summaryrefslogtreecommitdiffstats
path: root/sound/atmel
diff options
context:
space:
mode:
authorAndreas Mohr <andi@lisas.de>2010-11-21 12:09:32 +0100
committerTakashi Iwai <tiwai@suse.de>2010-11-22 10:56:53 +0100
commit78ac07b0d2b09b1ccb7a41a2e25f71d60b652920 (patch)
tree9dfa659eccd1865c6c5e5b71591689775a8fd7ca /sound/atmel
parenta0e90acc657990511c83bc69965bfd3c63386d45 (diff)
downloadlinux-78ac07b0d2b09b1ccb7a41a2e25f71d60b652920.tar.gz
linux-78ac07b0d2b09b1ccb7a41a2e25f71d60b652920.tar.bz2
linux-78ac07b0d2b09b1ccb7a41a2e25f71d60b652920.zip
ALSA: azt3328: period bug fix (for PA), add missing ACK on stop timer
. Fix PulseAudio "ALSA driver bug" issue (if we have two alternated areas within a 64k DMA buffer, then max period size should obviously be 32k only). Back references: http://pulseaudio.org/wiki/AlsaIssues http://fedoraproject.org/wiki/Features/GlitchFreeAudio . In stop timer function, need to supply ACK in the timer control byte. . Minor log output correction When I did my first PA testing recently, the period size bug resulted in quite precisely observeable half-period-based playback distortion. PA-based operation is quite a bit more underrun-prone (despite its zero-copy optimizations etc.) than raw ALSA with this rather spartan sound hardware implementation on my puny Athlon. Note that even with this patch, azt3328 still doesn't work for both cases yet, PA tsched=0 and tsched (on tsched=0 it will playback tiny fragments of periods, leading to tiny stuttering sounds with some pauses in between, whereas with timer-scheduled operation playback works fine - minus some quite increased underrun trouble on PA vs. ALSA, that is). Signed-off-by: Andreas Mohr <andi@lisas.de> Signed-off-by: Takashi Iwai <tiwai@suse.de>
Diffstat (limited to 'sound/atmel')
0 files changed, 0 insertions, 0 deletions