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

[Erik Österlund]

On Tue, 1 Oct 2024 18:38:33 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.

FWIW I think Coleen's patch is good regardless of how much we can trust lock() to fence() or not. It's more clear to keep the fence next to the ADS hammer so the code is more obviously correct. But it's still interesting to note that we might be looking at the tip of an iceberg. The lack of this fence was intentional, and I am very worried about how many more of these we will encounter.

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

Marked as reviewed by eosterlund (Reviewer).

PR Review: https://git.openjdk.org/jdk/pull/21295#pullrequestreview-2343046387