Re: Ceph and Netfslib

[Matthew Wilcox <willy@infradead.org>]

On Mon, Dec 23, 2024 at 11:13:47PM +0000, Viacheslav Dubeyko wrote:
>  * On writeback, we must submit writes to the osd IN SNAP ORDER.  So,
>  * we look for the first capsnap in i_cap_snaps and write out pages in
>  * that snap context _only_.  Then we move on to the next capsnap,
>  * eventually reaching the "live" or "head" context (i.e., pages that
>  * are not yet snapped) and are writing the most recently dirtied
>  * pages

Speaking of writeback, ceph doesn't need a writepage operation.  We're
removing ->writepage from filesystems in favour of using ->migrate_folio
for migration and ->writepages for writeback.  As far as I can tell,
filemap_migrate_folio() will be perfect for ceph (as the ceph_snap_context
contains no references to the address of the memory).  And ceph already
has a ->writepages.  So I think this patch should work.  Can you give it
a try?

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 85936f6d2bf7..5a5a870b6aee 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -810,32 +810,6 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	return err;
 }
 
-static int ceph_writepage(struct page *page, struct writeback_control *wbc)
-{
-	int err;
-	struct inode *inode = page->mapping->host;
-	BUG_ON(!inode);
-	ihold(inode);
-
-	if (wbc->sync_mode == WB_SYNC_NONE &&
-	    ceph_inode_to_fs_client(inode)->write_congested) {
-		redirty_page_for_writepage(wbc, page);
-		return AOP_WRITEPAGE_ACTIVATE;
-	}
-
-	folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */
-
-	err = writepage_nounlock(page, wbc);
-	if (err == -ERESTARTSYS) {
-		/* direct memory reclaimer was killed by SIGKILL. return 0
-		 * to prevent caller from setting mapping/page error */
-		err = 0;
-	}
-	unlock_page(page);
-	iput(inode);
-	return err;
-}
-
 /*
  * async writeback completion handler.
  *
@@ -1584,7 +1558,6 @@ static int ceph_write_end(struct file *file, struct address_space *mapping,
 const struct address_space_operations ceph_aops = {
 	.read_folio = netfs_read_folio,
 	.readahead = netfs_readahead,
-	.writepage = ceph_writepage,
 	.writepages = ceph_writepages_start,
 	.write_begin = ceph_write_begin,
 	.write_end = ceph_write_end,
@@ -1592,6 +1565,7 @@ const struct address_space_operations ceph_aops = {
 	.invalidate_folio = ceph_invalidate_folio,
 	.release_folio = netfs_release_folio,
 	.direct_IO = noop_direct_IO,
+	.migrate_folio = filemap_migrate_folio,
 };
 
 static void ceph_block_sigs(sigset_t *oldset)