A SRAM parity error can cause a surprise link down.  Since We can
recover from SRAM parity errors, mask PCI surprise down events.
Signed-off-by: NJon Mason <mason@myri.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Ensure that our tx queues remain stopped when we stop them in
myri10ge_close().  Not doing so can potentially lead to traffic being
transmitted when the interface is removed, which can lead to NULL
pointer dereferences.
Signed-off-by: NJon Mason <mason@myri.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch enables the 6131 family of chips to forward DSA
packets to other switch chips.  This is needed if multiple
DSA chips are used in a device.  Without this patch the
chip will drop any DSA packets not destined for it.

This patch only enables the forwarding of DSA packets if
multiple chips are used in the switch configuration.
Signed-off-by: NBarry Grussling <barry@grussling.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Just spelling fixes.

Actually, a twofer with vaiables/variables as well.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

fixes thses build errors:

drivers/net/ll_temac_main.c: In function 'temac_dma_bd_release':
drivers/net/ll_temac_main.c:209:4: error: implicit declaration of function 'dma_unmap_single'
drivers/net/ll_temac_main.c:215:3: error: implicit declaration of function 'dma_free_coherent'
drivers/net/ll_temac_main.c: In function 'temac_dma_bd_init':
drivers/net/ll_temac_main.c:243:2: error: implicit declaration of function 'dma_alloc_coherent'
drivers/net/ll_temac_main.c:243:14: warning: assignment makes pointer from integer without a cast
drivers/net/ll_temac_main.c:251:14: warning: assignment makes pointer from integer without a cast
drivers/net/ll_temac_main.c:280:3: error: implicit declaration of function 'dma_map_single'
drivers/net/ll_temac_main.c: In function 'temac_start_xmit_done':
drivers/net/ll_temac_main.c:628:22: warning: cast to pointer from integer of different size

Caused by commit commit b7f080cf ("net: remove mm.h inclusion from
netdevice.h").
Signed-off-by: NStephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

fixes these build errors:

drivers/net/can/sja1000/sja1000_of_platform.c: In function 'sja1000_ofp_read_reg':
drivers/net/can/sja1000/sja1000_of_platform.c:61:2: error: implicit declaration of function 'in_8'
drivers/net/can/sja1000/sja1000_of_platform.c: In function 'sja1000_ofp_write_reg':
drivers/net/can/sja1000/sja1000_of_platform.c:67:2: error: implicit declaration of function 'out_8'
drivers/net/can/sja1000/sja1000_of_platform.c: In function 'sja1000_ofp_remove':
drivers/net/can/sja1000/sja1000_of_platform.c:81:2: error: implicit declaration of function 'iounmap'
drivers/net/can/sja1000/sja1000_of_platform.c: In function 'sja1000_ofp_probe':
drivers/net/can/sja1000/sja1000_of_platform.c:113:2: error: implicit declaration of function 'ioremap_nocache'
drivers/net/can/sja1000/sja1000_of_platform.c:113:7: warning: assignment makes pointer from integer without a cast

Caused by commit b7f080cf ("net: remove mm.h inclusion from
netdevice.h").
Signed-off-by: NStephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When receiving packets from another guest on the same hypervisor, it's
generally possible to receive large packets because no segmentation is
necessary and these packets are handled by LRO.  However, when doing
routing or bridging we must disable LRO and lose this benefit.  In
these cases GRO can still be used and it is very effective because the
packets which are segmented in the hypervisor are received very close
together and can easily be merged.

CC: Shreyas Bhatewara <sbhatewara@vmware.com>
CC: Scott Goldman <scottjg@vmware.com>
CC: VMware PV-Drivers <pv-drivers@vmware.com>
Signed-off-by: NJesse Gross <jesse@nicira.com>
Signed-off-by: NScott J. Goldman <scottjg@vmware.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The PCIE capability offset is saved during PCI bus walking.  It will
remove an unnecessary search in the PCI configuration space if this
value is referenced instead of reacquiring it.
Signed-off-by: NJon Mason <jdmason@kudzu.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The PCIE capability offset is saved during PCI bus walking.  It will
remove an unnecessary search in the PCI configuration space if this
value is referenced instead of reacquiring it.  Also, pci_is_pcie is a
better way of determining if the device is PCIE or not (as it uses the
same saved PCIE capability offset).
Signed-off-by: NJon Mason <jdmason@kudzu.us>
Acked-by: NStephen Hemminger <shemminger@vyatta.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The PCIE capability offset is saved during PCI bus walking.  Use the
value from pci_dev instead of checking in the driver and saving it off
the the driver specific structure.  Also, it will remove an unnecessary
search in the PCI configuration space if this value is referenced
instead of reacquiring it.
Signed-off-by: NJon Mason <jdmason@kudzu.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The PCIE capability offset is saved during PCI bus walking.  It will
remove an unnecessary search in the PCI configuration space if this
value is referenced instead of reacquiring it.
Signed-off-by: NJon Mason <jdmason@kudzu.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The PCIE capability offset is saved during PCI bus walking.  It will
remove an unnecessary search in the PCI configuration space if this
value is referenced instead of reacquiring it.  Also, pci_is_pcie is a
better way of determining if the device is PCIE or not (as it uses the
same saved PCIE capability offset).
Signed-off-by: NJon Mason <jdmason@kudzu.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The PCIE capability offset is saved during PCI bus walking.  It will
remove an unnecessary search in the PCI configuration space if this
value is referenced instead of reacquiring it.  Also, pci_is_pcie is a
better way of determining if the device is PCIE or not (as it uses the
same saved PCIE capability offset).
Signed-off-by: NJon Mason <jdmason@kudzu.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The PCIE capability offset is saved during PCI bus walking.  It will
remove an unnecessary search in the PCI configuration space if this
value is referenced instead of reacquiring it.
Signed-off-by: NJon Mason <jdmason@kudzu.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The PCIE capability offset is saved during PCI bus walking.  It will
remove an unnecessary search in the PCI configuration space if this
value is referenced instead of reacquiring it.
Signed-off-by: NJon Mason <jdmason@kudzu.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The PCIE capability offset is saved during PCI bus walking.  It will
remove an unnecessary search in the PCI configuration space if this
value is referenced instead of reacquiring it.
Signed-off-by: NJon Mason <jdmason@kudzu.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The PCIE capability offset is saved during PCI bus walking.  It will
remove an unnecessary search in the PCI configuration space if this
value is referenced instead of reacquiring it.
Signed-off-by: NJon Mason <jdmason@kudzu.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The PCIE capability offset is saved during PCI bus walking.  Use the
value from pci_dev instead of checking in the driver and saving it off
the the driver specific structure.  It will remove an unnecessary search
in the PCI configuration space if this value is referenced instead of
reacquiring it.

v2 of the patch re-adds the PCI_EXPRESS flag and adds comments
describing why it is necessary.

[ pdev->pcie_cap --> pci_pcie_cap(pdev) -DaveM ]
Signed-off-by: NJon Mason <jdmason@kudzu.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch tidyup below warning

${LINUX}/drivers/net/sh_eth.c:1773: warning:
'mdp' may be used uninitialized in this function

Cc: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: NKuninori Morimoto <morimoto.kuninori@renesas.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This converts the vmxnet3 driver to use the new vlan model.  In doing so
it fixes missing tags in tcpdump and failure to do checksum offload when
tx vlan offload is disabled.

CC: Shreyas Bhatewara <sbhatewara@vmware.com>
CC: VMware PV-Drivers <pv-drivers@vmware.com>
Signed-off-by: NJesse Gross <jesse@nicira.com>
Signed-off-by: NScott J. Goldman <scottjg@vmware.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Since we have a struct that defines the sizes of the registers, we don't
need to explicitly use the 16bit read/write helpers.  Let the code figure
out which size access to make based on the size of the C type.

There should be no functional changes here.
Signed-off-by: NMike Frysinger <vapier@gentoo.org>
Acked-by: NWolfgang Grandegger <wg@grandegger.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If we look closely, the 4 writes to TRANSMIT_CHL.id1 can be collapsed
down into much simpler code.  So do just that.

This also fixes a build failure due to the I/O macros no longer
getting pulled in.  Their minor (and accidental) usage here gets
dropped as part of the unification.
Signed-off-by: NMike Frysinger <vapier@gentoo.org>
Acked-by: NWolfgang Grandegger <wg@grandegger.com>
Acked-by: NKurt Van Dijck <kurt.van.dijck@eia.be>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit 725c8999 (mlx4_en: Reporting HW revision
in ethtool -i) added code to read the revision ID from the PCI configuration
register while it's already stored by PCI subsystem in the 'revision' field of
'struct pci_dev'...

While at it, move the code being changed a bit in order to not break the
initialization sequence.
Signed-off-by: NSergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Results on dummy device can be seen in my netconf 2011
slides. These results are for a 10Gige IXGBE intel
nic - on another i5 machine, very similar specs to
the one used in the netconf2011 results.
It turns out - this is a hell lot worse than dummy
and so this patch is even more beneficial for 10G.

Test setup:
----------

System under test sending packets out.
Additional box connected directly dropping packets.
Installed prio qdisc on the eth device and default
netdev default length of 1000 used as is.
The 3 prio bands each were set to 100 (didnt factor in
the results).

5 packet runs were made and the middle 3 picked.

results
-------

The "cpu" column indicates the which cpu the sample
was taken on,
The "Pkt runx" carries the number of packets a cpu
dequeued when forced to be in the "dequeuer" role.
The "avg" for each run is the number of times each
cpu should be a "dequeuer" if the system was fair.

3.0-rc4      (plain)
cpu         Pkt run1        Pkt run2        Pkt run3
================================================
cpu0        21853354        21598183        22199900
cpu1          431058          473476          393159
cpu2          481975          477529          458466
cpu3        23261406        23412299        22894315
avg         11506948        11490372        11486460

3.0-rc4 with patch and default weight 64
cpu 	     Pkt run1        Pkt run2        Pkt run3
================================================
cpu0        13205312        13109359        13132333
cpu1        10189914        10159127        10122270
cpu2        10213871        10124367        10168722
cpu3        13165760        13164767        13096705
avg         11693714        11639405        11630008

As you can see the system is still not perfect but
is a lot better than what it was before...

At the moment we use the old backlog weight, weight_p
which is 64 packets. It seems to be reasonably fine
with that value.
The system could be made more fair if we reduce the
weight_p (as per my presentation), but we are going
to affect the shared backlog weight. Unless deemed
necessary, I think the default value is fine. If not
we could add yet another knob.
Signed-off-by: NJamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use pr_fmt, pr_<level> and netdev_<level> as appropriate.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use pr_fmt, pr_<level> and netdev_<level> as appropriate.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use pr_fmt, pr_<level> and netdev_<level> as appropriate.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use pr_fmt, pr_<level> and netdev_<level> as appropriate.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use pr_fmt, pr_<level> and netdev_<level> as appropriate.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use pr_fmt, pr_<level> and netdev_<level> as appropriate.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use pr_fmt, pr_<level> and netdev_<level> as appropriate.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use pr_fmt, pr_<level> and netdev_<level> as appropriate.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Initialization of this field to "all priorities" must be done before MCC queue
creation. As soon as the MCC queue is created, an event modifying this value
may be received.
Signed-off-by: NSathya Perla <sathya.perla@emulex.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NSathya Perla <sathya.perla@emulex.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Problem initially reproted and fixed by Eric Dumazet <eric.dumazet@gmail.com>

netdev_stats_update() resets netdev->stats and then accumulates stats from
various rings. This is wrong as stats readers can sometimes catch zero values.
Use temporary variables instead for accumulating per-ring values.
Signed-off-by: NSathya Perla <sathya.perla@emulex.com>
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Implement DCB ops dcb_ieee_del() and set FCoE to the default
priority when no priority exists.
Signed-off-by: NJohn Fastabend <john.r.fastabend@intel.com>
Tested-by: NRoss Brattain <ross.b.brattain@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The fcoe.tc field is no longer used so remove it. After
the field is removed there is no need to keep fcoe_setapp()
around so remove it as well. And finally we can get rid
of some DCB #ifdef's in the fcoe code.
Signed-off-by: NJohn Fastabend <john.r.fastabend@intel.com>
Tested-by: NRoss Brattain <ross.b.brattain@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Commit,

commit c8ca76eb
Author: John Fastabend <john.r.fastabend@intel.com>
Date:   Sat Mar 12 03:50:53 2011 +0000

    ixgbe: DCB, further cleanups to app configuration

Removed the getapp() routines from ixgbe because they are no
longer needed. It also allowed the set hardware routines to
use both IEEE 802.1Qaz app types and CEE app types. This
added code to do bit shifting in the IEEE case.

This patch reverts the checks and handles the IEEE case
from the setapp entry point. I prefer this because it
keeps the two paths from having to be aware of the DCB
mode. This resolves a bug where I missed setting the
selector bit in the IEEE spec value and left it in the
CEE value. Now that they are separate routines these types
of errors should not occur.
Signed-off-by: NJohn Fastabend <john.r.fastabend@intel.com>
Tested-by: NRoss Brattain <ross.b.brattain@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

There is a need to configure MMW_SIZE in register RTTBCNRM with a correct
value (0x4 for non jumbo frames and 0x14 for jumbo frames support).
For 82599 the value is 0x4 and for X540 the value is 0x14.
Signed-off-by: NLior Levy <lior.levy@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>