linux-kernel - Re: [PATCH] leds: trigger: Fix sleeping function called from invalid context

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] [day] [month] [year] [list]

Message-ID: <3233e3af-bd33-e719-7252-59d92a8da2b1@gmail.com>
Date:   Wed, 7 Nov 2018 21:45:26 +0100
From:   Jacek Anaszewski <jacek.anaszewski@...il.com>
To:     Geert Uytterhoeven <geert@...ux-m68k.org>,
        Baolin Wang <baolin.wang@...aro.org>
Cc:     Pavel Machek <pavel@....cz>, rteysseyre@...il.com,
        Mark Brown <broonie@...nel.org>, linux-leds@...r.kernel.org,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] leds: trigger: Fix sleeping function called from invalid
 context

Hi Baolin and Geert,

Geert - thanks for the heads-up.

Baolin - thanks for the quick fix.

Applied to the fixes-for-4.20-rc2 branch of linux-leds.git

Best regards,
Jacek Anaszewski

On 11/07/2018 08:59 AM, Geert Uytterhoeven wrote:
> Hi Baolin,
> 
> On Wed, Nov 7, 2018 at 6:43 AM Baolin Wang <baolin.wang@...aro.org> wrote:
>> We will meet below issue due to mutex_lock() is called in interrupt context.
>> The mutex lock is used to protect the pattern trigger data, but before changing
>> new pattern trigger data (pattern values or repeat value) by users, we always
>> cancel the timer firstly to clear previous patterns' performance. That means
>> there is no race in pattern_trig_timer_function(), so we can drop the mutex
>> lock in pattern_trig_timer_function() to avoid this issue.
>>
>> Moreover we can move the timer cancelling into mutex protection, since there
>> is no deadlock risk if we remove the mutex lock in pattern_trig_timer_function().
>>
>> BUG: sleeping function called from invalid context at kernel/locking/mutex.c:254
>> in_atomic(): 1, irqs_disabled(): 0, pid: 0, name: swapper/1
>> CPU: 1 PID: 0 Comm: swapper/1 Not tainted
>> 4.20.0-rc1-koelsch-00841-ga338c8181013c1a9 #171
>> Hardware name: Generic R-Car Gen2 (Flattened Device Tree)
>> [<c020f19c>] (unwind_backtrace) from [<c020aecc>] (show_stack+0x10/0x14)
>> [<c020aecc>] (show_stack) from [<c07affb8>] (dump_stack+0x7c/0x9c)
>> [<c07affb8>] (dump_stack) from [<c02417d4>] (___might_sleep+0xf4/0x158)
>> [<c02417d4>] (___might_sleep) from [<c07c92c4>] (mutex_lock+0x18/0x60)
>> [<c07c92c4>] (mutex_lock) from [<c067b28c>] (pattern_trig_timer_function+0x1c/0x11c)
>> [<c067b28c>] (pattern_trig_timer_function) from [<c027f6fc>] (call_timer_fn+0x1c/0x90)
>> [<c027f6fc>] (call_timer_fn) from [<c027f944>] (expire_timers+0x94/0xa4)
>> [<c027f944>] (expire_timers) from [<c027fc98>] (run_timer_softirq+0x108/0x15c)
>> [<c027fc98>] (run_timer_softirq) from [<c02021cc>] (__do_softirq+0x1d4/0x258)
>> [<c02021cc>] (__do_softirq) from [<c0224d24>] (irq_exit+0x64/0xc4)
>> [<c0224d24>] (irq_exit) from [<c0268dd0>] (__handle_domain_irq+0x80/0xb4)
>> [<c0268dd0>] (__handle_domain_irq) from [<c045e1b0>] (gic_handle_irq+0x58/0x90)
>> [<c045e1b0>] (gic_handle_irq) from [<c02019f8>] (__irq_svc+0x58/0x74)
>> Exception stack(0xeb483f60 to 0xeb483fa8)
>> 3f60: 00000000 00000000 eb9afaa0 c0217e80 00000000 ffffe000 00000000 c0e06408
>> 3f80: 00000002 c0e0647c c0c6a5f0 00000000 c0e04900 eb483fb0 c0207ea8 c0207e98
>> 3fa0: 60020013 ffffffff
>> [<c02019f8>] (__irq_svc) from [<c0207e98>] (arch_cpu_idle+0x1c/0x38)
>> [<c0207e98>] (arch_cpu_idle) from [<c0247ca8>] (do_idle+0x138/0x268)
>> [<c0247ca8>] (do_idle) from [<c0248050>] (cpu_startup_entry+0x18/0x1c)
>> [<c0248050>] (cpu_startup_entry) from [<402022ec>] (0x402022ec)
>>
>> Fixes: 5fd752b6b3a2 ("leds: core: Introduce LED pattern trigger")
>> Reported-by: Geert Uytterhoeven <geert@...ux-m68k.org>
>> Signed-off-by: Baolin Wang <baolin.wang@...aro.org>
> 
> Thanks!
> 
> Tested-by: Geert Uytterhoeven <geert+renesas@...der.be>
> 
> Gr{oetje,eeting}s,
> 
>                         Geert
>