Point 1:
The unregistering of a network device schedule a netdev_run_todo.
This function calls dev->destructor when it is set and the
destructor calls free_netdev.

Point 2:
In the case of an initialization of a network device the usual code
is:
 * alloc_netdev
 * register_netdev
    -> if this one fails, call free_netdev and exit with error.

Point 3:
In the register_netdevice function at the later state, when the device
is at the registered state, a call to the netdevice_notifiers is made.
If one of the notification falls into an error, a rollback to the
registered state is done using unregister_netdevice.

Conclusion:
When a network device fails to register during initialization because
one network subsystem returned an error during a notification call
chain, the network device is freed twice because of fact 1 and fact 2.
The second free_netdev will be done with an invalid pointer.

Proposed solution:
The following patch move all the code of unregister_netdevice *except*
the call to net_set_todo, to a new function "rollback_registered".

The following functions are changed in this way:
 * register_netdevice: calls rollback_registered when a notification fails
 * unregister_netdevice: calls rollback_register + net_set_todo, the call
                         order to net_set_todo is changed because it is the
                         latest now. Since it justs add an element to a list
                         that should not break anything.
Signed-off-by: NDaniel Lezcano <dlezcano@fr.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

netpoll_poll_lock() synchronizes the ->poll() invocation
code paths, but once we have the lock we have to make
sure that NAPI_STATE_SCHED is still set.  Otherwise we
get:

	cpu 0			cpu 1

	net_rx_action()		poll_napi()
	netpoll_poll_lock()	... spin on ->poll_lock
	->poll()
	  netif_rx_complete
	netpoll_poll_unlock()	acquire ->poll_lock()
				->poll()
				 netif_rx_complete()
				 CRASH

Based upon a bug report from Tina Yang.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It is not safe to to place struct pernet_operations in a special section.
We need struct pernet_operations to last until we call unregister_pernet_subsys.
Which doesn't happen until module unload.

So marking struct pernet_operations is a disaster for modules in two ways.
- We discard it before we call the exit method it points to.
- Because I keep struct pernet_operations on a linked list discarding
  it for compiled in code removes elements in the middle of a linked
  list and does horrible things for linked insert.

So this looks safe assuming __exit_refok is not discarded
for modules.
Signed-off-by: NEric W. Biederman <ebiederm@xmission.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Prevent error/backtrace from dev_rename() when changing
name of network device to the same name. This is a common
situation with udev and other scripts that bind addr to device.
Signed-off-by: NStephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Inconsistent prototype and real type for functions may have worse
consequences, than those for variables, so move them into a header.

Since they are used privately in net/core, make this file reside in
the same place.
Signed-off-by: NPavel Emelyanov <xemul@openvz.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NJeff Garzik <jgarzik@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Many places get the queue_mapping field from skb to pass it to the
netif_subqueue_stopped() which will be 0 in any case.

Make the helper that works with sk_buff
Signed-off-by: NPavel Emelyanov <xemul@openvz.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There's already such a helper to initialize this field.  Use it.
Signed-off-by: NPavel Emelyanov <xemul@openvz.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

TCP packets all have writable heads, that is, even though it's cloned, it is
writable up to the end of the TCP header.  This patch makes skb_checksum_help
aware of this fact by using skb_clone_writable and avoiding a copy for TCP.

I've also modified the BUG_ON tests to be unsigned.  The only case where this
makes a difference is if csum_start points to a location before skb->data.
Since skb->data should always include the header where the checksum field
is (and all currently callers adhere to that), this change is safe and may
uncover bugs later.
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As it is we always invoke pt_prev before ing_filter, even if there are no
ingress filters attached.  This can cause unnecessary cloning in pt_prev.

This patch changes it so that we only invoke pt_prev if there are ingress
filters attached.
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fix networking code kernel-doc for newly added parameters.

Warning(linux-2.6.23-git2//net/core/sock.c:879): No description found for parameter 'net'
Warning(linux-2.6.23-git2//net/core/dev.c:570): No description found for parameter 'net'
Warning(linux-2.6.23-git2//net/core/dev.c:594): No description found for parameter 'net'
Warning(linux-2.6.23-git2//net/core/dev.c:617): No description found for parameter 'net'
Warning(linux-2.6.23-git2//net/core/dev.c:641): No description found for parameter 'net'
Warning(linux-2.6.23-git2//net/core/dev.c:667): No description found for parameter 'net'
Warning(linux-2.6.23-git2//net/core/dev.c:722): No description found for parameter 'net'
Warning(linux-2.6.23-git2//net/core/dev.c:959): No description found for parameter 'net'
Warning(linux-2.6.23-git2//net/core/dev.c:1195): No description found for parameter 'dev'
Warning(linux-2.6.23-git2//net/core/dev.c:2105): No description found for parameter 'n'
Warning(linux-2.6.23-git2//net/core/dev.c:3272): No description found for parameter 'net'
Warning(linux-2.6.23-git2//net/core/dev.c:3445): No description found for parameter 'net'
Warning(linux-2.6.23-git2//include/linux/netdevice.h:1301): No description found for parameter 'cpu'
Signed-off-by: NRandy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The unregister_netdevice() and dev_change_net_namespace()
both check for dev->flags to be IFF_UP before calling the
dev_close(), but the dev_close() checks for IFF_UP itself,
so remove those unneeded checks.
Signed-off-by: NPavel Emelyanov <xemul@openvz.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

With the net namespaces many code leaved the __init section,
thus making the kernel occupy more memory than it did before.
Since we have a config option that prohibits the namespace
creation, the functions that initialize/finalize some netns
stuff are simply not needed and can be freed after the boot.

Currently, this is almost not noticeable, since few calls
are no longer in __init, but when the namespaces will be
merged it will be possible to free more code. I propose to
use the __net_init, __net_exit and __net_initdata "attributes"
for functions/variables that are not used if the CONFIG_NET_NS
is not set to save more space in memory.

The exiting functions cannot just reside in the __exit section,
as noticed by David, since the init section will have
references on it and the compilation will fail due to modpost
checks. These references can exist, since the init namespace
never dies and the exit callbacks are never called. So I
introduce the __exit_refok attribute just like it is already
done with the __init_refok.
Signed-off-by: NPavel Emelyanov <xemul@openvz.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This always bugged me: dev_ioctl() called dev_ifsioc() either inside
read_lock(dev_base_lock) or rtnl_lock(), depending on the ioctl being
executed.

This change moves the ioctls executed inside dev_base_lock to a new
function, dev_ifsioc_locked().  Now the locking context is completely
clear to the reader.
Signed-off-by: NJeff Garzik <jgarzik@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fix a bunch of sparse warnings. Mostly about 0 used as
NULL pointer, and shadowed variable declarations.
One notable case was that hash size should have been unsigned.
Signed-off-by: NStephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Since hardware header operations are part of the protocol class
not the device instance, make them into a separate object and
save memory.
Signed-off-by: NStephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When sysfs support is compiled out the kernel still keeps and maintains
the kobject tree.  So it is not safe to skip our kobject reference counting or
to avoid becoming members of the kobject tree.  It is safe to not add
the networking specific sysfs attributes.

This patch removes the sysfs special cases from net/core/dev.c
renames functions from netdev_sysfs_xxxx to netdev_kobject_xxxx
and always compiles in net-sysfs.c

net-sysfs.c is modified with a CONFIG_SYSFS guard around the parts
that are actually sysfs specific.
Signed-off-by: NEric W. Biederman <ebiederm@xmission.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The call_netdev_notifiers routine can successfully be used in
the net/core_dev.c itself.

This will save 6 lines of code and 62 ;) bytes of .text section.

62 is rather small, but I have one more patch saving ~30 bytes
from netns code (sent to Eric), so altogether they can save
some more noticeable amount.
Signed-off-by: NPavel Emelyanov <xemul@openvz.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The dev_name_hash and the dev_index_hash are now booth kmalloc-ed
(and each element is properly initialized as usually) so I think
it's worth consolidating this code making it look nicer (and
saving 28 bytes of .text section ;) )
Signed-off-by: NPavel Emelyanov <xemul@openvz.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This replaces the void * parameter with a struct net_device * which
is what is actually required.
Signed-off-by: NEric W. Biederman <ebiederm@xmission.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

HARD_TX_LOCK micro is a nice aggregation that could be used
in other spots. move it to netdevice.h
Also makes sure the previously superflous cpu arguement is used.
Thanks to DaveM for the suggestions.
Signed-off-by: NJamal Hadi Salim <hadi@cyberus.ca>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The problem:  proc_net files remember which network namespace the are
against but do not remember hold a reference count (as that would pin
the network namespace).   So we currently have a small window where
the reference count on a network namespace may be incremented when opening
a /proc file when it has already gone to zero.

To fix this introduce maybe_get_net and get_proc_net.

maybe_get_net increments the network namespace reference count only if it is
greater then zero, ensuring we don't increment a reference count after it
has gone to zero.

get_proc_net handles all of the magic to go from a proc inode to the network
namespace instance and call maybe_get_net on it.

PROC_NET the old accessor is removed so that we don't get confused and use
the wrong helper function.

Then I fix up the callers to use get_proc_net and handle the case case
where get_proc_net returns NULL.  In that case I return -ENXIO because
effectively the network namespace has already gone away so the files
we are trying to access don't exist anymore.
Signed-off-by: NEric W. Biederman <ebiederm@xmission.com>
Acked-by: NPaul E. McKenney <paulmck@us.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Requested by Johannes Berg.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch introduces NETIF_F_NETNS_LOCAL a flag to indicate
a network device is local to a single network namespace and
should never be moved.  Useful for pseudo devices that we
need an instance in each network namespace (like the loopback
device) and for any device we find that cannot handle multiple
network namespaces so we may trap them in the initial network
namespace.

This patch introduces the function dev_change_net_namespace
a function used to move a network device from one network
namespace to another.  To the network device nothing
special appears to happen, to the components of the network
stack it appears as if the network device was unregistered
in the network namespace it is in, and a new device
was registered in the network namespace the device
was moved to.

This patch sets up a namespace device destructor that
upon the exit of a network namespace moves all of the
movable network devices  to the initial network namespace
so they are not lost.
Signed-off-by: NEric W. Biederman <ebiederm@xmission.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When forcibly changing the network namespace of a device
I need something that can generate a name for the device
in the new namespace without overwriting the old name.

__dev_alloc_name provides me that functionality.
Signed-off-by: NEric W. Biederman <ebiederm@xmission.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch makes most of the generic device layer network
namespace safe.  This patch makes dev_base_head a
network namespace variable, and then it picks up
a few associated variables.  The functions:
dev_getbyhwaddr
dev_getfirsthwbytype
dev_get_by_flags
dev_get_by_name
__dev_get_by_name
dev_get_by_index
__dev_get_by_index
dev_ioctl
dev_ethtool
dev_load
wireless_process_ioctl

were modified to take a network namespace argument, and
deal with it.

vlan_ioctl_set and brioctl_set were modified so their
hooks will receive a network namespace argument.

So basically anthing in the core of the network stack that was
affected to by the change of dev_base was modified to handle
multiple network namespaces.  The rest of the network stack was
simply modified to explicitly use &init_net the initial network
namespace.  This can be fixed when those components of the network
stack are modified to handle multiple network namespaces.

For now the ifindex generator is left global.

Fundametally ifindex numbers are per namespace, or else
we will have corner case problems with migration when
we get that far.

At the same time there are assumptions in the network stack
that the ifindex of a network device won't change.  Making
the ifindex number global seems a good compromise until
the network stack can cope with ifindex changes when
you change namespaces, and the like.
Signed-off-by: NEric W. Biederman <ebiederm@xmission.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Except for carefully selected pseudo devices all network
interfaces should start out in the initial network namespace.
Ultimately it will be register_netdev that examines what
dev->nd_net is set to and places a device in a network namespace.

This patch modifies alloc_netdev to initialize the network
namespace a device is in with the initial network namespace.
This gets it right for the vast majority of devices so their
drivers need not be modified and for those few pseudo devices
that need something different they can change this parameter
before calling register_netdevice.

The network namespace parameter on a network device is not
reference counted as the devices are inside of a network namespace
and cannot remain in that namespace past the lifetime of the
network namespace.
Signed-off-by: NEric W. Biederman <ebiederm@xmission.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch makes /proc/net per network namespace.  It modifies the global
variables proc_net and proc_net_stat to be per network namespace.
The proc_net file helpers are modified to take a network namespace argument,
and all of their callers are fixed to pass &init_net for that argument.
This ensures that all of the /proc/net files are only visible and
usable in the initial network namespace until the code behind them
has been updated to be handle multiple network namespaces.

Making /proc/net per namespace is necessary as at least some files
in /proc/net depend upon the set of network devices which is per
network namespace, and even more files in /proc/net have contents
that are relevant to a single network namespace.
Signed-off-by: NEric W. Biederman <ebiederm@xmission.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.

In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.

The signature of the ->poll() call back goes from:

	int foo_poll(struct net_device *dev, int *budget)

to

	int foo_poll(struct napi_struct *napi, int budget)

The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract).  The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.

The napi_struct is to be embedded in the device driver private data
structures.

Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler.  Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.

With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.

Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.

[ Ported to current tree and all drivers converted.  Integrated
  Stephen's follow-on kerneldoc additions, and restored poll_list
  handling to the old style to fix mutual exclusion issues.  -DaveM ]
Signed-off-by: NStephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

http://bugzilla.kernel.org/show_bug.cgi?id=8797 shows that the
bonding driver may produce bogus combinations of the checksum
flags and SG/TSO.

For example, if you bond devices with NETIF_F_HW_CSUM and
NETIF_F_IP_CSUM you'll end up with a bonding device that
has neither flag set.  If both have TSO then this produces
an illegal combination.

The bridge device on the other hand has the correct code to
deal with this.

In fact, the same code can be used for both.  So this patch
moves that logic into net/core/dev.c and uses it for both
bonding and bridging.

In the process I've made small adjustments such as only
setting GSO_ROBUST if at least one constituent device
supports it.
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds code to allow errors to be passed up from event
handlers of NETDEV_REGISTER and NETDEV_CHANGENAME.  It also adds
the notifier_from_errno/notifier_to_errnor helpers to pass the
errno value up to the notifier caller.

If an error is detected when a device is registered, it causes
that operation to fail.  A NETDEV_UNREGISTER will be sent to
all event handlers.

Similarly if NETDEV_CHANGENAME fails the original name is restored
and a new NETDEV_CHANGENAME event is sent.

As such all event handlers must be idempotent with respect to
these events.

When an event handler is registered NETDEV_REGISTER events are
sent for all devices currently registered.  Should any of them
fail, we will send NETDEV_GOING_DOWN/NETDEV_DOWN/NETDEV_UNREGISTER
events to that handler for the devices which have already been
registered with it.  The handler registration itself will fail.
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When we added name-based hashing the dev_base_lock was designated as the
lock to take when changing the name hash list.  Unfortunately, because
it was a preexisting lock that just happened to be taken in the right
spots we neglected to take it in dev_change_name.

The race can affect calles of __dev_get_by_name that do so without taking
the RTNL.  They may end up walking down the wrong hash chain and end up
missing the device that they're looking for.
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch makes register_netdevice call dev->uninit if the regsitration
fails after dev->init has completed successfully.  Very few drivers use
the init/uninit calls but at least one (drivers/net/wan/sealevel.c) may
leak without this change.
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fix kernel-doc omissions in net/:

Warning(linux-2.6.23-rc1//net/core/dev.c:2728): No description found for parameter 'addr'
Warning(linux-2.6.23-rc1//net/core/dev.c:2752): No description found for parameter 'addr'
Warning(linux-2.6.23-rc1//net/core/dev.c:3839): No description found for parameter 'net_dma'
Warning(linux-2.6.23-rc1//net/core/dev.c:3877): No description found for parameter 'state'
Signed-off-by: NRandy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

From: Patrick McHardy <kaber@trash.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NYOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>

Signed-off-by: NDenis Cheng <crquan@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

this two functions could share the dev->_xmit_lock acquired context.
Signed-off-by: NDenis Cheng <crquan@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Because this function is only called by unregister_netdevice,
this moving could make this non-global function static,
and also remove its declaration in netdevice.h;

Any further, function __dev_addr_discard is also just called by
dev_mc_discard and dev_unicast_discard, keeping this two functions
both in one c file could make __dev_addr_discard also static
and remove its declaration in netdevice.h;

Futhermore, the sequential call to dev_unicast_discard and then
dev_mc_discard in unregister_netdevice have a similar mechanism that:
(netif_tx_lock_bh / __dev_addr_discard / netif_tx_unlock_bh),
they should merged into one to eliminate duplicates in acquiring and
releasing the dev->_xmit_lock, this would be done in my following patch.
Signed-off-by: NDenis Cheng <crquan@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add macvlan driver, which allows to create virtual ethernet devices
based on MAC address.
Signed-off-by: NPatrick McHardy <kaber@trash.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>