linux-kernel - Re: [PATCH] sched: fix rq lock recursion issue

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]

Date:   Tue, 5 Jul 2022 20:44:09 -0700
From:   Satya Durga Srinivasu Prabhala <quic_satyap@...cinc.com>
To:     Steven Rostedt <rostedt@...dmis.org>
CC:     <mingo@...hat.com>, <peterz@...radead.org>,
        <juri.lelli@...hat.com>, <vincent.guittot@...aro.org>,
        <dietmar.eggemann@....com>, <bsegall@...gle.com>,
        <mgorman@...e.de>, <bristot@...hat.com>, <vschneid@...hat.com>,
        <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] sched: fix rq lock recursion issue


On 7/1/22 8:54 AM, Steven Rostedt wrote:
> On Thu, 30 Jun 2022 18:37:04 -0400
> Steven Rostedt <rostedt@...dmis.org> wrote:
>
>>> Fix the issue by switching to preempt_enable/disable() for non-RT
>>> Kernels.
>>>
>>> -010 |spin_bug(lock = ???, msg = ???)
>>> -011 |debug_spin_lock_before(inline)
>>> -011 |do_raw_spin_lock(lock = 0xFFFFFF89323BB600)
>>> -012 |_raw_spin_lock(inline)
>>> -012 |raw_spin_rq_lock_nested(inline)
>>> -012 |raw_spin_rq_lock(inline)
>>> -012 |task_rq_lock(p = 0xFFFFFF88CFF1DA00, rf = 0xFFFFFFC03707BBE8)
>>> -013 |__set_cpus_allowed_ptr(inline)
>>> -013 |migrate_enable()
>>> -014 |trace_call_bpf(call = ?, ctx = 0xFFFFFFFDEF954600)
>>> -015 |perf_trace_run_bpf_submit(inline)
>>> -015 |perf_trace_sched_switch(__data = 0xFFFFFFE82CF0BCB8, preempt = FALSE, prev = ?, next = ?)
>>> -016 |__traceiter_sched_switch(inline)
>>> -016 |trace_sched_switch(inline)
>> trace_sched_switch() disables preemption.
>>
>> So how is this a fix?
> Let me rephrase my question.
>
> As trace_sched_switch() disables preemption, why is trace_call_bpf()
> calling migrate_disable()?
I'm not sure, why we have migrate_disable/enable(). I will need to cross
check further.

>
> Looks like you could modify the code to include a __bpf_prog_run_array()
> that skips the migrate_disable(). You even have a "cant_sleep()" call in
> trace_call_bpf().
Thanks for the inputs. I still need to cross check and find a better way 
to repro
the issue to be able to comment further. Will cross check on your 
suggestion.

>
> -- Steve