Rework the device ID #defines to follow the _DEV_ID convention
already established in the other Intel drivers.
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Kavindya Deegala <kavindya.s.deegala@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Allow compiling DCB related files if I40E_DCB option
is supported in the kernel configuration.

DCB is disabled by default.
Signed-off-by: Neerav Parikh <Neerav.Parikh@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Kavindya Deegala <kavindya.s.deegala@intel.com>
Tested-By: Jack Morgan<jack.morgan@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch adds capability to configure DCB on i40e network
interfaces using Intel XL710 adapter firmware APIs.

By default all VSIs are only enabled for the default traffic
class enabled by firmware for any given PF. The driver would
query the firmware for the traffic classes that are enabled for
the port and reconfigure the LAN VSI to match to the port traffic
class settings. All other VSIs are only enabled for the default
traffic class settings for now.

The driver registers and listens to firmware events that may
require change in the DCB settings. It may reconfigure the VSI
settings based on these events.

This patch exposes IEEE DCBNL interfaces for the i40e driver to
allow any application to query the DCB settings on the adapter.
Signed-off-by: Neerav Parikh <Neerav.Parikh@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-By: Jack Morgan<jack.morgan@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Intel XL710 series of adapters support QoS as per the
IEEE 802.1 DCB (Data Center Bridging) standard.
This is supported in conjuction with:
- Enhanced Transmission Selection (ETS) - IEEE 802.1Qaz
- Priority Flow Control (PFC) - IEEE 802.1Qbb
- DCB eXchange Protocol (DCBX) - IEEE 802.1Qaz

On Intel XL710 adapters DCBX is performed by the adapter
firmware. The firmware runs DCBX in willing mode and configures
the port as per the DCB settings recommended by it's link
partner.

By default in absence of any DCBX; firmware would configure the
port with a single traffic class and all of the port bandwith
will be allocated to that traffic class.

This patch adds functions and calls to support querying and
configuring DCB using firmware APIs.
Signed-off-by: Neerav Parikh <Neerav.Parikh@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-By: Jack Morgan<jack.morgan@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The i40e hardware was generating some inconsistent results
when using current programming methods.  This refactor
fixes the inconsistencies that were preventing clean
unloads of the driver, and moves the queues for handling
flow director errors into their own hardware VSI.

This patch also implements a corrected version of the
basic ethtool add ntuple rule, which will disable
the driver's automatic flow programming.  A future patch
adds remove/replay/list support for ntuple.
Signed-off-by: Anjali Singhai Jain <anjali.singhai@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Kavindya Deegala <kavindya.s.deegala@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The FLAG_FDIR_* defines can be renamed to be more descriptive.
This patch is in preparation for the following where the fdir
code is refactored.
Signed-off-by: Anjali Singhai Jain <anjali.singhai@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Kavindya Deegala <kavindya.s.deegala@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Fix more whitespace issues, including making some locals declared
in a nicer order.

Also update Copyright string printed when the driver loads.
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Kavindya Deegala <kavindya.s.deegala@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Remove a workaround that is no longer necessary and implement
a better understanding of what firmware is returning in the MSI-X
vector count.  This makes it so that the driver ends up with the
right amount of queues when using all available MSI-X vectors.

Change-ID: I34e60cc71dcfb1b5412f37df956fedcc49ade187
Signed-off-by: Catherine Sullivan <catherine.sullivan@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Kavindya Deegala <kavindya.s.deegala@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Compile testing with higher warning levels found this complaint:
i40e_nvm.c: warning: 'checksum_local' may be used uninitialized in
this function
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Kavindya Deegala <kavindya.s.deegala@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

It's now built as a separate utility module, and enabling BT selects
that module in Kconfig. This fixes:

net/ieee802154/built-in.o:(___ksymtab_gpl+lowpan_process_data+0x0): multiple definition of `__ksymtab_lowpan_process_data'
net/bluetooth/built-in.o:(___ksymtab_gpl+lowpan_process_data+0x0): first defined here
net/ieee802154/built-in.o:(___ksymtab_gpl+lowpan_header_compress+0x0): multiple definition of `__ksymtab_lowpan_header_compress'
net/bluetooth/built-in.o:(___ksymtab_gpl+lowpan_header_compress+0x0): first defined here
net/ieee802154/built-in.o: In function `lowpan_header_compress':
net/ieee802154/6lowpan_iphc.c:606: multiple definition of `lowpan_header_compress'
net/bluetooth/built-in.o:/home/swarren/shared/git_wa/kernel/kernel.git/net/bluetooth/../ieee802154/6lowpan_iphc.c:606: first defined here
net/ieee802154/built-in.o: In function `lowpan_process_data':
net/ieee802154/6lowpan_iphc.c:344: multiple definition of `lowpan_process_data'
net/bluetooth/built-in.o:/home/swarren/shared/git_wa/kernel/kernel.git/net/bluetooth/../ieee802154/6lowpan_iphc.c:344: first defined here
make[1]: *** [net/built-in.o] Error 1

(this change probably simply wasn't "git add"d to a53d34c3)

Fixes: a53d34c3 ("net: move 6lowpan compression code to separate module")
Fixes: 18722c24 ("Bluetooth: Enable 6LoWPAN support for BT LE devices")
Signed-off-by: Stephen Warren <swarren@nvidia.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Commit ab7db917 ("virtio-net: auto-tune mergeable rx buffer size for
improved performance") introduced a virtio-net dependency on EWMA.
The inclusion of EWMA is controlled by CONFIG_AVERAGE. Fix build error
when CONFIG_AVERAGE is not enabled by adding select AVERAGE to
virtio-net's Kconfig entry.

Build failure reported using config make ARCH=s390 defconfig.
Signed-off-by: Michael Dalton <mwdalton@google.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Aaron Brown says:

====================
Intel Wired LAN Driver Updates

This series contains an updates to ixgbe and ixgbevf.

Jacob add braces around some ixgbe_qv_lock_* calls lto better adhere
to Kernel style guidelines.  Don bumps the versions on ixgbe and
ixgbevf to match internal driver functionality better.
====================
Reviewed-by: Ding Tianhong <dingtianhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Bump the version number to better match functionality provided with out of
tree driver of the same version.
Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Bump the version number to better match functionality provided with out
of tree driver of the same version.
Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch adds braces around the ixgbe_qv_lock_* calls which previously only
had braces around the if portion. Kernel style guidelines for this require
parenthesis around all conditions if they are required around one. In addition
the comment while not illegal C syntax makes the code look wrong at a cursory
glance. This patch corrects the style and adds braces so that the full if-else
block is uniform.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

In order to get correct drop monitor notifications for dropped
packets, we should call kfree_skb() instead of dev_kfree_skb()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Scott Feldman says:

====================
bonding: add slave netlink and sysfs support

v2:

  - Address review comment from Ding (and Veacesiav): handle kobj cleanup
    if sysfs_create_file() fails when adding slave attribute nodes.

v1:

  The following series adds bonding slave netlink and sysfs interfaces.
  Slave interfaces get a new IFLA_SLAVE set of netlink attributes, along
  with RTM_NEWLINK notification when slave's active status changes.  The
  sysfs interface adds read-only nodes for slave attributes under a /slave
  dir, simliar to how bond interfaces get a /bonding dir for bonding
  attributes.
====================
Reviewed-by: Ding Tianhong <dingtianhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

If link is IFF_SLAVE, extend link dev netlink attributes to include
slave attributes with new IFLA_SLAVE nest.  Add netlink notification
(RTM_NEWLINK) when slave status changes from backup to active, or
visa-versa.

Adds new ndo_get_slave op to net_device_ops to fill skb with IFLA_SLAVE
attributes.  Currently only used by bonding driver, but could be
used by other aggregating devices with slaves.
Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Add sub-directory under /sys/class/net/<interface>/slave with
read-only attributes for slave.  Directory only appears when
<interface> is a slave.

$ tree /sys/class/net/eth2/slave/
/sys/class/net/eth2/slave/
├── ad_aggregator_id
├── link_failure_count
├── mii_status
├── perm_hwaddr
├── queue_id
└── state

$ cat /sys/class/net/eth2/slave/*
2
0
up
40:02:10:ef:06:01
0
active
Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Jesse Brandeburg reported that commit acaf4e70 caused a panic
when adding a network namespace while vxlan module was present in
the system:

[<ffffffff814d0865>] vxlan_lowerdev_event+0xf5/0x100
[<ffffffff816e9e5d>] notifier_call_chain+0x4d/0x70
[<ffffffff810912be>] __raw_notifier_call_chain+0xe/0x10
[<ffffffff810912d6>] raw_notifier_call_chain+0x16/0x20
[<ffffffff815d9610>] call_netdevice_notifiers_info+0x40/0x70
[<ffffffff815d9656>] call_netdevice_notifiers+0x16/0x20
[<ffffffff815e1bce>] register_netdevice+0x1be/0x3a0
[<ffffffff815e1dce>] register_netdev+0x1e/0x30
[<ffffffff814cb94a>] loopback_net_init+0x4a/0xb0
[<ffffffffa016ed6e>] ? lockd_init_net+0x6e/0xb0 [lockd]
[<ffffffff815d6bac>] ops_init+0x4c/0x150
[<ffffffff815d6d23>] setup_net+0x73/0x110
[<ffffffff815d725b>] copy_net_ns+0x7b/0x100
[<ffffffff81090e11>] create_new_namespaces+0x101/0x1b0
[<ffffffff81090f45>] copy_namespaces+0x85/0xb0
[<ffffffff810693d5>] copy_process.part.26+0x935/0x1500
[<ffffffff811d5186>] ? mntput+0x26/0x40
[<ffffffff8106a15c>] do_fork+0xbc/0x2e0
[<ffffffff811b7f2e>] ? ____fput+0xe/0x10
[<ffffffff81089c5c>] ? task_work_run+0xac/0xe0
[<ffffffff8106a406>] SyS_clone+0x16/0x20
[<ffffffff816ee689>] stub_clone+0x69/0x90
[<ffffffff816ee329>] ? system_call_fastpath+0x16/0x1b

Apparently loopback device is being registered first and thus we
receive an event notification when vxlan_net is not ready. Hence,
when we call net_generic() and request vxlan_net_id, we seem to
access garbage at that point in time. In setup_net() where we set
up a newly allocated network namespace, we traverse the list of
pernet ops ...

list_for_each_entry(ops, &pernet_list, list) {
	error = ops_init(ops, net);
	if (error < 0)
		goto out_undo;
}

... and loopback_net_init() is invoked first here, so in the middle
of setup_net() we get this notification in vxlan. As currently we
only care about devices that unregister, move access through
net_generic() there. Fix is based on Cong Wang's proposal, but
only changes what is needed here. It sucks a bit as we only work
around the actual cure: right now it seems the only way to check if
a netns actually finished traversing all init ops would be to check
if it's part of net_namespace_list. But that I find quite expensive
each time we go through a notifier callback. Anyway, did a couple
of tests and it seems good for now.

Fixes: acaf4e70 ("net: vxlan: when lower dev unregisters remove vxlan dev as well")
Reported-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Tested-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Aaron Brown says:

====================
Intel Wired LAN Driver Updates

This series contains updates to ixgbe Ethan Zhao.  The first one replaces
the magic number "63" with a macro, IXGBE_MAX_VFS_DRV_LIMIT, the second
moves the call to set driver_max_VFS to before SRIOV is enabled.

The code of these patches match the v3 (1/2) and v2 (2/2) versions sent
to the e1000-devel and netdev mailing lists.  The intermediate versions
(v4, v5) are from sorting out style issues, mostly tabs to spaces and
split lines probably introduced via mailer.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

commit 43dc4e01 Limit number of reported VFs to device
 specific value It doesn't work and always returns -EBUSY because VFs are
 already enabled.

ixgbe_enable_sriov()
        pci_enable_sriov()
                sriov_enable()
                {
                ... ..
                iov->ctrl |= PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE;
                pci_cfg_access_lock(dev);
                ... ...
                }

pci_sriov_set_totalvfs()
{
... ...
if (dev->sriov->ctrl & PCI_SRIOV_CTRL_VFE)
                return -EBUSY;
...
}

So should set driver_max_VFs with pci_sriov_set_totalvfs() before
enable VFs with ixgbe_enable_sriov().

V2: revised for net-next tree.
Signed-off-by: Ethan Zhao <ethan.kernel@gmail.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Because ixgbe driver limit the max number of VF
 functions could be enabled to 63, so define one macro IXGBE_MAX_VFS_DRV_LIMIT
 and cleanup the const 63 in code.

v3: revised for net-next tree.
Signed-off-by: Ethan Zhao <ethan.kernel@gmail.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch :

1) Remove a dst leak if DST_NOCACHE was set on dst
   Fix this by holding a reference only if dst really cached.

2) Remove a lockdep warning in __tunnel_dst_set()
    This was reported by Cong Wang.

3) Remove usage of a spinlock where xchg() is enough

4) Remove some spurious inline keywords.
   Let compiler decide for us.

Fixes: 7d442fab ("ipv4: Cache dst in tunnels")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Cong Wang <cwang@twopensource.com>
Cc: Tom Herbert <therbert@google.com>
Cc: Maciej Żenczykowski <maze@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The r7s72100 SoC includes a fast ethernet controller.
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
Acked-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Return a boolean from sh_eth_is_gether() and refactor it as a one-liner.
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
Acked-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The RFC 3810 defines two type of messages for multicast
listeners. The "Current State Report" message, as the name
implies, refreshes the *current* state to the querier.
Since the querier sends Query messages periodically, there
is no need to retransmit the report.

On the other hand, any change should be reported immediately
using "State Change Report" messages. Since it's an event
triggered by a change and that it can be affected by packet
loss, the rfc states it should be retransmitted [RobVar] times
to make sure routers will receive timely.

Currently, we are sending "Current State Reports" after
DAD is completed.  Before that, we send messages using
unspecified address (::) which should be silently discarded
by routers.

This patch changes to send "State Change Report" messages
after DAD is completed fixing the behavior to be RFC compliant
and also to pass TAHI IPv6 testsuite.
Signed-off-by: Flavio Leitner <fbl@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Remove function  qlcnic_enable_eswitch which was defined
but never used in current code.

Compile tested only.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Functions only used in one file should be static.
Found by running make namespacecheck

Compile tested only.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch is following the commit b903d324 (ipv6: tcp: fix TCLASS
value in ACK messages sent from TIME_WAIT).

For the same reason than tclass, we have to store the flow label in the
inet_timewait_sock to provide consistency of flow label on the last ACK.
Signed-off-by: Florent Fourcot <florent.fourcot@enst-bretagne.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>

John W. Linville says:

====================
Please pull this batch of updates for the 3.14 stream!

For the mac80211 bits, Johannes says:

"This time I have uAPSD fixes since I was working on that, hwsim
improvements to make dynamic radios possible for the test suite, the
evidently long-overdue channel_change_time removal and a few other small
collected fix and improvements."

For the iwlwifi bits, Emmanuel says:

"Besides a few trivial patches, I have an important workaround for a HW
issue that has kept me busy for a long time. Along with it, a fix that
prevents an error from being printed.
Eyal fixes our behavior against SISO APs and Ilan fixes an issue with
multiple interface scenarios.
Eliad fixes an error path in our init flow.
We also have a few 'static analyzers' fix."

For the NFC bits, Samuel says:

"It includes:

* A new NFC driver for Marvell's 8897, and a few NCI fixes and
  improvements needed to support this chipset.

* An LLCP fix for how we were setting the default MIU on a p2p link. If
  there is no explicit MIU extension announced at connection time, we
  must use the default one and not the one announced at LLCP link
  establishement time.

* A pn544 EEPROM config update. Some of the currently EEPROM configured
  values are overwriting the firmware ones while other should not be set
  by the driver itself.

* Some NFC digital stack fixes and improvements. Asynchronous functions
  are better documented, RF technologies and CRC functions are set upon
  PSL_REQ reception, and a few minor bugs are fixed.

* Minor and miscelaneous pn533, mei_phy and port100 fixes."

For the ath bits, Kalle says:

"Janusz added Kconfig option for DFS. The DFS code was there already, but
after fixes to mac80211 we can now enable it.

Bartosz added a runtime firmware feature flag to disable P2P. Our 10.1
firmware branch doesn't support P2P and ath10k can now disable that. He
also added a limit for how many clients can connect to ath10k AP.

Michal fixed WEP shared authentication, in case someone still uses it.
And I added firmware debug log to help the firmware engineers."

Along with that is a small batch of ath9k updates and a few other bits
here and there.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-next into for-davem

Michael Dalton says:

====================
virtio-net: mergeable rx buffer size auto-tuning

The virtio-net device currently uses aligned MTU-sized mergeable receive
packet buffers. Network throughput for workloads with large average
packet size can be improved by posting larger receive packet buffers.
However, due to SKB truesize effects, posting large (e.g, PAGE_SIZE)
buffers reduces the throughput of workloads that do not benefit from GRO
and have no large inbound packets.

This patchset introduces virtio-net mergeable buffer size auto-tuning,
with buffer sizes ranging from aligned MTU-size to PAGE_SIZE. Packet
buffer size is chosen based on a per-receive queue EWMA of incoming
packet size.

To unify mergeable receive buffer memory allocation and improve
SKB frag coalescing, all mergeable buffer memory allocation is
migrated to per-receive queue page frag allocators.

The per-receive queue mergeable packet buffer size is exported via
sysfs, and the network device sysfs layer has been extended to add
support for device-specific per-receive queue sysfs attribute groups.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Add initial support for per-rx queue sysfs attributes to virtio-net. If
mergeable packet buffers are enabled, adds a read-only mergeable packet
buffer size sysfs attribute for each RX queue.
Suggested-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael Dalton <mwdalton@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

To ensure ewma_read() without a lock returns a valid but possibly
out of date average, modify ewma_add() by using ACCESS_ONCE to prevent
intermediate wrong values from being written to avg->internal.
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Michael Dalton <mwdalton@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Extend existing support for netdevice receive queue sysfs attributes to
permit a device-specific attribute group. Initial use case for this
support will be to allow the virtio-net device to export per-receive
queue mergeable receive buffer size.
Signed-off-by: Michael Dalton <mwdalton@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Commit 2613af0e ("virtio_net: migrate mergeable rx buffers to page frag
allocators") changed the mergeable receive buffer size from PAGE_SIZE to
MTU-size, introducing a single-stream regression for benchmarks with large
average packet size. There is no single optimal buffer size for all
workloads.  For workloads with packet size <= MTU bytes, MTU + virtio-net
header-sized buffers are preferred as larger buffers reduce the TCP window
due to SKB truesize. However, single-stream workloads with large average
packet sizes have higher throughput if larger (e.g., PAGE_SIZE) buffers
are used.

This commit auto-tunes the mergeable receiver buffer packet size by
choosing the packet buffer size based on an EWMA of the recent packet
sizes for the receive queue. Packet buffer sizes range from MTU_SIZE +
virtio-net header len to PAGE_SIZE. This improves throughput for
large packet workloads, as any workload with average packet size >=
PAGE_SIZE will use PAGE_SIZE buffers.

These optimizations interact positively with recent commit
ba275241 ("virtio-net: coalesce rx frags when possible during rx"),
which coalesces adjacent RX SKB fragments in virtio_net. The coalescing
optimizations benefit buffers of any size.

Benchmarks taken from an average of 5 netperf 30-second TCP_STREAM runs
between two QEMU VMs on a single physical machine. Each VM has two VCPUs
with all offloads & vhost enabled. All VMs and vhost threads run in a
single 4 CPU cgroup cpuset, using cgroups to ensure that other processes
in the system will not be scheduled on the benchmark CPUs. Trunk includes
SKB rx frag coalescing.

net-next w/ virtio_net before 2613af0e (PAGE_SIZE bufs): 14642.85Gb/s
net-next (MTU-size bufs):  13170.01Gb/s
net-next + auto-tune: 14555.94Gb/s

Jason Wang also reported a throughput increase on mlx4 from 22Gb/s
using MTU-sized buffers to about 26Gb/s using auto-tuning.
Signed-off-by: Michael Dalton <mwdalton@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The virtio-net driver currently uses netdev_alloc_frag() for GFP_ATOMIC
mergeable rx buffer allocations. This commit migrates virtio-net to use
per-receive queue page frags for GFP_ATOMIC allocation. This change unifies
mergeable rx buffer memory allocation, which now will use skb_refill_frag()
for both atomic and GFP-WAIT buffer allocations.

To address fragmentation concerns, if after buffer allocation there
is too little space left in the page frag to allocate a subsequent
buffer, the remaining space is added to the current allocated buffer
so that the remaining space can be used to store packet data.
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael Dalton <mwdalton@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

skb_page_frag_refill currently permits only order-0 page allocs
unless GFP_WAIT is used. Change skb_page_frag_refill to attempt
higher-order page allocations whether or not GFP_WAIT is used. If
memory cannot be allocated, the allocator will fall back to
successively smaller page allocs (down to order-0 page allocs).

This change brings skb_page_frag_refill in line with the existing
page allocation strategy employed by netdev_alloc_frag, which attempts
higher-order page allocations whether or not GFP_WAIT is set, falling
back to successively lower-order page allocations on failure. Part
of migration of virtio-net to per-receive queue page frag allocators.
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Michael Dalton <mwdalton@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The error code was not set if change indev fail, so the error
condition wasn't reflected in the return value. Fix to return a
negative error code from this error handling case instead of 0.

Fixes: 2519a602 ('net_sched: optimize tcf_match_indev()')
Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>