From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754704Ab3LJPrh (ORCPT ); Tue, 10 Dec 2013 10:47:37 -0500 Received: from mx1.redhat.com ([209.132.183.28]:23147 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751929Ab3LJPrd (ORCPT ); Tue, 10 Dec 2013 10:47:33 -0500 Date: Tue, 10 Dec 2013 10:47:24 -0500 From: Dave Jones To: Linus Torvalds Cc: Linux Kernel Subject: process 'stuck' at exit. Message-ID: <20131210154724.GA30020@redhat.com> Mail-Followup-To: Dave Jones , Linus Torvalds , Linux Kernel MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org I woke up to find my fuzzer in a curious state. 1121 pts/5 SN+ 0:00 | \_ ../trinity -q -l off -N 999999 -C 42 1130 pts/5 SN+ 0:01 | \_ ../trinity -q -l off -N 999999 -C 42 1131 pts/5 SN+ 0:17 | \_ ../trinity -q -l off -N 999999 -C 42 10818 ? RNs 21115152:53 | \_ ../trinity -q -l off -N 999999 -C 42 (ignore the first 3 pids, they're waiting on 10818, which is the interesting one) It's completed its run of 999999 syscalls, and looking at tmux, it tried to exit. /proc/10818/stack just shows [] 0xffffffffffffffff Top reports a core is spinning in the kernel 100%, so I ran perf top -a and saw.. 8.63% [kernel] [k] trace_hardirqs_off_caller 7.68% [kernel] [k] __lock_acquire 5.35% [kernel] [k] gup_huge_pmd 5.31% [kernel] [k] put_compound_page 4.93% [kernel] [k] gup_pud_range 4.76% [kernel] [k] trace_hardirqs_on_caller 4.58% [kernel] [k] get_user_pages_fast 4.00% [kernel] [k] debug_smp_processor_id 4.00% [kernel] [k] lock_is_held 3.73% [kernel] [k] lock_acquired 3.67% [kernel] [k] lock_release sysrq-t shows.. trinity-child27 R running task 5520 10818 1131 0x00080004 0000000000000000 ffff8801b0ef4170 000000000000032c ffff8801b609e108 0000000000000000 ffff880160d21c30 ffffffff810ad895 ffffffff817587a0 ffff8801b0ef4170 ffff8801b609e0a8 ffff8801b609e000 ffff880160d21d50 Call Trace: [] ? retint_restore_args+0xe/0xe [] ? trace_hardirqs_on_thunk+0x3a/0x3f [] ? native_sched_clock+0x24/0x80 [] ? local_clock+0xf/0x50 [] ? put_lock_stats.isra.28+0xe/0x30 [] ? gup_pud_range+0x170/0x190 [] ? get_user_pages_fast+0x1a5/0x1c0 [] ? trace_hardirqs_on_caller+0x115/0x1e0 [] ? up_read+0x1f/0x40 [] ? get_user_pages_fast+0x1a5/0x1c0 [] ? put_page+0x3c/0x50 [] ? get_futex_key+0xd5/0x2c0 [] ? futex_requeue+0xfa/0x9c0 [] ? do_futex+0xae/0xc80 [] ? put_lock_stats.isra.28+0xe/0x30 [] ? lock_release_holdtime.part.29+0xee/0x170 [] ? context_tracking_user_exit+0x4e/0x190 [] ? trace_hardirqs_on_caller+0x115/0x1e0 [] ? SyS_futex+0x71/0x150 [] ? syscall_trace_enter+0x145/0x2a0 [] ? tracesys+0xdd/0xe2 any ideas ? Dave