Re: [PATCH v2 20/23] sched/cache: Add user control to adjust the parameters of cache-aware scheduling

[Chen, Yu C]

Hi Yangyu,

On 1/21/2026 11:21 PM, Yangyu Chen wrote:
> On 4/12/2025 07:07, Tim Chen wrote:

[ ... ]

> > +    scale = get_sched_cache_scale(256);
>
> Hi Tim Chen and Chen Yu,
>
> There's an integer overflow here. Since the unit of LLC size is bytes, 
> you have a 256-scale unit. For a typical LLC size of 32M, you calculate 
> 32M multiplied by 256, which equals 8GB. This value exceeds the maximum 
> integer value (2GB, INT_MAX), resulting in an integer overflow.
>
> I think such function should be use u64. Below is my patch:

Thanks very much for the investigation, Jianyong previously also
mentioned this issue
https://lore.kernel.org/all/SI2PR04MB49317BA503E9C8A381956D6AE38CA@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx/
we will fix the issue accordingly.


> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 205208f061bb..bcafb3c2b369 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -1226,20 +1226,20 @@ static int llc_id(int cpu)
>       return llc;
>   }
>
> -static inline int get_sched_cache_scale(int mul)
> +static inline u64 get_sched_cache_scale(int mul)
>   {
>       if (!llc_aggr_tolerance)
>           return 0;
>
>       if (llc_aggr_tolerance == 100)
> -        return INT_MAX;
> +        return ULLONG_MAX;
>
>       return (1 + (llc_aggr_tolerance - 1) * mul);
>   }
>
>   static bool exceed_llc_capacity(struct mm_struct *mm, int cpu)
>   {
> -    unsigned int llc, scale;
> +    unsigned long long llc, scale;

I suppose we only need to change llc to u64, and not change
scale, because (llc * scale) would be converted to u64 anyway.

thanks,
Chenyu