[aarch64-port-dev ] RFR(S): 8248851: CMS: Missing memory fences between free chunk check and klass read

Andrew Haley aph at redhat.com
Tue Jul 7 08:42:19 UTC 2020


On 07/07/2020 04:22, Yangfei (Felix) wrote:

> Webrev for jdk8u-dev:
> http://cr.openjdk.java.net/~fyang/8248851/webrev.00/ JTreg tested on
> x86_64-linux-gnu &aarch64-linux-gnu with jdk8u release builds.
> Comments?

That looks right. I was thinking of arguing that you only need
loadload here, but other parts of the same function use acquire, so we
might as well be consistent.

I'd lose this line:

// Bugfix for systems with weak memory model (AARCH64).

It doesn't add anything, and it may mislead people into thinking that
it's AArch64 specific. Looking at the code, it seems like all the
casting to volatile was an earlier attempt to fix the same bug.

-- 
Andrew Haley  (he/him)
Java Platform Lead Engineer
Red Hat UK Ltd. <https://www.redhat.com>
https://keybase.io/andrewhaley
EAC8 43EB D3EF DB98 CC77 2FAD A5CD 6035 332F A671



More information about the hotspot-gc-dev mailing list