Re: [PATCH 5/7] mm/migrate: add copy offload registration infrastructure

[David Hildenbrand (Arm)]

On 4/28/26 17:50, Shivank Garg wrote:
> Add a registration interface that lets a single offload provider
> (DMA, multi-threaded CPU copy, etc) take over the batch folio copy
> performed by migrate_pages_batch().
> 
> The provider fills in a struct migrator with an offload_copy()
> callback and calls migrate_offload_register(). Registration patches
> the migrate_offload_copy() static_call and flips the
> migrate_offload_enabled static branch. The migrate_offload_unregister()
> reverts both.
> 
> Whether a migration reason is batch-copy eligible is decided by the
> core in migrate_offload_do_batch(). A migrator may decline a particular
> batch (e.g. when nr_batch is too small to amortize setup) by returning
> -EOPNOTSUPP, and the move phase falls back to per-folio CPU copy.
> 
> Only one migrator can be active at a time. A second registration
> returns -EBUSY, and only the active migrator can unregister itself.
> The static_call dispatch is protected by SRCU so that the
> synchronize_srcu() in unregister waits for all in-flight copy before
> the module reference is dropped.
> 
> Co-developed-by: Mike Day <michael.day@xxxxxxx>
> Signed-off-by: Mike Day <michael.day@xxxxxxx>
> Signed-off-by: Shivank Garg <shivankg@xxxxxxx>

MAINTAINERS file deserves some love (likely put the new files under the
migration section)

> ---
>  include/linux/migrate_copy_offload.h | 44 +++++++++++++
>  mm/Kconfig                           |  6 ++
>  mm/Makefile                          |  1 +
>  mm/migrate.c                         | 57 +++++++++++++++--
>  mm/migrate_copy_offload.c            | 94 ++++++++++++++++++++++++++++
>  5 files changed, 198 insertions(+), 4 deletions(-)
>  create mode 100644 include/linux/migrate_copy_offload.h
>  create mode 100644 mm/migrate_copy_offload.c
> 
> diff --git a/include/linux/migrate_copy_offload.h b/include/linux/migrate_copy_offload.h
> new file mode 100644
> index 000000000000..d68b10a84743
> --- /dev/null
> +++ b/include/linux/migrate_copy_offload.h
> @@ -0,0 +1,44 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#ifndef _LINUX_MIGRATE_COPY_OFFLOAD_H
> +#define _LINUX_MIGRATE_COPY_OFFLOAD_H
> +
> +#include <linux/errno.h>
> +#include <linux/jump_label.h>
> +#include <linux/srcu.h>
> +#include <linux/types.h>
> +
> +struct list_head;
> +struct module;
> +
> +#define MIGRATOR_NAME_LEN 32
> +
> +/**
> + * struct migrator - batch-copy provider for page migration.
> + * @name: name of the provider.
> + * @offload_copy: copy @folio_cnt folios from @src_list to @dst_list.
> + *
> + *	The migrator may inspect @folio_cnt to decide whether the batch
> + * 	is worth offloading, e.g. skip when the batch is too small to
> + * 	amortize setup cost. If returns error, the core falls back to CPU copy.
> + *
> + * @owner: module providing the migrator.
> + */
> +struct migrator {
> +	char name[MIGRATOR_NAME_LEN];
> +	int (*offload_copy)(struct list_head *dst_list,
> +			    struct list_head *src_list,
> +			    unsigned int folio_cnt);
> +	struct module *owner;
> +};
> +
> +#ifdef CONFIG_MIGRATION_COPY_OFFLOAD
> +extern struct static_key_false migrate_offload_enabled;
> +extern struct srcu_struct migrate_offload_srcu;
> +int migrate_offload_register(struct migrator *m);
> +int migrate_offload_unregister(struct migrator *m);
> +#else
> +static inline int migrate_offload_register(struct migrator *m) { return -EOPNOTSUPP; }
> +static inline int migrate_offload_unregister(struct migrator *m) { return -EOPNOTSUPP; }
> +#endif
> +
> +#endif /* _LINUX_MIGRATE_COPY_OFFLOAD_H */
> diff --git a/mm/Kconfig b/mm/Kconfig
> index e8bf1e9e6ad9..325d79619680 100644
> --- a/mm/Kconfig
> +++ b/mm/Kconfig
> @@ -647,6 +647,12 @@ config MIGRATION
>  config DEVICE_MIGRATION
>  	def_bool MIGRATION && ZONE_DEVICE
>  
> +# Page-migration batch-copy offload infrastructure.
> +# Selected by migrator drivers (e.g. CONFIG_DCBM_DMA).
> +config MIGRATION_COPY_OFFLOAD
> +	bool
> +	depends on MIGRATION
> +
>  config ARCH_ENABLE_HUGEPAGE_MIGRATION
>  	bool
>  
> diff --git a/mm/Makefile b/mm/Makefile
> index 8ad2ab08244e..db1ac8097089 100644
> --- a/mm/Makefile
> +++ b/mm/Makefile
> @@ -96,6 +96,7 @@ obj-$(CONFIG_FAILSLAB) += failslab.o
>  obj-$(CONFIG_FAIL_PAGE_ALLOC) += fail_page_alloc.o
>  obj-$(CONFIG_MEMTEST)		+= memtest.o
>  obj-$(CONFIG_MIGRATION) += migrate.o
> +obj-$(CONFIG_MIGRATION_COPY_OFFLOAD) += migrate_copy_offload.o
>  obj-$(CONFIG_NUMA) += memory-tiers.o
>  obj-$(CONFIG_DEVICE_MIGRATION) += migrate_device.o
>  obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o khugepaged.o
> diff --git a/mm/migrate.c b/mm/migrate.c
> index 6c2f1cb66f96..9af070f9a1f2 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -44,6 +44,8 @@
>  #include <linux/memory-tiers.h>
>  #include <linux/pagewalk.h>
>  #include <linux/jump_label.h>
> +#include <linux/static_call.h>
> +#include <linux/migrate_copy_offload.h>
>  
>  #include <asm/tlbflush.h>
>  
> @@ -54,6 +56,51 @@
>  
>  DEFINE_STATIC_KEY_FALSE(migrate_offload_enabled);
>  
> +#ifdef CONFIG_MIGRATION_COPY_OFFLOAD
> +DEFINE_SRCU(migrate_offload_srcu);
> +DEFINE_STATIC_CALL(migrate_offload_copy, folios_mc_copy);
> +
> +static bool migrate_offload_do_batch(int reason)
> +{
> +	if (!static_branch_unlikely(&migrate_offload_enabled))
> +		return false;
> +
> +	switch (reason) {
> +	case MR_COMPACTION:
> +	case MR_SYSCALL:
> +	case MR_DEMOTION:
> +	case MR_NUMA_MISPLACED:
> +		return true;
> +	default:
> +		return false;
> +	}
> +}
> +
> +static int migrate_offload_batch_copy(struct list_head *dst_batch,
> +				      struct list_head *src_batch,
> +				      unsigned int nr_batch)
> +{
> +	int idx, rc;
> +
> +	idx = srcu_read_lock(&migrate_offload_srcu);
> +	rc = static_call(migrate_offload_copy)(dst_batch, src_batch, nr_batch);
> +	srcu_read_unlock(&migrate_offload_srcu, idx);
> +	return rc;
> +}
> +#else
> +static bool migrate_offload_do_batch(int reason)
> +{
> +	return false;
> +}
> +
> +static int migrate_offload_batch_copy(struct list_head *dst_batch,
> +				      struct list_head *src_batch,
> +				      unsigned int nr_batch)
> +{
> +	return -EOPNOTSUPP;
> +}
> +#endif

Can't all that go to migrate_copy_offload.(hc) Looks like a clean interface form
migrate.c, no?

> +
>  static const struct movable_operations *offline_movable_ops;
>  static const struct movable_operations *zsmalloc_movable_ops;
>  
> @@ -1833,7 +1880,7 @@ static int migrate_pages_batch(struct list_head *from,
>  	struct folio *folio, *folio2, *dst = NULL;
>  	int rc, rc_saved = 0, nr_pages;
>  	unsigned int nr_batch = 0;
> -	bool batch_copied = false;
> +	bool do_batch = false, batch_copied = false;
>  	LIST_HEAD(unmap_batch);
>  	LIST_HEAD(dst_batch);
>  	LIST_HEAD(unmap_single);
> @@ -1843,6 +1890,8 @@ static int migrate_pages_batch(struct list_head *from,
>  	VM_WARN_ON_ONCE(mode != MIGRATE_ASYNC &&
>  			!list_empty(from) && !list_is_singular(from));
>  
> +	do_batch = migrate_offload_do_batch(reason);
> +
>  	for (pass = 0; pass < nr_pass && retry; pass++) {
>  		retry = 0;
>  		thp_retry = 0;
> @@ -1984,8 +2033,7 @@ static int migrate_pages_batch(struct list_head *from,
>  				nr_retry_pages += nr_pages;
>  				break;
>  			case 0:
> -				if (static_branch_unlikely(&migrate_offload_enabled) &&
> -				    folio_supports_batch_copy(folio)) {
> +				if (do_batch && folio_supports_batch_copy(folio)) {

I was about to say, the migrate_offload_enabled usage in the previous patch
looks off.

Can you move that to this patch here, and use in the previous patch simply a
default migrate_offload_do_batch() that simply returns "false" ?

>  					list_move_tail(&folio->lru, &unmap_batch);
>  					list_add_tail(&dst->lru, &dst_batch);
>  					nr_batch++;
> @@ -2017,7 +2065,8 @@ static int migrate_pages_batch(struct list_head *from,
>  
>  	/* Batch-copy eligible folios before the move phase */
>  	if (!list_empty(&unmap_batch)) {
> -		rc = folios_mc_copy(&dst_batch, &unmap_batch, nr_batch);
> +		rc = migrate_offload_batch_copy(&dst_batch, &unmap_batch,
> +						nr_batch);
>  		batch_copied = (rc == 0);
>  	}
>  
> diff --git a/mm/migrate_copy_offload.c b/mm/migrate_copy_offload.c
-- 
Cheers,

David