Fix macvlan_handle_frame() to update the rx counters based
on the return value of the vlan->receive call.
Updated the patch to not do any packet count drops when the interface
is down based on Herber'ts comments.
Signed-off-by: Sridhar Samudrala <sri@us.ibm.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Mark Wagner reported OOM symptoms when sending UDP traffic over
a macvtap link to a kvm receiver.
This appears to be caused by the fact that macvtap packet queues
are unlimited in length. This means that if the receiver can't
keep up with the rate of flow, then we will hit OOM. Of course
it gets worse if the OOM killer then decides to kill the receiver.
This patch imposes a cap on the packet queue length, in the same
way as the tuntap driver, using the device TX queue length.
Please note that macvtap currently has no way of giving congestion
notification, that means the software device TX queue cannot be
used and packets will always be dropped once the macvtap driver
queue fills up.
This shouldn't be a great problem for the scenario where macvtap
is used to feed a kvm receiver, as the traffic is most likely
external in origin so congestion notification can't be applied
anyway.
Of course, if anybody decides to complain about guest-to-guest
UDP packet loss down the track, then we may have to revisit this.
Incidentally, this patch also fixes a real memory leak when
macvtap_get_queue fails.
Chris Wright noticed that for this patch to work, we need a
non-zero TX queue length. This patch includes his work to change
the default macvtap TX queue length to 500.
Reported-by: Mark Wagner <mwagner@redhat.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Chris Wright <chrisw@sous-sol.org>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
In commit be1f3c2c02 "net: Enable 64-bit
net device statistics on 32-bit architectures" I redefined struct
net_device_stats so that it could be used in a union with struct
rtnl_link_stats64, avoiding the need for explicit copying or
conversion between the two. However, this is unsafe because there is
no locking required and no lock consistently held around calls to
dev_get_stats() and use of the statistics structure it returns.
In commit 28172739f0 "net: fix 64 bit
counters on 32 bit arches" Eric Dumazet dealt with that problem by
requiring callers of dev_get_stats() to provide storage for the
result. This means that the net_device::stats64 field and the padding
in struct net_device_stats are now redundant, so remove them.
Update the comment on net_device_ops::ndo_get_stats64 to reflect its
new usage.
Change dev_txq_stats_fold() to use struct rtnl_link_stats64, since
that is what all its callers are really using and it is no longer
going to be compatible with struct net_device_stats.
Eric Dumazet suggested the separate function for the structure
conversion.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is a small possibility that a reader gets incorrect values on 32
bit arches. SNMP applications could catch incorrect counters when a
32bit high part is changed by another stats consumer/provider.
One way to solve this is to add a rtnl_link_stats64 param to all
ndo_get_stats64() methods, and also add such a parameter to
dev_get_stats().
Rule is that we are not allowed to use dev->stats64 as a temporary
storage for 64bit stats, but a caller provided area (usually on stack)
Old drivers (only providing get_stats() method) need no changes.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use u64_stats_sync infrastructure to implement 64bit stats.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Register macvlan_port pointer as rx_handler data pointer. As macvlan_port is
removed from struct net_device, another netdev priv_flag is added to indicate
the device serves as a macvlan port.
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add possibility to register rx_handler data pointer along with a rx_handler.
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use call_rcu rather than synchronize_rcu.
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
What this patch does is it removes two receive frame hooks (for bridge and for
macvlan) from __netif_receive_skb. These are replaced them with a single
hook for both. It only supports one hook per device because it makes no
sense to do bridging and macvlan on the same device.
Then a network driver (of virtual netdev like macvlan or bridge) can register
an rx_handler for needed net device.
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fixes possible memory leak.
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
vlan/macvlan start_xmit() can inform caller of congestion with
NET_XMIT_CN return value. This doesnt mean packet was dropped.
Increment normal stat counters instead of tx_dropped.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now there's null check here and also again in the hook. Looking at bridge bits
which are simmilar, port structure is rcu_dereferenced right away in
handle_bridge and passed to hook. Looks nicer.
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
+little renaming of unicast functions to be smooth with multicast ones
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It's not desired for underlaying devices to change type. At the time,
there is for example possible to have bond with changed type from
Ethernet to Infiniband as a port of a bridge. This patch fixes this.
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: Jay Vosburgh <fubar@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This makes it possible to hook into the macvlan driver
from another kernel module. In particular, the goal is
to extend it with the macvtap backend that provides
a tun/tap compatible interface directly on the macvlan
device.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
In the vlan and macvlan drivers, the start_xmit function forwards
data to the dev_queue_xmit function for another device, which may
potentially belong to a different namespace.
To make sure that classification stays within a single namespace,
this resets the potentially critical fields.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Allow macvlan devices to support GRO.
Signed-off-by: Patrick Mullaney <pmullaney@novell.com>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Provide common routine for the transition of operational state for a leaf
device during a root device transition.
Signed-off-by: Patrick Mullaney <pmullaney@novell.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
In order to support all three modes of macvlan at
runtime, extend the existing netlink protocol
to allow choosing the mode per macvlan slave
interface.
This depends on a matching patch to iproute2
in order to become accessible in user land.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
This allows each macvlan slave device to be in one
of three modes, depending on the use case:
MACVLAN_PRIVATE:
The device never communicates with any other device
on the same upper_dev. This even includes frames
coming back from a reflective relay, where supported
by the adjacent bridge.
MACVLAN_VEPA:
The new Virtual Ethernet Port Aggregator (VEPA) mode,
we assume that the adjacent bridge returns all frames
where both source and destination are local to the
macvlan port, i.e. the bridge is set up as a reflective
relay.
Broadcast frames coming in from the upper_dev get
flooded to all macvlan interfaces in VEPA mode.
We never deliver any frames locally.
MACVLAN_BRIDGE:
We provide the behavior of a simple bridge between
different macvlan interfaces on the same port. Frames
from one interface to another one get delivered directly
and are not sent out externally. Broadcast frames get
flooded to all other bridge ports and to the external
interface, but when they come back from a reflective
relay, we don't deliver them again.
Since we know all the MAC addresses, the macvlan bridge
mode does not require learning or STP like the bridge
module does.
Based on an earlier patch "macvlan: Reflect macvlan packets
meant for other macvlan devices" by Eric Biederman.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Patrick McHardy <kaber@trash.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We have very similar code for rx statistics in
two places in the macvlan driver, with a third
one being added in the next patch.
Consolidate them into one function to improve
overall readability of the driver.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
gso_max_size must be set based on the value of the underlying device to
support devices not using the full 64k.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
With multi queue devices, its possible that several cpus call
macvlan RX routines simultaneously for the same macvlan device.
We update RX stats counter without any locking, so we can
get slightly wrong counters.
One possible fix is to use percpu counters, to get precise
accounting and also get guarantee of no cache line ping pongs
between cpus.
Note: this adds 16 bytes (32 bytes on 64bit arches) of percpu
data per macvlan device.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Both vlan and macvlan devices usually don't use a qdisc and immediately
queue packets to the underlying device. Propagate transmission state of
the underlying device to the upper layers so they can react on congestion
and/or inform the sending process.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is no good reason to not support userspace specifying the
network namespace during device creation, and it makes it easier
to create a network device and pass it to a child network namespace
with a well known name.
We have to be careful to ensure that the target network namespace
for the new device exists through the life of the call. To keep
that logic clear I have factored out the network namespace grabbing
logic into rtnl_link_get_net.
In addtion we need to continue to pass the source network namespace
to the rtnl_link_ops.newlink method so that we can find the base
device source network namespace.
Signed-off-by: Eric W. Biederman <ebiederm@aristanetworks.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Adding a list_head parameter to rtnl_link_ops->dellink() methods
allow us to queue devices on a list, in order to dismantle
them all at once.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
macvlan devices are currently not multi-queue capable.
We can do that defining rtnl_link_ops method,
get_tx_queues(), called from rtnl_create_link()
This new method gets num_tx_queues/real_num_tx_queues
from lower device.
macvlan_get_tx_queues() is a copy of vlan_get_tx_queues().
Because macvlan_start_xmit() has to update netdev_queue
stats only (and not dev->stats), I chose to change
tx_errors/tx_aborted_errors accounting to tx_dropped,
since netdev_queue structure doesnt define tx_errors /
tx_aborted_errors.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
To speedup ether addresses compares, we can use compare_ether_addr_64bits()
(all operands are guaranteed to be at least 8 bytes long)
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
These are all drivers that don't touch real hardware.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Addresses http://bugzilla.kernel.org/show_bug.cgi?id=13348
akpm: the reporter disappeared, so I typed it in again.
It is not possible to make clone of tagged VLAN interface to be used as
mac-based vlan interfave.
How reproducible:
Use any 802.1q tagged vlan interface, e.g. eth2.700 and clone it:
ip link add link eth2.700 address 00:04:75:cb:38:09 macvlan0 type macvlan
ip link set dev macvlan0 up
ip addr add 10.195.1.1/24 dev macvlan0
So far, so good. Now try to ping anything via macvlan0:
ping 10.195.1.2
Actual results:
For every attempted packet tx kernel writes to console:
------------[ cut here ]------------
WARNING: at net/8021q/vlan_dev.c:254 vlan_dev_hard_header+0x36/0x126 [8021q]()
Hardware name: M22ES
Modules linked in: arptable_filter arp_tables bridge veth macvlan arc4 ecb
ppp_mppe ppp_async crc_ccitt ppp_generic slhc autofs4 sunrpc 8021q garp stp
ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack xt_tcpudp
x_tables dm_mirror dm_region_hash dm_log dm_multipath dm_mod sbs sbshc lp
floppy snd_intel8x0 joydev snd_seq_dummy snd_intel8x0m snd_ac97_codec
ide_cd_mod ac97_bus snd_seq_oss cdrom snd_seq_midi_event serio_raw snd_seq
snd_seq_device snd_pcm_oss snd_mixer_oss parport_pc snd_pcm parport battery
8139cp snd_timer i2c_sis96x ac button snd rtc_cmos rtc_core 8139too soundcore
rtc_lib mii i2c_core pcspkr snd_page_alloc pata_sis libata sd_mod scsi_mod ext3
jbd ehci_hcd ohci_hcd uhci_hcd [last unloaded: ip_tables]
Pid: 0, comm: swapper Tainted: G W 2.6.29.3 #1
Call Trace:
[<c0425f48>] warn_slowpath+0x60/0x9f
[<c0425f6f>] warn_slowpath+0x87/0x9f
[<dffb850d>] vlan_dev_hard_header+0x0/0x126 [8021q]
[<dffb8543>] vlan_dev_hard_header+0x36/0x126 [8021q]
[<dffb850d>] vlan_dev_hard_header+0x0/0x126 [8021q]
[<df83155d>] macvlan_hard_header+0x3c/0x47 [macvlan]
[<df831521>] macvlan_hard_header+0x0/0x47 [macvlan]
[<c062bf3f>] arp_create+0xef/0x1ff
[<c062c08c>] arp_send+0x3d/0x54
[<c062c916>] arp_solicit+0x16c/0x177
[<c05fadd2>] neigh_timer_handler+0x227/0x269
[<c05fabab>] neigh_timer_handler+0x0/0x269
[<c042ce4d>] run_timer_softirq+0xf0/0x141
[<c0429e5a>] __do_softirq+0x76/0xf8
[<c0429de4>] __do_softirq+0x0/0xf8
<IRQ> [<c044fb67>] handle_level_irq+0x0/0xad
[<c0429db7>] irq_exit+0x35/0x62
[<c04046bb>] do_IRQ+0xdf/0xf4
[<c04035a7>] common_interrupt+0x27/0x2c
[<c04079c5>] default_idle+0x2a/0x3d
[<c0401bb6>] cpu_idle+0x57/0x70
Macvlan driver always uses standard ethernet header length for all types
of interface to which it is linked. This patch fixes this problem.
Reported-by: <sg.tweak@gmail.com>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch converts unicast address list to standard list_head using
previously introduced struct netdev_hw_addr. It also relaxes the
locking. Original spinlock (still used for multicast addresses) is not
needed and is no longer used for a protection of this list. All
reading and writing takes place under rtnl (with no changes).
I also removed a possibility to specify the length of the address
while adding or deleting unicast address. It's always dev->addr_len.
The convertion touched especially e1000 and ixgbe codes when the
change is not so trivial.
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
drivers/net/bnx2.c | 13 +--
drivers/net/e1000/e1000_main.c | 24 +++--
drivers/net/ixgbe/ixgbe_common.c | 14 ++--
drivers/net/ixgbe/ixgbe_common.h | 4 +-
drivers/net/ixgbe/ixgbe_main.c | 6 +-
drivers/net/ixgbe/ixgbe_type.h | 4 +-
drivers/net/macvlan.c | 11 +-
drivers/net/mv643xx_eth.c | 11 +-
drivers/net/niu.c | 7 +-
drivers/net/virtio_net.c | 7 +-
drivers/s390/net/qeth_l2_main.c | 6 +-
drivers/scsi/fcoe/fcoe.c | 16 ++--
include/linux/netdevice.h | 18 ++--
net/8021q/vlan.c | 4 +-
net/8021q/vlan_dev.c | 10 +-
net/core/dev.c | 195 +++++++++++++++++++++++++++-----------
net/dsa/slave.c | 10 +-
net/packet/af_packet.c | 4 +-
18 files changed, 227 insertions(+), 137 deletions(-)
Signed-off-by: David S. Miller <davem@davemloft.net>
One point of contention in high network loads is the dst_release() performed
when a transmited skb is freed. This is because NIC tx completion calls
dev_kree_skb() long after original call to dev_queue_xmit(skb).
CPU cache is cold and the atomic op in dst_release() stalls. On SMP, this is
quite visible if one CPU is 100% handling softirqs for a network device,
since dst_clone() is done by other cpus, involving cache line ping pongs.
It seems right place to release dst is in dev_hard_start_xmit(), for most
devices but ones that are virtual, and some exceptions.
David Miller suggested to define a new device flag, set in alloc_netdev_mq()
(so that most devices set it at init time), and carefuly unset in devices
which dont want a NULL skb->dst in their ndo_start_xmit().
List of devices that must clear this flag is :
- loopback device, because it calls netif_rx() and quoting Patrick :
"ip_route_input() doesn't accept loopback addresses, so loopback packets
already need to have a dst_entry attached."
- appletalk/ipddp.c : needs skb->dst in its xmit function
- And all devices that call again dev_queue_xmit() from their xmit function
(as some classifiers need skb->dst) : bonding, vlan, macvlan, eql, ifb, hdlc_fr
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Check whether the underlying device provides a set of ethtool ops before
checking for individual handlers to avoid NULL pointer dereferences.
Reported-by: Art van Breemen <ard@telegraafnet.nl>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Changing the mac address when a macvlan device is up will leave the
device on the wrong hash chain making it impossible to receive
packets.
There is no checking of the mac address set on the macvlan. Allowing
a misconfiguration to grab packets from the the underlying device or
another macvlan.
To resolve these problems I update the hash table of macvlans when the
mac address of a macvlan changes, and when updating the hash table
I verify that the new mac address is usable.
The result is well defined and predictable if not perfect handling of
mac vlan mac addresses.
To keep the code clear I have created a set of hash table maintenance
in macvlan so I am not open coding the hash function and the logic
needed to update the hash table all over the place.
Signed-off-by: Eric Biederman <ebiederm@aristanetworks.com>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
When running in a network namespace whose only link to
the outside world is a macvlan device, not being
able to create another macvlan is a real pain.
So modify macvlan creation to allow automatically forward
a creation of a macvlan on a macvlan to become a creation
of a macvlan on the underlying network device.
Signed-off-by: Eric Biederman <ebiederm@aristanetworks.com>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
PAUSE frames are only relevant for the real device, broadcasting them
to all macvlan devices can cause a significant load increase.
Reported-by: Ben Greear <greearb@candelatech.com>
Tested-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch moves neigh_setup and hard_start_xmit into the network device ops
structure. For bisection, fix all the previously converted drivers as well.
Bonding driver took the biggest hit on this.
Added a prefetch of the hard_start_xmit in the fast path to try and reduce
any impact this would have.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Convert to net_device_ops function table.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The generic packet receive code takes care of setting
netdev->last_rx when necessary, for the sake of the
bonding ARP monitor.
Drivers need not do it any more.
Some cases had to be skipped over because the drivers
were making use of the ->last_rx value themselves.
Signed-off-by: David S. Miller <davem@davemloft.net>
If macvlan's are used, it is useful to propgate speed and other settings
from underlying device up for application usage.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
The new address list lock needs to handle the same device layering
issues that the _xmit_lock one does.
This integrates work done by Patrick McHardy.
Signed-off-by: David S. Miller <davem@davemloft.net>
alloc_netdev_mq() now allocates an array of netdev_queue
structures for TX, based upon the queue_count argument.
Furthermore, all accesses to the TX queues are now vectored
through the netdev_get_tx_queue() and netdev_for_each_tx_queue()
interfaces. This makes it easy to grep the tree for all
things that want to get to a TX queue of a net device.
Problem spots which are not really multiqueue aware yet, and
only work with one queue, can easily be spotted by grepping
for all netdev_get_tx_queue() calls that pass in a zero index.
Signed-off-by: David S. Miller <davem@davemloft.net>
allmulti might overflow.
Commit: "netdevice: Fix promiscuity and allmulti overflow" in net-next makes
dev_set_promiscuity/allmulti return error number if overflow happened.
Here, we check the positive increment for allmulti to get error return.
Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Accesses are mostly structured such that when there are multiple TX
queues the code transformations will be a little bit simpler.
Signed-off-by: David S. Miller <davem@davemloft.net>
Move rcu-protected lists from list.h into a new header file rculist.h.
This is done because list are a very used primitive structure all over the
kernel and it's currently impossible to include other header files in this
list.h without creating some circular dependencies.
For example, list.h implements rcu-protected list and uses rcu_dereference()
without including rcupdate.h. It actually compiles because users of
rcu_dereference() are macros. Others RCU functions could be used too but
aren't probably because of this.
Therefore this patch creates rculist.h which includes rcupdates without to
many changes/troubles.
Signed-off-by: Franck Bui-Huu <fbuihuu@gmail.com>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Josh Triplett <josh@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
