Re: [PATCH] mm/thp: expose deferred split folio memory usage in meminfo

+cc Johannes

On Fri, Jul 17, 2026 at 02:30:22PM +0800, Ye Liu wrote:
> From: Ye Liu <[email protected]>
>
> Folios on the deferred split list hold physical memory that is
> invisible in meminfo. When a THP becomes partially mapped, the
> unmapped pages are removed from AnonPages but remain physically
> allocated until the shrinker splits the folio. This creates a
> memory accounting gap where used memory cannot be attributed to
> any meminfo field.

Is this really that much of an issue? You're not giving any use cases here.

What real-world use case motivated this?

>
> Add NR_DEFERRED_SPLIT_PAGES to track the total memory consumed by
> folios currently on the deferred_split_lru, updated via
> mod_node_page_state() at all enqueue/dequeue points. The new field
> DeferredSplitPages is visible in /proc/meminfo, /proc/vmstat, and
> per-node /sys/devices/system/node/node*/meminfo.

Again you're not justifying anything, why do you need a per-node breakdown?

>
> Signed-off-by: Ye Liu <[email protected]>

You're updating these stats in a number of places and you've given zero
explanataion or evidence that you're accounting this correctly.

This is very subtle code and you're a very new contributor to this so I
wouldn't want us to take someting like this even if it was justified
without a very strong argument.

You'd probably want to do some refactoring stuff first also to combine any
such updates with moves.

> ---
>  drivers/base/node.c    |  4 +++-
>  fs/proc/meminfo.c      |  2 ++
>  include/linux/mmzone.h |  1 +
>  mm/huge_memory.c       | 24 +++++++++++++++++++++---
>  mm/vmstat.c            |  1 +
>  5 files changed, 28 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/base/node.c b/drivers/base/node.c
> index 3da91929ad4e..69463438300e 100644
> --- a/drivers/base/node.c
> +++ b/drivers/base/node.c
> @@ -519,6 +519,7 @@ static ssize_t node_read_meminfo(struct device *dev,
>  			     "Node %d ShmemPmdMapped: %8lu kB\n"
>  			     "Node %d FileHugePages:  %8lu kB\n"
>  			     "Node %d FilePmdMapped:  %8lu kB\n"
> +			     "Node %d DeferredSplitPages: %8lu kB\n"
>  #endif
>  #ifdef CONFIG_UNACCEPTED_MEMORY
>  			     "Node %d Unaccepted:     %8lu kB\n"
> @@ -553,7 +554,8 @@ static ssize_t node_read_meminfo(struct device *dev,
>  			     nid, K(node_page_state(pgdat, NR_SHMEM_THPS)),
>  			     nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)),
>  			     nid, K(node_page_state(pgdat, NR_FILE_THPS)),
> -			     nid, K(node_page_state(pgdat, NR_FILE_PMDMAPPED))
> +			     nid, K(node_page_state(pgdat, NR_FILE_PMDMAPPED)),
> +			     nid, K(node_page_state(pgdat, NR_DEFERRED_SPLIT_PAGES))
>  #endif
>  #ifdef CONFIG_UNACCEPTED_MEMORY
>  			     ,
> diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
> index b2813ff13cb2..76dbf51ad1e0 100644
> --- a/fs/proc/meminfo.c
> +++ b/fs/proc/meminfo.c
> @@ -149,6 +149,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
>  		    global_node_page_state(NR_FILE_THPS));
>  	show_val_kb(m, "FilePmdMapped:  ",
>  		    global_node_page_state(NR_FILE_PMDMAPPED));
> +	show_val_kb(m, "DeferredSplitPages: ",
> +		    global_node_page_state(NR_DEFERRED_SPLIT_PAGES));
>  #endif
>
>  #ifdef CONFIG_CMA
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index 0507193b3ae3..1e75adb73d00 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -267,6 +267,7 @@ enum node_stat_item {
>  	NR_FILE_THPS,
>  	NR_FILE_PMDMAPPED,
>  	NR_ANON_THPS,
> +	NR_DEFERRED_SPLIT_PAGES, /* THP/mTHP pages pending deferred split */
>  	NR_VMSCAN_WRITE,
>  	NR_VMSCAN_IMMEDIATE,	/* Prioritise for reclaim when writeback ends */
>  	NR_DIRTIED,		/* page dirtyings since bootup */
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index c642bec967fa..1094b844675c 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -77,6 +77,14 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
>  					 struct shrink_control *sc);
>  static bool split_underused_thp = true;
>
> +#define deferred_split_pages_add(folio) \
> +	mod_node_page_state(NODE_DATA(folio_nid(folio)), \
> +			    NR_DEFERRED_SPLIT_PAGES, folio_nr_pages(folio))
> +
> +#define deferred_split_pages_del(folio) \
> +	mod_node_page_state(NODE_DATA(folio_nid(folio)), \
> +			    NR_DEFERRED_SPLIT_PAGES, -folio_nr_pages(folio))

Why are these macros?

I really dislike the naming too, these read like they're actually
adding/deleting pages.

> +
>  static atomic_t huge_zero_refcount;
>  struct folio *huge_zero_folio __read_mostly;
>  unsigned long huge_zero_pfn __read_mostly = ~0UL;
> @@ -3913,8 +3921,10 @@ static int __folio_freeze_and_split_unmapped(struct folio *folio, unsigned int n
>  		struct lruvec *lruvec;
>
>  		if (dequeue_deferred) {
> -			__list_lru_del(&deferred_split_lru, lru,
> -				       &folio->_deferred_list, folio_nid(folio));
> +			if (__list_lru_del(&deferred_split_lru, lru,
> +					  &folio->_deferred_list, folio_nid(folio)) &&
> +			    folio_test_partially_mapped(folio))
> +				deferred_split_pages_del(folio);
>  			if (folio_test_partially_mapped(folio)) {
>  				folio_clear_partially_mapped(folio);
>  				mod_mthp_stat(old_order,
> @@ -4415,6 +4425,7 @@ bool __folio_unqueue_deferred_split(struct folio *folio)
>  	lru = list_lru_lock_irqsave(&deferred_split_lru, nid, &memcg, &flags);
>  	if (__list_lru_del(&deferred_split_lru, lru, &folio->_deferred_list, nid)) {
>  		if (folio_test_partially_mapped(folio)) {
> +			deferred_split_pages_del(folio);
>  			folio_clear_partially_mapped(folio);
>  			mod_mthp_stat(folio_order(folio),
>  				      MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
> @@ -4473,6 +4484,8 @@ void deferred_split_folio(struct folio *folio, bool partially_mapped)
>  		VM_WARN_ON_FOLIO(folio_test_partially_mapped(folio), folio);
>  	}
>  	__list_lru_add(&deferred_split_lru, lru, &folio->_deferred_list, nid, memcg);
> +	if (partially_mapped)
> +		deferred_split_pages_add(folio);
>  	list_lru_unlock_irqrestore(lru, &flags);
>  	rcu_read_unlock();
>  }
> @@ -4524,8 +4537,11 @@ static enum lru_status deferred_split_isolate(struct list_head *item,
>  {
>  	struct folio *folio = container_of(item, struct folio, _deferred_list);
>  	struct list_head *freeable = cb_arg;
> +	bool partially_mapped = folio_test_partially_mapped(folio);
>
>  	if (folio_try_get(folio)) {
> +		if (partially_mapped)
> +			deferred_split_pages_del(folio);
>  		list_lru_isolate_move(lru, item, freeable);
>  		return LRU_REMOVED;
>  	}
> @@ -4535,7 +4551,8 @@ static enum lru_status deferred_split_isolate(struct list_head *item,
>  	 * isolate: folio_unqueue_deferred_split() checks list_empty()
>  	 * locklessly, so once removed the folio can be freed any time.
>  	 */
> -	if (folio_test_partially_mapped(folio)) {
> +	if (partially_mapped) {
> +		deferred_split_pages_del(folio);
>  		folio_clear_partially_mapped(folio);
>  		mod_mthp_stat(folio_order(folio),
>  			      MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
> @@ -4596,6 +4613,7 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
>  					 &folio->_deferred_list,
>  					 folio_nid(folio),
>  					 folio_memcg(folio));
> +			deferred_split_pages_add(folio);
>  			rcu_read_unlock();
>  		}
>  		folio_put(folio);
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> index 3b5cb1031f72..ba71cc3e4c30 100644
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -1248,6 +1248,7 @@ const char * const vmstat_text[] = {
>  	[I(NR_FILE_THPS)]			= "nr_file_hugepages",
>  	[I(NR_FILE_PMDMAPPED)]			= "nr_file_pmdmapped",
>  	[I(NR_ANON_THPS)]			= "nr_anon_transparent_hugepages",
> +	[I(NR_DEFERRED_SPLIT_PAGES)]		= "nr_deferred_split_pages",
>  	[I(NR_VMSCAN_WRITE)]			= "nr_vmscan_write",
>  	[I(NR_VMSCAN_IMMEDIATE)]		= "nr_vmscan_immediate_reclaim",
>  	[I(NR_DIRTIED)]				= "nr_dirtied",
> --
> 2.43.0
>

Cheers, Lorenzo