[PATCH v5 5/5] hfsplus: convert regular file I/O to iomap

From: Viacheslav Dubeyko

Date: Tue Nov 17 2026 - 19:49:16 EST


Switch the HFS+ regular file data path from buffer heads and
blockdev_direct_IO() to iomap.

Add iomap.h and iomap.c with hfsplus_iomap_ops,
hfsplus_write_iomap_ops, hfsplus_writeback_ops and
hfsplus_write_dio_ops. iomap.c implements __hfsplus_iomap_begin(),
hfsplus_write_iomap_end(), hfsplus_iomap_cont_expand() and
hfsplus_writeback_range(), which are the basis of the HFS+ iomap
operations. Direct write completion uses the generic
iomap_dio_end_io() helper.

Implement iomap-based hfsplus_file_llseek(), hfsplus_file_read_iter()
and hfsplus_file_write_iter(). The volume capacity limit for writes is
enforced by generic_write_checks(), since s_maxbytes is already set
from the volume capacity.

Redefine hfsplus_aops as iomap-based operations for regular files.
As a result, hfsplus_direct_IO() is removed as a user of
blockdev_direct_IO(), and the LEGACY_DIRECT_IO dependency is dropped
from Kconfig. hfsplus_file_truncate() extends regular files by means
of hfsplus_iomap_cont_expand(), while other inodes still use the
write_begin/write_end path.

HFS+ does not support holes, so a write or truncate that extends a
file first zero-fills the range between the old end-of-file and the
new one by means of hfsplus_iomap_cont_expand(). Introduce
hfsplus_iomap_extend_size() that grows i_size, zero-fills the gap and
rolls back on failure, and use it in hfsplus_file_write_iter() and
hfsplus_setattr(). Introduce hfsplus_iomap_size_rollback() that waits
for in-flight direct I/O, sets i_size, truncates the page cache beyond
it and calls hfsplus_file_truncate() to release the blocks allocated
past it. It is not called when phys_size is below the new size, since
hfsplus_file_truncate() would zero-fill again in that case.

In hfsplus_file_write_iter(), roll back after the data write if fewer
bytes than requested were written: to the original size if nothing
was written, or to the current i_size after a short write. Queued
asynchronous direct I/O is skipped, because direct I/O beyond
phys_size is forced to be synchronous, so a queued request never
extends the file.

cc: Christoph Hellwig <hch@xxxxxx>
cc: John Paul Adrian Glaubitz <glaubitz@xxxxxxxxxxxxxxxxxxx>
cc: Yangtao Li <frank.li@xxxxxxxx>
cc: linux-fsdevel@xxxxxxxxxxxxxxx
Signed-off-by: Viacheslav Dubeyko <slava@xxxxxxxxxxx>
---
fs/hfsplus/Kconfig | 2 +-
fs/hfsplus/Makefile | 6 +-
fs/hfsplus/extents.c | 40 +++++--
fs/hfsplus/file.c | 187 ++++++++++++++++++++++++++++-
fs/hfsplus/hfsplus_fs.h | 17 +++
fs/hfsplus/inode.c | 155 ++++++++++++------------
fs/hfsplus/iomap.c | 254 ++++++++++++++++++++++++++++++++++++++++
fs/hfsplus/iomap.h | 17 +++
8 files changed, 583 insertions(+), 95 deletions(-)
create mode 100644 fs/hfsplus/iomap.c
create mode 100644 fs/hfsplus/iomap.h

diff --git a/fs/hfsplus/Kconfig b/fs/hfsplus/Kconfig
index ca8401cb6954..b4432c64db3b 100644
--- a/fs/hfsplus/Kconfig
+++ b/fs/hfsplus/Kconfig
@@ -5,7 +5,7 @@ config HFSPLUS_FS
select BUFFER_HEAD
select NLS
select NLS_UTF8
- select LEGACY_DIRECT_IO
+ select FS_IOMAP
help
If you say Y here, you will be able to mount extended format
Macintosh-formatted hard drive partitions with full read-write access.
diff --git a/fs/hfsplus/Makefile b/fs/hfsplus/Makefile
index 82738ce7ca4d..3ddea69a9c69 100644
--- a/fs/hfsplus/Makefile
+++ b/fs/hfsplus/Makefile
@@ -5,9 +5,9 @@

obj-$(CONFIG_HFSPLUS_FS) += hfsplus.o

-hfsplus-objs := super.o options.o inode.o file.o ioctl.o extents.o catalog.o dir.o \
- btree.o bnode.o brec.o bfind.o tables.o unicode.o wrapper.o bitmap.o \
- part_tbl.o \
+hfsplus-objs := super.o options.o inode.o file.o iomap.o ioctl.o extents.o \
+ catalog.o dir.o btree.o bnode.o brec.o bfind.o tables.o \
+ unicode.o wrapper.o bitmap.o part_tbl.o \
attributes.o xattr.o xattr_user.o xattr_security.o xattr_trusted.o

# KUnit tests
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index bb5a1508498d..0928d64684aa 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -15,6 +15,7 @@

#include "hfsplus_fs.h"
#include "hfsplus_raw.h"
+#include "iomap.h"

/* Compare two extents keys, returns 0 on same, pos/neg for difference */
int hfsplus_ext_cmp_key(const hfsplus_btree_key *k1,
@@ -610,20 +611,33 @@ void hfsplus_file_truncate(struct inode *inode)
inode->i_ino, (long long)hip->phys_size, inode->i_size);

if (inode->i_size > hip->phys_size) {
- struct address_space *mapping = inode->i_mapping;
- struct folio *folio;
- void *fsdata = NULL;
- loff_t size = inode->i_size;
+ if (S_ISREG(inode->i_mode)) {
+ res = hfsplus_iomap_cont_expand(inode, hip->phys_size,
+ inode->i_size);
+ if (res)
+ return;
+
+ mark_inode_dirty(inode);
+ } else {
+ struct address_space *mapping = inode->i_mapping;
+ struct folio *folio;
+ void *fsdata = NULL;
+
+ res = hfsplus_write_begin(NULL, mapping,
+ inode->i_size, 0,
+ &folio, &fsdata);
+ if (res)
+ return;
+
+ res = generic_write_end(NULL, mapping,
+ inode->i_size, 0, 0,
+ folio, fsdata);
+ if (res < 0)
+ return;
+
+ mark_inode_dirty(inode);
+ }

- res = hfsplus_write_begin(NULL, mapping, size, 0,
- &folio, &fsdata);
- if (res)
- return;
- res = generic_write_end(NULL, mapping, size, 0, 0,
- folio, fsdata);
- if (res < 0)
- return;
- mark_inode_dirty(inode);
return;
}

diff --git a/fs/hfsplus/file.c b/fs/hfsplus/file.c
index 6b14095b2aa6..f34cd80351e5 100644
--- a/fs/hfsplus/file.c
+++ b/fs/hfsplus/file.c
@@ -3,9 +3,11 @@
#include <linux/fs.h>
#include <linux/uio.h>
#include <linux/mount.h>
+#include <linux/iomap.h>

#include "hfsplus_fs.h"
#include "hfsplus_raw.h"
+#include "iomap.h"

static int hfsplus_file_open(struct inode *inode, struct file *file)
{
@@ -14,6 +16,7 @@ static int hfsplus_file_open(struct inode *inode, struct file *file)
if (!(file->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS)
return -EOVERFLOW;
atomic_inc(&HFSPLUS_I(inode)->opencnt);
+ file->f_mode |= FMODE_CAN_ODIRECT;
return 0;
}

@@ -113,10 +116,188 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end,
return error;
}

+/*
+ * Fall back to buffered I/O for the tail of a write that
+ * iomap_dio_rw() could not perform directly (unaligned tail,
+ * or no blocks could be mapped without allocation
+ * outside the direct path).
+ */
+static ssize_t hfsplus_fallback_buffered_write(struct kiocb *iocb,
+ struct iov_iter *from)
+{
+ loff_t offset = iocb->ki_pos, end;
+ ssize_t written;
+ int ret;
+
+ iocb->ki_flags &= ~IOCB_DIRECT;
+
+ written = iomap_file_buffered_write(iocb, from,
+ &hfsplus_write_iomap_ops,
+ NULL, NULL);
+ if (written < 0)
+ return written;
+
+ end = iocb->ki_pos + written - 1;
+ ret = filemap_write_and_wait_range(iocb->ki_filp->f_mapping,
+ offset, end);
+ if (ret)
+ return -EIO;
+
+ invalidate_mapping_pages(iocb->ki_filp->f_mapping,
+ offset >> PAGE_SHIFT,
+ end >> PAGE_SHIFT);
+
+ return written;
+}
+
+static ssize_t hfsplus_dio_write_iter(struct kiocb *iocb,
+ struct iov_iter *from,
+ unsigned int dio_flags)
+{
+ ssize_t ret;
+
+ ret = iomap_dio_rw(iocb, from,
+ &hfsplus_write_iomap_ops,
+ &hfsplus_write_dio_ops,
+ dio_flags, NULL, 0);
+ if (ret == -ENOTBLK)
+ ret = 0;
+ else if (ret < 0)
+ return ret;
+
+ if (iov_iter_count(from)) {
+ ssize_t written;
+
+ written = hfsplus_fallback_buffered_write(iocb, from);
+ if (written < 0)
+ return written;
+ ret += written;
+ }
+
+ return ret;
+}
+
+static ssize_t hfsplus_file_write_iter(struct kiocb *iocb,
+ struct iov_iter *iter)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file_inode(file);
+ loff_t old_size;
+ ssize_t count;
+ ssize_t ret;
+ int err;
+
+ inode_lock(inode);
+
+ ret = generic_write_checks(iocb, iter);
+ if (ret <= 0)
+ goto unlock;
+
+ count = ret;
+ old_size = i_size_read(inode);
+
+ err = file_modified(file);
+ if (err) {
+ ret = err;
+ goto unlock;
+ }
+
+ if (iocb->ki_pos > i_size_read(inode)) {
+ err = hfsplus_iomap_extend_size(inode, iocb->ki_pos);
+ if (err) {
+ ret = err;
+ goto unlock;
+ }
+ mark_inode_dirty(inode);
+ }
+
+ if (iocb->ki_flags & IOCB_DIRECT) {
+ unsigned int dio_flags = 0;
+
+ if (iocb->ki_pos + iov_iter_count(iter) >
+ HFSPLUS_I(inode)->phys_size)
+ dio_flags |= IOMAP_DIO_FORCE_WAIT;
+
+ ret = hfsplus_dio_write_iter(iocb, iter, dio_flags);
+ } else {
+ ret = iomap_file_buffered_write(iocb, iter,
+ &hfsplus_write_iomap_ops,
+ NULL, NULL);
+ }
+
+ /*
+ * On a failed write, undo the zero-filled extension so that the
+ * file keeps its original size. On a short write, keep what was
+ * written. Either way, release the blocks allocated beyond the
+ * resulting end-of-file. Queued async direct I/O never extends
+ * the file (it is forced synchronous beyond phys_size), so there
+ * is nothing to undo for it.
+ */
+ if (ret != -EIOCBQUEUED && ret < count) {
+ hfsplus_iomap_size_rollback(inode,
+ ret > 0 ? i_size_read(inode) :
+ old_size);
+ }
+
+unlock:
+ inode_unlock(inode);
+
+ if (ret > 0)
+ ret = generic_write_sync(iocb, ret);
+
+ return ret;
+}
+
+static ssize_t hfsplus_file_read_iter(struct kiocb *iocb,
+ struct iov_iter *iter)
+{
+ struct inode *inode = file_inode(iocb->ki_filp);
+ ssize_t ret;
+
+ inode_lock_shared(inode);
+
+ if (iocb->ki_flags & IOCB_DIRECT) {
+ file_accessed(iocb->ki_filp);
+ ret = iomap_dio_rw(iocb, iter,
+ &hfsplus_iomap_ops,
+ NULL, 0, NULL, 0);
+ } else
+ ret = generic_file_read_iter(iocb, iter);
+
+ inode_unlock_shared(inode);
+
+ return ret;
+}
+
+static loff_t hfsplus_file_llseek(struct file *file, loff_t offset, int whence)
+{
+ struct inode *inode = file->f_mapping->host;
+
+ switch (whence) {
+ case SEEK_HOLE:
+ inode_lock_shared(inode);
+ offset = iomap_seek_hole(inode, offset, &hfsplus_iomap_ops);
+ inode_unlock_shared(inode);
+ break;
+ case SEEK_DATA:
+ inode_lock_shared(inode);
+ offset = iomap_seek_data(inode, offset, &hfsplus_iomap_ops);
+ inode_unlock_shared(inode);
+ break;
+ default:
+ return generic_file_llseek(file, offset, whence);
+ }
+
+ if (offset < 0)
+ return offset;
+
+ return vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
+}
+
const struct file_operations hfsplus_file_operations = {
- .llseek = generic_file_llseek,
- .read_iter = generic_file_read_iter,
- .write_iter = generic_file_write_iter,
+ .llseek = hfsplus_file_llseek,
+ .read_iter = hfsplus_file_read_iter,
+ .write_iter = hfsplus_file_write_iter,
.mmap_prepare = generic_file_mmap_prepare,
.splice_read = filemap_splice_read,
.splice_write = iter_file_splice_write,
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 0b07259041f9..abd5857cac2b 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -176,6 +176,22 @@ static inline struct hfsplus_sb_info *HFSPLUS_SB(struct super_block *sb)
return sb->s_fs_info;
}

+/*
+ * Physical byte offset of allocation block 'dblock' on the volume.
+ */
+static inline loff_t hfsplus_ablock_to_phys_bytes(struct super_block *sb,
+ u32 dblock)
+{
+ struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+ loff_t phys_bytes;
+
+ phys_bytes = dblock;
+ phys_bytes <<= sbi->fs_shift;
+ phys_bytes += sbi->blockoffset;
+ phys_bytes <<= sb->s_blocksize_bits;
+
+ return phys_bytes;
+}

struct hfsplus_inode_info {
atomic_t opencnt;
@@ -456,6 +472,7 @@ void hfsplus_file_truncate(struct inode *inode);

/* inode.c */
extern const struct address_space_operations hfsplus_aops;
+extern const struct address_space_operations hfsplus_symlink_aops;
extern const struct address_space_operations hfsplus_btree_aops;
extern const struct dentry_operations hfsplus_dentry_operations;

diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index b43422155e7e..540392799a23 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -18,15 +18,12 @@
#include <linux/cred.h>
#include <linux/uio.h>
#include <linux/fileattr.h>
+#include <linux/iomap.h>

#include "hfsplus_fs.h"
#include "hfsplus_raw.h"
#include "xattr.h"
-
-static int hfsplus_read_folio(struct file *file, struct folio *folio)
-{
- return block_read_full_folio(folio, hfsplus_get_block);
-}
+#include "iomap.h"

static void hfsplus_write_failed(struct address_space *mapping, loff_t to)
{
@@ -121,67 +118,13 @@ static bool hfsplus_release_folio(struct folio *folio, gfp_t mask)
return res ? try_to_free_buffers(folio) : false;
}

-static ssize_t hfsplus_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
+static int hfsplus_btree_read_folio(struct file *file, struct folio *folio)
{
- struct file *file = iocb->ki_filp;
- struct address_space *mapping = file->f_mapping;
- struct inode *inode = mapping->host;
- loff_t isize;
- size_t count = iov_iter_count(iter);
- loff_t end = iocb->ki_pos + count;
- ssize_t ret;
-
- /*
- * The hfsplus_get_block() only allows creating the next sequential block.
- * For direct writes beyond EOF, expand the file first.
- */
- if (iov_iter_rw(iter) == WRITE && iocb->ki_pos > i_size_read(inode)) {
- loff_t start_off, end_off;
- loff_t start_page, end_page;
-
- isize = i_size_read(inode);
-
- /*
- * Wait for any in-flight DIO on this inode to finish before
- * calling generic_cont_expand_simple().
- */
- inode_dio_wait(inode);
-
- ret = generic_cont_expand_simple(inode, iocb->ki_pos);
- if (ret)
- return ret;
-
- start_off = isize;
- end_off = (end > 0) ? end - 1 : end;
-
- ret = filemap_write_and_wait_range(mapping, start_off, end_off);
- if (ret)
- return ret;
-
- start_page = start_off >> PAGE_SHIFT;
- end_page = end_off >> PAGE_SHIFT;
-
- invalidate_inode_pages2_range(mapping, start_page, end_page);
- }
-
- ret = blockdev_direct_IO(iocb, inode, iter, hfsplus_get_block);
-
- /*
- * In case of error extending write may have instantiated a few
- * blocks outside i_size. Trim these off again.
- */
- if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) {
- isize = i_size_read(inode);
-
- if (end > isize)
- hfsplus_write_failed(mapping, end);
- }
-
- return ret;
+ return block_read_full_folio(folio, hfsplus_get_block);
}

-static int hfsplus_writepages(struct address_space *mapping,
- struct writeback_control *wbc)
+static int hfsplus_btree_writepages(struct address_space *mapping,
+ struct writeback_control *wbc)
{
return mpage_writepages(mapping, wbc, hfsplus_get_block);
}
@@ -189,8 +132,8 @@ static int hfsplus_writepages(struct address_space *mapping,
const struct address_space_operations hfsplus_btree_aops = {
.dirty_folio = block_dirty_folio,
.invalidate_folio = block_invalidate_folio,
- .read_folio = hfsplus_read_folio,
- .writepages = hfsplus_writepages,
+ .read_folio = hfsplus_btree_read_folio,
+ .writepages = hfsplus_btree_writepages,
.write_begin = hfsplus_write_begin,
.write_end = generic_write_end,
.migrate_folio = buffer_migrate_folio,
@@ -198,18 +141,70 @@ const struct address_space_operations hfsplus_btree_aops = {
.release_folio = hfsplus_release_folio,
};

-const struct address_space_operations hfsplus_aops = {
+static int hfsplus_symlink_read_folio(struct file *file, struct folio *folio)
+{
+ return block_read_full_folio(folio, hfsplus_get_block);
+}
+
+static int hfsplus_symlink_writepages(struct address_space *mapping,
+ struct writeback_control *wbc)
+{
+ return mpage_writepages(mapping, wbc, hfsplus_get_block);
+}
+
+const struct address_space_operations hfsplus_symlink_aops = {
.dirty_folio = block_dirty_folio,
.invalidate_folio = block_invalidate_folio,
- .read_folio = hfsplus_read_folio,
+ .read_folio = hfsplus_symlink_read_folio,
.write_begin = hfsplus_write_begin,
.write_end = generic_write_end,
.bmap = hfsplus_bmap,
- .direct_IO = hfsplus_direct_IO,
- .writepages = hfsplus_writepages,
+ .writepages = hfsplus_symlink_writepages,
.migrate_folio = buffer_migrate_folio,
};

+static int hfsplus_read_folio(struct file *file, struct folio *folio)
+{
+ iomap_bio_read_folio(folio, &hfsplus_iomap_ops);
+ return 0;
+}
+
+static void hfsplus_readahead(struct readahead_control *rac)
+{
+ iomap_bio_readahead(rac, &hfsplus_iomap_ops);
+}
+
+static int hfsplus_writepages(struct address_space *mapping,
+ struct writeback_control *wbc)
+{
+ struct iomap_writepage_ctx wpc = {
+ .inode = mapping->host,
+ .wbc = wbc,
+ .ops = &hfsplus_writeback_ops,
+ };
+
+ return iomap_writepages(&wpc);
+}
+
+static sector_t hfsplus_aop_bmap(struct address_space *mapping, sector_t block)
+{
+ return iomap_bmap(mapping, block, &hfsplus_iomap_ops);
+}
+
+const struct address_space_operations hfsplus_aops = {
+ .read_folio = hfsplus_read_folio,
+ .readahead = hfsplus_readahead,
+ .writepages = hfsplus_writepages,
+ .dirty_folio = iomap_dirty_folio,
+ .bmap = hfsplus_aop_bmap,
+ .migrate_folio = filemap_migrate_folio,
+ .is_partially_uptodate = iomap_is_partially_uptodate,
+ .error_remove_folio = generic_error_remove_folio,
+ .release_folio = iomap_release_folio,
+ .invalidate_folio = iomap_invalidate_folio,
+ .swap_activate = hfsplus_iomap_swap_activate,
+};
+
const struct dentry_operations hfsplus_dentry_operations = {
.d_hash = hfsplus_hash_dentry,
.d_compare = hfsplus_compare_dentry,
@@ -283,13 +278,23 @@ static int hfsplus_setattr(const struct mnt_idmap *idmap,
attr->ia_size != i_size_read(inode)) {
inode_dio_wait(inode);
if (attr->ia_size > inode->i_size) {
- error = generic_cont_expand_simple(inode,
- attr->ia_size);
+ error = hfsplus_iomap_extend_size(inode,
+ attr->ia_size);
if (error)
return error;
+ truncate_setsize(inode, attr->ia_size);
+ } else {
+ bool did_zero = false;
+
+ error = iomap_truncate_page(inode, attr->ia_size,
+ &did_zero,
+ &hfsplus_write_iomap_ops,
+ NULL, NULL);
+ if (error)
+ return error;
+ truncate_setsize(inode, attr->ia_size);
+ hfsplus_file_truncate(inode);
}
- truncate_setsize(inode, attr->ia_size);
- hfsplus_file_truncate(inode);
inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
}

@@ -392,7 +397,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, struct inode *dir,
sbi->file_count++;
inode->i_op = &hfsplus_symlink_inode_operations;
inode_nohighmem(inode);
- inode->i_mapping->a_ops = &hfsplus_aops;
+ inode->i_mapping->a_ops = &hfsplus_symlink_aops;
hip->clump_blocks = 1;
} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
@@ -533,7 +538,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd)
} else if (S_ISLNK(inode->i_mode)) {
inode->i_op = &hfsplus_symlink_inode_operations;
inode_nohighmem(inode);
- inode->i_mapping->a_ops = &hfsplus_aops;
+ inode->i_mapping->a_ops = &hfsplus_symlink_aops;
} else {
inode->i_op = &hfsplus_special_inode_operations;
init_special_inode(inode, inode->i_mode,
diff --git a/fs/hfsplus/iomap.c b/fs/hfsplus/iomap.c
new file mode 100644
index 000000000000..6482d516d98c
--- /dev/null
+++ b/fs/hfsplus/iomap.c
@@ -0,0 +1,254 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/iomap.h>
+#include <linux/pagemap.h>
+
+#include "hfsplus_fs.h"
+#include "hfsplus_raw.h"
+#include "iomap.h"
+
+enum hfsplus_iomap_alloc {
+ HFSPLUS_IOMAP_NO_ALLOC, /* look up an existing mapping only */
+ HFSPLUS_IOMAP_MAY_ALLOC, /* allocate blocks as needed */
+};
+
+static int __hfsplus_iomap_begin(struct inode *inode, loff_t offset,
+ loff_t length, unsigned int flags,
+ struct iomap *iomap,
+ enum hfsplus_iomap_alloc may_alloc)
+{
+ struct super_block *sb = inode->i_sb;
+ struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+ struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
+ u32 ablock, dblock, max_blocks;
+ loff_t ablock_offset, ablock_bytes;
+ loff_t block_start;
+ bool is_new;
+ int err;
+
+ if (!may_alloc) {
+ /* Completely beyond EOF. Treat as hole */
+ if (i_size_read(inode) <= offset) {
+ iomap->type = IOMAP_HOLE;
+ iomap->addr = IOMAP_NULL_ADDR;
+ iomap->offset = offset;
+ iomap->length = length;
+ return 0;
+ }
+
+ /* Clamp length if the requested range goes beyond i_size */
+ if (offset + length > i_size_read(inode)) {
+ loff_t i_size = i_size_read(inode);
+ unsigned int blocksize = i_blocksize(inode);
+
+ length = round_up(i_size, blocksize) - offset;
+ }
+ }
+
+ ablock = offset >> sbi->alloc_blksz_shift;
+
+ err = hfsplus_map_extent(inode, ablock, may_alloc, &dblock,
+ &max_blocks, NULL);
+ if (err)
+ return err;
+
+ ablock_offset = offset & (sbi->alloc_blksz - 1);
+ ablock_bytes = (loff_t)max_blocks << sbi->alloc_blksz_shift;
+
+ length = min_t(loff_t, length, ablock_bytes - ablock_offset);
+ block_start = round_down(offset, i_blocksize(inode));
+ is_new = may_alloc && block_start >= hip->phys_size;
+
+ /*
+ * End a mapping of already initialized blocks at the first block
+ * boundary at or above phys_size, so that the blocks past it start
+ * a new mapping flagged IOMAP_F_NEW. The block holding an unaligned
+ * phys_size (e.g. after the inode is read from disk or truncated)
+ * stays in this mapping: ending it at phys_size itself would give
+ * a length that is not a multiple of the logical block size, which
+ * iomap direct I/O rejects with -EINVAL.
+ */
+ if (may_alloc && !is_new)
+ length = min_t(loff_t, length,
+ round_up(hip->phys_size, i_blocksize(inode)) -
+ offset);
+
+ iomap->bdev = sb->s_bdev;
+ iomap->offset = offset;
+ iomap->length = length;
+ iomap->addr = hfsplus_ablock_to_phys_bytes(sb, dblock) + ablock_offset;
+ iomap->type = IOMAP_MAPPED;
+ iomap->flags = IOMAP_F_MERGED;
+
+ if (is_new)
+ iomap->flags |= IOMAP_F_NEW;
+
+ return 0;
+}
+
+static int hfsplus_iomap_begin(struct inode *inode, loff_t offset,
+ loff_t length, unsigned int flags,
+ struct iomap *iomap, struct iomap *srcmap)
+{
+ return __hfsplus_iomap_begin(inode, offset, length, flags, iomap,
+ HFSPLUS_IOMAP_NO_ALLOC);
+}
+
+static int hfsplus_write_iomap_begin(struct inode *inode, loff_t offset,
+ loff_t length, unsigned int flags,
+ struct iomap *iomap, struct iomap *srcmap)
+{
+ return __hfsplus_iomap_begin(inode, offset, length, flags, iomap,
+ HFSPLUS_IOMAP_MAY_ALLOC);
+}
+
+static DEFINE_IOMAP_ITER_NEXT(hfsplus_iomap_next, hfsplus_iomap_begin);
+
+const struct iomap_ops hfsplus_iomap_ops = {
+ .iomap_next = hfsplus_iomap_next,
+};
+
+/*
+ * Advance the allocated-and-zeroed high-water mark (hip->phys_size)
+ * to cover the newly written range.
+ *
+ * phys_size stays byte-granular when the written block was not newly
+ * allocated, because the rest of that block was never zeroed on disk.
+ * The block accounting is kept as hfsplus_inode_read_fork() and
+ * hfsplus_file_truncate() set it up: fs_blocks is phys_size rounded up
+ * to whole blocks, and the inode's byte count changes in whole blocks.
+ */
+static int hfsplus_write_iomap_end(struct inode *inode, loff_t pos,
+ loff_t length, ssize_t written,
+ unsigned int flags, struct iomap *iomap)
+{
+ struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
+ struct super_block *sb = inode->i_sb;
+ sector_t fs_blocks;
+ loff_t end;
+
+ if (!written)
+ return 0;
+
+ end = pos + written;
+
+ if (iomap->flags & IOMAP_F_NEW)
+ end = round_up(end, sb->s_blocksize);
+
+ if (hip->phys_size >= end)
+ return written;
+
+ fs_blocks = DIV_ROUND_UP_ULL(end, sb->s_blocksize);
+ if (fs_blocks > hip->fs_blocks) {
+ inode_add_bytes(inode, (loff_t)(fs_blocks - hip->fs_blocks) <<
+ sb->s_blocksize_bits);
+ hip->fs_blocks = fs_blocks;
+ }
+ hip->phys_size = end;
+ mark_inode_dirty(inode);
+
+ return written;
+}
+
+static DEFINE_IOMAP_ITER_NEXT_END(hfsplus_write_iomap_next,
+ hfsplus_write_iomap_begin,
+ hfsplus_write_iomap_end);
+
+const struct iomap_ops hfsplus_write_iomap_ops = {
+ .iomap_next = hfsplus_write_iomap_next,
+};
+
+/*
+ * Zero the byte range [from, to) of a file that is being extended, where
+ * 'from' is the old end-of-file and 'to' the new one. Used by the extending
+ * write path, hfsplus_setattr() (truncate up) and hfsplus_file_truncate().
+ */
+int hfsplus_iomap_cont_expand(struct inode *inode, loff_t from, loff_t to)
+{
+ if (to <= from)
+ return 0;
+
+ return iomap_zero_range(inode, from, to - from, NULL,
+ &hfsplus_write_iomap_ops, NULL, NULL);
+}
+
+/*
+ * Undo a failed or short extending operation: set i_size to @size, drop
+ * the page cache beyond it and release the blocks allocated past it
+ * (including any clump preallocation made by hfsplus_file_extend()).
+ *
+ * Must be called with the inode lock held exclusively.
+ */
+void hfsplus_iomap_size_rollback(struct inode *inode, loff_t size)
+{
+ inode_dio_wait(inode);
+
+ i_size_write(inode, size);
+ truncate_pagecache(inode, size);
+
+ /*
+ * hfsplus_file_truncate() would try to zero-fill again if
+ * phys_size were below i_size, which is not what we want here.
+ */
+ if (HFSPLUS_I(inode)->phys_size >= size)
+ hfsplus_file_truncate(inode);
+}
+
+/*
+ * Grow i_size to @new_size and zero-fill the gap from the old end-of-file,
+ * since HFS+ cannot represent holes. If zeroing fails part way (typically
+ * with -ENOSPC), roll back to the old i_size and release the blocks that
+ * were allocated for the partially zeroed range.
+ *
+ * Must be called with the inode lock held exclusively.
+ */
+int hfsplus_iomap_extend_size(struct inode *inode, loff_t new_size)
+{
+ loff_t old_size = i_size_read(inode);
+ int err;
+
+ i_size_write(inode, new_size);
+
+ err = hfsplus_iomap_cont_expand(inode, old_size, new_size);
+ if (err)
+ hfsplus_iomap_size_rollback(inode, old_size);
+
+ return err;
+}
+
+/*
+ * Called for each folio during writeback. If the folio falls outside
+ * the current iomap, remaps by calling __hfsplus_iomap_begin() again.
+ */
+static ssize_t hfsplus_writeback_range(struct iomap_writepage_ctx *wpc,
+ struct folio *folio, u64 offset,
+ unsigned int len, u64 end_pos)
+{
+ int err;
+
+ if (offset < wpc->iomap.offset ||
+ offset >= wpc->iomap.offset + wpc->iomap.length) {
+ err = __hfsplus_iomap_begin(wpc->inode, offset, len, 0,
+ &wpc->iomap,
+ HFSPLUS_IOMAP_NO_ALLOC);
+ if (err)
+ return err;
+ }
+
+ return iomap_add_to_ioend(wpc, folio, offset, end_pos, len);
+}
+
+const struct iomap_writeback_ops hfsplus_writeback_ops = {
+ .writeback_range = hfsplus_writeback_range,
+ .writeback_submit = iomap_ioend_writeback_submit,
+};
+
+const struct iomap_dio_ops hfsplus_write_dio_ops = {
+ .end_io = iomap_dio_end_io,
+};
+
+int hfsplus_iomap_swap_activate(struct swap_info_struct *sis,
+ struct file *file, sector_t *span)
+{
+ return iomap_swapfile_activate(sis, file, span, &hfsplus_iomap_ops);
+}
diff --git a/fs/hfsplus/iomap.h b/fs/hfsplus/iomap.h
new file mode 100644
index 000000000000..53de07bf505a
--- /dev/null
+++ b/fs/hfsplus/iomap.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_HFSPLUS_IOMAP_H
+#define _LINUX_HFSPLUS_IOMAP_H
+
+extern const struct iomap_ops hfsplus_iomap_ops;
+extern const struct iomap_ops hfsplus_write_iomap_ops;
+extern const struct iomap_writeback_ops hfsplus_writeback_ops;
+extern const struct iomap_dio_ops hfsplus_write_dio_ops;
+
+int hfsplus_iomap_cont_expand(struct inode *inode, loff_t from, loff_t to);
+void hfsplus_iomap_size_rollback(struct inode *inode, loff_t size);
+int hfsplus_iomap_extend_size(struct inode *inode, loff_t new_size);
+int hfsplus_iomap_swap_activate(struct swap_info_struct *sis,
+ struct file *file, sector_t *span);
+
+#endif /* _LINUX_HFSPLUS_IOMAP_H */
--
2.53.0