From: Rik van Riel Date: Tue, 26 May 2026 22:37:39 +0000 (-0400) Subject: btrfs: allocate eb-attached btree pages as movable X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=23fd95663b070cf781f37b8058a8c055f168110b;p=thirdparty%2Flinux.git btrfs: allocate eb-attached btree pages as movable 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. 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. Have each caller of btrfs_alloc_page_array, btrfs_alloc_folio_array, and alloc_eb_folio_array pass in the full GFP mask directly, instead of having the functions calculate it from boolean flags. The alloc_extent_buffer call site passes GFP_NOFS | __GFP_NOFAIL | __GFP_MOVABLE. All other call sites pass plain GFP_NOFS. 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 (io_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. Assisted-by: Claude:claude-opus-4-6 Signed-off-by: Rik van Riel Signed-off-by: David Sterba --- diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index b7e3e83838d80..8a166b76a9dc9 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -617,24 +617,24 @@ 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. * - * @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 + * @gfp: GFP flags for the allocation * * 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 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, order); if (!folio_array[i]) goto error; } @@ -649,21 +649,18 @@ error: } /* - * Populate every free slot in a provided array with pages, using GFP_NOFS. + * Populate every free slot in a provided array with pages. * - * @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 + * @gfp: GFP flags for the allocation * * 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) +int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array, gfp_t gfp) { - const gfp_t gfp = nofail ? (GFP_NOFS | __GFP_NOFAIL) : GFP_NOFS; unsigned int allocated; for (allocated = 0; allocated < nr_pages;) { @@ -687,13 +684,13 @@ int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array, * * For now, the folios populated are always in order 0 (aka, single page). */ -static int alloc_eb_folio_array(struct extent_buffer *eb, bool nofail) +static int alloc_eb_folio_array(struct extent_buffer *eb, gfp_t gfp) { 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, gfp); if (ret < 0) return ret; @@ -3103,7 +3100,7 @@ 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, GFP_NOFS); if (ret) goto release_eb; @@ -3144,7 +3141,7 @@ 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, GFP_NOFS); if (ret) goto release_eb; @@ -3497,8 +3494,12 @@ 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, GFP_NOFS | __GFP_NOFAIL | __GFP_MOVABLE); 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 8c58b114f5b3e..9896e15ddc406 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -400,10 +400,9 @@ static inline void btrfs_clear_folio_dirty_tag(struct folio *folio) xa_unlock_irq(&folio->mapping->i_pages); } -int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array, - bool nofail); +int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array, gfp_t gfp); int btrfs_alloc_folio_array(unsigned int nr_folios, unsigned int order, - struct folio **folio_array); + struct folio **folio_array, gfp_t 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 61b5594c4206f..ae7194788c1fc 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9496,7 +9496,7 @@ 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, GFP_NOFS); if (ret) { ret = -ENOMEM; goto out; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 5512b32752030..561f4a90981be 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4617,7 +4617,7 @@ 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, GFP_NOFS); if (ret) { ret = -ENOMEM; goto out_fail; diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 08ee8f316d96d..fae4577122188 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, GFP_NOFS); 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, GFP_NOFS); 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, GFP_NOFS); if (ret < 0) return ret; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 955e338dcfd89..2b11eda49c06e 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -4051,7 +4051,7 @@ 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, GFP_NOFS); if (ret) { ret = -ENOMEM; goto end; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 1ac609239cbe3..d2f7ac5b6e961 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, + GFP_NOFS); if (ret < 0) goto error;