nfs: don't reuse partially completed requests in nfs_lock_and_join_requests

When NFS requests are split into sub-requests, nfs_inode_remove_request
calls nfs_page_group_sync_on_bit to set PG_REMOVE on this sub-request and
only completes the head requests once PG_REMOVE is set on all requests.
This means that when nfs_lock_and_join_requests sees a PG_REMOVE bit, I/O
on the request is in progress and has partially completed.   If such a
request is returned to nfs_try_to_update_request, it could be extended
with the newly dirtied region and I/O for the combined range will be
re-scheduled, leading to extra I/O.

Change the logic to instead restart the search for a request when any
PG_REMOVE bit is set, as the completion handler will remove the request
as soon as it can take the page group lock.  This not only avoid
extending the I/O but also does the right thing for the callers that
want to cancel or flush the request.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

fs/nfs/write.c

@@ -144,31 +144,6 @@ static void nfs_io_completion_put(struct nfs_io_completion *ioc)
 		kref_put(&ioc->refcount, nfs_io_completion_release);
 }
 
-static void
-nfs_page_set_inode_ref(struct nfs_page *req, struct inode *inode)
-{
-	if (!test_and_set_bit(PG_INODE_REF, &req->wb_flags)) {
-		kref_get(&req->wb_kref);
-		atomic_long_inc(&NFS_I(inode)->nrequests);
-	}
-}
-
-static int
-nfs_cancel_remove_inode(struct nfs_page *req, struct inode *inode)
-{
-	int ret;
-
-	if (!test_bit(PG_REMOVE, &req->wb_flags))
-		return 0;
-	ret = nfs_page_group_lock(req);
-	if (ret)
-		return ret;
-	if (test_and_clear_bit(PG_REMOVE, &req->wb_flags))
-		nfs_page_set_inode_ref(req, inode);
-	nfs_page_group_unlock(req);
-	return 0;
-}
-
 /**
  * nfs_folio_find_head_request - find head request associated with a folio
  * @folio: pointer to folio
@@ -566,6 +541,7 @@ static struct nfs_page *nfs_lock_and_join_requests(struct folio *folio)
 	struct inode *inode = folio->mapping->host;
 	struct nfs_page *head, *subreq;
 	struct nfs_commit_info cinfo;
+	bool removed;
 	int ret;
 
 	/*
@@ -590,18 +566,18 @@ static struct nfs_page *nfs_lock_and_join_requests(struct folio *folio)
 		goto retry;
 	}
 
-	ret = nfs_cancel_remove_inode(head, inode);
-	if (ret < 0)
-		goto out_unlock;
-
 	ret = nfs_page_group_lock(head);
 	if (ret < 0)
 		goto out_unlock;
 
+	removed = test_bit(PG_REMOVE, &head->wb_flags);
+
 	/* lock each request in the page group */
 	for (subreq = head->wb_this_page;
 	     subreq != head;
 	     subreq = subreq->wb_this_page) {
+		if (test_bit(PG_REMOVE, &subreq->wb_flags))
+			removed = true;
 		ret = nfs_page_group_lock_subreq(head, subreq);
 		if (ret < 0)
 			goto out_unlock;
@@ -609,6 +585,21 @@ static struct nfs_page *nfs_lock_and_join_requests(struct folio *folio)
 
 	nfs_page_group_unlock(head);
 
+	/*
+	 * If PG_REMOVE is set on any request, I/O on that request has
+	 * completed, but some requests were still under I/O at the time
+	 * we locked the head request.
+	 *
+	 * In that case the above wait for all requests means that all I/O
+	 * has now finished, and we can restart from a clean slate.  Let the
+	 * old requests go away and start from scratch instead.
+	 */
+	if (removed) {
+		nfs_unroll_locks(head, head);
+		nfs_unlock_and_release_request(head);
+		goto retry;
+	}
+
 	nfs_init_cinfo_from_inode(&cinfo, inode);
 	nfs_join_page_group(head, &cinfo, inode);
 	return head;