From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 48) id D17EE385043E; Mon, 30 May 2022 16:15:27 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org D17EE385043E From: "gprocida at google dot com" To: libabigail@sourceware.org Subject: [Bug default/29044] abidiff reporter inconsistency Date: Mon, 30 May 2022 16:15:27 +0000 X-Bugzilla-Reason: CC X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: libabigail X-Bugzilla-Component: default X-Bugzilla-Version: unspecified X-Bugzilla-Keywords: X-Bugzilla-Severity: normal X-Bugzilla-Who: gprocida at google dot com X-Bugzilla-Status: UNCONFIRMED X-Bugzilla-Resolution: X-Bugzilla-Priority: P2 X-Bugzilla-Assigned-To: dodji at redhat dot com X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Bugzilla-URL: http://sourceware.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: libabigail@sourceware.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Mailing list of the Libabigail project List-Unsubscribe: , List-Archive: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 30 May 2022 16:15:27 -0000 https://sourceware.org/bugzilla/show_bug.cgi?id=3D29044 --- 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 XM= L, a symbol list was passed and hash-based type ids were requested. abitidy (whi= ch 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 There is a small chance outdated tools were used.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 kern= el 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 result= ed 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 a= bidw (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. --=20 You are receiving this mail because: You are on the CC list for the bug.=