Re: [PATCH v10 8/8] mm/demotion: Update node_is_toptier to work with memory tiers

[Aneesh Kumar K V <aneesh.kumar@linux.ibm.com>]

On 7/25/22 2:24 PM, Huang, Ying wrote:
> "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> writes:
> 
>> With memory tiers support we can have memory only NUMA nodes
>> in the top tier from which we want to avoid promotion tracking NUMA
>> faults. Update node_is_toptier to work with memory tiers.
>> All NUMA nodes are by default top tier nodes. With lower memory
>> tiers added we consider all memory tiers above a memory tier having
>> CPU NUMA nodes as a top memory tier
>>
>> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
>> ---
>>  include/linux/memory-tiers.h | 11 +++++++++
>>  include/linux/node.h         |  5 -----
>>  mm/huge_memory.c             |  1 +
>>  mm/memory-tiers.c            | 43 ++++++++++++++++++++++++++++++++++++
>>  mm/migrate.c                 |  1 +
>>  mm/mprotect.c                |  1 +
>>  6 files changed, 57 insertions(+), 5 deletions(-)
>>
>> diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
>> index 0e58588fa066..085dd815bf73 100644
>> --- a/include/linux/memory-tiers.h
>> +++ b/include/linux/memory-tiers.h
>> @@ -20,6 +20,7 @@ extern bool numa_demotion_enabled;
>>  #ifdef CONFIG_MIGRATION
>>  int next_demotion_node(int node);
>>  void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
>> +bool node_is_toptier(int node);
>>  #else
>>  static inline int next_demotion_node(int node)
>>  {
>> @@ -30,6 +31,11 @@ static inline void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *target
>>  {
>>  	*targets = NODE_MASK_NONE;
>>  }
>> +
>> +static inline bool node_is_toptier(int node)
>> +{
>> +	return true;
>> +}
>>  #endif
>>  
>>  #else
>> @@ -44,5 +50,10 @@ static inline void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *target
>>  {
>>  	*targets = NODE_MASK_NONE;
>>  }
>> +
>> +static inline bool node_is_toptier(int node)
>> +{
>> +	return true;
>> +}
>>  #endif	/* CONFIG_NUMA */
>>  #endif  /* _LINUX_MEMORY_TIERS_H */
>> diff --git a/include/linux/node.h b/include/linux/node.h
>> index a2a16d4104fd..d0432db18094 100644
>> --- a/include/linux/node.h
>> +++ b/include/linux/node.h
>> @@ -191,9 +191,4 @@ static inline void register_hugetlbfs_with_node(node_registration_func_t reg,
>>  
>>  #define to_node(device) container_of(device, struct node, dev)
>>  
>> -static inline bool node_is_toptier(int node)
>> -{
>> -	return node_state(node, N_CPU);
>> -}
>> -
>>  #endif /* _LINUX_NODE_H_ */
>> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
>> index 834f288b3769..8405662646e9 100644
>> --- a/mm/huge_memory.c
>> +++ b/mm/huge_memory.c
>> @@ -35,6 +35,7 @@
>>  #include <linux/numa.h>
>>  #include <linux/page_owner.h>
>>  #include <linux/sched/sysctl.h>
>> +#include <linux/memory-tiers.h>
>>  
>>  #include <asm/tlb.h>
>>  #include <asm/pgalloc.h>
>> diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
>> index 4a96e4213d66..f0515bfd4051 100644
>> --- a/mm/memory-tiers.c
>> +++ b/mm/memory-tiers.c
>> @@ -13,6 +13,7 @@
>>  
>>  struct memory_tier {
>>  	struct list_head list;
>> +	int id;
>>  	int perf_level;
>>  	nodemask_t nodelist;
>>  	nodemask_t lower_tier_mask;
>> @@ -26,6 +27,7 @@ static LIST_HEAD(memory_tiers);
>>  static DEFINE_MUTEX(memory_tier_lock);
>>  
>>  #ifdef CONFIG_MIGRATION
>> +static int top_tier_id;
>>  /*
>>   * node_demotion[] examples:
>>   *
>> @@ -129,6 +131,7 @@ static struct memory_tier *find_create_memory_tier(unsigned int perf_level)
>>  	if (!new_memtier)
>>  		return ERR_PTR(-ENOMEM);
>>  
>> +	new_memtier->id = perf_level >> MEMTIER_CHUNK_BITS;
>>  	new_memtier->perf_level = perf_level;
>>  	if (found_slot)
>>  		list_add_tail(&new_memtier->list, ent);
>> @@ -154,6 +157,31 @@ static struct memory_tier *__node_get_memory_tier(int node)
>>  }
>>  
>>  #ifdef CONFIG_MIGRATION
>> +bool node_is_toptier(int node)
>> +{
>> +	bool toptier;
>> +	pg_data_t *pgdat;
>> +	struct memory_tier *memtier;
>> +
>> +	pgdat = NODE_DATA(node);
>> +	if (!pgdat)
>> +		return false;
>> +
>> +	rcu_read_lock();
>> +	memtier = rcu_dereference(pgdat->memtier);
>> +	if (!memtier) {
>> +		toptier = true;
>> +		goto out;
>> +	}
>> +	if (memtier->id >= top_tier_id)
>> +		toptier = true;
>> +	else
>> +		toptier = false;
>> +out:
>> +	rcu_read_unlock();
>> +	return toptier;
>> +}
>> +
>>  void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets)
>>  {
>>  	struct memory_tier *memtier;
>> @@ -304,6 +332,21 @@ static void establish_migration_targets(void)
>>  			}
>>  		} while (1);
>>  	}
>> +	/*
>> +	 * Promotion is allowed from a memory tier to higher
>> +	 * memory tier only if the memory tier doesn't include
>> +	 * compute. We want to  skip promotion from a memory tier,
>> +	 * if any node that is  part of the memory tier have CPUs.
>> +	 * Once we detect such a memory tier, we consider that tier
>> +	 * as top tiper from which promotion is not allowed.
>> +	 */
>> +	list_for_each_entry_reverse(memtier, &memory_tiers, list) {
>> +		nodes_and(used, node_states[N_CPU], memtier->nodelist);
>> +		if (!nodes_empty(used)) {
>> +			top_tier_id = memtier->id;
> 
> I don't think we need to introduce memory tier ID for this.  We can add
> a top_tier_perf_level, set it here and use it in node_is_toptier().
> 

Sure. Will switch to that in the next iteration.

-aneesh