Re: [RFC PATCH v4 08/28] sched: Set up LLC indexing

[Adam Li <adamli@os.amperecomputing.com>]

Hi Chen Yu,

I tested the patch set on AmpereOne CPU with 192 cores.
With certain firmware setting, each core has its own L1/L2 cache.
But *no* cores share LLC (L3). So *no* schedule domain
has flag 'SD_SHARE_LLC'.

With this topology:
per_cpu(sd_llc_id, cpu) is actually the cpu id (0-191).

And kernel bug will be triggered at:
'BUG_ON(idx > MAX_LLC)'

Please see details bellow.

The bug will disappear if setting 'MAX_LLC' to 192.
But I think we might disable CAS(cache aware scheduling)
if no domain has 'SD_SHARE_LLC'.

On 8/9/2025 1:03 PM, Chen Yu wrote:
> From: Tim Chen <tim.c.chen@linux.intel.com>
> 
> 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 02ff8b8be25b..81d92e8097f5 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -809,6 +809,9 @@ struct kmap_ctrl {
>  #endif
>  };
>  
> +/* XXX need fix to not use magic number */
> +#define MAX_LLC 64

The bug will disappear if setting 'MAX_LLC' to 192.

> +
>  struct task_struct {
>  #ifdef CONFIG_THREAD_INFO_IN_TASK
>  	/*
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 3128dbcf0a36..f5075d287c51 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);
>  }
>  
> +/*
> + * continuous 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 83552aab74fb..c37c74dfce25 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -2056,6 +2056,7 @@ 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);
> @@ -2064,6 +2065,7 @@ 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 b958fe48e020..91a2b7f65fee 100644
> --- a/kernel/sched/topology.c
> +++ b/kernel/sched/topology.c
> @@ -657,6 +657,7 @@ 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);
> @@ -666,6 +667,25 @@ 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);

[    2.793048] ------------[ cut here ]------------
[    2.797737] kernel BUG at kernel/sched/topology.c:682!
[    2.802957] Internal error: Oops - BUG: 00000000f2000800 [#1]  SMP
[snip]
[    2.917450]  update_top_cache_domain+0x248/0x260 (P)
[    2.922493]  cpu_attach_domain+0x170/0x250
[    2.926653]  build_sched_domains+0x640/0x7b0
[    2.930989]  sched_init_domains+0xbc/0xd8
[    2.935062]  sched_init_smp+0x48/0xd0
[    2.938778]  kernel_init_freeable+0xf4/0x148
[    2.943115]  kernel_init+0x2c/0x150
[    2.946658]  ret_from_fork+0x10/0x20
[    2.950288] Code: d2800001 17ffffc7 d2800000 17ffffdf (d4210000)
[    2.956481] ---[ end trace 0000000000000000 ]---
[    2.961170] Kernel panic - not syncing: Oops - BUG: Fatal exception
[    2.967540] SMP: stopping secondary CPUs
[    2.971529] ---[ end Kernel panic - not syncing: Oops - BUG: Fatal exception ]---


> +		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;
> @@ -684,6 +704,7 @@ 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)
> @@ -2456,6 +2477,14 @@ 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;
>  

A draft patch like bellow can fix the kernel BUG:
1) Do not call update_llc_idx() if domain has no SD_SHARE_LLC
2) Disable CAS if domain has no SD_SHARE_LLC

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 8483c02b4d28..cde9b6cdb1de 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -704,7 +704,8 @@ 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);
+       if (sd)
+               update_llc_idx(cpu);

        sd = lowest_flag_domain(cpu, SD_CLUSTER);
        if (sd)
@@ -2476,6 +2477,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
        int i, ret = -ENOMEM;
        bool has_asym = false;
        bool has_cluster = false;
+       bool has_llc = false;
        bool llc_has_parent_sd = false;
        unsigned int multi_llcs_node = 1;

@@ -2621,6 +2623,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att

                if (lowest_flag_domain(i, SD_CLUSTER))
                        has_cluster = true;
+
+               if (highest_flag_domain(i, SD_SHARE_LLC))
+                       has_llc = true;
        }
        rcu_read_unlock();

@@ -2631,7 +2636,8 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
                static_branch_inc_cpuslocked(&sched_cluster_active);

 #ifdef CONFIG_SCHED_CACHE
-       if (llc_has_parent_sd && multi_llcs_node && !sched_asym_cpucap_active())
+       if (has_llc && llc_has_parent_sd && multi_llcs_node &&
+           !sched_asym_cpucap_active())
                static_branch_inc_cpuslocked(&sched_cache_present);
 #endif


Thanks,
-adam