[Bug default/29044] abidiff reporter inconsistency

["gprocida at google dot com" <sourceware-bugzilla@sourceware.org>]

https://sourceware.org/bugzilla/show_bug.cgi?id=29044

--- Comment #2 from gprocida at google dot com ---
Hi.

Here's (roughly) how each XML was created.

An external developer built a kernel some time previously. abidw (likely our
version with some changes dating back to January) was used to create the XML, a
symbol list was passed and hash-based type ids were requested. abitidy (which
has not seen much recent development) post-processed this. There is a small
chance outdated tools were used. The resulting XML was committed to an AOSP
kernel branch.

A pending change (less than a week later) reached presubmit tests. The kernel
was built in a standardised environment. abidw extracted, abitidy tidied,
abidiff diffed. Both abidiff and abidiff --leaf-changes-only were run in
parallel and this is how we spotted the discrepancy. The symbol list resulted
in a 10M ABI file vs a 19M ABI file without it.

I can provide you with the second kernel. I may even be able to provide you
with the abidw, abitidy and abidiff command lines and corresponding source
commits. Bear in mind that everything would have been built with Clang.

I cannot provide you with the first kernel as we never had it. I could try to
reproduce the XML from first principles though and if I get a match provide you
with the kernel.

It will be a fair amount of work to collect all the information and files.
Perhaps I should try to reproduce the first XML file and go from there.
However, if you are not happy working with Clang or abitidy (which I can
understand), then it may not be worth the effort.

Just in case this is relevant: I've noticed that passing a symbol list to abidw
(which uses the existing symbol suppression mechanisms) results in fewer
fully-defined types in the ABI than just editing the XML output to remove
unwanted symbols. I'm tempted to open another bug. However, I'd definitely need
to send you a large vmlinux file.

Let me know if you'd like me to proceed with data gathering.

Regards,
Giuliano.

-- 
You are receiving this mail because:
You are on the CC list for the bug.