linux-kernel - Warning splat on x86

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [day] [month] [year] [list]

Message-ID: <20180810184740.5f8ca46d@gandalf.local.home>
Date:   Fri, 10 Aug 2018 18:47:40 -0400
From:   Steven Rostedt <rostedt@...dmis.org>
To:     LKML <linux-kernel@...r.kernel.org>
Cc:     Peter Zijlstra <peterz@...radead.org>,
        "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>,
        Joel Fernandes <joel@...lfernandes.org>,
        Ingo Molnar <mingo@...nel.org>
Subject: Warning splat on x86_32 during perf stress


I sometimes trigger this splat in my tests (which cause them to fail),
but it's not always hit. Note, this is on x86_32 arch.

------------[ cut here ]------------
IRQs not enabled as expected
WARNING: CPU: 0 PID: 0 at /work/build/trace/nobackup/linux-test.git/kernel/time/tick-sched.c:982 tick_nohz_idle_enter+0x44/0x8c
Modules linked in: ip6t_REJECT nf_reject_ipv6 nf_conntrack_ipv6 nf_defrag_ipv6 ip6table_filter ip6_tables ipv6 crc_ccitt r8169 ppdev parport_pc parport
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.18.0-rc6-test+ #3
Hardware name: MSI MS-7823/CSM-H87M-G43 (MS-7823), BIOS V1.6 02/22/2014
EIP: tick_nohz_idle_enter+0x44/0x8c
Code: e8 05 00 00 00 75 26 83 b8 bc 05 00 00 00 75 1d 80 3d 81 f7 3c c1 00 75 14 68 d6 82 11 c1 c6 05 81 f7 3c c1 01 e8 63 fb f8 ff <0f> 0b 58 fa bb 60 76 65 c1 e8 0d 04 04 00 64 03 1d 28 c1 50 c1 8b
EAX: 0000001c EBX: c14803a0 ECX: 00000006 EDX: 00000007
perf: interrupt took too long (12533 > 12527), lowering kernel.perf_event_max_sample_rate to 15000
ESI: c12b8d00 EDI: 01470000 EBP: c12a5f30 ESP: c12a5f28
DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010292
CR0: 80050033 CR2: 080a45b0 CR3: 3075b600 CR4: 001406f0
Call Trace:
 do_idle+0x33/0x1f9
 cpu_startup_entry+0x61/0x63
 rest_init+0xb2/0xb4
 start_kernel+0x3fa/0x410
 i386_start_kernel+0x9a/0x9e
 startup_32_smp+0x164/0x168
irq event stamp: 8712154
hardirqs last  enabled at (8712153): [<c04014f9>] trace_hardirqs_on_thunk+0xc/0x10
hardirqs last disabled at (8712154): [<c0401509>] trace_hardirqs_off_thunk+0xc/0x10
softirqs last  enabled at (8712148): [<c0dc8b60>] __do_softirq+0x258/0x2b8
softirqs last disabled at (8712107): [<c04169a9>] call_on_stack+0x45/0x4b
---[ end trace 7bebbaceab0fedbc ]---

This is where I think my patch:

  http://lkml.kernel.org/r/20180806214107.110626d0@gandalf.local.home

would help. As I don't know if IRQs were really enabled, or if lockdep
was broken.

-- Steve