A common operation in tiering is to migrate multiple pages at once.
The migrate_misplaced_folio function requires one call for each
individual folio.  Expose a batch-variant of the same call for use
when doing batch migrations.

Signed-off-by: Gregory Price <gourry@gourry.net>
---
 include/linux/migrate.h |  6 ++++++
 mm/migrate.c            | 31 +++++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+)

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 61899ec7a9a3..2df756128316 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -145,6 +145,7 @@ const struct movable_operations *page_movable_ops(struct page *page)
 int migrate_misplaced_folio_prepare(struct folio *folio,
 		struct vm_area_struct *vma, int node);
 int migrate_misplaced_folio(struct folio *folio, int node);
+int migrate_misplaced_folio_batch(struct list_head *foliolist, int node);
 #else
 static inline int migrate_misplaced_folio_prepare(struct folio *folio,
 		struct vm_area_struct *vma, int node)
@@ -155,6 +156,11 @@ static inline int migrate_misplaced_folio(struct folio *folio, int node)
 {
 	return -EAGAIN; /* can't migrate now */
 }
+static inline int migrate_misplaced_folio_batch(struct list_head *foliolist,
+						int node)
+{
+	return -EAGAIN; /* can't migrate now */
+}
 #endif /* CONFIG_NUMA_BALANCING */
 
 #ifdef CONFIG_MIGRATION
diff --git a/mm/migrate.c b/mm/migrate.c
index 047131f6c839..7e1ba6001596 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2731,5 +2731,36 @@ int migrate_misplaced_folio(struct folio *folio, int node)
 	BUG_ON(!list_empty(&migratepages));
 	return nr_remaining ? -EAGAIN : 0;
 }
+
+/*
+ * Batch variant of migrate_misplaced_folio. Attempts to migrate
+ * a folio list to the specified destination.
+ *
+ * Caller is expected to have isolated the folios by calling
+ * migrate_misplaced_folio_prepare(), which will result in an
+ * elevated reference count on the folio.
+ *
+ * This function will un-isolate the folios, dereference them, and
+ * remove them from the list before returning.
+ */
+int migrate_misplaced_folio_batch(struct list_head *folio_list, int node)
+{
+	pg_data_t *pgdat = NODE_DATA(node);
+	unsigned int nr_succeeded;
+	int nr_remaining;
+
+	nr_remaining = migrate_pages(folio_list, alloc_misplaced_dst_folio,
+				     NULL, node, MIGRATE_ASYNC,
+				     MR_NUMA_MISPLACED, &nr_succeeded);
+	if (nr_remaining)
+		putback_movable_pages(folio_list);
+
+	if (nr_succeeded) {
+		count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_succeeded);
+		mod_node_page_state(pgdat, PGPROMOTE_SUCCESS, nr_succeeded);
+	}
+	BUG_ON(!list_empty(folio_list));
+	return nr_remaining ? -EAGAIN : 0;
+}
 #endif /* CONFIG_NUMA_BALANCING */
 #endif /* CONFIG_NUMA */
-- 
2.49.0

On Fri, 11 Apr 2025 18:11:09 -0400 Gregory Price <gourry@gourry.net> wrote:

> A common operation in tiering is to migrate multiple pages at once.
> The migrate_misplaced_folio function requires one call for each
> individual folio.  Expose a batch-variant of the same call for use
> when doing batch migrations.
> 
> Signed-off-by: Gregory Price <gourry@gourry.net>
> ---
>  include/linux/migrate.h |  6 ++++++
>  mm/migrate.c            | 31 +++++++++++++++++++++++++++++++
>  2 files changed, 37 insertions(+)
> 
> diff --git a/include/linux/migrate.h b/include/linux/migrate.h
> index 61899ec7a9a3..2df756128316 100644
> --- a/include/linux/migrate.h
> +++ b/include/linux/migrate.h
> @@ -145,6 +145,7 @@ const struct movable_operations *page_movable_ops(struct page *page)
>  int migrate_misplaced_folio_prepare(struct folio *folio,
>  		struct vm_area_struct *vma, int node);
>  int migrate_misplaced_folio(struct folio *folio, int node);
> +int migrate_misplaced_folio_batch(struct list_head *foliolist, int node);

Nit.  s/foliolist/folio_list/ ?

The none-inline-definition of the function below calls the parameter
folio_list, and I show more treewide usage of folio_list than foliolist.

    linux$ git grep foliolist | wc -l
    4
    linux$ git grep folio_list | wc -l
    142

I wouldn't argue folio_list is the only one right name, but at least using same
name on the declaration and the definition[s] would be nice in terms of
consistency.

>  #else
>  static inline int migrate_misplaced_folio_prepare(struct folio *folio,
>  		struct vm_area_struct *vma, int node)
> @@ -155,6 +156,11 @@ static inline int migrate_misplaced_folio(struct folio *folio, int node)
>  {
>  	return -EAGAIN; /* can't migrate now */
>  }
> +static inline int migrate_misplaced_folio_batch(struct list_head *foliolist,

Ditto.

> +						int node)
> +{
> +	return -EAGAIN; /* can't migrate now */
> +}
>  #endif /* CONFIG_NUMA_BALANCING */
>  
>  #ifdef CONFIG_MIGRATION
> diff --git a/mm/migrate.c b/mm/migrate.c
> index 047131f6c839..7e1ba6001596 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -2731,5 +2731,36 @@ int migrate_misplaced_folio(struct folio *folio, int node)
>  	BUG_ON(!list_empty(&migratepages));
>  	return nr_remaining ? -EAGAIN : 0;
>  }
> +
> +/*
> + * Batch variant of migrate_misplaced_folio. Attempts to migrate
> + * a folio list to the specified destination.
> + *
> + * Caller is expected to have isolated the folios by calling
> + * migrate_misplaced_folio_prepare(), which will result in an
> + * elevated reference count on the folio.
> + *
> + * This function will un-isolate the folios, dereference them, and
> + * remove them from the list before returning.
> + */
> +int migrate_misplaced_folio_batch(struct list_head *folio_list, int node)
> +{
> +	pg_data_t *pgdat = NODE_DATA(node);
> +	unsigned int nr_succeeded;
> +	int nr_remaining;
> +
> +	nr_remaining = migrate_pages(folio_list, alloc_misplaced_dst_folio,
> +				     NULL, node, MIGRATE_ASYNC,
> +				     MR_NUMA_MISPLACED, &nr_succeeded);
> +	if (nr_remaining)
> +		putback_movable_pages(folio_list);
> +
> +	if (nr_succeeded) {
> +		count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_succeeded);

migrate_misplaced_folio() also counts memcg events and call mod_lruvec_state(),
but this variant doesn't.  Is this an intended difference?  If so, could you
please clarify the reason?

> +		mod_node_page_state(pgdat, PGPROMOTE_SUCCESS, nr_succeeded);
> +	}
> +	BUG_ON(!list_empty(folio_list));
> +	return nr_remaining ? -EAGAIN : 0;
> +}

I feel some code here is duplicated from a part of migrate_misplaced_folio().
Can we deduplicate those?  Maybe migrate_misplaced_folio() could be a wrapper
of migrate_mispalced_folio_batch()?


Thanks,
SJ

[...]