Re: [RFC PATCH 5/6 v8] sched/fair: Enable idle core tracking for !SMT

["Chen, Yu C" <yu.c.chen@intel.com>]

On 12/5/2025 11:52 PM, Christian Loehle wrote:
> On 12/2/25 18:12, Vincent Guittot wrote:
>> Enable has_idle_cores at llc level feature for !SMT system for which
>> CPU equals core.
>>
>> We don't enable has_idle_core feature of select_idle_cpu to be
>> conservative and don't parse all CPUs of LLC.
>>
>> At now, has_idle_cores can be cleared even if a CPU is idle because of
>> SIS_UTIL but it looks reasonnable as the probablity to get an idle CPU is
>> low anyway.
>>
>> Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
>> ---
>>   kernel/sched/fair.c  | 29 +++++++----------------------
>>   kernel/sched/sched.h | 42 +++++++++++++++++++++++++++++-------------
>>   2 files changed, 36 insertions(+), 35 deletions(-)
>>
>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
>> index 252254168c92..0c0c675f39cf 100644
>> --- a/kernel/sched/fair.c
>> +++ b/kernel/sched/fair.c
>> @@ -7501,19 +7501,6 @@ static inline int __select_idle_cpu(int cpu, struct task_struct *p)
>>   	return -1;
>>   }
>>   
>> -#ifdef CONFIG_SCHED_SMT
>> -DEFINE_STATIC_KEY_FALSE(sched_smt_present);
>> -EXPORT_SYMBOL_GPL(sched_smt_present);
>> -
>> -static inline void set_idle_cores(int cpu, int val)
>> -{
>> -	struct sched_domain_shared *sds;
>> -
>> -	sds = rcu_dereference(per_cpu(sd_llc_shared, cpu));
>> -	if (sds)
>> -		WRITE_ONCE(sds->has_idle_cores, val);
>> -}
>> -
>>   static inline bool test_idle_cores(int cpu)
>>   {
>>   	struct sched_domain_shared *sds;
>> @@ -7525,6 +7512,10 @@ static inline bool test_idle_cores(int cpu)
>>   	return false;
>>   }
>>   
>> +#ifdef CONFIG_SCHED_SMT
>> +DEFINE_STATIC_KEY_FALSE(sched_smt_present);
>> +EXPORT_SYMBOL_GPL(sched_smt_present);
>> +
>>   /*
>>    * Scans the local SMT mask to see if the entire core is idle, and records this
>>    * information in sd_llc_shared->has_idle_cores.
>> @@ -7612,15 +7603,6 @@ static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int t
>>   
>>   #else /* !CONFIG_SCHED_SMT: */
>>   
>> -static inline void set_idle_cores(int cpu, int val)
>> -{
>> -}
>> -
>> -static inline bool test_idle_cores(int cpu)
>> -{
>> -	return false;
>> -}
>> -
>>   static inline int select_idle_core(struct task_struct *p, int core, struct cpumask *cpus, int *idle_cpu)
>>   {
>>   	return __select_idle_cpu(core, p);
>> @@ -7886,6 +7868,9 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
>>   	if ((unsigned)i < nr_cpumask_bits)
>>   		return i;
>>   
> a
>> +
>>   	/*
>>   	 * For cluster machines which have lower sharing cache like L2 or
>>   	 * LLC Tag, we tend to find an idle CPU in the target's cluster
>> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
>> index 697bd654298a..b9e228333d5e 100644
>> --- a/kernel/sched/sched.h
>> +++ b/kernel/sched/sched.h
>> @@ -1591,19 +1591,6 @@ do {						\
>>   	flags = _raw_spin_rq_lock_irqsave(rq);	\
>>   } while (0)
>>   
>> -#ifdef CONFIG_SCHED_SMT
>> -extern void __update_idle_core(struct rq *rq);
>> -
>> -static inline void update_idle_core(struct rq *rq)
>> -{
>> -	if (static_branch_unlikely(&sched_smt_present))
>> -		__update_idle_core(rq);
>> -}
>> -
>> -#else /* !CONFIG_SCHED_SMT: */
>> -static inline void update_idle_core(struct rq *rq) { }
>> -#endif /* !CONFIG_SCHED_SMT */
>> -
>>   #ifdef CONFIG_FAIR_GROUP_SCHED
>>   
>>   static inline struct task_struct *task_of(struct sched_entity *se)
>> @@ -2091,6 +2078,35 @@ static __always_inline bool sched_asym_cpucap_active(void)
>>   	return static_branch_unlikely(&sched_asym_cpucapacity);
>>   }
>>   
>> +static inline void set_idle_cores(int cpu, int val)
>> +{
>> +	struct sched_domain_shared *sds;
>> +
>> +	sds = rcu_dereference(per_cpu(sd_llc_shared, cpu));
>> +	if (sds)
>> +		WRITE_ONCE(sds->has_idle_cores, val);
>> +}
> 
> FWIW this triggers
> [    0.172174] =============================
> [    0.172177] WARNING: suspicious RCU usage
> [    0.172179] 6.18.0-rc7-cix-build+ #215 Not tainted
> [    0.172184] Detected PIPT I-cache on CPU1
> [    0.178161] -----------------------------
> [    0.178163] kernel/sched/sched.h:2085 suspicious rcu_dereference_check() usage!
> [    0.178165]
>                 other info that might help us debug this:
> 
> [    0.178177] CPU features: SANITY CHECK: Unexpected variation in SYS_ID_AA64MMFR1_EL1. Boot CPU: 0x1001111010312122, CPU1: 0x1001111011312122
> [    0.182211]
>                 rcu_scheduler_active = 1, debug_locks = 1
> [    0.182213] 4 locks held by swapper/0/1:
> [    0.182224] CPU features: Unsupported CPU feature variation detected.
> [    0.186260]  #0: ffff800082b2bf00
> [    0.186277] GICv3: CPU1: found redistributor 0 region 0:0x000000000e090000
> [    0.191101]  (cpu_add_remove_lock){+.+.}-{4:4}, at: cpu_up+0x90/0x158
> [    0.191115] GICv3: CPU1: using allocated LPI pending table @0x0000000100330000
> [    0.195158]  #1: ffff800082b2c0a0 (cpu_hotplug_lock
> [    0.195277] CPU1: Booted secondary processor 0x0000000000 [0x410fd801]
> [    0.199208] ){++++}-{0:0}, at: _cpu_up+0x58/0x268
> [    0.199213]  #2: ffff800082ebddd0 (sparse_irq_lock){+.+.}-{4:4}, at: irq_lock_sparse+0x20/0x2c
> [    0.293548]  #3: ffff0001feec1c18 (&rq->__lock){-...}-{2:2}, at: __schedule+0x144/0x1058
> [    0.301737]
>                 stack backtrace:
> [    0.306136] CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Tainted: G S                  6.18.0-rc7-cix-build+ #215 PREEMPT
> [    0.306141] Tainted: [S]=CPU_OUT_OF_SPEC
> [    0.306144] Call trace:
> [    0.306145]  show_stack+0x18/0x24 (C)
> [    0.306150]  dump_stack_lvl+0x90/0xd0
> [    0.306155]  dump_stack+0x18/0x24
> [    0.306159]  lockdep_rcu_suspicious+0x168/0x238
> [    0.306164]  set_next_task_idle+0x144/0x148
> [    0.306167]  __schedule+0xc50/0x1058
> [    0.306171]  schedule+0x48/0x15c
> [    0.306173]  schedule_timeout+0x90/0x128
> [    0.306177]  wait_for_completion_timeout+0x88/0x13c
> [    0.306180]  __cpu_up+0x80/0x1e4
> [    0.306186]  bringup_cpu+0x48/0x2ac
> [    0.306189]  cpuhp_invoke_callback+0x18c/0x358
> [    0.306191]  __cpuhp_invoke_callback_range+0xf4/0x130
> [    0.306194]  _cpu_up+0x150/0x268
> [    0.306196]  cpu_up+0xcc/0x158
> [    0.306199]  bringup_nonboot_cpus+0x84/0xcc
> [    0.306203]  smp_init+0x30/0x8c
> [    0.306208]  kernel_init_freeable+0x18c/0x504
> [    0.306215]  kernel_init+0x20/0x1d8
> [    0.306218]  ret_from_fork+0x10/0x20
> 
> 
> on my machine...
> 

update_idle_core() might need to deal with rcu protection in the original
code, maybe something like this would help:


diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 9dfabaa314b1..4c9348075abf 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2094,17 +2094,22 @@ extern void __update_idle_core(struct rq *rq);

  static inline void update_idle_core(struct rq *rq)
  {
-       if (static_branch_unlikely(&sched_smt_present))
+       if (static_branch_unlikely(&sched_smt_present)) {
                 __update_idle_core(rq);
-       else
+       } else {
+               rcu_read_lock();
                 set_idle_cores(cpu_of(rq), 1);
+               rcu_read_unlock();
+       }

  }

  #else /* !CONFIG_SCHED_SMT: */
  static inline void update_idle_core(struct rq *rq)
  {
+       rcu_read_lock();
         set_idle_cores(cpu_of(rq), 1);
+       rcu_read_unlock();
  }
  #endif /* !CONFIG_SCHED_SMT */