Starts support for iomap in the buffered I/O path for regular files on
ext4.

 - Introduces a new iomap address space operation, ext4_iomap_aops.
 - Adds an inode state flag, EXT4_STATE_BUFFERED_IOMAP, which indicates
   that the inode uses the iomap path instead of the original
   buffer_head path for buffered I/O.

Most callbacks of ext4_iomap_aops can directly utilize generic iomap
implementations, the remaining callbacks: read_folio(), readahead(),
and writepages() will be implemented in later patches.

Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
 fs/ext4/ext4.h  |  7 +++++++
 fs/ext4/inode.c | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 19d0b4917aea..4930446cfec1 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1978,6 +1978,7 @@ enum {
 	EXT4_STATE_FC_COMMITTING,	/* Fast commit ongoing */
 	EXT4_STATE_FC_FLUSHING_DATA,	/* Fast commit flushing data */
 	EXT4_STATE_ORPHAN_FILE,		/* Inode orphaned in orphan file */
+	EXT4_STATE_BUFFERED_IOMAP,	/* Inode use iomap for buffered IO */
 };
 
 #define EXT4_INODE_BIT_FNS(name, field, offset)				\
@@ -2046,6 +2047,12 @@ static inline bool ext4_inode_orphan_tracked(struct inode *inode)
 		!list_empty(&EXT4_I(inode)->i_orphan);
 }
 
+/* Whether the inode pass through the iomap infrastructure for buffered I/O */
+static inline bool ext4_inode_buffered_iomap(struct inode *inode)
+{
+	return ext4_test_inode_state(inode, EXT4_STATE_BUFFERED_IOMAP);
+}
+
 /*
  * Codes for operating systems
  */
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 1ac93c39d21e..fb7e75de2065 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3903,6 +3903,22 @@ const struct iomap_ops ext4_iomap_report_ops = {
 	.iomap_begin = ext4_iomap_begin_report,
 };
 
+static int ext4_iomap_read_folio(struct file *file, struct folio *folio)
+{
+	return 0;
+}
+
+static void ext4_iomap_readahead(struct readahead_control *rac)
+{
+
+}
+
+static int ext4_iomap_writepages(struct address_space *mapping,
+				 struct writeback_control *wbc)
+{
+	return 0;
+}
+
 /*
  * For data=journal mode, folio should be marked dirty only when it was
  * writeably mapped. When that happens, it was already attached to the
@@ -3989,6 +4005,20 @@ static const struct address_space_operations ext4_da_aops = {
 	.swap_activate		= ext4_iomap_swap_activate,
 };
 
+static const struct address_space_operations ext4_iomap_aops = {
+	.read_folio		= ext4_iomap_read_folio,
+	.readahead		= ext4_iomap_readahead,
+	.writepages		= ext4_iomap_writepages,
+	.dirty_folio		= iomap_dirty_folio,
+	.bmap			= ext4_bmap,
+	.invalidate_folio	= iomap_invalidate_folio,
+	.release_folio		= iomap_release_folio,
+	.migrate_folio		= filemap_migrate_folio,
+	.is_partially_uptodate  = iomap_is_partially_uptodate,
+	.error_remove_folio	= generic_error_remove_folio,
+	.swap_activate		= ext4_iomap_swap_activate,
+};
+
 static const struct address_space_operations ext4_dax_aops = {
 	.writepages		= ext4_dax_writepages,
 	.dirty_folio		= noop_dirty_folio,
@@ -4010,6 +4040,8 @@ void ext4_set_aops(struct inode *inode)
 	}
 	if (IS_DAX(inode))
 		inode->i_mapping->a_ops = &ext4_dax_aops;
+	else if (ext4_inode_buffered_iomap(inode))
+		inode->i_mapping->a_ops = &ext4_iomap_aops;
 	else if (test_opt(inode->i_sb, DELALLOC))
 		inode->i_mapping->a_ops = &ext4_da_aops;
 	else
-- 
2.52.0