[PATCH v2 00/14] f2fs: support & optimize large folios for writable files

[PATCH v2 00/14] f2fs: support & optimize large folios for writable files

[Nanzhe Zhao]

This series supports large folios for most readable/writable files
in buffered I/O paths, including normal files, block-layer encrypted
files, and atomic files except for inline-data files, compressed files,
and quota files.

It also extends f2fs_folio_state to coexist with f2fs page-private
flags and to handle large folio write path and partial truncate of
large folios correctly.

Benchmark details can be found in the RFC v2 cover letter [1].

[1] https://lore.kernel.org/r/20260622160830.324455-1-zhaonanzhe@xiaomi.com

Changes in v2:
- Addressed most of Chao's and Daeho's review comments.
- Updated docs for compress policy with large folios.
- Link to v1: https://lore.kernel.org/r/20260826082641.2007658-1-zhaonanzhe@xiaomi.com

Many thanks to Chao and Daeho for your extensive reviews and valuable
suggestions!

Nanzhe Zhao (14):
  f2fs: extend folio state for large folio write path
  f2fs: carry subpage offset and count in write IO
  f2fs: support regular file buffered writes on large folios
  f2fs: support atomic file large folios buffered write
  f2fs: support large folio writeback
  f2fs: prepare mmap write faults for large folios
  f2fs: make GC migration large-folio aware
  f2fs: optimize small block size large folio read
  f2fs: support partial uptodate large folio read
  f2fs: handle partial truncate of large folio dirty subpages
  f2fs: fix zeroing paths for large folios
  f2fs: handle block cloning within the same large folio
  f2fs: allow large folio support to writeable files
  f2fs: make compressed files compatible with large folio

 Documentation/filesystems/f2fs.rst |   10 +
 fs/f2fs/checkpoint.c               |    2 +
 fs/f2fs/compress.c                 |    3 +
 fs/f2fs/data.c                     | 1221 +++++++++++++++++++++++++---
 fs/f2fs/f2fs.h                     |  105 ++-
 fs/f2fs/file.c                     |  229 ++++--
 fs/f2fs/gc.c                       |   32 +-
 fs/f2fs/inline.c                   |    7 +
 fs/f2fs/inode.c                    |    4 +-
 fs/f2fs/namei.c                    |    1 +
 fs/f2fs/node.c                     |    2 +
 fs/f2fs/segment.c                  |    6 +-
 12 files changed, 1404 insertions(+), 218 deletions(-)

-- 
2.43.0

[PATCH v2 01/14] f2fs: extend folio state for large folio write path

[Nanzhe Zhao]

Large folio write path needs a subpage status bitmap and write
pages pending counter, while keeping compatible with f2fs private
flags.

Move struct f2fs_folio_state to f2fs.h, add private_flags and
subpage state bitmap, and change PAGE_PRIVATE functions to be
compatible with f2fs_folio_state. Allocate f2fs_folio_state via kzalloc
instead of kmem_cache, since the state size depends on the folio order.

Note: Now if a path wants to use f2fs_folio_state, it must call
`folio_has_ffs` instead of `folio_test_large`` to make check.

Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
 fs/f2fs/data.c | 72 ++++++++++++++++++++++++++++++++------------------
 fs/f2fs/f2fs.h | 70 +++++++++++++++++++++++++++++++++++-------------
 2 files changed, 98 insertions(+), 44 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index a3b02c067e89..b3303109a696 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -32,15 +32,9 @@
 
 static struct kmem_cache *bio_post_read_ctx_cache;
 static struct kmem_cache *bio_entry_slab;
-static struct kmem_cache *ffs_entry_slab;
 static mempool_t *bio_post_read_ctx_pool;
 static struct bio_set f2fs_bioset;
 
-struct f2fs_folio_state {
-	spinlock_t		state_lock;
-	unsigned int		read_pages_pending;
-};
-
 struct f2fs_bio {
 	struct work_struct work;
 	struct bio bio;
@@ -125,6 +119,9 @@ struct bio_post_read_ctx {
 	block_t fs_blkaddr;
 };
 
+static bool __ffs_mark_subrange_uptodate(struct folio *folio,
+		struct f2fs_folio_state *ffs, size_t offset, size_t len);
+
 /*
  * Update and unlock a bio's pages, and free the bio.
  *
@@ -139,6 +136,23 @@ struct bio_post_read_ctx {
  * called (i.e., I/O error or decryption error, but *not* verity error), and
  * release the bio's reference to the decompress_io_ctx of the page's cluster.
  */
+/*
+ * Update read_pages_pending.
+ */
+static inline void f2fs_update_read_folio_pending(struct folio *folio, int nr)
+{
+	struct f2fs_folio_state *ffs;
+	unsigned long flags;
+
+	if (!f2fs_folio_has_ffs(folio))
+		return;
+
+	ffs = (struct f2fs_folio_state *)folio->private;
+	spin_lock_irqsave(&ffs->state_lock, flags);
+	ffs->read_pages_pending += nr;
+	spin_unlock_irqrestore(&ffs->state_lock, flags);
+}
+
 static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
 {
 	struct folio_iter fi;
@@ -147,7 +161,7 @@ static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
 
 	bio_for_each_folio_all(fi, bio) {
 		struct folio *folio = fi.folio;
-		unsigned nr_pages = fi.length >> PAGE_SHIFT;
+		unsigned int nr_pages = fi.length >> PAGE_SHIFT;
 		bool finished = true;
 
 		if (!folio_test_large(folio) &&
@@ -2487,17 +2501,31 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 }
 #endif
 
-static struct f2fs_folio_state *ffs_find_or_alloc(struct folio *folio)
+struct f2fs_folio_state *f2fs_ffs_find_or_alloc(struct folio *folio)
 {
-	struct f2fs_folio_state *ffs = folio->private;
+	struct f2fs_folio_state *ffs;
+	unsigned int nr_subpages = folio_nr_pages(folio);
+	unsigned long private = (unsigned long)folio->private;
+
+	f2fs_bug_on(F2FS_F_SB(folio), !folio_test_large(folio));
+	f2fs_bug_on(F2FS_F_SB(folio),
+		    test_bit(PAGE_PRIVATE_NOT_POINTER, &private));
 
-	if (ffs)
-		return ffs;
+	if (f2fs_folio_has_ffs(folio))
+		return (struct f2fs_folio_state *)folio->private;
 
-	ffs = f2fs_kmem_cache_alloc(ffs_entry_slab,
-			GFP_NOIO | __GFP_ZERO, true, NULL);
+	ffs = f2fs_kmalloc(F2FS_F_SB(folio),
+			struct_size(ffs, state, BITS_TO_LONGS(2 * nr_subpages)),
+			GFP_NOFS | __GFP_ZERO);
+	if (!ffs)
+		return NULL;
 
 	spin_lock_init(&ffs->state_lock);
+	if (folio_test_uptodate(folio))
+		bitmap_set(ffs->state, 0, nr_subpages);
+	if (folio_test_dirty(folio))
+		bitmap_set(ffs->state, nr_subpages, nr_subpages);
+
 	folio_attach_private(folio, ffs);
 	return ffs;
 }
@@ -2506,7 +2534,7 @@ static void ffs_detach_free(struct folio *folio)
 {
 	struct f2fs_folio_state *ffs;
 
-	if (!folio_test_large(folio)) {
+	if (!f2fs_folio_has_ffs(folio)) {
 		folio_detach_private(folio);
 		return;
 	}
@@ -2516,7 +2544,8 @@ static void ffs_detach_free(struct folio *folio)
 		return;
 
 	WARN_ON_ONCE(ffs->read_pages_pending != 0);
-	kmem_cache_free(ffs_entry_slab, ffs);
+	WARN_ON_ONCE(atomic_read(&ffs->write_pages_pending));
+	kfree(ffs);
 }
 
 static int f2fs_read_data_large_folio(struct inode *inode,
@@ -2529,7 +2558,7 @@ static int f2fs_read_data_large_folio(struct inode *inode,
 	pgoff_t index, offset, next_pgofs = 0;
 	unsigned max_nr_pages = rac ? readahead_count(rac) :
 				folio_nr_pages(folio);
-	unsigned nrpages;
+	unsigned int nrpages;
 	struct f2fs_folio_state *ffs;
 	int ret = 0;
 	bool folio_in_bio = false;
@@ -2605,7 +2634,7 @@ static int f2fs_read_data_large_folio(struct inode *inode,
 		 * to prevent from premature folio_end_read() call on folio
 		 */
 		if (folio_test_large(folio)) {
-			ffs = ffs_find_or_alloc(folio);
+			ffs = f2fs_ffs_find_or_alloc(folio);
 
 			/* set the bitmap to wait */
 			spin_lock_irq(&ffs->state_lock);
@@ -4522,21 +4551,12 @@ int __init f2fs_init_bio_entry_cache(void)
 	if (!bio_entry_slab)
 		return -ENOMEM;
 
-	ffs_entry_slab = f2fs_kmem_cache_create("f2fs_ffs_slab",
-			sizeof(struct f2fs_folio_state));
-
-	if (!ffs_entry_slab) {
-		kmem_cache_destroy(bio_entry_slab);
-		return -ENOMEM;
-	}
-
 	return 0;
 }
 
 void f2fs_destroy_bio_entry_cache(void)
 {
 	kmem_cache_destroy(bio_entry_slab);
-	kmem_cache_destroy(ffs_entry_slab);
 }
 
 static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index ebc621f302e1..9a2366a6c113 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1618,6 +1618,18 @@ static inline void f2fs_clear_bit(unsigned int nr, char *addr);
  * Layout B: lowest bit should be 0
  * page.private is a wrapped pointer.
  */
+
+struct f2fs_folio_state {
+	spinlock_t		state_lock;
+	unsigned int		read_pages_pending;
+	atomic_t		write_pages_pending;
+	unsigned long		private_flags;
+	/* state[0..nr_subpages - 1] tracks uptodate subpages.
+	 * state[nr_subpages..2 * nr_subpages - 1] tracks dirty subpages.
+	 */
+	unsigned long		state[];
+};
+
 enum {
 	PAGE_PRIVATE_NOT_POINTER,		/* private contains non-pointer data */
 	PAGE_PRIVATE_ONGOING_MIGRATION,		/* data page which is on-going migrating */
@@ -1627,6 +1639,13 @@ enum {
 	PAGE_PRIVATE_MAX
 };
 
+static inline bool f2fs_folio_has_ffs(const struct folio *folio)
+{
+	unsigned long private = (unsigned long)folio->private;
+
+	return folio_test_large(folio) && private;
+}
+
 /* For compression */
 enum compress_algorithm_type {
 	COMPRESS_LZO,
@@ -2738,13 +2757,35 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,
 	return -ENOSPC;
 }
 
+static inline unsigned long f2fs_folio_get_private_flags(const struct folio *folio)
+{
+	unsigned long private = (unsigned long)folio->private;
+
+	if (f2fs_folio_has_ffs(folio)) {
+		struct f2fs_folio_state *ffs = (struct f2fs_folio_state *)private;
+
+		return READ_ONCE(ffs->private_flags);
+	}
+
+	if (test_bit(PAGE_PRIVATE_NOT_POINTER, &private))
+		return private;
+
+	return 0;
+}
+
+static inline unsigned long *f2fs_folio_flags_addr(struct folio *folio)
+{
+	if (f2fs_folio_has_ffs(folio))
+		return &((struct f2fs_folio_state *)folio->private)->private_flags;
+
+	return (unsigned long *)&folio->private;
+}
+
 #define PAGE_PRIVATE_GET_FUNC(name, flagname) \
 static inline bool folio_test_f2fs_##name(const struct folio *folio)	\
 {									\
-	unsigned long priv = (unsigned long)folio->private;		\
-	unsigned long v = (1UL << PAGE_PRIVATE_NOT_POINTER) |		\
-			     (1UL << PAGE_PRIVATE_##flagname);		\
-	return (priv & v) == v;						\
+	return f2fs_folio_get_private_flags(folio) &			\
+				(1UL << PAGE_PRIVATE_##flagname);	\
 }									\
 static inline bool page_private_##name(struct page *page) \
 { \
@@ -2756,14 +2797,10 @@ static inline bool page_private_##name(struct page *page) \
 #define PAGE_PRIVATE_SET_FUNC(name, flagname) \
 static inline void folio_set_f2fs_##name(struct folio *folio)		\
 {									\
-	unsigned long v = (1UL << PAGE_PRIVATE_NOT_POINTER) |		\
-			     (1UL << PAGE_PRIVATE_##flagname);		\
 	if (!folio->private)						\
-		folio_attach_private(folio, (void *)v);			\
-	else {								\
-		v |= (unsigned long)folio->private;			\
-		folio->private = (void *)v;				\
-	}								\
+		folio_attach_private(folio,				\
+				(void *)BIT(PAGE_PRIVATE_NOT_POINTER));	\
+	set_bit(PAGE_PRIVATE_##flagname, f2fs_folio_flags_addr(folio));	\
 }									\
 static inline void set_page_private_##name(struct page *page) \
 { \
@@ -2776,13 +2813,10 @@ static inline void set_page_private_##name(struct page *page) \
 #define PAGE_PRIVATE_CLEAR_FUNC(name, flagname) \
 static inline void folio_clear_f2fs_##name(struct folio *folio)		\
 {									\
-	unsigned long v = (unsigned long)folio->private;		\
-									\
-	v &= ~(1UL << PAGE_PRIVATE_##flagname);				\
-	if (v == (1UL << PAGE_PRIVATE_NOT_POINTER))			\
+	clear_bit(PAGE_PRIVATE_##flagname,				\
+		  f2fs_folio_flags_addr(folio));			\
+	if (folio->private == (void *)BIT(PAGE_PRIVATE_NOT_POINTER))	\
 		folio_detach_private(folio);				\
-	else								\
-		folio->private = (void *)v;				\
 }									\
 static inline void clear_page_private_##name(struct page *page) \
 { \
@@ -2808,7 +2842,7 @@ PAGE_PRIVATE_CLEAR_FUNC(atomic, ATOMIC_WRITE);
 
 static inline unsigned long folio_get_f2fs_data(struct folio *folio)
 {
-	unsigned long data = (unsigned long)folio->private;
+	unsigned long data = f2fs_folio_get_private_flags(folio);
 
 	if (!test_bit(PAGE_PRIVATE_NOT_POINTER, &data))
 		return 0;
-- 
2.43.0

[PATCH v2 02/14] f2fs: carry subpage offset and count in write IO

[Nanzhe Zhao]

Large folio write paths need to submit I/O for a range inside a
folio instead of always submitting the whole folio from offset zero.
Add folio_offset and folio_blkcnt to f2fs_io_info to describe the
block offset inside the folio and the number of contiguous blocks
covered by the I/O.

Apply the new fields to the bio submit paths that need the subpage
offset or contiguous block count.

Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
 fs/f2fs/checkpoint.c |  2 ++
 fs/f2fs/compress.c   |  1 +
 fs/f2fs/data.c       | 63 +++++++++++++++++++++++++++++++-------------
 fs/f2fs/f2fs.h       | 11 ++++++++
 fs/f2fs/gc.c         |  2 ++
 fs/f2fs/inline.c     |  1 +
 fs/f2fs/node.c       |  2 ++
 fs/f2fs/segment.c    |  4 ++-
 8 files changed, 66 insertions(+), 20 deletions(-)

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index e95cd2118750..cd379183449e 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -264,6 +264,7 @@ static struct folio *__get_meta_folio(struct f2fs_sb_info *sbi, pgoff_t index,
 		.op_flags = REQ_META | REQ_PRIO,
 		.old_blkaddr = index,
 		.new_blkaddr = index,
+		.folio_blkcnt = 1,
 		.encrypted_page = NULL,
 		.is_por = !is_meta ? 1 : 0,
 	};
@@ -456,6 +457,7 @@ int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 		.type = META,
 		.op = REQ_OP_READ,
 		.op_flags = sync ? (REQ_META | REQ_PRIO) : REQ_RAHEAD,
+		.folio_blkcnt = 1,
 		.encrypted_page = NULL,
 		.in_list = 0,
 		.is_por = (type == META_POR) ? 1 : 0,
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index ce88092d9ce2..b130e43b4566 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -1282,6 +1282,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 		.op_flags = wbc_to_write_flags(wbc),
 		.old_blkaddr = NEW_ADDR,
 		.page = NULL,
+		.folio_blkcnt = 1,
 		.encrypted_page = NULL,
 		.compressed_page = NULL,
 		.io_type = io_type,
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index b3303109a696..f14044e8a6f4 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -769,6 +769,9 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 	struct folio *fio_folio = fio->folio;
 	struct folio *data_folio = fio->encrypted_page ?
 			page_folio(fio->encrypted_page) : fio_folio;
+	pgoff_t fio_lblk = F2FS_FIO_LBLK(fio);
+	size_t bio_offset = F2FS_FIO_BIO_OFFSET(fio);
+	size_t bio_len = F2FS_FIO_BIO_SIZE(fio);
 
 	if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
 			fio->is_por ? META_POR : (__is_meta_io(fio) ?
@@ -781,11 +784,11 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 	bio = __bio_alloc(fio, 1);
 
 	f2fs_set_bio_crypt_ctx(bio, fio_folio->mapping->host,
-			fio_folio->index, fio, GFP_NOIO);
-	bio_add_folio_nofail(bio, data_folio, folio_size(data_folio), 0);
+			fio_lblk, fio, GFP_NOIO);
+	bio_add_folio_nofail(bio, data_folio, bio_len, bio_offset);
 
 	if (fio->io_wbc && !is_read_io(fio->op))
-		wbc_account_cgroup_owner(fio->io_wbc, fio_folio, PAGE_SIZE);
+		wbc_account_cgroup_owner(fio->io_wbc, fio_folio, bio_len);
 
 	inc_page_count(fio->sbi, is_read_io(fio->op) ?
 			__read_io_type(data_folio) : WB_DATA_TYPE(fio->folio, false));
@@ -830,7 +833,8 @@ static bool io_is_mergeable(struct f2fs_sb_info *sbi, struct bio *bio,
 }
 
 static void add_bio_entry(struct f2fs_sb_info *sbi, struct bio *bio,
-				struct folio *folio, enum temp_type temp)
+				struct folio *folio, size_t len, size_t offset,
+				enum temp_type temp)
 {
 	struct f2fs_bio_info *io = sbi->write_io[DATA] + temp;
 	struct bio_entry *be;
@@ -839,7 +843,7 @@ static void add_bio_entry(struct f2fs_sb_info *sbi, struct bio *bio,
 	be->bio = bio;
 	bio_get(bio);
 
-	bio_add_folio_nofail(bio, folio, folio_size(folio), 0);
+	bio_add_folio_nofail(bio, folio, len, offset);
 
 	f2fs_down_write(&io->bio_list_lock);
 	list_add_tail(&be->list, &io->bio_list);
@@ -856,6 +860,9 @@ static int add_ipu_page(struct f2fs_io_info *fio, struct bio **bio,
 							struct folio *folio)
 {
 	struct folio *fio_folio = fio->folio;
+	pgoff_t fio_lblk = F2FS_FIO_LBLK(fio);
+	size_t bio_offset = F2FS_FIO_BIO_OFFSET(fio);
+	size_t bio_len = F2FS_FIO_BIO_SIZE(fio);
 	struct f2fs_sb_info *sbi = fio->sbi;
 	enum temp_type temp;
 	bool found = false;
@@ -878,8 +885,8 @@ static int add_ipu_page(struct f2fs_io_info *fio, struct bio **bio,
 							    fio->new_blkaddr));
 			if (f2fs_crypt_mergeable_bio(*bio,
 					fio_folio->mapping->host,
-					fio_folio->index, fio) &&
-			    bio_add_folio(*bio, folio, folio_size(folio), 0)) {
+					fio_lblk, fio) &&
+			    bio_add_folio(*bio, folio, bio_len, bio_offset)) {
 				ret = 0;
 				break;
 			}
@@ -993,6 +1000,10 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio)
 	struct folio *data_folio = fio->encrypted_page ?
 			page_folio(fio->encrypted_page) : fio->folio;
 	struct folio *folio = fio->folio;
+	pgoff_t fio_lblk = F2FS_FIO_LBLK(fio);
+	unsigned int fio_cnt = F2FS_FIO_BLKCNT(fio);
+	size_t bio_offset = F2FS_FIO_BIO_OFFSET(fio);
+	size_t bio_len = F2FS_FIO_BIO_SIZE(fio);
 
 	if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
 			__is_meta_io(fio) ? META_GENERIC : DATA_GENERIC))
@@ -1007,9 +1018,10 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio)
 	if (!bio) {
 		bio = __bio_alloc(fio, BIO_MAX_VECS);
 		f2fs_set_bio_crypt_ctx(bio, folio->mapping->host,
-				folio->index, fio, GFP_NOIO);
+				fio_lblk, fio, GFP_NOIO);
 
-		add_bio_entry(fio->sbi, bio, data_folio, fio->temp);
+		add_bio_entry(fio->sbi, bio, data_folio, bio_len,
+			     bio_offset, fio->temp);
 	} else {
 		if (add_ipu_page(fio, &bio, data_folio))
 			goto alloc_new;
@@ -1020,7 +1032,7 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio)
 
 	inc_page_count(fio->sbi, WB_DATA_TYPE(folio, false));
 
-	*fio->last_block = fio->new_blkaddr;
+	*fio->last_block = fio->new_blkaddr + fio_cnt - 1;
 	*fio->bio = bio;
 
 	return 0;
@@ -1056,6 +1068,10 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio)
 	struct folio *bio_folio;
 	struct f2fs_lock_context lc;
 	enum count_type type;
+	pgoff_t fio_lblk;
+	unsigned int fio_cnt;
+	size_t bio_offset;
+	size_t bio_len;
 
 	f2fs_bug_on(sbi, is_read_io(fio->op));
 
@@ -1094,33 +1110,39 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio)
 	/* set submitted = true as a return value */
 	fio->submitted = 1;
 
+	fio_lblk = F2FS_FIO_LBLK(fio);
+	fio_cnt = F2FS_FIO_BLKCNT(fio);
+
 	type = WB_DATA_TYPE(bio_folio, fio->compressed_page);
-	inc_page_count(sbi, type);
+	for (unsigned int i = 0; i < fio_cnt; i++)
+		inc_page_count(sbi, type);
 
 	if (io->bio &&
 	    (!io_is_mergeable(sbi, io->bio, io, fio, io->last_block_in_bio,
 			      fio->new_blkaddr) ||
 	     !f2fs_crypt_mergeable_bio(io->bio, fio_inode(fio),
-				bio_folio->index, fio)))
+				fio_lblk, fio)))
 		__submit_merged_bio(io);
 alloc_new:
 	if (io->bio == NULL) {
 		io->bio = __bio_alloc(fio, BIO_MAX_VECS);
 		f2fs_set_bio_crypt_ctx(io->bio, fio_inode(fio),
-				bio_folio->index, fio, GFP_NOIO);
+				fio_lblk, fio, GFP_NOIO);
 		io->fio = *fio;
 	}
 
-	if (!bio_add_folio(io->bio, bio_folio, folio_size(bio_folio), 0)) {
+	bio_offset = F2FS_FIO_BIO_OFFSET(fio);
+	bio_len = F2FS_FIO_BIO_SIZE(fio);
+
+	if (!bio_add_folio(io->bio, bio_folio, bio_len, bio_offset)) {
 		__submit_merged_bio(io);
 		goto alloc_new;
 	}
 
 	if (fio->io_wbc)
-		wbc_account_cgroup_owner(fio->io_wbc, fio->folio,
-				folio_size(fio->folio));
+		wbc_account_cgroup_owner(fio->io_wbc, fio->folio, bio_len);
 
-	io->last_block_in_bio = fio->new_blkaddr;
+	io->last_block_in_bio = fio->new_blkaddr + fio_cnt - 1;
 
 	trace_f2fs_submit_folio_write(fio->folio, fio);
 #ifdef CONFIG_BLK_DEV_ZONED
@@ -2999,7 +3021,8 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
 		set_new_dnode(&dn, inode, NULL, NULL, 0);
 
 	if (need_inplace_update(fio) &&
-	    f2fs_lookup_read_extent_cache_block(inode, folio->index,
+	    f2fs_lookup_read_extent_cache_block(inode,
+						F2FS_FIO_LBLK(fio),
 						&fio->old_blkaddr)) {
 		if (!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr,
 						DATA_GENERIC_ENHANCE))
@@ -3018,7 +3041,8 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
 	if (fio->need_lock == LOCK_REQ && !f2fs_trylock_op(fio->sbi, &lc))
 		return -EAGAIN;
 
-	err = f2fs_get_dnode_of_data(&dn, folio->index, LOOKUP_NODE);
+	err = f2fs_get_dnode_of_data(&dn, F2FS_FIO_LBLK(fio),
+				     LOOKUP_NODE);
 	if (err)
 		goto out;
 
@@ -3121,6 +3145,7 @@ int f2fs_write_single_data_page(struct folio *folio, int *submitted,
 		.op_flags = wbc_to_write_flags(wbc),
 		.old_blkaddr = NULL_ADDR,
 		.folio = folio,
+		.folio_blkcnt = 1,
 		.encrypted_page = NULL,
 		.submitted = 0,
 		.compr_blocks = compr_blocks,
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 9a2366a6c113..326382ede1c3 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1348,6 +1348,8 @@ struct f2fs_io_info {
 	blk_opf_t op_flags;	/* req_flag_bits */
 	block_t new_blkaddr;	/* new block address to be written */
 	block_t old_blkaddr;	/* old block address before Cow */
+	pgoff_t folio_offset;	/* offset in large folio */
+	unsigned int folio_blkcnt;	/* block count in large folio */
 	union {
 		struct page *page;	/* page to be written */
 		struct folio *folio;
@@ -1368,6 +1370,15 @@ struct f2fs_io_info {
 	sector_t *last_block;		/* last block number in bio */
 };
 
+#define F2FS_FIO_LBLK(fio)						\
+	(((fio)->folio)->index + (fio)->folio_offset)
+#define F2FS_FIO_BLKCNT(fio)						\
+	((fio)->folio_blkcnt)
+#define F2FS_FIO_BIO_OFFSET(fio)					\
+	((fio)->folio_offset << PAGE_SHIFT)
+#define F2FS_FIO_BIO_SIZE(fio)					\
+	F2FS_BLK_TO_BYTES((fio)->sbi, F2FS_FIO_BLKCNT(fio))
+
 struct bio_entry {
 	struct bio *bio;
 	struct list_head list;
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index c70deac9f1a3..16fce62740d7 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -1227,6 +1227,7 @@ static int ra_data_block(struct inode *inode, pgoff_t index)
 		.temp = COLD,
 		.op = REQ_OP_READ,
 		.op_flags = 0,
+		.folio_blkcnt = 1,
 		.encrypted_page = NULL,
 		.in_list = 0,
 	};
@@ -1337,6 +1338,7 @@ static int move_data_block(struct inode *inode, block_t bidx,
 		.temp = COLD,
 		.op = REQ_OP_READ,
 		.op_flags = 0,
+		.folio_blkcnt = 1,
 		.encrypted_page = NULL,
 		.in_list = 0,
 	};
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 925bdaad013c..8db083b545bc 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -151,6 +151,7 @@ int f2fs_convert_inline_folio(struct dnode_of_data *dn, struct folio *folio)
 		.op = REQ_OP_WRITE,
 		.op_flags = REQ_SYNC | REQ_PRIO,
 		.folio = folio,
+		.folio_blkcnt = 1,
 		.encrypted_page = NULL,
 		.io_type = FS_DATA_IO,
 	};
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index f16144b75d11..a19abc34c14a 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1475,6 +1475,7 @@ static int read_node_folio(struct folio *folio, blk_opf_t op_flags)
 		.op = REQ_OP_READ,
 		.op_flags = op_flags,
 		.folio = folio,
+		.folio_blkcnt = 1,
 		.encrypted_page = NULL,
 	};
 	int err;
@@ -1772,6 +1773,7 @@ static bool __write_node_folio(struct folio *folio, bool atomic, bool do_fsync,
 		.op = REQ_OP_WRITE,
 		.op_flags = wbc_to_write_flags(wbc),
 		.folio = folio,
+		.folio_blkcnt = 1,
 		.encrypted_page = NULL,
 		.submitted = 0,
 		.io_type = io_type,
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index ffdd2c510b3c..644ddfb984c9 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -3873,7 +3873,8 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
 		if (file_is_cold(inode) || f2fs_need_compress_data(inode))
 			return CURSEG_COLD_DATA;
 
-		type = __get_age_segment_type(inode, fio->folio->index);
+		type = __get_age_segment_type(inode,
+					     F2FS_FIO_LBLK(fio));
 		if (type != NO_CHECK_TYPE)
 			return type;
 
@@ -4195,6 +4196,7 @@ void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct folio *folio,
 		.old_blkaddr = folio->index,
 		.new_blkaddr = folio->index,
 		.folio = folio,
+		.folio_blkcnt = 1,
 		.encrypted_page = NULL,
 		.in_list = 0,
 	};
-- 
2.43.0

[PATCH v2 03/14] f2fs: support regular file buffered writes on large folios

[Nanzhe Zhao]

To avoid the complexity of unlocking a large folio in write_begin,
preallocate partial blocks for inodes that can use large folios.
During write_begin, read only the partial head and tail 4K subpages
that need read-before-write, and skip read I/O for the full middle
subpages covered by the write.

Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
 fs/f2fs/data.c | 300 +++++++++++++++++++++++++++++++++++++++++++++++--
 fs/f2fs/f2fs.h |   1 +
 fs/f2fs/file.c |  17 ++-
 3 files changed, 304 insertions(+), 14 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index f14044e8a6f4..a490df4f50b3 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1233,6 +1233,35 @@ static void f2fs_submit_page_read(struct inode *inode, struct fsverity_info *vi,
 	f2fs_submit_read_bio(sbi, bio, DATA);
 }
 
+/*
+ * Synchronously read a single 4K subpage by reusing f2fs_submit_page_read()
+ * so that iostat, trace, blk-crypto and post-read handling are all preserved.
+ * The caller must have already allocated ffs for the folio.
+ */
+static int f2fs_submit_page_read_sync(struct inode *inode, struct folio *folio,
+				      pgoff_t index, block_t blkaddr)
+{
+	struct f2fs_folio_state *ffs = folio->private;
+
+	/* Add bias so end_io does not call folio_end_read(). */
+	f2fs_update_read_folio_pending(folio, 1);
+
+	f2fs_submit_page_read(inode, NULL, folio, index, blkaddr,
+			      REQ_OP_READ, false);
+
+	/* Wait until all bios have completed (pending drops back to our bias). */
+	while (READ_ONCE(ffs->read_pages_pending) != 1)
+		f2fs_io_schedule_timeout(DEFAULT_SCHEDULE_TIMEOUT);
+
+	/* Remove the bias. */
+	f2fs_update_read_folio_pending(folio, -1);
+
+	if (!f2fs_ffs_test_blk_uptodate(folio, index))
+		return -EIO;
+
+	return 0;
+}
+
 static void __set_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
 {
 	__le32 *addr = get_dnode_addr(dn->inode, dn->node_folio);
@@ -2570,6 +2599,114 @@ static void ffs_detach_free(struct folio *folio)
 	kfree(ffs);
 }
 
+bool f2fs_ffs_test_blk_uptodate(const struct folio *folio, pgoff_t index)
+{
+	struct f2fs_folio_state *ffs;
+	unsigned int idx;
+
+	f2fs_bug_on(F2FS_F_SB(folio), !folio_contains(folio, index));
+
+	if (folio_test_uptodate(folio))
+		return true;
+
+	if (!f2fs_folio_has_ffs(folio))
+		return false;
+
+	ffs = (struct f2fs_folio_state *)folio->private;
+	idx = index - folio->index;
+	return test_bit(idx, ffs->state);
+}
+
+static bool __ffs_mark_subrange_uptodate(struct folio *folio,
+		struct f2fs_folio_state *ffs, size_t offset, size_t len)
+{
+	unsigned int nr_subpages = folio_nr_pages(folio);
+	unsigned int start, end;
+
+	start = offset >> PAGE_SHIFT;
+	end = (offset + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	end = min(end, nr_subpages);
+
+	bitmap_set(ffs->state, start, end - start);
+	return bitmap_full(ffs->state, nr_subpages);
+}
+
+static void f2fs_ffs_mark_subrange_uptodate(struct folio *folio, size_t offset,
+				       size_t len)
+{
+	struct f2fs_folio_state *ffs;
+	unsigned long flags;
+	bool mark_uptodate = false;
+
+	f2fs_bug_on(F2FS_F_SB(folio), offset + len > folio_size(folio));
+
+	if (!f2fs_folio_has_ffs(folio)) {
+		folio_mark_uptodate(folio);
+		return;
+	}
+
+	ffs = (struct f2fs_folio_state *)folio->private;
+	spin_lock_irqsave(&ffs->state_lock, flags);
+	mark_uptodate = __ffs_mark_subrange_uptodate(folio, ffs, offset, len) &&
+			!ffs->read_pages_pending;
+	spin_unlock_irqrestore(&ffs->state_lock, flags);
+	if (mark_uptodate)
+		folio_mark_uptodate(folio);
+}
+
+static void f2fs_ffs_mark_subrange_dirty(struct folio *folio,
+				    size_t offset, size_t len)
+{
+	struct f2fs_folio_state *ffs;
+	unsigned int nr_subpages, start, end;
+	unsigned long flags;
+
+	f2fs_bug_on(F2FS_F_SB(folio), offset + len > folio_size(folio));
+
+	if (!f2fs_folio_has_ffs(folio))
+		return;
+
+	ffs = (struct f2fs_folio_state *)folio->private;
+	nr_subpages = folio_nr_pages(folio);
+	start = offset >> PAGE_SHIFT;
+	end = (offset + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	end = min(end, nr_subpages);
+
+	spin_lock_irqsave(&ffs->state_lock, flags);
+	bitmap_set(ffs->state, nr_subpages + start, end - start);
+	spin_unlock_irqrestore(&ffs->state_lock, flags);
+}
+
+static bool find_next_valid_block(const struct folio *folio,
+				  size_t orig_off, size_t *need_off,
+				  size_t len)
+{
+	size_t start = orig_off;
+	size_t end = start + len;
+	size_t head, tail;
+	pgoff_t index;
+
+	if (start & (PAGE_SIZE - 1)) {
+		head = round_down(start, PAGE_SIZE);
+		index = folio->index + (head >> PAGE_SHIFT);
+		if (!f2fs_ffs_test_blk_uptodate(folio, index)) {
+			*need_off = head;
+			return true;
+		}
+	}
+
+	if (end & (PAGE_SIZE - 1)) {
+		tail = round_down(end - 1, PAGE_SIZE);
+		index = folio->index + (tail >> PAGE_SHIFT);
+		if (!f2fs_ffs_test_blk_uptodate(folio, index)) {
+			*need_off = tail;
+			return true;
+		}
+	}
+
+	return false;
+}
+
 static int f2fs_read_data_large_folio(struct inode *inode,
 		struct fsverity_info *vi,
 		struct readahead_control *rac, struct folio *folio)
@@ -3927,6 +4064,110 @@ static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi,
 	return 0;
 }
 
+static int prepare_large_folio_write_begin(struct inode *inode,
+					  struct folio *folio, loff_t pos,
+					  unsigned int len)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct f2fs_folio_state *ffs;
+	size_t ori_off = offset_in_folio(folio, pos);
+	size_t need_off = ori_off;
+	int err = 0;
+
+	len = min_t(unsigned int, len, folio_size(folio) - ori_off);
+
+	/*
+	 * When folio minimum order is non-zero, the fsverity
+	 * page_cache_write() path enters f2fs_write_begin() via
+	 * aops->write_begin without going through f2fs_write_iter(),
+	 * so preallocation from f2fs_write_iter() is skipped.  In that
+	 * case, if FI_PREALLOCATED_ALL is not set, we must preallocate
+	 * the write blocks here.
+	 */
+	if (!is_inode_flag_set(inode, FI_PREALLOCATED_ALL)) {
+		struct f2fs_map_blocks map = {};
+
+		map.m_lblk = F2FS_BYTES_TO_BLK(sbi, pos);
+		map.m_len = F2FS_BLK_ALIGN(sbi, pos + len) - map.m_lblk;
+
+		if (!IS_DEVICE_ALIASING(inode))
+			map.m_may_create = true;
+		map.m_seg_type = NO_CHECK_TYPE;
+
+		err = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_PRE_AIO);
+		if (err)
+			return err;
+	}
+
+	ffs = f2fs_ffs_find_or_alloc(folio);
+	if (!ffs)
+		return -ENOMEM;
+
+	/* Skip read if the folio is already fully uptodate or the write
+	 * covers the entire folio.
+	 */
+	if (folio_test_uptodate(folio) || len == folio_size(folio))
+		return 0;
+
+	if (!f2fs_verity_in_progress(inode) &&
+	    !(pos & (PAGE_SIZE - 1)) && (pos + len) >= i_size_read(inode)) {
+		size_t zoff = ori_off + len;
+
+		if (zoff < folio_size(folio))
+			folio_zero_segment(folio, zoff, folio_size(folio));
+		return 0;
+	}
+
+	/* Inline data must have been converted before reaching here. */
+	f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
+
+	while (find_next_valid_block(folio, ori_off,
+				     &need_off, len)) {
+		struct dnode_of_data dn;
+		pgoff_t index = folio->index + (need_off >> PAGE_SHIFT);
+		block_t blkaddr;
+		bool get_dn = false;
+
+		if (!f2fs_lookup_read_extent_cache_block(inode, index,
+							&blkaddr)) {
+			if (IS_DEVICE_ALIASING(inode))
+				return -ENODATA;
+
+			set_new_dnode(&dn, inode, NULL, NULL, 0);
+			err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
+			if (err)
+				return err;
+			get_dn = true;
+			blkaddr = dn.data_blkaddr;
+
+			if (blkaddr == NEW_ADDR) {
+				size_t off = offset_in_folio(folio,
+							     index << PAGE_SHIFT);
+
+				folio_zero_segment(folio, off, off + PAGE_SIZE);
+				f2fs_ffs_mark_subrange_uptodate(folio, off,
+							       PAGE_SIZE);
+				goto out;
+			}
+
+			if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
+						  DATA_GENERIC_ENHANCE_READ)) {
+				err = -EFSCORRUPTED;
+				goto out;
+			}
+		}
+
+		err = f2fs_submit_page_read_sync(inode, folio, index, blkaddr);
+out:
+		if (get_dn)
+			f2fs_put_dnode(&dn);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int f2fs_write_begin(const struct kiocb *iocb,
 			    struct address_space *mapping,
 			    loff_t pos, unsigned len, struct folio **foliop,
@@ -3938,6 +4179,7 @@ static int f2fs_write_begin(const struct kiocb *iocb,
 	pgoff_t index = pos >> PAGE_SHIFT;
 	bool need_balance = false;
 	block_t blkaddr = NULL_ADDR;
+	fgf_t fgp = FGP_LOCK | FGP_WRITE | FGP_CREAT;
 	int err = 0;
 
 	trace_f2fs_write_begin(inode, pos, len);
@@ -3985,9 +4227,15 @@ static int f2fs_write_begin(const struct kiocb *iocb,
 	 * Do not use FGP_STABLE to avoid deadlock.
 	 * Will wait that below with our IO control.
 	 */
-	folio = f2fs_filemap_get_folio(mapping, index,
-				FGP_LOCK | FGP_WRITE | FGP_CREAT,
-				mapping_gfp_mask(mapping));
+	/*
+	 * Inline data is carried in the first subpage.  Keep the index #0
+	 * folio order-0 so that the existing inline read/convert paths
+	 * (prepare_write_begin()) still apply; large folios are used from
+	 * the second folio on.
+	 */
+	fgp |= fgf_set_order(f2fs_has_inline_data(inode) ? PAGE_SIZE : len);
+	folio = f2fs_filemap_get_folio(mapping, index, fgp,
+				      mapping_gfp_mask(mapping));
 	if (IS_ERR(folio)) {
 		err = PTR_ERR(folio);
 		goto fail;
@@ -4000,7 +4248,7 @@ static int f2fs_write_begin(const struct kiocb *iocb,
 	if (f2fs_is_atomic_file(inode))
 		err = prepare_atomic_write_begin(sbi, folio, pos, len,
 					&blkaddr, &need_balance);
-	else
+	else if (!folio_test_large(folio))
 		err = prepare_write_begin(sbi, folio, pos, len,
 					&blkaddr, &need_balance);
 	if (err)
@@ -4021,6 +4269,14 @@ static int f2fs_write_begin(const struct kiocb *iocb,
 
 	f2fs_folio_wait_writeback(folio, DATA, false, true);
 
+	if (folio_test_large(folio)) {
+		err = prepare_large_folio_write_begin(inode,
+					folio, pos, len);
+		if (!err)
+			return 0;
+		goto put_folio;
+	}
+
 	if (len == folio_size(folio) || folio_test_uptodate(folio))
 		return 0;
 
@@ -4081,15 +4337,20 @@ static int f2fs_write_end(const struct kiocb *iocb,
 	trace_f2fs_write_end(inode, pos, len, copied);
 
 	/*
-	 * This should be come from len == PAGE_SIZE, and we expect copied
-	 * should be PAGE_SIZE. Otherwise, we treat it with zero copied and
-	 * let generic_perform_write() try to copy data again through copied=0.
+	 * If a short copy happens on a folio that isn't uptodate, we treat
+	 * it with zero copied and let generic_perform_write() try to copy
+	 * data again through copied=0.
 	 */
 	if (!folio_test_uptodate(folio)) {
-		if (unlikely(copied != len))
+		if (unlikely(copied != len)) {
 			copied = 0;
-		else
+		} else if (folio_test_large(folio)) {
+			f2fs_ffs_mark_subrange_uptodate(folio,
+					offset_in_folio(folio, pos), len);
+		} else {
+			/* This should be come from len == PAGE_SIZE */
 			folio_mark_uptodate(folio);
+		}
 	}
 
 #ifdef CONFIG_F2FS_FS_COMPRESSION
@@ -4108,6 +4369,9 @@ static int f2fs_write_end(const struct kiocb *iocb,
 	if (!copied)
 		goto unlock_out;
 
+	if (folio_test_large(folio))
+		f2fs_ffs_mark_subrange_dirty(folio, offset_in_folio(folio, pos),
+								   copied);
 	folio_mark_dirty(folio);
 
 	if (f2fs_is_atomic_file(inode))
@@ -4170,8 +4434,22 @@ static bool f2fs_dirty_data_folio(struct address_space *mapping,
 
 	trace_f2fs_set_page_dirty(folio, DATA);
 
-	if (!folio_test_uptodate(folio))
-		folio_mark_uptodate(folio);
+	if (!folio_test_uptodate(folio)) {
+		bool uptodate = true;
+
+		if (f2fs_folio_has_ffs(folio)) {
+			struct f2fs_folio_state *ffs =
+				(struct f2fs_folio_state *)folio->private;
+			unsigned long flags;
+
+			spin_lock_irqsave(&ffs->state_lock, flags);
+			uptodate = bitmap_full(ffs->state, folio_nr_pages(folio)) &&
+				   !ffs->read_pages_pending;
+			spin_unlock_irqrestore(&ffs->state_lock, flags);
+		}
+		if (uptodate)
+			folio_mark_uptodate(folio);
+	}
 	BUG_ON(folio_test_swapcache(folio));
 
 	if (filemap_dirty_folio(mapping, folio)) {
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 326382ede1c3..8eccca6e5d27 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -4392,6 +4392,7 @@ int f2fs_write_single_data_page(struct folio *folio, int *submitted,
 				struct writeback_control *wbc,
 				enum iostat_type io_type,
 				int compr_blocks, bool allow_balance);
+bool f2fs_ffs_test_blk_uptodate(const struct folio *folio, pgoff_t index);
 void f2fs_write_failed(struct inode *inode, loff_t to);
 void f2fs_invalidate_folio(struct folio *folio, size_t offset, size_t length);
 bool f2fs_release_folio(struct folio *folio, gfp_t wait);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index b0bdc7a977b9..9071bd23e57b 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -5412,9 +5412,20 @@ static int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *iter,
 			return ret;
 	}
 
-	/* Do not preallocate blocks that will be written partially in 4KB. */
-	map.m_lblk = F2FS_BLK_ALIGN(sbi, pos);
-	map.m_len = F2FS_BYTES_TO_BLK(sbi, pos + count);
+	if (!dio && mapping_large_folio_support(inode->i_mapping)) {
+		/*
+		 * Preallocate all blocks touched by a large-folio buffered write so
+		 * the regular write_begin path does not need to unlock the folio for
+		 * f2fs_balance_fs().  Rechecking large-folio state after unlock is
+		 * unreliable since partial truncation can split the folio.
+		 */
+		map.m_lblk = F2FS_BYTES_TO_BLK(sbi, pos);
+		map.m_len = F2FS_BLK_ALIGN(sbi, pos + count);
+	} else {
+		/* Do not preallocate blocks that will be written partially in 4KB. */
+		map.m_lblk = F2FS_BLK_ALIGN(sbi, pos);
+		map.m_len = F2FS_BYTES_TO_BLK(sbi, pos + count);
+	}
 	if (map.m_len > map.m_lblk)
 		map.m_len -= map.m_lblk;
 	else
-- 
2.43.0

[PATCH v2 04/14] f2fs: support atomic file large folios buffered write

[Nanzhe Zhao]

ioctl can convert an inode with large folio support into an atomic
file. Support large folio buffered writes for atomic files as well.

Add a large folio atomic write_begin helper that reserves COW mappings
for the write range. For partial head and tail subpages, read the
existing data from either the COW inode or the original inode before
marking the subpage uptodate.

Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
 fs/f2fs/data.c | 88 ++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 81 insertions(+), 7 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index a490df4f50b3..eb5fb8e52851 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -4016,18 +4016,16 @@ static int __reserve_data_block(struct inode *inode, pgoff_t index,
 }
 
 static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi,
-			struct folio *folio, loff_t pos, unsigned int len,
+			struct inode *inode, pgoff_t index,
 			block_t *blk_addr, bool *node_changed)
 {
-	struct inode *inode = folio->mapping->host;
 	struct inode *cow_inode = F2FS_I(inode)->cow_inode;
-	pgoff_t index = folio->index;
 	int err = 0;
 	block_t ori_blk_addr = NULL_ADDR;
 	bool cow_has_reserved_block = false;
 
 	/* If pos is beyond the end of file, reserve a new block in COW inode */
-	if ((pos & PAGE_MASK) >= i_size_read(inode))
+	if ((index << PAGE_SHIFT) >= i_size_read(inode))
 		goto reserve_block;
 
 	/* Look for the block in COW inode first */
@@ -4168,6 +4166,74 @@ static int prepare_large_folio_write_begin(struct inode *inode,
 	return 0;
 }
 
+static int prepare_large_folio_atomic_write_begin(struct inode *inode,
+		struct address_space *mapping, struct folio *folio, loff_t pos,
+		unsigned int len)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	size_t ori_off = offset_in_folio(folio, pos);
+	pgoff_t start, end, index;
+	unsigned int orig_order;
+	int err = 0;
+
+	len = min_t(unsigned int, len, folio_size(folio) - ori_off);
+
+	if (!f2fs_ffs_find_or_alloc(folio))
+		return -ENOMEM;
+
+	/* Inline data must have been converted before reaching here. */
+	f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
+
+	start = folio->index + (ori_off >> PAGE_SHIFT);
+	end = folio->index + ((ori_off + len - 1) >> PAGE_SHIFT);
+
+	for (index = start; index <= end; index++) {
+		block_t blkaddr = NULL_ADDR;
+		bool node_changed = false;
+		size_t off = (index - folio->index) << PAGE_SHIFT;
+
+		err = prepare_atomic_write_begin(sbi, inode, index,
+						&blkaddr, &node_changed);
+		if (err)
+			return err;
+
+		if (f2fs_ffs_test_blk_uptodate(folio, index))
+			goto balance;
+
+		if (blkaddr == NEW_ADDR) {
+			folio_zero_segment(folio, off, off + PAGE_SIZE);
+			f2fs_ffs_mark_subrange_uptodate(folio, off, PAGE_SIZE);
+			goto balance;
+		}
+
+		if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
+					   DATA_GENERIC_ENHANCE_READ))
+			return -EFSCORRUPTED;
+
+		err = f2fs_submit_page_read_sync(inode, folio, index,
+						blkaddr);
+		if (err)
+			return err;
+balance:
+		/*
+		 * Expand the 4K-page balance decision per subpage: check
+		 * right after each preallocated block.
+		 */
+		if (node_changed && !IS_NOQUOTA(inode) &&
+		    has_not_enough_free_secs(sbi, 0, 0)) {
+			orig_order = folio_order(folio);
+			folio_unlock(folio);
+			f2fs_balance_fs(sbi, true);
+			folio_lock(folio);
+			if (unlikely(folio->mapping != mapping ||
+				     folio_order(folio) != orig_order))
+				return -EAGAIN;
+		}
+	}
+
+	return 0;
+}
+
 static int f2fs_write_begin(const struct kiocb *iocb,
 			    struct address_space *mapping,
 			    loff_t pos, unsigned len, struct folio **foliop,
@@ -4245,8 +4311,8 @@ static int f2fs_write_begin(const struct kiocb *iocb,
 
 	*foliop = folio;
 
-	if (f2fs_is_atomic_file(inode))
-		err = prepare_atomic_write_begin(sbi, folio, pos, len,
+	if (f2fs_is_atomic_file(inode) && !folio_test_large(folio))
+		err = prepare_atomic_write_begin(sbi, inode, folio->index,
 					&blkaddr, &need_balance);
 	else if (!folio_test_large(folio))
 		err = prepare_write_begin(sbi, folio, pos, len,
@@ -4270,10 +4336,18 @@ static int f2fs_write_begin(const struct kiocb *iocb,
 	f2fs_folio_wait_writeback(folio, DATA, false, true);
 
 	if (folio_test_large(folio)) {
-		err = prepare_large_folio_write_begin(inode,
+		if (f2fs_is_atomic_file(inode))
+			err = prepare_large_folio_atomic_write_begin(inode,
+					mapping, folio, pos, len);
+		else
+			err = prepare_large_folio_write_begin(inode,
 					folio, pos, len);
 		if (!err)
 			return 0;
+		if (err == -EAGAIN) {
+			f2fs_folio_put(folio, true);
+			goto repeat;
+		}
 		goto put_folio;
 	}
 
-- 
2.43.0

[PATCH v2 05/14] f2fs: support large folio writeback

[Nanzhe Zhao]

Large folio can contain multiple dirty ranges.
Add a folio-based writeback path for large-folio mapping files
and keep the legacy f2fs_write_cache_pages() path unchanged for
non large-folio mapping files.

Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
 fs/f2fs/data.c | 412 ++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 407 insertions(+), 5 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index eb5fb8e52851..1f9c99689f38 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -355,7 +355,9 @@ static void f2fs_write_end_bio(struct bio *bio)
 
 	bio_for_each_folio_all(fi, bio) {
 		struct folio *folio = fi.folio;
+		unsigned int nr_pages = fi.length >> PAGE_SHIFT;
 		enum count_type type;
+		bool finished = true;
 
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 		if (f2fs_is_compressed_page(folio)) {
@@ -379,10 +381,19 @@ static void f2fs_write_end_bio(struct bio *bio)
 				folio->index, NODE_TYPE_REGULAR, true);
 			f2fs_bug_on(sbi, folio->index != nid_of_node(sbi, folio));
 		}
+		if (f2fs_folio_has_ffs(folio)) {
+			struct f2fs_folio_state *ffs =
+				(struct f2fs_folio_state *)folio->private;
+
+			finished = atomic_sub_and_test(nr_pages,
+					&ffs->write_pages_pending);
+		}
+
 		if (f2fs_in_warm_node_list(sbi, folio))
 			f2fs_del_fsync_node_entry(sbi, folio);
 
-		dec_page_count(sbi, type);
+		while (nr_pages--)
+			dec_page_count(sbi, type);
 
 		/*
 		 * we should access sbi before folio_end_writeback() to
@@ -392,8 +403,10 @@ static void f2fs_write_end_bio(struct bio *bio)
 				wq_has_sleeper(&sbi->cp_wait))
 			wake_up(&sbi->cp_wait);
 
-		folio_clear_f2fs_gcing(folio);
-		folio_end_writeback(folio);
+		if (finished) {
+			folio_clear_f2fs_gcing(folio);
+			folio_end_writeback(folio);
+		}
 	}
 
 	bio_put(bio);
@@ -2654,7 +2667,7 @@ static void f2fs_ffs_mark_subrange_uptodate(struct folio *folio, size_t offset,
 		folio_mark_uptodate(folio);
 }
 
-static void f2fs_ffs_mark_subrange_dirty(struct folio *folio,
+void f2fs_ffs_mark_subrange_dirty(struct folio *folio,
 				    size_t offset, size_t len)
 {
 	struct f2fs_folio_state *ffs;
@@ -2677,6 +2690,99 @@ static void f2fs_ffs_mark_subrange_dirty(struct folio *folio,
 	spin_unlock_irqrestore(&ffs->state_lock, flags);
 }
 
+static bool __ffs_clear_subrange_dirty(struct folio *folio,
+			struct f2fs_folio_state *ffs, size_t offset, size_t len)
+{
+	unsigned int nr_subpages = folio_nr_pages(folio);
+	unsigned int start, end;
+
+	start = offset >> PAGE_SHIFT;
+	end = (offset + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	end = min(end, nr_subpages);
+
+	bitmap_clear(ffs->state, nr_subpages + start, end - start);
+	return find_next_bit(ffs->state, 2 * nr_subpages, nr_subpages) <
+			2 * nr_subpages;
+}
+
+/**
+ * f2fs_ffs_clear_subrange_dirty_and_test - clear dirty bits and test remaining
+ * @folio: the large folio
+ * @offset: start byte offset within the folio
+ * @len: byte length of the subrange
+ *
+ * Clear the dirty bits of the 4K subpages covered by [offset, offset + len),
+ * and return whether the folio still has any dirty subpage left.
+ */
+bool f2fs_ffs_clear_subrange_dirty_and_test(struct folio *folio, size_t offset,
+					    size_t len)
+{
+	struct f2fs_folio_state *ffs;
+	unsigned long flags;
+	bool dirty;
+
+	if (!f2fs_folio_has_ffs(folio))
+		return false;
+
+	ffs = (struct f2fs_folio_state *)folio->private;
+	spin_lock_irqsave(&ffs->state_lock, flags);
+	dirty = __ffs_clear_subrange_dirty(folio, ffs, offset, len);
+	spin_unlock_irqrestore(&ffs->state_lock, flags);
+
+	return dirty;
+}
+
+static unsigned int ffs_next_dirty_subpage(struct f2fs_folio_state *ffs,
+			const struct folio *folio, unsigned int start,
+			unsigned int end)
+{
+	unsigned int nr_subpages = folio_nr_pages(folio);
+
+	return find_next_bit(ffs->state, nr_subpages + end + 1,
+			nr_subpages + start) - nr_subpages;
+}
+
+static unsigned int ffs_next_clean_subpage(struct f2fs_folio_state *ffs,
+			const struct folio *folio, unsigned int start,
+			unsigned int end)
+{
+	unsigned int nr_subpages = folio_nr_pages(folio);
+
+	return find_next_zero_bit(ffs->state, nr_subpages + end + 1,
+			nr_subpages + start) - nr_subpages;
+}
+
+static unsigned int ffs_find_dirty_range(struct folio *folio,
+					u64 *range_start, u64 range_end)
+{
+	struct f2fs_folio_state *ffs;
+	unsigned int start, end, nr_pages;
+
+	if (*range_start >= range_end)
+		return 0;
+
+	if (!f2fs_folio_has_ffs(folio))
+		return range_end - *range_start;
+
+	ffs = (struct f2fs_folio_state *)folio->private;
+	start = offset_in_folio(folio, *range_start) >> PAGE_SHIFT;
+	end = DIV_ROUND_UP(min_not_zero(offset_in_folio(folio, range_end),
+					folio_size(folio)), PAGE_SIZE) - 1;
+
+	start = ffs_next_dirty_subpage(ffs, folio, start, end);
+	if (start > end)
+		return 0;
+
+	if (start == end)
+		nr_pages = 1;
+	else
+		nr_pages = ffs_next_clean_subpage(ffs, folio,
+						 start + 1, end) - start;
+
+	*range_start = folio_pos(folio) + ((u64)start << PAGE_SHIFT);
+	return (u64)nr_pages << PAGE_SHIFT;
+}
+
 static bool find_next_valid_block(const struct folio *folio,
 				  size_t orig_off, size_t *need_off,
 				  size_t len)
@@ -3256,6 +3362,133 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
 	return err;
 }
 
+static int f2fs_write_single_data_folio(struct folio *folio, int *submitted,
+					struct writeback_control *wbc,
+					enum iostat_type io_type,
+					u64 *pos, u64 len)
+{
+	struct inode *inode = folio->mapping->host;
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	bool atomic_commit = f2fs_is_atomic_file(inode) &&
+				folio_test_f2fs_atomic(folio);
+	struct inode *dn_inode = atomic_commit ?
+				F2FS_I(inode)->cow_inode : inode;
+	struct f2fs_folio_state *ffs = NULL;
+	u64 folio_start = folio_pos(folio);
+	pgoff_t start_idx = (*pos - folio_start) >> PAGE_SHIFT;
+	pgoff_t end_idx = (*pos - folio_start + len - 1) >> PAGE_SHIFT;
+	int err = 0;
+
+	for (pgoff_t i = start_idx; i <= end_idx && !err; i++) {
+		struct dnode_of_data dn;
+		struct node_info ni;
+		pgoff_t data_idx = folio->index + i;
+		bool ipu_force = false;
+		bool dn_held = false;
+		bool submitted_blk = false;
+		struct f2fs_io_info fio = {
+			.sbi = sbi,
+			.ino = inode->i_ino,
+			.type = DATA,
+			.op = REQ_OP_WRITE,
+			.op_flags = wbc_to_write_flags(wbc),
+			.old_blkaddr = NULL_ADDR,
+			.folio = folio,
+			.folio_offset = i,
+			.folio_blkcnt = 1,
+			.encrypted_page = NULL,
+			.submitted = 0,
+			.need_lock = LOCK_DONE,
+			.meta_gc = f2fs_meta_inode_gc_required(inode) ? 1 : 0,
+			.io_type = io_type,
+			.io_wbc = wbc,
+		};
+
+		if (f2fs_folio_has_ffs(folio)) {
+			ffs = (struct f2fs_folio_state *)folio->private;
+			atomic_inc(&ffs->write_pages_pending);
+		}
+
+		set_new_dnode(&dn, dn_inode, NULL, NULL, 0);
+
+		if (need_inplace_update(&fio) &&
+		    f2fs_lookup_read_extent_cache_block(inode, data_idx,
+							&fio.old_blkaddr)) {
+			if (!f2fs_is_valid_blkaddr(sbi, fio.old_blkaddr,
+						   DATA_GENERIC_ENHANCE)) {
+				err = -EFSCORRUPTED;
+				goto block_done;
+			}
+			ipu_force = true;
+			goto got_it;
+		}
+
+		err = f2fs_get_dnode_of_data(&dn, data_idx, LOOKUP_NODE);
+		if (err)
+			goto block_done;
+		dn_held = true;
+
+		fio.old_blkaddr = dn.data_blkaddr;
+
+got_it:
+		if (__is_valid_data_blkaddr(fio.old_blkaddr) &&
+		    !f2fs_is_valid_blkaddr(sbi, fio.old_blkaddr,
+					   DATA_GENERIC_ENHANCE)) {
+			err = -EFSCORRUPTED;
+			goto block_done;
+		}
+
+		if (fio.meta_gc)
+			f2fs_wait_on_block_writeback(inode, fio.old_blkaddr);
+
+		if (ipu_force ||
+		    (__is_valid_data_blkaddr(fio.old_blkaddr) &&
+					    need_inplace_update(&fio))) {
+			f2fs_put_dnode(&dn);
+			err = f2fs_inplace_write_data(&fio);
+			trace_f2fs_do_write_data_page(folio, IPU);
+			if (err)
+				goto block_done;
+
+			if (submitted)
+				(*submitted)++;
+			submitted_blk = true;
+			set_inode_flag(inode, FI_UPDATE_WRITE);
+			goto block_done;
+		}
+
+		err = f2fs_get_node_info(sbi, dn.nid, &ni, false);
+		if (err)
+			goto block_done;
+
+		fio.version = ni.version;
+
+		f2fs_outplace_write_data(&dn, &fio);
+		if (submitted)
+			(*submitted)++;
+		submitted_blk = true;
+		set_inode_flag(inode, FI_APPEND_WRITE);
+		trace_f2fs_do_write_data_page(folio, OPU);
+		goto block_done;
+block_done:
+		if (dn_held)
+			f2fs_put_dnode(&dn);
+		if (!submitted_blk && ffs)
+			atomic_dec(&ffs->write_pages_pending);
+		if (!err) {
+			*pos = (data_idx + 1) << PAGE_SHIFT;
+			spin_lock(&F2FS_I(inode)->i_size_lock);
+			if (F2FS_I(inode)->last_disk_size < *pos)
+				F2FS_I(inode)->last_disk_size = *pos;
+			spin_unlock(&F2FS_I(inode)->i_size_lock);
+		} else {
+			file_set_keep_isize(inode);
+		}
+	}
+
+	return err;
+}
+
 int f2fs_write_single_data_page(struct folio *folio, int *submitted,
 				struct bio **bio,
 				sector_t *last_block,
@@ -3705,6 +3938,172 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
 	return ret;
 }
 
+static int f2fs_write_cache_folios(struct address_space *mapping,
+				   struct writeback_control *wbc,
+				   enum iostat_type io_type)
+{
+	struct folio *folio = NULL;
+	struct inode *inode = mapping->host;
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct f2fs_lock_context lc;
+	u64 pos = 0;
+	u64 end_pos = 0;
+	u32 r_len = 0;
+	int err = 0;
+	int submitted = 0;
+	int nwritten = 0;
+	bool op_locked = false;
+	bool next = false;
+	bool retry = false;
+
+	if (get_dirty_pages(inode) <= SM_I(sbi)->min_hot_blocks)
+		set_inode_flag(inode, FI_HOT_DATA);
+	else
+		clear_inode_flag(inode, FI_HOT_DATA);
+
+	while ((folio = writeback_iter(mapping, wbc, folio, &err))) {
+		struct f2fs_folio_state *ffs = NULL;
+		u64 isize;
+		size_t poff;
+		pgoff_t end_index;
+		bool verity_in_progress;
+		int folio_submitted = 0;
+		bool bias_added = false;
+
+		submitted = 0;
+		next = true;
+		retry = false;
+
+		if (atomic_read(&sbi->wb_sync_req[DATA]) &&
+		    wbc->sync_mode == WB_SYNC_NONE) {
+			folio_redirty_for_writepage(wbc, folio);
+			next = false;
+			goto retry_out;
+		}
+retry:
+		pos = folio_pos(folio);
+		end_pos = pos + folio_size(folio);
+		isize = i_size_read(inode);
+		verity_in_progress = f2fs_verity_in_progress(inode);
+		poff = 0;
+		end_index = 0;
+
+		if (retry) {
+
+			if (unlikely(folio->mapping != mapping))
+				goto retry_out;
+
+			if (!folio_test_dirty(folio))
+				goto retry_out;
+
+			if (folio_test_writeback(folio)) {
+				if (wbc->sync_mode == WB_SYNC_NONE)
+					goto retry_out;
+				f2fs_folio_wait_writeback(folio, DATA, true, true);
+			}
+
+			if (!folio_clear_dirty_for_io(folio))
+				goto retry_out;
+		}
+
+		/* To avoid dealing with the complexity for one subrange is in bio
+		 * while we trylock_op failed before writing another subrange.
+		 * Try to lock_op before any subrange write for the folio.
+		 */
+		if (!op_locked) {
+			if (!f2fs_trylock_op(sbi, &lc)) {
+				folio_redirty_for_writepage(wbc, folio);
+				err = 0;
+				if (wbc->sync_mode != WB_SYNC_ALL)
+					goto retry_out;
+
+				retry = true;
+				folio_unlock(folio);
+				f2fs_io_schedule_timeout(DEFAULT_SCHEDULE_TIMEOUT);
+				folio_lock(folio);
+				goto retry;
+			}
+			op_locked = true;
+		}
+
+		if (!verity_in_progress) {
+			poff = offset_in_folio(folio, isize);
+			end_index = isize >> PAGE_SHIFT;
+
+			if (folio->index > end_index ||
+			    (folio->index == end_index && poff == 0))
+				goto out;
+
+			if (end_pos > isize) {
+				folio_zero_segment(folio, poff, folio_size(folio));
+				end_pos = isize;
+			}
+		}
+
+		folio_start_writeback(folio);
+
+		if (!bias_added && f2fs_folio_has_ffs(folio)) {
+			ffs = (struct f2fs_folio_state *)folio->private;
+			WARN_ON_ONCE(atomic_read(&ffs->write_pages_pending) != 0);
+			atomic_inc(&ffs->write_pages_pending);
+			bias_added = true;
+		}
+
+		while ((r_len = ffs_find_dirty_range(folio, &pos, end_pos))) {
+			err = f2fs_write_single_data_folio(folio, &submitted,
+					wbc, io_type, &pos, r_len);
+			folio_submitted += submitted;
+			if (err)
+				goto out;
+
+			nwritten += submitted;
+		}
+
+		if (!err && folio_submitted &&
+		    f2fs_is_atomic_file(inode) &&
+		    folio_test_f2fs_atomic(folio))
+			folio_clear_f2fs_atomic(folio);
+
+out:
+		/*
+		 * Clear the dirty state of the subranges that were written back.
+		 * If some subranges are still dirty (e.g. the folio was only
+		 * partially written back), the folio must stay dirty so that
+		 * the remaining subranges are written back later.
+		 */
+		if (f2fs_ffs_clear_subrange_dirty_and_test(folio, 0,
+					(err ? pos : end_pos) - folio_pos(folio)))
+			folio_redirty_for_writepage(wbc, folio);
+		else
+			inode_dec_dirty_pages(inode);
+
+		if (bias_added) {
+			if (atomic_dec_and_test(&ffs->write_pages_pending))
+				folio_end_writeback(folio);
+		} else if (!folio_submitted && folio_test_writeback(folio)) {
+			folio_end_writeback(folio);
+		}
+
+retry_out:
+		if (folio_test_locked(folio))
+			folio_unlock(folio);
+
+		if (op_locked) {
+			f2fs_unlock_op(sbi, &lc);
+			op_locked = false;
+		}
+
+		if (err || !next)
+			break;
+	}
+
+	if (nwritten)
+		f2fs_submit_merged_write_cond(F2FS_M_SB(mapping), mapping->host,
+					       NULL, 0, DATA);
+
+	return err;
+}
+
 static inline bool __should_serialize_io(struct inode *inode,
 					struct writeback_control *wbc)
 {
@@ -3799,7 +4198,10 @@ static int __f2fs_write_data_pages(struct address_space *mapping,
 	account_writeback(inode, true);
 
 	blk_start_plug(&plug);
-	ret = f2fs_write_cache_pages(mapping, wbc, io_type);
+	if (mapping_large_folio_support(inode->i_mapping))
+		ret = f2fs_write_cache_folios(mapping, wbc, io_type);
+	else
+		ret = f2fs_write_cache_pages(mapping, wbc, io_type);
 	blk_finish_plug(&plug);
 
 	account_writeback(inode, false);
-- 
2.43.0

[PATCH v2 06/14] f2fs: prepare mmap write faults for large folios

[Nanzhe Zhao]

Now write protect `mmap` also need to support large folio,
Change `f2fs_vm_page_mkwrite` to acheive that.

Note it currently marks the whole large folio dirty
to avoid data loss which causes write amplification.
Further optimization is welcome.

PG_mappedtodisk is useless in f2fs, so drop the
folio_test_mappedtodisk() check and its goto out_sem
shortcut in f2fs_vm_page_mkwrite().  We extend the
folio_zero_segment() in mkwrite to zero the post-EOF part
of the faulted folio for both order-0 and large folios, so
the f2fs_zero_post_eof_page() call added to cover that
shortcut is no longer needed.

Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
 fs/f2fs/f2fs.h |   4 ++
 fs/f2fs/file.c | 107 ++++++++++++++++++++++++++++++-------------------
 2 files changed, 70 insertions(+), 41 deletions(-)

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 8eccca6e5d27..f48e2627d90a 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -4393,6 +4393,10 @@ int f2fs_write_single_data_page(struct folio *folio, int *submitted,
 				enum iostat_type io_type,
 				int compr_blocks, bool allow_balance);
 bool f2fs_ffs_test_blk_uptodate(const struct folio *folio, pgoff_t index);
+struct f2fs_folio_state *f2fs_ffs_find_or_alloc(struct folio *folio);
+void f2fs_ffs_mark_subrange_dirty(struct folio *folio, size_t offset, size_t len);
+bool f2fs_ffs_clear_subrange_dirty_and_test(struct folio *folio, size_t offset,
+					    size_t len);
 void f2fs_write_failed(struct inode *inode, loff_t to);
 void f2fs_invalidate_folio(struct folio *folio, size_t offset, size_t length);
 bool f2fs_release_folio(struct folio *folio, gfp_t wait);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 9071bd23e57b..738a751c3903 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -118,13 +118,47 @@ static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf)
 	return ret;
 }
 
+static int f2fs_get_block_mkwrite(struct inode *inode, struct folio *folio,
+				  pgoff_t index, bool need_alloc)
+{
+	struct dnode_of_data dn;
+	int err;
+
+	set_new_dnode(&dn, inode, NULL, NULL, 0);
+	if (need_alloc) {
+		err = f2fs_get_block_locked(&dn, index);
+	} else {
+		err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
+		f2fs_put_dnode(&dn);
+		if (f2fs_is_pinned_file(inode) &&
+		    !__is_valid_data_blkaddr(dn.data_blkaddr))
+			err = -EIO;
+	}
+
+	if (err)
+		return err;
+
+	f2fs_folio_wait_writeback(folio, DATA, false, true);
+
+	/* wait for GCed page writeback via META_MAPPING */
+	f2fs_wait_on_block_writeback(inode, dn.data_blkaddr);
+
+	return 0;
+}
+
 static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 {
 	struct folio *folio = page_folio(vmf->page);
 	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct dnode_of_data dn;
 	bool need_alloc = !f2fs_is_pinned_file(inode);
+	pgoff_t pidx = folio->index + folio_page_idx(folio, vmf->page);
+	loff_t pos = (loff_t)pidx << PAGE_SHIFT;
+	loff_t isize;
+	loff_t folio_start;
+	loff_t valid_end;
+	size_t dirty_len;
+	size_t subpage_off;
 	int err = 0;
 	vm_fault_t ret;
 
@@ -161,7 +195,7 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 	if (f2fs_compressed_file(inode)) {
-		int ret = f2fs_is_compressed_cluster(inode, folio->index);
+		int ret = f2fs_is_compressed_cluster(inode, pidx);
 
 		if (ret < 0) {
 			err = ret;
@@ -179,72 +213,63 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 
 	f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
 
-	err = f2fs_zero_post_eof_page(inode,
-		(folio->index + 1) << PAGE_SHIFT, true, false);
-	if (err)
-		goto out_pagefault;
-
 	file_update_time(vmf->vma->vm_file);
 	filemap_invalidate_lock_shared(inode->i_mapping);
 
 	folio_lock(folio);
+	isize = i_size_read(inode);
+	folio_start = folio_pos(folio);
+	subpage_off = offset_in_folio(folio, pos);
+	valid_end = min_t(loff_t, folio_start + folio_size(folio), isize);
+	dirty_len = valid_end > folio_start ? valid_end - folio_start : 0;
+
 	if (unlikely(folio->mapping != inode->i_mapping ||
-			folio_pos(folio) > i_size_read(inode) ||
-			!folio_test_uptodate(folio))) {
+			pos >= isize ||
+			!f2fs_ffs_test_blk_uptodate(folio,
+			folio->index + (subpage_off >> PAGE_SHIFT)))) {
 		folio_unlock(folio);
 		err = -EFAULT;
 		goto out_sem;
 	}
 
-	set_new_dnode(&dn, inode, NULL, NULL, 0);
-	if (need_alloc) {
-		/* block allocation */
-		err = f2fs_get_block_locked(&dn, folio->index);
-	} else {
-		err = f2fs_get_dnode_of_data(&dn, folio->index, LOOKUP_NODE);
-		f2fs_put_dnode(&dn);
-		if (f2fs_is_pinned_file(inode) &&
-		    !__is_valid_data_blkaddr(dn.data_blkaddr))
-			err = -EIO;
-	}
+	pgoff_t i, nr = DIV_ROUND_UP(dirty_len, PAGE_SIZE);
 
-	if (err) {
-		folio_unlock(folio);
-		goto out_sem;
+	for (i = 0; i < nr; i++) {
+		err = f2fs_get_block_mkwrite(inode, folio, folio->index + i,
+					     need_alloc);
+		if (err) {
+			folio_unlock(folio);
+			goto out_sem;
+		}
 	}
 
-	f2fs_folio_wait_writeback(folio, DATA, false, true);
-
-	/* wait for GCed page writeback via META_MAPPING */
-	f2fs_wait_on_block_writeback(inode, dn.data_blkaddr);
-
-	/*
-	 * check to see if the page is mapped already (no holes)
-	 */
-	if (folio_test_mappedtodisk(folio))
-		goto out_sem;
-
 	/* page is wholly or partially inside EOF */
-	if (((loff_t)(folio->index + 1) << PAGE_SHIFT) >
-						i_size_read(inode)) {
-		loff_t offset;
+	if (folio_start + folio_size(folio) > isize) {
+		size_t offset = offset_in_folio(folio, isize);
 
-		offset = i_size_read(inode) & ~PAGE_MASK;
 		folio_zero_segment(folio, offset, folio_size(folio));
 	}
+
+	if (folio_test_large(folio)) {
+		if (!f2fs_ffs_find_or_alloc(folio)) {
+			folio_unlock(folio);
+			err = -ENOMEM;
+			goto out_sem;
+		}
+		f2fs_ffs_mark_subrange_dirty(folio, 0, dirty_len);
+	}
 	folio_mark_dirty(folio);
 
-	f2fs_update_iostat(sbi, inode, APP_MAPPED_IO, F2FS_BLKSIZE(sbi));
+	f2fs_update_iostat(sbi, inode, APP_MAPPED_IO, dirty_len);
 	f2fs_update_time(sbi, REQ_TIME);
 
 out_sem:
 	filemap_invalidate_unlock_shared(inode->i_mapping);
-out_pagefault:
 	sb_end_pagefault(inode->i_sb);
 out:
 	ret = vmf_fs_error(err);
 
-	trace_f2fs_vm_page_mkwrite(inode, folio->index, vmf->vma->vm_flags, ret);
+	trace_f2fs_vm_page_mkwrite(inode, pidx, vmf->vma->vm_flags, ret);
 	return ret;
 }
 
-- 
2.43.0

[PATCH v2 07/14] f2fs: make GC migration large-folio aware

[Nanzhe Zhao]

GC can operate on a 4K block that is cached inside a large folio.
The data lookup helpers therefore need to test and update uptodate
state for the addressed subpage instead of rejecting large folios or
treating the whole folio as the target block.

Let f2fs_get_read_data_folio(), f2fs_find_data_folio(), and
f2fs_get_lock_data_folio() to use subpage uptodate state. Submit
single-block reads at the requested folio offset and zero only the
addressed 4K range for NEW_ADDR.

Also update `move_data_page` to mark, clear, and restore dirty
state for the target subpage, and submit write I/O with the subpage
offset recorded in f2fs_io_info.

Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
 fs/f2fs/data.c    | 75 ++++++++++++++++++++++++++++++-----------------
 fs/f2fs/f2fs.h    |  1 +
 fs/f2fs/gc.c      | 30 +++++++++++++++++--
 fs/f2fs/segment.c |  2 +-
 4 files changed, 78 insertions(+), 30 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 1f9c99689f38..287d83debf95 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1226,19 +1226,26 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode,
 
 /* This can handle encryption stuffs */
 static void f2fs_submit_page_read(struct inode *inode, struct fsverity_info *vi,
-				  struct folio *folio, block_t blkaddr,
-				  blk_opf_t op_flags, bool for_write)
+				  struct folio *folio, pgoff_t index,
+				  block_t blkaddr, blk_opf_t op_flags,
+				  bool for_write)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct bio *bio;
+	size_t offset = 0;
 
-	bio = f2fs_grab_read_bio(inode, vi, blkaddr, 1, op_flags, folio->index,
+	if (f2fs_folio_has_ffs(folio)) {
+		offset = offset_in_folio(folio, (loff_t)index << PAGE_SHIFT);
+		f2fs_update_read_folio_pending(folio, 1);
+	}
+
+	bio = f2fs_grab_read_bio(inode, vi, blkaddr, 1, op_flags, index,
 				 for_write);
 
 	/* wait for GCed page writeback via META_MAPPING */
 	f2fs_wait_on_block_writeback(inode, blkaddr);
 
-	if (!bio_add_folio(bio, folio, PAGE_SIZE, 0))
+	if (!bio_add_folio(bio, folio, PAGE_SIZE, offset))
 		f2fs_bug_on(sbi, 1);
 
 	inc_page_count(sbi, F2FS_RD_DATA);
@@ -1379,20 +1386,16 @@ struct folio *f2fs_get_read_data_folio(struct inode *inode, pgoff_t index,
 	struct dnode_of_data dn;
 	struct folio *folio;
 	int err;
-retry:
+
 	folio = f2fs_grab_cache_folio(mapping, index, for_write);
 	if (IS_ERR(folio))
 		return folio;
 
 	if (folio_test_large(folio)) {
-		pgoff_t folio_index = mapping_align_index(mapping, index);
-		unsigned long nr_pages = folio_nr_pages(folio);
-
-		f2fs_folio_put(folio, true);
-		invalidate_inode_pages2_range(mapping, folio_index,
-				folio_index + nr_pages - 1);
-		f2fs_schedule_timeout(DEFAULT_SCHEDULE_TIMEOUT);
-		goto retry;
+		if (!f2fs_ffs_find_or_alloc(folio)) {
+			err = -ENOMEM;
+			goto put_err;
+		}
 	}
 
 	if (f2fs_lookup_read_extent_cache_block(inode, index,
@@ -1428,7 +1431,7 @@ struct folio *f2fs_get_read_data_folio(struct inode *inode, pgoff_t index,
 		goto put_err;
 	}
 got_it:
-	if (folio_test_uptodate(folio)) {
+	if (f2fs_ffs_test_blk_uptodate(folio, index)) {
 		folio_unlock(folio);
 		return folio;
 	}
@@ -1441,15 +1444,17 @@ struct folio *f2fs_get_read_data_folio(struct inode *inode, pgoff_t index,
 	 * f2fs_init_inode_metadata.
 	 */
 	if (dn.data_blkaddr == NEW_ADDR) {
-		folio_zero_segment(folio, 0, folio_size(folio));
-		if (!folio_test_uptodate(folio))
-			folio_mark_uptodate(folio);
+		size_t offset = offset_in_folio(folio,
+						(loff_t)index << PAGE_SHIFT);
+
+		folio_zero_segment(folio, offset, offset + PAGE_SIZE);
+		f2fs_ffs_mark_subrange_uptodate(folio, offset, PAGE_SIZE);
 		folio_unlock(folio);
 		return folio;
 	}
 
-	f2fs_submit_page_read(inode, f2fs_need_verity(inode, folio->index),
-			      folio, dn.data_blkaddr, op_flags, for_write);
+	f2fs_submit_page_read(inode, f2fs_need_verity(inode, index),
+			      folio, index, dn.data_blkaddr, op_flags, for_write);
 	return folio;
 
 put_err:
@@ -1466,7 +1471,7 @@ struct folio *f2fs_find_data_folio(struct inode *inode, pgoff_t index,
 	folio = f2fs_filemap_get_folio(mapping, index, FGP_ACCESSED, 0);
 	if (IS_ERR(folio))
 		goto read;
-	if (folio_test_uptodate(folio))
+	if (f2fs_ffs_test_blk_uptodate(folio, index))
 		return folio;
 	f2fs_folio_put(folio, false);
 
@@ -1475,11 +1480,11 @@ struct folio *f2fs_find_data_folio(struct inode *inode, pgoff_t index,
 	if (IS_ERR(folio))
 		return folio;
 
-	if (folio_test_uptodate(folio))
+	if (f2fs_ffs_test_blk_uptodate(folio, index))
 		return folio;
 
 	folio_wait_locked(folio);
-	if (unlikely(!folio_test_uptodate(folio))) {
+	if (unlikely(!f2fs_ffs_test_blk_uptodate(folio, index))) {
 		f2fs_folio_put(folio, false);
 		return ERR_PTR(-EIO);
 	}
@@ -1503,7 +1508,8 @@ struct folio *f2fs_get_lock_data_folio(struct inode *inode, pgoff_t index,
 
 	/* wait for read completion */
 	folio_lock(folio);
-	if (unlikely(folio->mapping != mapping || !folio_test_uptodate(folio))) {
+	if (unlikely(folio->mapping != mapping ||
+		    !f2fs_ffs_test_blk_uptodate(folio, index))) {
 		f2fs_folio_put(folio, true);
 		return ERR_PTR(-EIO);
 	}
@@ -2667,6 +2673,22 @@ static void f2fs_ffs_mark_subrange_uptodate(struct folio *folio, size_t offset,
 		folio_mark_uptodate(folio);
 }
 
+bool f2fs_ffs_test_blk_dirty(const struct folio *folio, pgoff_t index)
+{
+	struct f2fs_folio_state *ffs;
+	unsigned int idx, nr_subpages;
+
+	f2fs_bug_on(F2FS_F_SB(folio), !folio_contains(folio, index));
+
+	if (!f2fs_folio_has_ffs(folio))
+		return folio_test_dirty(folio);
+
+	ffs = folio->private;
+	nr_subpages = folio_nr_pages(folio);
+	idx = index - folio->index;
+	return test_bit(nr_subpages + idx, ffs->state);
+}
+
 void f2fs_ffs_mark_subrange_dirty(struct folio *folio,
 				    size_t offset, size_t len)
 {
@@ -2724,14 +2746,13 @@ bool f2fs_ffs_clear_subrange_dirty_and_test(struct folio *folio, size_t offset,
 	if (!f2fs_folio_has_ffs(folio))
 		return false;
 
-	ffs = (struct f2fs_folio_state *)folio->private;
+	ffs = folio->private;
 	spin_lock_irqsave(&ffs->state_lock, flags);
 	dirty = __ffs_clear_subrange_dirty(folio, ffs, offset, len);
 	spin_unlock_irqrestore(&ffs->state_lock, flags);
 
 	return dirty;
 }
-
 static unsigned int ffs_next_dirty_subpage(struct f2fs_folio_state *ffs,
 			const struct folio *folio, unsigned int start,
 			unsigned int end)
@@ -3225,7 +3246,7 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio)
 		return true;
 
 	if (fio) {
-		if (page_private_gcing(fio->page))
+		if (folio_test_f2fs_gcing(fio->folio))
 			return true;
 		if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
 			f2fs_is_checkpointed_data(sbi, fio->old_blkaddr)))
@@ -4781,7 +4802,7 @@ static int f2fs_write_begin(const struct kiocb *iocb,
 		 */
 		f2fs_submit_page_read(inode,
 				      NULL, /* can't write to fsverity files */
-				      folio, blkaddr, 0, true);
+				      folio, index, blkaddr, 0, true);
 
 		folio_lock(folio);
 		if (unlikely(folio->mapping != mapping)) {
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index f48e2627d90a..6be08e45341c 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -4394,6 +4394,7 @@ int f2fs_write_single_data_page(struct folio *folio, int *submitted,
 				int compr_blocks, bool allow_balance);
 bool f2fs_ffs_test_blk_uptodate(const struct folio *folio, pgoff_t index);
 struct f2fs_folio_state *f2fs_ffs_find_or_alloc(struct folio *folio);
+bool f2fs_ffs_test_blk_dirty(const struct folio *folio, pgoff_t index);
 void f2fs_ffs_mark_subrange_dirty(struct folio *folio, size_t offset, size_t len);
 bool f2fs_ffs_clear_subrange_dirty_and_test(struct folio *folio, size_t offset,
 					    size_t len);
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 16fce62740d7..147836f1155f 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -1509,12 +1509,19 @@ static int move_data_page(struct inode *inode, block_t bidx, int gc_type,
 						unsigned int segno, int off)
 {
 	struct folio *folio;
+	size_t foff = 0;
+	bool large = false;
 	int err = 0;
 
 	folio = f2fs_get_lock_data_folio(inode, bidx, true);
 	if (IS_ERR(folio))
 		return PTR_ERR(folio);
 
+	if (f2fs_folio_has_ffs(folio)) {
+		large = true;
+		foff = offset_in_folio(folio, (loff_t)bidx << PAGE_SHIFT);
+	}
+
 	if (!check_valid_map(F2FS_I_SB(inode), segno, off)) {
 		err = -ENOENT;
 		goto out;
@@ -1529,6 +1536,8 @@ static int move_data_page(struct inode *inode, block_t bidx, int gc_type,
 			err = -EAGAIN;
 			goto out;
 		}
+		if (large)
+			f2fs_ffs_mark_subrange_dirty(folio, foff, PAGE_SIZE);
 		folio_mark_dirty(folio);
 		folio_set_f2fs_gcing(folio);
 	} else {
@@ -1541,32 +1550,49 @@ static int move_data_page(struct inode *inode, block_t bidx, int gc_type,
 			.op_flags = REQ_SYNC,
 			.old_blkaddr = NULL_ADDR,
 			.folio = folio,
+			.folio_offset = bidx - folio->index,
+			.folio_blkcnt = 1,
 			.encrypted_page = NULL,
 			.need_lock = LOCK_REQ,
 			.io_type = FS_GC_DATA_IO,
 		};
-		bool is_dirty = folio_test_dirty(folio);
+		struct f2fs_folio_state *ffs = NULL;
+		bool is_dirty = f2fs_ffs_test_blk_dirty(folio, bidx);
 
 retry:
 		f2fs_folio_wait_writeback(folio, DATA, true, true);
 
+		if (large) {
+			ffs = folio->private;
+			f2fs_ffs_mark_subrange_dirty(folio, foff, PAGE_SIZE);
+		}
 		folio_mark_dirty(folio);
 		if (folio_clear_dirty_for_io(folio)) {
 			inode_dec_dirty_pages(inode);
 			f2fs_remove_dirty_inode(inode);
+			if (large &&
+			    f2fs_ffs_clear_subrange_dirty_and_test(folio, foff, PAGE_SIZE))
+				folio_mark_dirty(folio);
 		}
 
+		if (large)
+			atomic_inc(&ffs->write_pages_pending);
 		folio_set_f2fs_gcing(folio);
 
 		err = f2fs_do_write_data_page(&fio);
 		if (err) {
 			folio_clear_f2fs_gcing(folio);
+			if (large)
+				atomic_dec(&ffs->write_pages_pending);
 			if (err == -ENOMEM) {
 				memalloc_retry_wait(GFP_NOFS);
 				goto retry;
 			}
-			if (is_dirty)
+			if (is_dirty) {
+				if (large)
+					f2fs_ffs_mark_subrange_dirty(folio, foff, PAGE_SIZE);
 				folio_mark_dirty(folio);
+			}
 		}
 	}
 out:
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 644ddfb984c9..a81cc8c5c34a 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -3860,7 +3860,7 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
 		if (is_inode_flag_set(inode, FI_ALIGNED_WRITE))
 			return CURSEG_COLD_DATA_PINNED;
 
-		if (page_private_gcing(fio->page)) {
+		if (folio_test_f2fs_gcing(fio->folio)) {
 			if (fio->sbi->am.atgc_enabled &&
 				(fio->io_type == FS_DATA_IO) &&
 				(fio->sbi->gc_mode != GC_URGENT_HIGH) &&
-- 
2.43.0

[PATCH v2 08/14] f2fs: optimize small block size large folio read

[Nanzhe Zhao]

The original f2fs_read_data_large_folio() implementation has limited
benefit with a 4KB block size, mainly because updating
read_pages_pending greatly increases the number of spinlock
operations.

Use len_blks to batch read_pages_pending and iostat updates for
contiguous mapped blocks. If the contiguous mapping covers the whole
folio, skip f2fs_folio_state allocation for that folio.

Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
 fs/f2fs/data.c | 65 ++++++++++++++++++++++++++++++++++----------------
 1 file changed, 45 insertions(+), 20 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 287d83debf95..09ad5cf0d9aa 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -173,8 +173,9 @@ static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
 			continue;
 		}
 
-		if (folio_test_large(folio)) {
-			struct f2fs_folio_state *ffs = folio->private;
+		if (f2fs_folio_has_ffs(folio)) {
+			struct f2fs_folio_state *ffs =
+				(struct f2fs_folio_state *)folio->private;
 
 			spin_lock_irqsave(&ffs->state_lock, flags);
 			ffs->read_pages_pending -= nr_pages;
@@ -2844,8 +2845,7 @@ static int f2fs_read_data_large_folio(struct inode *inode,
 	pgoff_t index, offset, next_pgofs = 0;
 	unsigned max_nr_pages = rac ? readahead_count(rac) :
 				folio_nr_pages(folio);
-	unsigned int nrpages;
-	struct f2fs_folio_state *ffs;
+	unsigned int nrpages, len_blks;
 	int ret = 0;
 	bool folio_in_bio = false;
 
@@ -2868,11 +2868,17 @@ static int f2fs_read_data_large_folio(struct inode *inode,
 	folio_in_bio = false;
 	index = folio->index;
 	offset = 0;
-	ffs = NULL;
 	nrpages = folio_nr_pages(folio);
 
-	for (; nrpages; nrpages--, max_nr_pages--, index++, offset++) {
+	for (; nrpages;
+	     nrpages -= len_blks, max_nr_pages -= len_blks,
+	     index += len_blks, offset += len_blks) {
 		sector_t block_nr;
+		bool whole_folio_in_bio;
+		unsigned int i;
+
+		len_blks = 1;
+
 		/*
 		 * Map blocks using the previous result first.
 		 */
@@ -2901,13 +2907,31 @@ static int f2fs_read_data_large_folio(struct inode *inode,
 got_it:
 		if ((map.m_flags & F2FS_MAP_MAPPED)) {
 			block_nr = map.m_pblk + index - map.m_lblk;
-			if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr,
+
+			len_blks = min_t(unsigned int, nrpages, max_nr_pages);
+			len_blks = min_t(unsigned int, len_blks,
+					(unsigned int)(map.m_lblk + map.m_len - index));
+
+			for (i = 0; i < len_blks; i++) {
+				if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode),
+						block_nr + i,
 						DATA_GENERIC_ENHANCE_READ)) {
-				ret = -EFSCORRUPTED;
-				goto err_out;
+					ret = -EFSCORRUPTED;
+					goto err_out;
+				}
 			}
+
+			/*
+			 * If an entire folio is added to one bio,
+			 * folio_end_read() can complete the folio read status
+			 * without relying on f2fs_folio_state.
+			 */
+			whole_folio_in_bio = offset == 0 &&
+					len_blks == folio_nr_pages(folio);
+
 		} else {
 			size_t page_offset = offset << PAGE_SHIFT;
+
 			folio_zero_range(folio, page_offset, PAGE_SIZE);
 			if (vi && !fsverity_verify_blocks(vi, folio, PAGE_SIZE, page_offset)) {
 				ret = -EIO;
@@ -2917,15 +2941,13 @@ static int f2fs_read_data_large_folio(struct inode *inode,
 		}
 
 		/* We must increment read_pages_pending before possible BIOs submitting
-		 * to prevent from premature folio_end_read() call on folio
+		 * to prevent from premature folio_end_read() call on folio.
 		 */
-		if (folio_test_large(folio)) {
-			ffs = f2fs_ffs_find_or_alloc(folio);
+		if (folio_test_large(folio) && !whole_folio_in_bio) {
+			f2fs_ffs_find_or_alloc(folio);
 
 			/* set the bitmap to wait */
-			spin_lock_irq(&ffs->state_lock);
-			ffs->read_pages_pending++;
-			spin_unlock_irq(&ffs->state_lock);
+			f2fs_update_read_folio_pending(folio, len_blks);
 		}
 
 		/*
@@ -2949,17 +2971,20 @@ static int f2fs_read_data_large_folio(struct inode *inode,
 		 * If the page is under writeback, we need to wait for
 		 * its completion to see the correct decrypted data.
 		 */
-		f2fs_wait_on_block_writeback(inode, block_nr);
+		for (i = 0; i < len_blks; i++)
+			f2fs_wait_on_block_writeback(inode, block_nr + i);
 
-		if (!bio_add_folio(bio, folio, F2FS_BLKSIZE(F2FS_I_SB(inode)),
+		if (!bio_add_folio(bio, folio,
+				len_blks * F2FS_BLKSIZE(F2FS_I_SB(inode)),
 				offset << PAGE_SHIFT))
 			goto submit_and_realloc;
 
 		folio_in_bio = true;
-		inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA);
+		for (i = 0; i < len_blks; i++)
+			inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA);
 		f2fs_update_iostat(F2FS_I_SB(inode), NULL, FS_DATA_READ_IO,
-				F2FS_BLKSIZE(F2FS_I_SB(inode)));
-		last_block_in_bio = block_nr;
+				len_blks * F2FS_BLKSIZE(F2FS_I_SB(inode)));
+		last_block_in_bio = block_nr + len_blks - 1;
 	}
 	trace_f2fs_read_folio(folio, DATA);
 err_out:
-- 
2.43.0

[PATCH v2 09/14] f2fs: support partial uptodate large folio read

[Nanzhe Zhao]

Buffered write can have write bytes smaller than folio
size for cases when folio minimum order is not zero.
This can left partially uptodate folio in page cache.
So we skip uptodate subpage read in read_data_large_folio.
Also mark hole subpage uptodate in uptodate bitmap.

Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
 fs/f2fs/data.c | 71 +++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 70 insertions(+), 1 deletion(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 09ad5cf0d9aa..d9e3a5c370d7 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -163,6 +163,7 @@ static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
 		struct folio *folio = fi.folio;
 		unsigned int nr_pages = fi.length >> PAGE_SHIFT;
 		bool finished = true;
+		bool uptodate = bio->bi_status == BLK_STS_OK;
 
 		if (!folio_test_large(folio) &&
 		    f2fs_is_compressed_page(folio)) {
@@ -178,6 +179,9 @@ static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
 				(struct f2fs_folio_state *)folio->private;
 
 			spin_lock_irqsave(&ffs->state_lock, flags);
+			if (bio->bi_status == BLK_STS_OK)
+				uptodate = __ffs_mark_subrange_uptodate(folio, ffs,
+						fi.offset, fi.length);
 			ffs->read_pages_pending -= nr_pages;
 			finished = !ffs->read_pages_pending;
 			spin_unlock_irqrestore(&ffs->state_lock, flags);
@@ -194,7 +198,8 @@ static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
 			bio->bi_status = BLK_STS_IOERR;
 
 		if (finished)
-			folio_end_read(folio, bio->bi_status == BLK_STS_OK);
+			folio_end_read(folio,
+				bio->bi_status == BLK_STS_OK && uptodate);
 	}
 
 	if (ctx)
@@ -2835,6 +2840,56 @@ static bool find_next_valid_block(const struct folio *folio,
 	return false;
 }
 
+static unsigned int ffs_next_uptodate_subpage(struct f2fs_folio_state *ffs,
+			unsigned int start, unsigned int end)
+{
+	return find_next_bit(ffs->state, end + 1, start);
+}
+
+static unsigned int ffs_next_nonuptodate_subpage(struct f2fs_folio_state *ffs,
+			unsigned int start, unsigned int end)
+{
+	return find_next_zero_bit(ffs->state, end + 1, start);
+}
+
+static void f2fs_skip_fully_uptodate_front(struct folio *folio,
+			pgoff_t *index, pgoff_t *offset, unsigned int *nrpages,
+			unsigned int *max_nr_pages)
+{
+	struct f2fs_folio_state *ffs;
+	unsigned int next, skipped;
+
+	if (!f2fs_folio_has_ffs(folio) || !*nrpages)
+		return;
+
+	ffs = folio->private;
+	next = ffs_next_nonuptodate_subpage(ffs, *offset,
+					    *offset + *nrpages - 1);
+	skipped = next - *offset;
+	if (!skipped)
+		return;
+
+	*index += skipped;
+	*offset += skipped;
+	*nrpages -= skipped;
+	*max_nr_pages -= skipped;
+}
+
+static void f2fs_truncate_read_extent(struct folio *folio, pgoff_t offset,
+				     unsigned int *len_blks)
+{
+	struct f2fs_folio_state *ffs;
+	unsigned int next, end;
+
+	if (!f2fs_folio_has_ffs(folio) || *len_blks <= 1)
+		return;
+
+	ffs = folio->private;
+	end = offset + *len_blks - 1;
+	next = ffs_next_uptodate_subpage(ffs, offset + 1, end);
+	if (next <= end)
+		*len_blks = next - offset;
+}
 static int f2fs_read_data_large_folio(struct inode *inode,
 		struct fsverity_info *vi,
 		struct readahead_control *rac, struct folio *folio)
@@ -2846,6 +2901,7 @@ static int f2fs_read_data_large_folio(struct inode *inode,
 	unsigned max_nr_pages = rac ? readahead_count(rac) :
 				folio_nr_pages(folio);
 	unsigned int nrpages, len_blks;
+	struct f2fs_folio_state *ffs;
 	int ret = 0;
 	bool folio_in_bio = false;
 
@@ -2879,6 +2935,11 @@ static int f2fs_read_data_large_folio(struct inode *inode,
 
 		len_blks = 1;
 
+		f2fs_skip_fully_uptodate_front(folio, &index, &offset,
+					       &nrpages, &max_nr_pages);
+		if (!nrpages)
+			break;
+
 		/*
 		 * Map blocks using the previous result first.
 		 */
@@ -2911,6 +2972,7 @@ static int f2fs_read_data_large_folio(struct inode *inode,
 			len_blks = min_t(unsigned int, nrpages, max_nr_pages);
 			len_blks = min_t(unsigned int, len_blks,
 					(unsigned int)(map.m_lblk + map.m_len - index));
+			f2fs_truncate_read_extent(folio, offset, &len_blks);
 
 			for (i = 0; i < len_blks; i++) {
 				if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode),
@@ -2937,6 +2999,13 @@ static int f2fs_read_data_large_folio(struct inode *inode,
 				ret = -EIO;
 				goto err_out;
 			}
+			if (folio_test_large(folio)) {
+				ffs = f2fs_ffs_find_or_alloc(folio);
+				spin_lock_irq(&ffs->state_lock);
+				__ffs_mark_subrange_uptodate(folio, ffs,
+						page_offset, PAGE_SIZE);
+				spin_unlock_irq(&ffs->state_lock);
+			}
 			continue;
 		}
 
-- 
2.43.0

[PATCH v2 10/14] f2fs: handle partial truncate of large folio dirty subpages

[Nanzhe Zhao]

A large folio can be partial truncated and stays in folio mapping, we
need to clear the subrange dirty bits and uptodate bits that the partial
truncate covers. If this partial truncate happens to clear the last
subrange dirty bits, then cancel the whole folio dirty state.

Also add a guard in f2fs_write_single_data_folio() so a large folio
subpage whose disk block was already truncated (NULL_ADDR) is skipped

Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
 fs/f2fs/data.c | 66 +++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 65 insertions(+), 1 deletion(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index d9e3a5c370d7..bf9b9c9b722f 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -2679,6 +2679,34 @@ static void f2fs_ffs_mark_subrange_uptodate(struct folio *folio, size_t offset,
 		folio_mark_uptodate(folio);
 }
 
+static void ffs_clear_subrange_uptodate(struct folio *folio,
+					size_t offset, size_t len)
+{
+	struct f2fs_folio_state *ffs;
+	unsigned int nr_subpages, start, end;
+	unsigned long flags;
+
+	f2fs_bug_on(F2FS_F_SB(folio), offset + len > folio_size(folio));
+
+	if (!f2fs_folio_has_ffs(folio)) {
+		if (folio_test_uptodate(folio))
+			folio_clear_uptodate(folio);
+		return;
+	}
+
+	ffs = (struct f2fs_folio_state *)folio->private;
+	nr_subpages = folio_nr_pages(folio);
+	start = offset >> PAGE_SHIFT;
+	end = (offset + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	end = min(end, nr_subpages);
+
+	spin_lock_irqsave(&ffs->state_lock, flags);
+	bitmap_clear(ffs->state, start, end - start);
+	spin_unlock_irqrestore(&ffs->state_lock, flags);
+	if (folio_test_uptodate(folio))
+		folio_clear_uptodate(folio);
+}
+
 bool f2fs_ffs_test_blk_dirty(const struct folio *folio, pgoff_t index)
 {
 	struct f2fs_folio_state *ffs;
@@ -3545,6 +3573,14 @@ static int f2fs_write_single_data_folio(struct folio *folio, int *submitted,
 
 		fio.old_blkaddr = dn.data_blkaddr;
 
+		/* This page is already truncated */
+		if (fio.old_blkaddr == NULL_ADDR) {
+			ffs_clear_subrange_uptodate(folio,
+					i << PAGE_SHIFT, PAGE_SIZE);
+			folio_clear_f2fs_gcing(folio);
+			goto block_done;
+		}
+
 got_it:
 		if (__is_valid_data_blkaddr(fio.old_blkaddr) &&
 		    !f2fs_is_valid_blkaddr(sbi, fio.old_blkaddr,
@@ -4987,8 +5023,36 @@ void f2fs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 
 	if (inode->i_ino >= F2FS_ROOT_INO(sbi) &&
-				(offset || length != folio_size(folio)))
+				(offset || length != folio_size(folio))) {
+		size_t clear_start = round_up(offset, PAGE_SIZE);
+		size_t clear_end = round_down(offset + length, PAGE_SIZE);
+		size_t clear_length;
+		bool dirty;
+
+		/*
+		 * If the truncated range falls within a single subpage, no
+		 * subpage state needs to be cleared.
+		 */
+		if (clear_start >= clear_end || !f2fs_folio_has_ffs(folio))
+			return;
+
+		clear_length = clear_end - clear_start;
+		dirty = f2fs_ffs_clear_subrange_dirty_and_test(folio,
+						clear_start, clear_length);
+		ffs_clear_subrange_uptodate(folio, clear_start, clear_length);
+
+		/*
+		 * If the truncated subrange happens to clear the remaining
+		 * dirty bitmap of the whole folio, cancel the folio-level
+		 * dirty state.
+		 */
+		if (!dirty && folio_test_dirty(folio)) {
+			inode_dec_dirty_pages(inode);
+			f2fs_remove_dirty_inode(inode);
+			folio_cancel_dirty(folio);
+		}
 		return;
+	}
 
 	if (folio_test_dirty(folio)) {
 		if (inode->i_ino == F2FS_META_INO(sbi)) {
-- 
2.43.0

[PATCH v2 11/14] f2fs: fix zeroing paths for large folios

[Nanzhe Zhao]

Several f2fs zeroing paths still use PAGE_SIZE based offsets after
a file mapping can contain large folios.  This is fine for order-0
folios, but it zeros the wrong range once the target block is not at
offset 0 in a large folio.

Use offset_in_folio() to translate the file block index to the folio
offset before zeroing data in truncate_partial_data_page(), fill_zero(),
and f2fs_get_new_data_folio().

Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
 fs/f2fs/data.c | 16 ++++++++++++----
 fs/f2fs/f2fs.h |  1 +
 fs/f2fs/file.c | 21 ++++++++++++++++-----
 3 files changed, 29 insertions(+), 9 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index bf9b9c9b722f..295424f2ade5 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1549,6 +1549,12 @@ struct folio *f2fs_get_new_data_folio(struct inode *inode,
 		return ERR_PTR(-ENOMEM);
 	}
 
+	if (folio_test_large(folio) && !f2fs_ffs_find_or_alloc(folio)) {
+		f2fs_folio_put(folio, true);
+		f2fs_folio_put(ifolio, true);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	set_new_dnode(&dn, inode, ifolio, NULL, 0);
 	err = f2fs_reserve_block(&dn, index);
 	if (err) {
@@ -1562,9 +1568,11 @@ struct folio *f2fs_get_new_data_folio(struct inode *inode,
 		goto got_it;
 
 	if (dn.data_blkaddr == NEW_ADDR) {
-		folio_zero_segment(folio, 0, folio_size(folio));
-		if (!folio_test_uptodate(folio))
-			folio_mark_uptodate(folio);
+		size_t off = offset_in_folio(folio,
+					(loff_t)index << PAGE_SHIFT);
+
+		folio_zero_segment(folio, off, off + PAGE_SIZE);
+		f2fs_ffs_mark_subrange_uptodate(folio, off, PAGE_SIZE);
 	} else {
 		f2fs_folio_put(folio, true);
 
@@ -2656,7 +2664,7 @@ static bool __ffs_mark_subrange_uptodate(struct folio *folio,
 	return bitmap_full(ffs->state, nr_subpages);
 }
 
-static void f2fs_ffs_mark_subrange_uptodate(struct folio *folio, size_t offset,
+void f2fs_ffs_mark_subrange_uptodate(struct folio *folio, size_t offset,
 				       size_t len)
 {
 	struct f2fs_folio_state *ffs;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 6be08e45341c..d99a812810d3 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -4381,6 +4381,7 @@ struct folio *f2fs_get_lock_data_folio(struct inode *inode, pgoff_t index,
 			bool for_write);
 struct folio *f2fs_get_new_data_folio(struct inode *inode,
 			struct folio *ifolio, pgoff_t index, bool new_i_size);
+void f2fs_ffs_mark_subrange_uptodate(struct folio *folio, size_t offset, size_t len);
 int f2fs_do_write_data_page(struct f2fs_io_info *fio);
 int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int flag);
 int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 738a751c3903..54aa045b549e 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -825,12 +825,13 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 static int truncate_partial_data_page(struct inode *inode, u64 from,
 								bool cache_only)
 {
-	loff_t offset = from & (PAGE_SIZE - 1);
 	pgoff_t index = from >> PAGE_SHIFT;
 	struct address_space *mapping = inode->i_mapping;
 	struct folio *folio;
+	size_t folio_off;
+	size_t blk_end;
 
-	if (!offset && !cache_only)
+	if (!(from & (PAGE_SIZE - 1)) && !cache_only)
 		return 0;
 
 	if (cache_only) {
@@ -848,12 +849,18 @@ static int truncate_partial_data_page(struct inode *inode, u64 from,
 		return PTR_ERR(folio) == -ENOENT ? 0 : PTR_ERR(folio);
 truncate_out:
 	f2fs_folio_wait_writeback(folio, DATA, true, true);
-	folio_zero_segment(folio, offset, folio_size(folio));
+	folio_off = offset_in_folio(folio, from);
+	blk_end = min_t(size_t, round_up(folio_off, PAGE_SIZE),
+					folio_size(folio));
+	folio_zero_segment(folio, folio_off, blk_end);
 
 	/* An encrypted inode should have a key and truncate the last page. */
 	f2fs_bug_on(F2FS_I_SB(inode), cache_only && IS_ENCRYPTED(inode));
-	if (!cache_only)
+	if (!cache_only) {
+		f2fs_ffs_mark_subrange_dirty(folio, folio_off,
+				blk_end - folio_off);
 		folio_mark_dirty(folio);
+	}
 	f2fs_folio_put(folio, true);
 	return 0;
 }
@@ -1321,6 +1328,7 @@ static int fill_zero(struct inode *inode, pgoff_t index,
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct folio *folio;
 	struct f2fs_lock_context lc;
+	size_t folio_off;
 
 	if (!len)
 		return 0;
@@ -1335,7 +1343,10 @@ static int fill_zero(struct inode *inode, pgoff_t index,
 		return PTR_ERR(folio);
 
 	f2fs_folio_wait_writeback(folio, DATA, true, true);
-	folio_zero_range(folio, start, len);
+	folio_off = offset_in_folio(folio,
+				   (loff_t)index << PAGE_SHIFT) + start;
+	folio_zero_range(folio, folio_off, len);
+	f2fs_ffs_mark_subrange_dirty(folio, folio_off, len);
 	folio_mark_dirty(folio);
 	f2fs_folio_put(folio, true);
 	return 0;
-- 
2.43.0

[PATCH v2 12/14] f2fs: handle block cloning within the same large folio

[Nanzhe Zhao]

With large folios, the source and destination block in __clone_blkaddrs()
can belong to the same folio during same-inode operations such as
collapse range and insert range.

In that case, locking the source folio and then looking up the
destination folio can try to lock the same folio again.  It also copies
from and to offset 0, which is only correct for order-0 folios.

Detect the same-inode, same-folio case before looking up the destination
folio.  Then in this case,we reserve the destination block explicitly.

Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
 fs/f2fs/file.c | 61 +++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 53 insertions(+), 8 deletions(-)

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 54aa045b549e..a36d243ca305 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -1586,25 +1586,70 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
 			f2fs_put_dnode(&dn);
 		} else {
 			struct folio *fsrc, *fdst;
+			size_t src_off, dst_off;
+			bool same_folio;
 
 			fsrc = f2fs_get_lock_data_folio(src_inode,
 							src + i, true);
 			if (IS_ERR(fsrc))
 				return PTR_ERR(fsrc);
-			fdst = f2fs_get_new_data_folio(dst_inode, NULL, dst + i,
-								true);
-			if (IS_ERR(fdst)) {
-				f2fs_folio_put(fsrc, true);
-				return PTR_ERR(fdst);
+
+			src_off = offset_in_folio(fsrc,
+						(loff_t)(src + i) << PAGE_SHIFT);
+
+			/*
+			 * For same-inode operations (collapse/insert), src and
+			 * dst may fall within the same large folio. Detect this
+			 * to avoid self-deadlock on folio lock.
+			 */
+			same_folio = src_inode == dst_inode &&
+				     folio_contains(fsrc, dst + i);
+			if (same_folio) {
+				struct dnode_of_data dn;
+
+				/* Reserve block for dst before copying */
+				set_new_dnode(&dn, dst_inode, NULL, NULL, 0);
+				ret = f2fs_reserve_block(&dn, dst + i);
+				if (ret) {
+					f2fs_folio_put(fsrc, true);
+					return ret;
+				}
+				fdst = fsrc;
+			} else {
+				fdst = f2fs_get_new_data_folio(dst_inode, NULL,
+							      dst + i, true);
+				if (IS_ERR(fdst)) {
+					f2fs_folio_put(fsrc, true);
+					return PTR_ERR(fdst);
+				}
 			}
 
+			dst_off = offset_in_folio(fdst,
+					(loff_t)(dst + i) << PAGE_SHIFT);
 			f2fs_folio_wait_writeback(fdst, DATA, true, true);
-
-			memcpy_folio(fdst, 0, fsrc, 0, PAGE_SIZE);
+			memcpy_folio(fdst, dst_off, fsrc, src_off,
+				    PAGE_SIZE);
+			if (folio_test_large(fdst)) {
+				if (!f2fs_ffs_find_or_alloc(fdst)) {
+					f2fs_folio_put(fdst, true);
+					if (!same_folio)
+						f2fs_folio_put(fsrc, true);
+					return -ENOMEM;
+				}
+				f2fs_ffs_mark_subrange_uptodate(fdst,
+							dst_off, PAGE_SIZE);
+				f2fs_ffs_mark_subrange_dirty(fdst, dst_off,
+							    PAGE_SIZE);
+			}
 			folio_mark_dirty(fdst);
+			if (same_folio && i_size_read(dst_inode) <
+			    ((loff_t)(dst + i + 1) << PAGE_SHIFT))
+				f2fs_i_size_write(dst_inode,
+					((loff_t)(dst + i + 1) << PAGE_SHIFT));
 			folio_set_f2fs_gcing(fdst);
 			f2fs_folio_put(fdst, true);
-			f2fs_folio_put(fsrc, true);
+			if (!same_folio)
+				f2fs_folio_put(fsrc, true);
 
 			ret = f2fs_truncate_hole(src_inode,
 						src + i, src + i + 1);
-- 
2.43.0

[PATCH v2 13/14] f2fs: allow large folio support to writeable files

[Nanzhe Zhao]

Now we make all write path support large folios,
so we open permission to let writeable file set
large folio mapping.

Keep fs-layer encrypted files excluded unless inline encryption is
enabled, since f2fs_encrypt_one_page() still encrypts one PAGE_SIZE
page and cannot handle large folios.

Inline files are allowed as well; their index #0 folio stays order-0
(see the large folio write path), so the existing inline read/convert
paths are not affected and large folios are used from the second folio
on.

Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
 fs/f2fs/data.c   |  2 +-
 fs/f2fs/f2fs.h   | 17 +++++++++++++++++
 fs/f2fs/file.c   | 16 ----------------
 fs/f2fs/inline.c |  6 ++++++
 fs/f2fs/inode.c  |  4 +---
 fs/f2fs/namei.c  |  1 +
 6 files changed, 26 insertions(+), 20 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 295424f2ade5..c9dba8d0ad3d 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -2941,7 +2941,7 @@ static int f2fs_read_data_large_folio(struct inode *inode,
 	int ret = 0;
 	bool folio_in_bio = false;
 
-	if (!IS_IMMUTABLE(inode) || f2fs_compressed_file(inode)) {
+	if (f2fs_compressed_file(inode)) {
 		if (folio)
 			folio_unlock(folio);
 		return -EOPNOTSUPP;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index d99a812810d3..d608376b1456 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -5251,6 +5251,23 @@ static inline bool f2fs_quota_file(struct f2fs_sb_info *sbi, nid_t ino)
 	return false;
 }
 
+static inline void f2fs_mapping_set_large_folio(struct inode *inode)
+{
+	if (!S_ISREG(inode->i_mode) ||
+	    f2fs_compressed_file(inode) ||
+	    f2fs_quota_file(F2FS_I_SB(inode), inode->i_ino))
+		return;
+
+	/*
+	 * Keep the folio order range at 0 as a transitional step; large
+	 * folios will be enabled once the whole write path is audited.
+	 */
+	if (IS_IMMUTABLE(inode))
+		mapping_set_folio_min_order(inode->i_mapping, 0);
+	else
+		mapping_set_folio_order_range(inode->i_mapping, 0, 0);
+}
+
 static inline bool f2fs_block_unit_discard(struct f2fs_sb_info *sbi)
 {
 	return F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_BLOCK;
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index a36d243ca305..db71cadefabd 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -162,17 +162,6 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 	int err = 0;
 	vm_fault_t ret;
 
-	/*
-	 * We only support large folio on the read case.
-	 * Don't make any dirty pages.
-	 */
-	if (unlikely(IS_IMMUTABLE(inode)) ||
-	    mapping_large_folio_support(inode->i_mapping)) {
-		f2fs_err(sbi, "Not expected: immutable: %d large_folio: %d",
-				IS_IMMUTABLE(inode),
-				mapping_large_folio_support(inode->i_mapping));
-		return VM_FAULT_SIGBUS;
-	}
 
 	if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) {
 		err = -EIO;
@@ -712,9 +701,6 @@ static int f2fs_file_open(struct inode *inode, struct file *filp)
 	if (!f2fs_is_compress_backend_ready(inode))
 		return -EOPNOTSUPP;
 
-	if (mapping_large_folio_support(inode->i_mapping) &&
-	    filp->f_mode & FMODE_WRITE)
-		return -EOPNOTSUPP;
 
 	err = fsverity_file_open(inode, filp);
 	if (err)
@@ -1186,8 +1172,6 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		return -EPERM;
 
 	if ((attr->ia_valid & ATTR_SIZE)) {
-		if (mapping_large_folio_support(inode->i_mapping))
-			return -EOPNOTSUPP;
 		if (IS_DEVICE_ALIASING(inode))
 			return -EPERM;
 		if (!f2fs_is_compress_backend_ready(inode))
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 8db083b545bc..51cc2e6c0284 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -238,6 +238,12 @@ int f2fs_convert_inline_inode(struct inode *inode)
 	if (IS_ERR(folio))
 		return PTR_ERR(folio);
 
+	/*
+	 * Inline data is only supported in an order-0 index #0 folio; the
+	 * inline write and mmap fault paths never request a larger order.
+	 */
+	f2fs_bug_on(sbi, folio_test_large(folio));
+
 	f2fs_lock_op(sbi, &lc);
 
 	ifolio = f2fs_get_inode_folio(sbi, inode->i_ino);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 24205a35be04..c8a4c62c9927 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -643,9 +643,7 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
 		inode->i_op = &f2fs_file_inode_operations;
 		inode->i_fop = &f2fs_file_operations;
 		inode->i_mapping->a_ops = &f2fs_dblock_aops;
-		if (IS_IMMUTABLE(inode) && !f2fs_compressed_file(inode) &&
-		    !f2fs_quota_file(sbi, inode->i_ino))
-			mapping_set_folio_min_order(inode->i_mapping, 0);
+		f2fs_mapping_set_large_folio(inode);
 	} else if (S_ISDIR(inode->i_mode)) {
 		inode->i_op = &f2fs_dir_inode_operations;
 		inode->i_fop = &f2fs_dir_operations;
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index ff86ee07290d..9d0cec72aacc 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -341,6 +341,7 @@ static struct inode *f2fs_new_inode(struct mnt_idmap *idmap,
 	f2fs_set_inode_flags(inode);
 
 	f2fs_init_extent_tree(inode);
+	f2fs_mapping_set_large_folio(inode);
 
 	trace_f2fs_new_inode(inode, 0);
 	return inode;
-- 
2.43.0

[PATCH v2 14/14] f2fs: make compressed files compatible with large folio

[Nanzhe Zhao]

The compression flag is the hint indicates that the inode can be
compressed, when the inode is using large folio, we expected it keeps
using the large folio read/write paths and its data stays uncompressed
on disk until the inode is evicted and re-read

Let f2fs_write_begin() skip the compression overwrite preparation for
such inodes and remove the compressed-file gate in
f2fs_read_data_large_folio() so the data is simply read/written as
regular blocks.

For the same reason, reject F2FS_IOC_COMPRESS_FILE with -EOPNOTSUPP
once the inode mapping is switched to large folios.

Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
 Documentation/filesystems/f2fs.rst | 10 ++++++++++
 fs/f2fs/compress.c                 |  2 ++
 fs/f2fs/data.c                     |  9 ++-------
 fs/f2fs/file.c                     |  7 +++++++
 4 files changed, 21 insertions(+), 7 deletions(-)

diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst
index 771216f45207..b4f436ffd9ac 100644
--- a/Documentation/filesystems/f2fs.rst
+++ b/Documentation/filesystems/f2fs.rst
@@ -941,6 +941,16 @@ Compression implementation
   reserved via ioctl(F2FS_IOC_RESERVE_COMPRESS_BLOCKS) or the file size is
   truncated to zero.
 
+- Compression and large folios are not effective at the same time on a file:
+  a compressed inode does not use large folios, while an inode which is
+  using large folios keeps its data uncompressed on disk.  If the compression
+  flag is set on an inode that is already using large folios, the flag works
+  as a hint until the inode is evicted: the inode keeps using the large folio
+  read/write paths, f2fs_write_begin() skips the compression overwrite
+  preparation, and ioctl(F2FS_IOC_COMPRESS_FILE) fails with -EOPNOTSUPP.
+  Once the inode is evicted and read back, it uses order-0 folios again and
+  compression is applied as usual.
+
 Compress metadata layout::
 
 				[Dnode Structure]
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index b130e43b4566..fa0f8449a12c 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -78,6 +78,8 @@ bool f2fs_is_compressed_page(struct folio *folio)
 		return false;
 	if (folio_test_f2fs_nonpointer(folio))
 		return false;
+	if (f2fs_folio_has_ffs(folio))
+		return false;
 
 	f2fs_bug_on(F2FS_F_SB(folio),
 		*((u32 *)folio->private) != F2FS_COMPRESSED_PAGE_MAGIC);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index c9dba8d0ad3d..f5421334ecf3 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -2941,12 +2941,6 @@ static int f2fs_read_data_large_folio(struct inode *inode,
 	int ret = 0;
 	bool folio_in_bio = false;
 
-	if (f2fs_compressed_file(inode)) {
-		if (folio)
-			folio_unlock(folio);
-		return -EOPNOTSUPP;
-	}
-
 	map.m_seg_type = NO_CHECK_TYPE;
 
 	if (rac)
@@ -4828,7 +4822,8 @@ static int f2fs_write_begin(const struct kiocb *iocb,
 	}
 
 #ifdef CONFIG_F2FS_FS_COMPRESSION
-	if (f2fs_compressed_file(inode)) {
+	if (f2fs_compressed_file(inode) &&
+	    !mapping_large_folio_support(inode->i_mapping)) {
 		int ret;
 		struct page *page;
 
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index db71cadefabd..c5cb0b0384b6 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -5002,6 +5002,13 @@ static int f2fs_ioc_compress_file(struct file *filp)
 	if (!(filp->f_mode & FMODE_WRITE))
 		return -EBADF;
 
+	/*
+	 * The mapping is already using large folios, where the data is kept
+	 * uncompressed, so refuse to start compressing the file.
+	 */
+	if (mapping_large_folio_support(inode->i_mapping))
+		return -EOPNOTSUPP;
+
 	f2fs_balance_fs(sbi, true);
 
 	ret = mnt_want_write_file(filp);
-- 
2.43.0

Re: [f2fs-dev] [PATCH v2 08/14] f2fs: optimize small block size large folio read

[Daeho Jeong]

On Mon, Sep 14, 2026 at 9:21 PM Nanzhe Zhao via Linux-f2fs-devel
<linux-f2fs-devel@lists.sourceforge.net> wrote:
>
> The original f2fs_read_data_large_folio() implementation has limited
> benefit with a 4KB block size, mainly because updating
> read_pages_pending greatly increases the number of spinlock
> operations.
>
> Use len_blks to batch read_pages_pending and iostat updates for
> contiguous mapped blocks. If the contiguous mapping covers the whole
> folio, skip f2fs_folio_state allocation for that folio.
>
> Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
> ---
>  fs/f2fs/data.c | 65 ++++++++++++++++++++++++++++++++++----------------
>  1 file changed, 45 insertions(+), 20 deletions(-)
>
> diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
> index 287d83debf95..09ad5cf0d9aa 100644
> --- a/fs/f2fs/data.c
> +++ b/fs/f2fs/data.c
> @@ -173,8 +173,9 @@ static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
>                         continue;
>                 }
>
> -               if (folio_test_large(folio)) {
> -                       struct f2fs_folio_state *ffs = folio->private;
> +               if (f2fs_folio_has_ffs(folio)) {
> +                       struct f2fs_folio_state *ffs =
> +                               (struct f2fs_folio_state *)folio->private;
>
>                         spin_lock_irqsave(&ffs->state_lock, flags);
>                         ffs->read_pages_pending -= nr_pages;
> @@ -2844,8 +2845,7 @@ static int f2fs_read_data_large_folio(struct inode *inode,
>         pgoff_t index, offset, next_pgofs = 0;
>         unsigned max_nr_pages = rac ? readahead_count(rac) :
>                                 folio_nr_pages(folio);
> -       unsigned int nrpages;
> -       struct f2fs_folio_state *ffs;
> +       unsigned int nrpages, len_blks;
>         int ret = 0;
>         bool folio_in_bio = false;
>
> @@ -2868,11 +2868,17 @@ static int f2fs_read_data_large_folio(struct inode *inode,
>         folio_in_bio = false;
>         index = folio->index;
>         offset = 0;
> -       ffs = NULL;
>         nrpages = folio_nr_pages(folio);
>
> -       for (; nrpages; nrpages--, max_nr_pages--, index++, offset++) {
> +       for (; nrpages;
> +            nrpages -= len_blks, max_nr_pages -= len_blks,
> +            index += len_blks, offset += len_blks) {
>                 sector_t block_nr;
> +               bool whole_folio_in_bio;
> +               unsigned int i;
> +
> +               len_blks = 1;
> +
>                 /*
>                  * Map blocks using the previous result first.
>                  */
> @@ -2901,13 +2907,31 @@ static int f2fs_read_data_large_folio(struct inode *inode,
>  got_it:
>                 if ((map.m_flags & F2FS_MAP_MAPPED)) {
>                         block_nr = map.m_pblk + index - map.m_lblk;
> -                       if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr,
> +
> +                       len_blks = min_t(unsigned int, nrpages, max_nr_pages);
> +                       len_blks = min_t(unsigned int, len_blks,
> +                                       (unsigned int)(map.m_lblk + map.m_len - index));
> +
> +                       for (i = 0; i < len_blks; i++) {
> +                               if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode),
> +                                               block_nr + i,
>                                                 DATA_GENERIC_ENHANCE_READ)) {
> -                               ret = -EFSCORRUPTED;
> -                               goto err_out;
> +                                       ret = -EFSCORRUPTED;
> +                                       goto err_out;
> +                               }
>                         }
> +
> +                       /*
> +                        * If an entire folio is added to one bio,
> +                        * folio_end_read() can complete the folio read status
> +                        * without relying on f2fs_folio_state.
> +                        */
> +                       whole_folio_in_bio = offset == 0 &&
> +                                       len_blks == folio_nr_pages(folio);
> +
>                 } else {
>                         size_t page_offset = offset << PAGE_SHIFT;
> +
>                         folio_zero_range(folio, page_offset, PAGE_SIZE);
>                         if (vi && !fsverity_verify_blocks(vi, folio, PAGE_SIZE, page_offset)) {
>                                 ret = -EIO;
> @@ -2917,15 +2941,13 @@ static int f2fs_read_data_large_folio(struct inode *inode,
>                 }
>
>                 /* We must increment read_pages_pending before possible BIOs submitting
> -                * to prevent from premature folio_end_read() call on folio
> +                * to prevent from premature folio_end_read() call on folio.
>                  */
> -               if (folio_test_large(folio)) {
> -                       ffs = f2fs_ffs_find_or_alloc(folio);
> +               if (folio_test_large(folio) && !whole_folio_in_bio) {

Hi Nanzhe,

I found a hang issue caused by the whole_folio_in_bio optimization
during my local 16KB page-4KB block testing:

Plz, check the whole_folio_in_bio optimization is safe for the below conditions.
1. read_blocks_pending underflow: If a folio already has ffs attached
(from previous writes/holes/reads), whole_folio_in_bio skips
incrementing read_blocks_pending.
When the BIO completes, f2fs_finish_read_bio() still decrements it,
underflowing the counter.
2. BIO split risk: If a large folio BIO gets split by the block/crypto
layer, f2fs_finish_read_bio() would call folio_end_read() prematurely
on the first completing piece.

Thanks,

> +                       f2fs_ffs_find_or_alloc(folio);
>
>                         /* set the bitmap to wait */
> -                       spin_lock_irq(&ffs->state_lock);
> -                       ffs->read_pages_pending++;
> -                       spin_unlock_irq(&ffs->state_lock);
> +                       f2fs_update_read_folio_pending(folio, len_blks);
>                 }
>
>                 /*
> @@ -2949,17 +2971,20 @@ static int f2fs_read_data_large_folio(struct inode *inode,
>                  * If the page is under writeback, we need to wait for
>                  * its completion to see the correct decrypted data.
>                  */
> -               f2fs_wait_on_block_writeback(inode, block_nr);
> +               for (i = 0; i < len_blks; i++)
> +                       f2fs_wait_on_block_writeback(inode, block_nr + i);
>
> -               if (!bio_add_folio(bio, folio, F2FS_BLKSIZE(F2FS_I_SB(inode)),
> +               if (!bio_add_folio(bio, folio,
> +                               len_blks * F2FS_BLKSIZE(F2FS_I_SB(inode)),
>                                 offset << PAGE_SHIFT))
>                         goto submit_and_realloc;
>
>                 folio_in_bio = true;
> -               inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA);
> +               for (i = 0; i < len_blks; i++)
> +                       inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA);
>                 f2fs_update_iostat(F2FS_I_SB(inode), NULL, FS_DATA_READ_IO,
> -                               F2FS_BLKSIZE(F2FS_I_SB(inode)));
> -               last_block_in_bio = block_nr;
> +                               len_blks * F2FS_BLKSIZE(F2FS_I_SB(inode)));
> +               last_block_in_bio = block_nr + len_blks - 1;
>         }
>         trace_f2fs_read_folio(folio, DATA);
>  err_out:
> --
> 2.43.0
>
>
>
> _______________________________________________
> Linux-f2fs-devel mailing list
> Linux-f2fs-devel@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

Re: [PATCH v2 01/14] f2fs: extend folio state for large folio write path

[Chao Yu]

On 9/15/26 12:18, Nanzhe Zhao wrote:
> Large folio write path needs a subpage status bitmap and write
> pages pending counter, while keeping compatible with f2fs private
> flags.
> 
> Move struct f2fs_folio_state to f2fs.h, add private_flags and
> subpage state bitmap, and change PAGE_PRIVATE functions to be
> compatible with f2fs_folio_state. Allocate f2fs_folio_state via kzalloc
> instead of kmem_cache, since the state size depends on the folio order.
> 
> Note: Now if a path wants to use f2fs_folio_state, it must call
> `folio_has_ffs` instead of `folio_test_large`` to make check.
> 
> Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
> ---
>  fs/f2fs/data.c | 72 ++++++++++++++++++++++++++++++++------------------
>  fs/f2fs/f2fs.h | 70 +++++++++++++++++++++++++++++++++++-------------
>  2 files changed, 98 insertions(+), 44 deletions(-)
> 
> diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
> index a3b02c067e89..b3303109a696 100644
> --- a/fs/f2fs/data.c
> +++ b/fs/f2fs/data.c
> @@ -32,15 +32,9 @@
>  
>  static struct kmem_cache *bio_post_read_ctx_cache;
>  static struct kmem_cache *bio_entry_slab;
> -static struct kmem_cache *ffs_entry_slab;
>  static mempool_t *bio_post_read_ctx_pool;
>  static struct bio_set f2fs_bioset;
>  
> -struct f2fs_folio_state {
> -	spinlock_t		state_lock;
> -	unsigned int		read_pages_pending;
> -};
> -
>  struct f2fs_bio {
>  	struct work_struct work;
>  	struct bio bio;
> @@ -125,6 +119,9 @@ struct bio_post_read_ctx {
>  	block_t fs_blkaddr;
>  };
>  
> +static bool __ffs_mark_subrange_uptodate(struct folio *folio,
> +		struct f2fs_folio_state *ffs, size_t offset, size_t len);
> +
>  /*
>   * Update and unlock a bio's pages, and free the bio.
>   *
> @@ -139,6 +136,23 @@ struct bio_post_read_ctx {
>   * called (i.e., I/O error or decryption error, but *not* verity error), and
>   * release the bio's reference to the decompress_io_ctx of the page's cluster.
>   */
> +/*
> + * Update read_pages_pending.
> + */
> +static inline void f2fs_update_read_folio_pending(struct folio *folio, int nr)
> +{
> +	struct f2fs_folio_state *ffs;
> +	unsigned long flags;
> +
> +	if (!f2fs_folio_has_ffs(folio))
> +		return;
> +
> +	ffs = (struct f2fs_folio_state *)folio->private;
> +	spin_lock_irqsave(&ffs->state_lock, flags);
> +	ffs->read_pages_pending += nr;
> +	spin_unlock_irqrestore(&ffs->state_lock, flags);
> +}
> +
>  static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
>  {
>  	struct folio_iter fi;
> @@ -147,7 +161,7 @@ static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
>  
>  	bio_for_each_folio_all(fi, bio) {
>  		struct folio *folio = fi.folio;
> -		unsigned nr_pages = fi.length >> PAGE_SHIFT;
> +		unsigned int nr_pages = fi.length >> PAGE_SHIFT;

No needed? it's trivial though.

>  		bool finished = true;
>  
>  		if (!folio_test_large(folio) &&
> @@ -2487,17 +2501,31 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
>  }
>  #endif
>  
> -static struct f2fs_folio_state *ffs_find_or_alloc(struct folio *folio)
> +struct f2fs_folio_state *f2fs_ffs_find_or_alloc(struct folio *folio)
>  {
> -	struct f2fs_folio_state *ffs = folio->private;
> +	struct f2fs_folio_state *ffs;
> +	unsigned int nr_subpages = folio_nr_pages(folio);
> +	unsigned long private = (unsigned long)folio->private;
> +
> +	f2fs_bug_on(F2FS_F_SB(folio), !folio_test_large(folio));
> +	f2fs_bug_on(F2FS_F_SB(folio),
> +		    test_bit(PAGE_PRIVATE_NOT_POINTER, &private));
>  
> -	if (ffs)
> -		return ffs;
> +	if (f2fs_folio_has_ffs(folio))
> +		return (struct f2fs_folio_state *)folio->private;
>  
> -	ffs = f2fs_kmem_cache_alloc(ffs_entry_slab,
> -			GFP_NOIO | __GFP_ZERO, true, NULL);
> +	ffs = f2fs_kmalloc(F2FS_F_SB(folio),
> +			struct_size(ffs, state, BITS_TO_LONGS(2 * nr_subpages)),
> +			GFP_NOFS | __GFP_ZERO);
> +	if (!ffs)
> +		return NULL;
>  
>  	spin_lock_init(&ffs->state_lock);
> +	if (folio_test_uptodate(folio))
> +		bitmap_set(ffs->state, 0, nr_subpages);
> +	if (folio_test_dirty(folio))
> +		bitmap_set(ffs->state, nr_subpages, nr_subpages);
> +
>  	folio_attach_private(folio, ffs);
>  	return ffs;
>  }
> @@ -2506,7 +2534,7 @@ static void ffs_detach_free(struct folio *folio)
>  {
>  	struct f2fs_folio_state *ffs;
>  
> -	if (!folio_test_large(folio)) {
> +	if (!f2fs_folio_has_ffs(folio)) {
>  		folio_detach_private(folio);
>  		return;
>  	}
> @@ -2516,7 +2544,8 @@ static void ffs_detach_free(struct folio *folio)
>  		return;
>  
>  	WARN_ON_ONCE(ffs->read_pages_pending != 0);
> -	kmem_cache_free(ffs_entry_slab, ffs);
> +	WARN_ON_ONCE(atomic_read(&ffs->write_pages_pending));
> +	kfree(ffs);
>  }
>  
>  static int f2fs_read_data_large_folio(struct inode *inode,
> @@ -2529,7 +2558,7 @@ static int f2fs_read_data_large_folio(struct inode *inode,
>  	pgoff_t index, offset, next_pgofs = 0;
>  	unsigned max_nr_pages = rac ? readahead_count(rac) :
>  				folio_nr_pages(folio);
> -	unsigned nrpages;
> +	unsigned int nrpages;

No needed? it's trivial though.

>  	struct f2fs_folio_state *ffs;
>  	int ret = 0;
>  	bool folio_in_bio = false;
> @@ -2605,7 +2634,7 @@ static int f2fs_read_data_large_folio(struct inode *inode,
>  		 * to prevent from premature folio_end_read() call on folio
>  		 */
>  		if (folio_test_large(folio)) {
> -			ffs = ffs_find_or_alloc(folio);
> +			ffs = f2fs_ffs_find_or_alloc(folio);

Do we need to handle no memory case?

Thanks,

>  
>  			/* set the bitmap to wait */
>  			spin_lock_irq(&ffs->state_lock);
> @@ -4522,21 +4551,12 @@ int __init f2fs_init_bio_entry_cache(void)
>  	if (!bio_entry_slab)
>  		return -ENOMEM;
>  
> -	ffs_entry_slab = f2fs_kmem_cache_create("f2fs_ffs_slab",
> -			sizeof(struct f2fs_folio_state));
> -
> -	if (!ffs_entry_slab) {
> -		kmem_cache_destroy(bio_entry_slab);
> -		return -ENOMEM;
> -	}
> -
>  	return 0;
>  }
>  
>  void f2fs_destroy_bio_entry_cache(void)
>  {
>  	kmem_cache_destroy(bio_entry_slab);
> -	kmem_cache_destroy(ffs_entry_slab);
>  }
>  
>  static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
> index ebc621f302e1..9a2366a6c113 100644
> --- a/fs/f2fs/f2fs.h
> +++ b/fs/f2fs/f2fs.h
> @@ -1618,6 +1618,18 @@ static inline void f2fs_clear_bit(unsigned int nr, char *addr);
>   * Layout B: lowest bit should be 0
>   * page.private is a wrapped pointer.
>   */
> +
> +struct f2fs_folio_state {
> +	spinlock_t		state_lock;
> +	unsigned int		read_pages_pending;
> +	atomic_t		write_pages_pending;
> +	unsigned long		private_flags;
> +	/* state[0..nr_subpages - 1] tracks uptodate subpages.
> +	 * state[nr_subpages..2 * nr_subpages - 1] tracks dirty subpages.
> +	 */
> +	unsigned long		state[];
> +};
> +
>  enum {
>  	PAGE_PRIVATE_NOT_POINTER,		/* private contains non-pointer data */
>  	PAGE_PRIVATE_ONGOING_MIGRATION,		/* data page which is on-going migrating */
> @@ -1627,6 +1639,13 @@ enum {
>  	PAGE_PRIVATE_MAX
>  };
>  
> +static inline bool f2fs_folio_has_ffs(const struct folio *folio)
> +{
> +	unsigned long private = (unsigned long)folio->private;
> +
> +	return folio_test_large(folio) && private;
> +}
> +
>  /* For compression */
>  enum compress_algorithm_type {
>  	COMPRESS_LZO,
> @@ -2738,13 +2757,35 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,
>  	return -ENOSPC;
>  }
>  
> +static inline unsigned long f2fs_folio_get_private_flags(const struct folio *folio)
> +{
> +	unsigned long private = (unsigned long)folio->private;
> +
> +	if (f2fs_folio_has_ffs(folio)) {
> +		struct f2fs_folio_state *ffs = (struct f2fs_folio_state *)private;
> +
> +		return READ_ONCE(ffs->private_flags);
> +	}
> +
> +	if (test_bit(PAGE_PRIVATE_NOT_POINTER, &private))
> +		return private;
> +
> +	return 0;
> +}
> +
> +static inline unsigned long *f2fs_folio_flags_addr(struct folio *folio)
> +{
> +	if (f2fs_folio_has_ffs(folio))
> +		return &((struct f2fs_folio_state *)folio->private)->private_flags;
> +
> +	return (unsigned long *)&folio->private;
> +}
> +
>  #define PAGE_PRIVATE_GET_FUNC(name, flagname) \
>  static inline bool folio_test_f2fs_##name(const struct folio *folio)	\
>  {									\
> -	unsigned long priv = (unsigned long)folio->private;		\
> -	unsigned long v = (1UL << PAGE_PRIVATE_NOT_POINTER) |		\
> -			     (1UL << PAGE_PRIVATE_##flagname);		\
> -	return (priv & v) == v;						\
> +	return f2fs_folio_get_private_flags(folio) &			\
> +				(1UL << PAGE_PRIVATE_##flagname);	\
>  }									\
>  static inline bool page_private_##name(struct page *page) \
>  { \
> @@ -2756,14 +2797,10 @@ static inline bool page_private_##name(struct page *page) \
>  #define PAGE_PRIVATE_SET_FUNC(name, flagname) \
>  static inline void folio_set_f2fs_##name(struct folio *folio)		\
>  {									\
> -	unsigned long v = (1UL << PAGE_PRIVATE_NOT_POINTER) |		\
> -			     (1UL << PAGE_PRIVATE_##flagname);		\
>  	if (!folio->private)						\
> -		folio_attach_private(folio, (void *)v);			\
> -	else {								\
> -		v |= (unsigned long)folio->private;			\
> -		folio->private = (void *)v;				\
> -	}								\
> +		folio_attach_private(folio,				\
> +				(void *)BIT(PAGE_PRIVATE_NOT_POINTER));	\
> +	set_bit(PAGE_PRIVATE_##flagname, f2fs_folio_flags_addr(folio));	\
>  }									\
>  static inline void set_page_private_##name(struct page *page) \
>  { \
> @@ -2776,13 +2813,10 @@ static inline void set_page_private_##name(struct page *page) \
>  #define PAGE_PRIVATE_CLEAR_FUNC(name, flagname) \
>  static inline void folio_clear_f2fs_##name(struct folio *folio)		\
>  {									\
> -	unsigned long v = (unsigned long)folio->private;		\
> -									\
> -	v &= ~(1UL << PAGE_PRIVATE_##flagname);				\
> -	if (v == (1UL << PAGE_PRIVATE_NOT_POINTER))			\
> +	clear_bit(PAGE_PRIVATE_##flagname,				\
> +		  f2fs_folio_flags_addr(folio));			\
> +	if (folio->private == (void *)BIT(PAGE_PRIVATE_NOT_POINTER))	\
>  		folio_detach_private(folio);				\
> -	else								\
> -		folio->private = (void *)v;				\
>  }									\
>  static inline void clear_page_private_##name(struct page *page) \
>  { \
> @@ -2808,7 +2842,7 @@ PAGE_PRIVATE_CLEAR_FUNC(atomic, ATOMIC_WRITE);
>  
>  static inline unsigned long folio_get_f2fs_data(struct folio *folio)
>  {
> -	unsigned long data = (unsigned long)folio->private;
> +	unsigned long data = f2fs_folio_get_private_flags(folio);
>  
>  	if (!test_bit(PAGE_PRIVATE_NOT_POINTER, &data))
>  		return 0;

Re: [PATCH v2 03/14] f2fs: support regular file buffered writes on large folios

[Chao Yu]

On 9/15/26 12:18, Nanzhe Zhao wrote:
> To avoid the complexity of unlocking a large folio in write_begin,
> preallocate partial blocks for inodes that can use large folios.
> During write_begin, read only the partial head and tail 4K subpages
> that need read-before-write, and skip read I/O for the full middle
> subpages covered by the write.
> 
> Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
> ---
>  fs/f2fs/data.c | 300 +++++++++++++++++++++++++++++++++++++++++++++++--
>  fs/f2fs/f2fs.h |   1 +
>  fs/f2fs/file.c |  17 ++-
>  3 files changed, 304 insertions(+), 14 deletions(-)
> 
> diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
> index f14044e8a6f4..a490df4f50b3 100644
> --- a/fs/f2fs/data.c
> +++ b/fs/f2fs/data.c
> @@ -1233,6 +1233,35 @@ static void f2fs_submit_page_read(struct inode *inode, struct fsverity_info *vi,
>  	f2fs_submit_read_bio(sbi, bio, DATA);
>  }
>  
> +/*
> + * Synchronously read a single 4K subpage by reusing f2fs_submit_page_read()
> + * so that iostat, trace, blk-crypto and post-read handling are all preserved.
> + * The caller must have already allocated ffs for the folio.
> + */
> +static int f2fs_submit_page_read_sync(struct inode *inode, struct folio *folio,
> +				      pgoff_t index, block_t blkaddr)
> +{
> +	struct f2fs_folio_state *ffs = folio->private;
> +
> +	/* Add bias so end_io does not call folio_end_read(). */
> +	f2fs_update_read_folio_pending(folio, 1);

f2fs_update_read_folio_pending() was used here for the first time, do we need
to relocate definition in this patch?

> +
> +	f2fs_submit_page_read(inode, NULL, folio, index, blkaddr,
> +			      REQ_OP_READ, false);
> +
> +	/* Wait until all bios have completed (pending drops back to our bias). */
> +	while (READ_ONCE(ffs->read_pages_pending) != 1)
> +		f2fs_io_schedule_timeout(DEFAULT_SCHEDULE_TIMEOUT);
> +
> +	/* Remove the bias. */
> +	f2fs_update_read_folio_pending(folio, -1);
> +
> +	if (!f2fs_ffs_test_blk_uptodate(folio, index))
> +		return -EIO;
> +
> +	return 0;
> +}
> +
>  static void __set_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
>  {
>  	__le32 *addr = get_dnode_addr(dn->inode, dn->node_folio);
> @@ -2570,6 +2599,114 @@ static void ffs_detach_free(struct folio *folio)
>  	kfree(ffs);
>  }
>  
> +bool f2fs_ffs_test_blk_uptodate(const struct folio *folio, pgoff_t index)
> +{
> +	struct f2fs_folio_state *ffs;
> +	unsigned int idx;
> +
> +	f2fs_bug_on(F2FS_F_SB(folio), !folio_contains(folio, index));
> +
> +	if (folio_test_uptodate(folio))
> +		return true;
> +
> +	if (!f2fs_folio_has_ffs(folio))
> +		return false;
> +
> +	ffs = (struct f2fs_folio_state *)folio->private;
> +	idx = index - folio->index;
> +	return test_bit(idx, ffs->state);
> +}
> +
> +static bool __ffs_mark_subrange_uptodate(struct folio *folio,
> +		struct f2fs_folio_state *ffs, size_t offset, size_t len)
> +{
> +	unsigned int nr_subpages = folio_nr_pages(folio);
> +	unsigned int start, end;
> +
> +	start = offset >> PAGE_SHIFT;
> +	end = (offset + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
> +	end = min(end, nr_subpages);
> +
> +	bitmap_set(ffs->state, start, end - start);
> +	return bitmap_full(ffs->state, nr_subpages);
> +}
> +
> +static void f2fs_ffs_mark_subrange_uptodate(struct folio *folio, size_t offset,
> +				       size_t len)
> +{
> +	struct f2fs_folio_state *ffs;
> +	unsigned long flags;
> +	bool mark_uptodate = false;
> +
> +	f2fs_bug_on(F2FS_F_SB(folio), offset + len > folio_size(folio));
> +
> +	if (!f2fs_folio_has_ffs(folio)) {
> +		folio_mark_uptodate(folio);
> +		return;
> +	}
> +
> +	ffs = (struct f2fs_folio_state *)folio->private;
> +	spin_lock_irqsave(&ffs->state_lock, flags);
> +	mark_uptodate = __ffs_mark_subrange_uptodate(folio, ffs, offset, len) &&
> +			!ffs->read_pages_pending;
> +	spin_unlock_irqrestore(&ffs->state_lock, flags);
> +	if (mark_uptodate)
> +		folio_mark_uptodate(folio);
> +}
> +
> +static void f2fs_ffs_mark_subrange_dirty(struct folio *folio,
> +				    size_t offset, size_t len)
> +{
> +	struct f2fs_folio_state *ffs;
> +	unsigned int nr_subpages, start, end;
> +	unsigned long flags;
> +
> +	f2fs_bug_on(F2FS_F_SB(folio), offset + len > folio_size(folio));
> +
> +	if (!f2fs_folio_has_ffs(folio))
> +		return;
> +
> +	ffs = (struct f2fs_folio_state *)folio->private;
> +	nr_subpages = folio_nr_pages(folio);
> +	start = offset >> PAGE_SHIFT;
> +	end = (offset + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
> +	end = min(end, nr_subpages);
> +
> +	spin_lock_irqsave(&ffs->state_lock, flags);
> +	bitmap_set(ffs->state, nr_subpages + start, end - start);
> +	spin_unlock_irqrestore(&ffs->state_lock, flags);
> +}
> +
> +static bool find_next_valid_block(const struct folio *folio,
> +				  size_t orig_off, size_t *need_off,
> +				  size_t len)
> +{
> +	size_t start = orig_off;
> +	size_t end = start + len;
> +	size_t head, tail;
> +	pgoff_t index;
> +
> +	if (start & (PAGE_SIZE - 1)) {
> +		head = round_down(start, PAGE_SIZE);
> +		index = folio->index + (head >> PAGE_SHIFT);
> +		if (!f2fs_ffs_test_blk_uptodate(folio, index)) {
> +			*need_off = head;
> +			return true;
> +		}
> +	}
> +
> +	if (end & (PAGE_SIZE - 1)) {
> +		tail = round_down(end - 1, PAGE_SIZE);

tail = round_down(end, PAGE_SIZE);

> +		index = folio->index + (tail >> PAGE_SHIFT);
> +		if (!f2fs_ffs_test_blk_uptodate(folio, index)) {
> +			*need_off = tail;
> +			return true;
> +		}
> +	}
> +
> +	return false;
> +}
> +
>  static int f2fs_read_data_large_folio(struct inode *inode,
>  		struct fsverity_info *vi,
>  		struct readahead_control *rac, struct folio *folio)
> @@ -3927,6 +4064,110 @@ static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi,
>  	return 0;
>  }
>  
> +static int prepare_large_folio_write_begin(struct inode *inode,
> +					  struct folio *folio, loff_t pos,
> +					  unsigned int len)
> +{
> +	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
> +	struct f2fs_folio_state *ffs;
> +	size_t ori_off = offset_in_folio(folio, pos);
> +	size_t need_off = ori_off;
> +	int err = 0;
> +
> +	len = min_t(unsigned int, len, folio_size(folio) - ori_off);
> +
> +	/*
> +	 * When folio minimum order is non-zero, the fsverity

Seems there is a condition that folio minimum order is non-zero, do we
need to check this condition along w/ FI_PREALLOCATED_ALL?

> +	 * page_cache_write() path enters f2fs_write_begin() via
> +	 * aops->write_begin without going through f2fs_write_iter(),
> +	 * so preallocation from f2fs_write_iter() is skipped.  In that
> +	 * case, if FI_PREALLOCATED_ALL is not set, we must preallocate
> +	 * the write blocks here.
> +	 */
> +	if (!is_inode_flag_set(inode, FI_PREALLOCATED_ALL)) {
> +		struct f2fs_map_blocks map = {};
> +
> +		map.m_lblk = F2FS_BYTES_TO_BLK(sbi, pos);
> +		map.m_len = F2FS_BLK_ALIGN(sbi, pos + len) - map.m_lblk;
> +
> +		if (!IS_DEVICE_ALIASING(inode))
> +			map.m_may_create = true;
> +		map.m_seg_type = NO_CHECK_TYPE;
> +
> +		err = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_PRE_AIO);
> +		if (err)
> +			return err;
> +	}
> +
> +	ffs = f2fs_ffs_find_or_alloc(folio);
> +	if (!ffs)
> +		return -ENOMEM;
> +
> +	/* Skip read if the folio is already fully uptodate or the write
> +	 * covers the entire folio.
> +	 */
> +	if (folio_test_uptodate(folio) || len == folio_size(folio))
> +		return 0;
> +
> +	if (!f2fs_verity_in_progress(inode) &&
> +	    !(pos & (PAGE_SIZE - 1)) && (pos + len) >= i_size_read(inode)) {
> +		size_t zoff = ori_off + len;
> +
> +		if (zoff < folio_size(folio))
> +			folio_zero_segment(folio, zoff, folio_size(folio));
> +		return 0;
> +	}
> +
> +	/* Inline data must have been converted before reaching here. */
> +	f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
> +
> +	while (find_next_valid_block(folio, ori_off,
> +				     &need_off, len)) {
> +		struct dnode_of_data dn;
> +		pgoff_t index = folio->index + (need_off >> PAGE_SHIFT);
> +		block_t blkaddr;
> +		bool get_dn = false;
> +
> +		if (!f2fs_lookup_read_extent_cache_block(inode, index,
> +							&blkaddr)) {
> +			if (IS_DEVICE_ALIASING(inode))
> +				return -ENODATA;
> +
> +			set_new_dnode(&dn, inode, NULL, NULL, 0);
> +			err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
> +			if (err)
> +				return err;
> +			get_dn = true;

Can we call f2fs_put_dnode(&dn) here? since we don't need to cover dnode
lock during I/O?

Thanks,

> +			blkaddr = dn.data_blkaddr;
> +
> +			if (blkaddr == NEW_ADDR) {
> +				size_t off = offset_in_folio(folio,
> +							     index << PAGE_SHIFT);
> +
> +				folio_zero_segment(folio, off, off + PAGE_SIZE);
> +				f2fs_ffs_mark_subrange_uptodate(folio, off,
> +							       PAGE_SIZE);
> +				goto out;
> +			}
> +
> +			if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
> +						  DATA_GENERIC_ENHANCE_READ)) {
> +				err = -EFSCORRUPTED;
> +				goto out;
> +			}
> +		}
> +
> +		err = f2fs_submit_page_read_sync(inode, folio, index, blkaddr);
> +out:
> +		if (get_dn)
> +			f2fs_put_dnode(&dn);
> +		if (err)
> +			return err;
> +	}
> +
> +	return 0;
> +}
> +
>  static int f2fs_write_begin(const struct kiocb *iocb,
>  			    struct address_space *mapping,
>  			    loff_t pos, unsigned len, struct folio **foliop,
> @@ -3938,6 +4179,7 @@ static int f2fs_write_begin(const struct kiocb *iocb,
>  	pgoff_t index = pos >> PAGE_SHIFT;
>  	bool need_balance = false;
>  	block_t blkaddr = NULL_ADDR;
> +	fgf_t fgp = FGP_LOCK | FGP_WRITE | FGP_CREAT;
>  	int err = 0;
>  
>  	trace_f2fs_write_begin(inode, pos, len);
> @@ -3985,9 +4227,15 @@ static int f2fs_write_begin(const struct kiocb *iocb,
>  	 * Do not use FGP_STABLE to avoid deadlock.
>  	 * Will wait that below with our IO control.
>  	 */
> -	folio = f2fs_filemap_get_folio(mapping, index,
> -				FGP_LOCK | FGP_WRITE | FGP_CREAT,
> -				mapping_gfp_mask(mapping));
> +	/*
> +	 * Inline data is carried in the first subpage.  Keep the index #0
> +	 * folio order-0 so that the existing inline read/convert paths
> +	 * (prepare_write_begin()) still apply; large folios are used from
> +	 * the second folio on.
> +	 */
> +	fgp |= fgf_set_order(f2fs_has_inline_data(inode) ? PAGE_SIZE : len);
> +	folio = f2fs_filemap_get_folio(mapping, index, fgp,
> +				      mapping_gfp_mask(mapping));
>  	if (IS_ERR(folio)) {
>  		err = PTR_ERR(folio);
>  		goto fail;
> @@ -4000,7 +4248,7 @@ static int f2fs_write_begin(const struct kiocb *iocb,
>  	if (f2fs_is_atomic_file(inode))
>  		err = prepare_atomic_write_begin(sbi, folio, pos, len,
>  					&blkaddr, &need_balance);
> -	else
> +	else if (!folio_test_large(folio))
>  		err = prepare_write_begin(sbi, folio, pos, len,
>  					&blkaddr, &need_balance);
>  	if (err)
> @@ -4021,6 +4269,14 @@ static int f2fs_write_begin(const struct kiocb *iocb,
>  
>  	f2fs_folio_wait_writeback(folio, DATA, false, true);
>  
> +	if (folio_test_large(folio)) {
> +		err = prepare_large_folio_write_begin(inode,
> +					folio, pos, len);
> +		if (!err)
> +			return 0;
> +		goto put_folio;
> +	}
> +
>  	if (len == folio_size(folio) || folio_test_uptodate(folio))
>  		return 0;
>  
> @@ -4081,15 +4337,20 @@ static int f2fs_write_end(const struct kiocb *iocb,
>  	trace_f2fs_write_end(inode, pos, len, copied);
>  
>  	/*
> -	 * This should be come from len == PAGE_SIZE, and we expect copied
> -	 * should be PAGE_SIZE. Otherwise, we treat it with zero copied and
> -	 * let generic_perform_write() try to copy data again through copied=0.
> +	 * If a short copy happens on a folio that isn't uptodate, we treat
> +	 * it with zero copied and let generic_perform_write() try to copy
> +	 * data again through copied=0.
>  	 */
>  	if (!folio_test_uptodate(folio)) {
> -		if (unlikely(copied != len))
> +		if (unlikely(copied != len)) {
>  			copied = 0;
> -		else
> +		} else if (folio_test_large(folio)) {
> +			f2fs_ffs_mark_subrange_uptodate(folio,
> +					offset_in_folio(folio, pos), len);
> +		} else {
> +			/* This should be come from len == PAGE_SIZE */
>  			folio_mark_uptodate(folio);
> +		}
>  	}
>  
>  #ifdef CONFIG_F2FS_FS_COMPRESSION
> @@ -4108,6 +4369,9 @@ static int f2fs_write_end(const struct kiocb *iocb,
>  	if (!copied)
>  		goto unlock_out;
>  
> +	if (folio_test_large(folio))
> +		f2fs_ffs_mark_subrange_dirty(folio, offset_in_folio(folio, pos),
> +								   copied);
>  	folio_mark_dirty(folio);
>  
>  	if (f2fs_is_atomic_file(inode))
> @@ -4170,8 +4434,22 @@ static bool f2fs_dirty_data_folio(struct address_space *mapping,
>  
>  	trace_f2fs_set_page_dirty(folio, DATA);
>  
> -	if (!folio_test_uptodate(folio))
> -		folio_mark_uptodate(folio);
> +	if (!folio_test_uptodate(folio)) {
> +		bool uptodate = true;
> +
> +		if (f2fs_folio_has_ffs(folio)) {
> +			struct f2fs_folio_state *ffs =
> +				(struct f2fs_folio_state *)folio->private;
> +			unsigned long flags;
> +
> +			spin_lock_irqsave(&ffs->state_lock, flags);
> +			uptodate = bitmap_full(ffs->state, folio_nr_pages(folio)) &&
> +				   !ffs->read_pages_pending;
> +			spin_unlock_irqrestore(&ffs->state_lock, flags);
> +		}
> +		if (uptodate)
> +			folio_mark_uptodate(folio);
> +	}
>  	BUG_ON(folio_test_swapcache(folio));
>  
>  	if (filemap_dirty_folio(mapping, folio)) {
> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
> index 326382ede1c3..8eccca6e5d27 100644
> --- a/fs/f2fs/f2fs.h
> +++ b/fs/f2fs/f2fs.h
> @@ -4392,6 +4392,7 @@ int f2fs_write_single_data_page(struct folio *folio, int *submitted,
>  				struct writeback_control *wbc,
>  				enum iostat_type io_type,
>  				int compr_blocks, bool allow_balance);
> +bool f2fs_ffs_test_blk_uptodate(const struct folio *folio, pgoff_t index);
>  void f2fs_write_failed(struct inode *inode, loff_t to);
>  void f2fs_invalidate_folio(struct folio *folio, size_t offset, size_t length);
>  bool f2fs_release_folio(struct folio *folio, gfp_t wait);
> diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
> index b0bdc7a977b9..9071bd23e57b 100644
> --- a/fs/f2fs/file.c
> +++ b/fs/f2fs/file.c
> @@ -5412,9 +5412,20 @@ static int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *iter,
>  			return ret;
>  	}
>  
> -	/* Do not preallocate blocks that will be written partially in 4KB. */
> -	map.m_lblk = F2FS_BLK_ALIGN(sbi, pos);
> -	map.m_len = F2FS_BYTES_TO_BLK(sbi, pos + count);
> +	if (!dio && mapping_large_folio_support(inode->i_mapping)) {
> +		/*
> +		 * Preallocate all blocks touched by a large-folio buffered write so
> +		 * the regular write_begin path does not need to unlock the folio for
> +		 * f2fs_balance_fs().  Rechecking large-folio state after unlock is
> +		 * unreliable since partial truncation can split the folio.
> +		 */
> +		map.m_lblk = F2FS_BYTES_TO_BLK(sbi, pos);
> +		map.m_len = F2FS_BLK_ALIGN(sbi, pos + count);
> +	} else {
> +		/* Do not preallocate blocks that will be written partially in 4KB. */
> +		map.m_lblk = F2FS_BLK_ALIGN(sbi, pos);
> +		map.m_len = F2FS_BYTES_TO_BLK(sbi, pos + count);
> +	}
>  	if (map.m_len > map.m_lblk)
>  		map.m_len -= map.m_lblk;
>  	else

Re: [PATCH v2 04/14] f2fs: support atomic file large folios buffered write

[Chao Yu]

On 9/15/26 12:18, Nanzhe Zhao wrote:
> ioctl can convert an inode with large folio support into an atomic
> file. Support large folio buffered writes for atomic files as well.
> 
> Add a large folio atomic write_begin helper that reserves COW mappings
> for the write range. For partial head and tail subpages, read the
> existing data from either the COW inode or the original inode before
> marking the subpage uptodate.
> 
> Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
> ---
>  fs/f2fs/data.c | 88 ++++++++++++++++++++++++++++++++++++++++++++++----
>  1 file changed, 81 insertions(+), 7 deletions(-)
> 
> diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
> index a490df4f50b3..eb5fb8e52851 100644
> --- a/fs/f2fs/data.c
> +++ b/fs/f2fs/data.c
> @@ -4016,18 +4016,16 @@ static int __reserve_data_block(struct inode *inode, pgoff_t index,
>  }
>  
>  static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi,
> -			struct folio *folio, loff_t pos, unsigned int len,
> +			struct inode *inode, pgoff_t index,
>  			block_t *blk_addr, bool *node_changed)
>  {
> -	struct inode *inode = folio->mapping->host;
>  	struct inode *cow_inode = F2FS_I(inode)->cow_inode;
> -	pgoff_t index = folio->index;
>  	int err = 0;
>  	block_t ori_blk_addr = NULL_ADDR;
>  	bool cow_has_reserved_block = false;
>  
>  	/* If pos is beyond the end of file, reserve a new block in COW inode */

              ^^^

Need to update comments here? there is no @pos in the function.

> -	if ((pos & PAGE_MASK) >= i_size_read(inode))
> +	if ((index << PAGE_SHIFT) >= i_size_read(inode))
>  		goto reserve_block;
>  
>  	/* Look for the block in COW inode first */
> @@ -4168,6 +4166,74 @@ static int prepare_large_folio_write_begin(struct inode *inode,
>  	return 0;
>  }
>  
> +static int prepare_large_folio_atomic_write_begin(struct inode *inode,
> +		struct address_space *mapping, struct folio *folio, loff_t pos,
> +		unsigned int len)
> +{
> +	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
> +	size_t ori_off = offset_in_folio(folio, pos);
> +	pgoff_t start, end, index;
> +	unsigned int orig_order;
> +	int err = 0;
> +
> +	len = min_t(unsigned int, len, folio_size(folio) - ori_off);
> +
> +	if (!f2fs_ffs_find_or_alloc(folio))
> +		return -ENOMEM;
> +
> +	/* Inline data must have been converted before reaching here. */
> +	f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
> +
> +	start = folio->index + (ori_off >> PAGE_SHIFT);
> +	end = folio->index + ((ori_off + len - 1) >> PAGE_SHIFT);
> +
> +	for (index = start; index <= end; index++) {
> +		block_t blkaddr = NULL_ADDR;
> +		bool node_changed = false;
> +		size_t off = (index - folio->index) << PAGE_SHIFT;
> +
> +		err = prepare_atomic_write_begin(sbi, inode, index,
> +						&blkaddr, &node_changed);
> +		if (err)
> +			return err;
> +
> +		if (f2fs_ffs_test_blk_uptodate(folio, index))
> +			goto balance;
> +
> +		if (blkaddr == NEW_ADDR) {
> +			folio_zero_segment(folio, off, off + PAGE_SIZE);
> +			f2fs_ffs_mark_subrange_uptodate(folio, off, PAGE_SIZE);
> +			goto balance;
> +		}
> +
> +		if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
> +					   DATA_GENERIC_ENHANCE_READ))
> +			return -EFSCORRUPTED;
> +
> +		err = f2fs_submit_page_read_sync(inode, folio, index,
> +						blkaddr);
> +		if (err)
> +			return err;
> +balance:
> +		/*
> +		 * Expand the 4K-page balance decision per subpage: check
> +		 * right after each preallocated block.
> +		 */
> +		if (node_changed && !IS_NOQUOTA(inode) &&

!IS_NOQUOTA(inode) is not needed.

> +		    has_not_enough_free_secs(sbi, 0, 0)) {
> +			orig_order = folio_order(folio);
> +			folio_unlock(folio);
> +			f2fs_balance_fs(sbi, true);
> +			folio_lock(folio);
> +			if (unlikely(folio->mapping != mapping ||
> +				     folio_order(folio) != orig_order))
> +				return -EAGAIN;
> +		}

Why can't we merge this logic w/ others? it seems duplicated.

Thanks,

> +	}
> +
> +	return 0;
> +}
> +
>  static int f2fs_write_begin(const struct kiocb *iocb,
>  			    struct address_space *mapping,
>  			    loff_t pos, unsigned len, struct folio **foliop,
> @@ -4245,8 +4311,8 @@ static int f2fs_write_begin(const struct kiocb *iocb,
>  
>  	*foliop = folio;
>  
> -	if (f2fs_is_atomic_file(inode))
> -		err = prepare_atomic_write_begin(sbi, folio, pos, len,
> +	if (f2fs_is_atomic_file(inode) && !folio_test_large(folio))
> +		err = prepare_atomic_write_begin(sbi, inode, folio->index,
>  					&blkaddr, &need_balance);
>  	else if (!folio_test_large(folio))
>  		err = prepare_write_begin(sbi, folio, pos, len,
> @@ -4270,10 +4336,18 @@ static int f2fs_write_begin(const struct kiocb *iocb,
>  	f2fs_folio_wait_writeback(folio, DATA, false, true);
>  
>  	if (folio_test_large(folio)) {
> -		err = prepare_large_folio_write_begin(inode,
> +		if (f2fs_is_atomic_file(inode))
> +			err = prepare_large_folio_atomic_write_begin(inode,
> +					mapping, folio, pos, len);
> +		else
> +			err = prepare_large_folio_write_begin(inode,
>  					folio, pos, len);
>  		if (!err)
>  			return 0;
> +		if (err == -EAGAIN) {
> +			f2fs_folio_put(folio, true);
> +			goto repeat;
> +		}
>  		goto put_folio;
>  	}
>