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 10/18] f2fs: make GC migration large-folio aware
Date: Tue, 13 Oct 2026 19:56:13 +0800 [thread overview]
Message-ID: <20261013115621.968742-11-nzzhao.sigma@gmail.com> (raw)
In-Reply-To: <20261013115621.968742-1-nzzhao.sigma@gmail.com>
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(), f2fs_find_data_folio(), and
f2fs_get_lock_data_folio() to use subpage uptodate state. Submit
single-block reads at the requested folio offset and zero only the
addressed 4K range for NEW_ADDR.
Also update `move_data_page` to mark, clear, and restore dirty
state for the target subpage, and submit write I/O with the subpage
offset recorded in f2fs_io_info.
Signed-off-by: Nanzhe Zhao <zhaonanzhe@xiaomi.com>
---
fs/f2fs/data.c | 71 ++++++++++++++++++++++++++++++++------------------
fs/f2fs/f2fs.h | 1 +
fs/f2fs/gc.c | 36 ++++++++++++++++++++++---
3 files changed, 79 insertions(+), 29 deletions(-)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index d158c343f..4484f65fd 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1455,19 +1455,26 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode,
/* This can handle encryption stuffs */
static void f2fs_submit_page_read(struct inode *inode, struct fsverity_info *vi,
- struct folio *folio, block_t blkaddr,
- blk_opf_t op_flags, bool for_write)
+ struct folio *folio, pgoff_t index,
+ block_t blkaddr, blk_opf_t op_flags,
+ bool for_write)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct bio *bio;
+ size_t offset = 0;
- bio = f2fs_grab_read_bio(inode, vi, blkaddr, 1, op_flags, folio->index,
+ if (f2fs_folio_has_ffs(folio)) {
+ offset = offset_in_folio(folio, (loff_t)index << PAGE_SHIFT);
+ f2fs_update_read_folio_pending(folio, 1);
+ }
+
+ bio = f2fs_grab_read_bio(inode, vi, blkaddr, 1, op_flags, index,
for_write);
/* wait for GCed page writeback via 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);
@@ -1609,20 +1616,16 @@ 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,
@@ -1658,7 +1661,7 @@ 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;
}
@@ -1671,15 +1674,17 @@ struct folio *f2fs_get_read_data_folio(struct inode *inode, pgoff_t index,
* f2fs_init_inode_metadata.
*/
if (dn.data_blkaddr == NEW_ADDR) {
- folio_zero_segment(folio, 0, folio_size(folio));
- if (!folio_test_uptodate(folio))
- folio_mark_uptodate(folio);
+ size_t offset = offset_in_folio(folio,
+ (loff_t)index << PAGE_SHIFT);
+
+ folio_zero_segment(folio, offset, offset + PAGE_SIZE);
+ f2fs_ffs_mark_subrange_uptodate(folio, offset, PAGE_SIZE);
folio_unlock(folio);
return folio;
}
- f2fs_submit_page_read(inode, f2fs_need_verity(inode, folio->index),
- folio, dn.data_blkaddr, op_flags, for_write);
+ f2fs_submit_page_read(inode, f2fs_need_verity(inode, index),
+ folio, index, dn.data_blkaddr, op_flags, for_write);
return folio;
put_err:
@@ -1696,7 +1701,7 @@ struct folio *f2fs_find_data_folio(struct inode *inode, pgoff_t index,
folio = f2fs_filemap_get_folio(mapping, index, FGP_ACCESSED, 0);
if (IS_ERR(folio))
goto read;
- if (folio_test_uptodate(folio))
+ if (f2fs_ffs_test_blk_uptodate(folio, index))
return folio;
f2fs_folio_put(folio, false);
@@ -1705,11 +1710,11 @@ struct folio *f2fs_find_data_folio(struct inode *inode, pgoff_t index,
if (IS_ERR(folio))
return folio;
- if (folio_test_uptodate(folio))
+ if (f2fs_ffs_test_blk_uptodate(folio, index))
return folio;
folio_wait_locked(folio);
- if (unlikely(!folio_test_uptodate(folio))) {
+ if (unlikely(!f2fs_ffs_test_blk_uptodate(folio, index))) {
f2fs_folio_put(folio, false);
return ERR_PTR(-EIO);
}
@@ -1733,7 +1738,8 @@ 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);
}
@@ -2913,6 +2919,22 @@ 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)
{
@@ -3006,7 +3028,6 @@ 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)
@@ -5115,7 +5136,7 @@ static int f2fs_write_begin(const struct kiocb *iocb,
*/
f2fs_submit_page_read(inode,
NULL, /* can't write to fsverity files */
- folio, blkaddr, 0, true);
+ folio, index, blkaddr, 0, true);
folio_lock(folio);
if (unlikely(folio->mapping != mapping)) {
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 876339eb2..c98607017 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -4471,6 +4471,7 @@ struct f2fs_folio_state *f2fs_ffs_alloc(struct f2fs_sb_info *sbi,
struct folio *folio);
void f2fs_ffs_attach(struct folio *folio, struct f2fs_folio_state *ffs);
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 d7fae1890..5bb117e5e 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -1512,12 +1512,19 @@ 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;
@@ -1532,6 +1539,8 @@ 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 {
@@ -1544,32 +1553,51 @@ static int move_data_page(struct inode *inode, block_t bidx, int gc_type,
.op_flags = REQ_SYNC,
.old_blkaddr = NULL_ADDR,
.folio = folio,
+ .folio_offset = bidx - folio->index,
+ .folio_blkcnt = 1,
.encrypted_page = NULL,
.need_lock = LOCK_REQ,
.io_type = FS_GC_DATA_IO,
};
- bool is_dirty = folio_test_dirty(folio);
+ struct f2fs_folio_state *ffs = NULL;
+ bool is_dirty = f2fs_ffs_test_blk_dirty(folio, bidx);
retry:
f2fs_folio_wait_writeback(folio, true, true);
+ if (large) {
+ ffs = (struct f2fs_folio_state *)folio->private;
+ f2fs_ffs_mark_subrange_dirty(folio, foff, PAGE_SIZE);
+ }
folio_mark_dirty(folio);
if (folio_clear_dirty_for_io(folio)) {
- inode_dec_dirty_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);
+ }
}
+ if (large)
+ atomic_inc(&ffs->write_pages_pending);
folio_set_f2fs_gcing(folio);
err = f2fs_do_write_data_page(&fio);
if (err) {
folio_clear_f2fs_gcing(folio);
+ if (large)
+ atomic_dec(&ffs->write_pages_pending);
if (err == -ENOMEM) {
memalloc_retry_wait(GFP_NOFS);
goto retry;
}
- if (is_dirty)
+ if (is_dirty) {
+ if (large)
+ f2fs_ffs_mark_subrange_dirty(folio, foff, PAGE_SIZE);
folio_mark_dirty(folio);
+ }
}
}
out:
--
2.43.0
next prev parent reply other threads:[~2026-10-13 11:57 UTC|newest]
Thread overview: 22+ 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 ` [PATCH v4 08/18] f2fs: account large folio dirty data at block granularity Nanzhe Zhao
2026-10-13 11:56 ` [PATCH v4 09/18] f2fs: prepare mmap write faults for large folios Nanzhe Zhao
2026-10-13 11:56 ` Nanzhe Zhao [this message]
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
2026-10-14 1:08 ` Chao Yu
2026-10-14 1:43 ` 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=20261013115621.968742-11-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®