Aneesh Kumar K V <aneesh.kumar@xxxxxxxxxxxxx> writes:
> On 7/26/22 9:33 AM, Huang, Ying wrote:
>> "Aneesh Kumar K.V" <aneesh.kumar@xxxxxxxxxxxxx> writes:
>>
>>> If the new NUMA node onlined doesn't have a performance level assigned,
>>> the kernel adds the NUMA node to default memory tier.
>>>
>>> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxx>
>>> ---
>>> include/linux/memory-tiers.h | 1 +
>>> mm/memory-tiers.c | 75 ++++++++++++++++++++++++++++++++++++
>>> 2 files changed, 76 insertions(+)
>>>
>>> diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
>>> index ef380a39db3a..3d5f14d57ae6 100644
>>> --- a/include/linux/memory-tiers.h
>>> +++ b/include/linux/memory-tiers.h
>>> @@ -14,6 +14,7 @@
>>> #define MEMTIER_PERF_LEVEL_DRAM (1 << (MEMTIER_CHUNK_BITS + 2))
>>> /* leave one tier below this slow pmem */
>>> #define MEMTIER_PERF_LEVEL_PMEM (1 << MEMTIER_CHUNK_BITS)
>>> +#define MEMTIER_HOTPLUG_PRIO 100
>>>
>>> extern bool numa_demotion_enabled;
>>>
>>> diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
>>> index 41a21cc5ae55..cc3a47ec18e4 100644
>>> --- a/mm/memory-tiers.c
>>> +++ b/mm/memory-tiers.c
>>> @@ -5,6 +5,7 @@
>>> #include <linux/lockdep.h>
>>> #include <linux/moduleparam.h>
>>> #include <linux/node.h>
>>> +#include <linux/memory.h>
>>> #include <linux/memory-tiers.h>
>>>
>>> struct memory_tier {
>>> @@ -64,6 +65,78 @@ static struct memory_tier *find_create_memory_tier(unsigned int perf_level)
>>> return new_memtier;
>>> }
>>>
>>> +static struct memory_tier *__node_get_memory_tier(int node)
>>> +{
>>> + struct memory_tier *memtier;
>>> +
>>> + list_for_each_entry(memtier, &memory_tiers, list) {
>>> + if (node_isset(node, memtier->nodelist))
>>> + return memtier;
>>> + }
>>> + return NULL;
>>> +}
>>> +
>>> +static void init_node_memory_tier(int node)
>>
>> set_node_memory_tier()?
>
> That was done based on feedback from Alistair
>
> https://lore.kernel.org/linux-mm/87h73iapg1.fsf@nvdebian.thelocal
>
>>
>>> +{
>>> + int perf_level;
>>> + struct memory_tier *memtier;
>>> +
>>> + mutex_lock(&memory_tier_lock);
>>> +
>>> + memtier = __node_get_memory_tier(node);
>>> + if (!memtier) {
>>> + perf_level = node_devices[node]->perf_level;
>>> + memtier = find_create_memory_tier(perf_level);
>>> + node_set(node, memtier->nodelist);
>>> + }
It's related to Alistair's comments too. When will memtier != NULL
here? We may need just VM_WARN_ON() here?
>>> + mutex_unlock(&memory_tier_lock);
>>> +}
>>> +
>>> +static void clear_node_memory_tier(int node)
>>> +{
>>> + struct memory_tier *memtier;
>>> +
>>> + mutex_lock(&memory_tier_lock);
>>> + memtier = __node_get_memory_tier(node);
>>> + if (memtier)
>>> + node_clear(node, memtier->nodelist);
>>
>> When memtier->nodelist becomes empty, we need to free memtier?
>>
>>> + mutex_unlock(&memory_tier_lock);
>>> +}
>>> +
>>> +/*
>>> + * This runs whether reclaim-based migration is enabled or not,
>>> + * which ensures that the user can turn reclaim-based migration
>>> + * at any time without needing to recalculate migration targets.
>>> + */
>>
>> The comments doesn't apply here.
>>
>>> +static int __meminit migrate_on_reclaim_callback(struct notifier_block *self,
>>> + unsigned long action, void *_arg)
>>
>> Now we are building memory tiers instead of working on demotion. So I
>> think we should rename the function to memtier_hotplug_callback().
>>
>>> +{
>>> + struct memory_notify *arg = _arg;
>>> +
>>> + /*
>>> + * Only update the node migration order when a node is
>>> + * changing status, like online->offline.
>>> + */
>>> + if (arg->status_change_nid < 0)
>>> + return notifier_from_errno(0);
>>> +
>>> + switch (action) {
>>> + case MEM_OFFLINE:
>>> + clear_node_memory_tier(arg->status_change_nid);
>>> + break;
>>> + case MEM_ONLINE:
>>> + init_node_memory_tier(arg->status_change_nid);
>>> + break;
>>> + }
>>> +
>>> + return notifier_from_errno(0);
>>> +}
>>> +
>>> +static void __init migrate_on_reclaim_init(void)
>>> +{
>>> + hotplug_memory_notifier(migrate_on_reclaim_callback, MEMTIER_HOTPLUG_PRIO);
>>> +}
>>
>> I suggest to call hotplug_memory_notifier() in memory_tier_init()
>> directly. We are not working on demotion here.
>>
>>> +
>>> static int __init memory_tier_init(void)
>>> {
>>> int node;
>>> @@ -96,6 +169,8 @@ static int __init memory_tier_init(void)
>>> node_property->perf_level = default_memtier_perf_level;
>>> }
>>> mutex_unlock(&memory_tier_lock);
>>> +
>>> + migrate_on_reclaim_init();
>>> return 0;
>>> }
>>> subsys_initcall(memory_tier_init);
>>
>> Best Regards,
>> Huang, Ying
>
>
> Will update the patch in next iteration to take care of other feedback.
Thanks!
Best Regards,
Huang, Ying
