RFR: 8325937: runtime/handshake/HandshakeDirectTest.java causes "monitor end should be strictly below the frame pointer" assertion failure on AArch64 [v4]

[Coleen Phillimore]

On Fri, 4 Oct 2024 14:50:09 GMT, Coleen Phillimore <coleenp at openjdk.org> wrote:

>> Add missing StoreLoad fences in handshaking code to match safepoint code.  Thanks to @pchilano for finding this bug.
>> 
>> Tested with tier1-4 and tier8 which has Kitchensink in it.
>
> Coleen Phillimore has updated the pull request incrementally with one additional commit since the last revision:
> 
>   Put suspend handshake fence() where Robbin suggested.

I filed [JDK-8341544](https://bugs.openjdk.org/browse/JDK-8341544) to investigate whether we need a fence() in mutex.lock and investigate other places we expect fences (other places we lock) to see if we also need a fence there too.  I meant to performance test this first part but got distracted by other things.  In any case, I'd like to integrate this fix but it needs a final approval.

-------------

PR Comment: https://git.openjdk.org/jdk/pull/21295#issuecomment-2419489304