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