ci: Run tests also on i686

[Jakuje]

Fixes: #285

[wiktor-k]

#282 has already been fixed... Should this be closed or is there anything valuable that we can scavenge? 😁

[Jakuje]

#282 has already been fixed... Should this be closed or is there anything valuable that we can scavenge? 😁

This is about running the tests on i386, not just building as with the ulong size on 32b arch, some things might explode even during runtime. I tried to rework it, but did not manage to finalize the linking on multiarch yet.

[Jakuje]

And it was a missing dollar sign all the time 🤦

So this should be good to review.

If not done early, I will start adding arm builds :)

[wiktor-k]

Okay, I think this looks good and should be merged 🚀

One question though, couldn't we adjust the test to use usize::MAX and have one thing that works regardless of the target pointer width?

I'll approve the thing anyway 😅

[Jakuje]

One question though, couldn't we adjust the test to use usize::MAX and have one thing that works regardless of the target pointer width?

Good idea! Its always better to fix the test than skip it. I will adjust it. I was probably too focused on fixing the CI, rather than fixing the tests.

[Jakuje]

One question though, couldn't we adjust the test to use usize::MAX and have one thing that works regardless of the target pointer width?

Good idea! Its always better to fix the test than skip it. I will adjust it. I was probably too focused on fixing the CI, rather than fixing the tests.

Actually the value 4294967295 is u32::MAX-1.

But actually this already fails non-gracefully in the test itself if changed to this value, as it looks like the max vector capacity is different on the 32b arch rust:

---- gcm_param_graceful_failure stdout ----

thread 'gcm_param_graceful_failure' panicked at cryptoki/tests/basic.rs:1865:18:
capacity overflow

So yes, I can probably try to find the vector capacity, but this would be already different test. This test tries this input specially made for the specs (commented in the code)

rust-cryptoki/cryptoki/src/mechanism/aead.rs

Lines 47 to 49 in 83790f2

	// Further, in v3.0, the IV is permitted to be up to 2^32-1 bytes,
	// which would cause ulIvBits to overflow on platforms where
	// sizeof(CK_ULONG) = 4.

So reverting back my first comment. Its probably best to skip it on 32b arch in the end.

Good to get merged.

[wiktor-k]

Oh yes, definitely. Sorry to send you on such a rabbit chase I thought it will be "just a simple fix" 😉

Merging, thanks for your work! 🙇