[RFC PATCH 34/40] btrfs: allocate eb-attached btree pages as movable

[Rik van Riel <riel@surriel.com>]

Extent buffer pages allocated by alloc_extent_buffer() are attached to
btree_inode->i_mapping (the buffer_tree path), reach the LRU, and are
served by the btree_migrate_folio aops in fs/btrfs/disk-io.c. They are
migratable in practice once their owning extent buffer hits refs == 1,
which happens naturally as tree roots rotate. The buddy allocator
classifies them by GFP, however, and bare GFP_NOFS lands them in
MIGRATE_UNMOVABLE pageblocks. The result: every btree_inode page we
read in pins an unmovable pageblock from the page-superblock allocator's
perspective, even though the page itself can be moved.

Add __GFP_MOVABLE to that one allocation site (alloc_extent_buffer's
call to alloc_eb_folio_array). Plumb the flag through
alloc_eb_folio_array → btrfs_alloc_page_array as a `gfp_t extra_gfp`
parameter. All other call sites pass 0.

Three categories of caller stay on bare GFP_NOFS, deliberately:

  - alloc_dummy_extent_buffer / btrfs_clone_extent_buffer: the
    resulting eb is EXTENT_BUFFER_UNMAPPED, folio->mapping stays NULL,
    the folios never enter LRU, never get migrate_folio aops. Tagging
    them __GFP_MOVABLE would violate the page allocator's migrability
    contract and they would defeat compaction in MOVABLE pageblocks
    where isolate_migratepages_block skips non-LRU non-movable_ops
    pages outright.

  - btrfs_alloc_page_array callers in fs/btrfs/raid56.c (stripe
    pages), fs/btrfs/inode.c (encoded reads), fs/btrfs/ioctl.c (uring
    encoded reads), fs/btrfs/relocation.c (relocation buffers): same
    contract violation. raid56 stripe_pages additionally persist in
    the stripe cache (RBIO_CACHE_SIZE=1024) well beyond a single I/O,
    so they are not transient enough to hand-wave the contract.

  - btrfs_alloc_folio_array caller in fs/btrfs/scrub.c (stripe
    folios): same -- stripe->folios[] are private buffers freed via
    folio_put in release_scrub_stripe.

This change targets the dominant fragmentation source observed on the
page-superblock series: ~28 GB of btree_inode pages parked across
many tainted superpageblocks on a 250 GB test system with btrfs root,
preventing 1 GiB hugepage allocation from those regions. With the
movable hint, those pages now land in MOVABLE pageblocks where the
existing background defragger drains them through the standard
PB_has_movable gate, no LRU-sample fallback needed.

Cc: Chris Mason <clm@meta.com>
Cc: David Sterba <dsterba@suse.com>
Cc: Boris Burkov <boris@bur.io>
Cc: linux-btrfs@vger.kernel.org
Signed-off-by: Rik van Riel <riel@surriel.com>
Assisted-by: Claude:claude-opus-4.7 syzkaller
---
 fs/btrfs/extent_io.c  | 69 ++++++++++++++++++++++++++++++-------------
 fs/btrfs/extent_io.h  |  4 +--
 fs/btrfs/inode.c      |  2 +-
 fs/btrfs/ioctl.c      |  2 +-
 fs/btrfs/raid56.c     |  6 ++--
 fs/btrfs/relocation.c |  2 +-
 fs/btrfs/scrub.c      |  3 +-
 7 files changed, 59 insertions(+), 29 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 2275189b7860..563c4a7eaa36 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -620,24 +620,33 @@ static void end_bbio_data_read(struct btrfs_bio *bbio)
 }
 
 /*
- * Populate every free slot in a provided array with folios using GFP_NOFS.
+ * Populate every free slot in a provided array with folios using
+ * GFP_NOFS plus optional caller-supplied flags.
  *
- * @nr_folios:   number of folios to allocate
- * @order:	 the order of the folios to be allocated
- * @folio_array: the array to fill with folios; any existing non-NULL entries in
- *		 the array will be skipped
+ * @nr_folios:    number of folios to allocate
+ * @order:	  folio order
+ * @folio_array:  array to fill with folios; non-NULL entries are skipped
+ * @extra_gfp:    extra GFP flags OR'd into GFP_NOFS. The only value used
+ *                today is __GFP_MOVABLE, which the extent-buffer real-mapping
+ *                path (alloc_extent_buffer) passes when the resulting folios
+ *                will be attached to btree_inode->i_mapping (added to LRU,
+ *                served by the btree_migrate_folio aops). Pass 0 for
+ *                everything else; folios allocated by other callers stay in
+ *                driver-owned arrays, never reach LRU and never register
+ *                movable_ops, so they cannot satisfy the __GFP_MOVABLE
+ *                migrability contract.
  *
  * Return: 0        if all folios were able to be allocated;
  *         -ENOMEM  otherwise, the partially allocated folios would be freed and
  *                  the array slots zeroed
  */
 int btrfs_alloc_folio_array(unsigned int nr_folios, unsigned int order,
-			    struct folio **folio_array)
+			    struct folio **folio_array, gfp_t extra_gfp)
 {
 	for (int i = 0; i < nr_folios; i++) {
 		if (folio_array[i])
 			continue;
-		folio_array[i] = folio_alloc(GFP_NOFS, order);
+		folio_array[i] = folio_alloc(GFP_NOFS | extra_gfp, order);
 		if (!folio_array[i])
 			goto error;
 	}
@@ -652,21 +661,27 @@ int btrfs_alloc_folio_array(unsigned int nr_folios, unsigned int order,
 }
 
 /*
- * Populate every free slot in a provided array with pages, using GFP_NOFS.
+ * Populate every free slot in a provided array with pages, using GFP_NOFS
+ * plus optional caller-supplied flags.
  *
- * @nr_pages:   number of pages to allocate
- * @page_array: the array to fill with pages; any existing non-null entries in
- *		the array will be skipped
- * @nofail:	whether using __GFP_NOFAIL flag
+ * @nr_pages:    number of pages to allocate
+ * @page_array:  array to fill; non-NULL entries are skipped
+ * @nofail:      whether to use __GFP_NOFAIL
+ * @extra_gfp:   extra GFP flags OR'd into the base mask. The only value used
+ *               today is __GFP_MOVABLE, which the extent-buffer real-mapping
+ *               path passes when the resulting pages will be attached to
+ *               btree_inode->i_mapping. See btrfs_alloc_folio_array() for
+ *               the full migrability rationale.
  *
  * Return: 0        if all pages were able to be allocated;
  *         -ENOMEM  otherwise, the partially allocated pages would be freed and
  *                  the array slots zeroed
  */
 int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array,
-			   bool nofail)
+			   bool nofail, gfp_t extra_gfp)
 {
-	const gfp_t gfp = nofail ? (GFP_NOFS | __GFP_NOFAIL) : GFP_NOFS;
+	const gfp_t gfp = (nofail ? (GFP_NOFS | __GFP_NOFAIL) : GFP_NOFS) |
+			  extra_gfp;
 	unsigned int allocated;
 
 	for (allocated = 0; allocated < nr_pages;) {
@@ -689,14 +704,23 @@ int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array,
  * Populate needed folios for the extent buffer.
  *
  * For now, the folios populated are always in order 0 (aka, single page).
+ *
+ * @movable: pass true only when the resulting pages will be attached to
+ *           btree_inode->i_mapping (the alloc_extent_buffer real path).
+ *           Cloned/dummy extent buffers (EXTENT_BUFFER_UNMAPPED) leave
+ *           folio->mapping NULL, never enter the LRU, and never get the
+ *           btree_migrate_folio aops, so __GFP_MOVABLE would violate the
+ *           page-allocator's migrability contract for them.
  */
-static int alloc_eb_folio_array(struct extent_buffer *eb, bool nofail)
+static int alloc_eb_folio_array(struct extent_buffer *eb, bool nofail,
+				bool movable)
 {
 	struct page *page_array[INLINE_EXTENT_BUFFER_PAGES] = { 0 };
 	int num_pages = num_extent_pages(eb);
 	int ret;
 
-	ret = btrfs_alloc_page_array(num_pages, page_array, nofail);
+	ret = btrfs_alloc_page_array(num_pages, page_array, nofail,
+				     movable ? __GFP_MOVABLE : 0);
 	if (ret < 0)
 		return ret;
 
@@ -3097,7 +3121,7 @@ struct extent_buffer *btrfs_clone_extent_buffer(const struct extent_buffer *src)
 	 */
 	set_bit(EXTENT_BUFFER_UNMAPPED, &new->bflags);
 
-	ret = alloc_eb_folio_array(new, false);
+	ret = alloc_eb_folio_array(new, false, false);
 	if (ret)
 		goto release_eb;
 
@@ -3138,7 +3162,7 @@ struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
 	if (!eb)
 		return NULL;
 
-	ret = alloc_eb_folio_array(eb, false);
+	ret = alloc_eb_folio_array(eb, false, false);
 	if (ret)
 		goto release_eb;
 
@@ -3491,8 +3515,13 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	}
 
 reallocate:
-	/* Allocate all pages first. */
-	ret = alloc_eb_folio_array(eb, true);
+	/*
+	 * Allocate all pages first. These will be attached to
+	 * btree_inode->i_mapping below (added to LRU, served by
+	 * btree_migrate_folio), so request __GFP_MOVABLE so the
+	 * page allocator places them in MOVABLE pageblocks.
+	 */
+	ret = alloc_eb_folio_array(eb, true, true);
 	if (ret < 0) {
 		btrfs_free_folio_state(prealloc);
 		goto out;
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index b310a5145cf6..5e263f07b59d 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -387,9 +387,9 @@ void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans,
 			      struct extent_buffer *buf);
 
 int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array,
-			   bool nofail);
+			   bool nofail, gfp_t extra_gfp);
 int btrfs_alloc_folio_array(unsigned int nr_folios, unsigned int order,
-			    struct folio **folio_array);
+			    struct folio **folio_array, gfp_t extra_gfp);
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 bool find_lock_delalloc_range(struct inode *inode,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 906d5c21ebc4..85f56ab815f9 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9659,7 +9659,7 @@ ssize_t btrfs_encoded_read_regular(struct kiocb *iocb, struct iov_iter *iter,
 	pages = kzalloc_objs(struct page *, nr_pages, GFP_NOFS);
 	if (!pages)
 		return -ENOMEM;
-	ret = btrfs_alloc_page_array(nr_pages, pages, false);
+	ret = btrfs_alloc_page_array(nr_pages, pages, false, 0);
 	if (ret) {
 		ret = -ENOMEM;
 		goto out;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index a39460bf68a7..77091915cacc 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -4621,7 +4621,7 @@ static int btrfs_uring_read_extent(struct kiocb *iocb, struct iov_iter *iter,
 	pages = kzalloc_objs(struct page *, nr_pages, GFP_NOFS);
 	if (!pages)
 		return -ENOMEM;
-	ret = btrfs_alloc_page_array(nr_pages, pages, 0);
+	ret = btrfs_alloc_page_array(nr_pages, pages, 0, 0);
 	if (ret) {
 		ret = -ENOMEM;
 		goto out_fail;
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 08ee8f316d96..4135bac62be1 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1123,7 +1123,7 @@ static int alloc_rbio_pages(struct btrfs_raid_bio *rbio)
 {
 	int ret;
 
-	ret = btrfs_alloc_page_array(rbio->nr_pages, rbio->stripe_pages, false);
+	ret = btrfs_alloc_page_array(rbio->nr_pages, rbio->stripe_pages, false, 0);
 	if (ret < 0)
 		return ret;
 	/* Mapping all sectors */
@@ -1138,7 +1138,7 @@ static int alloc_rbio_parity_pages(struct btrfs_raid_bio *rbio)
 	int ret;
 
 	ret = btrfs_alloc_page_array(rbio->nr_pages - data_pages,
-				     rbio->stripe_pages + data_pages, false);
+				     rbio->stripe_pages + data_pages, false, 0);
 	if (ret < 0)
 		return ret;
 
@@ -1732,7 +1732,7 @@ static int alloc_rbio_data_pages(struct btrfs_raid_bio *rbio)
 	const int data_pages = rbio->nr_data * rbio->stripe_npages;
 	int ret;
 
-	ret = btrfs_alloc_page_array(data_pages, rbio->stripe_pages, false);
+	ret = btrfs_alloc_page_array(data_pages, rbio->stripe_pages, false, 0);
 	if (ret < 0)
 		return ret;
 
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 3ebaf5880125..6f6d25724fb8 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -4038,7 +4038,7 @@ static int copy_remapped_data(struct btrfs_fs_info *fs_info, u64 old_addr,
 	if (!pages)
 		return -ENOMEM;
 
-	ret = btrfs_alloc_page_array(nr_pages, pages, 0);
+	ret = btrfs_alloc_page_array(nr_pages, pages, 0, 0);
 	if (ret) {
 		ret = -ENOMEM;
 		goto end;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 1ac609239cbe..4089e80077cc 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -369,7 +369,8 @@ static int init_scrub_stripe(struct btrfs_fs_info *fs_info,
 
 	ASSERT(BTRFS_STRIPE_LEN >> min_folio_shift <= SCRUB_STRIPE_MAX_FOLIOS);
 	ret = btrfs_alloc_folio_array(BTRFS_STRIPE_LEN >> min_folio_shift,
-				      fs_info->block_min_order, stripe->folios);
+				      fs_info->block_min_order, stripe->folios,
+				      0);
 	if (ret < 0)
 		goto error;
 
-- 
2.54.0