RFR: 8242115: C2 SATB barriers are not safepoint-safe
Vladimir Ivanov
vlivanov at openjdk.org
Fri Sep 30 22:39:19 UTC 2022
On Fri, 30 Sep 2022 21:22:47 GMT, Igor Veresov <iveresov at openjdk.org> wrote:
> Implement load pinning, use it for g1 pre-value loads, add verification that the load control dependency is kept and that there are no safepoints between the load of the pre-value and the marking check (with the exception of the CAS intrinsics where it's permitted).
Looks good.
Did you run any performance tests?
-------------
Marked as reviewed by vlivanov (Reviewer).
PR: https://git.openjdk.org/jdk/pull/10517
More information about the hotspot-compiler-dev
mailing list