Re: [PATCH] mm/migrate: put dest folio on deferred split list if source was there.

[Zi Yan <ziy@nvidia.com>]

[-- Attachment #1: Type: text/plain, Size: 5373 bytes --]

On 11 Mar 2024, at 15:53, Ryan Roberts wrote:

> On 11/03/2024 19:36, Zi Yan wrote:
>> From: Zi Yan <ziy@nvidia.com>
>>
>> Commit 616b8371539a6 ("mm: thp: enable thp migration in generic path")
>> did not check if a THP is on deferred split list before migration, thus,
>> the destination THP is never put on deferred split list even if the source
>> THP might be. The opportunity of reclaiming free pages in a partially
>> mapped THP during deferred list scanning is lost, but no other harmful
>> consequence is present[1]. Checking source folio deferred split list
>> status before page unmapped and add destination folio to the list if
>> source was after migration.
>>
>> [1]: https://lore.kernel.org/linux-mm/03CE3A00-917C-48CC-8E1C-6A98713C817C@nvidia.com/
>>
>> Fixes: 616b8371539a ("mm: thp: enable thp migration in generic path")
>> Signed-off-by: Zi Yan <ziy@nvidia.com>
>> ---
>>  mm/huge_memory.c | 22 ----------------------
>>  mm/internal.h    | 23 +++++++++++++++++++++++
>>  mm/migrate.c     | 26 +++++++++++++++++++++++++-
>>  3 files changed, 48 insertions(+), 23 deletions(-)
>>
>> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
>> index 9859aa4f7553..c6d4d0cdf4b3 100644
>> --- a/mm/huge_memory.c
>> +++ b/mm/huge_memory.c
>> @@ -766,28 +766,6 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
>>  	return pmd;
>>  }
>>
>> -#ifdef CONFIG_MEMCG
>> -static inline
>> -struct deferred_split *get_deferred_split_queue(struct folio *folio)
>> -{
>> -	struct mem_cgroup *memcg = folio_memcg(folio);
>> -	struct pglist_data *pgdat = NODE_DATA(folio_nid(folio));
>> -
>> -	if (memcg)
>> -		return &memcg->deferred_split_queue;
>> -	else
>> -		return &pgdat->deferred_split_queue;
>> -}
>> -#else
>> -static inline
>> -struct deferred_split *get_deferred_split_queue(struct folio *folio)
>> -{
>> -	struct pglist_data *pgdat = NODE_DATA(folio_nid(folio));
>> -
>> -	return &pgdat->deferred_split_queue;
>> -}
>> -#endif
>> -
>>  void folio_prep_large_rmappable(struct folio *folio)
>>  {
>>  	if (!folio || !folio_test_large(folio))
>> diff --git a/mm/internal.h b/mm/internal.h
>> index d1c69119b24f..8fa36e84463a 100644
>> --- a/mm/internal.h
>> +++ b/mm/internal.h
>> @@ -1107,6 +1107,29 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
>>  				   unsigned long addr, pmd_t *pmd,
>>  				   unsigned int flags);
>>
>> +#ifdef CONFIG_MEMCG
>> +static inline
>> +struct deferred_split *get_deferred_split_queue(struct folio *folio)
>> +{
>> +	struct mem_cgroup *memcg = folio_memcg(folio);
>> +	struct pglist_data *pgdat = NODE_DATA(folio_nid(folio));
>> +
>> +	if (memcg)
>> +		return &memcg->deferred_split_queue;
>> +	else
>> +		return &pgdat->deferred_split_queue;
>> +}
>> +#else
>> +static inline
>> +struct deferred_split *get_deferred_split_queue(struct folio *folio)
>> +{
>> +	struct pglist_data *pgdat = NODE_DATA(folio_nid(folio));
>> +
>> +	return &pgdat->deferred_split_queue;
>> +}
>> +#endif
>> +
>> +
>>  /*
>>   * mm/mmap.c
>>   */
>> diff --git a/mm/migrate.c b/mm/migrate.c
>> index 73a052a382f1..84ba1c65d20d 100644
>> --- a/mm/migrate.c
>> +++ b/mm/migrate.c
>> @@ -20,6 +20,7 @@
>>  #include <linux/pagemap.h>
>>  #include <linux/buffer_head.h>
>>  #include <linux/mm_inline.h>
>> +#include <linux/mmzone.h>
>>  #include <linux/nsproxy.h>
>>  #include <linux/ksm.h>
>>  #include <linux/rmap.h>
>> @@ -1037,7 +1038,10 @@ static int move_to_new_folio(struct folio *dst, struct folio *src,
>>  enum {
>>  	PAGE_WAS_MAPPED = BIT(0),
>>  	PAGE_WAS_MLOCKED = BIT(1),
>> -	PAGE_OLD_STATES = PAGE_WAS_MAPPED | PAGE_WAS_MLOCKED,
>> +	PAGE_WAS_ON_DEFERRED_LIST = BIT(2),
>> +	PAGE_OLD_STATES = PAGE_WAS_MAPPED |
>> +			  PAGE_WAS_MLOCKED |
>> +			  PAGE_WAS_ON_DEFERRED_LIST,
>>  };
>>
>>  static void __migrate_folio_record(struct folio *dst,
>> @@ -1168,6 +1172,17 @@ static int migrate_folio_unmap(new_folio_t get_new_folio,
>>  		folio_lock(src);
>>  	}
>>  	locked = true;
>> +	if (folio_test_large_rmappable(src) &&
>> +		!list_empty(&src->_deferred_list)) {
>> +		struct deferred_split *ds_queue = get_deferred_split_queue(src);
>> +
>> +		spin_lock(&ds_queue->split_queue_lock);
>> +		ds_queue->split_queue_len--;
>> +		list_del_init(&src->_deferred_list);
>> +		spin_unlock(&ds_queue->split_queue_lock);
>> +		old_page_state |= PAGE_WAS_ON_DEFERRED_LIST;
>> +	}
>> +
>>  	if (folio_test_mlocked(src))
>>  		old_page_state |= PAGE_WAS_MLOCKED;
>>
>> @@ -1307,6 +1322,15 @@ static int migrate_folio_move(free_folio_t put_new_folio, unsigned long private,
>>  	if (old_page_state & PAGE_WAS_MAPPED)
>>  		remove_migration_ptes(src, dst, false);
>>
>> +	if (old_page_state & PAGE_WAS_ON_DEFERRED_LIST) {
>> +		struct deferred_split *ds_queue = get_deferred_split_queue(src);
>
> do you mean dst here?

Right. I forgot the case of migrating from one node to another and thought
either src or dst works. Thanks.
>
>> +
>> +		spin_lock(&ds_queue->split_queue_lock);
>> +		ds_queue->split_queue_len++;
>> +		list_add(&dst->_deferred_list, &ds_queue->split_queue);
>> +		spin_unlock(&ds_queue->split_queue_lock);
>> +	}
>> +
>>  out_unlock_both:
>>  	folio_unlock(dst);
>>  	set_page_owner_migrate_reason(&dst->page, reason);


--
Best Regards,
Yan, Zi

[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 854 bytes --]