This reverts commit ff65e827.

As explained by Stephen Hemminger, the traversal doesn't require
RCU handling as we hold a lock.

The list addition et al. calls, on the other hand, do.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NNicholas Nunley <nicholasx.d.nunley@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NNicholas Nunley <nicholasx.d.nunley@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NNicholas Nunley <nicholasx.d.nunley@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NNicholas Nunley <nicholasx.d.nunley@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch makes it so that igb now uses the DMA API functions instead of
the PCI API functions.  To do this the pci_dev pointer that was in the
rings has been replaced with a device pointer, and as a result all
references to [tr]x_ring->pdev have been replaced with [tr]x_ring->dev.

This patch is based of of work originally done by Nicholas Nunley.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NNicholas Nunley <nicholasx.d.nunley@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NNicholas Nunley <nicholasx.d.nunley@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Noticed by Michał Mirosław.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Implement the ->set_flags ethtool method to control NETIF_F_RXHASH and
set skb->rxhash to the HW calculated hash accordingly.

Follow Eric Dumazet's suggestion and use the hash value raw.
Signed-off-by: NDimitris Michailidis <dm@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

doing it within the driver does not look good.
And surely isn't how platform devices were meat to be used.
Acked-by: NRalf Baechle <ralf@linux-mips.org>
Signed-off-by: NSebastian Andrzej Siewior <sebastian@breakpoint.cc>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

CONFIG_SIBYTE_STANDALONE is gone since v2.6.31-rc1 ("MIPS: Sibyte:
Remove standalone kernel support")
This is a missing piece.
Signed-off-by: NSebastian Andrzej Siewior <sebastian@breakpoint.cc>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now there's no need to use this fuction directly because it's handled by
register_pernet_device. So to make this simple and easy to understand,
make this static to do not tempt potentional users.
Signed-off-by: NJiri Pirko <jpirko@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Some boards have longer serial numbers in their VPD, up to 24 bytes.
Signed-off-by: NDimitris Michailidis <dm@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Some boards' VPDs contain additional keywords or have longer serial numbers,
meaning the keyword locations are variable.  Ditch the static layout and
use the pci_vpd_* family of functions to parse the VPD instead.
Signed-off-by: NDimitris Michailidis <dm@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Current socket backlog limit is not enough to really stop DDOS attacks,
because user thread spend many time to process a full backlog each
round, and user might crazy spin on socket lock.

We should add backlog size and receive_queue size (aka rmem_alloc) to
pace writers, and let user run without being slow down too much.

Introduce a sk_rcvqueues_full() helper, to avoid taking socket lock in
stress situations.

Under huge stress from a multiqueue/RPS enabled NIC, a single flow udp
receiver can now process ~200.000 pps (instead of ~100 pps before the
patch) on a 8 core machine.
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

batch skb dequeueing from softnet input_pkt_queue to reduce potential lock
contention when RPS is enabled.

Note: in the worst case, the number of packets in a softnet_data may
be double of netdev_max_backlog.
Signed-off-by: NChangli Gao <xiaosuo@gmail.com>
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Idea from Eric Dumazet.

As for placement inside of struct sock, I tried to choose a place
that otherwise has a 32-bit hole on 64-bit systems.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
Acked-by: NEric Dumazet <eric.dumazet@gmail.com>

Description: When using Intel smartspeed, the patch displays a
warning when the link down shifts to 1 Gig.
Signed-off-by: NAnjali Singhai <anjali.singhai@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The way we were setting autoneg via ethtool was inconstant with that
of our other drivers.  It will change the following:

If autoneg is off:
>ethtool -a eth0
Pause parameters for eth0:

Autonegotiate:  off
RX:             off
TX:             off

Before:
>ethtool -A eth0 autoneg on
>ethtool -a eth0
Pause parameters for eth0:

Autonegotiate:  off
RX:             off
TX:             off

Now:
>ethtool -A eth0 autoneg on
>ethtool -a eth0
Pause parameters for eth0:

Autonegotiate:  on
RX:             on
TX:             on
Signed-off-by: NDon Skidmore <donald.c.skidmore@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The ixgbevf driver would always report 10Gig speeds even when the link
speed is downshifted to 1Gig.  This patch fixes that problem.
Signed-off-by: NGreg Rose <gregory.v.rose@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

reimplement softnet_data.output_queue as a FIFO queue to keep the
fairness among the qdiscs rescheduled.
Signed-off-by: NChangli Gao <xiaosuo@gmail.com>
Acked-by: NEric Dumazet <eric.dumazet@gmail.com>
----
 include/linux/netdevice.h |    1 +
 net/core/dev.c            |   22 ++++++++++++----------
 2 files changed, 13 insertions(+), 10 deletions(-)
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Convert DEBUGOUTx to pr_debug
Convert DEBUGFUNC to more commonly used ENTER
Convert mac address output to %pM
Use #define pr_fmt
Convert a few printks to pr_<level>
Improve ixgb_mc_addr_list_update: use a temporary for current mc address
Use etherdevice.h functions for mac address testing
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There is a small race between when the tx queues are stopped
and when netif_carrier_off() is called in ixgbe_down.  If the
dev_watchdog() timer fires during this time it is possible for
a false tx timeout to occur.

This patch moves the netif_carrier_off() so that it is called before
the tx queues are stopped preventing the dev_watchdog timer from
detecting false tx timeouts.  The race is seen occosionally when
FCoE or DCB settings are being configured or changed.

Testing note, running ifconfig up/down will not reproduce this
issue because dev_open/dev_close call dev_deactivate() and then
dev_activate().
Signed-off-by: NJohn Fastabend <john.r.fastabend@intel.com>
Acked-by: NPeter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change corrects the fact that we were not reporting Gen2 link speeds
when we were in fact connected at Gen2 rates.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

writebacks can be held indefinitely by hardware if EITR=0, when
combined with TXDCTL.WTHRESH=8.  When EITR=0, WTHRESH should be
set back to zero.
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

82598/82599 can support EITR == 0, which allows for the
absolutely lowest latency setting in the hardware.  This disables
writeback batching and anything else that relies upon a delayed
interrupt. This patch enables the feature of "override" when a
user sets rx-usecs to zero, the driver will respect that setting
over using RSC, and automatically disable RSC.  If rx-usecs is
used to set the EITR value to 0, then the driver should disable
LRO (aka RSC) internally until EITR is set to non-zero again.
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There is no need to increment nr_frags because skb_fill_page_desc increments
it.
Signed-off-by: NKoki Sanagi <sanagi.koki@jp.fujitsu.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There is no need to increment nr_frags because skb_fill_page_desc increments
it.
Signed-off-by: NKoki Sanagi <sanagi.koki@jp.fujitsu.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

__sk_dst_set() might be called while no state can be integrated in a
rcu_dereference_check() condition.

So use rcu_dereference_raw() to shutup lockdep warnings (if
CONFIG_PROVE_RCU is set)
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Acked-by: NPaul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

const qualifier on sock argument is misleading, since we can modify rxhash.
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

RFC 1122 says the following:
...
  Keep-alive packets MUST only be sent when no data or
  acknowledgement packets have been received for the
  connection within an interval.
...

The acknowledgement packet is reseting the keepalive
timer but the data packet isn't. This patch fixes it by
checking the timestamp of the last received data packet
too when the keepalive timer expires.
Signed-off-by: NFlavio Leitner <fleitner@redhat.com>
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Acked-by: NIlpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

I prefer that the hlist be only accessed through the hlist macro
objects. Explicit twiddling of links (especially with RCU) exposes
the code to future bugs.

Compile tested only.
Signed-off-by: NStephen Hemminger <shemminger@vyatta.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use existing inline function.
Signed-off-by: NStephen Hemminger <shemminger@vyatta.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Conflicts:
	drivers/net/e100.c
	drivers/net/e1000e/netdev.c

Calls to twsk_net() are in some cases protected by reference counting
as an alternative to RCU protection.  Cases covered by reference counts
include __inet_twsk_kill(), inet_twsk_free(), inet_twdr_do_twkill_work(),
inet_twdr_twcal_tick(), and tcp_timewait_state_process().  RCU is used
by inet_twsk_purge().  Locking is used by established_get_first()
and established_get_next().  Finally, __inet_twsk_hashdance() is an
initialization case.

It appears to be non-trivial to locate the appropriate locks and
reference counts from within twsk_net(), so used rcu_dereference_raw().
Signed-off-by: NPaul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In some Power7 platforms, when using VIOS (Virtual I/O Server), we
need to wait longer for control packets to finish transfer during
initialization.
Without this change, initialization may fail prematurely.
Signed-off-by: NWen Xiong <wenxiong@us.ibm.com>
Signed-off-by: NAndre Detsch <adetsch@br.ibm.com>
Acked-by: NDivy Le Ray <divy@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Prompted by a previous patch submitted by Matthew Garret <mjg@redhat.com>,
further digging into errata documentation reveals the current enabling or
disabling of ASPM L0s and L1 states for certain parts supported by this
driver are incorrect.  82571 and 82572 should always disable L1.  For
standard frames, 82573/82574/82583 can enable L1 but L0s must be disabled,
and for jumbo frames 82573/82574 must disable L1.  This allows for some
parts to enable L1 in certain configurations leading to better power
savings.

Also according to the same errata, Early Receive (ERT) should be disabled
on 82573 when using jumbo frames.

Cc: Matthew Garret <mjg@redhat.com>
Signed-off-by: NBruce Allan <bruce.w.allan@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The PHY laser is still on during driver init.  It's allowing
garbage to hit our FIFO, which eventually can cause the entire
device to die.  Power down the laser while setting up the device,
and re-enable the laser before getting link.
Signed-off-by: NPeter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>