Re: [PATCH 2/2] mm: introduce CONFIG_NUMA_MIGRATION and simplify CONFIG_MIGRATION

["Lorenzo Stoakes (Oracle)" <ljs@kernel.org>]

On Thu, Mar 19, 2026 at 09:19:41AM +0100, David Hildenbrand (Arm) wrote:
> CONFIG_MEMORY_HOTREMOVE, CONFIG_COMPACTION and CONFIG_CMA all select
> CONFIG_MIGRATION, because they require it to work (users).
>
> Only CONFIG_NUMA_BALANCING and CONFIG_BALLOON_MIGRATION depend on
> CONFIG_MIGRATION. CONFIG_BALLOON_MIGRATION is not an actual user, but
> an implementation of migration support, so the dependency is correct
> (CONFIG_BALLOON_MIGRATION does not make any sense without
> CONFIG_MIGRATION).
>
> However, kconfig-language.rst  clearly states "In general use select only
> for non-visible symbols". So far CONFIG_MIGRATION is user-visible ...
> and the dependencies rather confusing.
>
> The whole reason why CONFIG_MIGRATION is user-visible is because of
> CONFIG_NUMA: some users might want CONFIG_NUMA but not page migration
> support.
>
> Let's clean all that up by introducing a dedicated CONFIG_NUMA_MIGRATION
> config option for that purpose only. Make CONFIG_NUMA_BALANCING that so
> far depended on CONFIG_NUMA && CONFIG_MIGRATION to depend on
> CONFIG_MIGRATION instead. CONFIG_NUMA_MIGRATION will depend on
> CONFIG_NUMA && CONFIG_MMU.
>
> CONFIG_NUMA_MIGRATION is user-visible and will default to "y". We
> use that default so new configs will automatically enable it, just
> like it was the case with CONFIG_MIGRATION. The downside is that
> some configs that used to have CONFIG_MIGRATION=n might get it
> re-enabled by CONFIG_NUMA_MIGRATION=y, which shouldn't be a problem.
>
> CONFIG_MIGRATION is now a non-visible config option. Any code that
> select CONFIG_MIGRATION (as before) must depend directly or indirectly
> on CONFIG_MMU.

Nice. I always found it odd that it was optional.

>
> CONFIG_NUMA_MIGRATION is responsible for any NUMA migration code, which is
> mempolicy migration code, memory-tiering code, and move_pages() code in
> migrate.c. CONFIG_NUMA_BALANCING uses its functionality.
>
> Note that this implies that with CONFIG_NUMA_MIGRATION=n, move_pages() will
> not be available even though CONFIG_MIGRATION=y, which is an expected
> change.
>
> In migrate.c, we can remove the CONFIG_NUMA check as both
> CONFIG_NUMA_MIGRATION and CONFIG_NUMA_BALANCING depend on it.
>
> With this change, CONFIG_MIGRATION is an internal config, all users of
> migration selects CONFIG_MIGRATION, and only CONFIG_BALLOON_MIGRATION
> depends on it.
>
> Signed-off-by: David Hildenbrand (Arm) <david@kernel.org>

AFAICT this all LGTM, so:

Reviewed-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>

> ---
>  include/linux/memory-tiers.h |  2 +-
>  init/Kconfig                 |  2 +-
>  mm/Kconfig                   | 26 +++++++++++++-------------
>  mm/memory-tiers.c            | 12 ++++++------
>  mm/mempolicy.c               |  2 +-
>  mm/migrate.c                 |  5 ++---
>  6 files changed, 24 insertions(+), 25 deletions(-)
>
> diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
> index 96987d9d95a8..7999c58629ee 100644
> --- a/include/linux/memory-tiers.h
> +++ b/include/linux/memory-tiers.h
> @@ -52,7 +52,7 @@ int mt_perf_to_adistance(struct access_coordinate *perf, int *adist);
>  struct memory_dev_type *mt_find_alloc_memory_type(int adist,
>  						  struct list_head *memory_types);
>  void mt_put_memory_types(struct list_head *memory_types);
> -#ifdef CONFIG_MIGRATION
> +#ifdef CONFIG_NUMA_MIGRATION
>  int next_demotion_node(int node, const nodemask_t *allowed_mask);
>  void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
>  bool node_is_toptier(int node);
> diff --git a/init/Kconfig b/init/Kconfig
> index 444ce811ea67..3648e401b78b 100644
> --- a/init/Kconfig
> +++ b/init/Kconfig
> @@ -997,7 +997,7 @@ config NUMA_BALANCING
>  	bool "Memory placement aware NUMA scheduler"
>  	depends on ARCH_SUPPORTS_NUMA_BALANCING
>  	depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY
> -	depends on SMP && NUMA && MIGRATION && !PREEMPT_RT
> +	depends on SMP && NUMA_MIGRATION && !PREEMPT_RT
>  	help
>  	  This option adds support for automatic NUMA aware memory/task placement.
>  	  The mechanism is quite primitive and is based on migrating memory when
> diff --git a/mm/Kconfig b/mm/Kconfig
> index b2e21d873d3f..bd283958d675 100644
> --- a/mm/Kconfig
> +++ b/mm/Kconfig
> @@ -627,20 +627,20 @@ config PAGE_REPORTING
>  	  those pages to another entity, such as a hypervisor, so that the
>  	  memory can be freed within the host for other uses.
>
> -#
> -# support for page migration
> -#
> -config MIGRATION
> -	bool "Page migration"
> +config NUMA_MIGRATION
> +	bool "NUMA page migration"
>  	default y
> -	depends on (NUMA || MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU
> -	help
> -	  Allows the migration of the physical location of pages of processes
> -	  while the virtual addresses are not changed. This is useful in
> -	  two situations. The first is on NUMA systems to put pages nearer
> -	  to the processors accessing. The second is when allocating huge
> -	  pages as migration can relocate pages to satisfy a huge page
> -	  allocation instead of reclaiming.
> +	depends on NUMA && MMU
> +	select MIGRATION
> +	help
> +	  Support the migration of pages to other NUMA nodes, available to
> +	  user space through interfaces like migrate_pages(), move_pages(),
> +	  and mbind(). Selecting this option also enables support for page
> +	  demotion for memory tiering.
> +
> +config MIGRATION
> +	bool
> +	depends on MMU
>
>  config DEVICE_MIGRATION
>  	def_bool MIGRATION && ZONE_DEVICE
> diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
> index 986f809376eb..54851d8a195b 100644
> --- a/mm/memory-tiers.c
> +++ b/mm/memory-tiers.c
> @@ -69,7 +69,7 @@ bool folio_use_access_time(struct folio *folio)
>  }
>  #endif
>
> -#ifdef CONFIG_MIGRATION
> +#ifdef CONFIG_NUMA_MIGRATION
>  static int top_tier_adistance;
>  /*
>   * node_demotion[] examples:
> @@ -129,7 +129,7 @@ static int top_tier_adistance;
>   *
>   */
>  static struct demotion_nodes *node_demotion __read_mostly;
> -#endif /* CONFIG_MIGRATION */
> +#endif /* CONFIG_NUMA_MIGRATION */
>
>  static BLOCKING_NOTIFIER_HEAD(mt_adistance_algorithms);
>
> @@ -273,7 +273,7 @@ static struct memory_tier *__node_get_memory_tier(int node)
>  				     lockdep_is_held(&memory_tier_lock));
>  }
>
> -#ifdef CONFIG_MIGRATION
> +#ifdef CONFIG_NUMA_MIGRATION
>  bool node_is_toptier(int node)
>  {
>  	bool toptier;
> @@ -519,7 +519,7 @@ static void establish_demotion_targets(void)
>
>  #else
>  static inline void establish_demotion_targets(void) {}
> -#endif /* CONFIG_MIGRATION */
> +#endif /* CONFIG_NUMA_MIGRATION */
>
>  static inline void __init_node_memory_type(int node, struct memory_dev_type *memtype)
>  {
> @@ -911,7 +911,7 @@ static int __init memory_tier_init(void)
>  	if (ret)
>  		panic("%s() failed to register memory tier subsystem\n", __func__);
>
> -#ifdef CONFIG_MIGRATION
> +#ifdef CONFIG_NUMA_MIGRATION
>  	node_demotion = kzalloc_objs(struct demotion_nodes, nr_node_ids);
>  	WARN_ON(!node_demotion);
>  #endif
> @@ -938,7 +938,7 @@ subsys_initcall(memory_tier_init);
>
>  bool numa_demotion_enabled = false;
>
> -#ifdef CONFIG_MIGRATION
> +#ifdef CONFIG_NUMA_MIGRATION
>  #ifdef CONFIG_SYSFS
>  static ssize_t demotion_enabled_show(struct kobject *kobj,
>  				     struct kobj_attribute *attr, char *buf)
> diff --git a/mm/mempolicy.c b/mm/mempolicy.c
> index e5528c35bbb8..fd08771e2057 100644
> --- a/mm/mempolicy.c
> +++ b/mm/mempolicy.c
> @@ -1239,7 +1239,7 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
>  	return err;
>  }
>
> -#ifdef CONFIG_MIGRATION
> +#ifdef CONFIG_NUMA_MIGRATION
>  static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist,
>  				unsigned long flags)
>  {
> diff --git a/mm/migrate.c b/mm/migrate.c
> index fdbb20163f66..05cb408846f2 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -2224,8 +2224,7 @@ struct folio *alloc_migration_target(struct folio *src, unsigned long private)
>  	return __folio_alloc(gfp_mask, order, nid, mtc->nmask);
>  }
>
> -#ifdef CONFIG_NUMA
> -
> +#ifdef CONFIG_NUMA_MIGRATION
>  static int store_status(int __user *status, int start, int value, int nr)
>  {
>  	while (nr-- > 0) {
> @@ -2624,6 +2623,7 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
>  {
>  	return kernel_move_pages(pid, nr_pages, pages, nodes, status, flags);
>  }
> +#endif /* CONFIG_NUMA_MIGRATION */
>
>  #ifdef CONFIG_NUMA_BALANCING
>  /*
> @@ -2766,4 +2766,3 @@ int migrate_misplaced_folio(struct folio *folio, int node)
>  	return nr_remaining ? -EAGAIN : 0;
>  }
>  #endif /* CONFIG_NUMA_BALANCING */
> -#endif /* CONFIG_NUMA */
>
> --
> 2.43.0
>