[PATCH v4 15/18] f2fs: fix zeroing paths for large folios

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

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 433d8f2b0..48376cbcc 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1799,6 +1799,12 @@ 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) {
@@ -1808,13 +1814,15 @@ 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);
 
@@ -2922,7 +2930,7 @@ 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 c98607017..a925d1a59 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -4455,6 +4455,7 @@ 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 37d41f593..69d1344a5 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -842,12 +842,13 @@ 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) {
@@ -865,12 +866,22 @@ 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;
 }
@@ -1335,6 +1346,7 @@ 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;
@@ -1349,7 +1361,14 @@ 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