linux-kernel - Re: [PATCH 0/9] sched: Migrate disable support

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

Message-ID: <20200925181727.ryuacrsipyaz65z7@linutronix.de>
Date:   Fri, 25 Sep 2020 20:17:27 +0200
From:   Sebastian Andrzej Siewior <bigeasy@...utronix.de>
To:     Peter Zijlstra <peterz@...radead.org>
Cc:     tglx@...utronix.de, mingo@...nel.org, linux-kernel@...r.kernel.org,
        qais.yousef@....com, swood@...hat.com, valentin.schneider@....com,
        juri.lelli@...hat.com, vincent.guittot@...aro.org,
        dietmar.eggemann@....com, rostedt@...dmis.org, bsegall@...gle.com,
        mgorman@...e.de, bristot@...hat.com, vincent.donnefort@....com
Subject: Re: [PATCH 0/9] sched: Migrate disable support

On 2020-09-21 18:35:57 [+0200], Peter Zijlstra wrote:
> Hi,
Hi,

> Here's my take on migrate_disable(). It avoids growing a second means of

I have here:

|005: numa_remove_cpu cpu 5 node 0: mask now 0,3-4,6-7
|007: smpboot: CPU 5 is now offline
|006: ------------[ cut here ]------------
|006: rq->balance_callback
|006: WARNING: CPU: 6 PID: 8392 at kernel/sched/sched.h:1234 try_to_wake_up+0x696/0x860
|006: Modules linked in:
|006:
|006: CPU: 6 PID: 8392 Comm: hackbench Not tainted 5.9.0-rc6-rt9+ #60
|006: Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.14.0-1 04/01/2014
|006: RIP: 0010:try_to_wake_up+0x696/0x860
|006: Code: c0 01 00 00 01 e9 d9 fb ff ff 80 3d 90 ef 6d 01 00 0f 85 6c fb ff ff 48 c7 c7 d4 4a 2c 82 c6 05 7c ef 6d 01 01 e8 dd 21 fc ff <0f> 0b e9 52 fb ff ff 0f 0b e9 b2
|006: RSP: 0018:ffffc90005b978f8 EFLAGS: 00010082
|006:
|006: RAX: 0000000000000000 RBX: ffff8882755cca40 RCX: 0000000000000000
|006: RDX: ffffffff8247aab8 RSI: 00000000ffffffff RDI: 00000000ffffffff
|006: RBP: 0000000000000000 R08: 0000000000000001 R09: ffffffff8247a9a0
|006: R10: ffffc90005b97838 R11: 332e39313320205b R12: ffff888276da8600
|006: R13: 0000000000000093 R14: ffff8882755cd7a0 R15: ffff888276da8618
|006: FS:  00007f6fa7805740(0000) GS:ffff888276d80000(0000) knlGS:0000000000000000
|006: CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
|006: CR2: 00007f6fa796af90 CR3: 0000000262588000 CR4: 00000000003506e0
|006: Call Trace:
|006:  ? cpu_stop_queue_work+0x8e/0x150
|006:  __wake_up_q+0x96/0xc0
|006:  cpu_stop_queue_work+0x9a/0x150
|006:  finish_task_switch.isra.0+0x2f1/0x460
|006:  __schedule+0x3bd/0xb20
|006:  schedule+0x4a/0x100
|006:  schedule_hrtimeout_range_clock+0x14f/0x160
|006:  ? rt_spin_unlock+0x39/0x90
|006:  ? rt_mutex_futex_unlock+0xcb/0xe0
|006:  poll_schedule_timeout.constprop.0+0x4d/0x90
|006:  do_sys_poll+0x314/0x430
|006:  ? __lock_acquire+0x39b/0x2010
|006:  ? poll_schedule_timeout.constprop.0+0x90/0x90
|006:  ? mark_held_locks+0x49/0x70
|006:  ? find_held_lock+0x2b/0x80
|006:  ? rt_spin_unlock+0x39/0x90
|006:  ? rt_mutex_futex_unlock+0xcb/0xe0
|006:  ? rt_spin_unlock+0x51/0x90
|006:  ? handle_mm_fault+0xfbd/0x1510
|006:  ? find_held_lock+0x2b/0x80
|006:  ? do_user_addr_fault+0x214/0x420
|006:  __x64_sys_poll+0x37/0x130
|006:  do_syscall_64+0x33/0x40
|006:  entry_SYSCALL_64_after_hwframe+0x44/0xa9
|006: RIP: 0033:0x7f6fa78fb483

Is this somewhere among the fixes Valentin received?
This SCHED_WARN_ON(rq->balance_callback); in rq_pin_lock().

Sebastian