[PATCH v7 04/15] f2fs: support atomic file large folios buffered write

[Nanzhe Zhao]

From: Nanzhe Zhao <zhaonanzhe@xxxxxxxxxx>

ioctl can convert an inode with large folio support into an atomic
file. Support large folio buffered writes for atomic files as well.

Add a large folio atomic write_begin helper that reserves COW mappings
for the write range. For partial head and tail subpages, read the
existing data from either the COW inode or the original inode before
marking the subpage uptodate.

Signed-off-by: Nanzhe Zhao <zhaonanzhe@xxxxxxxxxx>
---
 fs/f2fs/data.c | 86 ++++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 76 insertions(+), 10 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index f01bf06a77b0..126cad81227f 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -4305,18 +4305,22 @@ static int __reserve_data_block(struct inode *inode, pgoff_t index,
 }
 
 static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi,
-			struct folio *folio, loff_t pos, unsigned int len,
-			block_t *blk_addr, bool *node_changed)
+			struct inode *inode, pgoff_t index,
+			block_t *blk_addr, bool *node_changed,
+			bool check_reserved)
 {
-	struct inode *inode = folio->mapping->host;
 	struct inode *cow_inode = F2FS_I(inode)->cow_inode;
-	pgoff_t index = folio->index;
 	int err = 0;
 	block_t ori_blk_addr = NULL_ADDR;
 	bool cow_has_reserved_block = false;
+	bool append = ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode);
 
-	/* If pos is beyond the end of file, reserve a new block in COW inode */
-	if ((pos & PAGE_MASK) >= i_size_read(inode))
+	/*
+	 * On the first attempt, an append write can skip the COW lookup and
+	 * reserve directly.  On retry, check the COW block first so the same
+	 * block is not reserved and accounted twice.
+	 */
+	if (append && !check_reserved)
 		goto reserve_block;
 
 	/* Look for the block in COW inode first */
@@ -4330,7 +4334,7 @@ static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi,
 	if (*blk_addr == NEW_ADDR)
 		cow_has_reserved_block = true;
 
-	if (is_inode_flag_set(inode, FI_ATOMIC_REPLACE))
+	if (append || is_inode_flag_set(inode, FI_ATOMIC_REPLACE))
 		goto reserve_block;
 
 	/* Look for the block in the original inode */
@@ -4498,6 +4502,62 @@ static int prepare_large_folio_write_begin(struct inode *inode,
 	return 0;
 }
 
+static int prepare_large_folio_atomic_write_begin(struct inode *inode,
+		struct address_space *mapping, struct folio *folio, loff_t pos,
+		unsigned int len, bool retried)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	size_t ori_off = offset_in_folio(folio, pos);
+	pgoff_t start, end, index;
+	int err = 0;
+
+	len = min_t(unsigned int, len, folio_size(folio) - ori_off);
+
+	if (!f2fs_ffs_find_or_alloc(folio))
+		return -ENOMEM;
+
+	/* Inline data must have been converted before reaching here. */
+	f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
+
+	start = folio->index + (ori_off >> PAGE_SHIFT);
+	end = folio->index + ((ori_off + len - 1) >> PAGE_SHIFT);
+
+	for (index = start; index <= end; index++) {
+		block_t blkaddr = NULL_ADDR;
+		bool node_changed = false;
+		size_t off = (index - folio->index) << PAGE_SHIFT;
+
+		err = prepare_atomic_write_begin(sbi, inode, index,
+						&blkaddr, &node_changed,
+						retried);
+		if (err)
+			return err;
+
+		if (f2fs_ffs_test_blk_uptodate(folio, index))
+			goto balance;
+
+		if (blkaddr == NEW_ADDR) {
+			folio_zero_segment(folio, off, off + PAGE_SIZE);
+			f2fs_ffs_mark_subrange_uptodate(folio, off, PAGE_SIZE);
+			goto balance;
+		}
+
+		if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
+					   DATA_GENERIC_ENHANCE_READ))
+			return -EFSCORRUPTED;
+
+		err = f2fs_submit_page_read_sync(inode, folio, index,
+						blkaddr);
+		if (err)
+			return err;
+balance:
+		if (f2fs_balance_fs_folio_locked(folio, mapping, node_changed))
+			return -EAGAIN;
+	}
+
+	return 0;
+}
+
 static int f2fs_write_begin(const struct kiocb *iocb,
 			    struct address_space *mapping,
 			    loff_t pos, unsigned len, struct folio **foliop,
@@ -4508,6 +4568,7 @@ static int f2fs_write_begin(const struct kiocb *iocb,
 	struct folio *folio;
 	pgoff_t index = pos >> PAGE_SHIFT;
 	bool need_balance = false;
+	bool retried = false;
 	block_t blkaddr = NULL_ADDR;
 	fgf_t fgp = FGP_LOCK | FGP_WRITE | FGP_CREAT;
 	unsigned int blen;
@@ -4587,16 +4648,20 @@ static int f2fs_write_begin(const struct kiocb *iocb,
 	 */
 	f2fs_folio_wait_writeback(folio, false, true);
 
-	if (f2fs_is_atomic_file(inode))
-		err = prepare_atomic_write_begin(sbi, folio, pos, len,
-					&blkaddr, &need_balance);
+	if (f2fs_is_atomic_file(inode) && !folio_test_large(folio))
+		err = prepare_atomic_write_begin(sbi, inode, folio->index,
+					&blkaddr, &need_balance, retried);
 	else if (!folio_test_large(folio))
 		err = prepare_write_begin(sbi, folio, pos, blen,
 					&blkaddr, &need_balance);
+	else if (f2fs_is_atomic_file(inode))
+		err = prepare_large_folio_atomic_write_begin(inode,
+					mapping, folio, pos, len, retried);
 	else
 		err = prepare_large_folio_write_begin(inode, folio, pos, blen);
 	if (err) {
 		if (err == -EAGAIN) {
+			retried = true;
 			f2fs_folio_put(folio, true);
 			goto repeat;
 		}
@@ -4604,6 +4669,7 @@ static int f2fs_write_begin(const struct kiocb *iocb,
 	}
 
 	if (f2fs_balance_fs_folio_locked(folio, mapping, need_balance)) {
+		retried = true;
 		f2fs_folio_put(folio, true);
 		goto repeat;
 	}
-- 
2.43.0