[v1] clocksource/drivers/timer-ti-dm: fix child node refcount handling

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

Posted by Javier Carrasco 1 month, 2 weeks ago

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@vger.kernel.org
Fixes: 25de4ce5ed02 ("clocksource/drivers/timer-ti-dm: Handle dra7 timer wrap errata i940")
Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.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);
 
 	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,
-- 
Javier Carrasco <javier.carrasco.cruz@gmail.com>

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

Posted by Daniel Lezcano 4 weeks, 1 day ago

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@vger.kernel.org
> Fixes: 25de4ce5ed02 ("clocksource/drivers/timer-ti-dm: Handle dra7 timer wrap errata i940")
> Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.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,


-- 
<http://www.linaro.org/> Linaro.org │ Open source software for ARM SoCs

Follow Linaro:  <http://www.facebook.com/pages/Linaro> Facebook |
<http://twitter.com/#!/linaroorg> Twitter |
<http://www.linaro.org/linaro-blog/> Blog

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

Posted by Javier Carrasco 4 weeks, 1 day ago

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@vger.kernel.org
>> Fixes: 25de4ce5ed02 ("clocksource/drivers/timer-ti-dm: Handle dra7
>> timer wrap errata i940")
>> Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.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

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

Posted by Daniel Lezcano 4 weeks, 1 day ago

On 28/10/2024 13:26, Javier Carrasco wrote:

[ ... ]

> 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.

V2 with __free is fine



-- 
<http://www.linaro.org/> Linaro.org │ Open source software for ARM SoCs

Follow Linaro:  <http://www.facebook.com/pages/Linaro> Facebook |
<http://twitter.com/#!/linaroorg> Twitter |
<http://www.linaro.org/linaro-blog/> Blog