From: Nanzhe Zhao <nzzhao.sigma@gmail.com>
To: linux-f2fs-devel@lists.sourceforge.net,
Jaegeuk Kim <jaegeuk@kernel.org>, Chao Yu <chao@kernel.org>
Cc: Barry Song <baohua@kernel.org>, Juan Yescas <jyescas@google.com>,
Daeho Jeong <daehojeong@google.com>,
Pengfei Li <lipengfei28@xiaomi.com>, Dev Jain <Dev.Jain@arm.com>,
David Hildenbrand <David.Hildenbrand@arm.com>,
linux-kernel@vger.kernel.org, Bo Zhang <zhangbo56@xiaomi.com>,
Kalesh Singh <kaleshsingh@google.com>,
Nanzhe Zhao <nzzhao@126.com>, Nanzhe Zhao <zhaonanzhe@xiaomi.com>,
Ryan Roberts <Ryan.Roberts@arm.com>
Subject: [PATCH v6 01/15] f2fs: extend folio state for large folio write path
Date: Thu, 22 Oct 2026 15:53:28 +0800 [thread overview]
Message-ID: <20261022075343.3043003-2-nzzhao.sigma@gmail.com> (raw)
In-Reply-To: <20261022075343.3043003-1-nzzhao.sigma@gmail.com>
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
next prev parent reply other threads:[~2026-10-22 7:53 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
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 [this message]
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 ` [PATCH v6 03/15] f2fs: support regular file buffered writes on large folios Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 04/15] f2fs: support atomic file large folios buffered write Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 05/15] f2fs: support large folio writeback Nanzhe Zhao
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 ` [PATCH v6 07/15] f2fs: prepare mmap write faults for large folios Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 08/15] f2fs: make GC migration large-folio aware Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 09/15] f2fs: optimize small block size large folio read Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 10/15] f2fs: support partial uptodate " Nanzhe Zhao
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 ` [PATCH v6 12/15] f2fs: fix zeroing paths for large folios Nanzhe Zhao
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 ` [PATCH v6 14/15] f2fs: allow large folio support to writeable files Nanzhe Zhao
2026-10-22 7:53 ` [PATCH v6 15/15] f2fs: make compressed files compatible with large folio Nanzhe Zhao
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20261022075343.3043003-2-nzzhao.sigma@gmail.com \
--to=nzzhao.sigma@gmail.com \
--cc=David.Hildenbrand@arm.com \
--cc=Dev.Jain@arm.com \
--cc=Ryan.Roberts@arm.com \
--cc=baohua@kernel.org \
--cc=chao@kernel.org \
--cc=daehojeong@google.com \
--cc=jaegeuk@kernel.org \
--cc=jyescas@google.com \
--cc=kaleshsingh@google.com \
--cc=linux-f2fs-devel@lists.sourceforge.net \
--cc=linux-kernel@vger.kernel.org \
--cc=lipengfei28@xiaomi.com \
--cc=nzzhao@126.com \
--cc=zhangbo56@xiaomi.com \
--cc=zhaonanzhe@xiaomi.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®