kjetil, thanks for the patch.

however, the problem with fixing this problem has never been identifying where to put the barriers, it has been adding them in a portable way. __atomic_* are, as far as i can tell, gcc-specific. am i wrong about that?

On Fri, Mar 4, 2016 at 7:42 AM, Kjetil Matheussen <k.s.matheussen@gmail.com> wrote:


On Fri, Mar 4, 2016 at 1:22 PM, Kjetil Matheussen <k.s.matheussen@gmail.com> wrote:
You are right. There was even a discussion about how broken it was
in 2008, and it was fixed, at least in practice.

Theoretically (and not unlikely also in practice), it seems to be still broken.
This can also confirmed by compiling with -fsanitize=thread:



It can probably be optimized by relaxing some of the barrier strenghtnessness though,
but it probably makes no practical difference in execution time.
Perhaps apply this to jack, at least to avoid uncertainty about whether it will really
always work?


_______________________________________________
Linux-audio-dev mailing list
Linux-audio-dev@lists.linuxaudio.org
http://lists.linuxaudio.org/listinfo/linux-audio-dev