<feed xmlns='http://www.w3.org/2005/Atom'>
<title>kernel/drivers/net/ethernet/intel/i40e/i40e_main.c, branch linux-4.3.y</title>
<subtitle>Hosts the 0x221E linux distro kernel.</subtitle>
<id>https://universe.0xinfinity.dev/distro/kernel/atom?h=linux-4.3.y</id>
<link rel='self' href='https://universe.0xinfinity.dev/distro/kernel/atom?h=linux-4.3.y'/>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/'/>
<updated>2015-10-23T01:06:18Z</updated>
<entry>
<title>i40e: fix annoying message</title>
<updated>2015-10-23T01:06:18Z</updated>
<author>
<name>Jesse Brandeburg</name>
<email>jesse.brandeburg@intel.com</email>
</author>
<published>2015-10-03T00:57:21Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=e9e53662d8130dd950885e37dc1d97008e1283f9'/>
<id>urn:sha1:e9e53662d8130dd950885e37dc1d97008e1283f9</id>
<content type='text'>
The driver was printing a message about not being able
to assign VMDq because of a lack of MSI-X vectors.

This was because a line was missing that initialized a variable,
simply a merge error.

Signed-off-by: Jesse Brandeburg &lt;jesse.brandeburg@intel.com&gt;
Tested-by: Andrew Bowers &lt;andrewx.bowers@intel.com&gt;
Signed-off-by: Jeff Kirsher &lt;jeffrey.t.kirsher@intel.com&gt;
</content>
</entry>
<entry>
<title>i40e: fix offload of GRE tunnels</title>
<updated>2015-10-05T11:31:41Z</updated>
<author>
<name>Jesse Brandeburg</name>
<email>jesse.brandeburg@intel.com</email>
</author>
<published>2015-10-02T01:25:42Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=fec31ffffa6e05845ab13908d0ac0d5a10816836'/>
<id>urn:sha1:fec31ffffa6e05845ab13908d0ac0d5a10816836</id>
<content type='text'>
The driver still was not offloading TSO on GRE tunnels because
it forgot to set the GSO_GRE flag, causing lots of retransmits.

This fixes generic GRE traffic (like a tunnel added like below)
whereas before it would get 1Gb/s or less, now on a 10G adapter
it gets 8.7Gb/s.

ip ad ad 11.1.0.2/24 dev ens2f0
ip l set ens2f0 up
ip link add gre2 type gretap remote 11.1.0.1 local 11.1.0.2 dev ens2f0
ip l set gre2 up
ip ad ad 192.168.124.2/24 dev gre2
ping 192.168.124.1
netperf -H 192.168.124.1

Signed-off-by: Jesse Brandeburg &lt;jesse.brandeburg@intel.com&gt;
Signed-off-by: Jeff Kirsher &lt;jeffrey.t.kirsher@intel.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
</entry>
<entry>
<title>i40e: fix VLAN inside VXLAN</title>
<updated>2015-09-29T03:56:58Z</updated>
<author>
<name>Jesse Brandeburg</name>
<email>jesse.brandeburg@intel.com</email>
</author>
<published>2015-09-28T18:21:48Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=c4bbac3913c0d649898a0d767728a585869a7d7d'/>
<id>urn:sha1:c4bbac3913c0d649898a0d767728a585869a7d7d</id>
<content type='text'>
Previously to this patch, the hardware was removing
VLAN tags from the inner header of VXLAN packets.  The
hardware configuration can be changed to leave the
packet alone since that is what the linux stack
expects for this type of VLAN in VXLAN packet.

Signed-off-by: Jesse Brandeburg &lt;jesse.brandeburg@intel.com&gt;
Tested-by: Andrew Bowers &lt;andrewx.bowers@intel.com&gt;
Signed-off-by: Jeff Kirsher &lt;jeffrey.t.kirsher@intel.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
</entry>
<entry>
<title>i40e: Set defport behavior for the Main VSI when in promiscuous mode</title>
<updated>2015-09-01T23:33:00Z</updated>
<author>
<name>Anjali Singhai Jain</name>
<email>anjali.singhai@intel.com</email>
</author>
<published>2015-07-28T17:02:00Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=92faef85613d6d56803ad6130f6daf4a803deddc'/>
<id>urn:sha1:92faef85613d6d56803ad6130f6daf4a803deddc</id>
<content type='text'>
This fixes bugs where the port is not receiving multicast or VLAN tagged
packets when in promiscuous mode. This can occur when a SW bridge is
created on top of the device.

This also fixes issues where the promiscuous behavior setting was not
being preserved across a reset caused by features being enabled or
disabled.

We are using defport instead of doing a true promiscuous mode because we do
not need to receive the SRIOV or VMDq VSI directed traffic which would suck
up bandwidth and is really not intended for the SW bridge.

In addition, with defport we get VLAN promiscuous behavior which is not
possible from the VSI level promiscuous setting.

Change-ID: Ie21985eac32d5af1c02e9d71c6430a90d5bab40f
Signed-off-by: Anjali Singhai Jain &lt;anjali.singhai@intel.com&gt;
Signed-off-by: Jeff Kirsher &lt;jeffrey.t.kirsher@intel.com&gt;
</content>
</entry>
<entry>
<title>i40e/i40evf: Bump i40e to 1.3.9 and i40evf to 1.3.5</title>
<updated>2015-08-26T22:14:36Z</updated>
<author>
<name>Catherine Sullivan</name>
<email>catherine.sullivan@intel.com</email>
</author>
<published>2015-07-10T23:36:10Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=bf41846edf5b1618a37f8ec830251b31d8ed6ab3'/>
<id>urn:sha1:bf41846edf5b1618a37f8ec830251b31d8ed6ab3</id>
<content type='text'>
Bump version and update the copyright year for i40evf.

Change-ID: Iddb81b9dba09f0dc57ab54937b5821ecdd721ff6
Signed-off-by: Catherine Sullivan &lt;catherine.sullivan@intel.com&gt;
Tested-by: Andrew Bowers &lt;andrewx.bowers@intel.com&gt;
Signed-off-by: Jeff Kirsher &lt;jeffrey.t.kirsher@intel.com&gt;
</content>
</entry>
<entry>
<title>i40e: Remove redundant and unneeded messages</title>
<updated>2015-08-26T22:07:34Z</updated>
<author>
<name>Greg Rose</name>
<email>gregory.v.rose@intel.com</email>
</author>
<published>2015-07-10T23:36:07Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=2b20c88397fde2902c7834bb9e3ef8afc0237306'/>
<id>urn:sha1:2b20c88397fde2902c7834bb9e3ef8afc0237306</id>
<content type='text'>
The kernel notifies all VXLAN capable registered drivers, i.e. any
driver that implements ndo_add_vxlan_port(), of the addition of a
port so that the driver can track which ports are in use.  There's
no need to log this - it just fills the system log with useless and
irksome noise.

Also, when failing to init SR-IOV interfaces the driver was printing the
same message twice. Just remove the inner printk and let the outer message
catch enable as well as the other failures.

Change-ID: Id5ecb1d425c2a357ee2bc1635dab24553831dade
Signed-off-by: Greg Rose &lt;gregory.v.rose@intel.com&gt;
Signed-off-by: Jesse Brandeburg &lt;jesse.brandeburg@intel.com&gt;
Tested-by: Andrew Bowers &lt;andrewx.bowers@intel.com&gt;
Signed-off-by: Jeff Kirsher &lt;jeffrey.t.kirsher@intel.com&gt;
</content>
</entry>
<entry>
<title>i40e/i40evf: Add capability to gather VEB per TC stats</title>
<updated>2015-08-26T21:56:08Z</updated>
<author>
<name>Neerav Parikh</name>
<email>neerav.parikh@intel.com</email>
</author>
<published>2015-07-10T23:36:02Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=fe860afb4638f5e62e7d861bfc35a1580fb633bb'/>
<id>urn:sha1:fe860afb4638f5e62e7d861bfc35a1580fb633bb</id>
<content type='text'>
This patch adds capability to update per VEB per TC statistics and dump
it via ethtool. It also adds a structure to hold VEB per TC statistics.
The fields can be filled by reading the GLVEBTC_* counters.

Change-ID: I28b4759b9ab6ad5a61f046a1bc9ef6b16fe31538
Signed-off-by: Neerav Parikh &lt;neerav.parikh@intel.com&gt;
Tested-by: Andrew Bowers &lt;andrewx.bowers@intel.com&gt;
Signed-off-by: Jeff Kirsher &lt;jeffrey.t.kirsher@intel.com&gt;
</content>
</entry>
<entry>
<title>i40e: Fix legacy interrupt mode in the driver</title>
<updated>2015-08-26T21:51:28Z</updated>
<author>
<name>Anjali Singhai Jain</name>
<email>anjali.singhai@intel.com</email>
</author>
<published>2015-07-10T23:36:00Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=26cdc443fd8fccccdfb17fd2845cf9233a995325'/>
<id>urn:sha1:26cdc443fd8fccccdfb17fd2845cf9233a995325</id>
<content type='text'>
This patch fixes the driver flow to take into account legacy interrupts.
Over time we added code that assumes MSIX is the only mode that the
driver runs in. It also enables a legacy workaround to trigger SWINT
when the TX ring has non-cache aligned descriptors pending and interrupts
are disabled.

We work with a single vector in MSI mode too, so apply the same
restrictions as Legacy.

Change-ID: I826ddff1f9bd45d2dbe11f56a3ddcef0dbf42563
Signed-off-by: Anjali Singhai Jain &lt;anjali.singhai@intel.com&gt;
Tested-by: Andrew Bowers &lt;andrewx.bowers@intel.com&gt;
Signed-off-by: Jeff Kirsher &lt;jeffrey.t.kirsher@intel.com&gt;
</content>
</entry>
<entry>
<title>i40e: Move function calls to i40e_shutdown instead of i40e_suspend</title>
<updated>2015-08-26T21:49:09Z</updated>
<author>
<name>Catherine Sullivan</name>
<email>catherine.sullivan@intel.com</email>
</author>
<published>2015-07-10T23:35:59Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=02b42498f383a6c24f7c751d4fe89a911a249242'/>
<id>urn:sha1:02b42498f383a6c24f7c751d4fe89a911a249242</id>
<content type='text'>
We should be stopping the service task and flow director on
shutdown not on suspension.

Signed-off-by: Catherine Sullivan &lt;catherine.sullivan@intel.com&gt;
Tested-by: Andrew Bowers &lt;andrewx.bowers@intel.com&gt;
Signed-off-by: Jeff Kirsher &lt;jeffrey.t.kirsher@intel.com&gt;
</content>
</entry>
<entry>
<title>i40e: don't degrade __le16</title>
<updated>2015-08-26T21:44:38Z</updated>
<author>
<name>Mitch Williams</name>
<email>mitch.a.williams@intel.com</email>
</author>
<published>2015-07-10T23:35:56Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=ecbb44e8f81b860ef279b0f176a878da9ebd614e'/>
<id>urn:sha1:ecbb44e8f81b860ef279b0f176a878da9ebd614e</id>
<content type='text'>
Sparse cries when we compare an __le16 to a u16, almost like it cares
about architectures other than x86. Weird. Use the le16_to_cpu macro to
make it stop crying.

Change-ID: Id068f4d7868a2d3df234a791a76d15938f37db35
Signed-off-by: Mitch Williams &lt;mitch.a.williams@intel.com&gt;
Tested-by: Andrew Bowers &lt;andrewx.bowers@intel.com&gt;
Signed-off-by: Jeff Kirsher &lt;jeffrey.t.kirsher@intel.com&gt;
</content>
</entry>
</feed>
