With following patch I can reach maximum rate of my pktgen+udpsink
simulator :
- 'old' machine : dual quad core E5450  @3.00GHz
- 64 UDP rx flows (only differ by destination port)
- RPS enabled, NIC interrupts serviced on cpu0
- rps dispatched on 7 other cores. (~130.000 IPI per second)
- SLAB allocator (faster than SLUB in this workload)
- tg3 NIC
- 1.080.000 pps without a single drop at NIC level.

Idea is to add two prefetchw() calls in __alloc_skb(), one to prefetch
first sk_buff cache line, the second to prefetch the shinfo part.

Also using one memset() to initialize all skb_shared_info fields instead
of one by one to reduce number of instructions, using long word moves.

All skb_shared_info fields before 'dataref' are cleared in 
__alloc_skb().
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

pernet memory is guaranteed to exist when notifiers are called.
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

All distributions enable it, therefore no significant body of users
are even testing the driver with it disabled.  And making NAPI
configurable is heavily discouraged anyways.

I left the MSI-X interrupt enabling thing in an "#if 0" block
so hopefully someone can debug that and it can get re-enabled.
Probably it was just one of the NVIDIA chipset MSI erratas that
we work handle these days in the PCI quirks (see drivers/pci/quirks.c
and stuff like nvenet_msi_disable()).
Signed-off-by: David S. Miller <davem@davemloft.net>

Add GRO support to forcedeth.
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Commit 4b0b72f7 ( net: speedup udp receive path )
introduced a bug in skb_free_datagram_locked().

We should not skb_orphan() skb if we dont have the guarantee we are the
last skb user, this might happen with MSG_PEEK concurrent users.

To keep socket locked for the smallest period of time, we split
consume_skb() logic, inlined in skb_free_datagram_locked()
Reported-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Add missing linux/vmalloc.h include to net/sctp/probe.c
Signed-off-by: David S. Miller <davem@davemloft.net>

Add hlist_for_each_entry_rcu_bh() and
hlist_for_each_entry_continue_rcu_bh() macros, and use them in
ipv6_get_ifaddr(), if6_get_first() and if6_get_next() to fix lockdeps
warnings.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Reviewed-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: David S. Miller <davem@davemloft.net>

This is the first version of phy driver from Micrel Inc.
Signed-off-by: David J. Choi <david.choi@micrel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Worse yet, it seems that its arguments were in reverse order. Also
remove one related helper which seems hardly worth keeping.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>

Use correct bit positions in DM_SHARED_CTRL register for writes.

Michael Planes recently encountered a 'KY-RS9600 USB-LAN converter', which
came with a driver CD containing a Linux driver. This driver turns out to
be a copy of dm9601.c with symbols renamed and my copyright stripped.
That aside, it did contain 1 functional change in dm_write_shared_word(),
and after checking the datasheet the original value was indeed wrong
(read versus write bits).

On Michaels HW, this change bumps receive speed from ~30KB/s to ~900KB/s.
On other devices the difference is less spectacular, but still significant
(~30%).
Reported-by: Michael Planes <michael.planes@free.fr>
CC: stable@kernel.org
Signed-off-by: Peter Korsgaard <jacmet@sunsite.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>

This reverts commit d5ffd75a.

As requested by Jeff Kircher.
Signed-off-by: David S. Miller <davem@davemloft.net>

Frequently when using PPPoE with an interface MTU greater than 1500,
the skb is likely to be non-linear. If the skb needs to be passed to
pppd then the skb data must be read correctly.

The previous commit fixes an issue with accidentally sending skbs
to pppd based on an invalid read of the protocol type. When that
error occurred pppd was reading invalid skb data too.
Signed-off-by: Simon Arlott <simon@fire.lp0.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>

In ppp_input(), PPP_PROTO(skb) may refer to invalid data in the skb.

If this happens and (proto >= 0xc000 || proto == PPP_CCPFRAG) then
the packet is passed directly to pppd.

This occurs frequently when using PPPoE with an interface MTU
greater than 1500 because the skb is more likely to be non-linear.

The next 2 bytes need to be pulled in ppp_input(). The pull of 2
bytes in ppp_receive_frame() has been removed as it is no longer
required.
Signed-off-by: Simon Arlott <simon@fire.lp0.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: David S. Miller <davem@davemloft.net>

Per cpu variable softnet_data.total was shared between IRQ and SoftIRQ context
without any protection. And enqueue_to_backlog should update the netdev_rx_stat
of the target CPU.

This patch renames softnet_data.total to softnet_data.processed: the number of
packets processed in uppper levels(IP stacks).

softnet_stat data is moved into softnet_data.
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
----
 include/linux/netdevice.h |   17 +++++++----------
 net/core/dev.c            |   26 ++++++++++++--------------
 net/sched/sch_generic.c   |    2 +-
 3 files changed, 20 insertions(+), 25 deletions(-)
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Fix this one:
include/net/sock.h: error: two or more data types in declaration specifiers
Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

In commit 6be8ac2f ("[NET]: uninline skb_pull, de-bloats a lot")
we uninlined skb_pull.

But in some critical paths it makes sense to inline this thing
and it helps performance significantly.

Create an skb_pull_inline() so that we can do this in a way that
serves also as annotation.

Based upon a patch by Eric Dumazet.
Signed-off-by: David S. Miller <davem@davemloft.net>

The following patch adds the initiation of the sync sequence to
"sierra_net_bind()". If this step is omitted, the modem will never sync up
with the host and it will not be possible to establish a data connection.
Signed-off-by: Elina Pasheva <epasheva@sierrawireless.com>
Signed-off-by: Rory Filer <rfiler@sierrawireless.com>
Tested-by: Elina Pasheva <epasheva@sierrawireless.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we
need two atomic operations (and associated dirtying) per incoming
packet.

RCU conversion is pretty much needed :

1) Add a new structure, called "struct socket_wq" to hold all fields
that will need rcu_read_lock() protection (currently: a
wait_queue_head_t and a struct fasync_struct pointer).

[Future patch will add a list anchor for wakeup coalescing]

2) Attach one of such structure to each "struct socket" created in
sock_alloc_inode().

3) Respect RCU grace period when freeing a "struct socket_wq"

4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct
socket_wq"

5) Change sk_sleep() function to use new sk->sk_wq instead of
sk->sk_sleep

6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside
a rcu_read_lock() section.

7) Change all sk_has_sleeper() callers to :
  - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock)
  - Use wq_has_sleeper() to eventually wakeup tasks.
  - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock)

8) sock_wake_async() is modified to use rcu protection as well.

9) Exceptions :
  macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq"
instead of dynamically allocated ones. They dont need rcu freeing.

Some cleanups or followups are probably needed, (possible
sk_callback_lock conversion to a spinlock for example...).
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

When we create the sctp_datamsg and fragment the user data,
we know exactly if we are sending full segments or not and
how they might be bundled.  During this time, we can mark
messages a Nagle capable or not.  This makes the check at
transmit time much simpler.
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

Right now, if the highest tsn in the SACK doesn't change, we'll
end up scanning the transmitted lists on the transports twice:
once for locating the highest _new_ tsn, and once for actually
tagging chunks as acked.  This is a waste, since we can record
the highest _new_ tsn at the same time as tagging chunks.  Long
ago this was not possible because we would try to mark chunks
as missing at the same time as tagging them acked and this approach
didn't work.  Now that the two steps are separate, we can re-use
the old approach.
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

According to RFC 4960 Section 7.2.4:
 					If an endpoint is in Fast
   Recovery and a SACK arrives that advances the Cumulative TSN Ack
   Point, the miss indications are incremented for all TSNs reported
   missing in the SACK.
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

rwnd_press tracks the pressure on the recieve window.  Every
timer the receive buffer overlows, we truncate the receive
window and then grow it back.  However, if we don't track
the cumulative presser, it's possible to reach a situation
when receive buffer is empty, but rwnd stays truncated.
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

SCTP fast recovery algorithm really applies per association
and impacts all transports.
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

Right now, sctp transports are not fully initialized and when
adding any new fields, they have to be explicitely initialized.
This is prone to mistakes.  So we switch to calling kzalloc()
which makes things much simpler.
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

Saves some room in the sctp_transport structure.
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

We don't need to force the T3 timer any more and it's
actually wrong to do as it causes too long of a delay.
The timer will be started if one is not running, but if
one is running, we leave it alone.
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

The 'resent' bit is used to make sure that we don't update
rto estimate based on retransmitted chunks.  However, we already
have the 'rto_pending' bit that we test when need to update rto,
so 'resent' bit is just extra.  Additionally, we currently have
a bug in that we always set a 'resent' bit and thus rto estimate
is only updated by Heartbeats.
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

commit 4951feda0c60d1ef681f1a270afdd617924ab041
    sctp: Do no select unconfirmed transports for retransmissions

added code to make sure that we do not select unconfirmed paths
for data transmission.  This caused a problem when there are only
2 paths, 1 unconfirmed and 1 unreachable.  In that case, the next
retransmit path returned is NULL and that causes a kernel crash.

The solution is to only change retransmit paths if we found one to use.
Reported-by: Frank Schuster <frank.schuster01@web.de>
Signed-off-b: Vlad Yasevich <vladislav.yasevich@hp.com>

This assignment isn't needed because we did it earlier already.

Also another reason to delete the assignment is because it triggers a
Smatch warning about checking for NULL pointers after a dereference.
Reported-by: Vlad Yasevich <vladislav.yasevich@hp.com>
Signed-off-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

This patch implement sctp association probing module, the module
will be called sctp_probe.

This module allows for capturing the changes to SCTP association
state in response to incoming packets. It is used for debugging
SCTP congestion control algorithms.

Usage:
  $ modprobe sctp_probe [full=n] [port=n] [bufsize=n]
  $ cat /proc/net/sctpprobe

  The output format is:
    TIME     ASSOC     LPORT RPORT MTU    RWND  UNACK <REMOTE-ADDR   STATE  CWND   SSTHRESH  INFLIGHT  PARTIAL_BYTES_ACKED MTU> ...

  The output will be like this:
    9.226086 c4064c48  9000  8000  1500    53352     1 *192.168.0.19  1     4380    54784     1252        0     1500
    9.287195 c4064c48  9000  8000  1500    45144     5 *192.168.0.19  1     5880    54784     6500        0     1500
    9.289130 c4064c48  9000  8000  1500    42724     5 *192.168.0.19  1     7380    54784     6500        0     1500
    9.620332 c4064c48  9000  8000  1500    48284     4 *192.168.0.19  1     8880    54784     5200        0     1500
    ......
Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

sctp_chunk_is_data macro is defined to decide that
whether a chunk is data chunk or not.
Signed-off-by: Shan Wei <shanwei@cn.fujitsu.com>
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

An unconfirmed transport is one that we have not been
able to reach since the beginning.  There is no point in
trying to retrasnmit data on those transports.  Also, the
specification forbids it due to security issues.
Reported-by: Frank Schuster <frank.schuster01@web.de>
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

While doing retranmit, if control chunk exists, such as
FORWARD TSN chunk, and the DATA chunk can not be bundled with
this control chunk because of PMTU limit, no DATA chunk
will be retranmitted in the current implementation. This
patch makes sure to retranmit at least one DATA chunk in this case.
Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

The following patch removes the default from the Kconfig entry for sierra_net
driver as recommended.
Signed-off-by: Elina Pasheva <epasheva@sierrawireless.com>
Signed-off-by: Rory Filer <rfiler@sierrawireless.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

While lookup the output route, we do not set the src and dest
port. This will cause we got a wrong route if we had set the
outbund transport to IPsec with src or dst port.
Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>

In current implementation if ABORT chunk is received with T flag is set
and zero verification tag in COOKIE-WAIT state, the ABORT chunk will be
always accepted. This is because in COOKIE-WAIT state, the endpoint does
not know the peer's verification tag, and it's zero in the endpoint.
Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>