In addition to the source/destination IP which are already hashed.
Only for unicast traffic for now.
Signed-off-by: NAchiad Shochat <achiad@mellanox.com>
Signed-off-by: NAmir Vadai <amirv@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

No logical change in this commit.
Signed-off-by: NAchiad Shochat <achiad@mellanox.com>
Signed-off-by: NAmir Vadai <amirv@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

A regular TX WQE execution involves two or more DMA reads -
one to fetch the WQE, and another one per WQE gather entry.

These DMA reads obviously increase the TX latency.
There are two mlx5 mechanisms to bypass these DMA reads:
1) Inline WQE
2) Blue Flame (BF)

An inline WQE contains a whole packet, thus saves the DMA read/s
of the regular WQE gather entry/s. Inline WQE support was already
added in the previous commit.

A BF WQE is written directly to the device I/O mapped memory, thus
enables saving the DMA read that fetches the WQE.

The BF WQE I/O write must be in cache line granularity, thus uses
the CPU write combining mechanism.
A BF WQE I/O write acts also as a TX doorbell for notifying the
device of new TX WQEs.
A BF WQE is written to the same I/O mapped address as the regular TX
doorbell, thus this address is being mapped twice - once by ioremap()
and once by io_mapping_map_wc().

While both mechanisms reduce the TX latency, they both consume more CPU
cycles than a regular WQE:
- A BF WQE must still be written to host memory, in addition to being
  written directly to the device I/O mapped memory.
- An inline WQE involves copying the SKB data into it.

To handle this tradeoff, we introduce here a heuristic algorithm that
strives to avoid using these two mechanisms in case the TX queue is
being back-pressured by the device, and limit their usage rate otherwise.

An inline WQE will always be "Blue Flamed" (written directly to the
device I/O mapped memory) while a BF WQE may not be inlined (may contain
gather entries).

Preliminary testing using netperf UDP_RR shows that the latency goes down
from 17.5us to 16.9us, while the message rate (tested with pktgen) stays
the same.
Signed-off-by: NAchiad Shochat <achiad@mellanox.com>
Signed-off-by: NAmir Vadai <amirv@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

AKA inline WQE.
A TX latency optimization to save data gather DMA reads.
Controlled by ETHTOOL_TX_COPYBREAK.
Signed-off-by: NAchiad Shochat <achiad@mellanox.com>
Signed-off-by: NAmir Vadai <amirv@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

By affinity hints and XPS, each mlx5e channel is assigned a CPU
core.

Channel DMA coherent memory that is written by the NIC and read
by SW (e.g CQ buffer) is allocated on the NUMA node of the CPU
core assigned for the channel.

Channel DMA coherent memory that is written by SW and read by the
NIC (e.g SQ/RQ buffer) is allocated on the NUMA node of the NIC.

Doorbell record (written by SW and read by the NIC) is an
exception since it is accessed by SW more frequently.
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NAmir Vadai <amirv@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The ConnectX-4 HW implements inverted XOR8.
To make it act as XOR we re-order the HW RSS indirection table.

Set XOR to be the default RSS hash function and add ethtool API to
control it.
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NAmir Vadai <amirv@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

WingMan Kwok says:

====================
net: netcp: Bug fixes of CPSW statistics collection

This patch set contains bug fixes and enhencements of hw ethernet
statistics processing on TI's Keystone2 CPSW ethernet switches.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds the missing statistics for the host
and slave ports of the CPSW on K2L and K2E platforms.
Signed-off-by: NWingMan Kwok <w-kwok2@ti.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In certain applications it's beneficial to allow the CPSW h/w
stats counters to continue to increment even while the kernel
polls them. This patch implements this behavior for both 1G
and 10G ethernet subsystem modules.
Signed-off-by: NWingMan Kwok <w-kwok2@ti.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Different Keystone2 platforms have different number and
layouts of hw statistics modules.  This patch consolidates
the statistics processing of different Keystone2 platforms
for easy maintenance.
Signed-off-by: NWingMan Kwok <w-kwok2@ti.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The CPSW driver keeps internally some, but not all, of
the statistics available in the hw statistics modules.  Furthermore,
some of the locations in the hw statistics modules are reserved and
contain no useful information.  Prior to this patch, the driver
allocates memory of the size of the the whole hw statistics modules,
instead of the size of statistics-entries-interested-in (i.e. et_stats),
for internal storage.  This patch fixes that.
Signed-off-by: NWingMan Kwok <w-kwok2@ti.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch fixes error in the setting of the hw statistics
module base for K2HK platform.  In K2HK although there are
4 hw statistics modules, but only 2 are visible at a time.
Thus when setting up the pointers to the base of the
corresponding hw statistics modules, modules 0 and 2 should
point to one base, while modules 1 and 3 should point to the
other.
Signed-off-by: NWingMan Kwok <w-kwok2@ti.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch fixes a bug in which the timer routine synchronized
against the ethtool-triggered statistics updates with spin_lock_bh().
A timer function is itself a bottom-half, so this should be
spin_lock().
Signed-off-by: NWingMan Kwok <w-kwok2@ti.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

VF driver was reading incorrect freelist congestion notification threshold
for FLM queues when packing is enabled for T5 and T6 adapter. Fixing it
now.
Signed-off-by: NHariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Note also that include/linux/lwtunnel.h is not needed.

CC: Thomas Graf <tgraf@suug.ch>
CC: Roopa Prabhu <roopa@cumulusnetworks.com>
Fixes: 499a2425 ("lwtunnel: infrastructure for handling light weight tunnels like mpls")
Signed-off-by: NNicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: NRoopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Send notifications on router port add and del/expire, re-use the already
existing MDBA_ROUTER and send NEWMDB/DELMDB netlink notifications
respectively.
Signed-off-by: NSatish Ashok <sashok@cumulusnetworks.com>
Signed-off-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Retrieve the tunnel metadata for packets received by a net_device and
provide it to ovs_vport_receive() for flow key extraction.

[This hunk was in the GRE patch in the initial series and missed the
 cut for the initial submission for merging.]

Fixes: 614732ea ("openvswitch: Use regular VXLAN net_device device")
Signed-off-by: NThomas Graf <tgraf@suug.ch>
Acked-by: NPravin B Shelar <pshelar@nicira.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

JUMBO and NO_GIGABIT_HALF have the same capability masks.
Change one of them.
Signed-off-by: NHarini Katakam <harinik@xilinx.com>
Acked-by: NNicolas Ferre <nicolas.ferre@atmel.com>
Acked-by: NAlexandre Belloni <alexandre.belloni@free-electrons.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

With CONFIG_VXLAN=m and CONFIG_OPENVSWITCH=y, there was the following
compilation error:
  LD      init/built-in.o
  net/built-in.o: In function `vxlan_tnl_create':
  .../net/openvswitch/vport-netdev.c:322: undefined reference to `vxlan_dev_create'
  make: *** [vmlinux] Error 1

CC: Thomas Graf <tgraf@suug.ch>
Fixes: 614732ea ("openvswitch: Use regular VXLAN net_device device")
Signed-off-by: NNicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: NThomas Graf <tgraf@suug.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently, we do not notice if new alternative gateways
are added. We can do it by checking for present neigh
entry. Also, gateways that are currently probed (NUD_INCOMPLETE)
can be skipped from round-robin probing.
Suggested-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NJulian Anastasov <ja@ssi.bg>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Similar check was added in ip_rcv but not in ipv6_rcv.

BUG: unable to handle kernel NULL pointer dereference at (null)
IP: [<ffffffff81734e0a>] ipv6_rcv+0xfa/0x500
Call Trace:
[<ffffffff816c9786>] ? ip_rcv+0x296/0x400
[<ffffffff817732d2>] ? packet_rcv+0x52/0x410
[<ffffffff8168e99f>] __netif_receive_skb_core+0x63f/0x9a0
[<ffffffffc02b34a0>] ? br_handle_frame_finish+0x580/0x580 [bridge]
[<ffffffff8109912c>] ? update_rq_clock.part.81+0x1c/0x40
[<ffffffff8168ed18>] __netif_receive_skb+0x18/0x60
[<ffffffff8168fa1f>] process_backlog+0x9f/0x150

Fixes: ee122c79 (vxlan: Flow based tunneling)
Signed-off-by: NWei-Chun Chao <weichunc@plumgrid.com>
Acked-by: NThomas Graf <tgraf@suug.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit 8d88c6eb ("net: bcmgenet: enable MoCA link state change
detection") added a fixed PHY link_update callback for MoCA PHYs when
registered using platform_data exclusively, this change is also
applicable to systems using Device Tree as their primary configuration
interface.

In order for this to work, move the link_update assignment into
bcmgenet_moca_phy_setup() where we know for sure that we are running on
a MoCA GENET instance, and do not override phydev->link since this is:

- properly taken care of by the PHY library by getting the link UP/DOWN
  interrupts
- this now runs everytime we call bcmgenet_open(), so we need to
  preserve whatever we detected before we went administratively DOWN and
  then UP
- we need to make sure that MoCA PHYs start with a link DOWN during
  probe in order to force a link transition to occur

To avoid a forward declaration, move bcmgenet_fixed_phy_link_update()
above its caller.
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Instead of multiplying the number of checks for IS_ERR(priv->clk),
simply NULLify the 'struct clk' pointer which is something the Linux
common clock framework perfectly deals with and does early return for
each and every single clk_* API functions.

Having every single function check for !IS_ERR(priv->clk) is both
redundant and error prone, as it turns out, we were doing it for the
main GENET clock: priv->clk, but not for the Wake-on-LAN or EEE clock,
so let's just be consistent here.
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Acked-by: NPetri Gynther <pgynther@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The current code returns from probe without waiting for the proper handling
of subchannels that may be requested. If the netvsc driver were to be rapidly
loaded/unloaded, we can  trigger a panic as the unload will be tearing
down state that may not have been fully setup yet. We fix this issue by making
sure that we return from the probe call only after ensuring that the
sub-channel offers in flight are properly handled.

Reviewed-and-tested-by: Haiyang Zhang <haiyangz@microsoft.com
Signed-off-by: NK. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Adapter can go for a toss, if cxgb4 is loaded as slave and we try to
upgrade the firmware. So add a check for the same before flashing
firmware using ethtool.
Signed-off-by: NHariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Silences the following sparse warnings:
drivers/net/vxlan.c:1818:21: warning: incorrect type in assignment (different base types)
drivers/net/vxlan.c:1818:21:    expected restricted __be32 [usertype] vx_vni
drivers/net/vxlan.c:1818:21:    got unsigned int [unsigned] [usertype] vni
drivers/net/vxlan.c:2014:58: warning: incorrect type in argument 11 (different base types)
drivers/net/vxlan.c:2014:58:    expected unsigned int [unsigned] [usertype] vni
drivers/net/vxlan.c:2014:58:    got restricted __be32 [usertype] <noident>

Fixes: 614732ea ("openvswitch: Use regular VXLAN net_device device")
Reported-by: Nkbuild test robot <fengguang.wu@intel.com>
Signed-off-by: NThomas Graf <tgraf@suug.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Jon Maloy says:

====================
tipc: clean up socket message reception

Despite recent improvements the message reception code in socket.c is
perceived as obscure and hard to follow, especially regarding the logics
for message rejection. With the commits in this series we try to remedy
this situation.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When a message is received in a socket, one of the call chains
tipc_sk_rcv()->tipc_sk_enqueue()->filter_rcv()(->tipc_sk_proto_rcv())
or
tipc_sk_backlog_rcv()->filter_rcv()(->tipc_sk_proto_rcv())
are followed. At each of these levels we may encounter situations
where the message may need to be rejected, or a new message
produced for transfer back to the sender. Despite recent
improvements, the current code for doing this is perceived
as awkward and hard to follow.

Leveraging the two previous commits in this series, we now
introduce a more uniform handling of such situations. We
let each of the functions in the chain itself produce/reverse
the message to be returned to the sender, but also perform the
actual forwarding. This simplifies the necessary logics within
each function.
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently, we use the code sequence

if (msg_reverse())
   tipc_link_xmit_skb()

at numerous locations in socket.c. The preparation of arguments
for these calls, as well as the sequence itself, makes the code
unecessarily complex.

In this commit, we introduce a new function, tipc_sk_respond(),
that performs this call combination. We also replace some, but not
yet all, of these explicit call sequences with calls to the new
function. Notably, we let the function tipc_sk_proto_rcv() use
the new function to directly send out PROBE_REPLY messages,
instead of deferring this to the calling tipc_sk_rcv() function,
as we do now.
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The shortest TIPC message header, for cluster local CONNECTED messages,
is 24 bytes long. With this format, the fields "dest_node" and
"orig_node" are optimized away, since they in reality are redundant
in this particular case.

However, the absence of these fields leads to code inconsistencies
that are difficult to handle in some cases, especially when we need
to reverse or reject messages at the socket layer.

In this commit, we concentrate the handling of the absent fields
to one place, by letting the function tipc_msg_reverse() reallocate
the buffer and expand the header to 32 bytes when necessary. This
means that the socket code now can assume that the two previously
absent fields are present in the header when a message needs to be
rejected. This opens up for some further simplifications of the
socket code.
Reviewed-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NJon Maloy <jon.maloy@ericsson.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Jeff Kirsher says:

====================
Intel Wired LAN Driver Updates 2015-07-23

This series contains updates to e1000e, igb, ixgbevf, i40e and i40evf.

Emil extends the reporting of the RSS key and hash table by adding support
for x550 VFs.

Jia-Ju Bai fixes a QoS issue in e1000e where the error handling lacked a
call to pm_qos_remove_request() to cleanup the QoS request made in
e1000_open().

Todd updates igb to report unsupported for ethtool coalesce settings
that are not supported.  Also updated the driver to use the ARRAY_SIZE()
macro.

Carolyn fixes and refactors the dynamic ITR code for i40e and i40evf
which would never change dynamically.  So update the switch() statement
to have a default case and switch on "new_latency_range" versus the
current ITR setting.

Shannon cleans up i40e code, where there were un-needed goto's.  Also
clean up error status messages that were causing some confusion in
PHY and FCoE setup error reports.

Mitch updates the virtual channel interface to prepare for the x722 device
and other future devices, so that the VF driver can report what its
capable of supporting to the PF driver.  Updates the i40evf driver to
handle resets like Core or EMP resets, where the device is reinitialized
and the VF will not get the same VSI.

Jesse updates the i40e and i40evf driver to use the kernel BIT() and
BIT_ULL() macros.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch fixes setting of vinfo.flags in the br_fill_ifvlaninfo_range() method. The
assignment of vinfo.flags &= ~BRIDGE_VLAN_INFO_RANGE_BEGIN has no effect and is
unneeded, as vinfo.flags value is overriden by the  immediately following
vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_END assignement.
Signed-off-by: NRami Rosen <rami.rosen@intel.com>
Acked-by: NRoopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add be_get_phys_port_id() function to report physical port id. The port id
should be unique across different be2net devices in the system. We use the
chip serial number along with the physical port number for this.
Signed-off-by: NSriharsha Basavapatna <sriharsha.basavapatna@avagotech.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use macros for abstracting (1 << foo) to BIT(foo)
and (1ULL << foo64) to BIT_ULL(foo64) in order to match
better with kernel requirements.

NOTE: the adminq_cmd.h file was not modified on purpose because
of the dependency upon firmware for that file.

Change-ID: I73ee2e48c880d671948aad19bd53ca6b2ac558fc
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NCatherine Sullivan <catherine.sullivan@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Clean up a little confusion in reporting error status in phy and fcoe
setup error reports by separating the return status from the AQ error.

Add two decoder functions to make this easier.

Change-ID: I960bcdeef3978a15fec1cdb5eff781d5cbae42fb
Signed-off-by: NShannon Nelson <shannon.nelson@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This driver fully supports VF drivers using both the 1.0 and 1.1
versions of the virtual channel API. However, VF drivers using
version 1.0 get upset if we provide them with a version other than
that, and refuse to play with us.

Correct this by checking the VFs API version at the time that we
store it off, and provide the correct version number back to the VF
so we can all get along.

Change-ID: I86dfe02e67b2bef336b4b49a1bb072f3e7229abc
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Store off the PF's API version, then use it to determine whether or not
to send it our capabilities. Change the version checking to allow for PF
drivers with lower API versions than our current version, so we can
still talk to PF drivers over the 1.0 API.

Change-ID: I8edc55d1229c7decf0ed3f285a63032694007c2e
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Tested-by: NJim young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The most common type of reset that the VF will encounter is a PF reset
that cascades down into a VF reset for each VF. In this case, the VF
will always be assigned the same VSI and recovery is fairly simple.

However, in the case of 'bigger' resets, such as a Core or EMP reset,
when the device is reinitialized, it's probable that the VF will NOT get
the same VSI. When this happens, the VF will not be able to recover, as
it will continue to request resources for its original VSI.

Add an extra state to the admin queue state machine so that the driver
can re-request its configuration information at runtime. During reset
recovery, set this bit in the aq_required field, and fetch the (possibly
new) configuration information before attempting to bring the driver
back up. Since the driver doesn't know what kind of reset it has
encountered, this step is done even for a PF reset, but it doesn't hurt
anything - it just gets the same VSI back.

Change-ID: I915d59ffb40375215117362f4ac7a37811aba748
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Store off the VF API version for use when figuring out the VF driver
capabilities. Add support for the VF driver handing its capabilities to
the PF driver and then use this information when sending VF resource
information back to the VF driver.

Change-ID: Ic00d0eeeb5b8118085e12f068ef857089a8f7c2d
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Now that we've rolled the virtual channel API version to 1.1, add some
macros to test what version is being used by our partner in crime. For the
VF, add some macros to determine what our device capabilities are.

Change-ID: I79f6683d4c23bd76a8ad9fd492776fcc1208e1dc
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>