skb truesize currently accounts for sk_buff struct and part of skb head.
kmalloc() roundings are also ignored.

Considering that skb_shared_info is larger than sk_buff, its time to
take it into account for better memory accounting.

This patch introduces SKB_TRUESIZE(X) macro to centralize various
assumptions into a single place.

At skb alloc phase, we put skb_shared_info struct at the exact end of
skb head, to allow a better use of memory (lowering number of
reallocations), since kmalloc() gives us power-of-two memory blocks.

Unless SLUB/SLUB debug is active, both skb->head and skb_shared_info are
aligned to cache lines, as before.

Note: This patch might trigger performance regressions because of
misconfigured protocol stacks, hitting per socket or global memory
limits that were previously not reached. But its a necessary step for a
more accurate memory accounting.
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
CC: Andi Kleen <ak@linux.intel.com>
CC: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This change updates the driver version to 3.2.10.
Signed-off-by: NCarolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch adds VMDq loopback pf support for i350 devices. The patch
is necessary since the register that enabled loopback was moved and
renamed from DTXSWC to TXSWC.
Signed-off-by: N"Akeem G. Abodunrin" <akeem.g.abodunrin@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

igb_update/validate_nvm_checksum_with_offset() should be static.
Also removes unneeded prototypes for the above functions.
Signed-off-by: NEmil Tantilov <emil.s.tantilov@intel.com>
Tested-by: NAaron Brown  <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

On i350 when traffic is looped back from a VF to the PF the value is byte
swapped from the normal format.  In order to address this we need to add a
flag indicating that the ring will need to byte swap the loopback packets
prior to processing them.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAaron Brown  <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Since we mask interrupts in EIMS not in IMS there is no need to re-enable
mask bits in that register.  As such we can remove the write to IMS from
the end of igb_msix_other.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAaron Brown  <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This change allows support for per packet timesync and global device reset
on the i350 adapter.  These features were supported on both 82580 and i350
however it looks like several checks where not updated and as such the i350
support was not enabled.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAaron Brown  <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This change makes certain that one interrupt is always initialized in
igb_request_irq.  In addition we drop the use of adapter->pdev and
instead just call pdev since we made a local copy of the pointer earlier in
the function.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAaron Brown  <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This is mostly a drop of unnecessary pointer defines for q_vector when we
don't have issues with line width and don't have multiple references to
the pointer.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAaron Brown  <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Correct a check for change in FCoE priority when IEEE mode DCB is in use.
In IEEE mode a different function has to be used to get the FCoE priority
mask. Also, the check for the mask assumed that only one priority was set.
In case there should be more than one, check just the bit.

These changes help avoid link flapping issues that can come up when IEEE
DCB is in use.
Signed-off-by: NMark Rustad <mark.d.rustad@intel.com>
Tested-by: NRoss Brattain <ross.b.brattain@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Add 2 new counters to ethtool:
	1. Count DDP allocation failure since we max the number of buffers
		allowed in one DDP context.
	2. Count DDP allocation failure since we max the number of buffers
		allowed in one DDP context when we alloc an extra buffer.
Signed-off-by: NAmir Hanania <amir.hanania@intel.com>
Tested-by: NRoss Brattain <ross.b.brattain@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

It is possible for a VF to set an invalid target DMA address in its
Tx/Rx descriptor buffer pointers.  The workarounds in this patch
will guard against such an event and issue a VFLR to the VF in response.
The VFLR will shut down the VF until an administrator can take action
to investigate the event and correct the problem.
Signed-off-by: NGreg Rose <gregory.v.rose@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch exposes the tos value for the TCP sockets when the TOS flag
is requested in the ext_flags for the inet_diag request. This would mainly be
used to expose TOS values for both for TCP and UDP sockets. Currently it is
supported for TCP. When netlink support for UDP would be added the support
to expose the TOS values would alse be done. For IPV4 tos value is exposed
and for IPV6 tclass value is exposed.
Signed-off-by: NMurali Raja <muralira@google.com>
Acked-by: NStephen Hemminger <shemminger@vyatta.com>
Acked-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We dereference doi_def on the line before the NULL check.  It has
been this way since 2008.  I checked all the callers and doi_def is
always non-NULL here.
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Conflicts:
	Documentation/feature-removal-schedule.txt

  CC [M]  drivers/net/wireless/ath/ath6kl/cfg80211.o
drivers/net/wireless/ath/ath6kl/cfg80211.c:1838:2: warning: initialization from incompatible pointer type

Caused by commit e9f935e3...
Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>

Signed-off-by: NIan Campbell <ian.campbell@citrix.com>
Cc: netdev@vger.kernel.org
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NIan Campbell <ian.campbell@citrix.com>
Cc: netdev@vger.kernel.org
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NIan Campbell <ian.campbell@citrix.com>
Cc: Breno Leitao <leitao@linux.vnet.ibm.com>
Cc: netdev@vger.kernel.org
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If skb is NULL, then stack trace is thrown anyway on dereference.
Therefore, the stack trace triggered by BUG_ON is duplicate.
Signed-off-by: NDaniel Borkmann <danborkmann@googlemail.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NFlorian Fainelli <florian@openwrt.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Joe reported to me that right after a bring up of a r6040 interface
the ethtool output had no consistent output with respect to link duplex
and speed. Fix this by adding a missing phy_start call in r6040_up and
conversely a phy_stop call in r6040_down to properly initialize phy states.
Reported-by: NJoe Chou <Joe.Chou@rdc.com.tw>
Signed-off-by: NFlorian Fainelli <florian@openwrt.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Query port will now identify a 40G Ethernet speed.
Signed-off-by: NAlexander Guller <alexg@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Netdevice was being freed without being unregistered first if
mlx4_SET_PORT_general or mlx4_INIT_PORT failed.
Signed-off-by: NAlexander Guller <alexg@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Number of bits taken from mac table index in QP
calculation should be based on log_num_mac parameter.
Signed-off-by: NAlexander Guller <alexg@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fixed a memory leak caused by missing iounmap when device
is being released.
Signed-off-by: NAlexander Guller <alexg@mellanox.co.il>
Signed-off-by: NSharon Cohen <sharonc@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Moderation is now done per ring and coalescing is enabled
by set_ring_param in ethtool.
Signed-off-by: NAlexander Guller <alexg@mellanox.co.il>
Signed-off-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fixed a bug where ring size change caused insufficient memory
upon driver restart due to unreleased EQs.
Signed-off-by: NAlexander Guller <alexg@mellanox.co.il>
Signed-off-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Until now only RX rings used irq per ring
and TX used only one per port.
>From now on, both of them will use the
irq per ring while RX & TX ring[i] will
use the same irq.
Signed-off-by: NAlexander Guller <alexg@mellanox.co.il>
Signed-off-by: NSharon Cohen <sharonc@mellanox.co.il>
Signed-off-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds support for Rx hashing.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAaron Brown  <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This change moves the Tx hang check into the ring flags.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAaron Brown  <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch cleans up several issues with VLANs on igb after the recent
changes that were meant to leave the VLANs enabled/disable via the
netdev->features flags.

Specifically the Rx VLAN settings were being dropped after reset due to the
fact that they were not being restored correctly.  In addition I removed
the IRQ disable/enable since those were in place to protect the setting of
vlgrp.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAaron Brown  <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Instead of doing a byte swap on the staterr bits in the Rx descriptor we can
save ourselves a bit of space and some CPU time by instead just testing for
the various bits out of the Rx descriptor directly.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAaron Brown  <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Since the netdev now has its' own checksum flag to indicate if Rx checksum
is enabled we might as well use that instead of using the ring flag.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAaron Brown  <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This change is meant to cleanup some of the IVAR register configuration.
igb_assign_vector had become pretty large with multiple copies of the same
general code for setting the IVAR. This change consolidates most of that
code by adding the igb_write_ivar function which allows us just to compute
the index and offset and then use that information to setup the IVAR.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAaron Brown  <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This change moves information related to interrupt throttle rate
configuration into a separate q_vector sub-structure called a work
container. A similar change has already been made for ixgbe and this work
is based off of that.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAaron Brown  <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This change moves all of the ring flags into a single value.  The advantage
to this is that there is one central area for all of these flags and they
can all make use of the set/test bit operations.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAaron Brown  <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>