Use iomap for dirty folio writeback in ->writepages().
This allows for granular dirty writeback of large folios.
Only the dirty portions of the large folio will be written instead of
having to write out the entire folio. For example if there is a 1 MB
large folio and only 2 bytes in it are dirty, only the page for those
dirty bytes will be written out.
Signed-off-by: Joanne Koong <joannelkoong@xxxxxxxxx>
---
fs/fuse/file.c | 118 +++++++++++++++++++++++++++++--------------------
1 file changed, 70 insertions(+), 48 deletions(-)
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 59ff1dfd755b..db6804f6cc1d 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1835,7 +1835,7 @@ 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);
}
@@ -2022,19 +2022,20 @@ 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;
@@ -2047,7 +2048,7 @@ 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;
@@ -2103,7 +2104,7 @@ struct fuse_fill_wb_data {
struct fuse_file *ff;
struct inode *inode;
unsigned int max_folios;
- unsigned int nr_pages;
+ unsigned int nr_bytes;
};
static bool fuse_pages_realloc(struct fuse_fill_wb_data *data)
@@ -2145,21 +2146,28 @@ static void fuse_writepages_send(struct fuse_fill_wb_data *data)
}
static bool fuse_writepage_need_send(struct fuse_conn *fc, struct folio *folio,
+ loff_t offset, unsigned len,
struct fuse_args_pages *ap,
struct fuse_fill_wb_data *data)
{
+ struct folio *prev_folio;
+ struct fuse_folio_desc prev_desc;
+
WARN_ON(!ap->num_folios);
/* Reached max pages */
- if (data->nr_pages + folio_nr_pages(folio) > fc->max_pages)
+ if ((data->nr_bytes + len) / PAGE_SIZE > fc->max_pages)
return true;
/* Reached max write bytes */
- if ((data->nr_pages * PAGE_SIZE) + folio_size(folio) > fc->max_write)
+ if (data->nr_bytes + len > 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];
+ if ((folio_pos(prev_folio) + prev_desc.offset + prev_desc.length) !=
+ folio_pos(folio) + offset)
return true;
/* Need to grow the pages array? If so, did the expansion fail? */
@@ -2169,85 +2177,99 @@ static bool fuse_writepage_need_send(struct fuse_conn *fc, struct folio *folio,
return false;
}
-static int fuse_writepages_fill(struct folio *folio,
- struct writeback_control *wbc, void *_data)
+static int fuse_iomap_writeback_folio(struct iomap_writeback_folio_range *ctx)
{
- struct fuse_fill_wb_data *data = _data;
+ struct fuse_fill_wb_data *data = ctx->wpc->private;
struct fuse_writepage_args *wpa = data->wpa;
+ struct folio *folio = ctx->folio;
struct fuse_args_pages *ap = &wpa->ia.ap;
- struct inode *inode = data->inode;
- struct fuse_inode *fi = get_fuse_inode(inode);
+ struct inode *inode = folio->mapping->host;
struct fuse_conn *fc = get_fuse_conn(inode);
- int err;
+ struct fuse_inode *fi = get_fuse_inode(inode);
+ loff_t offset = offset_in_folio(folio, ctx->pos);
+ unsigned len = ctx->dirty_len;
+
+ /* 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)) {
+ iomap_start_folio_write(inode, folio, 1);
+ ctx->async_writeback = true;
+
+ if (wpa && fuse_writepage_need_send(fc, folio, offset, len, ap, data)) {
fuse_writepages_send(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);
+ 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 0;
+}
+
+static int fuse_iomap_writeback_complete(struct iomap_writepage_ctx *wpc, int error)
+{
+ struct fuse_fill_wb_data *data = wpc->private;
+
+ WARN_ON_ONCE(!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);
+
+ return error;
}
+static const struct iomap_writeback_ops fuse_writeback_ops = {
+ .writeback_folio = fuse_iomap_writeback_folio,
+ .writeback_complete = fuse_iomap_writeback_complete,
+};
+
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 = {
+ .inode = inode,
+ };
+ struct iomap_writepage_ctx wpc = {
+ .iomap.type = IOMAP_MAPPED,
+ .private = &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;
+ return iomap_writepages(mapping, wbc, &wpc, &fuse_writeback_ops);
}
static int fuse_launder_folio(struct folio *folio)
--
2.47.1
