Re: [PATCH 2/6] sched/fair: Attach sched_domain_shared to sd_asym_cpucapacity

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

On 4/28/26 10:46 AM, Andrea Righi wrote:
> From: K Prateek Nayak <kprateek.nayak@amd.com>
> 
> On asymmetric CPU capacity systems, the wakeup path uses
> select_idle_capacity(), which scans the span of sd_asym_cpucapacity
> rather than sd_llc.
> 
> The has_idle_cores hint however lives on sd_llc->shared, so the
> wakeup-time read of has_idle_cores operates on an LLC-scoped blob while
> the actual scan/decision spans the asym domain; nr_busy_cpus also lives
> in the same shared sched_domain data, but it's never used in the asym
> CPU capacity scenario.
> 
> Therefore, move the sched_domain_shared object to sd_asym_cpucapacity
> whenever the CPU has a SD_ASYM_CPUCAPACITY_FULL ancestor and that
> ancestor is non-overlapping (i.e., not built from SD_NUMA). In that case
> the scope of has_idle_cores matches the scope of the wakeup scan.
> 
> Fall back to attaching the shared object to sd_llc in three cases:
> 
>    1) plain symmetric systems (no SD_ASYM_CPUCAPACITY_FULL anywhere);
> 
>    2) CPUs in an exclusive cpuset that carves out a symmetric capacity
>       island: has_asym is system-wide but those CPUs have no
>       SD_ASYM_CPUCAPACITY_FULL ancestor in their hierarchy and follow
>       the symmetric LLC path in select_idle_sibling();
> 
>    3) exotic topologies where SD_ASYM_CPUCAPACITY_FULL lands on an
>       SD_NUMA-built domain. init_sched_domain_shared() keys the shared
>       blob off cpumask_first(span), which on overlapping NUMA domains
>       would alias unrelated spans onto the same blob. Keep the shared
>       object on the LLC there; select_idle_capacity() gracefully skips
>       the has_idle_cores preference when sd->shared is NULL.
> 

Can you share the example topology where this benefits?

Is SD_ASYM_CPUCAPACITY_FULL one level above LLC but below NUMA?

> While at it, also rename the per-CPU sd_llc_shared to sd_balance_shared,
> as it is no longer strictly tied to the LLC.
> 

llc scans are at wakeup's. name sd_balance_shared indicates it is for load balance.

> Co-developed-by: Andrea Righi <arighi@nvidia.com>
> Signed-off-by: Andrea Righi <arighi@nvidia.com>
> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
> ---
>   kernel/sched/fair.c     | 20 +++++----
>   kernel/sched/sched.h    |  2 +-
>   kernel/sched/topology.c | 91 +++++++++++++++++++++++++++++++++++------
>   3 files changed, 91 insertions(+), 22 deletions(-)
> 
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index fc0828150c780..ece3a26f59c27 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -7790,7 +7790,7 @@ static inline void set_idle_cores(int cpu, int val)
>   {
>   	struct sched_domain_shared *sds;
>   
> -	sds = rcu_dereference_all(per_cpu(sd_llc_shared, cpu));
> +	sds = rcu_dereference_all(per_cpu(sd_balance_shared, cpu));
>   	if (sds)
>   		WRITE_ONCE(sds->has_idle_cores, val);
>   }
> @@ -7799,7 +7799,7 @@ static inline bool test_idle_cores(int cpu)
>   {
>   	struct sched_domain_shared *sds;
>   
> -	sds = rcu_dereference_all(per_cpu(sd_llc_shared, cpu));
> +	sds = rcu_dereference_all(per_cpu(sd_balance_shared, cpu));
>   	if (sds)
>   		return READ_ONCE(sds->has_idle_cores);
>   
> @@ -7808,7 +7808,7 @@ static inline bool test_idle_cores(int cpu)
>   
>   /*
>    * Scans the local SMT mask to see if the entire core is idle, and records this
> - * information in sd_llc_shared->has_idle_cores.
> + * information in sd_balance_shared->has_idle_cores.
>    *
>    * Since SMT siblings share all cache levels, inspecting this limited remote
>    * state should be fairly cheap.
> @@ -7925,7 +7925,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
>   	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_rq_mask);
>   	int i, cpu, idle_cpu = -1, nr = INT_MAX;
>   
> -	if (sched_feat(SIS_UTIL)) {
> +	if (sched_feat(SIS_UTIL) && sd->shared) {
>   		/*
>   		 * Increment because !--nr is the condition to stop scan.
>   		 *
> @@ -12759,7 +12759,7 @@ static bool nohz_balancer_needs_kick(struct rq *rq)
>   		return false;
>   	}
>   
> -	sds = rcu_dereference_all(per_cpu(sd_llc_shared, cpu));
> +	sds = rcu_dereference_all(per_cpu(sd_balance_shared, cpu));
>   	if (sds) {
>   		/*
>   		 * If there is an imbalance between LLC domains (IOW we could
> @@ -12841,10 +12841,13 @@ static void set_cpu_sd_state_busy(int cpu)
>   	guard(rcu)();
>   	sd = rcu_dereference_all(per_cpu(sd_llc, cpu));
>   
> -	if (!sd || !sd->nohz_idle)
> +	/*
> +	 * sd->nohz_idle only pairs with nr_busy_cpus on sd->shared; if this LLC
> +	 * domain has no shared object there is nothing to clear or account.
> +	 */
> +	if (!sd || !sd->shared || !sd->nohz_idle)
>   		return;
>   	sd->nohz_idle = 0;
> -
>   	atomic_inc(&sd->shared->nr_busy_cpus);
>   }
>   
> @@ -12868,7 +12871,8 @@ static void set_cpu_sd_state_idle(int cpu)
>   	guard(rcu)();
>   	sd = rcu_dereference_all(per_cpu(sd_llc, cpu));
>   
> -	if (!sd || sd->nohz_idle)
> +	/* See set_cpu_sd_state_busy(): nohz_idle is only used with sd->shared. */
> +	if (!sd || !sd->shared || sd->nohz_idle)
>   		return;
>   	sd->nohz_idle = 1;
>   
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index 9f63b15d309d1..330f5893c4561 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -2170,7 +2170,7 @@ 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_share_id);
> -DECLARE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
> +DECLARE_PER_CPU(struct sched_domain_shared __rcu *, sd_balance_shared);
>   DECLARE_PER_CPU(struct sched_domain __rcu *, sd_numa);
>   DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
>   DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
> diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
> index 5847b83d9d552..1e6ce369a4bbc 100644
> --- a/kernel/sched/topology.c
> +++ b/kernel/sched/topology.c
> @@ -665,7 +665,7 @@ 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_share_id);
> -DEFINE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
> +DEFINE_PER_CPU(struct sched_domain_shared __rcu *, sd_balance_shared);
>   DEFINE_PER_CPU(struct sched_domain __rcu *, sd_numa);
>   DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
>   DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
> @@ -680,20 +680,39 @@ static void update_top_cache_domain(int cpu)
>   	int id = cpu;
>   	int size = 1;
>   
> +	sd = lowest_flag_domain(cpu, SD_ASYM_CPUCAPACITY_FULL);
> +	/*
> +	 * The shared object is attached to sd_asym_cpucapacity only when the
> +	 * asym domain is non-overlapping (i.e., not built from SD_NUMA).
> +	 * On overlapping (NUMA) asym domains we fall back to letting the
> +	 * SD_SHARE_LLC path own the shared object, so sd->shared may be NULL
> +	 * here.
> +	 */
> +	if (sd && sd->shared)
> +		sds = sd->shared;
> +
> +	rcu_assign_pointer(per_cpu(sd_asym_cpucapacity, cpu), sd);
> +
>   	sd = highest_flag_domain(cpu, SD_SHARE_LLC);
>   	if (sd) {
>   		id = cpumask_first(sched_domain_span(sd));
>   		size = cpumask_weight(sched_domain_span(sd));
>   
> -		/* If sd_llc exists, sd_llc_shared should exist too. */
> -		WARN_ON_ONCE(!sd->shared);
> -		sds = sd->shared;
> +		/*
> +		 * If sd_asym_cpucapacity didn't claim the shared object,
> +		 * sd_llc must have one linked.
> +		 */
> +		if (!sds) {
> +			WARN_ON_ONCE(!sd->shared);
> +			sds = sd->shared;
> +		}
>   	}
>   
>   	rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
>   	per_cpu(sd_llc_size, cpu) = size;
>   	per_cpu(sd_llc_id, cpu) = id;
> -	rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds);
> +
> +	rcu_assign_pointer(per_cpu(sd_balance_shared, cpu), sds);
>   
>   	sd = lowest_flag_domain(cpu, SD_CLUSTER);
>   	if (sd)
> @@ -711,9 +730,6 @@ static void update_top_cache_domain(int cpu)
>   
>   	sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
>   	rcu_assign_pointer(per_cpu(sd_asym_packing, cpu), sd);
> -
> -	sd = lowest_flag_domain(cpu, SD_ASYM_CPUCAPACITY_FULL);
> -	rcu_assign_pointer(per_cpu(sd_asym_cpucapacity, cpu), sd);
>   }
>   
>   /*
> @@ -2650,6 +2666,49 @@ static void adjust_numa_imbalance(struct sched_domain *sd_llc)
>   	}
>   }
>   
> +static void init_sched_domain_shared(struct s_data *d, struct sched_domain *sd)
> +{
> +	int sd_id = cpumask_first(sched_domain_span(sd));
> +
> +	sd->shared = *per_cpu_ptr(d->sds, sd_id);
> +	atomic_set(&sd->shared->nr_busy_cpus, sd->span_weight);
> +	atomic_inc(&sd->shared->ref);
> +}
> +
> +/*
> + * For asymmetric CPU capacity, attach sched_domain_shared on the innermost
> + * SD_ASYM_CPUCAPACITY_FULL ancestor of @cpu's base domain when that ancestor is
> + * not an overlapping NUMA-built domain (then LLC should claim shared).
> + *
> + * A CPU may lack any FULL ancestor (e.g., exclusive cpuset symmetric island),
> + * then LLC must claim shared instead.
> + *
> + * Note: SD_ASYM_CPUCAPACITY_FULL is only set when multiple distinct capacities
> + * exist in the domain span, so the asym domain we attach to cannot degenerate
> + * into a single-capacity group. The relevant edge cases are instead covered by
> + * the caveats above.
> + *
> + * Return true if this CPU's asym path claimed sd->shared, false otherwise.
> + */
> +static bool claim_asym_sched_domain_shared(struct s_data *d, int cpu)
> +{
> +	struct sched_domain *sd = *per_cpu_ptr(d->sd, cpu);
> +	struct sched_domain *sd_asym;
> +
> +	if (!sd)
> +		return false;
> +
> +	sd_asym = sd;
> +	while (sd_asym && !(sd_asym->flags & SD_ASYM_CPUCAPACITY_FULL))
> +		sd_asym = sd_asym->parent;
> +
> +	if (!sd_asym || (sd_asym->flags & SD_NUMA))
> +		return false;
> +
> +	init_sched_domain_shared(d, sd_asym);
> +	return true;
> +}
> +
>   /*
>    * Build sched domains for a given set of CPUs and attach the sched domains
>    * to the individual CPUs
> @@ -2708,20 +2767,26 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
>   	}
>   
>   	for_each_cpu(i, cpu_map) {
> +		bool asym_claimed = false;
> +
>   		sd = *per_cpu_ptr(d.sd, i);
>   		if (!sd)
>   			continue;
>   
> +		if (has_asym)
> +			asym_claimed = claim_asym_sched_domain_shared(&d, i);
> +
>   		/* First, find the topmost SD_SHARE_LLC domain */
>   		while (sd->parent && (sd->parent->flags & SD_SHARE_LLC))
>   			sd = sd->parent;
>   
>   		if (sd->flags & SD_SHARE_LLC) {
> -			int sd_id = cpumask_first(sched_domain_span(sd));
> -
> -			sd->shared = *per_cpu_ptr(d.sds, sd_id);
> -			atomic_set(&sd->shared->nr_busy_cpus, sd->span_weight);
> -			atomic_inc(&sd->shared->ref);
> +			/*
> +			 * Initialize the sd->shared for SD_SHARE_LLC unless
> +			 * the asym path above already claimed it.
> +			 */
> +			if (!asym_claimed)
> +				init_sched_domain_shared(&d, sd);
>   
>   			/*
>   			 * In presence of higher domains, adjust the