summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorTakashi Sakamoto <o-takashi@sakamocchi.jp>2015-09-30 09:39:17 +0900
committerTakashi Iwai <tiwai@suse.de>2015-09-30 15:34:25 +0200
commit163ae6f3f3f059ab44311792af5a73f70f747263 (patch)
treef746842349ebf50a7bcdc9f8971b25c225a2fb05 /kernel
parent9edf723fd85822c7b7d8ef4f41a74c5a33eeca0c (diff)
downloadlinux-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