linux-kernel - Re: [PATCH] clocksource/drivers/timer-ti-dm: fix child node refcount handling

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: <e7ca7a5d-749d-40c1-893f-da3d593eb4d4@gmail.com>
Date: Mon, 28 Oct 2024 13:26:43 +0100
From: Javier Carrasco <javier.carrasco.cruz@...il.com>
To: Daniel Lezcano <daniel.lezcano@...aro.org>,
 Thomas Gleixner <tglx@...utronix.de>, Tony Lindgren <tony@...mide.com>
Cc: linux-kernel@...r.kernel.org, stable@...r.kernel.org
Subject: Re: [PATCH] clocksource/drivers/timer-ti-dm: fix child node refcount
 handling

On 28/10/2024 12:24, Daniel Lezcano wrote:
> 
> Hi Javier,
> 
> thanks for spotting the issue
> 
> 
> On 13/10/2024 12:14, Javier Carrasco wrote:
>> of_find_compatible_node() increments the node's refcount, and it must be
>> decremented again with a call to of_node_put() when the pointer is no
>> longer required to avoid leaking memory.
>>
>> Add the missing calls to of_node_put() in dmtimer_percpu_quirck_init()
>> for the 'arm_timer' device node.
>>
>> Cc: stable@...r.kernel.org
>> Fixes: 25de4ce5ed02 ("clocksource/drivers/timer-ti-dm: Handle dra7
>> timer wrap errata i940")
>> Signed-off-by: Javier Carrasco <javier.carrasco.cruz@...il.com>
>> ---
>>   drivers/clocksource/timer-ti-dm-systimer.c | 2 ++
>>   1 file changed, 2 insertions(+)
>>
>> diff --git a/drivers/clocksource/timer-ti-dm-systimer.c b/drivers/
>> clocksource/timer-ti-dm-systimer.c
>> index c2dcd8d68e45..23be1d21ce21 100644
>> --- a/drivers/clocksource/timer-ti-dm-systimer.c
>> +++ b/drivers/clocksource/timer-ti-dm-systimer.c
>> @@ -691,8 +691,10 @@ static int __init
>> dmtimer_percpu_quirk_init(struct device_node *np, u32 pa)
>>       arm_timer = of_find_compatible_node(NULL, NULL, "arm,armv7-timer");
>>       if (of_device_is_available(arm_timer)) {
>>           pr_warn_once("ARM architected timer wrap issue i940
>> detected\n");
>> +        of_node_put(arm_timer);
>>           return 0;
>>       }
>> +    of_node_put(arm_timer);
> 
> Best practice would be to group of_node_put into a single place.
> 
>     bool available;
> 
>     [ ... ]
> 
>     available = of_device_is_available(arm_timer);
>     of_node_put(arm_timer);
> 
>     if (available) {
>         pr_warn_once("ARM architected timer wrap issue i940 detected\n");
>         return 0;
>     }
> 
> 
>>       if (pa == 0x4882c000)           /* dra7 dmtimer15 */
>>           return dmtimer_percpu_timer_init(np, 0);
>>
>> ---
>> base-commit: d61a00525464bfc5fe92c6ad713350988e492b88
>> change-id: 20241013-timer-ti-dm-systimer-of_node_put-d42735687698
>>
>> Best regards,
> 
> 

Hi Daniel, thanks for your feedback.

Actually, if we are going to refactor the code, we would not need the
extra variable or even the call to of_node_put(), since we could use the
__free() macro. That would be a second patch after the fix, which could
stay as it is without refactoring, because it is only to backport the
missing calls to of_node_put().

I can send a v2 with the extra patch leaving this one as it is, or if
really desired, with the available variable.


Best regards,
Javier Carrasco