CVS commit: src/sys/kern

["Taylor R Campbell" <riastradh%netbsd.org@localhost>]

Module Name:    src
Committed By:   riastradh
Date:           Mon Jul 17 21:51:45 UTC 2023

Modified Files:
        src/sys/kern: kern_tc.c

Log Message:
timecounter(9): Sprinkle membar_consumer around th->th_generation.

This code was apparently written under the misapprehension that
membar_producer on one side is good enough, but that doesn't
accomplish anything other than making the code unnecessarily obscure.

For semantics, you always always always need memory barriers to come
in pairs, with membar_consumer on the reading side if you want the
membar_producer to have on the writing side to have any useful
effect.

It is unfortunate that this might hurt performance, but that's an
unfortunate consequence of the design made without understanding
memory barriers, not an unfortunate consequence of the memory
barriers.

If it is really critical for the read side to avoid memory barriers,
then the write side needs to issue an IPI or xcall to effect memory
barriers -- at higher cost to the write side, of course.


To generate a diff of this commit:
cvs rdiff -u -r1.72 -r1.73 src/sys/kern/kern_tc.c

Please note that diffs are not public domain; they are subject to the
copyright notices on the relevant files.