Re: [RFC patch v3 08/20] sched: Set up LLC indexing

[Shrikanth Hegde <sshegde@linux.ibm.com>]

On 6/18/25 23:57, Tim Chen wrote:
> Prepare for indexing arrays that track in each run queue: the number
> of tasks preferring current LLC and each of the other LLC.
> 
> The reason to introduce LLC index is because the per LLC-scope data
> is needed to do cache aware load balancing. However, the native lld_id
> is usually the first CPU of that LLC domain, which is not continuous,
> which might waste the space if the per LLC-scope data is stored
> in an array (in current implementation).
> 
> In the future, this LLC index could be removed after
> the native llc_id is used as the key to search into xarray based
> array.
> 
> Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
> ---
>   include/linux/sched.h   |  3 +++
>   kernel/sched/fair.c     | 12 ++++++++++++
>   kernel/sched/sched.h    |  2 ++
>   kernel/sched/topology.c | 29 +++++++++++++++++++++++++++++
>   4 files changed, 46 insertions(+)
> 
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index d0e4cda2b3cd..7ce95a32e9ff 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -810,6 +810,9 @@ struct kmap_ctrl {
>   #endif
>   };
>   
> +/* XXX need fix to not use magic number */
> +#define MAX_LLC 64

This number needs to be much higher. maybe keeping NR_CPUS wont hurt.

> +
>   struct task_struct {
>   #ifdef CONFIG_THREAD_INFO_IN_TASK
>   	/*
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 10ea408d0e40..5549710d95cf 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -1183,6 +1183,18 @@ static int llc_id(int cpu)
>   	return per_cpu(sd_llc_id, cpu);
>   }
>   
> +/*
> + * continous index.
> + * TBD: replace by xarray with key llc_id()
> + */
> +static inline int llc_idx(int cpu)
> +{
> +	if (cpu < 0)
> +		return -1;
> +
> +	return per_cpu(sd_llc_idx, cpu);
> +}
> +
>   void mm_init_sched(struct mm_struct *mm, struct mm_sched __percpu *_pcpu_sched)
>   {
>   	unsigned long epoch;
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index 1c6fd45c7f62..74eb2f3615aa 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -2037,6 +2037,7 @@ static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
>   DECLARE_PER_CPU(struct sched_domain __rcu *, sd_llc);
>   DECLARE_PER_CPU(int, sd_llc_size);
>   DECLARE_PER_CPU(int, sd_llc_id);
> +DECLARE_PER_CPU(int, sd_llc_idx);
>   DECLARE_PER_CPU(int, sd_share_id);
>   DECLARE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
>   DECLARE_PER_CPU(struct sched_domain __rcu *, sd_numa);
> @@ -2045,6 +2046,7 @@ DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
>   
>   extern struct static_key_false sched_asym_cpucapacity;
>   extern struct static_key_false sched_cluster_active;
> +extern int max_llcs;
>   
>   static __always_inline bool sched_asym_cpucap_active(void)
>   {
> diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
> index f1ebc60d967f..b7bb13045dd8 100644
> --- a/kernel/sched/topology.c
> +++ b/kernel/sched/topology.c
> @@ -672,6 +672,7 @@ static void destroy_sched_domains(struct sched_domain *sd)
>   DEFINE_PER_CPU(struct sched_domain __rcu *, sd_llc);
>   DEFINE_PER_CPU(int, sd_llc_size);
>   DEFINE_PER_CPU(int, sd_llc_id);
> +DEFINE_PER_CPU(int, sd_llc_idx);
>   DEFINE_PER_CPU(int, sd_share_id);
>   DEFINE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
>   DEFINE_PER_CPU(struct sched_domain __rcu *, sd_numa);
> @@ -681,6 +682,25 @@ DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
>   DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
>   DEFINE_STATIC_KEY_FALSE(sched_cluster_active);
>   
> +int max_llcs = -1;
> +
> +static void update_llc_idx(int cpu)
> +{
> +#ifdef CONFIG_SCHED_CACHE
> +	int idx = -1, llc_id = -1;
> +
> +	llc_id = per_cpu(sd_llc_id, cpu);
> +	idx = per_cpu(sd_llc_idx, llc_id);
> +
> +	if (idx < 0) {
> +		idx = max_llcs++;
> +		BUG_ON(idx > MAX_LLC); 

maybe a warning instead here?

> +		per_cpu(sd_llc_idx, llc_id) = idx;
> +	}
> +	per_cpu(sd_llc_idx, cpu) = idx;
> +#endif
> +}
> +
>   static void update_top_cache_domain(int cpu)
>   {
>   	struct sched_domain_shared *sds = NULL;
> @@ -699,6 +719,7 @@ static void update_top_cache_domain(int cpu)
>   	per_cpu(sd_llc_size, cpu) = size;
>   	per_cpu(sd_llc_id, cpu) = id;
>   	rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds);
> +	update_llc_idx(cpu);
>   
>   	sd = lowest_flag_domain(cpu, SD_CLUSTER);
>   	if (sd)
> @@ -2394,6 +2415,14 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
>   	bool has_asym = false;
>   	bool has_cluster = false;
>   
> +#ifdef CONFIG_SCHED_CACHE
> +	if (max_llcs < 0) {
> +		for_each_possible_cpu(i)
> +			per_cpu(sd_llc_idx, i) = -1;
> +		max_llcs = 0;
> +	}
> +#endif
> +
>   	if (WARN_ON(cpumask_empty(cpu_map)))
>   		goto error;
>