[PATCH v13 14/35] mm: Add AS_UNMOVABLE to mark mapping as completely unmovable

[Paolo Bonzini]

On 10/27/23 20:21, Sean Christopherson wrote:
> Add an "unmovable" flag for mappings that cannot be migrated under any
> circumstance.  KVM will use the flag for its upcoming GUEST_MEMFD support,
> which will not support compaction/migration, at least not in the
> foreseeable future.
> 
> Test AS_UNMOVABLE under folio lock as already done for the async
> compaction/dirty folio case, as the mapping can be removed by truncation
> while compaction is running.  To avoid having to lock every folio with a
> mapping, assume/require that unmovable mappings are also unevictable, and
> have mapping_set_unmovable() also set AS_UNEVICTABLE.
> 
> Cc: Matthew Wilcox <willy at infradead.org>
> Co-developed-by: Vlastimil Babka <vbabka at suse.cz>
> Signed-off-by: Vlastimil Babka <vbabka at suse.cz>
> Signed-off-by: Sean Christopherson <seanjc at google.com>

I think this could even be "From: Vlastimil", but no biggie.

Paolo

> ---
>   include/linux/pagemap.h | 19 +++++++++++++++++-
>   mm/compaction.c         | 43 +++++++++++++++++++++++++++++------------
>   mm/migrate.c            |  2 ++
>   3 files changed, 51 insertions(+), 13 deletions(-)
> 
> diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
> index 351c3b7f93a1..82c9bf506b79 100644
> --- a/include/linux/pagemap.h
> +++ b/include/linux/pagemap.h
> @@ -203,7 +203,8 @@ enum mapping_flags {
>   	/* writeback related tags are not used */
>   	AS_NO_WRITEBACK_TAGS = 5,
>   	AS_LARGE_FOLIO_SUPPORT = 6,
> -	AS_RELEASE_ALWAYS,	/* Call ->release_folio(), even if no private data */
> +	AS_RELEASE_ALWAYS = 7,	/* Call ->release_folio(), even if no private data */
> +	AS_UNMOVABLE	= 8,	/* The mapping cannot be moved, ever */
>   };
>   
>   /**
> @@ -289,6 +290,22 @@ static inline void mapping_clear_release_always(struct address_space *mapping)
>   	clear_bit(AS_RELEASE_ALWAYS, &mapping->flags);
>   }
>   
> +static inline void mapping_set_unmovable(struct address_space *mapping)
> +{
> +	/*
> +	 * It's expected unmovable mappings are also unevictable. Compaction
> +	 * migrate scanner (isolate_migratepages_block()) relies on this to
> +	 * reduce page locking.
> +	 */
> +	set_bit(AS_UNEVICTABLE, &mapping->flags);
> +	set_bit(AS_UNMOVABLE, &mapping->flags);
> +}
> +
> +static inline bool mapping_unmovable(struct address_space *mapping)
> +{
> +	return test_bit(AS_UNMOVABLE, &mapping->flags);
> +}
> +
>   static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
>   {
>   	return mapping->gfp_mask;
> diff --git a/mm/compaction.c b/mm/compaction.c
> index 38c8d216c6a3..12b828aed7c8 100644
> --- a/mm/compaction.c
> +++ b/mm/compaction.c
> @@ -883,6 +883,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
>   
>   	/* Time to isolate some pages for migration */
>   	for (; low_pfn < end_pfn; low_pfn++) {
> +		bool is_dirty, is_unevictable;
>   
>   		if (skip_on_failure && low_pfn >= next_skip_pfn) {
>   			/*
> @@ -1080,8 +1081,10 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
>   		if (!folio_test_lru(folio))
>   			goto isolate_fail_put;
>   
> +		is_unevictable = folio_test_unevictable(folio);
> +
>   		/* Compaction might skip unevictable pages but CMA takes them */
> -		if (!(mode & ISOLATE_UNEVICTABLE) && folio_test_unevictable(folio))
> +		if (!(mode & ISOLATE_UNEVICTABLE) && is_unevictable)
>   			goto isolate_fail_put;
>   
>   		/*
> @@ -1093,26 +1096,42 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
>   		if ((mode & ISOLATE_ASYNC_MIGRATE) && folio_test_writeback(folio))
>   			goto isolate_fail_put;
>   
> -		if ((mode & ISOLATE_ASYNC_MIGRATE) && folio_test_dirty(folio)) {
> -			bool migrate_dirty;
> +		is_dirty = folio_test_dirty(folio);
> +
> +		if (((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) ||
> +		    (mapping && is_unevictable)) {
> +			bool migrate_dirty = true;
> +			bool is_unmovable;
>   
>   			/*
>   			 * Only folios without mappings or that have
> -			 * a ->migrate_folio callback are possible to
> -			 * migrate without blocking.  However, we may
> -			 * be racing with truncation, which can free
> -			 * the mapping.  Truncation holds the folio lock
> -			 * until after the folio is removed from the page
> -			 * cache so holding it ourselves is sufficient.
> +			 * a ->migrate_folio callback are possible to migrate
> +			 * without blocking.
> +			 *
> +			 * Folios from unmovable mappings are not migratable.
> +			 *
> +			 * However, we can be racing with truncation, which can
> +			 * free the mapping that we need to check. Truncation
> +			 * holds the folio lock until after the folio is removed
> +			 * from the page so holding it ourselves is sufficient.
> +			 *
> +			 * To avoid locking the folio just to check unmovable,
> +			 * assume every unmovable folio is also unevictable,
> +			 * which is a cheaper test.  If our assumption goes
> +			 * wrong, it's not a correctness bug, just potentially
> +			 * wasted cycles.
>   			 */
>   			if (!folio_trylock(folio))
>   				goto isolate_fail_put;
>   
>   			mapping = folio_mapping(folio);
> -			migrate_dirty = !mapping ||
> -					mapping->a_ops->migrate_folio;
> +			if ((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) {
> +				migrate_dirty = !mapping ||
> +						mapping->a_ops->migrate_folio;
> +			}
> +			is_unmovable = mapping && mapping_unmovable(mapping);
>   			folio_unlock(folio);
> -			if (!migrate_dirty)
> +			if (!migrate_dirty || is_unmovable)
>   				goto isolate_fail_put;
>   		}
>   
> diff --git a/mm/migrate.c b/mm/migrate.c
> index 2053b54556ca..ed874e43ecd7 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -956,6 +956,8 @@ static int move_to_new_folio(struct folio *dst, struct folio *src,
>   
>   		if (!mapping)
>   			rc = migrate_folio(mapping, dst, src, mode);
> +		else if (mapping_unmovable(mapping))
> +			rc = -EOPNOTSUPP;
>   		else if (mapping->a_ops->migrate_folio)
>   			/*
>   			 * Most folios have a mapping and most filesystems