compiletest crashes on CI with: expected success, got: signal: 11 (core dumped)

[klensy]

runner: x86_64-gnu-llvm-12, ubuntu-20.04-xl
Occured in multiple pr across CI:
#93361: https://github.com/rust-lang/rust/runs/4969749566?check_suite_focus=true
#93381: https://github.com/rust-lang/rust/runs/4969258442?check_suite_focus=true
#93375: https://github.com/rust-lang/rust/runs/4967313356?check_suite_focus=true
#93239: https://github.com/rust-lang/rust/runs/4963643970?check_suite_focus=true
and others

[JakobDegen]

Possibly this was #91840 ? Looking at what's been merged in the last day, that seems to be the most relevant thing

[matthiaskrgr]

You mean it might have introduced a new miscompilation that made compiletest crash?

[JakobDegen]

Maybe. Its also possible that there was some existing UB elsewhere that happened to get set off by this, don't really know. My observation just mostly comes from where the segfault is happening and what commits in the last day have touched nearby code

[klensy]

Warning: Skipping "src/test/ui": not a regular file or directory
Warning: Skipping "src/test/mir-opt": not a regular file or directory

Why this even triggered? Looks unrelated, but still suspicious.

[ehuss]

Those warnings are unrelated. I'll post a patch soon to fix it.

EDIT: #93399

[klensy]

Funny thing: #93352 been merged even with crashed compiletest: #93352 (comment), how this works?

[fee1-dead]

Funny thing: #93352 been merged even with crashed compiletest: #93352 (comment), how this works?

The comment by @rust-log-analyzer is about the CI run not the bors run.

[klensy]

The comment by @rust-log-analyzer is about the CI run not the bors run.

Yes, it failed on PR check, not on check-all-platforms-and-merge.
So fast approving PR, so it merged even with failed PR check :-(

[klensy]

@JakobDegen can you try to revert that #91840 pr and see, will it fail or not on test?