* [PATCH v6 01/15] f2fs: extend folio state for large folio write path
2026-10-22 7:53 [PATCH v6 00/15] f2fs: support & optimize large folios for writable files Nanzhe Zhao
@ 2026-10-22 7:53 ` Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 02/15] f2fs: carry subpage offset and count in write IO Nanzhe Zhao
` (14 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Nanzhe Zhao @ 2026-10-22 7:53 UTC (permalink / raw)
To: linux-f2fs-devel, Jaegeuk Kim, Chao Yu
Cc: Barry Song, Juan Yescas, Daeho Jeong, Pengfei Li, Dev Jain,
David Hildenbrand, linux-kernel, Bo Zhang, Kalesh Singh,
Nanzhe Zhao, Nanzhe Zhao, Ryan Roberts
From: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
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 | 52 ++++++++++++++++++++-----------------
fs/f2fs/f2fs.h | 70 +++++++++++++++++++++++++++++++++++++-------------
2 files changed, 80 insertions(+), 42 deletions(-)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index a8d39add5cbe..95212e60f09d 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;
-};
-
#define F2FS_BIO_POOL_SIZE NR_CURSEG_TYPE
int __init f2fs_init_bioset(void)
@@ -2717,17 +2711,31 @@ 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;
- if (ffs)
- return ffs;
+ 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));
- ffs = f2fs_kmem_cache_alloc(ffs_entry_slab,
- GFP_NOIO | __GFP_ZERO, true, NULL);
+ if (f2fs_folio_has_ffs(folio))
+ return (struct f2fs_folio_state *)folio->private;
+
+ 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;
}
@@ -2736,7 +2744,7 @@ 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;
}
@@ -2746,7 +2754,8 @@ 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,
@@ -2835,7 +2844,11 @@ 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);
+ if (!ffs) {
+ ret = -ENOMEM;
+ goto err_out;
+ }
/* set the bitmap to wait */
spin_lock_irq(&ffs->state_lock);
@@ -4750,21 +4763,12 @@ 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 aedba8b79baa..abb0c0caed91 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1621,6 +1621,18 @@ 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 */
@@ -1629,6 +1641,13 @@ 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,
@@ -2759,13 +2778,35 @@ 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) \
{ \
@@ -2777,14 +2818,10 @@ 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) \
{ \
@@ -2797,13 +2834,10 @@ 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) \
{ \
@@ -2826,7 +2860,7 @@ 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
^ permalink raw reply [flat|nested] 17+ messages in thread* [PATCH v6 02/15] f2fs: carry subpage offset and count in write IO
2026-10-22 7:53 [PATCH v6 00/15] f2fs: support & optimize large folios for writable files Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 01/15] f2fs: extend folio state for large folio write path Nanzhe Zhao
@ 2026-10-22 7:53 ` Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 03/15] f2fs: support regular file buffered writes on large folios Nanzhe Zhao
` (13 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Nanzhe Zhao @ 2026-10-22 7:53 UTC (permalink / raw)
To: linux-f2fs-devel, Jaegeuk Kim, Chao Yu
Cc: Barry Song, Juan Yescas, Daeho Jeong, Pengfei Li, Dev Jain,
David Hildenbrand, linux-kernel, Bo Zhang, Kalesh Singh,
Nanzhe Zhao, Nanzhe Zhao, Ryan Roberts
From: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
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 | 78 ++++++++++++++++++++++++++++++++------------
fs/f2fs/f2fs.h | 11 +++++++
fs/f2fs/gc.c | 3 ++
fs/f2fs/inline.c | 1 +
fs/f2fs/segment.c | 3 +-
7 files changed, 78 insertions(+), 21 deletions(-)
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 5c5b45d3c67b..3ad709f69893 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -264,6 +264,7 @@ static struct f2fs_cached_block *__get_meta_cache(struct f2fs_sb_info *sbi,
.op_flags = REQ_META | REQ_PRIO,
.old_blkaddr = index,
.new_blkaddr = index,
+ .folio_blkcnt = 1,
.encrypted_page = NULL,
.is_por = !is_meta ? 1 : 0,
.is_cache = 1,
@@ -462,6 +463,7 @@ int f2fs_ra_meta_caches(struct f2fs_sb_info *sbi, block_t start,
.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 747141c79900..c0e39f580993 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 95212e60f09d..280ea6b72473 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -849,6 +849,13 @@ 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;
+ size_t bio_len;
+
+ bio_offset = data_folio == fio_folio ? F2FS_FIO_BIO_OFFSET(fio) : 0;
+ bio_len = data_folio == fio_folio ? F2FS_FIO_BIO_SIZE(fio) :
+ folio_size(data_folio);
if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
fio->is_por ? META_POR : (__is_meta_io(fio) ?
@@ -861,11 +868,11 @@ 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_cache_count(fio->sbi, is_read_io(fio->op) ?
F2FS_RD_DATA : WB_DATA_TYPE(fio->folio, false));
@@ -924,7 +931,8 @@ 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;
@@ -933,7 +941,7 @@ 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);
@@ -950,7 +958,14 @@ 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;
+ size_t bio_len;
struct f2fs_sb_info *sbi = fio->sbi;
+
+ bio_offset = folio == fio_folio ? F2FS_FIO_BIO_OFFSET(fio) : 0;
+ bio_len = folio == fio_folio ? F2FS_FIO_BIO_SIZE(fio) :
+ folio_size(folio);
enum temp_type temp;
bool found = false;
int ret = -EAGAIN;
@@ -972,8 +987,8 @@ 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;
}
@@ -1087,6 +1102,14 @@ 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;
+ size_t bio_len;
+
+ bio_offset = data_folio == folio ? F2FS_FIO_BIO_OFFSET(fio) : 0;
+ bio_len = data_folio == folio ? F2FS_FIO_BIO_SIZE(fio) :
+ folio_size(data_folio);
if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
__is_meta_io(fio) ? META_GENERIC : DATA_GENERIC))
@@ -1101,20 +1124,21 @@ 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;
}
if (fio->io_wbc)
- wbc_account_cgroup_owner(fio->io_wbc, folio, folio_size(folio));
+ wbc_account_cgroup_owner(fio->io_wbc, folio, bio_len);
inc_cache_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;
@@ -1177,6 +1201,10 @@ 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));
@@ -1209,24 +1237,32 @@ 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_cache_count(sbi, type);
+ for (unsigned int i = 0; i < fio_cnt; i++)
+ inc_cache_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 = bio_folio == fio->folio ? F2FS_FIO_BIO_OFFSET(fio) : 0;
+ bio_len = bio_folio == fio->folio ? F2FS_FIO_BIO_SIZE(fio) :
+ folio_size(bio_folio);
+
+ if (!bio_add_folio(io->bio, bio_folio, bio_len, bio_offset)) {
__submit_merged_bio(io);
goto alloc_new;
}
@@ -1234,10 +1270,9 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio)
F2FS_BIO(io->bio)->entry_cnt++;
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
@@ -3213,7 +3248,8 @@ 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))
@@ -3232,7 +3268,8 @@ 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;
@@ -3335,6 +3372,7 @@ 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 abb0c0caed91..62117de4b404 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1350,6 +1350,8 @@ 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;
@@ -1372,6 +1374,15 @@ 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 5b948c92f981..485c01b6756b 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -1228,6 +1228,7 @@ 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,
.is_cache = 1,
@@ -1338,6 +1339,7 @@ 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,
.is_cache = 1,
@@ -1550,6 +1552,7 @@ 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_blkcnt = 1,
.encrypted_page = NULL,
.need_lock = LOCK_REQ,
.io_type = FS_GC_DATA_IO,
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 273b6428c9f9..ab7537ff7ebd 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/segment.c b/fs/f2fs/segment.c
index daf6d9617d5b..80f58c586e33 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -3876,7 +3876,8 @@ 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;
--
2.43.0
^ permalink raw reply [flat|nested] 17+ messages in thread* [PATCH v6 03/15] f2fs: support regular file buffered writes on large folios
2026-10-22 7:53 [PATCH v6 00/15] f2fs: support & optimize large folios for writable files Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 01/15] f2fs: extend folio state for large folio write path Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 02/15] f2fs: carry subpage offset and count in write IO Nanzhe Zhao
@ 2026-10-22 7:53 ` Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 04/15] f2fs: support atomic file large folios buffered write Nanzhe Zhao
` (12 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Nanzhe Zhao @ 2026-10-22 7:53 UTC (permalink / raw)
To: linux-f2fs-devel, Jaegeuk Kim, Chao Yu
Cc: Barry Song, Juan Yescas, Daeho Jeong, Pengfei Li, Dev Jain,
David Hildenbrand, linux-kernel, Bo Zhang, Kalesh Singh,
Nanzhe Zhao, Nanzhe Zhao, Ryan Roberts
From: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
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 | 431 +++++++++++++++++++++++++++++++++++++++++++++----
fs/f2fs/f2fs.h | 1 +
fs/f2fs/file.c | 17 +-
3 files changed, 412 insertions(+), 37 deletions(-)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 280ea6b72473..ffc25eb09a92 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -93,6 +93,20 @@ 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)
+{
+ 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);
+}
+
/*
* Update and unlock a bio's pages, and free the bio.
*
@@ -107,6 +121,23 @@ 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;
@@ -128,7 +159,8 @@ static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
}
if (folio_test_large(folio)) {
- struct f2fs_folio_state *ffs = folio->private;
+ struct f2fs_folio_state *ffs =
+ (struct f2fs_folio_state *)folio->private;
spin_lock_irqsave(&ffs->state_lock, flags);
ffs->read_pages_pending -= nr_pages;
@@ -1437,19 +1469,26 @@ 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;
+
+ 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, folio->index,
+ bio = f2fs_grab_read_bio(inode, vi, blkaddr, 1, op_flags, index,
for_write);
/* wait for GCed page writeback via generic cache */
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_cache_count(sbi, F2FS_RD_DATA);
@@ -1457,6 +1496,40 @@ 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 =
+ (struct f2fs_folio_state *)folio->private;
+
+ /* Add bias so end_io does not call folio_end_read(). */
+ f2fs_update_read_folio_pending(folio, 1);
+
+ /*
+ * We are holding the folio lock, so use GFP_NOIO for the bio
+ * allocation to avoid entering mm reclaim.
+ */
+ f2fs_submit_page_read(inode, NULL, folio, index, blkaddr,
+ REQ_OP_READ, true);
+
+ /* 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_entry);
@@ -1630,8 +1703,8 @@ struct folio *f2fs_get_read_data_folio(struct inode *inode, pgoff_t index,
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:
@@ -2793,6 +2866,110 @@ 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 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 unsigned int __ffs_mark_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, before;
+
+ start = offset >> PAGE_SHIFT;
+ end = (offset + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ end = min(end, nr_subpages);
+
+ before = bitmap_weight(ffs->state, 2 * nr_subpages);
+ bitmap_set(ffs->state, nr_subpages + start, end - start);
+ return bitmap_weight(ffs->state, 2 * nr_subpages) - before;
+}
+
+static void f2fs_ffs_mark_subrange_dirty(struct folio *folio,
+ size_t offset, size_t len)
+{
+ struct f2fs_folio_state *ffs;
+ 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;
+
+ spin_lock_irqsave(&ffs->state_lock, flags);
+ __ffs_mark_subrange_dirty(folio, ffs, offset, len);
+ 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, 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)
@@ -4158,6 +4335,151 @@ static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi,
return 0;
}
+/*
+ * Drop the folio lock when a node was changed, then balance the
+ * filesystem and reacquire the lock.
+ *
+ * Return: true if the folio became unusable while unlocked (being
+ * truncated), false if the folio is still usable.
+ */
+static bool f2fs_balance_fs_folio_locked(struct folio *folio,
+ struct address_space *mapping, bool node_changed)
+{
+ struct inode *inode = folio->mapping->host;
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ unsigned int orig_order;
+ bool had_ffs;
+
+ if (!node_changed || IS_NOQUOTA(inode) ||
+ !has_not_enough_free_secs(sbi, 0, 0))
+ return false;
+
+ had_ffs = f2fs_folio_has_ffs(folio);
+ orig_order = folio_order(folio);
+ folio_unlock(folio);
+ f2fs_balance_fs(sbi, true);
+ folio_lock(folio);
+
+ /*
+ * Writeback may have started on the folio during the unlock
+ * window, so wait for it before the caller proceeds.
+ */
+ f2fs_folio_wait_writeback(folio, true, true);
+
+ if (folio->mapping != mapping)
+ return true;
+
+ if (folio_order(folio) != orig_order)
+ return true;
+
+ /* large folio was released */
+ if (had_ffs && !f2fs_folio_has_ffs(folio))
+ return true;
+
+ return false;
+}
+
+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;
+
+ /*
+ * when the write did not come through f2fs_write_iter, we preallocate all
+ * blocks in the write range here.
+ */
+ if (!is_inode_flag_set(inode, FI_PREALLOCATED_ALL) &&
+ !IS_DEVICE_ALIASING(inode)) {
+ pgoff_t first = F2FS_BYTES_TO_BLK(sbi, pos);
+ pgoff_t last = F2FS_BLK_ALIGN(sbi, pos + len);
+ pgoff_t idx;
+
+ for (idx = first; idx < last; idx++) {
+ block_t blkaddr = NULL_ADDR;
+ bool node_changed = false;
+
+ err = __reserve_data_block(inode, idx, &blkaddr,
+ &node_changed);
+ if (err)
+ return err;
+ if (f2fs_balance_fs_folio_locked(folio, folio->mapping,
+ node_changed))
+ return -EAGAIN;
+ }
+ }
+
+ 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;
+
+ 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;
+ blkaddr = dn.data_blkaddr;
+ f2fs_put_dnode(&dn);
+
+ if (blkaddr == NEW_ADDR) {
+ 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);
+ continue;
+ }
+ }
+
+ /*
+ * The read extent cache only validates the first and last
+ * block of i_ext, so check both the cached and dnode paths.
+ */
+ 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;
+ }
+
+ return 0;
+}
+
static int f2fs_write_begin(const struct kiocb *iocb,
struct address_space *mapping,
loff_t pos, unsigned len, struct folio **foliop,
@@ -4169,6 +4491,8 @@ 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;
+ unsigned int blen;
int err = 0;
trace_f2fs_write_begin(inode, pos, len);
@@ -4216,9 +4540,15 @@ 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;
@@ -4228,31 +4558,42 @@ static int f2fs_write_begin(const struct kiocb *iocb,
*foliop = folio;
+ /* Clamp the write length to the folio size. */
+ blen = min_t(unsigned int, len,
+ folio_size(folio) - offset_in_folio(folio, pos));
+
+ /*
+ * Flush the cached IO of this folio before touching it, especially
+ * for the large folio prepare below which reads and updates subpage
+ * states.
+ */
+ f2fs_folio_wait_writeback(folio, false, true);
+
if (f2fs_is_atomic_file(inode))
err = prepare_atomic_write_begin(sbi, folio, pos, len,
&blkaddr, &need_balance);
- else
- err = prepare_write_begin(sbi, folio, pos, len,
+ else if (!folio_test_large(folio))
+ err = prepare_write_begin(sbi, folio, pos, blen,
&blkaddr, &need_balance);
- if (err)
- goto put_folio;
-
- if (need_balance && !IS_NOQUOTA(inode) &&
- has_not_enough_free_secs(sbi, 0, 0)) {
- folio_unlock(folio);
- f2fs_balance_fs(sbi, true);
- folio_lock(folio);
- if (folio->mapping != mapping) {
- /* The folio got truncated from under us */
- folio_unlock(folio);
- folio_put(folio);
+ else
+ err = prepare_large_folio_write_begin(inode, folio, pos, blen);
+ if (err) {
+ if (err == -EAGAIN) {
+ f2fs_folio_put(folio, true);
goto repeat;
}
+ goto put_folio;
}
- f2fs_folio_wait_writeback(folio, false, true);
+ if (f2fs_balance_fs_folio_locked(folio, mapping, need_balance)) {
+ f2fs_folio_put(folio, true);
+ goto repeat;
+ }
+
+ if (folio_test_large(folio))
+ return 0;
- if (len == folio_size(folio) || folio_test_uptodate(folio))
+ if (blen == folio_size(folio) || folio_test_uptodate(folio))
return 0;
if (!(pos & (PAGE_SIZE - 1)) && (pos + len) >= i_size_read(inode) &&
@@ -4280,7 +4621,7 @@ 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)) {
@@ -4312,15 +4653,20 @@ 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
@@ -4339,6 +4685,9 @@ 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))
@@ -4395,8 +4744,22 @@ 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 62117de4b404..df0091591ff5 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -4454,6 +4454,7 @@ 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 b077e4eb790d..85b4f1a2ff0d 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -5420,9 +5420,20 @@ 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
^ permalink raw reply [flat|nested] 17+ messages in thread* [PATCH v6 04/15] f2fs: support atomic file large folios buffered write
2026-10-22 7:53 [PATCH v6 00/15] f2fs: support & optimize large folios for writable files Nanzhe Zhao
` (2 preceding siblings ...)
2026-10-22 7:53 ` [PATCH v6 03/15] f2fs: support regular file buffered writes on large folios Nanzhe Zhao
@ 2026-10-22 7:53 ` Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 05/15] f2fs: support large folio writeback Nanzhe Zhao
` (11 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Nanzhe Zhao @ 2026-10-22 7:53 UTC (permalink / raw)
To: linux-f2fs-devel, Jaegeuk Kim, Chao Yu
Cc: Barry Song, Juan Yescas, Daeho Jeong, Pengfei Li, Dev Jain,
David Hildenbrand, linux-kernel, Bo Zhang, Kalesh Singh,
Nanzhe Zhao, Nanzhe Zhao, Ryan Roberts
From: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
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 | 70 +++++++++++++++++++++++++++++++++++++++++++++-----
1 file changed, 63 insertions(+), 7 deletions(-)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index ffc25eb09a92..e3d6e3087bb9 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -4287,18 +4287,16 @@ 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 is beyond the end of file, reserve a new block in COW inode */
+ if (((loff_t)index << PAGE_SHIFT) >= i_size_read(inode))
goto reserve_block;
/* Look for the block in COW inode first */
@@ -4480,6 +4478,61 @@ 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;
+ 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:
+ if (f2fs_balance_fs_folio_locked(folio, mapping, node_changed))
+ 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,
@@ -4569,12 +4622,15 @@ static int f2fs_write_begin(const struct kiocb *iocb,
*/
f2fs_folio_wait_writeback(folio, false, true);
- 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, blen,
&blkaddr, &need_balance);
+ else 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, blen);
if (err) {
--
2.43.0
^ permalink raw reply [flat|nested] 17+ messages in thread* [PATCH v6 05/15] f2fs: support large folio writeback
2026-10-22 7:53 [PATCH v6 00/15] f2fs: support & optimize large folios for writable files Nanzhe Zhao
` (3 preceding siblings ...)
2026-10-22 7:53 ` [PATCH v6 04/15] f2fs: support atomic file large folios buffered write Nanzhe Zhao
@ 2026-10-22 7:53 ` Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 06/15] f2fs: account large folio dirty data at block granularity Nanzhe Zhao
` (10 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Nanzhe Zhao @ 2026-10-22 7:53 UTC (permalink / raw)
To: linux-f2fs-devel, Jaegeuk Kim, Chao Yu
Cc: Barry Song, Juan Yescas, Daeho Jeong, Pengfei Li, Dev Jain,
David Hildenbrand, linux-kernel, Bo Zhang, Kalesh Singh,
Nanzhe Zhao, Nanzhe Zhao, Ryan Roberts
From: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
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 | 521 +++++++++++++++++++++++++++++++++++++++++++++-
fs/f2fs/segment.c | 8 +-
2 files changed, 521 insertions(+), 8 deletions(-)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index e3d6e3087bb9..74583f0f1833 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -358,6 +358,49 @@ static void f2fs_cache_write_end_bio(struct bio *bio)
bio_put(bio);
}
+static bool f2fs_ffs_has_dirty_subpage(struct folio *folio)
+{
+ struct f2fs_folio_state *ffs;
+ unsigned long flags;
+ unsigned int nr_subpages;
+ bool dirty;
+
+ if (!f2fs_folio_has_ffs(folio))
+ return false;
+
+ ffs = (struct f2fs_folio_state *)folio->private;
+ nr_subpages = folio_nr_pages(folio);
+
+ spin_lock_irqsave(&ffs->state_lock, flags);
+ dirty = find_next_bit(ffs->state, 2 * nr_subpages,
+ nr_subpages) < 2 * nr_subpages;
+ spin_unlock_irqrestore(&ffs->state_lock, flags);
+
+ return dirty;
+}
+
+/*
+ * Drop a write page pending of @folio. When the last pending is gone,
+ * clear PAGE_PRIVATE_GCING if no dirty subpage is left, and end
+ * writeback if it was started.
+ */
+static void f2fs_ffs_put_write_pending(struct folio *folio, unsigned int nr)
+{
+ struct f2fs_folio_state *ffs;
+
+ if (!f2fs_folio_has_ffs(folio))
+ goto release;
+
+ ffs = (struct f2fs_folio_state *)folio->private;
+ if (!atomic_sub_and_test(nr, &ffs->write_pages_pending))
+ return;
+release:
+ if (!f2fs_ffs_has_dirty_subpage(folio))
+ folio_clear_f2fs_gcing(folio);
+ if (folio_test_writeback(folio))
+ folio_end_writeback(folio);
+}
+
static void f2fs_write_end_bio(struct bio *bio)
{
struct f2fs_sb_info *sbi = bio->bi_private;
@@ -373,6 +416,8 @@ 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;
+ unsigned int npages = nr_pages;
enum count_type type;
#ifdef CONFIG_F2FS_FS_COMPRESSION
@@ -392,7 +437,8 @@ static void f2fs_write_end_bio(struct bio *bio)
}
}
- dec_cache_count(sbi, type);
+ while (nr_pages--)
+ dec_cache_count(sbi, type);
/*
* we should access sbi before folio_end_writeback() to
@@ -402,8 +448,7 @@ 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);
+ f2fs_ffs_put_write_pending(folio, npages);
}
bio_put(bio);
@@ -2922,7 +2967,7 @@ static unsigned int __ffs_mark_subrange_dirty(struct folio *folio,
return bitmap_weight(ffs->state, 2 * nr_subpages) - before;
}
-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;
@@ -2940,6 +2985,99 @@ 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)
@@ -3477,7 +3615,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
if (ipu_force ||
(__is_valid_data_blkaddr(fio->old_blkaddr) &&
need_inplace_update(fio))) {
- folio_start_writeback(folio);
+ __folio_start_writeback(folio, folio_test_dirty(folio));
f2fs_put_dnode(&dn);
if (fio->need_lock == LOCK_REQ)
f2fs_unlock_op(fio->sbi, &lc);
@@ -3504,7 +3642,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
fio->version = ni.version;
- folio_start_writeback(folio);
+ __folio_start_writeback(folio, folio_test_dirty(folio));
if (fio->compr_blocks && fio->old_blkaddr == COMPRESS_ADDR)
f2fs_i_compr_blocks_update(inode, fio->compr_blocks - 1, false);
@@ -3512,6 +3650,13 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
/* LFS mode write path */
f2fs_outplace_write_data(&dn, fio);
trace_f2fs_do_write_data_page(folio, OPU);
+ /*
+ * The outplace write path failed to submit this block.
+ */
+ if (!fio->submitted) {
+ err = -EIO;
+ goto out_writepage;
+ }
set_inode_flag(inode, FI_APPEND_WRITE);
if (atomic_commit)
folio_clear_f2fs_atomic(folio);
@@ -3523,6 +3668,144 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
return err;
}
+static int f2fs_write_folio_dirty_range(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);
+ dn_held = false;
+ 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);
+ /*
+ * The outplace write path failed to submit this block.
+ */
+ if (!fio.submitted) {
+ err = -EIO;
+ goto block_done;
+ }
+ if (submitted)
+ (*submitted)++;
+ submitted_blk = true;
+ set_inode_flag(inode, FI_APPEND_WRITE);
+ trace_f2fs_do_write_data_page(folio, OPU);
+block_done:
+ if (dn_held)
+ f2fs_put_dnode(&dn);
+ /*
+ * If this block was not submitted, roll back its
+ * write pages pending.
+ */
+ if (!submitted_blk && ffs)
+ f2fs_ffs_put_write_pending(folio, 1);
+ if (!err) {
+ *pos = ((loff_t)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,
@@ -3972,6 +4255,226 @@ 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 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;
+ retry = false;
+
+ if (err) {
+ folio_redirty_for_writepage(wbc, folio);
+ goto retry_out;
+ }
+
+ if (atomic_read(&sbi->wb_sync_req[DATA]) &&
+ wbc->sync_mode == WB_SYNC_NONE) {
+ folio_redirty_for_writepage(wbc, folio);
+ /*
+ * A WB_SYNC_ALL writeback is in progress, so defer
+ * this writeback. Mark the error as -EBUSY to let
+ * writeback_iter() stop iterating.
+ */
+ err = -EBUSY;
+ goto retry_out;
+ }
+
+ /*
+ * If cp_error is set, all subpages of this folio are not written
+ * back unless the filesystem is mounted with errors=remount-ro.
+ */
+ if (unlikely(f2fs_cp_error(sbi))) {
+ mapping_set_error(folio->mapping, -EIO);
+ if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_READONLY) {
+ folio_redirty_for_writepage(wbc, folio);
+ } else {
+ if (f2fs_folio_has_ffs(folio))
+ f2fs_ffs_clear_subrange_dirty_and_test(folio, 0,
+ folio_size(folio));
+ inode_dec_dirty_pages(inode);
+ }
+ goto retry_out;
+ }
+
+ /*
+ * Writing back one large folio performs multiple block allocations, so
+ * best-effort balance the filesystem before writing it back.
+ */
+ if (!F2FS_I(inode)->wb_task && has_not_enough_free_secs(sbi, 0, 0)) {
+ folio_redirty_for_writepage(wbc, folio);
+ retry = true;
+ folio_unlock(folio);
+ f2fs_balance_fs(sbi, true);
+ folio_lock(folio);
+ goto retry;
+ }
+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, 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);
+
+ /*
+ * Large folios can be submitted as multiple bios, which may
+ * complete while we are still submitting the remaining dirty
+ * ranges. Hold a bias on write_pages_pending to prevent
+ * folio_end_writeback() from being called early.
+ */
+ 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_folio_dirty_range(folio, &submitted,
+ wbc, io_type, &pos, r_len);
+ folio_submitted += submitted;
+ nwritten += submitted;
+ if (err)
+ goto out;
+ }
+
+ /* If none of the subpages of a folio is submitted, keep the atomic flag */
+ if (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), or if the writeback failed, 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)) || err)
+ folio_redirty_for_writepage(wbc, folio);
+ else
+ inode_dec_dirty_pages(inode);
+
+ /*
+ * Release the bias taken above and we end writeback here if
+ * no write bio is in flight.
+ */
+ if (bias_added) {
+ f2fs_ffs_put_write_pending(folio, 1);
+ } else if (!folio_submitted && folio_test_writeback(folio)) {
+ /*
+ * Order-0 folios take no bias, so end the writeback
+ * if nothing was submitted.
+ */
+ folio_end_writeback(folio);
+ }
+
+retry_out:
+ if (op_locked) {
+ f2fs_unlock_op(sbi, &lc);
+ op_locked = false;
+ }
+
+ folio_unlock(folio);
+ }
+
+ if (nwritten)
+ f2fs_submit_merged_write_cond(F2FS_M_SB(mapping), mapping->host,
+ NULL);
+
+ /*
+ * Prevent the -EBUSY error that stopped writeback_iter() from
+ * propagating to the user.
+ */
+ if (err == -EBUSY)
+ err = 0;
+ return err;
+}
+
static inline bool __should_serialize_io(struct inode *inode,
struct writeback_control *wbc)
{
@@ -4066,7 +4569,11 @@ 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) &&
+ !f2fs_has_inline_data(inode))
+ 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);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 80f58c586e33..cbb65e0343c8 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -4173,7 +4173,13 @@ static void do_write_block(struct f2fs_summary *sum, struct f2fs_io_info *fio)
"%s Failed to allocate data block, ino:%u, index:%lu, type:%d, old_blkaddr:0x%x, new_blkaddr:0x%x, err:%d",
__func__, fio->ino, folio->index, type,
fio->old_blkaddr, fio->new_blkaddr, err);
- folio_end_writeback(folio);
+ /*
+ * For a large folio, the caller rolls back
+ * write_pages_pending and ends writeback when the last
+ * pending write is gone.
+ */
+ if (!f2fs_folio_has_ffs(folio))
+ folio_end_writeback(folio);
}
f2fs_bug_on(fio->sbi, !is_set_ckpt_flags(fio->sbi,
CP_ERROR_FLAG));
--
2.43.0
^ permalink raw reply [flat|nested] 17+ messages in thread* [PATCH v6 06/15] f2fs: account large folio dirty data at block granularity
2026-10-22 7:53 [PATCH v6 00/15] f2fs: support & optimize large folios for writable files Nanzhe Zhao
` (4 preceding siblings ...)
2026-10-22 7:53 ` [PATCH v6 05/15] f2fs: support large folio writeback Nanzhe Zhao
@ 2026-10-22 7:53 ` Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 07/15] f2fs: prepare mmap write faults for large folios Nanzhe Zhao
` (9 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Nanzhe Zhao @ 2026-10-22 7:53 UTC (permalink / raw)
To: linux-f2fs-devel, Jaegeuk Kim, Chao Yu
Cc: Barry Song, Juan Yescas, Daeho Jeong, Pengfei Li, Dev Jain,
David Hildenbrand, linux-kernel, Bo Zhang, Kalesh Singh,
Nanzhe Zhao, Nanzhe Zhao, Ryan Roberts
From: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
Originally inode->dirty_pages was accounted once per folio, but f2fs
needs the counter to be accounted in blocks.
This introduces batch dirty page add/sub accounting; for a large folio
the changed dirty page count is computed from the dirty bitmap bit
changes.
Found by f2fs/006 (lfs + checkpoint=disable) and generic/363.
Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
fs/f2fs/checkpoint.c | 38 ++++++++++++++++++++++----
fs/f2fs/compress.c | 4 +--
fs/f2fs/data.c | 50 +++++++++++++++++++++++-----------
fs/f2fs/dir.c | 2 +-
fs/f2fs/f2fs.h | 65 ++++++++++++++++++++++++++++++++++----------
fs/f2fs/gc.c | 2 +-
fs/f2fs/inline.c | 2 +-
fs/f2fs/node.c | 2 +-
8 files changed, 123 insertions(+), 42 deletions(-)
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 3ad709f69893..1ed38c668fc5 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -1324,20 +1324,46 @@ static void __remove_dirty_inode(struct inode *inode, enum inode_type type)
stat_dec_dirty_inode(F2FS_I_SB(inode), type);
}
-void f2fs_update_dirty_folio(struct inode *inode, struct folio *folio)
+/*
+ * Account @nr dirty pages (negative when dirtiness is cleared) for @inode.
+ */
+void f2fs_account_dirty_blocks(struct inode *inode, int nr)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE;
- if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
- !S_ISLNK(inode->i_mode))
+ if (!nr)
return;
spin_lock(&sbi->inode_lock[type]);
- if (type != FILE_INODE || test_opt(sbi, DATA_FLUSH))
- __add_dirty_inode(inode, type);
- inode_inc_dirty_pages(inode);
+ if (nr > 0) {
+ if (type != FILE_INODE || test_opt(sbi, DATA_FLUSH))
+ __add_dirty_inode(inode, type);
+ inode_add_dirty_blocks(inode, nr);
+ } else {
+ inode_sub_dirty_blocks(inode, -nr);
+ __remove_dirty_inode(inode, type);
+ }
spin_unlock(&sbi->inode_lock[type]);
+}
+
+void f2fs_update_dirty_folio(struct inode *inode, struct folio *folio)
+{
+ if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
+ !S_ISLNK(inode->i_mode))
+ return;
+
+ /*
+ * Large folios have a subpage dirty bitmap, so defer their dirty accounting
+ * to the f2fs_ffs_*subrange_dirty*() helpers. This avoids nesting
+ * ffs->state_lock with the inode dirty list lock.
+ */
+ if (f2fs_folio_has_ffs(folio)) {
+ folio_set_f2fs_reference(folio);
+ return;
+ }
+
+ f2fs_account_dirty_blocks(inode, 1);
folio_set_f2fs_reference(folio);
}
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index c0e39f580993..162bd8ef822a 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -1065,7 +1065,7 @@ static void cancel_cluster_writeback(struct compress_ctx *cc,
/* Cancel writeback and stay locked. */
for (i = 0; i < cc->cluster_size; i++) {
if (i < submitted) {
- inode_inc_dirty_pages(cc->inode);
+ inode_inc_dirty_block(cc->inode);
lock_page(cc->rpages[i]);
}
clear_page_private_gcing(cc->rpages[i]);
@@ -1409,7 +1409,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
}
(*submitted)++;
unlock_continue:
- inode_dec_dirty_pages(cc->inode);
+ inode_dec_dirty_block(cc->inode);
folio_unlock(fio.folio);
}
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 74583f0f1833..f415c3eb4e78 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -2967,10 +2967,18 @@ static unsigned int __ffs_mark_subrange_dirty(struct folio *folio,
return bitmap_weight(ffs->state, 2 * nr_subpages) - before;
}
+/*
+ * Mark the given range dirty for writeback.
+ *
+ * Callers must guarantee that the corresponding subpages are already
+ * uptodate: a dirty subpage always holds the latest data, whose
+ * on-disk copy may be stale.
+ */
void f2fs_ffs_mark_subrange_dirty(struct folio *folio,
size_t offset, size_t len)
{
struct f2fs_folio_state *ffs;
+ unsigned int set;
unsigned long flags;
f2fs_bug_on(F2FS_F_SB(folio), offset + len > folio_size(folio));
@@ -2981,21 +2989,27 @@ void f2fs_ffs_mark_subrange_dirty(struct folio *folio,
ffs = (struct f2fs_folio_state *)folio->private;
spin_lock_irqsave(&ffs->state_lock, flags);
- __ffs_mark_subrange_dirty(folio, ffs, offset, len);
+ set = __ffs_mark_subrange_dirty(folio, ffs, offset, len);
spin_unlock_irqrestore(&ffs->state_lock, flags);
+
+ if (set)
+ f2fs_account_dirty_blocks(folio->mapping->host, set);
}
static bool __ffs_clear_subrange_dirty(struct folio *folio,
- struct f2fs_folio_state *ffs, size_t offset, size_t len)
+ struct f2fs_folio_state *ffs, size_t offset, size_t len,
+ unsigned int *cleared)
{
unsigned int nr_subpages = folio_nr_pages(folio);
- unsigned int start, end;
+ unsigned int start, end, before;
start = offset >> PAGE_SHIFT;
end = (offset + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
end = min(end, nr_subpages);
+ before = bitmap_weight(ffs->state, 2 * nr_subpages);
bitmap_clear(ffs->state, nr_subpages + start, end - start);
+ *cleared = before - bitmap_weight(ffs->state, 2 * nr_subpages);
return find_next_bit(ffs->state, 2 * nr_subpages, nr_subpages) <
2 * nr_subpages;
}
@@ -3007,13 +3021,15 @@ static bool __ffs_clear_subrange_dirty(struct folio *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.
+ * account the cleared subpages against the inode dirty counters, 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;
+ unsigned int cleared = 0;
bool dirty;
if (!f2fs_folio_has_ffs(folio))
@@ -3021,9 +3037,12 @@ bool f2fs_ffs_clear_subrange_dirty_and_test(struct folio *folio, size_t offset,
ffs = (struct f2fs_folio_state *)folio->private;
spin_lock_irqsave(&ffs->state_lock, flags);
- dirty = __ffs_clear_subrange_dirty(folio, ffs, offset, len);
+ dirty = __ffs_clear_subrange_dirty(folio, ffs, offset, len, &cleared);
spin_unlock_irqrestore(&ffs->state_lock, flags);
+ if (cleared)
+ f2fs_account_dirty_blocks(folio->mapping->host, -cleared);
+
return dirty;
}
@@ -3933,7 +3952,7 @@ int f2fs_write_single_data_page(struct folio *folio, int *submitted,
goto redirty_out;
out:
- inode_dec_dirty_pages(inode);
+ inode_dec_dirty_block(inode);
if (err) {
folio_clear_uptodate(folio);
folio_clear_f2fs_gcing(folio);
@@ -4312,14 +4331,13 @@ static int f2fs_write_cache_folios(struct address_space *mapping,
*/
if (unlikely(f2fs_cp_error(sbi))) {
mapping_set_error(folio->mapping, -EIO);
- if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_READONLY) {
+ if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_READONLY)
folio_redirty_for_writepage(wbc, folio);
- } else {
- if (f2fs_folio_has_ffs(folio))
- f2fs_ffs_clear_subrange_dirty_and_test(folio, 0,
- folio_size(folio));
- inode_dec_dirty_pages(inode);
- }
+ else if (f2fs_folio_has_ffs(folio))
+ f2fs_ffs_clear_subrange_dirty_and_test(folio, 0,
+ folio_size(folio));
+ else
+ f2fs_account_dirty_blocks(inode, -1);
goto retry_out;
}
@@ -4436,8 +4454,8 @@ static int f2fs_write_cache_folios(struct address_space *mapping,
if (f2fs_ffs_clear_subrange_dirty_and_test(folio, 0,
(err ? pos : end_pos) - folio_pos(folio)) || err)
folio_redirty_for_writepage(wbc, folio);
- else
- inode_dec_dirty_pages(inode);
+ else if (!f2fs_folio_has_ffs(folio))
+ inode_dec_dirty_block(inode);
/*
* Release the bias taken above and we end writeback here if
@@ -5279,7 +5297,7 @@ void f2fs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
return;
if (folio_test_dirty(folio)) {
- inode_dec_dirty_pages(inode);
+ inode_dec_dirty_block(inode);
f2fs_remove_dirty_inode(inode);
}
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 97f7fef6b068..70847313ca6a 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -937,7 +937,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, void *dentry_block,
folio_clear_uptodate(folio);
folio_detach_private(folio);
- inode_dec_dirty_pages(dir);
+ inode_dec_dirty_block(dir);
f2fs_remove_dirty_inode(dir);
}
f2fs_folio_put(folio, true);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index df0091591ff5..b89664e28a92 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -2919,9 +2919,10 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
f2fs_i_blocks_write(inode, count, false, true);
}
-static inline void inc_cache_count(struct f2fs_sb_info *sbi, int count_type)
+static inline void add_cache_counts(struct f2fs_sb_info *sbi,
+ int count_type, int nr)
{
- atomic_inc(&sbi->nr_caches[count_type]);
+ atomic_add(nr, &sbi->nr_caches[count_type]);
if (count_type == F2FS_DIRTY_DENTS ||
count_type == F2FS_DIRTY_NODES ||
@@ -2931,31 +2932,66 @@ static inline void inc_cache_count(struct f2fs_sb_info *sbi, int count_type)
set_sbi_flag(sbi, SBI_IS_DIRTY);
}
-static inline void inode_inc_dirty_pages(struct inode *inode)
+static inline void sub_cache_counts(struct f2fs_sb_info *sbi,
+ int count_type, int nr)
{
- atomic_inc(&F2FS_I(inode)->dirty_pages);
- inc_cache_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
- F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
- if (IS_NOQUOTA(inode))
- inc_cache_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA);
+ atomic_sub(nr, &sbi->nr_caches[count_type]);
+}
+
+static inline void inc_cache_count(struct f2fs_sb_info *sbi, int count_type)
+{
+ add_cache_counts(sbi, count_type, 1);
}
static inline void dec_cache_count(struct f2fs_sb_info *sbi, int count_type)
{
- atomic_dec(&sbi->nr_caches[count_type]);
+ sub_cache_counts(sbi, count_type, 1);
+}
+
+/*
+ * Account @nr dirty pages for @inode; one page is
+ * (PAGE_SIZE >> log_blocksize) filesystem blocks.
+ */
+static inline void inode_add_dirty_blocks(struct inode *inode, int nr)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ int blocks = nr * (PAGE_SIZE >> sbi->log_blocksize);
+
+ atomic_add(blocks, &F2FS_I(inode)->dirty_pages);
+ if (S_ISDIR(inode->i_mode))
+ add_cache_counts(sbi, F2FS_DIRTY_DENTS, blocks);
+ else
+ add_cache_counts(sbi, F2FS_DIRTY_DATA, blocks);
+ if (IS_NOQUOTA(inode))
+ add_cache_counts(sbi, F2FS_DIRTY_QDATA, blocks);
}
-static inline void inode_dec_dirty_pages(struct inode *inode)
+static inline void inode_sub_dirty_blocks(struct inode *inode, int nr)
{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ int blocks = nr * (PAGE_SIZE >> sbi->log_blocksize);
+
if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
!S_ISLNK(inode->i_mode))
return;
- atomic_dec(&F2FS_I(inode)->dirty_pages);
- dec_cache_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
- F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
+ atomic_sub(blocks, &F2FS_I(inode)->dirty_pages);
+ if (S_ISDIR(inode->i_mode))
+ sub_cache_counts(sbi, F2FS_DIRTY_DENTS, blocks);
+ else
+ sub_cache_counts(sbi, F2FS_DIRTY_DATA, blocks);
if (IS_NOQUOTA(inode))
- dec_cache_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA);
+ sub_cache_counts(sbi, F2FS_DIRTY_QDATA, blocks);
+}
+
+static inline void inode_inc_dirty_block(struct inode *inode)
+{
+ inode_add_dirty_blocks(inode, 1);
+}
+
+static inline void inode_dec_dirty_block(struct inode *inode)
+{
+ inode_sub_dirty_blocks(inode, 1);
}
static inline void inc_atomic_write_cnt(struct inode *inode)
@@ -4384,6 +4420,7 @@ void f2fs_remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino);
int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi);
int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi);
void f2fs_update_dirty_folio(struct inode *inode, struct folio *folio);
+void f2fs_account_dirty_blocks(struct inode *inode, int nr);
void f2fs_remove_dirty_inode(struct inode *inode);
int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type,
bool from_cp);
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 485c01b6756b..67a4224a5d75 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -1564,7 +1564,7 @@ static int move_data_page(struct inode *inode, block_t bidx, int gc_type,
folio_mark_dirty(folio);
if (folio_clear_dirty_for_io(folio)) {
- inode_dec_dirty_pages(inode);
+ inode_dec_dirty_block(inode);
f2fs_remove_dirty_inode(inode);
}
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index ab7537ff7ebd..49905aa08418 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -199,7 +199,7 @@ int f2fs_convert_inline_folio(struct dnode_of_data *dn, struct folio *folio)
f2fs_outplace_write_data(dn, &fio);
f2fs_folio_wait_writeback(folio, true, true);
if (dirty) {
- inode_dec_dirty_pages(dn->inode);
+ inode_dec_dirty_block(dn->inode);
f2fs_remove_dirty_inode(dn->inode);
}
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 424e95ca5878..1fdef678dcef 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1699,7 +1699,7 @@ static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
goto folio_out;
ret = f2fs_write_inline_data(inode, folio);
- inode_dec_dirty_pages(inode);
+ inode_dec_dirty_block(inode);
f2fs_remove_dirty_inode(inode);
if (ret)
folio_mark_dirty(folio);
--
2.43.0
^ permalink raw reply [flat|nested] 17+ messages in thread* [PATCH v6 07/15] f2fs: prepare mmap write faults for large folios
2026-10-22 7:53 [PATCH v6 00/15] f2fs: support & optimize large folios for writable files Nanzhe Zhao
` (5 preceding siblings ...)
2026-10-22 7:53 ` [PATCH v6 06/15] f2fs: account large folio dirty data at block granularity Nanzhe Zhao
@ 2026-10-22 7:53 ` Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 08/15] f2fs: make GC migration large-folio aware Nanzhe Zhao
` (8 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Nanzhe Zhao @ 2026-10-22 7:53 UTC (permalink / raw)
To: linux-f2fs-devel, Jaegeuk Kim, Chao Yu
Cc: Barry Song, Juan Yescas, Daeho Jeong, Pengfei Li, Dev Jain,
David Hildenbrand, linux-kernel, Bo Zhang, Kalesh Singh,
Nanzhe Zhao, Nanzhe Zhao, Ryan Roberts
From: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
Now write protect `mmap` also need to support large folio,
Change `f2fs_vm_page_mkwrite` to achieve that.
Note it currently marks the whole large folio dirty
to avoid data loss which causes write amplification.
Further optimization is welcome.
The folio_zero_segment() in mkwrite is extended 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 that was added
to cover the removed shortcut is no longer needed.
Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
fs/f2fs/f2fs.h | 4 +++
fs/f2fs/file.c | 96 ++++++++++++++++++++++++++++++++------------------
2 files changed, 65 insertions(+), 35 deletions(-)
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index b89664e28a92..915ca72cf276 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -4492,6 +4492,10 @@ 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 85b4f1a2ff0d..808b72d3d78a 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -118,14 +118,48 @@ 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, 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;
+ pgoff_t i, nr;
int err = 0;
vm_fault_t ret;
@@ -162,7 +196,7 @@ 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;
@@ -180,11 +214,6 @@ 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);
@@ -200,62 +229,59 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
}
folio_lock(folio);
- /*
- * A concurrent buffered write can extend isize, so we store isize in a
- * local variable to let the zeroing offset match the EOF check below.
- */
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;
if (unlikely(folio->mapping != inode->i_mapping ||
- folio_pos(folio) > isize ||
- !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;
- }
-
- if (err) {
+ if (folio_test_large(folio) && !f2fs_ffs_find_or_alloc(folio)) {
folio_unlock(folio);
+ err = -ENOMEM;
goto out_sem;
}
- f2fs_folio_wait_writeback(folio, false, true);
+ nr = DIV_ROUND_UP(dirty_len, PAGE_SIZE);
- /* wait for GCed page writeback via generic cache */
- f2fs_wait_on_block_writeback(inode, dn.data_blkaddr);
+ 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;
+ }
+ }
/* page is wholly or partially inside EOF */
- if (((loff_t)(folio->index + 1) << PAGE_SHIFT) > isize) {
- loff_t offset;
+ if (folio_start + folio_size(folio) > isize) {
+ size_t offset = offset_in_folio(folio, isize);
- offset = isize & ~PAGE_MASK;
folio_zero_segment(folio, offset, folio_size(folio));
}
+
+ if (folio_test_large(folio))
+ 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
^ permalink raw reply [flat|nested] 17+ messages in thread* [PATCH v6 08/15] f2fs: make GC migration large-folio aware
2026-10-22 7:53 [PATCH v6 00/15] f2fs: support & optimize large folios for writable files Nanzhe Zhao
` (6 preceding siblings ...)
2026-10-22 7:53 ` [PATCH v6 07/15] f2fs: prepare mmap write faults for large folios Nanzhe Zhao
@ 2026-10-22 7:53 ` Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 09/15] f2fs: optimize small block size large folio read Nanzhe Zhao
` (7 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Nanzhe Zhao @ 2026-10-22 7:53 UTC (permalink / raw)
To: linux-f2fs-devel, Jaegeuk Kim, Chao Yu
Cc: Barry Song, Juan Yescas, Daeho Jeong, Pengfei Li, Dev Jain,
David Hildenbrand, linux-kernel, Bo Zhang, Kalesh Singh,
Nanzhe Zhao, Nanzhe Zhao, Ryan Roberts
From: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
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() 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.
The write_pages_pending reference is taken by f2fs_do_write_data_page()
and dropped from its common error path, so a block that is truncated
concurrently no longer leaks the counter.
Reported-by: kernel test robot <yi1.lai@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202610081027.b13dcf10-lkp@intel.com
Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
fs/f2fs/data.c | 63 ++++++++++++++++++++++++++++++++++-------------
fs/f2fs/f2fs.h | 1 +
fs/f2fs/gc.c | 29 ++++++++++++++++++----
fs/f2fs/segment.c | 2 +-
4 files changed, 72 insertions(+), 23 deletions(-)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index f415c3eb4e78..5671395130b2 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1679,20 +1679,16 @@ 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,
@@ -1728,7 +1724,7 @@ 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;
}
@@ -1741,9 +1737,11 @@ 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;
}
@@ -1803,7 +1801,8 @@ 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);
}
@@ -2952,6 +2951,22 @@ 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 = (struct f2fs_folio_state *)folio->private;
+ nr_subpages = folio_nr_pages(folio);
+ idx = index - folio->index;
+ return test_bit(nr_subpages + idx, ffs->state);
+}
+
static unsigned int __ffs_mark_subrange_dirty(struct folio *folio,
struct f2fs_folio_state *ffs, size_t offset, size_t len)
{
@@ -3045,7 +3060,6 @@ bool f2fs_ffs_clear_subrange_dirty_and_test(struct folio *folio, size_t offset,
return dirty;
}
-
static unsigned int ffs_next_dirty_subpage(struct f2fs_folio_state *ffs,
const struct folio *folio, unsigned int start,
unsigned int end)
@@ -3543,7 +3557,7 @@ 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)))
@@ -3569,8 +3583,11 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
struct dnode_of_data dn;
struct node_info ni;
struct f2fs_lock_context lc;
+ struct f2fs_folio_state *ffs;
bool ipu_force = false;
bool atomic_commit;
+ bool pending_added = false;
+ bool submitted = false;
int err = 0;
/* Use COW inode to make dnode_of_data for atomic write */
@@ -3612,7 +3629,6 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
/* This page is already truncated */
if (fio->old_blkaddr == NULL_ADDR) {
folio_clear_uptodate(folio);
- folio_clear_f2fs_gcing(folio);
goto out_writepage;
}
got_it:
@@ -3662,6 +3678,11 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
fio->version = ni.version;
__folio_start_writeback(folio, folio_test_dirty(folio));
+ if (f2fs_folio_has_ffs(folio)) {
+ ffs = (struct f2fs_folio_state *)folio->private;
+ atomic_inc(&ffs->write_pages_pending);
+ pending_added = true;
+ }
if (fio->compr_blocks && fio->old_blkaddr == COMPRESS_ADDR)
f2fs_i_compr_blocks_update(inode, fio->compr_blocks - 1, false);
@@ -3676,6 +3697,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
err = -EIO;
goto out_writepage;
}
+ submitted = true;
set_inode_flag(inode, FI_APPEND_WRITE);
if (atomic_commit)
folio_clear_f2fs_atomic(folio);
@@ -3684,6 +3706,13 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
out:
if (fio->need_lock == LOCK_REQ)
f2fs_unlock_op(fio->sbi, &lc);
+ if (!submitted) {
+ if (pending_added) {
+ f2fs_ffs_put_write_pending(folio, 1);
+ } else if (!f2fs_ffs_has_dirty_subpage(folio)) {
+ folio_clear_f2fs_gcing(folio);
+ }
+ }
return err;
}
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 915ca72cf276..1b63dd961f15 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -4493,6 +4493,7 @@ 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 67a4224a5d75..c3e01f6811b4 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -1520,12 +1520,19 @@ 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;
@@ -1540,6 +1547,8 @@ 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 {
@@ -1552,33 +1561,43 @@ 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);
+ bool is_dirty = f2fs_ffs_test_blk_dirty(folio, bidx);
retry:
f2fs_folio_wait_writeback(folio, true, true);
+ if (large)
+ f2fs_ffs_mark_subrange_dirty(folio, foff, PAGE_SIZE);
folio_mark_dirty(folio);
if (folio_clear_dirty_for_io(folio)) {
- inode_dec_dirty_block(inode);
- f2fs_remove_dirty_inode(inode);
+ if (!large) {
+ inode_dec_dirty_block(inode);
+ f2fs_remove_dirty_inode(inode);
+ } else if (f2fs_ffs_clear_subrange_dirty_and_test(folio,
+ foff, PAGE_SIZE)) {
+ folio_mark_dirty(folio);
+ }
}
folio_set_f2fs_gcing(folio);
err = f2fs_do_write_data_page(&fio);
if (err) {
- folio_clear_f2fs_gcing(folio);
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 cbb65e0343c8..e017a5f2a67f 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -3863,7 +3863,7 @@ 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
^ permalink raw reply [flat|nested] 17+ messages in thread* [PATCH v6 09/15] f2fs: optimize small block size large folio read
2026-10-22 7:53 [PATCH v6 00/15] f2fs: support & optimize large folios for writable files Nanzhe Zhao
` (7 preceding siblings ...)
2026-10-22 7:53 ` [PATCH v6 08/15] f2fs: make GC migration large-folio aware Nanzhe Zhao
@ 2026-10-22 7:53 ` Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 10/15] f2fs: support partial uptodate " Nanzhe Zhao
` (6 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Nanzhe Zhao @ 2026-10-22 7:53 UTC (permalink / raw)
To: linux-f2fs-devel, Jaegeuk Kim, Chao Yu
Cc: Barry Song, Juan Yescas, Daeho Jeong, Pengfei Li, Dev Jain,
David Hildenbrand, linux-kernel, Bo Zhang, Kalesh Singh,
Nanzhe Zhao, Nanzhe Zhao, Ryan Roberts
From: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
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.
Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
fs/f2fs/data.c | 46 +++++++++++++++++++++++++++++++---------------
1 file changed, 31 insertions(+), 15 deletions(-)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 5671395130b2..bc1bffbb15ca 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -158,7 +158,7 @@ static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
continue;
}
- if (folio_test_large(folio)) {
+ if (f2fs_folio_has_ffs(folio)) {
struct f2fs_folio_state *ffs =
(struct f2fs_folio_state *)folio->private;
@@ -3151,7 +3151,7 @@ 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 nrpages, len_blks;
struct f2fs_folio_state *ffs;
int ret = 0;
bool folio_in_bio = false;
@@ -3175,11 +3175,16 @@ 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;
+ unsigned int i;
+
+ len_blks = 1;
+
/*
* Map blocks using the previous result first.
*/
@@ -3208,13 +3213,23 @@ 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;
+ }
}
+
} 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;
@@ -3234,9 +3249,7 @@ static int f2fs_read_data_large_folio(struct inode *inode,
}
/* 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);
}
/*
@@ -3260,17 +3273,20 @@ 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_cache_count(F2FS_I_SB(inode), F2FS_RD_DATA);
+ for (i = 0; i < len_blks; i++)
+ inc_cache_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
^ permalink raw reply [flat|nested] 17+ messages in thread* [PATCH v6 10/15] f2fs: support partial uptodate large folio read
2026-10-22 7:53 [PATCH v6 00/15] f2fs: support & optimize large folios for writable files Nanzhe Zhao
` (8 preceding siblings ...)
2026-10-22 7:53 ` [PATCH v6 09/15] f2fs: optimize small block size large folio read Nanzhe Zhao
@ 2026-10-22 7:53 ` Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 11/15] f2fs: handle partial truncate of large folio dirty subpages Nanzhe Zhao
` (5 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Nanzhe Zhao @ 2026-10-22 7:53 UTC (permalink / raw)
To: linux-f2fs-devel, Jaegeuk Kim, Chao Yu
Cc: Barry Song, Juan Yescas, Daeho Jeong, Pengfei Li, Dev Jain,
David Hildenbrand, linux-kernel, Bo Zhang, Kalesh Singh,
Nanzhe Zhao, Nanzhe Zhao, Ryan Roberts
From: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
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 | 102 +++++++++++++++++++++++++++++++++++++++++++++----
1 file changed, 95 insertions(+), 7 deletions(-)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index bc1bffbb15ca..e718ed01fe7c 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -148,6 +148,7 @@ static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
struct folio *folio = fi.folio;
unsigned 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)) {
@@ -163,6 +164,9 @@ 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 (uptodate)
+ 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);
@@ -172,7 +176,7 @@ static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
dec_cache_count(F2FS_F_SB(folio), F2FS_RD_DATA);
if (finished)
- folio_end_read(folio, bio->bi_status == BLK_STS_OK);
+ folio_end_read(folio, uptodate);
}
if (ctx)
@@ -3141,6 +3145,70 @@ 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 = (struct f2fs_folio_state *)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 inode *inode, struct folio *folio,
+ pgoff_t offset, block_t block_nr,
+ unsigned int *len_blks)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_folio_state *ffs;
+ unsigned int next, end;
+
+ if (!f2fs_folio_has_ffs(folio) || *len_blks <= 1)
+ return;
+
+ if (f2fs_is_multi_device(sbi)) {
+ int bidx = f2fs_target_device_index(sbi, block_nr);
+
+ *len_blks = min_t(unsigned int, *len_blks,
+ FDEV(bidx).end_blk + 1 - block_nr);
+ }
+ *len_blks = min_t(unsigned int, *len_blks,
+ (unsigned int)fscrypt_limit_io_blocks(inode,
+ folio->index + offset,
+ *len_blks));
+
+ ffs = (struct f2fs_folio_state *)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)
@@ -3173,6 +3241,19 @@ static int f2fs_read_data_large_folio(struct inode *inode,
f2fs_update_read_folio_count(F2FS_I_SB(inode), folio);
folio_in_bio = false;
+ ffs = NULL;
+ if (folio_test_large(folio)) {
+ /*
+ * Allocate the folio state before doing anything with the
+ * folio, so that the block mapping helpers below can rely on
+ * it, and fail early if memory is not available.
+ */
+ ffs = f2fs_ffs_find_or_alloc(folio);
+ if (!ffs) {
+ ret = -ENOMEM;
+ goto err_out;
+ }
+ }
index = folio->index;
offset = 0;
nrpages = folio_nr_pages(folio);
@@ -3185,6 +3266,11 @@ 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.
*/
@@ -3217,6 +3303,8 @@ 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(inode, folio, offset,
+ block_nr, &len_blks);
for (i = 0; i < len_blks; i++) {
if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode),
@@ -3235,6 +3323,12 @@ static int f2fs_read_data_large_folio(struct inode *inode,
ret = -EIO;
goto err_out;
}
+ if (folio_test_large(folio)) {
+ spin_lock_irq(&ffs->state_lock);
+ __ffs_mark_subrange_uptodate(folio, ffs,
+ page_offset, PAGE_SIZE);
+ spin_unlock_irq(&ffs->state_lock);
+ }
continue;
}
@@ -3242,12 +3336,6 @@ 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 = f2fs_ffs_find_or_alloc(folio);
- if (!ffs) {
- ret = -ENOMEM;
- goto err_out;
- }
-
/* set the bitmap to wait */
f2fs_update_read_folio_pending(folio, len_blks);
}
--
2.43.0
^ permalink raw reply [flat|nested] 17+ messages in thread* [PATCH v6 11/15] f2fs: handle partial truncate of large folio dirty subpages
2026-10-22 7:53 [PATCH v6 00/15] f2fs: support & optimize large folios for writable files Nanzhe Zhao
` (9 preceding siblings ...)
2026-10-22 7:53 ` [PATCH v6 10/15] f2fs: support partial uptodate " Nanzhe Zhao
@ 2026-10-22 7:53 ` Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 12/15] f2fs: fix zeroing paths for large folios Nanzhe Zhao
` (4 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Nanzhe Zhao @ 2026-10-22 7:53 UTC (permalink / raw)
To: linux-f2fs-devel, Jaegeuk Kim, Chao Yu
Cc: Barry Song, Juan Yescas, Daeho Jeong, Pengfei Li, Dev Jain,
David Hildenbrand, linux-kernel, Bo Zhang, Kalesh Singh,
Nanzhe Zhao, Nanzhe Zhao, Ryan Roberts
From: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
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_folio_dirty_range() 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 | 94 +++++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 89 insertions(+), 5 deletions(-)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index e718ed01fe7c..24613b00f843 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -404,7 +404,6 @@ static void f2fs_ffs_put_write_pending(struct folio *folio, unsigned int nr)
if (folio_test_writeback(folio))
folio_end_writeback(folio);
}
-
static void f2fs_write_end_bio(struct bio *bio)
{
struct f2fs_sb_info *sbi = bio->bi_private;
@@ -2955,6 +2954,41 @@ 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))
+ 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);
+}
+
+static void f2fs_clear_truncated_page_state(struct folio *folio, pgoff_t i)
+{
+ if (f2fs_folio_has_ffs(folio)) {
+ ffs_clear_subrange_uptodate(folio,
+ (loff_t)i << PAGE_SHIFT, PAGE_SIZE);
+ folio_clear_uptodate(folio);
+ } else {
+ folio_clear_uptodate(folio);
+ folio_clear_f2fs_gcing(folio);
+ }
+}
+
bool f2fs_ffs_test_blk_dirty(const struct folio *folio, pgoff_t index)
{
struct f2fs_folio_state *ffs;
@@ -3732,7 +3766,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
/* This page is already truncated */
if (fio->old_blkaddr == NULL_ADDR) {
- folio_clear_uptodate(folio);
+ f2fs_clear_truncated_page_state(folio, fio->folio_offset);
goto out_writepage;
}
got_it:
@@ -3882,12 +3916,31 @@ static int f2fs_write_folio_dirty_range(struct folio *folio, int *submitted,
}
err = f2fs_get_dnode_of_data(&dn, data_idx, LOOKUP_NODE);
- if (err)
+ /*
+ * If a subpage of folio for a cow file is dirtied but not
+ * reserve a cow block, fallback to original inode to lookup
+ * block address
+ */
+ if (atomic_commit && (err == -ENOENT ||
+ (!err && dn.data_blkaddr == NULL_ADDR))) {
+ f2fs_put_dnode(&dn);
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ err = f2fs_get_dnode_of_data(&dn, data_idx,
+ LOOKUP_NODE);
+ }
+ if (err && err != -ENOENT)
goto block_done;
dn_held = true;
fio.old_blkaddr = dn.data_blkaddr;
+ /* This page is already truncated */
+ if (err == -ENOENT || fio.old_blkaddr == NULL_ADDR) {
+ f2fs_clear_truncated_page_state(folio, i);
+ err = 0;
+ goto block_done;
+ }
+
got_it:
if (__is_valid_data_blkaddr(fio.old_blkaddr) &&
!f2fs_is_valid_blkaddr(sbi, fio.old_blkaddr,
@@ -5426,10 +5479,41 @@ 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);
+ folio_clear_uptodate(folio);
+
+ /*
+ * 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))
+ folio_cancel_dirty(folio);
+ if (!dirty && !folio_test_writeback(folio))
+ folio_clear_f2fs_gcing(folio);
return;
+ }
- if (folio_test_dirty(folio)) {
+ if (f2fs_folio_has_ffs(folio)) {
+ f2fs_ffs_clear_subrange_dirty_and_test(folio, 0,
+ folio_size(folio));
+ } else if (folio_test_dirty(folio)) {
inode_dec_dirty_block(inode);
f2fs_remove_dirty_inode(inode);
}
--
2.43.0
^ permalink raw reply [flat|nested] 17+ messages in thread* [PATCH v6 12/15] f2fs: fix zeroing paths for large folios
2026-10-22 7:53 [PATCH v6 00/15] f2fs: support & optimize large folios for writable files Nanzhe Zhao
` (10 preceding siblings ...)
2026-10-22 7:53 ` [PATCH v6 11/15] f2fs: handle partial truncate of large folio dirty subpages Nanzhe Zhao
@ 2026-10-22 7:53 ` Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 13/15] f2fs: handle block cloning within the same large folio Nanzhe Zhao
` (3 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Nanzhe Zhao @ 2026-10-22 7:53 UTC (permalink / raw)
To: linux-f2fs-devel, Jaegeuk Kim, Chao Yu
Cc: Barry Song, Juan Yescas, Daeho Jeong, Pengfei Li, Dev Jain,
David Hildenbrand, linux-kernel, Bo Zhang, Kalesh Singh,
Nanzhe Zhao, Nanzhe Zhao, Ryan Roberts
From: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
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 | 18 +++++++++++++-----
fs/f2fs/f2fs.h | 1 +
fs/f2fs/file.c | 29 ++++++++++++++++++++++++-----
3 files changed, 38 insertions(+), 10 deletions(-)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 24613b00f843..f71fb7c993ef 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1839,6 +1839,12 @@ 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_put_cache(ientry, true);
+ return ERR_PTR(-ENOMEM);
+ }
+
set_new_dnode(&dn, inode, ientry, NULL, 0);
err = f2fs_reserve_block(&dn, index);
if (err) {
@@ -1848,13 +1854,15 @@ struct folio *f2fs_get_new_data_folio(struct inode *inode,
if (!ientry)
f2fs_put_dnode(&dn);
- if (folio_test_uptodate(folio))
+ if (f2fs_ffs_test_blk_uptodate(folio, index))
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);
@@ -2931,7 +2939,7 @@ bool f2fs_ffs_test_blk_uptodate(const struct folio *folio, pgoff_t index)
return test_bit(idx, ffs->state);
}
-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 1b63dd961f15..2c9343eb6b5e 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -4480,6 +4480,7 @@ 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 f2fs_cached_block *ientry, 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 808b72d3d78a..439e84a4aec3 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -833,12 +833,13 @@ 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) {
@@ -856,12 +857,22 @@ 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, 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) {
+ /*
+ * The folio was read back above, so the subpage is
+ * already uptodate and dirty data stays valid.
+ */
+ f2fs_ffs_mark_subrange_dirty(folio, folio_off,
+ blk_end - folio_off);
folio_mark_dirty(folio);
+ }
f2fs_folio_put(folio, true);
return 0;
}
@@ -1325,6 +1336,7 @@ 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;
@@ -1339,7 +1351,14 @@ static int fill_zero(struct inode *inode, pgoff_t index,
return PTR_ERR(folio);
f2fs_folio_wait_writeback(folio, 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);
+ /*
+ * This subpage must be uptodate here, which is guaranteed by
+ * f2fs_get_new_data_folio() above.
+ */
+ f2fs_ffs_mark_subrange_dirty(folio, folio_off, len);
folio_mark_dirty(folio);
f2fs_folio_put(folio, true);
return 0;
--
2.43.0
^ permalink raw reply [flat|nested] 17+ messages in thread* [PATCH v6 13/15] f2fs: handle block cloning within the same large folio
2026-10-22 7:53 [PATCH v6 00/15] f2fs: support & optimize large folios for writable files Nanzhe Zhao
` (11 preceding siblings ...)
2026-10-22 7:53 ` [PATCH v6 12/15] f2fs: fix zeroing paths for large folios Nanzhe Zhao
@ 2026-10-22 7:53 ` Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 14/15] f2fs: allow large folio support to writeable files Nanzhe Zhao
` (2 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Nanzhe Zhao @ 2026-10-22 7:53 UTC (permalink / raw)
To: linux-f2fs-devel, Jaegeuk Kim, Chao Yu
Cc: Barry Song, Juan Yescas, Daeho Jeong, Pengfei Li, Dev Jain,
David Hildenbrand, linux-kernel, Bo Zhang, Kalesh Singh,
Nanzhe Zhao, Nanzhe Zhao, Ryan Roberts
From: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
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 439e84a4aec3..f621d5e65023 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -1598,25 +1598,70 @@ 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, 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
^ permalink raw reply [flat|nested] 17+ messages in thread* [PATCH v6 14/15] f2fs: allow large folio support to writeable files
2026-10-22 7:53 [PATCH v6 00/15] f2fs: support & optimize large folios for writable files Nanzhe Zhao
` (12 preceding siblings ...)
2026-10-22 7:53 ` [PATCH v6 13/15] f2fs: handle block cloning within the same large folio Nanzhe Zhao
@ 2026-10-22 7:53 ` Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 15/15] f2fs: make compressed files compatible with large folio Nanzhe Zhao
2026-10-23 0:55 ` [PATCH v6 00/15] f2fs: support & optimize large folios for writable files Chao Yu
15 siblings, 0 replies; 17+ messages in thread
From: Nanzhe Zhao @ 2026-10-22 7:53 UTC (permalink / raw)
To: linux-f2fs-devel, Jaegeuk Kim, Chao Yu
Cc: Barry Song, Juan Yescas, Daeho Jeong, Pengfei Li, Dev Jain,
David Hildenbrand, linux-kernel, Bo Zhang, Kalesh Singh,
Nanzhe Zhao, Nanzhe Zhao, Ryan Roberts
From: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
Now we make all write path support large folios,
so we open permission to let writeable file set
large folio mapping.
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, 27 insertions(+), 19 deletions(-)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index f71fb7c993ef..2338450ce031 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -3266,7 +3266,7 @@ 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 2c9343eb6b5e..53914629c604 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -5348,6 +5348,23 @@ 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 f621d5e65023..3d621a20766d 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -163,17 +163,8 @@ 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));
+ if (unlikely(IS_IMMUTABLE(inode)))
return VM_FAULT_SIGBUS;
- }
if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) {
err = -EIO;
@@ -720,9 +711,6 @@ 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)
@@ -1194,8 +1182,6 @@ 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 49905aa08418..0dca6c3d58fb 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -239,6 +239,12 @@ 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);
ientry = f2fs_get_inode_cache(sbi, inode->i_ino);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 9164a2b5d9f0..f5a4dac98ef2 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -599,9 +599,7 @@ 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 38fcea8b72bf..6a1ff631393c 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
^ permalink raw reply [flat|nested] 17+ messages in thread* [PATCH v6 15/15] f2fs: make compressed files compatible with large folio
2026-10-22 7:53 [PATCH v6 00/15] f2fs: support & optimize large folios for writable files Nanzhe Zhao
` (13 preceding siblings ...)
2026-10-22 7:53 ` [PATCH v6 14/15] f2fs: allow large folio support to writeable files Nanzhe Zhao
@ 2026-10-22 7:53 ` Nanzhe Zhao
2026-10-23 0:55 ` [PATCH v6 00/15] f2fs: support & optimize large folios for writable files Chao Yu
15 siblings, 0 replies; 17+ messages in thread
From: Nanzhe Zhao @ 2026-10-22 7:53 UTC (permalink / raw)
To: linux-f2fs-devel, Jaegeuk Kim, Chao Yu
Cc: Barry Song, Juan Yescas, Daeho Jeong, Pengfei Li, Dev Jain,
David Hildenbrand, linux-kernel, Bo Zhang, Kalesh Singh,
Nanzhe Zhao, Nanzhe Zhao, Ryan Roberts
From: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
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 55798421f2c4..b79bb67ee78e 100644
--- a/Documentation/filesystems/f2fs.rst
+++ b/Documentation/filesystems/f2fs.rst
@@ -942,6 +942,16 @@ 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 162bd8ef822a..721b01dd0d24 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 2338450ce031..c5728fe28370 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -3266,12 +3266,6 @@ 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)
@@ -5286,7 +5280,8 @@ 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 3d621a20766d..e61c80ae7537 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -5021,6 +5021,13 @@ 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
^ permalink raw reply [flat|nested] 17+ messages in thread* Re: [PATCH v6 00/15] f2fs: support & optimize large folios for writable files
2026-10-22 7:53 [PATCH v6 00/15] f2fs: support & optimize large folios for writable files Nanzhe Zhao
` (14 preceding siblings ...)
2026-10-22 7:53 ` [PATCH v6 15/15] f2fs: make compressed files compatible with large folio Nanzhe Zhao
@ 2026-10-23 0:55 ` Chao Yu
15 siblings, 0 replies; 17+ messages in thread
From: Chao Yu @ 2026-10-23 0:55 UTC (permalink / raw)
To: Nanzhe Zhao, linux-f2fs-devel, Jaegeuk Kim
Cc: chao, Barry Song, Juan Yescas, Daeho Jeong, Pengfei Li, Dev Jain,
David Hildenbrand, linux-kernel, Bo Zhang, Kalesh Singh,
Nanzhe Zhao, Nanzhe Zhao, Ryan Roberts
Nanzhe,
FYI, this is from my local sashiko, please take a look to see if there is any
valid review comment.
Patch 1: f2fs: extend folio state for large folio write path
Result:
Critical: 1 · High: 0 · Medium: 0 · Low: 0
Reviewed
▼ Inline Review
Copy
commit 8845b499928f22b0f7dcf2d87614719b304cb8d8
Author: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
f2fs: extend folio state for large folio write path
Large folio write path needs a subpage status bitmap and write pages
pending counter, while keeping compatible with f2fs private flags.
This patch moves struct f2fs_folio_state to f2fs.h and updates
PAGE_PRIVATE functions to be compatible with it.
> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
> index e9f8b31d5dab..c4778e5f5925 100644
> --- a/fs/f2fs/f2fs.h
> +++ b/fs/f2fs/f2fs.h
[ ... ]
> @@ -1629,6 +1641,13 @@ 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;
> +}
> +
Should this check also exclude the PAGE_PRIVATE_NOT_POINTER bit?
If a large folio has no ffs structure attached, but has an integer stored in
folio->private with the PAGE_PRIVATE_NOT_POINTER bit set, this function will
incorrectly return true.
[ ... ]
> @@ -2769,13 +2788,35 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,
[ ... ]
> +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;
> +}
> +
If f2fs_folio_has_ffs() returns true because an integer with the
PAGE_PRIVATE_NOT_POINTER bit is stored in folio->private, does this code cast
that raw integer into a struct f2fs_folio_state pointer?
This would return an invalid out-of-bounds address for the private_flags
field, leading to a crash when it gets dereferenced.
[ ... ]
> @@ -2787,14 +2828,10 @@ 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) \
> { \
Can this sequence trigger an invalid pointer dereference and a kernel panic?
If PAGE_PRIVATE_SET_FUNC (e.g., folio_set_f2fs_gcing) is called on a large
folio without an ffs structure:
1. folio->private is set to BIT(PAGE_PRIVATE_NOT_POINTER) (which is 1).
2. f2fs_folio_flags_addr() is called.
3. f2fs_folio_has_ffs() sees folio_test_large() and private != 0, returning
true.
4. f2fs_folio_flags_addr() casts the integer 1 to a struct f2fs_folio_state
pointer, returning a memory address based off this invalid pointer.
5. set_bit() attempts to write to this invalid unmapped memory address.
To: None Cc: None Status: Disabled (SMTP not configured)
Tokens used: In: 1376k · Cached: 7798k · Out: 22k
View Review Map·View Raw Log
↑ Back to Summary
Patch 2: f2fs: carry subpage offset and count in write IO
Result:
No regressions
Reviewed
▶ Inline Review
To: None Cc: None Status: Disabled (SMTP not configured)
Tokens used: In: 1891k · Cached: 28375k · Out: 43k
View Review Map·View Raw Log
↑ Back to Summary
Patch 3: f2fs: support regular file buffered writes on large folios
Result:
Critical: 0 · High: 2 · Medium: 0 · Low: 0
Reviewed
▼ Inline Review
Copy
commit 0f231c7061b3be0f1eb6bb222db57bfbcdc48ecb
Author: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
f2fs: support regular file buffered writes on large folios
This commit introduces large folio support for f2fs regular buffered
writes. It preallocates partial blocks for inodes that use large folios
to avoid complex unlocking during write_begin. During write_begin, it
only reads the partial head and tail 4K subpages that require
read-before-write.
> diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
> --- a/fs/f2fs/data.c
> +++ b/fs/f2fs/data.c
[ ... ]
> @@ -4158,6 +4335,151 @@ static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi,
[ ... ]
> +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;
> +
> + /*
> + * when the write did not come through f2fs_write_iter, we preallocate all
> + * blocks in the write range here.
> + */
> + if (!is_inode_flag_set(inode, FI_PREALLOCATED_ALL) &&
> + !IS_DEVICE_ALIASING(inode)) {
> + pgoff_t first = F2FS_BYTES_TO_BLK(sbi, pos);
> + pgoff_t last = F2FS_BLK_ALIGN(sbi, pos + len);
> + pgoff_t idx;
> +
> + for (idx = first; idx < last; idx++) {
> + block_t blkaddr = NULL_ADDR;
> + bool node_changed = false;
> +
> + err = __reserve_data_block(inode, idx, &blkaddr,
> + &node_changed);
> + if (err)
> + return err;
> + if (f2fs_balance_fs_folio_locked(folio, folio->mapping,
> + node_changed))
> + return -EAGAIN;
> + }
> + }
[ ... ]
> + /*
> + * The read extent cache only validates the first and last
> + * block of i_ext, so check both the cached and dnode paths.
> + */
> + if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
> + DATA_GENERIC_ENHANCE_READ))
> + return -EFSCORRUPTED;
Can this result in a spurious -EFSCORRUPTED error during a direct I/O
fallback?
In f2fs_preallocate_blocks(), FI_PREALLOCATED_ALL is set unconditionally
when f2fs_map_blocks() returns 0. However, for direct I/O, the allocation
exits early on physically unmergeable extents, meaning map.m_len might be
smaller than requested.
If a partial direct I/O write falls back to buffered I/O via
f2fs_buffered_write_iter(), this new prepare_large_folio_write_begin()
path will see FI_PREALLOCATED_ALL and skip block reservation for the
unallocated tail.
Will reading the unallocated hole then yield a NULL_ADDR and trigger the
-EFSCORRUPTED failure here?
[ ... ]
> @@ -4395,8 +4744,22 @@ 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)) {
Does this miss updating the ffs dirty bitmap for large folios modified via
external paths like get_user_pages?
Modifications made to an mmapped f2fs large folio via external subsystems
(like direct I/O or device DMA using get_user_pages) call
folio_mark_dirty() when unpinning. This triggers f2fs_dirty_data_folio()
which sets the generic PG_dirty flag.
However, because the subpages are not marked dirty in the ffs bitmap,
when writeback later runs f2fs_write_cache_folios(), it relies on
ffs_find_dirty_range(). If the ffs dirty bitmap is empty, it appears the
loop will skip the I/O entirely and discard the data.
Should we be updating the ffs dirty bitmap here after a successful
filemap_dirty_folio() for large folios?
To: None Cc: None Status: Disabled (SMTP not configured)
Tokens used: In: 1542k · Cached: 14448k · Out: 36k
View Review Map·View Raw Log
↑ Back to Summary
Patch 4: f2fs: support atomic file large folios buffered write
Result:
Critical: 0 · High: 0 · Medium: 1 · Low: 0
Reviewed
▼ Inline Review
Copy
commit 53688cad23a91b76f64efcd823a6c489381ac485
Author: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
f2fs: support atomic file large folios buffered write
This commit adds support for large folio buffered writes to f2fs atomic files.
It introduces a helper to reserve COW mappings for the write range and handle
partial head and tail subpages.
> diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
> --- a/fs/f2fs/data.c
> +++ b/fs/f2fs/data.c
[ ... ]
> @@ -4480,6 +4478,61 @@ static int prepare_large_folio_write_begin(struct inode *inode,
> +static int prepare_large_folio_atomic_write_begin(struct inode *inode,
> + struct address_space *mapping, struct folio *folio, loff_t pos,
> + unsigned int len)
> +{
[ ... ]
> + 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;
[ ... ]
> +balance:
> + if (f2fs_balance_fs_folio_locked(folio, mapping, node_changed))
> + return -EAGAIN;
Can returning -EAGAIN here cause atomic write counts to be double counted for
prior subpages?
If f2fs_balance_fs_folio_locked() requires balance, it returns -EAGAIN. This
causes the outer loop in f2fs_write_begin() to restart the folio preparation,
which re-runs prepare_large_folio_atomic_write_begin() starting from the
first subpage.
On this retry, prepare_atomic_write_begin() will be called again for subpages
that have already been processed. For append writes, the COW lookup is skipped
and it goes straight to block reservation:
fs/f2fs/data.c:prepare_atomic_write_begin() {
...
if (((loff_t)index << PAGE_SHIFT) >= i_size_read(inode))
goto reserve_block;
...
reserve_block:
if (!cow_has_reserved_block) {
err = __reserve_data_block(...);
...
inc_atomic_write_cnt(inode);
}
}
Because cow_has_reserved_block defaults to false and the COW lookup was
skipped, inc_atomic_write_cnt() will be incremented a second time for every
subpage already processed before the abort. Could this corrupt the atomic
write statistics?
> + }
> +
> + return 0;
> +}
To: None Cc: None Status: Disabled (SMTP not configured)
Tokens used: In: 1041k · Cached: 12285k · Out: 31k
View Review Map·View Raw Log
↑ Back to Summary
Patch 5: f2fs: support large folio writeback
Result:
Critical: 0 · High: 3 · Medium: 0 · Low: 0
Reviewed
▼ Inline Review
Copy
commit 5beb2c47fdab941c94ce2dbf16d7119ff73077df
Author: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
f2fs: support large folio writeback
This commit adds a folio-based writeback path for large-folio mapping files
to handle multiple dirty ranges within a large folio. It introduces
f2fs_write_cache_folios() for large folios while keeping the legacy
f2fs_write_cache_pages() path for non-large-folio files.
> diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
> index e3d6e3087bb9..74583f0f1833 100644
> --- a/fs/f2fs/data.c
> +++ b/fs/f2fs/data.c
[ ... ]
> @@ -358,6 +358,49 @@ static void f2fs_cache_write_end_bio(struct bio *bio)
> bio_put(bio);
> }
>
> +static bool f2fs_ffs_has_dirty_subpage(struct folio *folio)
[ ... ]
> +static void f2fs_ffs_put_write_pending(struct folio *folio, unsigned int nr)
> +{
> + struct f2fs_folio_state *ffs;
> +
> + if (!f2fs_folio_has_ffs(folio))
> + goto release;
> +
> + ffs = (struct f2fs_folio_state *)folio->private;
> + if (!atomic_sub_and_test(nr, &ffs->write_pages_pending))
> + return;
> +release:
> + if (!f2fs_ffs_has_dirty_subpage(folio))
> + folio_clear_f2fs_gcing(folio);
> + if (folio_test_writeback(folio))
> + folio_end_writeback(folio);
> +}
Does this prematurely end writeback for the entire large folio when it lacks FFS
state?
If a large folio is dirtied without an attached f2fs_folio_state (FFS), it
bypasses the write_pages_pending reference counter during background writeback.
When the first I/O block completes, f2fs_ffs_put_write_pending() will
immediately call folio_end_writeback(). This clears the page cache writeback
state while other blocks from the same folio might still be undergoing active
DMA, which could lead to data corruption or a use-after-free if the page
cache frees the folio or userspace modifies it.
A Time-Of-Check to Time-Of-Use (TOCTOU) race exists when retrieving a folio
using f2fs_get_lock_data_folio(). It calls f2fs_get_read_data_folio(), which
allocates FFS but then unlocks the folio if it is already up-to-date. Before
f2fs_get_lock_data_folio() re-acquires the lock, a concurrent memory reclaim
can call f2fs_release_folio() on the clean folio, freeing its FFS state. Once
successfully re-locked, callers like move_data_page() or
truncate_partial_data_page() dirty the folio, silently falling back to
folio_mark_dirty() and inserting a dirty large folio without FFS into the
writeback path.
[ ... ]
> @@ -3523,6 +3668,144 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
> return err;
> }
>
> +static int f2fs_write_folio_dirty_range(struct folio *folio, int *submitted,
> + struct writeback_control *wbc,
> + enum iostat_type io_type,
> + u64 *pos, u64 len)
> +{
[ ... ]
> + 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;
> + }
Can this crash the kernel via f2fs_bug_on() due to a missing NULL_ADDR check?
When f2fs_get_dnode_of_data() returns the dnode for a punched hole block, its
data_blkaddr is NULL_ADDR. This code assigns it to fio.old_blkaddr but
fails to check if fio.old_blkaddr is NULL_ADDR before unconditionally calling
f2fs_outplace_write_data().
The legacy f2fs_do_write_data_page() checks if the old block address is
NULL_ADDR to cleanly skip subpages that were hole-punched after being dirtied.
Without that check here, f2fs_outplace_write_data() will hit this assertion
and panic the kernel:
f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR);
This could be triggered by overlapping mmap writes and fallocate hole punches.
[ ... ]
> @@ -3972,6 +4255,226 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
> return ret;
> }
>
> +static int f2fs_write_cache_folios(struct address_space *mapping,
[ ... ]
> + /*
> + * Large folios can be submitted as multiple bios, which may
> + * complete while we are still submitting the remaining dirty
> + * ranges. Hold a bias on write_pages_pending to prevent
> + * folio_end_writeback() from being called early.
> + */
> + 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;
> + }
If a large folio lacks FFS state (for instance, due to the reclaim race
mentioned above), this path skips incrementing the write_pages_pending bias
but will still loop over and submit I/O for all blocks in the folio. This
directly contributes to the premature writeback completion issue.
[ ... ]
> +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), or if the writeback failed, 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)) || err)
> + folio_redirty_for_writepage(wbc, folio);
Does this logic trap the worker in an infinite writeback loop on truncated or
hole-punched large folios?
If a hole is punched, f2fs_get_dnode_of_data() returns -ENOENT, which is
propagated up to f2fs_write_cache_folios() as err. The || err condition
evaluates to true and unconditionally redirties the folio, causing it to be
retried endlessly.
Similarly, if the file is truncated such that the EOF splits the folio,
end_pos is clamped to isize. f2fs_ffs_clear_subrange_dirty_and_test() will
clear bits from 0 to end_pos, skipping the subpages beyond EOF. Because
those dirty bits remain, it returns true, which also triggers
folio_redirty_for_writepage() and leaves the folio dirty permanently.
To: None Cc: None Status: Disabled (SMTP not configured)
Tokens used: In: 1211k · Cached: 11018k · Out: 26k
View Review Map·View Raw Log
↑ Back to Summary
Patch 6: f2fs: account large folio dirty data at block granularity
Result:
No regressions
Reviewed
▶ Inline Review
To: None Cc: None Status: Disabled (SMTP not configured)
Tokens used: In: 698k · Cached: 5473k · Out: 14k
View Review Map·View Raw Log
↑ Back to Summary
Patch 7: f2fs: prepare mmap write faults for large folios
Result:
No regressions
Reviewed
▶ Inline Review
To: None Cc: None Status: Disabled (SMTP not configured)
Tokens used: In: 1435k · Cached: 6126k · Out: 20k
View Review Map·View Raw Log
↑ Back to Summary
Patch 8: f2fs: make GC migration large-folio aware
Result:
Critical: 0 · High: 0 · Medium: 1 · Low: 0
Reviewed
▼ Inline Review
Copy
commit 69c900aae91680bd5f0dda56fae4dc1617abe3a5
Author: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
f2fs: make GC migration large-folio aware
This patch makes garbage collection migration large-folio aware by updating
data lookup helpers to test and update uptodate state for the addressed
subpage. It also modifies move_data_page() to track dirty state per subpage
and delegates write_pages_pending tracking and cleanup to
f2fs_do_write_data_page().
Link: https://lore.kernel.org/oe-lkp/202610081027.b13dcf10-lkp@intel.com
> diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
> index f415c3eb4e78..5671395130b2 100644
> --- a/fs/f2fs/data.c
> +++ b/fs/f2fs/data.c
[ ... ]
> @@ -3684,6 +3706,13 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
> out:
> if (fio->need_lock == LOCK_REQ)
> f2fs_unlock_op(fio->sbi, &lc);
> + if (!submitted) {
> + if (pending_added) {
> + f2fs_ffs_put_write_pending(folio, 1);
> + } else if (!f2fs_ffs_has_dirty_subpage(folio)) {
> + folio_clear_f2fs_gcing(folio);
> + }
> + }
> return err;
> }
>
> diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
> index 8e80e857e220..04ed3d37c237 100644
> --- a/fs/f2fs/gc.c
> +++ b/fs/f2fs/gc.c
[ ... ]
> @@ -1552,33 +1561,43 @@ static int move_data_page(struct inode *inode, block_t bidx, int gc_type,
[ ... ]
> folio_set_f2fs_gcing(folio);
>
> err = f2fs_do_write_data_page(&fio);
> if (err) {
> - folio_clear_f2fs_gcing(folio);
> if (err == -ENOMEM) {
> memalloc_retry_wait(GFP_NOFS);
> goto retry;
> }
Is there a regression here where f2fs_do_write_data_page() bypasses the
newly added cleanup code on early errors, leaking the PG_f2fs_gcing flag on
the folio?
The removed cleanup relies on f2fs_do_write_data_page() performing it at the
out label added above, but f2fs_do_write_data_page() can return directly
without reaching that label. For example, it might fail on lock acquisition:
/* Deadlock due to between page->lock and f2fs_lock_op */
if (fio->need_lock == LOCK_REQ && !f2fs_trylock_op(fio->sbi, &lc))
return -EAGAIN;
Could the folio permanently retain the PG_f2fs_gcing flag since the
caller-side cleanup was removed?
> - if (is_dirty)
> + if (is_dirty) {
> + if (large)
> + f2fs_ffs_mark_subrange_dirty(folio, foff, PAGE_SIZE);
> folio_mark_dirty(folio);
> + }
> }
> }
To: None Cc: None Status: Disabled (SMTP not configured)
Tokens used: In: 1183k · Cached: 20602k · Out: 37k
View Review Map·View Raw Log
↑ Back to Summary
Patch 9: f2fs: optimize small block size large folio read
Result:
No regressions
Reviewed
▶ Inline Review
To: None Cc: None Status: Disabled (SMTP not configured)
Tokens used: In: 886k · Cached: 7605k · Out: 20k
View Review Map·View Raw Log
↑ Back to Summary
Patch 10: f2fs: support partial uptodate large folio read
Result:
No regressions
Reviewed
▶ Inline Review
To: None Cc: None Status: Disabled (SMTP not configured)
Tokens used: In: 613k · Cached: 1023k · Out: 12k
View Review Map·View Raw Log
↑ Back to Summary
Patch 11: f2fs: handle partial truncate of large folio dirty subpages
Result:
No regressions
Reviewed
▶ Inline Review
To: None Cc: None Status: Disabled (SMTP not configured)
Tokens used: In: 1417k · Cached: 16831k · Out: 28k
View Review Map·View Raw Log
↑ Back to Summary
Patch 12: f2fs: fix zeroing paths for large folios
Result:
Critical: 0 · High: 1 · Medium: 0 · Low: 0
Reviewed
▼ Inline Review
Copy
commit 506953384e1ed7cc966a73a775ee46b38f01377e
Author: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
f2fs: fix zeroing paths for large folios
This commit updates several f2fs zeroing paths to use folio offsets instead
of PAGE_SIZE based offsets to properly handle large folios.
> diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
> index 808b72d3d78a..439e84a4aec3 100644
> --- a/fs/f2fs/file.c
> +++ b/fs/f2fs/file.c
[ ... ]
> @@ -856,12 +857,22 @@ 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, true, true);
> - folio_zero_segment(folio, offset, folio_size(folio));
> + folio_off = offset_in_folio(folio, from);
Does this code skip zeroing valid subpages of partially up-to-date large
folios?
Just above this hunk in truncate_partial_data_page(), the cache_only block
checks the uptodate status of the folio:
if (cache_only) {
folio = filemap_lock_folio(mapping, index);
if (IS_ERR(folio))
return 0;
if (folio_test_uptodate(folio))
goto truncate_out;
f2fs_folio_put(folio, true);
return 0;
}
For large folios, folio_test_uptodate() returns true only if the entire
folio is up-to-date. If the folio is only partially up-to-date, but the
specific subpage being truncated is valid, this check returns false.
This causes the function to exit without jumping to truncate_out,
skipping the zeroing and leaking stale pre-truncation data in the page
cache.
Should this check be converted to f2fs_ffs_test_blk_uptodate(folio, index)
to match the changes made in f2fs_get_new_data_folio()?
> + blk_end = min_t(size_t, round_up(folio_off, PAGE_SIZE),
> + folio_size(folio));
> + folio_zero_segment(folio, folio_off, blk_end);
To: None Cc: None Status: Disabled (SMTP not configured)
Tokens used: In: 1446k · Cached: 13715k · Out: 21k
View Review Map·View Raw Log
↑ Back to Summary
Patch 13: f2fs: handle block cloning within the same large folio
Result:
Critical: 0 · High: 1 · Medium: 0 · Low: 0
Reviewed
▼ Inline Review
Copy
commit e71bedd5f33b6f06c04e1ac6a7f0f828fabd0fc0
Author: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
f2fs: handle block cloning within the same large folio
This commit modifies __clone_blkaddrs() to correctly handle block cloning
when source and destination blocks belong to the same large folio. It
detects the same-folio case and explicitly reserves the destination block
to avoid self-deadlocks.
> diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
> index 439e84a4aec3..f621d5e65023 100644
> --- a/fs/f2fs/file.c
> +++ b/fs/f2fs/file.c
[ ... ]
> @@ -1598,25 +1598,70 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
> f2fs_put_dnode(&dn);
> } else {
> struct folio *fsrc, *fdst;
[ ... ]
> + 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);
[ ... ]
> f2fs_folio_wait_writeback(fdst, 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;
> + }
Does returning -ENOMEM here leave the page cache corrupted?
Before this check, memcpy_folio() has already copied the data into the
destination folio. If f2fs_ffs_find_or_alloc() fails and we return -ENOMEM,
the page cache modification is not reverted.
If the cloning operation is aborted, would userspace read the incorrectly
modified page cache? Could this corrupted data also be persisted to disk if
the folio is later dirtied?
Additionally, when same_folio is true, the block reserved earlier with
f2fs_reserve_block() does not appear to be reverted on this error path.
> + f2fs_ffs_mark_subrange_uptodate(fdst,
> + dst_off, PAGE_SIZE);
> + f2fs_ffs_mark_subrange_dirty(fdst, dst_off,
> + PAGE_SIZE);
> + }
> folio_mark_dirty(fdst);
To: None Cc: None Status: Disabled (SMTP not configured)
Tokens used: In: 418k · Cached: 3283k · Out: 15k
View Review Map·View Raw Log
↑ Back to Summary
Patch 14: f2fs: allow large folio support to writeable files
Result:
Critical: 0 · High: 1 · Medium: 1 · Low: 0
Reviewed
▼ Inline Review
Copy
commit 2533e48a3606c7c0d5518871039a69a5277636bd
Author: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
f2fs: allow large folio support to writeable files
This commit enables large folio mappings for writable files in f2fs by removing
runtime restrictions. It attempts to restrict them using an IS_IMMUTABLE check
at inode initialization as a transitional safety measure.
> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
> index d0297730c07f..288edc1a688f 100644
> --- a/fs/f2fs/f2fs.h
> +++ b/fs/f2fs/f2fs.h
[ ... ]
> @@ -5358,6 +5358,23 @@ 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);
Can this check be bypassed using FS_IOC_SETFLAGS?
If a user creates a file, sets it immutable (chattr +i), and drops caches to
force an inode reload, the mapping is configured with MAX_PAGECACHE_ORDER. The
user can then clear the immutable flag (chattr -i).
Since f2fs_setflags_common() clears S_IMMUTABLE but does not downgrade the VFS
mapping limits, this now-mutable file can be opened for writing and populate
the page cache with large folios.
> + else
> + mapping_set_folio_order_range(inode->i_mapping, 0, 0);
> +}
> diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
> index f621d5e65023..3d621a20766d 100644
> --- a/fs/f2fs/file.c
> +++ b/fs/f2fs/file.c
> @@ -163,17 +163,8 @@ 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));
> + if (unlikely(IS_IMMUTABLE(inode)))
> return VM_FAULT_SIGBUS;
> - }
Because this patch removes the runtime mapping_large_folio_support() safety
checks here (and in f2fs_file_open and f2fs_setattr), the folios from the
bypass described above will enter the unaudited write paths.
Does this cause O(N^2) complexity and massive stat inflation for large folios?
When a large folio is mapped into a writable VMA, the core MM generates page
faults for each 4KB subpage independently. In f2fs_vm_page_mkwrite(), the code
calculates dirty_len as the size of the entire valid portion of the folio up
to EOF, rather than the size of the faulting subpage.
It then loops over all blocks in the folio:
for (i = 0; i < nr; i++) {
err = f2fs_get_block_mkwrite(inode, folio, folio->index + i,
need_alloc);
and increments the IO stats by the full folio size:
f2fs_update_iostat(sbi, inode, APP_MAPPED_IO, dirty_len);
For a 2MB large folio, sequentially writing to all 512 subpages will trigger
this page fault handler 512 times. Each invocation processes all 512 blocks
and increments the IO stats by 2MB, resulting in 262,144 block iterations and
a 1GB inflation to APP_MAPPED_IO.
To: None Cc: None Status: Disabled (SMTP not configured)
Tokens used: In: 1573k · Cached: 22463k · Out: 34k
View Review Map·View Raw Log
↑ Back to Summary
Patch 15: f2fs: make compressed files compatible with large folio
Result:
No regressions
Reviewed
▶ Inline Review
To: None Cc: None Status: Disabled (SMTP not configured)
Tokens used: In: 743k · Cached: 15590k · Out: 28k
View Review Map·View Raw Log
↑ Back to Summary
^ permalink raw reply [flat|nested] 17+ messages in thread