Second round of drivers for Gb cards (and NIU one I forgot in the 10GB round)

Now that core network takes care of trans_start updates, dont do it
in drivers themselves, if possible. Drivers can avoid one cache miss
(on dev->trans_start) in their start_xmit() handler.

Exceptions are NETIF_F_LLTX drivers
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Based on previous patch from Jesper Dangaard Brouer.

The RNBC (Receive No Buffers Count) register for the 82576, indicate
that frames were received when there were no available buffers in host
memory to store those frames (receive descriptor head and tail
pointers were equal).  The packet is still received by the NIC if
there is space in the FIFO on the NIC.

As the RNBC value is not a packet drop, the driver stores this value
in net_stats.rx_fifo_errors to indicate that there were no system
buffers available for the incoming packet.  Actual dropped packets
are counted in the MPC value.

Saving the stats in dev->net_stats makes it visible via
/proc/net/dev as "fifo", and thus viewable to ifconfig
as "overruns" and 'netstat -i' as "RX-OVR".

The Receive No Buffers Count (RNBC) can already be queried by
ethtool -S as "rx_no_buffer_count".
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
CC: Jesper Dangaard Brouer <hawk@comx.dk>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Based on the previous patches from Jesper Dangaard Brouer <hawk@comx.dk>

Implement reading the per queue drop stats register
RQDPC (Receive Queue Drop Packet Count).  It counts the number of
packets dropped by a queue due to lack of descriptors available.

Notice RQDPC (Receive Queue Drop Packet Count) stats only gets
incremented, if the DROP_EN bit it set (in the SRRCTL register
for that queue).  If DROP_EN bit is NOT set, then the some what
equivalent count is stored in RNBC (not per queue basis).

The RQDPC register is only 12 bit, thus the precision might
suffer due to overrun in-netween the watchdog polling interval.
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
CC: Jesper Dangaard Brouer <hawk@comx.dk>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The current driver is re-registering the DCA requester after every reset.
Instead of doing this we should only be updating the on board DCA registers
and not unregistering/re-registering our requester.
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>

after the recent changes to wired drivers to use only
netif_carrier_off the driver can have outstanding tx work to
complete that will never complete once link is down.  Since the
intel hardware will hold this tx work forever, the driver
notices a tx timeout condition internally and might try
to instigate printk and reset of the part with a
netif_stop_queue, which doesn't work because link is down.

Don't bother arming to tx hang detection when link is down.
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>

The setup_rctl call was making a call into the ring structure after it had
been freed.  This was causing a panic on shutdown.  This call wasn't
necessary since it is possible to get the needed index from
adapter->vfs_allocated_count.
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>

An issue was found in which rx checksum could not be enabled without
resetting the interface.  The issue was the hardware enable was not being
done via ethtool.  To resolve this issue and prevent conflicts with VF
configuration we will leave the feature always enabled in hardware, and
then in software we will choose to ignore the results via a sw flag.
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>

Originally from: Vlad Yasevich <vladislav.yasevich@hp.com>

This patch, both the driver portion and the sctp code was
modified by Jesse Brandeburg and is

Copyright(c) 2009 Intel Corporation.

Thanks go to Vlad for starting this work.

Intel 82576 chipset supports SCTP checksum offloading.  This
patch enables this functionality in the driver.  A new NETIF
feature is introduced for SCTP checksum offload.  If the driver
supports CRC32c checksum, it can set this feature flag.  The
hardware can offload both transmit and receive.
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NVlad Yasevich <vladislav.yasevich@hp.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Both of these drivers do a check to verify ip_summed is set to
CHECKSUM_UNNECESSARY prior to passing the packet to GRO.  GRO itself
already does such a check so it is redundant and can be removed as this
will likely cause out of order issues when receiving a packet that didn't
pass checksum validation.
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>

The igb driver was being incorrectly setup to only allow disabling receive
checksum if multiqueue was disabled.  This change corrects that so that
RXCSUM is configured regardless of queue configuration.
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>

The igb driver was switching between adapter->itr containing the EITR value
and the number of interrupts per second.  This resulted in high latencies
being seen after brining the interface down and then back up.  To resolve
the issue the itr value will now only contain the value that should be
programmed into EITR.
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>

It was pointed out that the Intel wired ethernet drivers do not need to
wake the tx queue since netif_carrier_on/off will take care of the qdisc
management in order to guarantee the correct handling of the transmit
routine enable state.
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>

As reported by Andrew Lutomirski <amluto@gmail.com>

All the intel wired ethernet drivers were calling netif_carrier_off
and netif_stop_queue (or variants) before calling register_netdevice

This is incorrect behavior as was pointed out by davem, and causes
ifconfig and friends to report a strange state before first link
after the driver was loaded, since without a netif_carrier_off, the stack
assumes carrier_on, but before register_netdev, netlink messages are not
sent out telling link state.

This apparently confused *some* versions of networkmanager.
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Reported-by: NAndrew Lutomirski <amluto@gmail.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The driver is currently dumping a message in the log about failing to
allocate vf data when max_vfs is equal to 0.  This change makes it so the
error message is only displayed if we set max_vfs to a non zero value.
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>

This patch removes the sysfs entry num_vfs which was added to support
enabling pci virtual functions for 82576.

To prevent VFs from loading automatically a module parameter "max_vfs" was
added so that the number of VFs per PF can be limited.  This is especially
useful when 4 or more 82576 ports are on the system because otherwise to
load all VFs would result in 8 interface per physical port.
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>

Replace all DMA_32BIT_MASK macro with DMA_BIT_MASK(32)

Signed-off-by: Yang Hongyang<yanghy@cn.fujitsu.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Replace all DMA_64BIT_MASK macro with DMA_BIT_MASK(64)

Signed-off-by: Yang Hongyang<yanghy@cn.fujitsu.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Impact: Fix

Yinghai Lu found one system with 82575EB where, in the kernel that is
kexeced, probe igb failed with -2, the reason being that the adapter
could not be brought back from D3 by the kexec kernel, most probably
due to quirky hardware (it looks like the same behavior happened on
forcedeth).

Prevent igb from putting the adapter into D3 during shutdown except
when we going to power off the system.  For this purpose, seperate
igb_shutdown() from igb_suspend() and use the appropriate PCI PM
callbacks in both of them.
Signed-off-by: N"Rafael J. Wysocki" <rjw@sisk.pl>
Reported-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

An issue was seen on suspend in which the system reported a page fault.  This
was due to the new reg_idx code being called after the queues were freed.

This update prevents any for loops from going through the queues by setting
the number of queues to 0 when they are freed.
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>

When device is on PCIe link trained as x2 the driver is currently reporting
link width as "unknown".  The original patch provided by Myron adds the x2
link support and my changes are cosmetic to clean up the readability of the
conditional operators.

Based on work by: Myron Stowe <myron.stowe@hp.com>
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>

The igb driver was using map_single to map the skbs and then unmap_page to
unmap them.  This update changes that so instead uses skb_dma_map and
skb_dma_unmap.

In addition the next_to_watch member of the buffer_info struct was being
set uneccesarily.  I removed the spots where it was set without being needed.
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>

Currently if there are no multicast addresses programmed into the PF then
the VFs cannot have their multicast filters reset.  This change makes it so
the code path that updates vf multicast is always called along with the pf
updates.
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>

igb was previously setting up all of the timer members itself.  It is
easier to just call setup_timer and reduce the calls to one line.
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>

This patch removes IGB_DESC_UNUSED and replaces it with a function call
instead in order to cleanup some of the ugliness introduced by the macro.
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>

When the 82575 is fed 802.1q packets, it chokes with
an error of the form:

igb 0000:08:00.1 partial checksum but proto=81!

As the logic there was not smart enough to look into
the vlan header to pick out the encapsulated protocol.

There are times when we'd like to send these packets
out without having to configure a vlan on the interface.
Here we check for the vlan tag and allow the packet to
go out with the correct hardware checksum.

Thanks to Kand Ly <kand@riverbed.com> for discovering the
issue and the coming up with a solution.  This patch is
based upon his work.
Signed-off-by: NArthur Jones <ajones@riverbed.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The L0s workaround should be moved into a pci quirk and so it is not
necessary in the driver.  This update removes the L0s workaround from the
igb driver.

This was the second half of the PCI quirk patch that Matthew Wilcox did
not pick up when he picked up the quirk patch.
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>

Add support for 82576 copper adapter and necessary code to restrict wol for
quad port adapter to first port.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Acked-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>

Adding device id to support 82576NS dual port copper
NIC.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Acked-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>

This patch corrects a typo that was doing a less than comparison instead of
a left shift due to the fact that I didn't get enough <'s in there.

This resolves an issue in which vlans were not functioning correctly.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Acked-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>

Add Pf to pool if adding a VLVF register value and the VFTA bit is
already set.

This patch addresses the unlikely situation that the PF adds a vlan
entry when the vlvf is full, and a vf later adds the vlan to the vlvf.
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>

We need to support wol on the second port for situations such as when the
lan ports are on the motherboard itself.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Acked-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>

If DCA is undefined then the adapter struct becomes unnecessary.  To
resolve this issue the DCA calls can simply make a call to the adapter
struct through the rx_ring adapter struct member.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Acked-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>

The netif_running check in igb poll is a hold over from the use of fake
netdevs to use multiple queues with NAPI prior to 2.6.24.  It is no longer
necessary to have the call there and it currently can cause errors if
work_done == budget.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Acked-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>

With the new DCA API, the driver should use dca3_get_tag() instead of
the obsolete dca_get_tag().

Signed-off-by: Maciej Sosnowski < maciej.sosnowski@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Remove skb_orphan call from igb driver as it can cause multiple issues due
to the fact that it is calling the desctructor and removing the skb from
the socket prior to transmission.

The call was added to improve performance but did so by allowing the skb to
be removed from the socket which gave the socket more window space to
transmit.  The performance gain is not worth the extra problems that this
kind of workaround can introduce as this could lead to a potential DoS if a
UDP stream decided to monopolize the transmit path.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Acked-by: NMitch Williams <mitch.a.williams@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This code adds a module parameter called num_vfs which defines if the
driver should attempt to use sr-iov and if so how many VFs should be
enabled.
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>

This patch adds the support to handle requests from the VF to perform
operations such as completing resets, setting/reading mac address, adding
vlans, adding multicast addresses, setting rlpml, and general
communications between the PF and all VFs.
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>

Add the pf portion of vmdq support.  This provides enough support so that
VMDq is enabled, and the pf is functional without enabling vfs.
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>

This is the first step in supporting sr-iov.  The vf_allocated_count value
will be 0 until we actually have vfs present.  In the meantime it
represents an offset value for the start of the queues.
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>

igb is currently not returning the correct values for napi.  In addition it
is doing more work than necessary since it will not exit polling until
work_done is equal to zero.

This patch makes the following changes:
1.  Consolidates msi-x and non-msi polling routines.
2.  Corrects return values for polling routines.
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>