src/sys/dev/etherswitch, branch release/12.3.0

Improve detection of addressing mode in e6000sw

2018-04-10T08:35:43Z

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 Obtained from: Semihalf Sponsored by: Stormshield Differential Revision: https://reviews.freebsd.org/D14800

Clean up OF_getprop_alloc API

2018-04-08T22:59:34Z

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

[arswitch] Implement the switch MAC address fetch API.

2018-02-06T08:35:49Z

The placeholders are here for some future "set" MAC address API. Tested: * AR9340 switch * AR8327 switch

[etherswitch] add initial support for potentially configuring and fetching the switch MAC address.

2018-02-06T08:34:50Z

Switches that originate their own frames (eg obvious ones like Pause frames) need a MAC address to use to send those frames from. This API will hopefully begin to allow that to be configurable.

[arswitch] disable ARP copy-to-CPU port for AR9340 for now.

2018-02-05T20:37:29Z

I'll have to go double check to see if it does indeed pass ARP frames between switch ports with this disabled, but it seems required for the CPU port to see ARP traffic. I'll dig into this some more.

[arswitch] fix build breakage.

2018-02-05T20:30:53Z

Apparently the last time I checked building this it didn't pick up that the header had changed.

[arswitch] Enable ATU dump support for the AR9340.

2018-02-05T07:05:28Z

This indeed uses the same registers as the AR8216 and later chips. There seems to be an issue with ARP requests being sent out from the CPU through this switch here, so figuring that out is next. Learning works fine on the AR8327 ethernet switch on the /other/ gigabit ethernet port, so I don't think it's the network stack or ethernet driver. Tested: * DB120 - AR9340 SOC + ethernet switch (and other bits.)

[arswitch] fix mac address field definition.

2018-02-05T07:03:45Z

Whilst here, add some further fields for future experimenting. Tested: * AR9340 switch * AR9330 switch * AR7240 switch

[arswitch] Break out of the loop upon any error, not just -1.

2018-02-05T05:51:37Z

This fixes the AR9340 "unimplemented" thingy for now.

[arswitch] fix up issues on the AR8327.

2018-02-04T08:22:11Z

This correctly dumps the ethernet bridge contents on an AR8327 switch. Tested: * AP135 - QCA9550 + AR8327 ethernet switch: # etherswitchcfg atu dump [0] c0:3f:d5:7e:6f:45: portmask 0x00000004 [1] f6:b6:03:96:1e:ba: portmask 0x00000004 [2] 00:03:7f:11:38:4f: portmask 0x00000040 # arp -na ? (192.168.3.170) at 00:03:7f:11:38:4f on arge0 permanent [ethernet] ? (192.168.3.12) at c0:3f:d5:7e:6f:45 on arge0 expires in 1188 seconds [ethernet] ? (192.168.3.1) at f6:b6:03:96:1e:ba on arge0 expires in 1186 seconds [ethernet]