diff --git a/Documentation/filesystems/iomap/design.rst b/Documentation/filesystems/iomap/design.rst
index f2df9b6df988..0f7672676c0b 100644
--- a/Documentation/filesystems/iomap/design.rst
+++ b/Documentation/filesystems/iomap/design.rst
@@ -167,7 +167,6 @@ structure below:
struct dax_device *dax_dev;
void *inline_data;
void *private;
- const struct iomap_folio_ops *folio_ops;
u64 validity_cookie;
};
@@ -292,8 +291,6 @@ The fields are as follows:
`_.
This value will be passed unchanged to ``->iomap_end``.
- * ``folio_ops`` will be covered in the section on pagecache operations.
-
* ``validity_cookie`` is a magic freshness value set by the filesystem
that should be used to detect stale mappings.
For pagecache operations this is critical for correct operation
diff --git a/Documentation/filesystems/iomap/operations.rst b/Documentation/filesystems/iomap/operations.rst
index 3b628e370d88..067ed8e14ef3 100644
--- a/Documentation/filesystems/iomap/operations.rst
+++ b/Documentation/filesystems/iomap/operations.rst
@@ -57,21 +57,19 @@ The following address space operations can be wrapped easily:
* ``bmap``
* ``swap_activate``
-``struct iomap_folio_ops``
+``struct iomap_write_ops``
--------------------------
-The ``->iomap_begin`` function for pagecache operations may set the
-``struct iomap::folio_ops`` field to an ops structure to override
-default behaviors of iomap:
-
.. code-block:: c
- struct iomap_folio_ops {
+ struct iomap_write_ops {
struct folio *(*get_folio)(struct iomap_iter *iter, loff_t pos,
unsigned len);
void (*put_folio)(struct inode *inode, loff_t pos, unsigned copied,
struct folio *folio);
bool (*iomap_valid)(struct inode *inode, const struct iomap *iomap);
+ int (*read_folio_range)(const struct iomap_iter *iter,
+ struct folio *folio, loff_t pos, size_t len);
};
iomap calls these functions:
@@ -127,6 +125,10 @@ iomap calls these functions:
``->iomap_valid``, then the iomap should considered stale and the
validation failed.
+ - ``read_folio_range``: Called to synchronously read in the range that will
+ be written to. If this function is not provided, iomap will default to
+ submitting a bio read request.
+
These ``struct kiocb`` flags are significant for buffered I/O with iomap:
* ``IOCB_NOWAIT``: Turns on ``IOMAP_NOWAIT``.
@@ -271,7 +273,7 @@ writeback.
It does not lock ``i_rwsem`` or ``invalidate_lock``.
The dirty bit will be cleared for all folios run through the
-``->map_blocks`` machinery described below even if the writeback fails.
+``->writeback_range`` machinery described below even if the writeback fails.
This is to prevent dirty folio clots when storage devices fail; an
``-EIO`` is recorded for userspace to collect via ``fsync``.
@@ -283,15 +285,14 @@ The ``ops`` structure must be specified and is as follows:
.. code-block:: c
struct iomap_writeback_ops {
- int (*map_blocks)(struct iomap_writepage_ctx *wpc, struct inode *inode,
- loff_t offset, unsigned len);
- int (*submit_ioend)(struct iomap_writepage_ctx *wpc, int status);
- void (*discard_folio)(struct folio *folio, loff_t pos);
+ int (*writeback_range)(struct iomap_writepage_ctx *wpc,
+ struct folio *folio, u64 pos, unsigned int len, u64 end_pos);
+ int (*writeback_submit)(struct iomap_writepage_ctx *wpc, int error);
};
The fields are as follows:
- - ``map_blocks``: Sets ``wpc->iomap`` to the space mapping of the file
+ - ``writeback_range``: Sets ``wpc->iomap`` to the space mapping of the file
range (in bytes) given by ``offset`` and ``len``.
iomap calls this function for each dirty fs block in each dirty folio,
though it will `reuse mappings
@@ -306,27 +307,26 @@ The fields are as follows:
This revalidation must be open-coded by the filesystem; it is
unclear if ``iomap::validity_cookie`` can be reused for this
purpose.
- This function must be supplied by the filesystem.
- - ``submit_ioend``: Allows the file systems to hook into writeback bio
- submission.
- This might include pre-write space accounting updates, or installing
- a custom ``->bi_end_io`` function for internal purposes, such as
- deferring the ioend completion to a workqueue to run metadata update
- transactions from process context before submitting the bio.
- This function is optional.
-
- - ``discard_folio``: iomap calls this function after ``->map_blocks``
- fails to schedule I/O for any part of a dirty folio.
- The function should throw away any reservations that may have been
- made for the write.
+ If this methods fails to schedule I/O for any part of a dirty folio, it
+ should throw away any reservations that may have been made for the write.
The folio will be marked clean and an ``-EIO`` recorded in the
pagecache.
Filesystems can use this callback to `remove
`_
delalloc reservations to avoid having delalloc reservations for
clean pagecache.
- This function is optional.
+ This function must be supplied by the filesystem.
+
+ - ``writeback_submit``: Submit the previous built writeback context.
+ Block based file systems should use the iomap_ioend_writeback_submit
+ helper, other file system can implement their own.
+ File systems can optionall to hook into writeback bio submission.
+ This might include pre-write space accounting updates, or installing
+ a custom ``->bi_end_io`` function for internal purposes, such as
+ deferring the ioend completion to a workqueue to run metadata update
+ transactions from process context before submitting the bio.
+ This function must be supplied by the filesystem.
Pagecache Writeback Completion
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -340,10 +340,9 @@ If the write failed, it will also set the error bits on the folios and
the address space.
This can happen in interrupt or process context, depending on the
storage device.
-
Filesystems that need to update internal bookkeeping (e.g. unwritten
-extent conversions) should provide a ``->submit_ioend`` function to
-set ``struct iomap_end::bio::bi_end_io`` to its own function.
+extent conversions) should set their own bi_end_io on the bios
+submitted by ``->submit_writeback``
This function should call ``iomap_finish_ioends`` after finishing its
own work (e.g. unwritten extent conversion).
diff --git a/block/fops.c b/block/fops.c
index 14f706d3af6e..82451ac8ff25 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -540,30 +540,42 @@ static void blkdev_readahead(struct readahead_control *rac)
iomap_readahead(rac, &blkdev_iomap_ops);
}
-static int blkdev_map_blocks(struct iomap_writepage_ctx *wpc,
- struct inode *inode, loff_t offset, unsigned int len)
+static ssize_t blkdev_writeback_range(struct iomap_writepage_ctx *wpc,
+ struct folio *folio, u64 offset, unsigned int len, u64 end_pos)
{
- loff_t isize = i_size_read(inode);
+ loff_t isize = i_size_read(wpc->inode);
if (WARN_ON_ONCE(offset >= isize))
return -EIO;
- if (offset >= wpc->iomap.offset &&
- offset < wpc->iomap.offset + wpc->iomap.length)
- return 0;
- return blkdev_iomap_begin(inode, offset, isize - offset,
- IOMAP_WRITE, &wpc->iomap, NULL);
+
+ if (offset < wpc->iomap.offset ||
+ offset >= wpc->iomap.offset + wpc->iomap.length) {
+ int error;
+
+ error = blkdev_iomap_begin(wpc->inode, offset, isize - offset,
+ IOMAP_WRITE, &wpc->iomap, NULL);
+ if (error)
+ return error;
+ }
+
+ return iomap_add_to_ioend(wpc, folio, offset, end_pos, len);
}
static const struct iomap_writeback_ops blkdev_writeback_ops = {
- .map_blocks = blkdev_map_blocks,
+ .writeback_range = blkdev_writeback_range,
+ .writeback_submit = iomap_ioend_writeback_submit,
};
static int blkdev_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
- struct iomap_writepage_ctx wpc = { };
+ struct iomap_writepage_ctx wpc = {
+ .inode = mapping->host,
+ .wbc = wbc,
+ .ops = &blkdev_writeback_ops
+ };
- return iomap_writepages(mapping, wbc, &wpc, &blkdev_writeback_ops);
+ return iomap_writepages(&wpc);
}
const struct address_space_operations def_blk_aops = {
@@ -714,7 +726,8 @@ blkdev_direct_write(struct kiocb *iocb, struct iov_iter *from)
static ssize_t blkdev_buffered_write(struct kiocb *iocb, struct iov_iter *from)
{
- return iomap_file_buffered_write(iocb, from, &blkdev_iomap_ops, NULL);
+ return iomap_file_buffered_write(iocb, from, &blkdev_iomap_ops, NULL,
+ NULL);
}
/*
diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig
index ca215a3cba3e..a774166264de 100644
--- a/fs/fuse/Kconfig
+++ b/fs/fuse/Kconfig
@@ -2,6 +2,7 @@
config FUSE_FS
tristate "FUSE (Filesystem in Userspace) support"
select FS_POSIX_ACL
+ select FS_IOMAP
help
With FUSE it is possible to implement a fully functional filesystem
in a userspace program.
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 2ddfb3bb6483..617fd1b562fd 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -21,6 +21,7 @@
#include
#include
#include
+#include
static int fuse_send_open(struct fuse_mount *fm, u64 nodeid,
unsigned int open_flags, int opcode,
@@ -788,12 +789,16 @@ static void fuse_short_read(struct inode *inode, u64 attr_ver, size_t num_read,
}
}
-static int fuse_do_readfolio(struct file *file, struct folio *folio)
+static int fuse_do_readfolio(struct file *file, struct folio *folio,
+ size_t off, size_t len)
{
struct inode *inode = folio->mapping->host;
struct fuse_mount *fm = get_fuse_mount(inode);
- loff_t pos = folio_pos(folio);
- struct fuse_folio_desc desc = { .length = folio_size(folio) };
+ loff_t pos = folio_pos(folio) + off;
+ struct fuse_folio_desc desc = {
+ .offset = off,
+ .length = len,
+ };
struct fuse_io_args ia = {
.ap.args.page_zeroing = true,
.ap.args.out_pages = true,
@@ -820,8 +825,6 @@ static int fuse_do_readfolio(struct file *file, struct folio *folio)
if (res < desc.length)
fuse_short_read(inode, attr_ver, res, &ia.ap);
- folio_mark_uptodate(folio);
-
return 0;
}
@@ -834,13 +837,26 @@ static int fuse_read_folio(struct file *file, struct folio *folio)
if (fuse_is_bad(inode))
goto out;
- err = fuse_do_readfolio(file, folio);
+ err = fuse_do_readfolio(file, folio, 0, folio_size(folio));
+ if (!err)
+ folio_mark_uptodate(folio);
+
fuse_invalidate_atime(inode);
out:
folio_unlock(folio);
return err;
}
+static int fuse_iomap_read_folio_range(const struct iomap_iter *iter,
+ struct folio *folio, loff_t pos,
+ size_t len)
+{
+ struct file *file = iter->private;
+ size_t off = offset_in_folio(folio, pos);
+
+ return fuse_do_readfolio(file, folio, off, len);
+}
+
static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
int err)
{
@@ -1374,6 +1390,24 @@ static void fuse_dio_unlock(struct kiocb *iocb, bool exclusive)
}
}
+static const struct iomap_write_ops fuse_iomap_write_ops = {
+ .read_folio_range = fuse_iomap_read_folio_range,
+};
+
+static int fuse_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
+ unsigned int flags, struct iomap *iomap,
+ struct iomap *srcmap)
+{
+ iomap->type = IOMAP_MAPPED;
+ iomap->length = length;
+ iomap->offset = offset;
+ return 0;
+}
+
+static const struct iomap_ops fuse_iomap_ops = {
+ .iomap_begin = fuse_iomap_begin,
+};
+
static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
@@ -1383,6 +1417,7 @@ static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from)
struct inode *inode = mapping->host;
ssize_t err, count;
struct fuse_conn *fc = get_fuse_conn(inode);
+ bool writeback = false;
if (fc->writeback_cache) {
/* Update size (EOF optimization) and mode (SUID clearing) */
@@ -1391,16 +1426,11 @@ static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (err)
return err;
- if (fc->handle_killpriv_v2 &&
- setattr_should_drop_suidgid(idmap,
- file_inode(file))) {
- goto writethrough;
- }
-
- return generic_file_write_iter(iocb, from);
+ if (!fc->handle_killpriv_v2 ||
+ !setattr_should_drop_suidgid(idmap, file_inode(file)))
+ writeback = true;
}
-writethrough:
inode_lock(inode);
err = count = generic_write_checks(iocb, from);
@@ -1419,6 +1449,15 @@ static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from)
goto out;
written = direct_write_fallback(iocb, from, written,
fuse_perform_write(iocb, from));
+ } else if (writeback) {
+ /*
+ * Use iomap so that we can do granular uptodate reads
+ * and granular dirty tracking for large folios.
+ */
+ written = iomap_file_buffered_write(iocb, from,
+ &fuse_iomap_ops,
+ &fuse_iomap_write_ops,
+ file);
} else {
written = fuse_perform_write(iocb, from);
}
@@ -1793,7 +1832,7 @@ static void fuse_writepage_finish(struct fuse_writepage_args *wpa)
* scope of the fi->lock alleviates xarray lock
* contention and noticeably improves performance.
*/
- folio_end_writeback(ap->folios[i]);
+ iomap_finish_folio_write(inode, ap->folios[i], 1);
dec_wb_stat(&bdi->wb, WB_WRITEBACK);
wb_writeout_inc(&bdi->wb);
}
@@ -1980,19 +2019,20 @@ static void fuse_writepage_add_to_bucket(struct fuse_conn *fc,
}
static void fuse_writepage_args_page_fill(struct fuse_writepage_args *wpa, struct folio *folio,
- uint32_t folio_index)
+ uint32_t folio_index, loff_t offset, unsigned len)
{
struct inode *inode = folio->mapping->host;
struct fuse_args_pages *ap = &wpa->ia.ap;
ap->folios[folio_index] = folio;
- ap->descs[folio_index].offset = 0;
- ap->descs[folio_index].length = folio_size(folio);
+ ap->descs[folio_index].offset = offset;
+ ap->descs[folio_index].length = len;
inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
}
static struct fuse_writepage_args *fuse_writepage_args_setup(struct folio *folio,
+ size_t offset,
struct fuse_file *ff)
{
struct inode *inode = folio->mapping->host;
@@ -2005,7 +2045,7 @@ static struct fuse_writepage_args *fuse_writepage_args_setup(struct folio *folio
return NULL;
fuse_writepage_add_to_bucket(fc, wpa);
- fuse_write_args_fill(&wpa->ia, ff, folio_pos(folio), 0);
+ fuse_write_args_fill(&wpa->ia, ff, folio_pos(folio) + offset, 0);
wpa->ia.write.in.write_flags |= FUSE_WRITE_CACHE;
wpa->inode = inode;
wpa->ia.ff = ff;
@@ -2017,63 +2057,28 @@ static struct fuse_writepage_args *fuse_writepage_args_setup(struct folio *folio
return wpa;
}
-static int fuse_writepage_locked(struct folio *folio)
-{
- struct address_space *mapping = folio->mapping;
- struct inode *inode = mapping->host;
- struct fuse_inode *fi = get_fuse_inode(inode);
- struct fuse_writepage_args *wpa;
- struct fuse_args_pages *ap;
- struct fuse_file *ff;
- int error = -EIO;
-
- ff = fuse_write_file_get(fi);
- if (!ff)
- goto err;
-
- wpa = fuse_writepage_args_setup(folio, ff);
- error = -ENOMEM;
- if (!wpa)
- goto err_writepage_args;
-
- ap = &wpa->ia.ap;
- ap->num_folios = 1;
-
- folio_start_writeback(folio);
- fuse_writepage_args_page_fill(wpa, folio, 0);
-
- spin_lock(&fi->lock);
- list_add_tail(&wpa->queue_entry, &fi->queued_writes);
- fuse_flush_writepages(inode);
- spin_unlock(&fi->lock);
-
- return 0;
-
-err_writepage_args:
- fuse_file_put(ff, false);
-err:
- mapping_set_error(folio->mapping, error);
- return error;
-}
-
struct fuse_fill_wb_data {
struct fuse_writepage_args *wpa;
struct fuse_file *ff;
- struct inode *inode;
unsigned int max_folios;
- unsigned int nr_pages;
+ /*
+ * nr_bytes won't overflow since fuse_writepage_need_send() caps
+ * wb requests to never exceed fc->max_pages (which has an upper bound
+ * of U16_MAX).
+ */
+ unsigned int nr_bytes;
};
-static bool fuse_pages_realloc(struct fuse_fill_wb_data *data)
+static bool fuse_pages_realloc(struct fuse_fill_wb_data *data,
+ unsigned int max_pages)
{
struct fuse_args_pages *ap = &data->wpa->ia.ap;
- struct fuse_conn *fc = get_fuse_conn(data->inode);
struct folio **folios;
struct fuse_folio_desc *descs;
unsigned int nfolios = min_t(unsigned int,
max_t(unsigned int, data->max_folios * 2,
FUSE_DEFAULT_MAX_PAGES_PER_REQ),
- fc->max_pages);
+ max_pages);
WARN_ON(nfolios <= data->max_folios);
folios = fuse_folios_alloc(nfolios, GFP_NOFS, &descs);
@@ -2090,10 +2095,10 @@ static bool fuse_pages_realloc(struct fuse_fill_wb_data *data)
return true;
}
-static void fuse_writepages_send(struct fuse_fill_wb_data *data)
+static void fuse_writepages_send(struct inode *inode,
+ struct fuse_fill_wb_data *data)
{
struct fuse_writepage_args *wpa = data->wpa;
- struct inode *inode = data->inode;
struct fuse_inode *fi = get_fuse_inode(inode);
spin_lock(&fi->lock);
@@ -2102,199 +2107,150 @@ static void fuse_writepages_send(struct fuse_fill_wb_data *data)
spin_unlock(&fi->lock);
}
-static bool fuse_writepage_need_send(struct fuse_conn *fc, struct folio *folio,
- struct fuse_args_pages *ap,
+static bool fuse_writepage_need_send(struct fuse_conn *fc, loff_t pos,
+ unsigned len, struct fuse_args_pages *ap,
struct fuse_fill_wb_data *data)
{
+ struct folio *prev_folio;
+ struct fuse_folio_desc prev_desc;
+ unsigned bytes = data->nr_bytes + len;
+ loff_t prev_pos;
+
WARN_ON(!ap->num_folios);
/* Reached max pages */
- if (data->nr_pages + folio_nr_pages(folio) > fc->max_pages)
+ if ((bytes + PAGE_SIZE - 1) >> PAGE_SHIFT > fc->max_pages)
return true;
/* Reached max write bytes */
- if ((data->nr_pages * PAGE_SIZE) + folio_size(folio) > fc->max_write)
+ if (bytes > fc->max_write)
return true;
/* Discontinuity */
- if (folio_next_index(ap->folios[ap->num_folios - 1]) != folio->index)
+ prev_folio = ap->folios[ap->num_folios - 1];
+ prev_desc = ap->descs[ap->num_folios - 1];
+ prev_pos = folio_pos(prev_folio) + prev_desc.offset + prev_desc.length;
+ if (prev_pos != pos)
return true;
/* Need to grow the pages array? If so, did the expansion fail? */
- if (ap->num_folios == data->max_folios && !fuse_pages_realloc(data))
+ if (ap->num_folios == data->max_folios &&
+ !fuse_pages_realloc(data, fc->max_pages))
return true;
return false;
}
-static int fuse_writepages_fill(struct folio *folio,
- struct writeback_control *wbc, void *_data)
+static ssize_t fuse_iomap_writeback_range(struct iomap_writepage_ctx *wpc,
+ struct folio *folio, u64 pos,
+ unsigned len, u64 end_pos)
{
- struct fuse_fill_wb_data *data = _data;
+ struct fuse_fill_wb_data *data = wpc->wb_ctx;
struct fuse_writepage_args *wpa = data->wpa;
struct fuse_args_pages *ap = &wpa->ia.ap;
- struct inode *inode = data->inode;
+ struct inode *inode = wpc->inode;
struct fuse_inode *fi = get_fuse_inode(inode);
struct fuse_conn *fc = get_fuse_conn(inode);
- int err;
+ loff_t offset = offset_in_folio(folio, pos);
+
+ WARN_ON_ONCE(!data);
+ /* len will always be page aligned */
+ WARN_ON_ONCE(len & (PAGE_SIZE - 1));
if (!data->ff) {
- err = -EIO;
data->ff = fuse_write_file_get(fi);
if (!data->ff)
- goto out_unlock;
+ return -EIO;
}
- if (wpa && fuse_writepage_need_send(fc, folio, ap, data)) {
- fuse_writepages_send(data);
+ if (wpa && fuse_writepage_need_send(fc, pos, len, ap, data)) {
+ fuse_writepages_send(inode, data);
data->wpa = NULL;
- data->nr_pages = 0;
+ data->nr_bytes = 0;
}
if (data->wpa == NULL) {
- err = -ENOMEM;
- wpa = fuse_writepage_args_setup(folio, data->ff);
+ wpa = fuse_writepage_args_setup(folio, offset, data->ff);
if (!wpa)
- goto out_unlock;
+ return -ENOMEM;
fuse_file_get(wpa->ia.ff);
data->max_folios = 1;
ap = &wpa->ia.ap;
}
- folio_start_writeback(folio);
- fuse_writepage_args_page_fill(wpa, folio, ap->num_folios);
- data->nr_pages += folio_nr_pages(folio);
+ iomap_start_folio_write(inode, folio, 1);
+ fuse_writepage_args_page_fill(wpa, folio, ap->num_folios,
+ offset, len);
+ data->nr_bytes += len;
- err = 0;
ap->num_folios++;
if (!data->wpa)
data->wpa = wpa;
-out_unlock:
- folio_unlock(folio);
- return err;
+ return len;
}
+static int fuse_iomap_writeback_submit(struct iomap_writepage_ctx *wpc,
+ int error)
+{
+ struct fuse_fill_wb_data *data = wpc->wb_ctx;
+
+ WARN_ON_ONCE(!data);
+
+ if (data->wpa) {
+ WARN_ON(!data->wpa->ia.ap.num_folios);
+ fuse_writepages_send(wpc->inode, data);
+ }
+
+ if (data->ff)
+ fuse_file_put(data->ff, false);
+
+ return error;
+}
+
+static const struct iomap_writeback_ops fuse_writeback_ops = {
+ .writeback_range = fuse_iomap_writeback_range,
+ .writeback_submit = fuse_iomap_writeback_submit,
+};
+
static int fuse_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
struct fuse_conn *fc = get_fuse_conn(inode);
- struct fuse_fill_wb_data data;
- int err;
+ struct fuse_fill_wb_data data = {};
+ struct iomap_writepage_ctx wpc = {
+ .inode = inode,
+ .iomap.type = IOMAP_MAPPED,
+ .wbc = wbc,
+ .ops = &fuse_writeback_ops,
+ .wb_ctx = &data,
+ };
- err = -EIO;
if (fuse_is_bad(inode))
- goto out;
+ return -EIO;
if (wbc->sync_mode == WB_SYNC_NONE &&
fc->num_background >= fc->congestion_threshold)
return 0;
- data.inode = inode;
- data.wpa = NULL;
- data.ff = NULL;
- data.nr_pages = 0;
-
- err = write_cache_pages(mapping, wbc, fuse_writepages_fill, &data);
- if (data.wpa) {
- WARN_ON(!data.wpa->ia.ap.num_folios);
- fuse_writepages_send(&data);
- }
- if (data.ff)
- fuse_file_put(data.ff, false);
-
-out:
- return err;
-}
-
-/*
- * It's worthy to make sure that space is reserved on disk for the write,
- * but how to implement it without killing performance need more thinking.
- */
-static int fuse_write_begin(const struct kiocb *iocb,
- struct address_space *mapping,
- loff_t pos, unsigned len, struct folio **foliop,
- void **fsdata)
-{
- pgoff_t index = pos >> PAGE_SHIFT;
- struct file *file = iocb->ki_filp;
- struct fuse_conn *fc = get_fuse_conn(file_inode(file));
- struct folio *folio;
- loff_t fsize;
- int err = -ENOMEM;
-
- WARN_ON(!fc->writeback_cache);
-
- folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
- mapping_gfp_mask(mapping));
- if (IS_ERR(folio))
- goto error;
-
- if (folio_test_uptodate(folio) || len >= folio_size(folio))
- goto success;
- /*
- * Check if the start of this folio comes after the end of file,
- * in which case the readpage can be optimized away.
- */
- fsize = i_size_read(mapping->host);
- if (fsize <= folio_pos(folio)) {
- size_t off = offset_in_folio(folio, pos);
- if (off)
- folio_zero_segment(folio, 0, off);
- goto success;
- }
- err = fuse_do_readfolio(file, folio);
- if (err)
- goto cleanup;
-success:
- *foliop = folio;
- return 0;
-
-cleanup:
- folio_unlock(folio);
- folio_put(folio);
-error:
- return err;
-}
-
-static int fuse_write_end(const struct kiocb *iocb,
- struct address_space *mapping,
- loff_t pos, unsigned len, unsigned copied,
- struct folio *folio, void *fsdata)
-{
- struct inode *inode = folio->mapping->host;
-
- /* Haven't copied anything? Skip zeroing, size extending, dirtying. */
- if (!copied)
- goto unlock;
-
- pos += copied;
- if (!folio_test_uptodate(folio)) {
- /* Zero any unwritten bytes at the end of the page */
- size_t endoff = pos & ~PAGE_MASK;
- if (endoff)
- folio_zero_segment(folio, endoff, PAGE_SIZE);
- folio_mark_uptodate(folio);
- }
-
- if (pos > inode->i_size)
- i_size_write(inode, pos);
-
- folio_mark_dirty(folio);
-
-unlock:
- folio_unlock(folio);
- folio_put(folio);
-
- return copied;
+ return iomap_writepages(&wpc);
}
static int fuse_launder_folio(struct folio *folio)
{
int err = 0;
+ struct fuse_fill_wb_data data = {};
+ struct iomap_writepage_ctx wpc = {
+ .inode = folio->mapping->host,
+ .iomap.type = IOMAP_MAPPED,
+ .ops = &fuse_writeback_ops,
+ .wb_ctx = &data,
+ };
+
if (folio_clear_dirty_for_io(folio)) {
- err = fuse_writepage_locked(folio);
+ err = iomap_writeback_folio(&wpc, folio);
+ err = fuse_iomap_writeback_submit(&wpc, err);
if (!err)
folio_wait_writeback(folio);
}
@@ -3147,12 +3103,13 @@ static const struct address_space_operations fuse_file_aops = {
.readahead = fuse_readahead,
.writepages = fuse_writepages,
.launder_folio = fuse_launder_folio,
- .dirty_folio = filemap_dirty_folio,
+ .dirty_folio = iomap_dirty_folio,
+ .release_folio = iomap_release_folio,
+ .invalidate_folio = iomap_invalidate_folio,
+ .is_partially_uptodate = iomap_is_partially_uptodate,
.migrate_folio = filemap_migrate_folio,
.bmap = fuse_bmap,
.direct_IO = fuse_direct_IO,
- .write_begin = fuse_write_begin,
- .write_end = fuse_write_end,
};
void fuse_init_file_inode(struct inode *inode, unsigned int flags)
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 14f204cd5a82..47d74afd63ac 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -159,7 +159,11 @@ static int gfs2_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping);
- struct iomap_writepage_ctx wpc = { };
+ struct iomap_writepage_ctx wpc = {
+ .inode = mapping->host,
+ .wbc = wbc,
+ .ops = &gfs2_writeback_ops,
+ };
int ret;
/*
@@ -168,7 +172,7 @@ static int gfs2_writepages(struct address_space *mapping,
* want balance_dirty_pages() to loop indefinitely trying to write out
* pages held in the ail that it can't find.
*/
- ret = iomap_writepages(mapping, wbc, &wpc, &gfs2_writeback_ops);
+ ret = iomap_writepages(&wpc);
if (ret == 0 && wbc->nr_to_write > 0)
set_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags);
return ret;
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 7703d0471139..131091520de6 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -963,12 +963,16 @@ static struct folio *
gfs2_iomap_get_folio(struct iomap_iter *iter, loff_t pos, unsigned len)
{
struct inode *inode = iter->inode;
+ struct gfs2_inode *ip = GFS2_I(inode);
unsigned int blockmask = i_blocksize(inode) - 1;
struct gfs2_sbd *sdp = GFS2_SB(inode);
unsigned int blocks;
struct folio *folio;
int status;
+ if (!gfs2_is_jdata(ip) && !gfs2_is_stuffed(ip))
+ return iomap_get_folio(iter, pos, len);
+
blocks = ((pos & blockmask) + len + blockmask) >> inode->i_blkbits;
status = gfs2_trans_begin(sdp, RES_DINODE + blocks, 0);
if (status)
@@ -987,7 +991,7 @@ static void gfs2_iomap_put_folio(struct inode *inode, loff_t pos,
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
- if (!gfs2_is_stuffed(ip))
+ if (gfs2_is_jdata(ip) && !gfs2_is_stuffed(ip))
gfs2_trans_add_databufs(ip->i_gl, folio,
offset_in_folio(folio, pos),
copied);
@@ -995,13 +999,14 @@ static void gfs2_iomap_put_folio(struct inode *inode, loff_t pos,
folio_unlock(folio);
folio_put(folio);
- if (tr->tr_num_buf_new)
- __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
-
- gfs2_trans_end(sdp);
+ if (gfs2_is_jdata(ip) || gfs2_is_stuffed(ip)) {
+ if (tr->tr_num_buf_new)
+ __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+ gfs2_trans_end(sdp);
+ }
}
-static const struct iomap_folio_ops gfs2_iomap_folio_ops = {
+const struct iomap_write_ops gfs2_iomap_write_ops = {
.get_folio = gfs2_iomap_get_folio,
.put_folio = gfs2_iomap_put_folio,
};
@@ -1078,8 +1083,6 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
gfs2_trans_end(sdp);
}
- if (gfs2_is_stuffed(ip) || gfs2_is_jdata(ip))
- iomap->folio_ops = &gfs2_iomap_folio_ops;
return 0;
out_trans_end:
@@ -1304,7 +1307,7 @@ static int gfs2_block_zero_range(struct inode *inode, loff_t from, loff_t length
return 0;
length = min(length, inode->i_size - from);
return iomap_zero_range(inode, from, length, NULL, &gfs2_iomap_ops,
- NULL);
+ &gfs2_iomap_write_ops, NULL);
}
#define GFS2_JTRUNC_REVOKES 8192
@@ -2469,23 +2472,26 @@ int __gfs2_punch_hole(struct file *file, loff_t offset, loff_t length)
return error;
}
-static int gfs2_map_blocks(struct iomap_writepage_ctx *wpc, struct inode *inode,
- loff_t offset, unsigned int len)
+static ssize_t gfs2_writeback_range(struct iomap_writepage_ctx *wpc,
+ struct folio *folio, u64 offset, unsigned int len, u64 end_pos)
{
- int ret;
-
- if (WARN_ON_ONCE(gfs2_is_stuffed(GFS2_I(inode))))
+ if (WARN_ON_ONCE(gfs2_is_stuffed(GFS2_I(wpc->inode))))
return -EIO;
- if (offset >= wpc->iomap.offset &&
- offset < wpc->iomap.offset + wpc->iomap.length)
- return 0;
+ if (offset < wpc->iomap.offset ||
+ offset >= wpc->iomap.offset + wpc->iomap.length) {
+ int ret;
- memset(&wpc->iomap, 0, sizeof(wpc->iomap));
- ret = gfs2_iomap_get(inode, offset, INT_MAX, &wpc->iomap);
- return ret;
+ memset(&wpc->iomap, 0, sizeof(wpc->iomap));
+ ret = gfs2_iomap_get(wpc->inode, offset, INT_MAX, &wpc->iomap);
+ if (ret)
+ return ret;
+ }
+
+ return iomap_add_to_ioend(wpc, folio, offset, end_pos, len);
}
const struct iomap_writeback_ops gfs2_writeback_ops = {
- .map_blocks = gfs2_map_blocks,
+ .writeback_range = gfs2_writeback_range,
+ .writeback_submit = iomap_ioend_writeback_submit,
};
diff --git a/fs/gfs2/bmap.h b/fs/gfs2/bmap.h
index 4e8b1e8ebdf3..6cdc72dd55a3 100644
--- a/fs/gfs2/bmap.h
+++ b/fs/gfs2/bmap.h
@@ -44,6 +44,7 @@ static inline void gfs2_write_calc_reserv(const struct gfs2_inode *ip,
}
extern const struct iomap_ops gfs2_iomap_ops;
+extern const struct iomap_write_ops gfs2_iomap_write_ops;
extern const struct iomap_writeback_ops gfs2_writeback_ops;
int gfs2_unstuff_dinode(struct gfs2_inode *ip);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 65f4371f428c..72d95185a39f 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -1058,7 +1058,8 @@ static ssize_t gfs2_file_buffered_write(struct kiocb *iocb,
}
pagefault_disable();
- ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops, NULL);
+ ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops,
+ &gfs2_iomap_write_ops, NULL);
pagefault_enable();
if (ret > 0)
written += ret;
diff --git a/fs/iomap/Makefile b/fs/iomap/Makefile
index 69e8ebb41302..f7e1c8534c46 100644
--- a/fs/iomap/Makefile
+++ b/fs/iomap/Makefile
@@ -9,9 +9,9 @@ ccflags-y += -I $(src) # needed for trace events
obj-$(CONFIG_FS_IOMAP) += iomap.o
iomap-y += trace.o \
- iter.o
-iomap-$(CONFIG_BLOCK) += buffered-io.o \
- direct-io.o \
+ iter.o \
+ buffered-io.o
+iomap-$(CONFIG_BLOCK) += direct-io.o \
ioend.o \
fiemap.o \
seek.o
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 8f29be98a46e..fd827398afd2 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -3,20 +3,11 @@
* Copyright (C) 2010 Red Hat, Inc.
* Copyright (C) 2016-2023 Christoph Hellwig.
*/
-#include
-#include
-#include
#include
-#include
-#include
#include
-#include
#include
#include
-#include
-#include
#include
-#include "internal.h"
#include "trace.h"
#include "../internal.h"
@@ -287,6 +278,46 @@ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio,
*lenp = plen;
}
+static inline bool iomap_block_needs_zeroing(const struct iomap_iter *iter,
+ loff_t pos)
+{
+ const struct iomap *srcmap = iomap_iter_srcmap(iter);
+
+ return srcmap->type != IOMAP_MAPPED ||
+ (srcmap->flags & IOMAP_F_NEW) ||
+ pos >= i_size_read(iter->inode);
+}
+
+/**
+ * iomap_read_inline_data - copy inline data into the page cache
+ * @iter: iteration structure
+ * @folio: folio to copy to
+ *
+ * Copy the inline data in @iter into @folio and zero out the rest of the folio.
+ * Only a single IOMAP_INLINE extent is allowed at the end of each file.
+ * Returns zero for success to complete the read, or the usual negative errno.
+ */
+static int iomap_read_inline_data(const struct iomap_iter *iter,
+ struct folio *folio)
+{
+ const struct iomap *iomap = iomap_iter_srcmap(iter);
+ size_t size = i_size_read(iter->inode) - iomap->offset;
+ size_t offset = offset_in_folio(folio, iomap->offset);
+
+ if (folio_test_uptodate(folio))
+ return 0;
+
+ if (WARN_ON_ONCE(size > iomap->length))
+ return -EIO;
+ if (offset > 0)
+ ifs_alloc(iter->inode, folio, iter->flags);
+
+ folio_fill_tail(folio, offset, iomap->inline_data, size);
+ iomap_set_range_uptodate(folio, offset, folio_size(folio) - offset);
+ return 0;
+}
+
+#ifdef CONFIG_BLOCK
static void iomap_finish_folio_read(struct folio *folio, size_t off,
size_t len, int error)
{
@@ -326,45 +357,6 @@ struct iomap_readpage_ctx {
struct readahead_control *rac;
};
-/**
- * iomap_read_inline_data - copy inline data into the page cache
- * @iter: iteration structure
- * @folio: folio to copy to
- *
- * Copy the inline data in @iter into @folio and zero out the rest of the folio.
- * Only a single IOMAP_INLINE extent is allowed at the end of each file.
- * Returns zero for success to complete the read, or the usual negative errno.
- */
-static int iomap_read_inline_data(const struct iomap_iter *iter,
- struct folio *folio)
-{
- const struct iomap *iomap = iomap_iter_srcmap(iter);
- size_t size = i_size_read(iter->inode) - iomap->offset;
- size_t offset = offset_in_folio(folio, iomap->offset);
-
- if (folio_test_uptodate(folio))
- return 0;
-
- if (WARN_ON_ONCE(size > iomap->length))
- return -EIO;
- if (offset > 0)
- ifs_alloc(iter->inode, folio, iter->flags);
-
- folio_fill_tail(folio, offset, iomap->inline_data, size);
- iomap_set_range_uptodate(folio, offset, folio_size(folio) - offset);
- return 0;
-}
-
-static inline bool iomap_block_needs_zeroing(const struct iomap_iter *iter,
- loff_t pos)
-{
- const struct iomap *srcmap = iomap_iter_srcmap(iter);
-
- return srcmap->type != IOMAP_MAPPED ||
- (srcmap->flags & IOMAP_F_NEW) ||
- pos >= i_size_read(iter->inode);
-}
-
static int iomap_readpage_iter(struct iomap_iter *iter,
struct iomap_readpage_ctx *ctx)
{
@@ -557,6 +549,27 @@ void iomap_readahead(struct readahead_control *rac, const struct iomap_ops *ops)
}
EXPORT_SYMBOL_GPL(iomap_readahead);
+static int iomap_read_folio_range(const struct iomap_iter *iter,
+ struct folio *folio, loff_t pos, size_t len)
+{
+ const struct iomap *srcmap = iomap_iter_srcmap(iter);
+ struct bio_vec bvec;
+ struct bio bio;
+
+ bio_init(&bio, srcmap->bdev, &bvec, 1, REQ_OP_READ);
+ bio.bi_iter.bi_sector = iomap_sector(srcmap, pos);
+ bio_add_folio_nofail(&bio, folio, len, offset_in_folio(folio, pos));
+ return submit_bio_wait(&bio);
+}
+#else
+static int iomap_read_folio_range(const struct iomap_iter *iter,
+ struct folio *folio, loff_t pos, size_t len)
+{
+ WARN_ON_ONCE(1);
+ return -EIO;
+}
+#endif /* CONFIG_BLOCK */
+
/*
* iomap_is_partially_uptodate checks whether blocks within a folio are
* uptodate or not.
@@ -670,22 +683,10 @@ iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
pos + len - 1);
}
-static int iomap_read_folio_sync(loff_t block_start, struct folio *folio,
- size_t poff, size_t plen, const struct iomap *iomap)
-{
- struct bio_vec bvec;
- struct bio bio;
-
- bio_init(&bio, iomap->bdev, &bvec, 1, REQ_OP_READ);
- bio.bi_iter.bi_sector = iomap_sector(iomap, block_start);
- bio_add_folio_nofail(&bio, folio, plen, poff);
- return submit_bio_wait(&bio);
-}
-
-static int __iomap_write_begin(const struct iomap_iter *iter, size_t len,
+static int __iomap_write_begin(const struct iomap_iter *iter,
+ const struct iomap_write_ops *write_ops, size_t len,
struct folio *folio)
{
- const struct iomap *srcmap = iomap_iter_srcmap(iter);
struct iomap_folio_state *ifs;
loff_t pos = iter->pos;
loff_t block_size = i_blocksize(iter->inode);
@@ -734,8 +735,12 @@ static int __iomap_write_begin(const struct iomap_iter *iter, size_t len,
if (iter->flags & IOMAP_NOWAIT)
return -EAGAIN;
- status = iomap_read_folio_sync(block_start, folio,
- poff, plen, srcmap);
+ if (write_ops && write_ops->read_folio_range)
+ status = write_ops->read_folio_range(iter,
+ folio, block_start, plen);
+ else
+ status = iomap_read_folio_range(iter,
+ folio, block_start, plen);
if (status)
return status;
}
@@ -745,28 +750,27 @@ static int __iomap_write_begin(const struct iomap_iter *iter, size_t len,
return 0;
}
-static struct folio *__iomap_get_folio(struct iomap_iter *iter, size_t len)
+static struct folio *__iomap_get_folio(struct iomap_iter *iter,
+ const struct iomap_write_ops *write_ops, size_t len)
{
- const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops;
loff_t pos = iter->pos;
if (!mapping_large_folio_support(iter->inode->i_mapping))
len = min_t(size_t, len, PAGE_SIZE - offset_in_page(pos));
- if (folio_ops && folio_ops->get_folio)
- return folio_ops->get_folio(iter, pos, len);
- else
- return iomap_get_folio(iter, pos, len);
+ if (write_ops && write_ops->get_folio)
+ return write_ops->get_folio(iter, pos, len);
+ return iomap_get_folio(iter, pos, len);
}
-static void __iomap_put_folio(struct iomap_iter *iter, size_t ret,
+static void __iomap_put_folio(struct iomap_iter *iter,
+ const struct iomap_write_ops *write_ops, size_t ret,
struct folio *folio)
{
- const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops;
loff_t pos = iter->pos;
- if (folio_ops && folio_ops->put_folio) {
- folio_ops->put_folio(iter->inode, pos, ret, folio);
+ if (write_ops && write_ops->put_folio) {
+ write_ops->put_folio(iter->inode, pos, ret, folio);
} else {
folio_unlock(folio);
folio_put(folio);
@@ -803,10 +807,10 @@ static int iomap_write_begin_inline(const struct iomap_iter *iter,
* offset, and length. Callers can optionally pass a max length *plen,
* otherwise init to zero.
*/
-static int iomap_write_begin(struct iomap_iter *iter, struct folio **foliop,
+static int iomap_write_begin(struct iomap_iter *iter,
+ const struct iomap_write_ops *write_ops, struct folio **foliop,
size_t *poffset, u64 *plen)
{
- const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops;
const struct iomap *srcmap = iomap_iter_srcmap(iter);
loff_t pos = iter->pos;
u64 len = min_t(u64, SIZE_MAX, iomap_length(iter));
@@ -821,7 +825,7 @@ static int iomap_write_begin(struct iomap_iter *iter, struct folio **foliop,
if (fatal_signal_pending(current))
return -EINTR;
- folio = __iomap_get_folio(iter, len);
+ folio = __iomap_get_folio(iter, write_ops, len);
if (IS_ERR(folio))
return PTR_ERR(folio);
@@ -835,8 +839,8 @@ static int iomap_write_begin(struct iomap_iter *iter, struct folio **foliop,
* could do the wrong thing here (zero a page range incorrectly or fail
* to zero) and corrupt data.
*/
- if (folio_ops && folio_ops->iomap_valid) {
- bool iomap_valid = folio_ops->iomap_valid(iter->inode,
+ if (write_ops && write_ops->iomap_valid) {
+ bool iomap_valid = write_ops->iomap_valid(iter->inode,
&iter->iomap);
if (!iomap_valid) {
iter->iomap.flags |= IOMAP_F_STALE;
@@ -852,7 +856,7 @@ static int iomap_write_begin(struct iomap_iter *iter, struct folio **foliop,
else if (srcmap->flags & IOMAP_F_BUFFER_HEAD)
status = __block_write_begin_int(folio, pos, len, NULL, srcmap);
else
- status = __iomap_write_begin(iter, len, folio);
+ status = __iomap_write_begin(iter, write_ops, len, folio);
if (unlikely(status))
goto out_unlock;
@@ -862,8 +866,7 @@ static int iomap_write_begin(struct iomap_iter *iter, struct folio **foliop,
return 0;
out_unlock:
- __iomap_put_folio(iter, 0, folio);
-
+ __iomap_put_folio(iter, write_ops, 0, folio);
return status;
}
@@ -934,7 +937,8 @@ static bool iomap_write_end(struct iomap_iter *iter, size_t len, size_t copied,
return __iomap_write_end(iter->inode, pos, len, copied, folio);
}
-static int iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
+static int iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i,
+ const struct iomap_write_ops *write_ops)
{
ssize_t total_written = 0;
int status = 0;
@@ -978,7 +982,8 @@ static int iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
break;
}
- status = iomap_write_begin(iter, &folio, &offset, &bytes);
+ status = iomap_write_begin(iter, write_ops, &folio, &offset,
+ &bytes);
if (unlikely(status)) {
iomap_write_failed(iter->inode, iter->pos, bytes);
break;
@@ -1007,7 +1012,7 @@ static int iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
i_size_write(iter->inode, pos + written);
iter->iomap.flags |= IOMAP_F_SIZE_CHANGED;
}
- __iomap_put_folio(iter, written, folio);
+ __iomap_put_folio(iter, write_ops, written, folio);
if (old_size < pos)
pagecache_isize_extended(iter->inode, old_size, pos);
@@ -1040,7 +1045,8 @@ static int iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
ssize_t
iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i,
- const struct iomap_ops *ops, void *private)
+ const struct iomap_ops *ops,
+ const struct iomap_write_ops *write_ops, void *private)
{
struct iomap_iter iter = {
.inode = iocb->ki_filp->f_mapping->host,
@@ -1057,7 +1063,7 @@ iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i,
iter.flags |= IOMAP_DONTCACHE;
while ((ret = iomap_iter(&iter, ops)) > 0)
- iter.status = iomap_write_iter(&iter, i);
+ iter.status = iomap_write_iter(&iter, i, write_ops);
if (unlikely(iter.pos == iocb->ki_pos))
return ret;
@@ -1291,7 +1297,8 @@ void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte,
}
EXPORT_SYMBOL_GPL(iomap_write_delalloc_release);
-static int iomap_unshare_iter(struct iomap_iter *iter)
+static int iomap_unshare_iter(struct iomap_iter *iter,
+ const struct iomap_write_ops *write_ops)
{
struct iomap *iomap = &iter->iomap;
u64 bytes = iomap_length(iter);
@@ -1306,14 +1313,15 @@ static int iomap_unshare_iter(struct iomap_iter *iter)
bool ret;
bytes = min_t(u64, SIZE_MAX, bytes);
- status = iomap_write_begin(iter, &folio, &offset, &bytes);
+ status = iomap_write_begin(iter, write_ops, &folio, &offset,
+ &bytes);
if (unlikely(status))
return status;
if (iomap->flags & IOMAP_F_STALE)
break;
ret = iomap_write_end(iter, bytes, bytes, folio);
- __iomap_put_folio(iter, bytes, folio);
+ __iomap_put_folio(iter, write_ops, bytes, folio);
if (WARN_ON_ONCE(!ret))
return -EIO;
@@ -1331,7 +1339,8 @@ static int iomap_unshare_iter(struct iomap_iter *iter)
int
iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
- const struct iomap_ops *ops)
+ const struct iomap_ops *ops,
+ const struct iomap_write_ops *write_ops)
{
struct iomap_iter iter = {
.inode = inode,
@@ -1346,7 +1355,7 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
iter.len = min(len, size - pos);
while ((ret = iomap_iter(&iter, ops)) > 0)
- iter.status = iomap_unshare_iter(&iter);
+ iter.status = iomap_unshare_iter(&iter, write_ops);
return ret;
}
EXPORT_SYMBOL_GPL(iomap_file_unshare);
@@ -1365,7 +1374,8 @@ static inline int iomap_zero_iter_flush_and_stale(struct iomap_iter *i)
return filemap_write_and_wait_range(mapping, i->pos, end);
}
-static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
+static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero,
+ const struct iomap_write_ops *write_ops)
{
u64 bytes = iomap_length(iter);
int status;
@@ -1376,7 +1386,8 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
bool ret;
bytes = min_t(u64, SIZE_MAX, bytes);
- status = iomap_write_begin(iter, &folio, &offset, &bytes);
+ status = iomap_write_begin(iter, write_ops, &folio, &offset,
+ &bytes);
if (status)
return status;
if (iter->iomap.flags & IOMAP_F_STALE)
@@ -1389,7 +1400,7 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
folio_mark_accessed(folio);
ret = iomap_write_end(iter, bytes, bytes, folio);
- __iomap_put_folio(iter, bytes, folio);
+ __iomap_put_folio(iter, write_ops, bytes, folio);
if (WARN_ON_ONCE(!ret))
return -EIO;
@@ -1405,7 +1416,8 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
int
iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
- const struct iomap_ops *ops, void *private)
+ const struct iomap_ops *ops,
+ const struct iomap_write_ops *write_ops, void *private)
{
struct iomap_iter iter = {
.inode = inode,
@@ -1435,7 +1447,8 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
filemap_range_needs_writeback(mapping, pos, pos + plen - 1)) {
iter.len = plen;
while ((ret = iomap_iter(&iter, ops)) > 0)
- iter.status = iomap_zero_iter(&iter, did_zero);
+ iter.status = iomap_zero_iter(&iter, did_zero,
+ write_ops);
iter.len = len - (iter.pos - pos);
if (ret || !iter.len)
@@ -1466,7 +1479,7 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
continue;
}
- iter.status = iomap_zero_iter(&iter, did_zero);
+ iter.status = iomap_zero_iter(&iter, did_zero, write_ops);
}
return ret;
}
@@ -1474,7 +1487,8 @@ EXPORT_SYMBOL_GPL(iomap_zero_range);
int
iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
- const struct iomap_ops *ops, void *private)
+ const struct iomap_ops *ops,
+ const struct iomap_write_ops *write_ops, void *private)
{
unsigned int blocksize = i_blocksize(inode);
unsigned int off = pos & (blocksize - 1);
@@ -1483,7 +1497,7 @@ iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
if (!off)
return 0;
return iomap_zero_range(inode, pos, blocksize - off, did_zero, ops,
- private);
+ write_ops, private);
}
EXPORT_SYMBOL_GPL(iomap_truncate_page);
@@ -1537,7 +1551,18 @@ vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops,
}
EXPORT_SYMBOL_GPL(iomap_page_mkwrite);
-static void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
+void iomap_start_folio_write(struct inode *inode, struct folio *folio,
+ size_t len)
+{
+ struct iomap_folio_state *ifs = folio->private;
+
+ WARN_ON_ONCE(i_blocks_per_folio(inode, folio) > 1 && !ifs);
+ if (ifs)
+ atomic_add(len, &ifs->write_bytes_pending);
+}
+EXPORT_SYMBOL_GPL(iomap_start_folio_write);
+
+void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
size_t len)
{
struct iomap_folio_state *ifs = folio->private;
@@ -1548,269 +1573,32 @@ static void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
if (!ifs || atomic_sub_and_test(len, &ifs->write_bytes_pending))
folio_end_writeback(folio);
}
+EXPORT_SYMBOL_GPL(iomap_finish_folio_write);
-/*
- * We're now finished for good with this ioend structure. Update the page
- * state, release holds on bios, and finally free up memory. Do not use the
- * ioend after this.
- */
-u32 iomap_finish_ioend_buffered(struct iomap_ioend *ioend)
+static int iomap_writeback_range(struct iomap_writepage_ctx *wpc,
+ struct folio *folio, u64 pos, u32 rlen, u64 end_pos,
+ bool *wb_pending)
{
- struct inode *inode = ioend->io_inode;
- struct bio *bio = &ioend->io_bio;
- struct folio_iter fi;
- u32 folio_count = 0;
-
- if (ioend->io_error) {
- mapping_set_error(inode->i_mapping, ioend->io_error);
- if (!bio_flagged(bio, BIO_QUIET)) {
- pr_err_ratelimited(
-"%s: writeback error on inode %lu, offset %lld, sector %llu",
- inode->i_sb->s_id, inode->i_ino,
- ioend->io_offset, ioend->io_sector);
- }
- }
-
- /* walk all folios in bio, ending page IO on them */
- bio_for_each_folio_all(fi, bio) {
- iomap_finish_folio_write(inode, fi.folio, fi.length);
- folio_count++;
- }
-
- bio_put(bio); /* frees the ioend */
- return folio_count;
-}
-
-static void iomap_writepage_end_bio(struct bio *bio)
-{
- struct iomap_ioend *ioend = iomap_ioend_from_bio(bio);
-
- ioend->io_error = blk_status_to_errno(bio->bi_status);
- iomap_finish_ioend_buffered(ioend);
-}
-
-/*
- * Submit an ioend.
- *
- * If @error is non-zero, it means that we have a situation where some part of
- * the submission process has failed after we've marked pages for writeback.
- * We cannot cancel ioend directly in that case, so call the bio end I/O handler
- * with the error status here to run the normal I/O completion handler to clear
- * the writeback bit and let the file system proess the errors.
- */
-static int iomap_submit_ioend(struct iomap_writepage_ctx *wpc, int error)
-{
- if (!wpc->ioend)
- return error;
-
- /*
- * Let the file systems prepare the I/O submission and hook in an I/O
- * comletion handler. This also needs to happen in case after a
- * failure happened so that the file system end I/O handler gets called
- * to clean up.
- */
- if (wpc->ops->submit_ioend) {
- error = wpc->ops->submit_ioend(wpc, error);
- } else {
- if (WARN_ON_ONCE(wpc->iomap.flags & IOMAP_F_ANON_WRITE))
- error = -EIO;
- if (!error)
- submit_bio(&wpc->ioend->io_bio);
- }
-
- if (error) {
- wpc->ioend->io_bio.bi_status = errno_to_blk_status(error);
- bio_endio(&wpc->ioend->io_bio);
- }
-
- wpc->ioend = NULL;
- return error;
-}
-
-static struct iomap_ioend *iomap_alloc_ioend(struct iomap_writepage_ctx *wpc,
- struct writeback_control *wbc, struct inode *inode, loff_t pos,
- u16 ioend_flags)
-{
- struct bio *bio;
-
- bio = bio_alloc_bioset(wpc->iomap.bdev, BIO_MAX_VECS,
- REQ_OP_WRITE | wbc_to_write_flags(wbc),
- GFP_NOFS, &iomap_ioend_bioset);
- bio->bi_iter.bi_sector = iomap_sector(&wpc->iomap, pos);
- bio->bi_end_io = iomap_writepage_end_bio;
- bio->bi_write_hint = inode->i_write_hint;
- wbc_init_bio(wbc, bio);
- wpc->nr_folios = 0;
- return iomap_init_ioend(inode, bio, pos, ioend_flags);
-}
-
-static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos,
- u16 ioend_flags)
-{
- if (ioend_flags & IOMAP_IOEND_BOUNDARY)
- return false;
- if ((ioend_flags & IOMAP_IOEND_NOMERGE_FLAGS) !=
- (wpc->ioend->io_flags & IOMAP_IOEND_NOMERGE_FLAGS))
- return false;
- if (pos != wpc->ioend->io_offset + wpc->ioend->io_size)
- return false;
- if (!(wpc->iomap.flags & IOMAP_F_ANON_WRITE) &&
- iomap_sector(&wpc->iomap, pos) !=
- bio_end_sector(&wpc->ioend->io_bio))
- return false;
- /*
- * Limit ioend bio chain lengths to minimise IO completion latency. This
- * also prevents long tight loops ending page writeback on all the
- * folios in the ioend.
- */
- if (wpc->nr_folios >= IOEND_BATCH_SIZE)
- return false;
- return true;
-}
-
-/*
- * Test to see if we have an existing ioend structure that we could append to
- * first; otherwise finish off the current ioend and start another.
- *
- * If a new ioend is created and cached, the old ioend is submitted to the block
- * layer instantly. Batching optimisations are provided by higher level block
- * plugging.
- *
- * At the end of a writeback pass, there will be a cached ioend remaining on the
- * writepage context that the caller will need to submit.
- */
-static int iomap_add_to_ioend(struct iomap_writepage_ctx *wpc,
- struct writeback_control *wbc, struct folio *folio,
- struct inode *inode, loff_t pos, loff_t end_pos,
- unsigned len)
-{
- struct iomap_folio_state *ifs = folio->private;
- size_t poff = offset_in_folio(folio, pos);
- unsigned int ioend_flags = 0;
- int error;
-
- if (wpc->iomap.type == IOMAP_UNWRITTEN)
- ioend_flags |= IOMAP_IOEND_UNWRITTEN;
- if (wpc->iomap.flags & IOMAP_F_SHARED)
- ioend_flags |= IOMAP_IOEND_SHARED;
- if (folio_test_dropbehind(folio))
- ioend_flags |= IOMAP_IOEND_DONTCACHE;
- if (pos == wpc->iomap.offset && (wpc->iomap.flags & IOMAP_F_BOUNDARY))
- ioend_flags |= IOMAP_IOEND_BOUNDARY;
-
- if (!wpc->ioend || !iomap_can_add_to_ioend(wpc, pos, ioend_flags)) {
-new_ioend:
- error = iomap_submit_ioend(wpc, 0);
- if (error)
- return error;
- wpc->ioend = iomap_alloc_ioend(wpc, wbc, inode, pos,
- ioend_flags);
- }
-
- if (!bio_add_folio(&wpc->ioend->io_bio, folio, len, poff))
- goto new_ioend;
-
- if (ifs)
- atomic_add(len, &ifs->write_bytes_pending);
-
- /*
- * Clamp io_offset and io_size to the incore EOF so that ondisk
- * file size updates in the ioend completion are byte-accurate.
- * This avoids recovering files with zeroed tail regions when
- * writeback races with appending writes:
- *
- * Thread 1: Thread 2:
- * ------------ -----------
- * write [A, A+B]
- * update inode size to A+B
- * submit I/O [A, A+BS]
- * write [A+B, A+B+C]
- * update inode size to A+B+C
- *
- *
- *
- * After reboot:
- * 1) with A+B+C < A+BS, the file has zero padding in range
- * [A+B, A+B+C]
- *
- * |< Block Size (BS) >|
- * |DDDDDDDDDDDD0000000000000|
- * ^ ^ ^
- * A A+B A+B+C
- * (EOF)
- *
- * 2) with A+B+C > A+BS, the file has zero padding in range
- * [A+B, A+BS]
- *
- * |< Block Size (BS) >|< Block Size (BS) >|
- * |DDDDDDDDDDDD0000000000000|00000000000000000000000000|
- * ^ ^ ^ ^
- * A A+B A+BS A+B+C
- * (EOF)
- *
- * D = Valid Data
- * 0 = Zero Padding
- *
- * Note that this defeats the ability to chain the ioends of
- * appending writes.
- */
- wpc->ioend->io_size += len;
- if (wpc->ioend->io_offset + wpc->ioend->io_size > end_pos)
- wpc->ioend->io_size = end_pos - wpc->ioend->io_offset;
-
- wbc_account_cgroup_owner(wbc, folio, len);
- return 0;
-}
-
-static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc,
- struct writeback_control *wbc, struct folio *folio,
- struct inode *inode, u64 pos, u64 end_pos,
- unsigned dirty_len, unsigned *count)
-{
- int error;
-
do {
- unsigned map_len;
+ ssize_t ret;
- error = wpc->ops->map_blocks(wpc, inode, pos, dirty_len);
- if (error)
- break;
- trace_iomap_writepage_map(inode, pos, dirty_len, &wpc->iomap);
+ ret = wpc->ops->writeback_range(wpc, folio, pos, rlen, end_pos);
+ if (WARN_ON_ONCE(ret == 0 || ret > rlen))
+ return -EIO;
+ if (ret < 0)
+ return ret;
+ rlen -= ret;
+ pos += ret;
- map_len = min_t(u64, dirty_len,
- wpc->iomap.offset + wpc->iomap.length - pos);
- WARN_ON_ONCE(!folio->private && map_len < dirty_len);
+ /*
+ * Holes are not be written back by ->writeback_range, so track
+ * if we did handle anything that is not a hole here.
+ */
+ if (wpc->iomap.type != IOMAP_HOLE)
+ *wb_pending = true;
+ } while (rlen);
- switch (wpc->iomap.type) {
- case IOMAP_INLINE:
- WARN_ON_ONCE(1);
- error = -EIO;
- break;
- case IOMAP_HOLE:
- break;
- default:
- error = iomap_add_to_ioend(wpc, wbc, folio, inode, pos,
- end_pos, map_len);
- if (!error)
- (*count)++;
- break;
- }
- dirty_len -= map_len;
- pos += map_len;
- } while (dirty_len && !error);
-
- /*
- * We cannot cancel the ioend directly here on error. We may have
- * already set other pages under writeback and hence we have to run I/O
- * completion to mark the error state of the pages under writeback
- * appropriately.
- *
- * Just let the file system know what portion of the folio failed to
- * map.
- */
- if (error && wpc->ops->discard_folio)
- wpc->ops->discard_folio(folio, pos);
- return error;
+ return 0;
}
/*
@@ -1819,7 +1607,7 @@ static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc,
* If the folio is entirely beyond i_size, return false. If it straddles
* i_size, adjust end_pos and zero all data beyond i_size.
*/
-static bool iomap_writepage_handle_eof(struct folio *folio, struct inode *inode,
+static bool iomap_writeback_handle_eof(struct folio *folio, struct inode *inode,
u64 *end_pos)
{
u64 isize = i_size_read(inode);
@@ -1871,15 +1659,14 @@ static bool iomap_writepage_handle_eof(struct folio *folio, struct inode *inode,
return true;
}
-static int iomap_writepage_map(struct iomap_writepage_ctx *wpc,
- struct writeback_control *wbc, struct folio *folio)
+int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio)
{
struct iomap_folio_state *ifs = folio->private;
- struct inode *inode = folio->mapping->host;
+ struct inode *inode = wpc->inode;
u64 pos = folio_pos(folio);
u64 end_pos = pos + folio_size(folio);
u64 end_aligned = 0;
- unsigned count = 0;
+ bool wb_pending = false;
int error = 0;
u32 rlen;
@@ -1887,12 +1674,10 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc,
WARN_ON_ONCE(folio_test_dirty(folio));
WARN_ON_ONCE(folio_test_writeback(folio));
- trace_iomap_writepage(inode, pos, folio_size(folio));
+ trace_iomap_writeback_folio(inode, pos, folio_size(folio));
- if (!iomap_writepage_handle_eof(folio, inode, &end_pos)) {
- folio_unlock(folio);
+ if (!iomap_writeback_handle_eof(folio, inode, &end_pos))
return 0;
- }
WARN_ON_ONCE(end_pos <= pos);
if (i_blocks_per_folio(inode, folio) > 1) {
@@ -1908,7 +1693,7 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc,
* all blocks.
*/
WARN_ON_ONCE(atomic_read(&ifs->write_bytes_pending) != 0);
- atomic_inc(&ifs->write_bytes_pending);
+ iomap_start_folio_write(inode, folio, 1);
}
/*
@@ -1922,14 +1707,14 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc,
*/
end_aligned = round_up(end_pos, i_blocksize(inode));
while ((rlen = iomap_find_dirty_range(folio, &pos, end_aligned))) {
- error = iomap_writepage_map_blocks(wpc, wbc, folio, inode,
- pos, end_pos, rlen, &count);
+ error = iomap_writeback_range(wpc, folio, pos, rlen, end_pos,
+ &wb_pending);
if (error)
break;
pos += rlen;
}
- if (count)
+ if (wb_pending)
wpc->nr_folios++;
/*
@@ -1946,23 +1731,22 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc,
* already at this point. In that case we need to clear the writeback
* bit ourselves right after unlocking the page.
*/
- folio_unlock(folio);
if (ifs) {
if (atomic_dec_and_test(&ifs->write_bytes_pending))
folio_end_writeback(folio);
} else {
- if (!count)
+ if (!wb_pending)
folio_end_writeback(folio);
}
mapping_set_error(inode->i_mapping, error);
return error;
}
+EXPORT_SYMBOL_GPL(iomap_writeback_folio);
int
-iomap_writepages(struct address_space *mapping, struct writeback_control *wbc,
- struct iomap_writepage_ctx *wpc,
- const struct iomap_writeback_ops *ops)
+iomap_writepages(struct iomap_writepage_ctx *wpc)
{
+ struct address_space *mapping = wpc->inode->i_mapping;
struct folio *folio = NULL;
int error;
@@ -1974,9 +1758,22 @@ iomap_writepages(struct address_space *mapping, struct writeback_control *wbc,
PF_MEMALLOC))
return -EIO;
- wpc->ops = ops;
- while ((folio = writeback_iter(mapping, wbc, folio, &error)))
- error = iomap_writepage_map(wpc, wbc, folio);
- return iomap_submit_ioend(wpc, error);
+ while ((folio = writeback_iter(mapping, wpc->wbc, folio, &error))) {
+ error = iomap_writeback_folio(wpc, folio);
+ folio_unlock(folio);
+ }
+
+ /*
+ * If @error is non-zero, it means that we have a situation where some
+ * part of the submission process has failed after we've marked pages
+ * for writeback.
+ *
+ * We cannot cancel the writeback directly in that case, so always call
+ * ->writeback_submit to run the I/O completion handler to clear the
+ * writeback bit and let the file system proess the errors.
+ */
+ if (wpc->wb_ctx)
+ return wpc->ops->writeback_submit(wpc, error);
+ return error;
}
EXPORT_SYMBOL_GPL(iomap_writepages);
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 844261a31156..6f25d4cfea9f 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -3,14 +3,9 @@
* Copyright (C) 2010 Red Hat, Inc.
* Copyright (c) 2016-2025 Christoph Hellwig.
*/
-#include
-#include
-#include
#include
#include
#include
-#include
-#include
#include
#include "internal.h"
#include "trace.h"
diff --git a/fs/iomap/fiemap.c b/fs/iomap/fiemap.c
index 80675c42e94e..d11dadff8286 100644
--- a/fs/iomap/fiemap.c
+++ b/fs/iomap/fiemap.c
@@ -2,9 +2,6 @@
/*
* Copyright (c) 2016-2021 Christoph Hellwig.
*/
-#include
-#include
-#include
#include
#include
#include
diff --git a/fs/iomap/internal.h b/fs/iomap/internal.h
index f6992a3bf66a..d05cb3aed96e 100644
--- a/fs/iomap/internal.h
+++ b/fs/iomap/internal.h
@@ -4,7 +4,6 @@
#define IOEND_BATCH_SIZE 4096
-u32 iomap_finish_ioend_buffered(struct iomap_ioend *ioend);
u32 iomap_finish_ioend_direct(struct iomap_ioend *ioend);
#endif /* _IOMAP_INTERNAL_H */
diff --git a/fs/iomap/ioend.c b/fs/iomap/ioend.c
index 18894ebba6db..b49fa75eab26 100644
--- a/fs/iomap/ioend.c
+++ b/fs/iomap/ioend.c
@@ -1,10 +1,13 @@
// SPDX-License-Identifier: GPL-2.0
/*
- * Copyright (c) 2024-2025 Christoph Hellwig.
+ * Copyright (c) 2016-2025 Christoph Hellwig.
*/
#include
#include
+#include
+#include
#include "internal.h"
+#include "trace.h"
struct bio_set iomap_ioend_bioset;
EXPORT_SYMBOL_GPL(iomap_ioend_bioset);
@@ -28,6 +31,221 @@ struct iomap_ioend *iomap_init_ioend(struct inode *inode,
}
EXPORT_SYMBOL_GPL(iomap_init_ioend);
+/*
+ * We're now finished for good with this ioend structure. Update the folio
+ * state, release holds on bios, and finally free up memory. Do not use the
+ * ioend after this.
+ */
+static u32 iomap_finish_ioend_buffered(struct iomap_ioend *ioend)
+{
+ struct inode *inode = ioend->io_inode;
+ struct bio *bio = &ioend->io_bio;
+ struct folio_iter fi;
+ u32 folio_count = 0;
+
+ if (ioend->io_error) {
+ mapping_set_error(inode->i_mapping, ioend->io_error);
+ if (!bio_flagged(bio, BIO_QUIET)) {
+ pr_err_ratelimited(
+"%s: writeback error on inode %lu, offset %lld, sector %llu",
+ inode->i_sb->s_id, inode->i_ino,
+ ioend->io_offset, ioend->io_sector);
+ }
+ }
+
+ /* walk all folios in bio, ending page IO on them */
+ bio_for_each_folio_all(fi, bio) {
+ iomap_finish_folio_write(inode, fi.folio, fi.length);
+ folio_count++;
+ }
+
+ bio_put(bio); /* frees the ioend */
+ return folio_count;
+}
+
+static void ioend_writeback_end_bio(struct bio *bio)
+{
+ struct iomap_ioend *ioend = iomap_ioend_from_bio(bio);
+
+ ioend->io_error = blk_status_to_errno(bio->bi_status);
+ iomap_finish_ioend_buffered(ioend);
+}
+
+/*
+ * We cannot cancel the ioend directly in case of an error, so call the bio end
+ * I/O handler with the error status here to run the normal I/O completion
+ * handler.
+ */
+int iomap_ioend_writeback_submit(struct iomap_writepage_ctx *wpc, int error)
+{
+ struct iomap_ioend *ioend = wpc->wb_ctx;
+
+ if (!ioend->io_bio.bi_end_io)
+ ioend->io_bio.bi_end_io = ioend_writeback_end_bio;
+
+ if (WARN_ON_ONCE(wpc->iomap.flags & IOMAP_F_ANON_WRITE))
+ error = -EIO;
+
+ if (error) {
+ ioend->io_bio.bi_status = errno_to_blk_status(error);
+ bio_endio(&ioend->io_bio);
+ return error;
+ }
+
+ submit_bio(&ioend->io_bio);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(iomap_ioend_writeback_submit);
+
+static struct iomap_ioend *iomap_alloc_ioend(struct iomap_writepage_ctx *wpc,
+ loff_t pos, u16 ioend_flags)
+{
+ struct bio *bio;
+
+ bio = bio_alloc_bioset(wpc->iomap.bdev, BIO_MAX_VECS,
+ REQ_OP_WRITE | wbc_to_write_flags(wpc->wbc),
+ GFP_NOFS, &iomap_ioend_bioset);
+ bio->bi_iter.bi_sector = iomap_sector(&wpc->iomap, pos);
+ bio->bi_write_hint = wpc->inode->i_write_hint;
+ wbc_init_bio(wpc->wbc, bio);
+ wpc->nr_folios = 0;
+ return iomap_init_ioend(wpc->inode, bio, pos, ioend_flags);
+}
+
+static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos,
+ u16 ioend_flags)
+{
+ struct iomap_ioend *ioend = wpc->wb_ctx;
+
+ if (ioend_flags & IOMAP_IOEND_BOUNDARY)
+ return false;
+ if ((ioend_flags & IOMAP_IOEND_NOMERGE_FLAGS) !=
+ (ioend->io_flags & IOMAP_IOEND_NOMERGE_FLAGS))
+ return false;
+ if (pos != ioend->io_offset + ioend->io_size)
+ return false;
+ if (!(wpc->iomap.flags & IOMAP_F_ANON_WRITE) &&
+ iomap_sector(&wpc->iomap, pos) != bio_end_sector(&ioend->io_bio))
+ return false;
+ /*
+ * Limit ioend bio chain lengths to minimise IO completion latency. This
+ * also prevents long tight loops ending page writeback on all the
+ * folios in the ioend.
+ */
+ if (wpc->nr_folios >= IOEND_BATCH_SIZE)
+ return false;
+ return true;
+}
+
+/*
+ * Test to see if we have an existing ioend structure that we could append to
+ * first; otherwise finish off the current ioend and start another.
+ *
+ * If a new ioend is created and cached, the old ioend is submitted to the block
+ * layer instantly. Batching optimisations are provided by higher level block
+ * plugging.
+ *
+ * At the end of a writeback pass, there will be a cached ioend remaining on the
+ * writepage context that the caller will need to submit.
+ */
+ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio,
+ loff_t pos, loff_t end_pos, unsigned int dirty_len)
+{
+ struct iomap_ioend *ioend = wpc->wb_ctx;
+ size_t poff = offset_in_folio(folio, pos);
+ unsigned int ioend_flags = 0;
+ unsigned int map_len = min_t(u64, dirty_len,
+ wpc->iomap.offset + wpc->iomap.length - pos);
+ int error;
+
+ trace_iomap_add_to_ioend(wpc->inode, pos, dirty_len, &wpc->iomap);
+
+ WARN_ON_ONCE(!folio->private && map_len < dirty_len);
+
+ switch (wpc->iomap.type) {
+ case IOMAP_INLINE:
+ WARN_ON_ONCE(1);
+ return -EIO;
+ case IOMAP_HOLE:
+ return map_len;
+ default:
+ break;
+ }
+
+ if (wpc->iomap.type == IOMAP_UNWRITTEN)
+ ioend_flags |= IOMAP_IOEND_UNWRITTEN;
+ if (wpc->iomap.flags & IOMAP_F_SHARED)
+ ioend_flags |= IOMAP_IOEND_SHARED;
+ if (folio_test_dropbehind(folio))
+ ioend_flags |= IOMAP_IOEND_DONTCACHE;
+ if (pos == wpc->iomap.offset && (wpc->iomap.flags & IOMAP_F_BOUNDARY))
+ ioend_flags |= IOMAP_IOEND_BOUNDARY;
+
+ if (!ioend || !iomap_can_add_to_ioend(wpc, pos, ioend_flags)) {
+new_ioend:
+ if (ioend) {
+ error = wpc->ops->writeback_submit(wpc, 0);
+ if (error)
+ return error;
+ }
+ wpc->wb_ctx = ioend = iomap_alloc_ioend(wpc, pos, ioend_flags);
+ }
+
+ if (!bio_add_folio(&ioend->io_bio, folio, map_len, poff))
+ goto new_ioend;
+
+ iomap_start_folio_write(wpc->inode, folio, map_len);
+
+ /*
+ * Clamp io_offset and io_size to the incore EOF so that ondisk
+ * file size updates in the ioend completion are byte-accurate.
+ * This avoids recovering files with zeroed tail regions when
+ * writeback races with appending writes:
+ *
+ * Thread 1: Thread 2:
+ * ------------ -----------
+ * write [A, A+B]
+ * update inode size to A+B
+ * submit I/O [A, A+BS]
+ * write [A+B, A+B+C]
+ * update inode size to A+B+C
+ *
+ *
+ *
+ * After reboot:
+ * 1) with A+B+C < A+BS, the file has zero padding in range
+ * [A+B, A+B+C]
+ *
+ * |< Block Size (BS) >|
+ * |DDDDDDDDDDDD0000000000000|
+ * ^ ^ ^
+ * A A+B A+B+C
+ * (EOF)
+ *
+ * 2) with A+B+C > A+BS, the file has zero padding in range
+ * [A+B, A+BS]
+ *
+ * |< Block Size (BS) >|< Block Size (BS) >|
+ * |DDDDDDDDDDDD0000000000000|00000000000000000000000000|
+ * ^ ^ ^ ^
+ * A A+B A+BS A+B+C
+ * (EOF)
+ *
+ * D = Valid Data
+ * 0 = Zero Padding
+ *
+ * Note that this defeats the ability to chain the ioends of
+ * appending writes.
+ */
+ ioend->io_size += map_len;
+ if (ioend->io_offset + ioend->io_size > end_pos)
+ ioend->io_size = end_pos - ioend->io_offset;
+
+ wbc_account_cgroup_owner(wpc->wbc, folio, map_len);
+ return map_len;
+}
+EXPORT_SYMBOL_GPL(iomap_add_to_ioend);
+
static u32 iomap_finish_ioend(struct iomap_ioend *ioend, int error)
{
if (ioend->io_parent) {
diff --git a/fs/iomap/iter.c b/fs/iomap/iter.c
index 6ffc6a7b9ba5..cef77ca0c20b 100644
--- a/fs/iomap/iter.c
+++ b/fs/iomap/iter.c
@@ -3,7 +3,6 @@
* Copyright (C) 2010 Red Hat, Inc.
* Copyright (c) 2016-2021 Christoph Hellwig.
*/
-#include
#include
#include "trace.h"
diff --git a/fs/iomap/seek.c b/fs/iomap/seek.c
index 04d7919636c1..56db2dd4b10d 100644
--- a/fs/iomap/seek.c
+++ b/fs/iomap/seek.c
@@ -3,12 +3,8 @@
* Copyright (C) 2017 Red Hat, Inc.
* Copyright (c) 2018-2021 Christoph Hellwig.
*/
-#include
-#include
-#include
#include
#include
-#include
static int iomap_seek_hole_iter(struct iomap_iter *iter,
loff_t *hole_pos)
diff --git a/fs/iomap/swapfile.c b/fs/iomap/swapfile.c
index c1a762c10ce4..0db77c449467 100644
--- a/fs/iomap/swapfile.c
+++ b/fs/iomap/swapfile.c
@@ -3,9 +3,6 @@
* Copyright (C) 2018 Oracle. All Rights Reserved.
* Author: Darrick J. Wong
*/
-#include
-#include
-#include
#include
#include
diff --git a/fs/iomap/trace.c b/fs/iomap/trace.c
index 728d5443daf5..da217246b1a9 100644
--- a/fs/iomap/trace.c
+++ b/fs/iomap/trace.c
@@ -3,7 +3,6 @@
* Copyright (c) 2019 Christoph Hellwig
*/
#include
-#include
/*
* We include this last to have the helpers above available for the trace
diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h
index 455cc6f90be0..6ad66e6ba653 100644
--- a/fs/iomap/trace.h
+++ b/fs/iomap/trace.h
@@ -79,7 +79,7 @@ DECLARE_EVENT_CLASS(iomap_range_class,
DEFINE_EVENT(iomap_range_class, name, \
TP_PROTO(struct inode *inode, loff_t off, u64 len),\
TP_ARGS(inode, off, len))
-DEFINE_RANGE_EVENT(iomap_writepage);
+DEFINE_RANGE_EVENT(iomap_writeback_folio);
DEFINE_RANGE_EVENT(iomap_release_folio);
DEFINE_RANGE_EVENT(iomap_invalidate_folio);
DEFINE_RANGE_EVENT(iomap_dio_invalidate_fail);
@@ -169,7 +169,7 @@ DEFINE_EVENT(iomap_class, name, \
DEFINE_IOMAP_EVENT(iomap_iter_dstmap);
DEFINE_IOMAP_EVENT(iomap_iter_srcmap);
-TRACE_EVENT(iomap_writepage_map,
+TRACE_EVENT(iomap_add_to_ioend,
TP_PROTO(struct inode *inode, u64 pos, unsigned int dirty_len,
struct iomap *iomap),
TP_ARGS(inode, pos, dirty_len, iomap),
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 63151feb9c3f..1ee4f835ac3c 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -233,6 +233,47 @@ xfs_end_bio(
spin_unlock_irqrestore(&ip->i_ioend_lock, flags);
}
+/*
+ * We cannot cancel the ioend directly on error. We may have already set other
+ * pages under writeback and hence we have to run I/O completion to mark the
+ * error state of the pages under writeback appropriately.
+ *
+ * If the folio has delalloc blocks on it, the caller is asking us to punch them
+ * out. If we don't, we can leave a stale delalloc mapping covered by a clean
+ * page that needs to be dirtied again before the delalloc mapping can be
+ * converted. This stale delalloc mapping can trip up a later direct I/O read
+ * operation on the same region.
+ *
+ * We prevent this by truncating away the delalloc regions on the folio. Because
+ * they are delalloc, we can do this without needing a transaction. Indeed - if
+ * we get ENOSPC errors, we have to be able to do this truncation without a
+ * transaction as there is no space left for block reservation (typically why
+ * we see a ENOSPC in writeback).
+ */
+static void
+xfs_discard_folio(
+ struct folio *folio,
+ loff_t pos)
+{
+ struct xfs_inode *ip = XFS_I(folio->mapping->host);
+ struct xfs_mount *mp = ip->i_mount;
+
+ if (xfs_is_shutdown(mp))
+ return;
+
+ xfs_alert_ratelimited(mp,
+ "page discard on page "PTR_FMT", inode 0x%llx, pos %llu.",
+ folio, ip->i_ino, pos);
+
+ /*
+ * The end of the punch range is always the offset of the first
+ * byte of the next folio. Hence the end offset is only dependent on the
+ * folio itself and not the start offset that is passed in.
+ */
+ xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, pos,
+ folio_pos(folio) + folio_size(folio), NULL);
+}
+
/*
* Fast revalidation of the cached writeback mapping. Return true if the current
* mapping is valid, false otherwise.
@@ -278,13 +319,12 @@ xfs_imap_valid(
static int
xfs_map_blocks(
struct iomap_writepage_ctx *wpc,
- struct inode *inode,
loff_t offset,
unsigned int len)
{
- struct xfs_inode *ip = XFS_I(inode);
+ struct xfs_inode *ip = XFS_I(wpc->inode);
struct xfs_mount *mp = ip->i_mount;
- ssize_t count = i_blocksize(inode);
+ ssize_t count = i_blocksize(wpc->inode);
xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset);
xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + count);
xfs_fileoff_t cow_fsb;
@@ -436,6 +476,24 @@ xfs_map_blocks(
return 0;
}
+static ssize_t
+xfs_writeback_range(
+ struct iomap_writepage_ctx *wpc,
+ struct folio *folio,
+ u64 offset,
+ unsigned int len,
+ u64 end_pos)
+{
+ ssize_t ret;
+
+ ret = xfs_map_blocks(wpc, offset, len);
+ if (!ret)
+ ret = iomap_add_to_ioend(wpc, folio, offset, end_pos, len);
+ if (ret < 0)
+ xfs_discard_folio(folio, offset);
+ return ret;
+}
+
static bool
xfs_ioend_needs_wq_completion(
struct iomap_ioend *ioend)
@@ -456,79 +514,40 @@ xfs_ioend_needs_wq_completion(
}
static int
-xfs_submit_ioend(
- struct iomap_writepage_ctx *wpc,
- int status)
+xfs_writeback_submit(
+ struct iomap_writepage_ctx *wpc,
+ int error)
{
- struct iomap_ioend *ioend = wpc->ioend;
- unsigned int nofs_flag;
+ struct iomap_ioend *ioend = wpc->wb_ctx;
/*
- * We can allocate memory here while doing writeback on behalf of
- * memory reclaim. To avoid memory allocation deadlocks set the
- * task-wide nofs context for the following operations.
+ * Convert CoW extents to regular.
+ *
+ * We can allocate memory here while doing writeback on behalf of memory
+ * reclaim. To avoid memory allocation deadlocks, set the task-wide
+ * nofs context.
*/
- nofs_flag = memalloc_nofs_save();
+ if (!error && (ioend->io_flags & IOMAP_IOEND_SHARED)) {
+ unsigned int nofs_flag;
- /* Convert CoW extents to regular */
- if (!status && (ioend->io_flags & IOMAP_IOEND_SHARED)) {
- status = xfs_reflink_convert_cow(XFS_I(ioend->io_inode),
+ nofs_flag = memalloc_nofs_save();
+ error = xfs_reflink_convert_cow(XFS_I(ioend->io_inode),
ioend->io_offset, ioend->io_size);
+ memalloc_nofs_restore(nofs_flag);
}
- memalloc_nofs_restore(nofs_flag);
-
- /* send ioends that might require a transaction to the completion wq */
+ /*
+ * Send ioends that might require a transaction to the completion wq.
+ */
if (xfs_ioend_needs_wq_completion(ioend))
ioend->io_bio.bi_end_io = xfs_end_bio;
- if (status)
- return status;
- submit_bio(&ioend->io_bio);
- return 0;
-}
-
-/*
- * If the folio has delalloc blocks on it, the caller is asking us to punch them
- * out. If we don't, we can leave a stale delalloc mapping covered by a clean
- * page that needs to be dirtied again before the delalloc mapping can be
- * converted. This stale delalloc mapping can trip up a later direct I/O read
- * operation on the same region.
- *
- * We prevent this by truncating away the delalloc regions on the folio. Because
- * they are delalloc, we can do this without needing a transaction. Indeed - if
- * we get ENOSPC errors, we have to be able to do this truncation without a
- * transaction as there is no space left for block reservation (typically why
- * we see a ENOSPC in writeback).
- */
-static void
-xfs_discard_folio(
- struct folio *folio,
- loff_t pos)
-{
- struct xfs_inode *ip = XFS_I(folio->mapping->host);
- struct xfs_mount *mp = ip->i_mount;
-
- if (xfs_is_shutdown(mp))
- return;
-
- xfs_alert_ratelimited(mp,
- "page discard on page "PTR_FMT", inode 0x%llx, pos %llu.",
- folio, ip->i_ino, pos);
-
- /*
- * The end of the punch range is always the offset of the first
- * byte of the next folio. Hence the end offset is only dependent on the
- * folio itself and not the start offset that is passed in.
- */
- xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, pos,
- folio_pos(folio) + folio_size(folio), NULL);
+ return iomap_ioend_writeback_submit(wpc, error);
}
static const struct iomap_writeback_ops xfs_writeback_ops = {
- .map_blocks = xfs_map_blocks,
- .submit_ioend = xfs_submit_ioend,
- .discard_folio = xfs_discard_folio,
+ .writeback_range = xfs_writeback_range,
+ .writeback_submit = xfs_writeback_submit,
};
struct xfs_zoned_writepage_ctx {
@@ -545,11 +564,10 @@ XFS_ZWPC(struct iomap_writepage_ctx *ctx)
static int
xfs_zoned_map_blocks(
struct iomap_writepage_ctx *wpc,
- struct inode *inode,
loff_t offset,
unsigned int len)
{
- struct xfs_inode *ip = XFS_I(inode);
+ struct xfs_inode *ip = XFS_I(wpc->inode);
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset);
xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + len);
@@ -608,22 +626,44 @@ xfs_zoned_map_blocks(
return 0;
}
-static int
-xfs_zoned_submit_ioend(
+static ssize_t
+xfs_zoned_writeback_range(
struct iomap_writepage_ctx *wpc,
- int status)
+ struct folio *folio,
+ u64 offset,
+ unsigned int len,
+ u64 end_pos)
{
- wpc->ioend->io_bio.bi_end_io = xfs_end_bio;
- if (status)
- return status;
- xfs_zone_alloc_and_submit(wpc->ioend, &XFS_ZWPC(wpc)->open_zone);
+ ssize_t ret;
+
+ ret = xfs_zoned_map_blocks(wpc, offset, len);
+ if (!ret)
+ ret = iomap_add_to_ioend(wpc, folio, offset, end_pos, len);
+ if (ret < 0)
+ xfs_discard_folio(folio, offset);
+ return ret;
+}
+
+static int
+xfs_zoned_writeback_submit(
+ struct iomap_writepage_ctx *wpc,
+ int error)
+{
+ struct iomap_ioend *ioend = wpc->wb_ctx;
+
+ ioend->io_bio.bi_end_io = xfs_end_bio;
+ if (error) {
+ ioend->io_bio.bi_status = errno_to_blk_status(error);
+ bio_endio(&ioend->io_bio);
+ return error;
+ }
+ xfs_zone_alloc_and_submit(ioend, &XFS_ZWPC(wpc)->open_zone);
return 0;
}
static const struct iomap_writeback_ops xfs_zoned_writeback_ops = {
- .map_blocks = xfs_zoned_map_blocks,
- .submit_ioend = xfs_zoned_submit_ioend,
- .discard_folio = xfs_discard_folio,
+ .writeback_range = xfs_zoned_writeback_range,
+ .writeback_submit = xfs_zoned_writeback_submit,
};
STATIC int
@@ -636,19 +676,29 @@ xfs_vm_writepages(
xfs_iflags_clear(ip, XFS_ITRUNCATED);
if (xfs_is_zoned_inode(ip)) {
- struct xfs_zoned_writepage_ctx xc = { };
+ struct xfs_zoned_writepage_ctx xc = {
+ .ctx = {
+ .inode = mapping->host,
+ .wbc = wbc,
+ .ops = &xfs_zoned_writeback_ops
+ },
+ };
int error;
- error = iomap_writepages(mapping, wbc, &xc.ctx,
- &xfs_zoned_writeback_ops);
+ error = iomap_writepages(&xc.ctx);
if (xc.open_zone)
xfs_open_zone_put(xc.open_zone);
return error;
} else {
- struct xfs_writepage_ctx wpc = { };
+ struct xfs_writepage_ctx wpc = {
+ .ctx = {
+ .inode = mapping->host,
+ .wbc = wbc,
+ .ops = &xfs_writeback_ops
+ },
+ };
- return iomap_writepages(mapping, wbc, &wpc.ctx,
- &xfs_writeback_ops);
+ return iomap_writepages(&wpc.ctx);
}
}
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 35d028688f33..b04c59d87378 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -979,7 +979,8 @@ xfs_file_buffered_write(
trace_xfs_file_buffered_write(iocb, from);
ret = iomap_file_buffered_write(iocb, from,
- &xfs_buffered_write_iomap_ops, NULL);
+ &xfs_buffered_write_iomap_ops, &xfs_iomap_write_ops,
+ NULL);
/*
* If we hit a space limit, try to free up some lingering preallocated
@@ -1059,7 +1060,8 @@ xfs_file_buffered_write_zoned(
retry:
trace_xfs_file_buffered_write(iocb, from);
ret = iomap_file_buffered_write(iocb, from,
- &xfs_buffered_write_iomap_ops, &ac);
+ &xfs_buffered_write_iomap_ops, &xfs_iomap_write_ops,
+ &ac);
if (ret == -ENOSPC && !cleared_space) {
/*
* Kick off writeback to convert delalloc space and release the
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index ec30b78bf5c4..2a74f2957341 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -79,6 +79,9 @@ xfs_iomap_valid(
{
struct xfs_inode *ip = XFS_I(inode);
+ if (iomap->type == IOMAP_HOLE)
+ return true;
+
if (iomap->validity_cookie !=
xfs_iomap_inode_sequence(ip, iomap->flags)) {
trace_xfs_iomap_invalid(ip, iomap);
@@ -89,7 +92,7 @@ xfs_iomap_valid(
return true;
}
-static const struct iomap_folio_ops xfs_iomap_folio_ops = {
+const struct iomap_write_ops xfs_iomap_write_ops = {
.iomap_valid = xfs_iomap_valid,
};
@@ -151,7 +154,6 @@ xfs_bmbt_to_iomap(
iomap->flags |= IOMAP_F_DIRTY;
iomap->validity_cookie = sequence_cookie;
- iomap->folio_ops = &xfs_iomap_folio_ops;
return 0;
}
@@ -2198,7 +2200,8 @@ xfs_zero_range(
return dax_zero_range(inode, pos, len, did_zero,
&xfs_dax_write_iomap_ops);
return iomap_zero_range(inode, pos, len, did_zero,
- &xfs_buffered_write_iomap_ops, ac);
+ &xfs_buffered_write_iomap_ops, &xfs_iomap_write_ops,
+ ac);
}
int
@@ -2214,5 +2217,6 @@ xfs_truncate_page(
return dax_truncate_page(inode, pos, did_zero,
&xfs_dax_write_iomap_ops);
return iomap_truncate_page(inode, pos, did_zero,
- &xfs_buffered_write_iomap_ops, ac);
+ &xfs_buffered_write_iomap_ops, &xfs_iomap_write_ops,
+ ac);
}
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 674f8ac1b9bd..ebcce7d49446 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -57,5 +57,6 @@ extern const struct iomap_ops xfs_seek_iomap_ops;
extern const struct iomap_ops xfs_xattr_iomap_ops;
extern const struct iomap_ops xfs_dax_write_iomap_ops;
extern const struct iomap_ops xfs_atomic_write_cow_iomap_ops;
+extern const struct iomap_write_ops xfs_iomap_write_ops;
#endif /* __XFS_IOMAP_H__*/
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index ad3bcb76d805..3f177b4ec131 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1881,7 +1881,8 @@ xfs_reflink_unshare(
&xfs_dax_write_iomap_ops);
else
error = iomap_file_unshare(inode, offset, len,
- &xfs_buffered_write_iomap_ops);
+ &xfs_buffered_write_iomap_ops,
+ &xfs_iomap_write_ops);
if (error)
goto out;
diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c
index c1848163b378..fd3a5922f6c3 100644
--- a/fs/zonefs/file.c
+++ b/fs/zonefs/file.c
@@ -124,37 +124,46 @@ static void zonefs_readahead(struct readahead_control *rac)
* Map blocks for page writeback. This is used only on conventional zone files,
* which implies that the page range can only be within the fixed inode size.
*/
-static int zonefs_write_map_blocks(struct iomap_writepage_ctx *wpc,
- struct inode *inode, loff_t offset,
- unsigned int len)
+static ssize_t zonefs_writeback_range(struct iomap_writepage_ctx *wpc,
+ struct folio *folio, u64 offset, unsigned len, u64 end_pos)
{
- struct zonefs_zone *z = zonefs_inode_zone(inode);
+ struct zonefs_zone *z = zonefs_inode_zone(wpc->inode);
if (WARN_ON_ONCE(zonefs_zone_is_seq(z)))
return -EIO;
- if (WARN_ON_ONCE(offset >= i_size_read(inode)))
+ if (WARN_ON_ONCE(offset >= i_size_read(wpc->inode)))
return -EIO;
/* If the mapping is already OK, nothing needs to be done */
- if (offset >= wpc->iomap.offset &&
- offset < wpc->iomap.offset + wpc->iomap.length)
- return 0;
+ if (offset < wpc->iomap.offset ||
+ offset >= wpc->iomap.offset + wpc->iomap.length) {
+ int error;
- return zonefs_write_iomap_begin(inode, offset,
- z->z_capacity - offset,
- IOMAP_WRITE, &wpc->iomap, NULL);
+ error = zonefs_write_iomap_begin(wpc->inode, offset,
+ z->z_capacity - offset, IOMAP_WRITE,
+ &wpc->iomap, NULL);
+ if (error)
+ return error;
+ }
+
+ return iomap_add_to_ioend(wpc, folio, offset, end_pos, len);
}
static const struct iomap_writeback_ops zonefs_writeback_ops = {
- .map_blocks = zonefs_write_map_blocks,
+ .writeback_range = zonefs_writeback_range,
+ .writeback_submit = iomap_ioend_writeback_submit,
};
static int zonefs_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
- struct iomap_writepage_ctx wpc = { };
+ struct iomap_writepage_ctx wpc = {
+ .inode = mapping->host,
+ .wbc = wbc,
+ .ops = &zonefs_writeback_ops,
+ };
- return iomap_writepages(mapping, wbc, &wpc, &zonefs_writeback_ops);
+ return iomap_writepages(&wpc);
}
static int zonefs_swap_activate(struct swap_info_struct *sis,
@@ -565,7 +574,8 @@ static ssize_t zonefs_file_buffered_write(struct kiocb *iocb,
if (ret <= 0)
goto inode_unlock;
- ret = iomap_file_buffered_write(iocb, from, &zonefs_write_iomap_ops, NULL);
+ ret = iomap_file_buffered_write(iocb, from, &zonefs_write_iomap_ops,
+ NULL, NULL);
if (ret == -EIO)
zonefs_io_error(inode, true);
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 522644d62f30..73dceabc21c8 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -101,8 +101,6 @@ struct vm_fault;
*/
#define IOMAP_NULL_ADDR -1ULL /* addr is not valid */
-struct iomap_folio_ops;
-
struct iomap {
u64 addr; /* disk offset of mapping, bytes */
loff_t offset; /* file offset of mapping, bytes */
@@ -113,7 +111,6 @@ struct iomap {
struct dax_device *dax_dev; /* dax_dev for dax operations */
void *inline_data;
void *private; /* filesystem private */
- const struct iomap_folio_ops *folio_ops;
u64 validity_cookie; /* used with .iomap_valid() */
};
@@ -143,16 +140,11 @@ static inline bool iomap_inline_data_valid(const struct iomap *iomap)
}
/*
- * When a filesystem sets folio_ops in an iomap mapping it returns, get_folio
- * and put_folio will be called for each folio written to. This only applies
- * to buffered writes as unbuffered writes will not typically have folios
- * associated with them.
- *
* When get_folio succeeds, put_folio will always be called to do any
* cleanup work necessary. put_folio is responsible for unlocking and putting
* @folio.
*/
-struct iomap_folio_ops {
+struct iomap_write_ops {
struct folio *(*get_folio)(struct iomap_iter *iter, loff_t pos,
unsigned len);
void (*put_folio)(struct inode *inode, loff_t pos, unsigned copied,
@@ -174,6 +166,16 @@ struct iomap_folio_ops {
* locked by the iomap code.
*/
bool (*iomap_valid)(struct inode *inode, const struct iomap *iomap);
+
+ /*
+ * Optional if the filesystem wishes to provide a custom handler for
+ * reading in the contents of a folio, otherwise iomap will default to
+ * submitting a bio read request.
+ *
+ * The read must be done synchronously.
+ */
+ int (*read_folio_range)(const struct iomap_iter *iter,
+ struct folio *folio, loff_t pos, size_t len);
};
/*
@@ -335,7 +337,8 @@ static inline bool iomap_want_unshare_iter(const struct iomap_iter *iter)
}
ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
- const struct iomap_ops *ops, void *private);
+ const struct iomap_ops *ops,
+ const struct iomap_write_ops *write_ops, void *private);
int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops);
void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops);
bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count);
@@ -344,11 +347,14 @@ bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags);
void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len);
bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio);
int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
- const struct iomap_ops *ops);
+ const struct iomap_ops *ops,
+ const struct iomap_write_ops *write_ops);
int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
- bool *did_zero, const struct iomap_ops *ops, void *private);
+ bool *did_zero, const struct iomap_ops *ops,
+ const struct iomap_write_ops *write_ops, void *private);
int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
- const struct iomap_ops *ops, void *private);
+ const struct iomap_ops *ops,
+ const struct iomap_write_ops *write_ops, void *private);
vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops,
void *private);
typedef void (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length,
@@ -391,8 +397,7 @@ sector_t iomap_bmap(struct address_space *mapping, sector_t bno,
/*
* Structure for writeback I/O completions.
*
- * File systems implementing ->submit_ioend (for buffered I/O) or ->submit_io
- * for direct I/O) can split a bio generated by iomap. In that case the parent
+ * File systems can split a bio generated by iomap. In that case the parent
* ioend it was split from is recorded in ioend->io_parent.
*/
struct iomap_ioend {
@@ -416,41 +421,38 @@ static inline struct iomap_ioend *iomap_ioend_from_bio(struct bio *bio)
struct iomap_writeback_ops {
/*
- * Required, maps the blocks so that writeback can be performed on
- * the range starting at offset.
+ * Performs writeback on the passed in range
*
- * Can return arbitrarily large regions, but we need to call into it at
+ * Can map arbitrarily large regions, but we need to call into it at
* least once per folio to allow the file systems to synchronize with
* the write path that could be invalidating mappings.
*
* An existing mapping from a previous call to this method can be reused
* by the file system if it is still valid.
- */
- int (*map_blocks)(struct iomap_writepage_ctx *wpc, struct inode *inode,
- loff_t offset, unsigned len);
-
- /*
- * Optional, allows the file systems to hook into bio submission,
- * including overriding the bi_end_io handler.
*
- * Returns 0 if the bio was successfully submitted, or a negative
- * error code if status was non-zero or another error happened and
- * the bio could not be submitted.
+ * Returns the number of bytes processed or a negative errno.
*/
- int (*submit_ioend)(struct iomap_writepage_ctx *wpc, int status);
+ ssize_t (*writeback_range)(struct iomap_writepage_ctx *wpc,
+ struct folio *folio, u64 pos, unsigned int len,
+ u64 end_pos);
/*
- * Optional, allows the file system to discard state on a page where
- * we failed to submit any I/O.
+ * Submit a writeback context previously build up by ->writeback_range.
+ *
+ * Returns 0 if the context was successfully submitted, or a negative
+ * error code if not. If @error is non-zero a failure occurred, and
+ * the writeback context should be completed with an error.
*/
- void (*discard_folio)(struct folio *folio, loff_t pos);
+ int (*writeback_submit)(struct iomap_writepage_ctx *wpc, int error);
};
struct iomap_writepage_ctx {
struct iomap iomap;
- struct iomap_ioend *ioend;
+ struct inode *inode;
+ struct writeback_control *wbc;
const struct iomap_writeback_ops *ops;
u32 nr_folios; /* folios added to the ioend */
+ void *wb_ctx; /* pending writeback context */
};
struct iomap_ioend *iomap_init_ioend(struct inode *inode, struct bio *bio,
@@ -461,9 +463,17 @@ void iomap_finish_ioends(struct iomap_ioend *ioend, int error);
void iomap_ioend_try_merge(struct iomap_ioend *ioend,
struct list_head *more_ioends);
void iomap_sort_ioends(struct list_head *ioend_list);
-int iomap_writepages(struct address_space *mapping,
- struct writeback_control *wbc, struct iomap_writepage_ctx *wpc,
- const struct iomap_writeback_ops *ops);
+ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio,
+ loff_t pos, loff_t end_pos, unsigned int dirty_len);
+int iomap_ioend_writeback_submit(struct iomap_writepage_ctx *wpc, int error);
+
+void iomap_start_folio_write(struct inode *inode, struct folio *folio,
+ size_t len);
+void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
+ size_t len);
+
+int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio);
+int iomap_writepages(struct iomap_writepage_ctx *wpc);
/*
* Flags for direct I/O ->end_io: