On 07.10.2015 08:14, Konstantin Belousov wrote:
> I believe there are subtle differences between our- and Linux- nowait
> behaviour.  I claim (but do not want to take liability of prove it with
> references to Linux code) that our M_NOWAIT may fail transiently due to
> pagedaemon not keeping up with load, while Linux top-half nowait alloc
> only fails for real out-of-resources conditions.
> 
> What I am trying to say, leave M_NOWAIT out of syscalls.  Some time ago
> M_NOWAIT also means that the caller is allowed to use reserves to satisfy
> allocation, but this was fixed.

Ok, I understand. Let's revert to use M_WAITOK then.

During the DRM core update, I also used M_NOWAIT. Likewise for the i915
WIP. I will change some of them back to M_WAITOK after checking the
context of the allocation (syscall or not).

Thank you for the clarification on those flags!

-- 
Jean-Sébastien Pédron

Attachment: signature.asc
Description: OpenPGP digital signature

Reply via email to