<feed xmlns='http://www.w3.org/2005/Atom'>
<title>src/sys/dev/etherswitch/e6000sw, branch releng/12.4</title>
<subtitle>FreeBSD source tree</subtitle>
<id>https://cgit-dev.freebsd.org/src/atom?h=releng%2F12.4</id>
<link rel='self' href='https://cgit-dev.freebsd.org/src/atom?h=releng%2F12.4'/>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/'/>
<updated>2018-04-10T08:35:43Z</updated>
<entry>
<title>Improve detection of addressing mode in e6000sw</title>
<updated>2018-04-10T08:35:43Z</updated>
<author>
<name>Marcin Wojtas</name>
<email>mw@FreeBSD.org</email>
</author>
<published>2018-04-10T08:35:43Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=fb4478a33619b2d254ee73c91dfdbf2b515f5607'/>
<id>urn:sha1:fb4478a33619b2d254ee73c91dfdbf2b515f5607</id>
<content type='text'>
Some devices cannot rely on the switch MDIO address passed in the DTB
for specifying single/multi-chip addressing mode. Introduce new property
"single-chip-addressing" which added to DTS will force single-chip mode.

Submitted by: Michal Mazur &lt;mkm@semihalf.com&gt;
Obtained from: Semihalf
Sponsored by: Stormshield
Differential Revision: https://reviews.freebsd.org/D14800
</content>
</entry>
<entry>
<title>Clean up OF_getprop_alloc API</title>
<updated>2018-04-08T22:59:34Z</updated>
<author>
<name>Oleksandr Tymoshenko</name>
<email>gonzo@FreeBSD.org</email>
</author>
<published>2018-04-08T22:59:34Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=217d17bcd3f525fbdf124cfbc926f8033da69805'/>
<id>urn:sha1:217d17bcd3f525fbdf124cfbc926f8033da69805</id>
<content type='text'>
OF_getprop_alloc takes element size argument and returns number of
elements in the property. There are valid use cases for such behavior
but mostly API consumers pass 1 as element size to get string
properties. What API users would expect from OF_getprop_alloc is to be
a combination of malloc + OF_getprop with the same semantic of return
value. This patch modifies API signature to match these expectations.

For the valid use cases with element size != 1 and to reduce
modification scope new OF_getprop_alloc_multi function has been
introduced that behaves the same way OF_getprop_alloc behaved prior to
this patch.

Reviewed by:	ian, manu
Differential Revision:	https://reviews.freebsd.org/D14850
</content>
</entry>
<entry>
<title>[etherswitch] check if_alloc returns NULL</title>
<updated>2018-01-24T21:33:18Z</updated>
<author>
<name>Michael Zhilin</name>
<email>mizhka@FreeBSD.org</email>
</author>
<published>2018-01-24T21:33:18Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=0774131e27d6764f90967f6e2571ca84e8e6590f'/>
<id>urn:sha1:0774131e27d6764f90967f6e2571ca84e8e6590f</id>
<content type='text'>
This patch is cosmetic. It checks if allocation of ifnet structure failed.
It's better to have this check rather than assume positive scenario.

Submitted by:	Dmitry Luhtionov &lt;dmitryluhtionov@gmail.com&gt;
Reported by:	Dmitry Luhtionov &lt;dmitryluhtionov@gmail.com&gt;
</content>
</entry>
<entry>
<title>Fix the port vlan support in e6000 based switches.</title>
<updated>2017-07-27T02:38:53Z</updated>
<author>
<name>Luiz Otavio O Souza</name>
<email>loos@FreeBSD.org</email>
</author>
<published>2017-07-27T02:38:53Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=0e779c2f7b8d766e5f0264c92f380ea38476287b'/>
<id>urn:sha1:0e779c2f7b8d766e5f0264c92f380ea38476287b</id>
<content type='text'>
Reduce the use of local copies of switch register data.

The switch now works with the upstream dsa node (i.e. the upstream DTS).

Tested on:	ClearFog Pro (88E6176), SG-3100 (88E6141)
Sponsored by:	Rubicon Communications, LLC (Netgate)
</content>
</entry>
<entry>
<title>Add support to 2.5G uplink for the MV88E6141 and MV88E6341 switches.</title>
<updated>2017-06-20T18:11:23Z</updated>
<author>
<name>Luiz Otavio O Souza</name>
<email>loos@FreeBSD.org</email>
</author>
<published>2017-06-20T18:11:23Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=091d140c99e499feccd4b17bede11600b1964947'/>
<id>urn:sha1:091d140c99e499feccd4b17bede11600b1964947</id>
<content type='text'>
Force the switch port settings for fixed media types.

Tested with:	88E6176, 88E6141
Sponsored by:	Rubicon Communications, LLC (Netgate)
</content>
</entry>
<entry>
<title>Prevent multiple lock initialization in e6000sw probe</title>
<updated>2017-06-13T18:35:14Z</updated>
<author>
<name>Zbigniew Bodek</name>
<email>zbb@FreeBSD.org</email>
</author>
<published>2017-06-13T18:35:14Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=eb3ffa577b3753b48426df567776dc971fd6739a'/>
<id>urn:sha1:eb3ffa577b3753b48426df567776dc971fd6739a</id>
<content type='text'>
r319886 ("Add the initial support for the Marvell 88E6141
and 88E6341 switches.") unveiled a problem with possible
multiple lock creation. Move its initialization
to the driver attach and for obtaining the switch ID
create a temprorary one, which is immediately destroyed
after the check.

Submitted by: Zbigniew Bodek &lt;zbb@semihalf.com&gt;
	      Marcin Wojtas &lt;mw@semihalf.com&gt;
Obtained from: Semihalf
</content>
</entry>
<entry>
<title>Add the initial support for the Marvell 88E6141 and 88E6341 switches.</title>
<updated>2017-06-13T00:42:23Z</updated>
<author>
<name>Luiz Otavio O Souza</name>
<email>loos@FreeBSD.org</email>
</author>
<published>2017-06-13T00:42:23Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=ff2748ec10e48d546cc0928ec94e1d9192d6ddb9'/>
<id>urn:sha1:ff2748ec10e48d546cc0928ec94e1d9192d6ddb9</id>
<content type='text'>
Right now the driver only supports port VLANs, so make sure
etherswitch_getinfo() return the proper switch capabilities.

Handle the cases where not all ports are in use (that will also require
etherswitch cooperation).

Sponsored by:	Rubicon Communications, LLC (Netgate)
</content>
</entry>
<entry>
<title>Remove an unnecessary variable from the switch softc structure and make the</title>
<updated>2017-06-09T20:38:18Z</updated>
<author>
<name>Luiz Otavio O Souza</name>
<email>loos@FreeBSD.org</email>
</author>
<published>2017-06-09T20:38:18Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=595d629c09dfedb70f7fd05f21b505a07aeddd68'/>
<id>urn:sha1:595d629c09dfedb70f7fd05f21b505a07aeddd68</id>
<content type='text'>
functions that are used as booleans return real boolean values.

Sponsored by:	Rubicon Communications, LLC (Netgate)
</content>
</entry>
<entry>
<title>style(9) fixes, remove unnecessary headers, remove duplicate #defines and</title>
<updated>2017-06-02T15:12:32Z</updated>
<author>
<name>Luiz Otavio O Souza</name>
<email>loos@FreeBSD.org</email>
</author>
<published>2017-06-02T15:12:32Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=33c2a3cb16bd91563365c92af98ee2dcd98e4d59'/>
<id>urn:sha1:33c2a3cb16bd91563365c92af98ee2dcd98e4d59</id>
<content type='text'>
in some cases, shuffle the code around to simplify locking.

No functional changes.

Sponsored by:	Rubicon Communications, LLC (Netgate)
</content>
</entry>
<entry>
<title>Poll PHY status using internal e6000sw registers</title>
<updated>2017-05-19T08:24:23Z</updated>
<author>
<name>Wojciech Macek</name>
<email>wma@FreeBSD.org</email>
</author>
<published>2017-05-19T08:24:23Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=2dd020069e3d868047357044d87dfe509df1643e'/>
<id>urn:sha1:2dd020069e3d868047357044d87dfe509df1643e</id>
<content type='text'>
e6000sw family automatically reflects PHY status in each port's registers.
Therefore it is not necessary to do a full PHY polling squence, which
results in much quicker operation and much less significant usage of
the SMI bus.

Care must be taken that the resulting ifmedia_active is identical to
what the PHY will compute, or gratuitous link status changes will
occur whenever the PHYs update function is called.

This patch implements above improvement. On the occasion set a pointer to
the proc structure to be part of software context instead of being
a global variable.

Submitted by: Marcin Wojtas &lt;mw@semihalf.com&gt;
Obtained from: Semihalf
Sponsored by: Stormshield
Reviewed by: loos
Differential revision: https://reviews.freebsd.org/D10714
</content>
</entry>
</feed>
