[release/8.0] JIT: Fix case where we illegally optimize away a memory barrier on ARM32 #91870
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
The ARM32/ARM64 backends have an optimization where they optimize out the latter of two subsequent memory barriers if no memory store/load has been seen between them. This optimization should not be allowed to remove memory barriers when a call has been seen. Fix #91732
dotnet-issue-labeler
bot
added
the
area-CodeGen-coreclr
|
Tagging subscribers to this area: @JulieLeeMSFT, @jakobbotsch Issue DetailsBackport of #91827 to release/8.0 /cc @jakobbotsch Customer ImpactTestingRiskIMPORTANT: If this backport is for a servicing release, please verify that:
|
jakobbotsch
changed the title
EgorBo
approved these changes
Sep 11, 2023
jeffschwMSFT
approved these changes
Sep 11, 2023
ghost
locked as resolved and limited conversation to collaborators
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Backport of #91827 to release/8.0
/cc @jakobbotsch
Customer Impact
The JIT may optimize out the latter of two memory barrier if no store/load happens between them. This optimization may happen even if there is a call between the two memory barriers. This can result in illegal reordering of stores/loads happening inside the called function with other stores/loads happening after.
This bug fix has diffs in built-in BCL primitives like
ConcurrentQueueandThreadPool.Testing
Verified that the affected test case no longer reproduces the issue within 1 hour (previously it was reproduced within a few minutes).
Risk
Low. This makes the optimization more conservative.