From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 2172 invoked by alias); 26 Oct 2010 07:51:13 -0000 Received: (qmail 2162 invoked by uid 22791); 26 Oct 2010 07:51:12 -0000 X-SWARE-Spam-Status: No, hits=-2.2 required=5.0 tests=ALL_TRUSTED,AWL,BAYES_00,MISSING_MID X-Spam-Check-By: sourceware.org Received: from localhost (HELO sourceware.org) (127.0.0.1) by sourceware.org (qpsmtpd/0.43rc1) with ESMTP; Tue, 26 Oct 2010 07:51:11 +0000 From: "viriketo at gmail dot com" To: glibc-bugs@sources.redhat.com Subject: [Bug libc/12123] SIGBUS on strstr_sse42 due to bad alignment X-Bugzilla-Reason: CC X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: glibc X-Bugzilla-Component: libc X-Bugzilla-Keywords: X-Bugzilla-Severity: normal X-Bugzilla-Who: viriketo at gmail dot com X-Bugzilla-Status: WAITING X-Bugzilla-Priority: P2 X-Bugzilla-Assigned-To: drepper.fsp at gmail dot com X-Bugzilla-Target-Milestone: --- X-Bugzilla-Changed-Fields: In-Reply-To: References: X-Bugzilla-URL: http://sourceware.org/bugzilla/ Auto-Submitted: auto-generated Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Date: Tue, 26 Oct 2010 07:51:00 -0000 Mailing-List: contact glibc-bugs-help@sourceware.org; run by ezmlm Precedence: bulk List-Id: List-Subscribe: List-Post: List-Help: , Sender: glibc-bugs-owner@sourceware.org X-SW-Source: 2010-10/txt/msg00153.txt.bz2 Message-ID: <20101026075100.8mZ5YPQGkDYRY7vaRw_ge-SN5pr5uwIH07rFbNrRiOk@z> http://sourceware.org/bugzilla/show_bug.cgi?id=3D12123 --- Comment #5 from Llu=C3=ADs 2010-10-26 07:50= :57 UTC --- Sorry, but I don't think the problem is in the strstr file. As the traces show, the code in strstr is properly compiled and looks good. Simply gcc assumed at the start of the function the code will be stack-alig= ned. Before main() in C programs, the libc assures that the stack is aligned. And gcc assures that no function misaligns the stack. But the problem I mention happens in a strstr() call *BEFORE* main(), in the dynamic loader, where the stack may not be aligned. And then, any SIMD code compiled by gcc will fail, because the assumption of aligned stack looks li= ke not being true at that moment. I think this problem is more of the dynamic loader, which should assure an aligned stack before calling anything like strstr(). --=20 Configure bugmail: http://sourceware.org/bugzilla/userprefs.cgi?tab=3Demail ------- You are receiving this mail because: ------- You are on the CC list for the bug.