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

Wed Oct 2 11:58:37 UTC 2024

On Wed, 2 Oct 2024 10:49:57 GMT, Andrew Haley <aph at openjdk.org> wrote:

> 
> Hans Boehm has this historical info, https://hboehm.info/misc_slides/reordering.pdf

I may be misunderstanding things a bit here, but slides 17 and 19 seem to imply that `pthread_mutex_lock` *does* need a full barrier (whereas `std::mutex` wouldn't necessarily).

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

PR Comment: https://git.openjdk.org/jdk/pull/21295#issuecomment-2388459768