fsdax: shift partition offset handling into the file systems

Remove the last user of ->bdev in dax.c by requiring the file system to
pass in an address that already includes the DAX offset.  As part of the
only set ->bdev or ->daxdev when actually required in the ->iomap_begin
methods.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com> [erofs]
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Link: https://lore.kernel.org/r/20211129102203.2243509-27-hch@lst.de
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

Author: Christoph Hellwig

fs/dax.c

@@ -711,11 +711,7 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 
 static pgoff_t dax_iomap_pgoff(const struct iomap *iomap, loff_t pos)
 {
-	phys_addr_t paddr = iomap->addr + (pos & PAGE_MASK) - iomap->offset;
-
-	if (iomap->bdev)
-		paddr += (get_start_sect(iomap->bdev) << SECTOR_SHIFT);
-	return PHYS_PFN(paddr);
+	return PHYS_PFN(iomap->addr + (pos & PAGE_MASK) - iomap->offset);
 }
 
 static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter)

fs/erofs/data.c

@@ -159,6 +159,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 	/* primary device by default */
 	map->m_bdev = sb->s_bdev;
 	map->m_daxdev = EROFS_SB(sb)->dax_dev;
+	map->m_dax_part_off = EROFS_SB(sb)->dax_part_off;
 
 	if (map->m_deviceid) {
 		down_read(&devs->rwsem);
@@ -169,6 +170,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 		}
 		map->m_bdev = dif->bdev;
 		map->m_daxdev = dif->dax_dev;
+		map->m_dax_part_off = dif->dax_part_off;
 		up_read(&devs->rwsem);
 	} else if (devs->extra_devices) {
 		down_read(&devs->rwsem);
@@ -185,6 +187,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 				map->m_pa -= startoff;
 				map->m_bdev = dif->bdev;
 				map->m_daxdev = dif->dax_dev;
+				map->m_dax_part_off = dif->dax_part_off;
 				break;
 			}
 		}
@@ -215,9 +218,13 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	if (ret)
 		return ret;
 
-	iomap->bdev = mdev.m_bdev;
-	iomap->dax_dev = mdev.m_daxdev;
 	iomap->offset = map.m_la;
+	if (flags & IOMAP_DAX) {
+		iomap->dax_dev = mdev.m_daxdev;
+		iomap->offset += mdev.m_dax_part_off;
+	} else {
+		iomap->bdev = mdev.m_bdev;
+	}
 	iomap->length = map.m_llen;
 	iomap->flags = 0;
 	iomap->private = NULL;

fs/erofs/internal.h

@@ -438,6 +438,7 @@ static inline int z_erofs_map_blocks_iter(struct inode *inode,
 struct erofs_map_dev {
 	struct block_device *m_bdev;
 	struct dax_device *m_daxdev;
+	u64 m_dax_part_off;
 
 	erofs_off_t m_pa;
 	unsigned int m_deviceid;

fs/ext2/inode.c

@@ -817,9 +817,11 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 		return ret;
 
 	iomap->flags = 0;
-	iomap->bdev = inode->i_sb->s_bdev;
 	iomap->offset = (u64)first_block << blkbits;
-	iomap->dax_dev = sbi->s_daxdev;
+	if (flags & IOMAP_DAX)
+		iomap->dax_dev = sbi->s_daxdev;
+	else
+		iomap->bdev = inode->i_sb->s_bdev;
 
 	if (ret == 0) {
 		iomap->type = IOMAP_HOLE;
@@ -828,6 +830,8 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	} else {
 		iomap->type = IOMAP_MAPPED;
 		iomap->addr = (u64)bno << blkbits;
+		if (flags & IOMAP_DAX)
+			iomap->addr += sbi->s_dax_part_off;
 		iomap->length = (u64)ret << blkbits;
 		iomap->flags |= IOMAP_F_MERGED;
 	}

fs/ext4/inode.c

@@ -3272,7 +3272,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode)
 
 static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
 			   struct ext4_map_blocks *map, loff_t offset,
-			   loff_t length)
+			   loff_t length, unsigned int flags)
 {
 	u8 blkbits = inode->i_blkbits;
 
@@ -3289,8 +3289,10 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
 	if (map->m_flags & EXT4_MAP_NEW)
 		iomap->flags |= IOMAP_F_NEW;
 
-	iomap->bdev = inode->i_sb->s_bdev;
-	iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev;
+	if (flags & IOMAP_DAX)
+		iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev;
+	else
+		iomap->bdev = inode->i_sb->s_bdev;
 	iomap->offset = (u64) map->m_lblk << blkbits;
 	iomap->length = (u64) map->m_len << blkbits;
 
@@ -3310,9 +3312,13 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
 	if (map->m_flags & EXT4_MAP_UNWRITTEN) {
 		iomap->type = IOMAP_UNWRITTEN;
 		iomap->addr = (u64) map->m_pblk << blkbits;
+		if (flags & IOMAP_DAX)
+			iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off;
 	} else if (map->m_flags & EXT4_MAP_MAPPED) {
 		iomap->type = IOMAP_MAPPED;
 		iomap->addr = (u64) map->m_pblk << blkbits;
+		if (flags & IOMAP_DAX)
+			iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off;
 	} else {
 		iomap->type = IOMAP_HOLE;
 		iomap->addr = IOMAP_NULL_ADDR;
@@ -3421,7 +3427,7 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	if (ret < 0)
 		return ret;
 out:
-	ext4_set_iomap(inode, iomap, &map, offset, length);
+	ext4_set_iomap(inode, iomap, &map, offset, length, flags);
 
 	return 0;
 }
@@ -3541,7 +3547,7 @@ static int ext4_iomap_begin_report(struct inode *inode, loff_t offset,
 		delalloc = ext4_iomap_is_delalloc(inode, &map);
 
 set_iomap:
-	ext4_set_iomap(inode, iomap, &map, offset, length);
+	ext4_set_iomap(inode, iomap, &map, offset, length, flags);
 	if (delalloc && iomap->type == IOMAP_HOLE)
 		iomap->type = IOMAP_DELALLOC;
 

fs/xfs/xfs_iomap.c

@@ -71,15 +71,21 @@ xfs_bmbt_to_iomap(
 		iomap->type = IOMAP_DELALLOC;
 	} else {
 		iomap->addr = BBTOB(xfs_fsb_to_db(ip, imap->br_startblock));
+		if (mapping_flags & IOMAP_DAX)
+			iomap->addr += target->bt_dax_part_off;
+
 		if (imap->br_state == XFS_EXT_UNWRITTEN)
 			iomap->type = IOMAP_UNWRITTEN;
 		else
 			iomap->type = IOMAP_MAPPED;
+
 	}
 	iomap->offset = XFS_FSB_TO_B(mp, imap->br_startoff);
 	iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount);
-	iomap->bdev = target->bt_bdev;
-	iomap->dax_dev = target->bt_daxdev;
+	if (mapping_flags & IOMAP_DAX)
+		iomap->dax_dev = target->bt_daxdev;
+	else
+		iomap->bdev = target->bt_bdev;
 	iomap->flags = iomap_flags;
 
 	if (xfs_ipincount(ip) &&