On Oct 07 Stefan Richter wrote:
On Oct 04 Takashi Sakamoto wrote:
Current ALSA BeBoB drivers has an entry for this model, while the value of vendor ID seems to be wrong according to an user's report.
The vendor had released no updated firmware, thus we can judge that this model had not changed the content of its config ROM. It's reasonable to fix the ID according to the report.
$ ./linux-firewire-utils/src/crpp < /sys/bus/firewire/devices/fw1/config_rom
ROM header and bus information block -----------------------------------------------------------------400 0425720f bus_info_length 4, crc_length 37, crc 29199 404 31333934 bus_name "1394" 408 f0646122 irmc 1, cmc 1, isc 1, bmc 1, pmc 0, cyc_clk_acc 100, max_rec 6 (128), max_rom 1, gen 2, spd 2 (S400) 40c 00000ff2 company_id 00000f | 410 00004697 device_id f200004697 | EUI-64 00000ff200004697
This is a mistake from the firmware author. The company ID part (OUI-24) within the EUI-64 should obviously be 0x000ff2 for Loud, Inc. instead of 0x00000f for NeXT, Inc.. The firmware author accidentally shifted the company ID by one byte into the device ID.
root directory -----------------------------------------------------------------414 000859be directory_length 8, crc 22974 418 04000082 hardware version 41c 0c0083c0 node capabilities per IEEE 1394 420 03000ff2 vendor 424 8100000a --> descriptor leaf at 44c
Here is the correct value.
firewire-core uses _this_ entry when it generates the modalias of a FireWire unit device,
[...]
The configuration file of the FFADO userspace drivers is apparently affected by this matter too:
device_definitions = ( { vendorid = 0x00000f; modelid = 0x00010065; vendorname = "Mackie"; modelname = "Onyx Firewire"; driver = "BEBOB"; xmit_max_cycles_early_transmit = 4; }, { # Added by arnonym from ffado-mixers list vendorid = 0x00000f; modelid = 0x00010067; vendorname = "Mackie"; modelname = "Onyx Firewire"; driver = "BEBOB"; mixer = "MackieOnyx"; xmit_max_cycles_early_transmit = 4; }, [...]
I am not 100% sure, but I think that FFADO takes the vendor ID from the root directory too, not from the GUID in the bus information block.
[...]
Hmm, seems I was wrong. This is a debug log from the ffado-user mailinglist, August 31:
1441054790505378: (ffado.cpp)[ 92] ffado_streaming_init: libffado 2.2.9999- built Jun 5 2015 15:13:52 01789081089: Debug (devicemanager.cpp)[ 354] discover: Starting discovery... 01789165571: Debug (Configuration.cpp)[ 163] showSetting: Group: (null) 01789165589: Debug (Configuration.cpp)[ 185] showSetting: vendorid = 15 (0x0000000F) 01789165593: Debug (Configuration.cpp)[ 185] showSetting: modelid = 65637 (0x00010065) 01789165601: Debug (Configuration.cpp)[ 209] showSetting: vendorname = Mackie 01789165605: Debug (Configuration.cpp)[ 209] showSetting: modelname = Onyx Firewire 01789165608: Debug (Configuration.cpp)[ 209] showSetting: driver = BEBOB 01789165610: Debug (Configuration.cpp)[ 185] showSetting: xmit_max_cycles_early_transmit = 4 (0x00000004) 01789165755: Debug (devicemanager.cpp)[ 616] discover: driver found for device 1
So the original FFADO configuration works as-is.