diff options
author | Takashi Sakamoto <o-takashi@sakamocchi.jp> | 2015-09-30 09:39:17 +0900 |
---|---|---|
committer | Takashi Iwai <tiwai@suse.de> | 2015-09-30 15:34:25 +0200 |
commit | 163ae6f3f3f059ab44311792af5a73f70f747263 (patch) | |
tree | f746842349ebf50a7bcdc9f8971b25c225a2fb05 /kernel | |
parent | 9edf723fd85822c7b7d8ef4f41a74c5a33eeca0c (diff) | |
download | linux-163ae6f3f3f059ab44311792af5a73f70f747263.tar.bz2 |
ALSA: firewire-digi00x: add data block processing layer
Digi 002/003 family uses its own format for data blocks. The format is
quite similar to AM824 in IEC 61883-6, while there're some differences:
* The Valid Bit Length (VBL) code is always 0x40 in Multi-bit Linear Audio
(MBLA) data channel.
* The first data channel includes MIDI messages, against IEC 61883-6
recommendation.
* The Counter field is always zero in MIDI conformant data channel.
* Sequence multiplexing in IEC 61883-6 is not applied to the MIDI
conformant data channel.
* PCM samples are scrambled in received AMDTP packets. We call the way
as Double-Oh-Three (DOT). The algorithm was discovered by
Robin Gareus and Damien Zammit in 2012.
This commit adds data processing layer to satisfy these differences.
There's a quirk about transmission mode for received packets. When this
driver applies non-blocking mode to outgoing packets with isochronous
channel 2 or more, after 15 to 20 seconds since playbacking, any PCM
samples causes noisy sound on the device. With isochronous channel 0 or 1,
this doesn't occur. As long as I investigated, this quirk is not observed
when applying blocking mode to the received packets.
This driver applies blocking mode to outgoing packets, while non-blocking
mode to incoming packgets.
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Diffstat (limited to 'kernel')
0 files changed, 0 insertions, 0 deletions