[RFC PATCH 2/8] fat: use iomap for ->bmap()

[Matheus Alves de Almeida]

Make FAT ->bmap() use iomap_bmap(). Add an iomap-backed
fat_swap_activate() to prevent a swapon() deadlock. Remove
truncate_lock as ->bmap() now uses i_rwsem.

Signed-off-by: Matheus Alves de Almeida <matheus.aalmeida@xxxxxxxxxxxx>
---
 fs/fat/fat.h   |  2 +-
 fs/fat/file.c  |  2 --
 fs/fat/inode.c | 47 ++++++++++++++---------------------------------
 fs/fat/iomap.c | 24 ++++++++++++++++++++++++
 4 files changed, 39 insertions(+), 36 deletions(-)

diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index 3d0f91fa11df..81c454f8a78a 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -131,7 +131,6 @@ struct msdos_inode_info {
 	loff_t i_pos;		/* on-disk position of directory entry or 0 */
 	struct hlist_node i_fat_hash;	/* hash by i_location */
 	struct hlist_node i_dir_hash;	/* hash by i_logstart */
-	struct rw_semaphore truncate_lock; /* protect bmap against truncate */
 	struct timespec64 i_crtime;	/* File creation (birth) time */
 	struct mapping_metadata_bhs i_metadata_bhs;
 	struct inode vfs_inode;
@@ -492,6 +491,7 @@ extern const struct export_operations fat_export_ops_nostale;
 
 /* fat/iomap.c */
 extern const struct iomap_ops fat_iomap_ops;
+extern const struct iomap_ops fat_iomap_bmap_ops;
 
 /* helper for printk */
 typedef unsigned long long	llu;
diff --git a/fs/fat/file.c b/fs/fat/file.c
index 531abf9e533c..c27d4e7f698c 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -613,10 +613,8 @@ int fat_setattr(const struct mnt_idmap *idmap, struct dentry *dentry,
 		error = fat_block_truncate_page(inode, attr->ia_size);
 		if (error)
 			goto out;
-		down_write(&MSDOS_I(inode)->truncate_lock);
 		truncate_setsize(inode, attr->ia_size);
 		fat_truncate_blocks(inode, attr->ia_size);
-		up_write(&MSDOS_I(inode)->truncate_lock);
 	}
 
 	/*
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 2a16ed415631..3885ddb916bd 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -216,9 +216,7 @@ static void fat_write_failed(struct address_space *mapping, loff_t to)
 
 	if (to > inode->i_size) {
 		truncate_pagecache(inode, inode->i_size);
-		down_write(&MSDOS_I(inode)->truncate_lock);
 		fat_truncate_blocks(inode, inode->i_size);
-		up_write(&MSDOS_I(inode)->truncate_lock);
 	}
 }
 
@@ -290,43 +288,26 @@ static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	return ret;
 }
 
-static int fat_get_block_bmap(struct inode *inode, sector_t iblock,
-		struct buffer_head *bh_result, int create)
-{
-	struct super_block *sb = inode->i_sb;
-	unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
-	int err;
-	sector_t bmap;
-	unsigned long mapped_blocks;
-
-	BUG_ON(create != 0);
-
-	err = fat_bmap(inode, iblock, &bmap, &mapped_blocks, create, true);
-	if (err)
-		return err;
-
-	if (bmap) {
-		map_bh(bh_result, sb, bmap);
-		max_blocks = min(mapped_blocks, max_blocks);
-	}
-
-	bh_result->b_size = max_blocks << sb->s_blocksize_bits;
-
-	return 0;
-}
-
 static sector_t _fat_bmap(struct address_space *mapping, sector_t block)
 {
 	sector_t blocknr;
 
-	/* fat_get_cluster() assumes the requested blocknr isn't truncated. */
-	down_read(&MSDOS_I(mapping->host)->truncate_lock);
-	blocknr = generic_block_bmap(mapping, block, fat_get_block_bmap);
-	up_read(&MSDOS_I(mapping->host)->truncate_lock);
-
+	inode_lock_shared(mapping->host);
+	blocknr = iomap_bmap(mapping, block, &fat_iomap_bmap_ops);
+	inode_unlock_shared(mapping->host);
 	return blocknr;
 }
 
+static int fat_swap_activate(struct swap_info_struct *sis, struct file *file,
+			     sector_t *span)
+{
+#ifdef CONFIG_SWAP
+	return iomap_swapfile_activate(sis, file, span, &fat_iomap_ops);
+#else
+	return -EIO;
+#endif
+}
+
 /*
  * fat_block_truncate_page() zeroes out a mapping from file offset `from'
  * up to the end of the block which corresponds to `from'.
@@ -350,6 +331,7 @@ static const struct address_space_operations fat_aops = {
 	.direct_IO	= fat_direct_IO,
 	.bmap		= _fat_bmap,
 	.migrate_folio	= buffer_migrate_folio,
+	.swap_activate  = fat_swap_activate,
 };
 
 /*
@@ -790,7 +772,6 @@ static struct inode *fat_alloc_inode(struct super_block *sb)
 	if (!ei)
 		return NULL;
 
-	init_rwsem(&ei->truncate_lock);
 	/* Zeroing to allow iput() even if partial initialized inode. */
 	ei->mmu_private = 0;
 	ei->i_start = 0;
diff --git a/fs/fat/iomap.c b/fs/fat/iomap.c
index 7fb24d0296f7..7977147889bb 100644
--- a/fs/fat/iomap.c
+++ b/fs/fat/iomap.c
@@ -69,3 +69,27 @@ static DEFINE_IOMAP_ITER_NEXT(fat_iomap_next, fat_iomap_begin);
 const struct iomap_ops fat_iomap_ops = {
 	.iomap_next = fat_iomap_next
 };
+
+static int fat_iomap_begin_bmap(struct inode *inode, loff_t offset,
+				loff_t length, unsigned int flags,
+				struct iomap *iomap, struct iomap *srcmap)
+{
+	int err;
+
+	err = __fat_iomap_begin(inode, offset, length, flags, iomap);
+	if (err)
+		return err;
+	/*
+	 * iomap_bmap() only returns blocks in an IOMAP_MAPPED range.
+	 * As the old ->bmap() returned KEEP_SIZE blocks, keep that behavior.
+	 */
+	if (iomap->type == IOMAP_UNWRITTEN)
+		iomap->type = IOMAP_MAPPED;
+	return 0;
+}
+
+static DEFINE_IOMAP_ITER_NEXT(fat_iomap_next_bmap, fat_iomap_begin_bmap);
+
+const struct iomap_ops fat_iomap_bmap_ops = {
+	.iomap_next = fat_iomap_next_bmap
+};
-- 
2.43.0