1 files changed, 238 insertions, 273 deletions

diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 2329cbb0e446..336c510f3750 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -63,9 +63,6 @@ static void nfs_clear_request_commit(struct nfs_commit_info *cinfo,
 				     struct nfs_page *req);
 static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo,
 				      struct inode *inode);
-static struct nfs_page *
-nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi,
-						struct folio *folio);
 
 static struct kmem_cache *nfs_wdata_cachep;
 static mempool_t *nfs_wdata_mempool;
@@ -156,44 +153,29 @@ nfs_page_set_inode_ref(struct nfs_page *req, struct inode *inode)
 	}
 }
 
-static int
-nfs_cancel_remove_inode(struct nfs_page *req, struct inode *inode)
+static void 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;
-}
-
-static struct nfs_page *nfs_folio_private_request(struct folio *folio)
-{
-	return folio_get_private(folio);
 }
 
 /**
- * nfs_folio_find_private_request - find head request associated with a folio
+ * nfs_folio_find_head_request - find head request associated with a folio
  * @folio: pointer to folio
  *
  * must be called while holding the inode lock.
  *
  * returns matching head request with reference held, or NULL if not found.
  */
-static struct nfs_page *nfs_folio_find_private_request(struct folio *folio)
+static struct nfs_page *nfs_folio_find_head_request(struct folio *folio)
 {
-	struct address_space *mapping = folio_file_mapping(folio);
+	struct address_space *mapping = folio->mapping;
 	struct nfs_page *req;
 
 	if (!folio_test_private(folio))
 		return NULL;
 	spin_lock(&mapping->i_private_lock);
-	req = nfs_folio_private_request(folio);
+	req = folio->private;
 	if (req) {
 		WARN_ON_ONCE(req->wb_head != req);
 		kref_get(&req->wb_kref);
@@ -202,86 +184,20 @@ static struct nfs_page *nfs_folio_find_private_request(struct folio *folio)
 	return req;
 }
 
-static struct nfs_page *nfs_folio_find_swap_request(struct folio *folio)
-{
-	struct inode *inode = folio_file_mapping(folio)->host;
-	struct nfs_inode *nfsi = NFS_I(inode);
-	struct nfs_page *req = NULL;
-	if (!folio_test_swapcache(folio))
-		return NULL;
-	mutex_lock(&nfsi->commit_mutex);
-	if (folio_test_swapcache(folio)) {
-		req = nfs_page_search_commits_for_head_request_locked(nfsi,
-								      folio);
-		if (req) {
-			WARN_ON_ONCE(req->wb_head != req);
-			kref_get(&req->wb_kref);
-		}
-	}
-	mutex_unlock(&nfsi->commit_mutex);
-	return req;
-}
-
-/**
- * nfs_folio_find_head_request - find head request associated with a folio
- * @folio: pointer to folio
- *
- * returns matching head request with reference held, or NULL if not found.
- */
-static struct nfs_page *nfs_folio_find_head_request(struct folio *folio)
-{
-	struct nfs_page *req;
-
-	req = nfs_folio_find_private_request(folio);
-	if (!req)
-		req = nfs_folio_find_swap_request(folio);
-	return req;
-}
-
-static struct nfs_page *nfs_folio_find_and_lock_request(struct folio *folio)
-{
-	struct inode *inode = folio_file_mapping(folio)->host;
-	struct nfs_page *req, *head;
-	int ret;
-
-	for (;;) {
-		req = nfs_folio_find_head_request(folio);
-		if (!req)
-			return req;
-		head = nfs_page_group_lock_head(req);
-		if (head != req)
-			nfs_release_request(req);
-		if (IS_ERR(head))
-			return head;
-		ret = nfs_cancel_remove_inode(head, inode);
-		if (ret < 0) {
-			nfs_unlock_and_release_request(head);
-			return ERR_PTR(ret);
-		}
-		/* Ensure that nobody removed the request before we locked it */
-		if (head == nfs_folio_private_request(folio))
-			break;
-		if (folio_test_swapcache(folio))
-			break;
-		nfs_unlock_and_release_request(head);
-	}
-	return head;
-}
-
 /* Adjust the file length if we're writing beyond the end */
 static void nfs_grow_file(struct folio *folio, unsigned int offset,
 			  unsigned int count)
 {
-	struct inode *inode = folio_file_mapping(folio)->host;
+	struct inode *inode = folio->mapping->host;
 	loff_t end, i_size;
 	pgoff_t end_index;
 
 	spin_lock(&inode->i_lock);
 	i_size = i_size_read(inode);
 	end_index = ((i_size - 1) >> folio_shift(folio)) << folio_order(folio);
-	if (i_size > 0 && folio_index(folio) < end_index)
+	if (i_size > 0 && folio->index < end_index)
 		goto out;
-	end = folio_file_pos(folio) + (loff_t)offset + (loff_t)count;
+	end = folio_pos(folio) + (loff_t)offset + (loff_t)count;
 	if (i_size >= end)
 		goto out;
 	trace_nfs_size_grow(inode, end);
@@ -289,6 +205,8 @@ static void nfs_grow_file(struct folio *folio, unsigned int offset,
 	NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_SIZE;
 	nfs_inc_stats(inode, NFSIOS_EXTENDWRITE);
 out:
+	/* Atomically update timestamps if they are delegated to us. */
+	nfs_update_delegated_mtime_locked(inode);
 	spin_unlock(&inode->i_lock);
 	nfs_fscache_invalidate(inode, 0);
 }
@@ -309,9 +227,8 @@ static void nfs_set_pageerror(struct address_space *mapping)
 
 static void nfs_mapping_set_error(struct folio *folio, int error)
 {
-	struct address_space *mapping = folio_file_mapping(folio);
+	struct address_space *mapping = folio->mapping;
 
-	folio_set_error(folio);
 	filemap_set_wb_err(mapping, error);
 	if (mapping->host)
 		errseq_set(&mapping->host->i_sb->s_wb_err,
@@ -320,59 +237,17 @@ static void nfs_mapping_set_error(struct folio *folio, int error)
 }
 
 /*
- * nfs_page_group_search_locked
- * @head - head request of page group
- * @page_offset - offset into page
- *
- * Search page group with head @head to find a request that contains the
- * page offset @page_offset.
- *
- * Returns a pointer to the first matching nfs request, or NULL if no
- * match is found.
+ * nfs_page_covers_folio
+ * @req: struct nfs_page
  *
- * Must be called with the page group lock held
- */
-static struct nfs_page *
-nfs_page_group_search_locked(struct nfs_page *head, unsigned int page_offset)
-{
-	struct nfs_page *req;
-
-	req = head;
-	do {
-		if (page_offset >= req->wb_pgbase &&
-		    page_offset < (req->wb_pgbase + req->wb_bytes))
-			return req;
-
-		req = req->wb_this_page;
-	} while (req != head);
-
-	return NULL;
-}
-
-/*
- * nfs_page_group_covers_page
- * @head - head request of page group
- *
- * Return true if the page group with head @head covers the whole page,
- * returns false otherwise
+ * Return true if the request covers the whole folio.
+ * Note that the caller should ensure all subrequests have been joined
  */
 static bool nfs_page_group_covers_page(struct nfs_page *req)
 {
 	unsigned int len = nfs_folio_length(nfs_page_to_folio(req));
-	struct nfs_page *tmp;
-	unsigned int pos = 0;
-
-	nfs_page_group_lock(req);
-
-	for (;;) {
-		tmp = nfs_page_group_search_locked(req->wb_head, pos);
-		if (!tmp)
-			break;
-		pos = tmp->wb_pgbase + tmp->wb_bytes;
-	}
 
-	nfs_page_group_unlock(req);
-	return pos >= len;
+	return req->wb_pgbase == 0 && req->wb_bytes == len;
 }
 
 /* We can set the PG_uptodate flag if we see that a write request
@@ -410,7 +285,7 @@ int nfs_congestion_kb;
 
 static void nfs_folio_set_writeback(struct folio *folio)
 {
-	struct nfs_server *nfss = NFS_SERVER(folio_file_mapping(folio)->host);
+	struct nfs_server *nfss = NFS_SERVER(folio->mapping->host);
 
 	folio_start_writeback(folio);
 	if (atomic_long_inc_return(&nfss->writeback) > NFS_CONGESTION_ON_THRESH)
@@ -419,12 +294,14 @@ static void nfs_folio_set_writeback(struct folio *folio)
 
 static void nfs_folio_end_writeback(struct folio *folio)
 {
-	struct nfs_server *nfss = NFS_SERVER(folio_file_mapping(folio)->host);
+	struct nfs_server *nfss = NFS_SERVER(folio->mapping->host);
 
-	folio_end_writeback(folio);
+	folio_end_writeback_no_dropbehind(folio);
 	if (atomic_long_dec_return(&nfss->writeback) <
-	    NFS_CONGESTION_OFF_THRESH)
+	    NFS_CONGESTION_OFF_THRESH) {
 		nfss->write_congested = 0;
+		wake_up_all(&nfss->write_congestion_wait);
+	}
 }
 
 static void nfs_page_end_writeback(struct nfs_page *req)
@@ -548,6 +425,74 @@ void nfs_join_page_group(struct nfs_page *head, struct nfs_commit_info *cinfo,
 	nfs_destroy_unlinked_subrequests(destroy_list, head, inode);
 }
 
+/**
+ * nfs_wait_on_request - Wait for a request to complete.
+ * @req: request to wait upon.
+ *
+ * Interruptible by fatal signals only.
+ * The user is responsible for holding a count on the request.
+ */
+static int nfs_wait_on_request(struct nfs_page *req)
+{
+	if (!test_bit(PG_BUSY, &req->wb_flags))
+		return 0;
+	set_bit(PG_CONTENDED2, &req->wb_flags);
+	smp_mb__after_atomic();
+	return wait_on_bit_io(&req->wb_flags, PG_BUSY,
+			      TASK_UNINTERRUPTIBLE);
+}
+
+/*
+ * nfs_unroll_locks -  unlock all newly locked reqs and wait on @req
+ * @head: head request of page group, must be holding head lock
+ * @req: request that couldn't lock and needs to wait on the req bit lock
+ *
+ * This is a helper function for nfs_lock_and_join_requests
+ * returns 0 on success, < 0 on error.
+ */
+static void
+nfs_unroll_locks(struct nfs_page *head, struct nfs_page *req)
+{
+	struct nfs_page *tmp;
+
+	/* relinquish all the locks successfully grabbed this run */
+	for (tmp = head->wb_this_page ; tmp != req; tmp = tmp->wb_this_page) {
+		if (!kref_read(&tmp->wb_kref))
+			continue;
+		nfs_unlock_and_release_request(tmp);
+	}
+}
+
+/*
+ * nfs_page_group_lock_subreq -  try to lock a subrequest
+ * @head: head request of page group
+ * @subreq: request to lock
+ *
+ * This is a helper function for nfs_lock_and_join_requests which
+ * must be called with the head request and page group both locked.
+ * On error, it returns with the page group unlocked.
+ */
+static int
+nfs_page_group_lock_subreq(struct nfs_page *head, struct nfs_page *subreq)
+{
+	int ret;
+
+	if (!kref_get_unless_zero(&subreq->wb_kref))
+		return 0;
+	while (!nfs_lock_request(subreq)) {
+		nfs_page_group_unlock(head);
+		ret = nfs_wait_on_request(subreq);
+		if (!ret)
+			ret = nfs_page_group_lock(head);
+		if (ret < 0) {
+			nfs_unroll_locks(head, subreq);
+			nfs_release_request(subreq);
+			return ret;
+		}
+	}
+	return 0;
+}
+
 /*
  * nfs_lock_and_join_requests - join all subreqs to the head req
  * @folio: the folio used to lookup the "page group" of nfs_page structures
@@ -565,31 +510,60 @@ void nfs_join_page_group(struct nfs_page *head, struct nfs_commit_info *cinfo,
  */
 static struct nfs_page *nfs_lock_and_join_requests(struct folio *folio)
 {
-	struct inode *inode = folio_file_mapping(folio)->host;
-	struct nfs_page *head;
+	struct inode *inode = folio->mapping->host;
+	struct nfs_page *head, *subreq;
 	struct nfs_commit_info cinfo;
 	int ret;
 
-	nfs_init_cinfo_from_inode(&cinfo, inode);
 	/*
 	 * A reference is taken only on the head request which acts as a
 	 * reference to the whole page group - the group will not be destroyed
 	 * until the head reference is released.
 	 */
-	head = nfs_folio_find_and_lock_request(folio);
-	if (IS_ERR_OR_NULL(head))
-		return head;
+retry:
+	head = nfs_folio_find_head_request(folio);
+	if (!head)
+		return NULL;
 
-	/* lock each request in the page group */
-	ret = nfs_page_group_lock_subrequests(head);
-	if (ret < 0) {
+	while (!nfs_lock_request(head)) {
+		ret = nfs_wait_on_request(head);
+		if (ret < 0) {
+			nfs_release_request(head);
+			return ERR_PTR(ret);
+		}
+	}
+
+	ret = nfs_page_group_lock(head);
+	if (ret < 0)
+		goto out_unlock;
+
+	/* Ensure that nobody removed the request before we locked it */
+	if (head != folio->private) {
+		nfs_page_group_unlock(head);
 		nfs_unlock_and_release_request(head);
-		return ERR_PTR(ret);
+		goto retry;
 	}
 
-	nfs_join_page_group(head, &cinfo, inode);
+	nfs_cancel_remove_inode(head, inode);
 
+	/* lock each request in the page group */
+	for (subreq = head->wb_this_page;
+	     subreq != head;
+	     subreq = subreq->wb_this_page) {
+		ret = nfs_page_group_lock_subreq(head, subreq);
+		if (ret < 0)
+			goto out_unlock;
+	}
+
+	nfs_page_group_unlock(head);
+
+	nfs_init_cinfo_from_inode(&cinfo, inode);
+	nfs_join_page_group(head, &cinfo, inode);
 	return head;
+
+out_unlock:
+	nfs_unlock_and_release_request(head);
+	return ERR_PTR(ret);
 }
 
 static void nfs_write_error(struct nfs_page *req, int error)
@@ -605,20 +579,21 @@ static void nfs_write_error(struct nfs_page *req, int error)
  * Find an associated nfs write request, and prepare to flush it out
  * May return an error if the user signalled nfs_wait_on_request().
  */
-static int nfs_page_async_flush(struct folio *folio,
-				struct writeback_control *wbc,
-				struct nfs_pageio_descriptor *pgio)
+static int nfs_do_writepage(struct folio *folio, struct writeback_control *wbc,
+		struct nfs_pageio_descriptor *pgio)
 {
 	struct nfs_page *req;
-	int ret = 0;
+	int ret;
+
+	nfs_pageio_cond_complete(pgio, folio->index);
 
 	req = nfs_lock_and_join_requests(folio);
 	if (!req)
-		goto out;
-	ret = PTR_ERR(req);
+		return 0;
 	if (IS_ERR(req))
-		goto out;
+		return PTR_ERR(req);
 
+	trace_nfs_do_writepage(req);
 	nfs_folio_set_writeback(folio);
 	WARN_ON_ONCE(test_bit(PG_CLEAN, &req->wb_flags));
 
@@ -627,7 +602,6 @@ static int nfs_page_async_flush(struct folio *folio,
 	if (nfs_error_is_fatal_on_server(ret))
 		goto out_launder;
 
-	ret = 0;
 	if (!nfs_pageio_add_request(pgio, req)) {
 		ret = pgio->pg_error;
 		/*
@@ -635,28 +609,20 @@ static int nfs_page_async_flush(struct folio *folio,
 		 */
 		if (nfs_error_is_fatal_on_server(ret))
 			goto out_launder;
-		if (wbc->sync_mode == WB_SYNC_NONE)
-			ret = AOP_WRITEPAGE_ACTIVATE;
 		folio_redirty_for_writepage(wbc, folio);
 		nfs_redirty_request(req);
 		pgio->pg_error = 0;
-	} else
-		nfs_add_stats(folio_file_mapping(folio)->host,
-			      NFSIOS_WRITEPAGES, 1);
-out:
-	return ret;
+		return ret;
+	}
+
+	nfs_add_stats(folio->mapping->host, NFSIOS_WRITEPAGES, 1);
+	return 0;
+
 out_launder:
 	nfs_write_error(req, ret);
 	return 0;
 }
 
-static int nfs_do_writepage(struct folio *folio, struct writeback_control *wbc,
-			    struct nfs_pageio_descriptor *pgio)
-{
-	nfs_pageio_cond_complete(pgio, folio_index(folio));
-	return nfs_page_async_flush(folio, wbc, pgio);
-}
-
 /*
  * Write an mmapped page to the server.
  */
@@ -664,7 +630,7 @@ static int nfs_writepage_locked(struct folio *folio,
 				struct writeback_control *wbc)
 {
 	struct nfs_pageio_descriptor pgio;
-	struct inode *inode = folio_file_mapping(folio)->host;
+	struct inode *inode = folio->mapping->host;
 	int err;
 
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
@@ -676,17 +642,6 @@ static int nfs_writepage_locked(struct folio *folio,
 	return err;
 }
 
-static int nfs_writepages_callback(struct folio *folio,
-				   struct writeback_control *wbc, void *data)
-{
-	int ret;
-
-	ret = nfs_do_writepage(folio, wbc, data);
-	if (ret != AOP_WRITEPAGE_ACTIVATE)
-		folio_unlock(folio);
-	return ret;
-}
-
 static void nfs_io_completion_commit(void *inode)
 {
 	nfs_commit_inode(inode, 0);
@@ -698,17 +653,24 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 	struct nfs_pageio_descriptor pgio;
 	struct nfs_io_completion *ioc = NULL;
 	unsigned int mntflags = NFS_SERVER(inode)->flags;
+	struct nfs_server *nfss = NFS_SERVER(inode);
 	int priority = 0;
 	int err;
 
-	if (wbc->sync_mode == WB_SYNC_NONE &&
-	    NFS_SERVER(inode)->write_congested)
-		return 0;
+	trace_nfs_writepages(inode, wbc->range_start, wbc->range_end - wbc->range_start);
+
+	/* Wait with writeback until write congestion eases */
+	if (wbc->sync_mode == WB_SYNC_NONE && nfss->write_congested) {
+		err = wait_event_killable(nfss->write_congestion_wait,
+					  nfss->write_congested == 0);
+		if (err)
+			goto out_err;
+	}
 
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);
 
 	if (!(mntflags & NFS_MOUNT_WRITE_EAGER) || wbc->for_kupdate ||
-	    wbc->for_background || wbc->for_sync || wbc->for_reclaim) {
+	    wbc->for_background || wbc->for_sync) {
 		ioc = nfs_io_completion_alloc(GFP_KERNEL);
 		if (ioc)
 			nfs_io_completion_init(ioc, nfs_io_completion_commit,
@@ -717,11 +679,15 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 	}
 
 	do {
+		struct folio *folio = NULL;
+
 		nfs_pageio_init_write(&pgio, inode, priority, false,
 				      &nfs_async_write_completion_ops);
 		pgio.pg_io_completion = ioc;
-		err = write_cache_pages(mapping, wbc, nfs_writepages_callback,
-					&pgio);
+		while ((folio = writeback_iter(mapping, wbc, folio, &err))) {
+			err = nfs_do_writepage(folio, wbc, &pgio);
+			folio_unlock(folio);
+		}
 		pgio.pg_error = 0;
 		nfs_pageio_complete(&pgio);
 		if (err == -EAGAIN && mntflags & NFS_MOUNT_SOFTERR)
@@ -729,10 +695,10 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 	} while (err < 0 && !nfs_error_is_fatal(err));
 	nfs_io_completion_put(ioc);
 
-	if (err < 0)
-		goto out_err;
-	return 0;
+	if (err > 0)
+		err = 0;
 out_err:
+	trace_nfs_writepages_done(inode, wbc->range_start, wbc->range_end - wbc->range_start, err);
 	return err;
 }
 
@@ -742,24 +708,17 @@ out_err:
 static void nfs_inode_add_request(struct nfs_page *req)
 {
 	struct folio *folio = nfs_page_to_folio(req);
-	struct address_space *mapping = folio_file_mapping(folio);
+	struct address_space *mapping = folio->mapping;
 	struct nfs_inode *nfsi = NFS_I(mapping->host);
 
 	WARN_ON_ONCE(req->wb_this_page != req);
 
 	/* Lock the request! */
 	nfs_lock_request(req);
-
-	/*
-	 * Swap-space should not get truncated. Hence no need to plug the race
-	 * with invalidate/truncate.
-	 */
 	spin_lock(&mapping->i_private_lock);
-	if (likely(!folio_test_swapcache(folio))) {
-		set_bit(PG_MAPPED, &req->wb_flags);
-		folio_set_private(folio);
-		folio->private = req;
-	}
+	set_bit(PG_MAPPED, &req->wb_flags);
+	folio_set_private(folio);
+	folio->private = req;
 	spin_unlock(&mapping->i_private_lock);
 	atomic_long_inc(&nfsi->nrequests);
 	/* this a head request for a page group - mark it as having an
@@ -777,18 +736,22 @@ static void nfs_inode_remove_request(struct nfs_page *req)
 {
 	struct nfs_inode *nfsi = NFS_I(nfs_page_to_inode(req));
 
-	if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) {
+	nfs_page_group_lock(req);
+	if (nfs_page_group_sync_on_bit_locked(req, PG_REMOVE)) {
 		struct folio *folio = nfs_page_to_folio(req->wb_head);
-		struct address_space *mapping = folio_file_mapping(folio);
+		struct address_space *mapping = folio->mapping;
 
 		spin_lock(&mapping->i_private_lock);
-		if (likely(folio && !folio_test_swapcache(folio))) {
+		if (likely(folio)) {
 			folio->private = NULL;
 			folio_clear_private(folio);
 			clear_bit(PG_MAPPED, &req->wb_head->wb_flags);
 		}
 		spin_unlock(&mapping->i_private_lock);
+
+		folio_end_dropbehind(folio);
 	}
+	nfs_page_group_unlock(req);
 
 	if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) {
 		atomic_long_dec(&nfsi->nrequests);
@@ -803,38 +766,6 @@ static void nfs_mark_request_dirty(struct nfs_page *req)
 		filemap_dirty_folio(folio_mapping(folio), folio);
 }
 
-/*
- * nfs_page_search_commits_for_head_request_locked
- *
- * Search through commit lists on @inode for the head request for @folio.
- * Must be called while holding the inode (which is cinfo) lock.
- *
- * Returns the head request if found, or NULL if not found.
- */
-static struct nfs_page *
-nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi,
-						struct folio *folio)
-{
-	struct nfs_page *freq, *t;
-	struct nfs_commit_info cinfo;
-	struct inode *inode = &nfsi->vfs_inode;
-
-	nfs_init_cinfo_from_inode(&cinfo, inode);
-
-	/* search through pnfs commit lists */
-	freq = pnfs_search_commit_reqs(inode, &cinfo, folio);
-	if (freq)
-		return freq->wb_head;
-
-	/* Linearly search the commit list for the correct request */
-	list_for_each_entry_safe(freq, t, &cinfo.mds->list, wb_list) {
-		if (nfs_page_to_folio(freq) == folio)
-			return freq->wb_head;
-	}
-
-	return NULL;
-}
-
 /**
  * nfs_request_add_commit_list_locked - add request to a commit list
  * @req: pointer to a struct nfs_page
@@ -941,7 +872,7 @@ static void nfs_folio_clear_commit(struct folio *folio)
 		long nr = folio_nr_pages(folio);
 
 		node_stat_mod_folio(folio, NR_WRITEBACK, -nr);
-		wb_stat_mod(&inode_to_bdi(folio_file_mapping(folio)->host)->wb,
+		wb_stat_mod(&inode_to_bdi(folio->mapping->host)->wb,
 			    WB_WRITEBACK, -nr);
 	}
 }
@@ -1000,7 +931,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr)
 			req->wb_nio = 0;
 			memcpy(&req->wb_verf, &hdr->verf.verifier, sizeof(req->wb_verf));
 			nfs_mark_request_commit(req, hdr->lseg, &cinfo,
-				hdr->pgio_mirror_idx);
+				hdr->ds_commit_idx);
 			goto next;
 		}
 remove_req:
@@ -1091,11 +1022,12 @@ static struct nfs_page *nfs_try_to_update_request(struct folio *folio,
 	unsigned int end;
 	int error;
 
+	trace_nfs_try_to_update_request(folio_inode(folio), offset, bytes);
 	end = offset + bytes;
 
 	req = nfs_lock_and_join_requests(folio);
 	if (IS_ERR_OR_NULL(req))
-		return req;
+		goto out;
 
 	rqend = req->wb_offset + req->wb_bytes;
 	/*
@@ -1117,6 +1049,9 @@ static struct nfs_page *nfs_try_to_update_request(struct folio *folio,
 	else
 		req->wb_bytes = rqend - req->wb_offset;
 	req->wb_nio = 0;
+out:
+	trace_nfs_try_to_update_request_done(folio_inode(folio), offset, bytes,
+					     PTR_ERR_OR_ZERO(req));
 	return req;
 out_flushme:
 	/*
@@ -1126,7 +1061,8 @@ out_flushme:
 	 */
 	nfs_mark_request_dirty(req);
 	nfs_unlock_and_release_request(req);
-	error = nfs_wb_folio(folio_file_mapping(folio)->host, folio);
+	error = nfs_wb_folio(folio->mapping->host, folio);
+	trace_nfs_try_to_update_request_done(folio_inode(folio), offset, bytes, error);
 	return (error < 0) ? ERR_PTR(error) : NULL;
 }
 
@@ -1164,6 +1100,7 @@ static int nfs_writepage_setup(struct nfs_open_context *ctx,
 	req = nfs_setup_write_request(ctx, folio, offset, count);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
+	trace_nfs_writepage_setup(req);
 	/* Update file length */
 	nfs_grow_file(folio, offset, count);
 	nfs_mark_uptodate(req);
@@ -1202,7 +1139,7 @@ int nfs_flush_incompatible(struct file *file, struct folio *folio)
 		nfs_release_request(req);
 		if (!do_flush)
 			return 0;
-		status = nfs_wb_folio(folio_file_mapping(folio)->host, folio);
+		status = nfs_wb_folio(folio->mapping->host, folio);
 	} while (status == 0);
 	return status;
 }
@@ -1276,7 +1213,7 @@ out:
  */
 static bool nfs_folio_write_uptodate(struct folio *folio, unsigned int pagelen)
 {
-	struct inode *inode = folio_file_mapping(folio)->host;
+	struct inode *inode = folio->mapping->host;
 	struct nfs_inode *nfsi = NFS_I(inode);
 
 	if (nfs_have_delegated_attributes(inode))
@@ -1315,12 +1252,15 @@ static int nfs_can_extend_write(struct file *file, struct folio *folio,
 	struct file_lock_context *flctx = locks_inode_context(inode);
 	struct file_lock *fl;
 	int ret;
+	unsigned int mntflags = NFS_SERVER(inode)->flags;
 
+	if (mntflags & NFS_MOUNT_NO_ALIGNWRITE)
+		return 0;
 	if (file->f_flags & O_DSYNC)
 		return 0;
 	if (!nfs_folio_write_uptodate(folio, pagelen))
 		return 0;
-	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
+	if (nfs_have_write_delegation(inode))
 		return 1;
 	if (!flctx || (list_empty_careful(&flctx->flc_flock) &&
 		       list_empty_careful(&flctx->flc_posix)))
@@ -1354,28 +1294,35 @@ int nfs_update_folio(struct file *file, struct folio *folio,
 		     unsigned int offset, unsigned int count)
 {
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
-	struct address_space *mapping = folio_file_mapping(folio);
+	struct address_space *mapping = folio->mapping;
 	struct inode *inode = mapping->host;
 	unsigned int pagelen = nfs_folio_length(folio);
 	int		status = 0;
 
 	nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE);
 
+	trace_nfs_update_folio(inode, offset, count);
+
 	dprintk("NFS:       nfs_update_folio(%pD2 %d@%lld)\n", file, count,
-		(long long)(folio_file_pos(folio) + offset));
+		(long long)(folio_pos(folio) + offset));
 
 	if (!count)
 		goto out;
 
 	if (nfs_can_extend_write(file, folio, pagelen)) {
-		count = max(count + offset, pagelen);
-		offset = 0;
+		unsigned int end = count + offset;
+
+		offset = round_down(offset, PAGE_SIZE);
+		if (end < pagelen)
+			end = min(round_up(end, PAGE_SIZE), pagelen);
+		count = end - offset;
 	}
 
 	status = nfs_writepage_setup(ctx, folio, offset, count);
 	if (status < 0)
 		nfs_set_pageerror(mapping);
 out:
+	trace_nfs_update_folio_done(inode, offset, count, status);
 	dprintk("NFS:       nfs_update_folio returns %d (isize %lld)\n",
 			status, (long long)i_size_read(inode));
 	return status;
@@ -1514,6 +1461,13 @@ void nfs_writeback_update_inode(struct nfs_pgio_header *hdr)
 	struct nfs_fattr *fattr = &hdr->fattr;
 	struct inode *inode = hdr->inode;
 
+	if (nfs_have_delegated_mtime(inode)) {
+		spin_lock(&inode->i_lock);
+		nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS);
+		spin_unlock(&inode->i_lock);
+		return;
+	}
+
 	spin_lock(&inode->i_lock);
 	nfs_writeback_check_extend(hdr, fattr);
 	nfs_post_op_update_inode_force_wcc_locked(inode, fattr);
@@ -1581,7 +1535,8 @@ static int nfs_writeback_done(struct rpc_task *task,
 	/* Deal with the suid/sgid bit corner case */
 	if (nfs_should_remove_suid(inode)) {
 		spin_lock(&inode->i_lock);
-		nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE);
+		nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE
+				| NFS_INO_REVAL_FORCED);
 		spin_unlock(&inode->i_lock);
 	}
 	return 0;
@@ -1670,7 +1625,8 @@ EXPORT_SYMBOL_GPL(nfs_commitdata_release);
 int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
 			const struct nfs_rpc_ops *nfs_ops,
 			const struct rpc_call_ops *call_ops,
-			int how, int flags)
+			int how, int flags,
+			struct nfsd_file *localio)
 {
 	struct rpc_task *task;
 	int priority = flush_task_priority(how);
@@ -1699,6 +1655,9 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
 
 	dprintk("NFS: initiated commit call\n");
 
+	if (localio)
+		return nfs_local_commit(localio, data, call_ops, how);
+
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
 		return PTR_ERR(task);
@@ -1798,6 +1757,7 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
 		struct nfs_commit_info *cinfo)
 {
 	struct nfs_commit_data	*data;
+	struct nfsd_file *localio;
 	unsigned short task_flags = 0;
 
 	/* another commit raced with us */
@@ -1814,9 +1774,13 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
 	nfs_init_commit(data, head, NULL, cinfo);
 	if (NFS_SERVER(inode)->nfs_client->cl_minorversion)
 		task_flags = RPC_TASK_MOVEABLE;
+
+	localio = nfs_local_open_fh(NFS_SERVER(inode)->nfs_client, data->cred,
+				    data->args.fh, &data->context->nfl,
+				    data->context->mode);
 	return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode),
 				   data->mds_ops, how,
-				   RPC_TASK_CRED_NOREF | task_flags);
+				   RPC_TASK_CRED_NOREF | task_flags, localio);
 }
 
 /*
@@ -1837,7 +1801,6 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 	struct nfs_page	*req;
 	int status = data->task.tk_status;
 	struct nfs_commit_info cinfo;
-	struct nfs_server *nfss;
 	struct folio *folio;
 
 	while (!list_empty(&data->pages)) {
@@ -1858,7 +1821,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 				nfs_mapping_set_error(folio, status);
 				nfs_inode_remove_request(req);
 			}
-			dprintk_cont(", error = %d\n", status);
+			dprintk(", error = %d\n", status);
 			goto next;
 		}
 
@@ -1868,11 +1831,11 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 			/* We have a match */
 			if (folio)
 				nfs_inode_remove_request(req);
-			dprintk_cont(" OK\n");
+			dprintk(" OK\n");
 			goto next;
 		}
 		/* We have a mismatch. Write the page again */
-		dprintk_cont(" mismatch\n");
+		dprintk(" mismatch\n");
 		nfs_mark_request_dirty(req);
 		atomic_long_inc(&NFS_I(data->inode)->redirtied_pages);
 	next:
@@ -1880,9 +1843,6 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 		/* Latency breaker */
 		cond_resched();
 	}
-	nfss = NFS_SERVER(data->inode);
-	if (atomic_long_read(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
-		nfss->write_congested = 0;
 
 	nfs_init_cinfo(&cinfo, data->inode, data->dreq);
 	nfs_commit_end(cinfo.mds);
@@ -2058,6 +2018,7 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio)
 		 * release it */
 		nfs_inode_remove_request(req);
 		nfs_unlock_and_release_request(req);
+		folio_cancel_dirty(folio);
 	}
 
 	return ret;
@@ -2073,17 +2034,17 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio)
  */
 int nfs_wb_folio(struct inode *inode, struct folio *folio)
 {
-	loff_t range_start = folio_file_pos(folio);
-	loff_t range_end = range_start + (loff_t)folio_size(folio) - 1;
+	loff_t range_start = folio_pos(folio);
+	size_t len = folio_size(folio);
 	struct writeback_control wbc = {
 		.sync_mode = WB_SYNC_ALL,
 		.nr_to_write = 0,
 		.range_start = range_start,
-		.range_end = range_end,
+		.range_end = range_start + len - 1,
 	};
 	int ret;
 
-	trace_nfs_writeback_folio(inode, folio);
+	trace_nfs_writeback_folio(inode, range_start, len);
 
 	for (;;) {
 		folio_wait_writeback(folio);
@@ -2101,7 +2062,7 @@ int nfs_wb_folio(struct inode *inode, struct folio *folio)
 			goto out_error;
 	}
 out_error:
-	trace_nfs_writeback_folio_done(inode, folio, ret);
+	trace_nfs_writeback_folio_done(inode, range_start, len, ret);
 	return ret;
 }
 
@@ -2117,8 +2078,12 @@ int nfs_migrate_folio(struct address_space *mapping, struct folio *dst,
 	 *        that we can safely release the inode reference while holding
 	 *        the folio lock.
 	 */
-	if (folio_test_private(src))
-		return -EBUSY;
+	if (folio_test_private(src)) {
+		if (mode == MIGRATE_SYNC)
+			nfs_wb_folio(src->mapping->host, src);
+		if (folio_test_private(src))
+			return -EBUSY;
+	}
 
 	if (folio_test_private_2(src)) { /* [DEPRECATED] */
 		if (mode == MIGRATE_ASYNC)