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>,
Nanzhe Zhao <zhaonanzhe@xiaomi.com>,
Juan Yescas <jyescas@google.com>,
Daeho Jeong <daehojeong@google.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>, Pengfei Li <lipengfei28@xiaomi.com>,
Ryan Roberts <Ryan.Roberts@arm.com>
Subject: [PATCH v4 08/18] f2fs: account large folio dirty data at block granularity
Date: Tue, 13 Oct 2026 19:56:11 +0800 [thread overview]
Message-ID: <20261013115621.968742-9-nzzhao.sigma@gmail.com> (raw)
In-Reply-To: <20261013115621.968742-1-nzzhao.sigma@gmail.com>
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 | 37 +++++++++++++++++++------
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, 117 insertions(+), 35 deletions(-)
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 81c1c2de9..27ea41d7f 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -1316,20 +1316,46 @@ 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 0719a0e1e..3d26bdd4d 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -1067,7 +1067,7 @@ static void cancel_cluster_writeback(struct compress_ctx *cc,
struct folio *folio = page_folio(cc->rpages[i]);
if (i < submitted) {
- inode_inc_dirty_pages(cc->inode);
+ inode_inc_dirty_block(cc->inode);
folio_lock(folio);
}
folio_clear_f2fs_gcing(folio);
@@ -1415,7 +1415,7 @@ 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 be182b9e8..f994a31f8 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -2897,10 +2897,18 @@ 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));
@@ -2911,21 +2919,27 @@ 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;
}
@@ -2937,13 +2951,15 @@ 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))
@@ -2951,9 +2967,12 @@ 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;
}
@@ -3854,7 +3873,7 @@ 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);
@@ -4330,8 +4349,8 @@ 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)))
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
@@ -5160,7 +5179,7 @@ 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 97f7fef6b..70847313c 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 f1a37e4fd..e5c1d6a65 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -2895,9 +2895,10 @@ 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 ||
@@ -2907,31 +2908,66 @@ 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)
@@ -4359,6 +4395,7 @@ 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 89e50f871..d7fae1890 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -1555,7 +1555,7 @@ 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 ab7537ff7..49905aa08 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 be14dfa31..277c12922 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1677,7 +1677,7 @@ 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
next prev parent reply other threads:[~2026-10-13 11:57 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-13 11:56 [PATCH v4 00/18] f2fs: support & optimize large folios for writable files Nanzhe Zhao
2026-10-13 11:56 ` [PATCH v4 01/18] f2fs: read i_size once in f2fs_vm_page_mkwrite Nanzhe Zhao
2026-10-13 11:56 ` [PATCH v4 02/18] f2fs: remove mappedtodisk flag usage in mmap write path Nanzhe Zhao
2026-10-13 11:56 ` [PATCH v4 03/18] f2fs: extend folio state for large folio " Nanzhe Zhao
2026-10-13 11:56 ` [PATCH v4 04/18] f2fs: carry subpage offset and count in write IO Nanzhe Zhao
2026-10-13 11:56 ` [PATCH v4 05/18] f2fs: support regular file buffered writes on large folios Nanzhe Zhao
2026-10-13 11:56 ` [PATCH v4 06/18] f2fs: support atomic file large folios buffered write Nanzhe Zhao
2026-10-13 11:56 ` [PATCH v4 07/18] f2fs: support large folio writeback Nanzhe Zhao
2026-10-13 11:56 ` Nanzhe Zhao [this message]
2026-10-13 11:56 ` [PATCH v4 09/18] f2fs: prepare mmap write faults for large folios Nanzhe Zhao
2026-10-13 11:56 ` [PATCH v4 10/18] f2fs: make GC migration large-folio aware Nanzhe Zhao
2026-10-13 11:56 ` [PATCH v4 11/18] f2fs: optimize small block size large folio read Nanzhe Zhao
2026-10-13 11:56 ` [PATCH v4 12/18] f2fs: support partial uptodate " Nanzhe Zhao
2026-10-13 11:56 ` [PATCH v4 13/18] f2fs: handle partial truncate of large folio dirty subpages Nanzhe Zhao
2026-10-13 11:56 ` [PATCH v4 14/18] f2fs: wait for folio writeback before ffs_detach_free Nanzhe Zhao
2026-10-13 11:56 ` [PATCH v4 15/18] f2fs: fix zeroing paths for large folios Nanzhe Zhao
2026-10-13 11:56 ` [PATCH v4 16/18] f2fs: handle block cloning within the same large folio Nanzhe Zhao
2026-10-13 11:56 ` [PATCH v4 17/18] f2fs: allow large folio support to writeable files Nanzhe Zhao
2026-10-13 11:56 ` [PATCH v4 18/18] f2fs: make compressed files compatible with large folio Nanzhe Zhao
2026-10-13 18:46 ` [f2fs-dev] [PATCH v4 00/18] f2fs: support & optimize large folios for writable files Jaegeuk Kim
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=20261013115621.968742-9-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®