The first version of the driver had hard-coded the logic
for handling the checksum offloading.
This was designed according to the chips included in
the STM platforms where:
o MAC10/100 supports no COE at all.
o GMAC fully supports RX/TX COE.

This is not good for other chip configurations where,
for example, the mac10/100 supports the tx csum in HW
or when the GMAC has no IPC.

Thanks to Johannes Stezenbach; he provided me a first
draft of this patch that only reviewed the IPC for the
GMAC devices.

This patch also helps on SPEAr platforms where the
MAC10/100 can perform the TX csum in HW.
Thanks to Deepak SIKRI for his support on this.

In the end, GMAC devices for STM platforms have
a bugged Jumbo frame support that needs to have
the Tx COE disabled for oversized frames (due to
limited buffer sizes). This information is also
passed through the driver's platform structure.
Signed-off-by: NGiuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: NJohannes Stezenbach <js@sig21.net>
Signed-off-by: NDeepak SIKRI <deepak.sikri@st.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds the CSR Clock range selection.

Original patch from Johannes Stezenbach fixed the CSR
in the stmmac_mdio. We agreed to provide this through
the platform instead of.
Also thanks to Johannes for having tested it on ARM.
Signed-off-by: NGiuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: NJohannes Stezenbach <js@sig21.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

commit ab95bfe0 (net: replace hooks in __netif_receive_skb) added
rx_handler at wrong place, between two cache line aligned objects,
creating a big hole (a full cache line)

Move rx_handler and rx_handler_data before rx_queue, filling existing
hole.

Move master field in the cache line(s) used in receive path.

This saves 64 bytes (or L1_CACHE_BYTES), and avoids two possible
cache misses in receive path.
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

dev->ip_ptr is protected by rtnl and rcu.

Yet some places dont use appropriate primitives and/or locking rules.
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NRémi Denis-Courmont <remi.denis-courmont@nokia.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

I wish we could use something cleaner, such as bind(). But that would
not work since resource subscription is orthogonal/in addition to the
normal object ID allocated via bind(). This is similar to multicasting
which also uses ioctl()'s.
Signed-off-by: NRémi Denis-Courmont <remi.denis-courmont@nokia.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When both destination device and object are nul, Phonet routes the
packet according to the resource field. In fact, this is the most
common pattern when sending Phonet "request" packets. In this case,
the packet is delivered to whichever endpoint (socket) has
registered the resource.

This adds a new table so that Linux processes can register their
Phonet sockets to Phonet resources, if they have adequate privileges.

(Namespace support is not implemented at the moment.)
Signed-off-by: NRémi Denis-Courmont <remi.denis-courmont@nokia.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Closing a pipe endpoint is not normally allowed by the Phonet pipe,
other than as a side after-effect of removing the pipe between two
endpoints. But there is no way to prevent Linux userspace processes
from being killed or suffering from bugs, so this can still happen.
We might as well forcefully close Phonet pipe endpoints then.

The cellular modem supports only a few existing pipes at a time. So we
really should not leak them. This change instructs the modem to destroy
the pipe if either of the pipe's endpoint (Linux socket) is closed too
early.
Signed-off-by: NRémi Denis-Courmont <remi.denis-courmont@nokia.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We sometime want to dereference an rcu protected pointer while
holding RTNL. Use a macro to hide all lockdep details.
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

struct ethtool_rawip4_spec and struct ethtool_ether_spec are neither
commented nor used by any driver, so remove them.  Adjust padding in
the user-visible unions that included these structures.

Fix references to struct ethtool_rawip4_spec in
ethtool_get_rx_ntuple(), which should use struct ethtool_usrip4_spec.

struct ethtool_usrip4_spec cannot hold IPv6 host addresses and there
is no separate structure that can, so remove ETH_RX_NFC_IP6 and the
reference to it in niu.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There are now several interfaces within the ethtool API for getting
and setting RX flow filtering and hashing behaviour, most of which are
poorly documented.  This adds kernel-doc comments for all these
interfaces, based on the existing incomplete comments and on the
initial implementations.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

commit 30fff923 introduced in linux-2.6.33 (udp: bind() optimisation)
added a secondary hash on UDP, hashed on (local addr, local port).

Problem is that following sequence :

fd = socket(...)
connect(fd, &remote, ...)

not only selects remote end point (address and port), but also sets
local address, while UDP stack stored in secondary hash table the socket
while its local address was INADDR_ANY (or ipv6 equivalent)

Sequence is :
 - autobind() : choose a random local port, insert socket in hash tables
              [while local address is INADDR_ANY]
 - connect() : set remote address and port, change local address to IP
              given by a route lookup.

When an incoming UDP frame comes, if more than 10 sockets are found in
primary hash table, we switch to secondary table, and fail to find
socket because its local address changed.

One solution to this problem is to rehash datagram socket if needed.

We add a new rehash(struct socket *) method in "struct proto", and
implement this method for UDP v4 & v6, using a common helper.

This rehashing only takes care of secondary hash table, since primary
hash (based on local port only) is not changed.
Reported-by: NKrzysztof Piotr Oledzki <ole@ans.pl>
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Tested-by: NKrzysztof Piotr Oledzki <ole@ans.pl>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

flows are an obsolete date type.
Signed-off-by: NAndy Grover <andy.grover@oracle.com>

Replace e.g. u_int32_t types with the more common uint32_t.
Reported-by: NMatthew Wilcox <willy@linux.intel.com>
Signed-off-by: NAndy Grover <andy.grover@oracle.com>

Also, a number of changes were made based on the assumption that
rds.h wasn't exported, so roll these back.
Signed-off-by: NAndy Grover <andy.grover@oracle.com>

Add two CMSGs for masked versions of cswp and fadd. args
struct modified to use a union for different atomic op type's
arguments. Change IB to do masked atomic ops. Atomic op type
in rds_message similarly unionized.
Signed-off-by: NAndy Grover <andy.grover@oracle.com>

Add a flag to the API so users can indicate they want
silent operations. This is needed because silent ops
cannot be used with USE_ONCE MRs, so we can't just
assume silent.

Also, change send_xmit to do atomic op before rdma op if
both are present, and centralize the hairy logic to determine if
we want to attempt silent, or not.
Signed-off-by: NAndy Grover <andy.grover@oracle.com>

Implement a CMSG-based interface to do FADD and CSWP ops.

Alter send routines to handle atomic ops.

Add atomic counters to stats.

Add xmit_atomic() to struct rds_transport

Inline rds_ib_send_unmap_rdma into unmap_rm
Signed-off-by: NAndy Grover <andy.grover@oracle.com>

We use rcu_dereference_check(p, rcu_read_lock_held() ||
lockdep_rtnl_is_held()) several times in network stack.

More usages to come too, so its time to create a helper.
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

- Do not create expectation when forwarding the PORT
  command to avoid blocking the connection. The problem is that
  nf_conntrack_ftp.c:help() tries to create the same expectation later in
  POST_ROUTING and drops the packet with "dropping packet" message after
  failure in nf_ct_expect_related.

- Change ip_vs_update_conntrack to alter the conntrack
  for related connections from real server. If we do not alter the reply in
  this direction the next packet from client sent to vport 20 comes as NEW
  connection. We alter it but may be some collision happens for both
  conntracks and the second conntrack gets destroyed immediately. The
  connection stucks too.
Signed-off-by: NJulian Anastasov <ja@ssi.bg>
Signed-off-by: NSimon Horman <horms@verge.net.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Sandybridge GTT has new cache control bits in PTE, which controls
graphics page cache in LLC or LLC/MLC, so we need to extend the mask
function to respect the new bits.

And set cache control to always LLC only by default on Gen6.
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>
Cc: stable@kernel.org
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>

cgroup_attach_task_current_cg API that have upstream is backwards: we
really need an API to attach to the cgroups from another process A to
the current one.

In our case (vhost), a priveledged user wants to attach it's task to cgroups
from a less priveledged one, the API makes us run it in the other
task's context, and this fails.

So let's make the API generic and just pass in 'from' and 'to' tasks.
Add an inline wrapper for cgroup_attach_task_current_cg to avoid
breaking bisect.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Acked-by: NLi Zefan <lizf@cn.fujitsu.com>
Acked-by: NPaul Menage <menage@google.com>

Bug seen by Dr. David Alan Gilbert with sparse
Signed-off-by: NPhilippe Langlais <philippe.langlais@stericsson.com>
Cc: stable <stable@kernel.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Dave reported an rcu lockdep warning on 2.6.35.4 kernel

task->cgroups and task->cgroups->subsys[i] are protected by RCU.
So we avoid accessing invalid pointers here. This might happen,
for example, when you are deref-ing those pointers while someone
move @task from one cgroup to another.
Reported-by: NDave Jones <davej@redhat.com>
Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

fresh skbs have ip_summed set to CHECKSUM_NONE (0)

We can avoid setting again skb->ip_summed to CHECKSUM_NONE in drivers.

Introduce skb_checksum_none_assert() helper so that we keep this
assertion documented in driver sources.

Change most occurrences of :

skb->ip_summed = CHECKSUM_NONE;

by :

skb_checksum_none_assert(skb);
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Correct state range of PHY bus addresses (i.e. 0-31) in comment,
make spelling of PHY consistent in comments.
Signed-off-by: NPeter Meerwald <pmeerw@pmeerw.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

- napi_gro_flush() is exported from net/core/dev.c, to avoid
  an irq_save/irq_restore in the packet receive path.
- use napi_gro_receive() instead of netif_receive_skb()
- use napi_gro_flush() before calling __napi_complete()
- turn on NETIF_F_GRO by default
- Tested on a Marvell 88E8001 Gigabit NIC
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This is needed for proper PCI-E support on P1021 SoCs.
Signed-off-by: NAnton Vorontsov <avorontsov@mvista.com>
Signed-off-by: NKumar Gala <galak@kernel.crashing.org>

As some driver authors seem to reintroduce dev->last_rx use,
add a comment to strongly discourage this.

Since commit 6cf3f41e (bonding, net: Move last_rx update into bonding
recv logic), network drivers dont need to update last_rx themselves,
unless they use this field to implement a timeout.

Not updating last_rx helps not dirtying a cache line, improving
performance in SMP.
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This updates the use of larger initial windows, as originally specified in
RFC 3390, to use the newer IW values specified in RFC 5681, section 3.1.

The changes made in RFC 5681 are:
 a) the setting now is more clearly specified in units of segments (as the
    comments  by John Heffner emphasized, this was not very clear in RFC 3390);
 b) for connections with 1095 < SMSS <= 2190 there is now a change:
    - RFC 3390 says that IW <= 4380,
    - RFC 5681 says that IW = 3 * SMSS <= 6570.

Since RFC 3390 is older and "only" proposed standard, whereas the newer RFC 5681
is already draft standard, it seems preferable to use the newer IW variant.
Signed-off-by: NGerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch consolidates initial-window code common to TCP and CCID-2:
 * TCP uses RFC 3390 in a packet-oriented manner (tcp_input.c) and
 * CCID-2 uses RFC 3390 in packet-oriented manner (RFC 4341).
Signed-off-by: NGerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch provides a "user timeout" support as described in RFC793. The
socket option is also needed for the the local half of RFC5482 "TCP User
Timeout Option".

TCP_USER_TIMEOUT is a TCP level socket option that takes an unsigned int,
when > 0, to specify the maximum amount of time in ms that transmitted
data may remain unacknowledged before TCP will forcefully close the
corresponding connection and return ETIMEDOUT to the application. If
0 is given, TCP will continue to use the system default.

Increasing the user timeouts allows a TCP connection to survive extended
periods without end-to-end connectivity. Decreasing the user timeouts
allows applications to "fail fast" if so desired. Otherwise it may take
upto 20 minutes with the current system defaults in a normal WAN
environment.

The socket option can be made during any state of a TCP connection, but
is only effective during the synchronized states of a connection
(ESTABLISHED, FIN-WAIT-1, FIN-WAIT-2, CLOSE-WAIT, CLOSING, or LAST-ACK).
Moreover, when used with the TCP keepalive (SO_KEEPALIVE) option,
TCP_USER_TIMEOUT will overtake keepalive to determine when to close a
connection due to keepalive failure.

The option does not change in anyway when TCP retransmits a packet, nor
when a keepalive probe will be sent.

This option, like many others, will be inherited by an acceptor from its
listener.
Signed-off-by: NH.K. Jerry Chu <hkchu@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NSimon Horman <horms@verge.net.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Stub out vm_get_page_prot() if there's no MMU.

This was added by commit 804af2cf ("[AGPGART] remove private page
protection map") and is used in commit c07fbfd1 ("fbmem: VM_IO set,
but not propagated") in the fbmem video driver, but the function doesn't
exist on NOMMU, resulting in an undefined symbol at link time.
Signed-off-by: NDavid Howells <dhowells@redhat.com>
Reviewed-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

resize pid and reorder the fanotify_event_metadata so it is naturally
aligned and we can work towards dropping the packed attributed
Signed-off-by: NTvrtko Ursulin <tvrtko.ursulin@sophos.com>
Cc: Andreas Dilger <adilger@dilger.ca>
Signed-off-by: NEric Paris <eparis@redhat.com>

Add support to mac80211 for changing the interface
type even when the interface is UP, if the driver
supports it.

To achieve this
 * add a new driver callback for switching,
 * split some of the interface up/down code out
   into new functions (do_open/do_stop), and
 * maintain an own __SDATA_RUNNING bit that will
   not be set during interface type, so that any
   other code doesn't use the interface.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>

Some vendor specified mechanisms for 802.1X-style
functionality use a different protocol than EAP
(even if EAP is vendor-extensible). Allow setting
the ethertype for the protocol when a driver has
support for this. The default if unspecified is
EAP, of course.

Note: This is suitable only for station mode, not
      for AP implementation.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NJuuso Oikarinen <juuso.oikarinen@nokia.com>
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>

The ieee80211_scan_completed() function was a frequent
source of potential deadlocks, since it is called by
drivers but may call back into drivers, so drivers had
to make sure to call it without any locks held, which
frequently lead to more complex code in drivers. Avoid
that problem by allowing the function to be called in
any context, and queueing the actual work it does.
Also update the documentation for it to indicate this.
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>