Re: [PATCH 27/33] sched/arm64: Move fallback task cpumask to HK_TYPE_DOMAIN

[Waiman Long <llong@redhat.com>]

On 8/29/25 11:48 AM, Frederic Weisbecker wrote:
> When none of the allowed CPUs of a task are online, it gets migrated
> to the fallback cpumask which is all the non nohz_full CPUs.
>
> However just like nohz_full CPUs, domain isolated CPUs don't want to be
> disturbed by tasks that have lost their CPU affinities.
>
> And since nohz_full rely on domain isolation to work correctly, the
> housekeeping mask of domain isolated CPUs is always a subset of the
> housekeeping mask of nohz_full CPUs (there can be CPUs that are domain
> isolated but not nohz_full, OTOH there can't be nohz_full CPUs that are
> not domain isolated):
>
> 	HK_TYPE_DOMAIN & HK_TYPE_KERNEL_NOISE == HK_TYPE_DOMAIN
>
> Therefore use HK_TYPE_DOMAIN as the appropriate fallback target for
> tasks and since this cpumask can be modified at runtime, make sure
> that 32 bits support CPUs on ARM64 mismatched systems are not isolated
> by cpusets.
>
> CC: linux-arm-kernel@lists.infradead.org
> Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
> ---
>   arch/arm64/kernel/cpufeature.c | 18 ++++++++++++---
>   include/linux/cpu.h            |  4 ++++
>   kernel/cgroup/cpuset.c         | 40 +++++++++++++++++++++++-----------
>   3 files changed, 46 insertions(+), 16 deletions(-)
>
> diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
> index 9ad065f15f1d..38046489d2ea 100644
> --- a/arch/arm64/kernel/cpufeature.c
> +++ b/arch/arm64/kernel/cpufeature.c
> @@ -1653,6 +1653,18 @@ has_cpuid_feature(const struct arm64_cpu_capabilities *entry, int scope)
>   	return feature_matches(val, entry);
>   }
>   
> +/*
> + * 32 bits support CPUs can't be isolated because tasks may be
> + * arbitrarily affine to them, defeating the purpose of isolation.
> + */
> +bool arch_isolated_cpus_can_update(struct cpumask *new_cpus)
> +{
> +	if (static_branch_unlikely(&arm64_mismatched_32bit_el0))
> +		return !cpumask_intersects(cpu_32bit_el0_mask, new_cpus);
> +	else
> +		return true;
> +}
> +
>   const struct cpumask *system_32bit_el0_cpumask(void)
>   {
>   	if (!system_supports_32bit_el0())
> @@ -1666,7 +1678,7 @@ const struct cpumask *system_32bit_el0_cpumask(void)
>   
>   const struct cpumask *task_cpu_fallback_mask(struct task_struct *p)
>   {
> -	return __task_cpu_possible_mask(p, housekeeping_cpumask(HK_TYPE_TICK));
> +	return __task_cpu_possible_mask(p, housekeeping_cpumask(HK_TYPE_DOMAIN));
>   }
>   
>   static int __init parse_32bit_el0_param(char *str)
> @@ -3963,8 +3975,8 @@ static int enable_mismatched_32bit_el0(unsigned int cpu)
>   	bool cpu_32bit = false;
>   
>   	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
> -		if (!housekeeping_cpu(cpu, HK_TYPE_TICK))
> -			pr_info("Treating adaptive-ticks CPU %u as 64-bit only\n", cpu);
> +		if (!housekeeping_cpu(cpu, HK_TYPE_DOMAIN))
> +			pr_info("Treating domain isolated CPU %u as 64-bit only\n", cpu);
>   		else
>   			cpu_32bit = true;
>   	}
> diff --git a/include/linux/cpu.h b/include/linux/cpu.h
> index b91b993f58ee..8bb239080534 100644
> --- a/include/linux/cpu.h
> +++ b/include/linux/cpu.h
> @@ -228,4 +228,8 @@ static inline bool cpu_attack_vector_mitigated(enum cpu_attack_vectors v)
>   #define smt_mitigations SMT_MITIGATIONS_OFF
>   #endif
>   
> +struct cpumask;
> +
> +bool arch_isolated_cpus_can_update(struct cpumask *new_cpus);
> +
>   #endif /* _LINUX_CPU_H_ */
> diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
> index 8260dd699fd8..cf99ea844c1d 100644
> --- a/kernel/cgroup/cpuset.c
> +++ b/kernel/cgroup/cpuset.c
> @@ -1352,33 +1352,47 @@ static bool partition_xcpus_del(int old_prs, struct cpuset *parent,
>   	return isolcpus_updated;
>   }
>   
> +bool __weak arch_isolated_cpus_can_update(struct cpumask *new_cpus)
> +{
> +	return true;
> +}
> +
>   /*
> - * isolcpus_nohz_conflict - check for isolated & nohz_full conflicts
> + * isolated_cpus_can_update - check for conflicts against housekeeping and
> + *                            CPUs capabilities.
>    * @new_cpus: cpu mask for cpus that are going to be isolated
> - * Return: true if there is conflict, false otherwise
> + * Return: true if there no conflict, false otherwise
>    *
> - * If nohz_full is enabled and we have isolated CPUs, their combination must
> - * still leave housekeeping CPUs.
> + * Check for conflicts:
> + * - If nohz_full is enabled and there are isolated CPUs, their combination must
> + *   still leave housekeeping CPUs.
> + * - Architecture has CPU capabilities incompatible with being isolated
>    */
> -static bool isolcpus_nohz_conflict(struct cpumask *new_cpus)
> +static bool isolated_cpus_can_update(struct cpumask *new_cpus)
>   {
>   	cpumask_var_t full_hk_cpus;
> -	int res = false;
> +	bool res;
> +
> +	if (!arch_isolated_cpus_can_update(new_cpus))
> +		return false;
>   
>   	if (!housekeeping_enabled(HK_TYPE_KERNEL_NOISE))
> -		return false;
> +		return true;
>   
>   	if (!alloc_cpumask_var(&full_hk_cpus, GFP_KERNEL))
> -		return true;
> +		return false;
> +
> +	res = true;
>   
>   	cpumask_and(full_hk_cpus, housekeeping_cpumask(HK_TYPE_KERNEL_NOISE),
>   		    housekeeping_cpumask(HK_TYPE_DOMAIN));
>   	cpumask_andnot(full_hk_cpus, full_hk_cpus, isolated_cpus);
>   	cpumask_and(full_hk_cpus, full_hk_cpus, cpu_online_mask);

We should construct the new cpumask by adding new CPUs and removing old 
ones from the existing isolated_cpus and pass it to 
arch_isolated_cpus_can_update() for the checking to be correct.

Cheers,
Longman