[PATCH 3/3] cifs: Partially revert and use filemap_get_folio_tag()

From: David Howells
Date: Thu Mar 02 2023 - 18:18:56 EST


Mirror the changes made to afs to partially revert the changes made by:

acc8d8588cb7e3e64b0d2fa611dad06574cd67b1.
"afs: convert afs_writepages_region() to use filemap_get_folios_tag()"

that were then mirrored into cifs.

The issue is that filemap_get_folios_tag() gets a batch of pages at a time,
and then cifs_writepages_region() goes through them one at a time, extends
each into an operation with as many pages as will fit using the loop in
cifs_extend_writeback() and submits it - but, in the common case, this
means that the other pages in the batch already got annexed and processed
in cifs_extend_writeback() and we end up doing duplicate processing.

Switching to write_cache_pages() isn't an immediate substitute as that
doesn't take account of PG_fscache (and this bit is used in other ways by
other filesystems).

So go back to finding the next folio from the VM one at a time and then
extending the op onwards.

Fixes: 3822a7c40997 ("Merge tag 'mm-stable-2023-02-20-13-37' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm")
Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
cc: Steve French <sfrench@xxxxxxxxx>
cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
cc: Shyam Prasad N <nspmangalore@xxxxxxxxx>
cc: Rohith Surabattula <rohiths.msft@xxxxxxxxx>
cc: Jeff Layton <jlayton@xxxxxxxxxx>
cc: Paulo Alcantara <pc@xxxxxx>
cc: "Vishal Moola (Oracle)" <vishal.moola@xxxxxxxxx>
cc: "Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx>
cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
cc: linux-cifs@xxxxxxxxxxxxxxx
cc: linux-mm@xxxxxxxxx
Link: https://lore.kernel.org/r/2214157.1677250083@xxxxxxxxxxxxxxxxxxxxxx/
---
fs/cifs/file.c | 115 +++++++++++++++++++++----------------------------
1 file changed, 49 insertions(+), 66 deletions(-)

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 4d4a2d82636d..a3e89e741b42 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2864,93 +2864,76 @@ static int cifs_writepages_region(struct address_space *mapping,
struct writeback_control *wbc,
loff_t start, loff_t end, loff_t *_next)
{
- struct folio_batch fbatch;
+ struct folio *folio;
+ ssize_t ret;
int skips = 0;

- folio_batch_init(&fbatch);
do {
- int nr;
pgoff_t index = start / PAGE_SIZE;

- nr = filemap_get_folios_tag(mapping, &index, end / PAGE_SIZE,
- PAGECACHE_TAG_DIRTY, &fbatch);
- if (!nr)
+ folio = filemap_get_folio_tag(mapping, &index, end / PAGE_SIZE,
+ PAGECACHE_TAG_DIRTY);
+ if (!folio)
break;

- for (int i = 0; i < nr; i++) {
- ssize_t ret;
- struct folio *folio = fbatch.folios[i];
-
-redo_folio:
- start = folio_pos(folio); /* May regress with THPs */
+ start = folio_pos(folio); /* May regress with THPs */

- /* At this point we hold neither the i_pages lock nor the
- * page lock: the page may be truncated or invalidated
- * (changing page->mapping to NULL), or even swizzled
- * back from swapper_space to tmpfs file mapping
- */
- if (wbc->sync_mode != WB_SYNC_NONE) {
- ret = folio_lock_killable(folio);
- if (ret < 0)
- goto write_error;
- } else {
- if (!folio_trylock(folio))
- goto skip_write;
+ /* At this point we hold neither the i_pages lock nor the
+ * page lock: the page may be truncated or invalidated
+ * (changing page->mapping to NULL), or even swizzled
+ * back from swapper_space to tmpfs file mapping
+ */
+ if (wbc->sync_mode != WB_SYNC_NONE) {
+ ret = folio_lock_killable(folio);
+ if (ret < 0) {
+ folio_put(folio);
+ return ret;
}
-
- if (folio_mapping(folio) != mapping ||
- !folio_test_dirty(folio)) {
- start += folio_size(folio);
- folio_unlock(folio);
- continue;
+ } else {
+ if (!folio_trylock(folio)) {
+ folio_put(folio);
+ return 0;
}
+ }

- if (folio_test_writeback(folio) ||
- folio_test_fscache(folio)) {
- folio_unlock(folio);
- if (wbc->sync_mode == WB_SYNC_NONE)
- goto skip_write;
+ if (folio_mapping(folio) != mapping ||
+ !folio_test_dirty(folio)) {
+ start += folio_size(folio);
+ folio_unlock(folio);
+ folio_put(folio);
+ continue;
+ }

+ if (folio_test_writeback(folio) ||
+ folio_test_fscache(folio)) {
+ folio_unlock(folio);
+ if (wbc->sync_mode != WB_SYNC_NONE) {
folio_wait_writeback(folio);
#ifdef CONFIG_CIFS_FSCACHE
folio_wait_fscache(folio);
#endif
- goto redo_folio;
+ } else {
+ start += folio_size(folio);
}
-
- if (!folio_clear_dirty_for_io(folio))
- /* We hold the page lock - it should've been dirty. */
- WARN_ON(1);
-
- ret = cifs_write_back_from_locked_folio(mapping, wbc, folio, start, end);
- if (ret < 0)
- goto write_error;
-
- start += ret;
- continue;
-
-write_error:
- folio_batch_release(&fbatch);
- *_next = start;
- return ret;
-
-skip_write:
- /*
- * Too many skipped writes, or need to reschedule?
- * Treat it as a write error without an error code.
- */
- if (skips >= 5 || need_resched()) {
- ret = 0;
- goto write_error;
+ folio_put(folio);
+ if (wbc->sync_mode == WB_SYNC_NONE) {
+ if (skips >= 5 || need_resched())
+ break;
+ skips++;
}
-
- /* Otherwise, just skip that folio and go on to the next */
- skips++;
- start += folio_size(folio);
continue;
}

- folio_batch_release(&fbatch);
+ if (!folio_clear_dirty_for_io(folio))
+ /* We hold the page lock - it should've been dirty. */
+ WARN_ON(1);
+
+ ret = cifs_write_back_from_locked_folio(mapping, wbc, folio, start, end);
+ folio_put(folio);
+ if (ret < 0)
+ return ret;
+
+ start += ret;
cond_resched();
} while (wbc->nr_to_write > 0);