[PATCH v4 13/18] f2fs: handle partial truncate of large folio dirty subpages

[Nanzhe Zhao <nzzhao.sigma@gmail.com>]

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 | 128 ++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 122 insertions(+), 6 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 0c4c41871..61fe4a0c5 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -328,6 +328,27 @@ static void f2fs_read_end_io(struct bio *bio)
 	f2fs_verify_and_finish_bio(bio, intask);
 }
 
+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;
+}
+
 static void f2fs_write_end_bio(struct bio *bio)
 {
 	struct f2fs_sb_info *sbi = bio->bi_private;
@@ -379,7 +400,8 @@ static void f2fs_write_end_bio(struct bio *bio)
 			wake_up(&sbi->cp_wait);
 
 		if (finished) {
-			folio_clear_f2fs_gcing(folio);
+			if (!f2fs_ffs_has_dirty_subpage(folio))
+				folio_clear_f2fs_gcing(folio);
 			folio_end_writeback(folio);
 		}
 	}
@@ -2923,6 +2945,40 @@ 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);
+	} 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;
@@ -3807,12 +3863,31 @@ 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,
@@ -4360,6 +4435,7 @@ static int f2fs_write_cache_folios(struct address_space *mapping,
 		bool verity_in_progress;
 		int folio_submitted = 0;
 		bool bias_added = false;
+		bool dirty;
 
 		submitted = 0;
 		retry = false;
@@ -4481,8 +4557,9 @@ static int f2fs_write_cache_folios(struct address_space *mapping,
 		 * partially written back), the folio must stay dirty so that
 		 * the remaining subranges are written back later.
 		 */
-		if (f2fs_ffs_clear_subrange_dirty_and_test(folio, 0,
-					(err ? pos : end_pos) - folio_pos(folio)))
+		dirty = f2fs_ffs_clear_subrange_dirty_and_test(folio, 0,
+					(err ? pos : end_pos) - folio_pos(folio));
+		if (dirty)
 			folio_redirty_for_writepage(wbc, folio);
 		else if (!f2fs_folio_has_ffs(folio))
 			inode_dec_dirty_block(inode);
@@ -4493,6 +4570,14 @@ static int f2fs_write_cache_folios(struct address_space *mapping,
 		 */
 		if (bias_added &&
 		    atomic_dec_and_test(&ffs->write_pages_pending)) {
+			/*
+			 * For a large folio we clear PAGE_PRIVATE_GCING only
+			 * when the last dirty bit is cleared, otherwise the
+			 * remaining subpages are no longer written back as
+			 * checkpoint-guaranteed data (f2fs_is_cp_guaranteed()).
+			 */
+			if (!dirty)
+				folio_clear_f2fs_gcing(folio);
 			folio_end_writeback(folio);
 		} else if (!folio_submitted && folio_test_writeback(folio)) {
 			/*
@@ -5310,10 +5395,41 @@ 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