[PATCH V2 1/2] mm/filemap: Add NUMA mempolicy support to filemap_alloc_folio()

[PATCH V2 1/2] mm/filemap: Add NUMA mempolicy support to filemap_alloc_folio()

[Shivank Garg]

From: "Matthew Wilcox (Oracle)" <willy@infradead.org>

Add a mempolicy parameter to filemap_alloc_folio() to enable NUMA-aware
page cache allocations. This will be used by upcoming changes to
support NUMA policies in guest-memfd, where guest_memory needs to be
allocated according to NUMA policy specified by the VMM.

All existing users pass NULL maintaining current behavior.

Reviewed-by: Pankaj Gupta <pankaj.gupta@amd.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Shivank Garg <shivankg@amd.com>
---
Changes in V2:
- fix checkpatch warnings.
- touch up commit description and fix code alignments to make it
  more readable.

V1: https://lore.kernel.org/all/20250620143502.3055777-1-willy@infradead.org

 fs/bcachefs/fs-io-buffered.c |  2 +-
 fs/btrfs/compression.c       |  4 ++--
 fs/btrfs/verity.c            |  2 +-
 fs/erofs/zdata.c             |  2 +-
 fs/f2fs/compress.c           |  2 +-
 include/linux/pagemap.h      |  8 +++++---
 mm/filemap.c                 | 14 +++++++++-----
 mm/readahead.c               |  2 +-
 8 files changed, 21 insertions(+), 15 deletions(-)

diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c
index 66bacdd49f78..392344232b16 100644
--- a/fs/bcachefs/fs-io-buffered.c
+++ b/fs/bcachefs/fs-io-buffered.c
@@ -124,7 +124,7 @@ static int readpage_bio_extend(struct btree_trans *trans,
 			if (folio && !xa_is_value(folio))
 				break;
 
-			folio = filemap_alloc_folio(readahead_gfp_mask(iter->mapping), order);
+			folio = filemap_alloc_folio(readahead_gfp_mask(iter->mapping), order, NULL);
 			if (!folio)
 				break;
 
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 48d07939fee4..a0808c8f897f 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -474,8 +474,8 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 			continue;
 		}
 
-		folio = filemap_alloc_folio(mapping_gfp_constraint(mapping,
-								   ~__GFP_FS), 0);
+		folio = filemap_alloc_folio(mapping_gfp_constraint(mapping, ~__GFP_FS),
+					    0, NULL);
 		if (!folio)
 			break;
 
diff --git a/fs/btrfs/verity.c b/fs/btrfs/verity.c
index b7a96a005487..c43a789ba6d2 100644
--- a/fs/btrfs/verity.c
+++ b/fs/btrfs/verity.c
@@ -742,7 +742,7 @@ static struct page *btrfs_read_merkle_tree_page(struct inode *inode,
 	}
 
 	folio = filemap_alloc_folio(mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS),
-				    0);
+				    0, NULL);
 	if (!folio)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index fe8071844724..00e9160a0d24 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -562,7 +562,7 @@ static void z_erofs_bind_cache(struct z_erofs_frontend *fe)
 			 * Allocate a managed folio for cached I/O, or it may be
 			 * then filled with a file-backed folio for in-place I/O
 			 */
-			newfolio = filemap_alloc_folio(gfp, 0);
+			newfolio = filemap_alloc_folio(gfp, 0, NULL);
 			if (!newfolio)
 				continue;
 			newfolio->private = Z_EROFS_PREALLOCATED_FOLIO;
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index b3c1df93a163..7ef937dd7624 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -1942,7 +1942,7 @@ void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi, struct page *page,
 		return;
 	}
 
-	cfolio = filemap_alloc_folio(__GFP_NOWARN | __GFP_IO, 0);
+	cfolio = filemap_alloc_folio(__GFP_NOWARN | __GFP_IO, 0, NULL);
 	if (!cfolio)
 		return;
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index e63fbfbd5b0f..78ea357d2077 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -646,9 +646,11 @@ static inline void *detach_page_private(struct page *page)
 }
 
 #ifdef CONFIG_NUMA
-struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order);
+struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order,
+		struct mempolicy *policy);
 #else
-static inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order)
+static inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order,
+		struct mempolicy *policy)
 {
 	return folio_alloc_noprof(gfp, order);
 }
@@ -659,7 +661,7 @@ static inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int o
 
 static inline struct page *__page_cache_alloc(gfp_t gfp)
 {
-	return &filemap_alloc_folio(gfp, 0)->page;
+	return &filemap_alloc_folio(gfp, 0, NULL)->page;
 }
 
 static inline gfp_t readahead_gfp_mask(struct address_space *x)
diff --git a/mm/filemap.c b/mm/filemap.c
index bada249b9fb7..a30cd4dd085a 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -989,11 +989,16 @@ int filemap_add_folio(struct address_space *mapping, struct folio *folio,
 EXPORT_SYMBOL_GPL(filemap_add_folio);
 
 #ifdef CONFIG_NUMA
-struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order)
+struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order,
+		struct mempolicy *policy)
 {
 	int n;
 	struct folio *folio;
 
+	if (policy)
+		return folio_alloc_mpol_noprof(gfp, order, policy,
+				NO_INTERLEAVE_INDEX, numa_node_id());
+
 	if (cpuset_do_page_mem_spread()) {
 		unsigned int cpuset_mems_cookie;
 		do {
@@ -1977,7 +1982,7 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 			err = -ENOMEM;
 			if (order > min_order)
 				alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN;
-			folio = filemap_alloc_folio(alloc_gfp, order);
+			folio = filemap_alloc_folio(alloc_gfp, order, NULL);
 			if (!folio)
 				continue;
 
@@ -2516,7 +2521,7 @@ static int filemap_create_folio(struct kiocb *iocb, struct folio_batch *fbatch)
 	if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ))
 		return -EAGAIN;
 
-	folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order);
+	folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order, NULL);
 	if (!folio)
 		return -ENOMEM;
 	if (iocb->ki_flags & IOCB_DONTCACHE)
@@ -3853,8 +3858,7 @@ static struct folio *do_read_cache_folio(struct address_space *mapping,
 repeat:
 	folio = filemap_get_folio(mapping, index);
 	if (IS_ERR(folio)) {
-		folio = filemap_alloc_folio(gfp,
-					    mapping_min_folio_order(mapping));
+		folio = filemap_alloc_folio(gfp, mapping_min_folio_order(mapping), NULL);
 		if (!folio)
 			return ERR_PTR(-ENOMEM);
 		index = mapping_align_index(mapping, index);
diff --git a/mm/readahead.c b/mm/readahead.c
index 20d36d6b055e..0b2aec0231e6 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -183,7 +183,7 @@ static struct folio *ractl_alloc_folio(struct readahead_control *ractl,
 {
 	struct folio *folio;
 
-	folio = filemap_alloc_folio(gfp_mask, order);
+	folio = filemap_alloc_folio(gfp_mask, order, NULL);
 	if (folio && ractl->dropbehind)
 		__folio_set_dropbehind(folio);
 
-- 
2.43.0

[PATCH V2 2/2] mm/filemap: Extend __filemap_get_folio() to support NUMA memory policies

[Shivank Garg]

From: "Matthew Wilcox (Oracle)" <willy@infradead.org>

Extend __filemap_get_folio() to support NUMA memory policies by
renaming the implementation to __filemap_get_folio_mpol() and adding
a mempolicy parameter. The original function becomes a static inline
wrapper that passes NULL for the mempolicy.

This infrastructure will enable future support for NUMA-aware page cache
allocations in guest_memfd memory backend KVM guests.

Reviewed-by: Pankaj Gupta <pankaj.gupta@amd.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Shivank Garg <shivankg@amd.com>
---
Changes in V2:
- fix checkpatch warnings.
- touch up commit description and fix code alignments to make it
  more readable.
V1:
https://lore.kernel.org/all/20250620143502.3055777-2-willy@infradead.org

 include/linux/pagemap.h | 10 ++++++++--
 mm/filemap.c            | 11 ++++++-----
 2 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 78ea357d2077..981ff97b4445 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -747,11 +747,17 @@ static inline fgf_t fgf_set_order(size_t size)
 }
 
 void *filemap_get_entry(struct address_space *mapping, pgoff_t index);
-struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
-		fgf_t fgp_flags, gfp_t gfp);
+struct folio *__filemap_get_folio_mpol(struct address_space *mapping,
+		pgoff_t index, fgf_t fgf_flags, gfp_t gfp, struct mempolicy *policy);
 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
 		fgf_t fgp_flags, gfp_t gfp);
 
+static inline struct folio *__filemap_get_folio(struct address_space *mapping,
+		pgoff_t index, fgf_t fgf_flags, gfp_t gfp)
+{
+	return __filemap_get_folio_mpol(mapping, index, fgf_flags, gfp, NULL);
+}
+
 /**
  * filemap_get_folio - Find and get a folio.
  * @mapping: The address_space to search.
diff --git a/mm/filemap.c b/mm/filemap.c
index a30cd4dd085a..ec7de38c17c1 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1896,11 +1896,12 @@ void *filemap_get_entry(struct address_space *mapping, pgoff_t index)
 }
 
 /**
- * __filemap_get_folio - Find and get a reference to a folio.
+ * __filemap_get_folio_mpol - Find and get a reference to a folio.
  * @mapping: The address_space to search.
  * @index: The page index.
  * @fgp_flags: %FGP flags modify how the folio is returned.
  * @gfp: Memory allocation flags to use if %FGP_CREAT is specified.
+ * @policy: NUMA memory allocation policy to follow.
  *
  * Looks up the page cache entry at @mapping & @index.
  *
@@ -1911,8 +1912,8 @@ void *filemap_get_entry(struct address_space *mapping, pgoff_t index)
  *
  * Return: The found folio or an ERR_PTR() otherwise.
  */
-struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
-		fgf_t fgp_flags, gfp_t gfp)
+struct folio *__filemap_get_folio_mpol(struct address_space *mapping,
+		pgoff_t index, fgf_t fgp_flags, gfp_t gfp, struct mempolicy *policy)
 {
 	struct folio *folio;
 
@@ -1982,7 +1983,7 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 			err = -ENOMEM;
 			if (order > min_order)
 				alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN;
-			folio = filemap_alloc_folio(alloc_gfp, order, NULL);
+			folio = filemap_alloc_folio(alloc_gfp, order, policy);
 			if (!folio)
 				continue;
 
@@ -2029,7 +2030,7 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 		folio_clear_dropbehind(folio);
 	return folio;
 }
-EXPORT_SYMBOL(__filemap_get_folio);
+EXPORT_SYMBOL(__filemap_get_folio_mpol);
 
 static inline struct folio *find_get_entry(struct xa_state *xas, pgoff_t max,
 		xa_mark_t mark)
-- 
2.43.0

Re: [PATCH V2 1/2] mm/filemap: Add NUMA mempolicy support to filemap_alloc_folio()

[Matthew Wilcox]

On Mon, Jun 23, 2025 at 09:39:41AM +0000, Shivank Garg wrote:
> From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
> 
> Add a mempolicy parameter to filemap_alloc_folio() to enable NUMA-aware
> page cache allocations. This will be used by upcoming changes to
> support NUMA policies in guest-memfd, where guest_memory needs to be
> allocated according to NUMA policy specified by the VMM.
> 
> All existing users pass NULL maintaining current behavior.

I don't want to see this as a separate series.  I want to see it as part
of the series that introduces the user.

Andrew, please drop these two patches from your tree.