When boot with maxcpu=1 restrict, and LPI(Low Power Idle States) is on,
only CPU0 will go online. The support AMU flag of CPU0 will be set but the
flags of other CPUs will not. This will cause AMU FIE set up fail for CPU0
when it shares a cpufreq policy with other CPU(s). After that, when other
CPUs are finally online and the support AMU flags of them are set, they'll
never have a chance to set up AMU FIE, even though they're eligible.

To solve this problem, the process of setting up AMU FIE needs to be
modified as follows:

1. Set up AMU FIE only for the online CPUs.

2. Try to set up AMU FIE each time a CPU goes online and do the
freq_counters_valid() check. If this check fails, clear scale freq source
of all the CPUs related to the same policy, in case they use different
source of the freq scale.

At the same time, this change also be applied to cpufreq when calling
arch_set_freq_scale.

Signed-off-by: Lifeng Zheng <zhenglifeng1@huawei.com>
---
 arch/arm64/kernel/topology.c | 54 ++++++++++++++++++++++++++++++++++--
 drivers/cpufreq/cpufreq.c    |  4 +--
 2 files changed, 54 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 9317a618bb87..a9d9e9969cea 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -385,7 +385,7 @@ static int init_amu_fie_callback(struct notifier_block *nb, unsigned long val,
 	struct cpufreq_policy *policy = data;
 
 	if (val == CPUFREQ_CREATE_POLICY)
-		amu_fie_setup(policy->related_cpus);
+		amu_fie_setup(policy->cpus);
 
 	/*
 	 * We don't need to handle CPUFREQ_REMOVE_POLICY event as the AMU
@@ -404,10 +404,60 @@ static struct notifier_block init_amu_fie_notifier = {
 	.notifier_call = init_amu_fie_callback,
 };
 
+static int cpuhp_topology_online(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_policy(cpu);
+
+	/*
+	 * If the online CPUs are not all AMU FIE CPUs or the new one is already
+	 * an AMU FIE one, no need to set it.
+	 */
+	if (!policy || !cpumask_available(amu_fie_cpus) ||
+	    !cpumask_subset(policy->cpus, amu_fie_cpus) ||
+	    cpumask_test_cpu(cpu, amu_fie_cpus))
+		return 0;
+
+	/*
+	 * If the new online CPU cannot pass this check, all the CPUs related to
+	 * the same policy should be clear from amu_fie_cpus mask, otherwise they
+	 * may use different source of the freq scale.
+	 */
+	if (WARN_ON(!freq_counters_valid(cpu))) {
+		topology_clear_scale_freq_source(SCALE_FREQ_SOURCE_ARCH,
+						 policy->related_cpus);
+		cpumask_andnot(amu_fie_cpus, amu_fie_cpus, policy->related_cpus);
+		return 0;
+	}
+
+	cpumask_set_cpu(cpu, amu_fie_cpus);
+
+	topology_set_scale_freq_source(&amu_sfd, cpumask_of(cpu));
+
+	pr_debug("CPU[%u]: counter will be used for FIE.", cpu);
+
+	return 0;
+}
+
 static int __init init_amu_fie(void)
 {
-	return cpufreq_register_notifier(&init_amu_fie_notifier,
+	int ret;
+
+	ret = cpufreq_register_notifier(&init_amu_fie_notifier,
 					CPUFREQ_POLICY_NOTIFIER);
+	if (ret)
+		return ret;
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"arm64/topology:online",
+					cpuhp_topology_online,
+					NULL);
+	if (ret < 0) {
+		cpufreq_unregister_notifier(&init_amu_fie_notifier,
+					    CPUFREQ_POLICY_NOTIFIER);
+		return ret;
+	}
+
+	return 0;
 }
 core_initcall(init_amu_fie);
 
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 78ca68ea754d..d1890a2af1af 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -417,7 +417,7 @@ void cpufreq_freq_transition_end(struct cpufreq_policy *policy,
 
 	cpufreq_notify_post_transition(policy, freqs, transition_failed);
 
-	arch_set_freq_scale(policy->related_cpus,
+	arch_set_freq_scale(policy->cpus,
 			    policy->cur,
 			    arch_scale_freq_ref(policy->cpu));
 
@@ -2219,7 +2219,7 @@ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
 		return 0;
 
 	policy->cur = freq;
-	arch_set_freq_scale(policy->related_cpus, freq,
+	arch_set_freq_scale(policy->cpus, freq,
 			    arch_scale_freq_ref(policy->cpu));
 	cpufreq_stats_record_transition(policy, freq);
 
-- 
2.33.0

Hi Lifeng,

kernel test robot noticed the following build errors:

[auto build test ERROR on arm64/for-next/core]
[also build test ERROR on rafael-pm/linux-next rafael-pm/bleeding-edge arm/for-next arm/fixes kvmarm/next soc/for-next linus/master v6.17-rc1 next-20250814]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Lifeng-Zheng/arm64-topology-Set-scale-freq-source-only-for-the-CPUs-that-have-not-been-set-before/20250814-153732
base:   https://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git for-next/core
patch link:    https://lore.kernel.org/r/20250814072853.3426386-4-zhenglifeng1%40huawei.com
patch subject: [PATCH v4 3/3] arm64: topology: Setup AMU FIE for online CPUs only
config: arm64-allnoconfig (https://download.01.org/0day-ci/archive/20250815/202508151158.Hm9U6le6-lkp@intel.com/config)
compiler: aarch64-linux-gcc (GCC) 15.1.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250815/202508151158.Hm9U6le6-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202508151158.Hm9U6le6-lkp@intel.com/

All errors (new ones prefixed by >>):

   arch/arm64/kernel/topology.c: In function 'cpuhp_topology_online':
>> arch/arm64/kernel/topology.c:409:41: error: implicit declaration of function 'cpufreq_cpu_policy'; did you mean 'cpufreq_cpu_put'? [-Wimplicit-function-declaration]
     409 |         struct cpufreq_policy *policy = cpufreq_cpu_policy(cpu);
         |                                         ^~~~~~~~~~~~~~~~~~
         |                                         cpufreq_cpu_put
   arch/arm64/kernel/topology.c:409:41: error: initialization of 'struct cpufreq_policy *' from 'int' makes pointer from integer without a cast [-Wint-conversion]


vim +409 arch/arm64/kernel/topology.c

   406	
   407	static int cpuhp_topology_online(unsigned int cpu)
   408	{
 > 409		struct cpufreq_policy *policy = cpufreq_cpu_policy(cpu);
   410	
   411		/*
   412		 * If the online CPUs are not all AMU FIE CPUs or the new one is already
   413		 * an AMU FIE one, no need to set it.
   414		 */
   415		if (!policy || !cpumask_available(amu_fie_cpus) ||
   416		    !cpumask_subset(policy->cpus, amu_fie_cpus) ||
   417		    cpumask_test_cpu(cpu, amu_fie_cpus))
   418			return 0;
   419	
   420		/*
   421		 * If the new online CPU cannot pass this check, all the CPUs related to
   422		 * the same policy should be clear from amu_fie_cpus mask, otherwise they
   423		 * may use different source of the freq scale.
   424		 */
   425		if (WARN_ON(!freq_counters_valid(cpu))) {
   426			topology_clear_scale_freq_source(SCALE_FREQ_SOURCE_ARCH,
   427							 policy->related_cpus);
   428			cpumask_andnot(amu_fie_cpus, amu_fie_cpus, policy->related_cpus);
   429			return 0;
   430		}
   431	
   432		cpumask_set_cpu(cpu, amu_fie_cpus);
   433	
   434		topology_set_scale_freq_source(&amu_sfd, cpumask_of(cpu));
   435	
   436		pr_debug("CPU[%u]: counter will be used for FIE.", cpu);
   437	
   438		return 0;
   439	}
   440	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki