net/wireless/ath/ath9k/rc.c:815: warning: ‘nextindex’ may be used uninitialized in this function
drivers/net/wireless/hostap/hostap_plx.c: In function ‘prism2_plx_probe’:
drivers/net/wireless/hostap/hostap_plx.c:438: warning: ‘cor_index’ may be used uninitialized in this function
drivers/net/wireless/hostap/hostap_plx.c:438: warning: ‘cor_offset’ may be used uninitialized in this function
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Related-to: commit 325fb5b4d2
The compat path suffers from a similar problem. It only uses a __be32
when all of the recent code uses, and expects, an nf_inet_addr
everywhere. As a result, addresses stored by xt_recents were
filled with whatever other stuff was on the stack following the be32.
Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
With a minor compile fix from Roman.
Reported-and-tested-by: Roman Hoog Antink <rha@open.ch>
Signed-off-by: Patrick McHardy <kaber@trash.net>
This patch adds missing role attribute to the DCCP type, otherwise
the creation of entries is not of any use.
The attribute added is CTA_PROTOINFO_DCCP_ROLE which contains the
role of the conntrack original tuple.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Commit d0dba725 (netfilter: ctnetlink: add callbacks to the per-proto
nlattrs) changed the protocol registration function to abort if the
to-be registered protocol doesn't provide a new callback function.
The DCCP and UDP-Lite IPv6 protocols were missed in this conversion,
add the required callback pointer.
Reported-and-tested-by: Steven Jan Springl <steven@springl.ukfsn.org>
Signed-off-by: Patrick McHardy <kaber@trash.net>
From: Ursula Braun <ubraun@linux.vnet.ibm.com>
net/iucv/af_iucv.c in net-next-2.6 is almost correct. 4 lines should
still be deleted. These are the remaining changes:
Signed-off-by: David S. Miller <davem@davemloft.net>
The SO_MSGLIMIT socket option modifies the message limit for new
IUCV communication paths.
The message limit specifies the maximum number of outstanding messages
that are allowed for connections. This setting can be lowered by z/VM
when an IUCV connection is established.
Expects an integer value in the range of 1 to 65535.
The default value is 65535.
The message limit must be set before calling connect() or listen()
for sockets.
If sockets are already connected or in state listen, changing the message
limit is not supported.
For reading the message limit value, unconnected sockets return the limit
that has been set or the default limit. For connected sockets, the actual
message limit is returned. The actual message limit is assigned by z/VM
for each connection and it depends on IUCV MSGLIMIT authorizations
specified for the z/VM guest virtual machine.
Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Ursula Braun <ursula.braun@de.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jan Engelhardt