Merge branch 'devel-stable' into for-next

41 files changed, 624 insertions, 179 deletions

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 993642199326..6d67f32e648d 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1645,14 +1645,14 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 
 	parent_nritems = btrfs_header_nritems(parent);
 	blocksize = root->nodesize;
-	end_slot = parent_nritems;
+	end_slot = parent_nritems - 1;
 
-	if (parent_nritems == 1)
+	if (parent_nritems <= 1)
 		return 0;
 
 	btrfs_set_lock_blocking(parent);
 
-	for (i = start_slot; i < end_slot; i++) {
+	for (i = start_slot; i <= end_slot; i++) {
 		int close = 1;
 
 		btrfs_node_key(parent, &disk_key, i);
@@ -1669,7 +1669,7 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 			other = btrfs_node_blockptr(parent, i - 1);
 			close = close_blocks(blocknr, other, blocksize);
 		}
-		if (!close && i < end_slot - 2) {
+		if (!close && i < end_slot) {
 			other = btrfs_node_blockptr(parent, i + 1);
 			close = close_blocks(blocknr, other, blocksize);
 		}
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 571f402d3fc4..6f080451fcb1 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3208,6 +3208,8 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group,
 		return 0;
 	}
 
+	if (trans->aborted)
+		return 0;
 again:
 	inode = lookup_free_space_inode(root, block_group, path);
 	if (IS_ERR(inode) && PTR_ERR(inode) != -ENOENT) {
@@ -3243,6 +3245,20 @@ again:
 	 */
 	BTRFS_I(inode)->generation = 0;
 	ret = btrfs_update_inode(trans, root, inode);
+	if (ret) {
+		/*
+		 * So theoretically we could recover from this, simply set the
+		 * super cache generation to 0 so we know to invalidate the
+		 * cache, but then we'd have to keep track of the block groups
+		 * that fail this way so we know we _have_ to reset this cache
+		 * before the next commit or risk reading stale cache.  So to
+		 * limit our exposure to horrible edge cases lets just abort the
+		 * transaction, this only happens in really bad situations
+		 * anyway.
+		 */
+		btrfs_abort_transaction(trans, root, ret);
+		goto out_put;
+	}
 	WARN_ON(ret);
 
 	if (i_size_read(inode) > 0) {
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index b78bbbac900d..30982bbd31c3 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1811,22 +1811,10 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	mutex_unlock(&inode->i_mutex);
 
 	/*
-	 * we want to make sure fsync finds this change
-	 * but we haven't joined a transaction running right now.
-	 *
-	 * Later on, someone is sure to update the inode and get the
-	 * real transid recorded.
-	 *
-	 * We set last_trans now to the fs_info generation + 1,
-	 * this will either be one more than the running transaction
-	 * or the generation used for the next transaction if there isn't
-	 * one running right now.
-	 *
 	 * We also have to set last_sub_trans to the current log transid,
 	 * otherwise subsequent syncs to a file that's been synced in this
 	 * transaction will appear to have already occured.
 	 */
-	BTRFS_I(inode)->last_trans = root->fs_info->generation + 1;
 	BTRFS_I(inode)->last_sub_trans = root->log_transid;
 	if (num_written > 0) {
 		err = generic_write_sync(file, pos, num_written);
@@ -1959,25 +1947,37 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	atomic_inc(&root->log_batch);
 
 	/*
-	 * check the transaction that last modified this inode
-	 * and see if its already been committed
-	 */
-	if (!BTRFS_I(inode)->last_trans) {
-		mutex_unlock(&inode->i_mutex);
-		goto out;
-	}
-
-	/*
-	 * if the last transaction that changed this file was before
-	 * the current transaction, we can bail out now without any
-	 * syncing
+	 * If the last transaction that changed this file was before the current
+	 * transaction and we have the full sync flag set in our inode, we can
+	 * bail out now without any syncing.
+	 *
+	 * Note that we can't bail out if the full sync flag isn't set. This is
+	 * because when the full sync flag is set we start all ordered extents
+	 * and wait for them to fully complete - when they complete they update
+	 * the inode's last_trans field through:
+	 *
+	 *     btrfs_finish_ordered_io() ->
+	 *         btrfs_update_inode_fallback() ->
+	 *             btrfs_update_inode() ->
+	 *                 btrfs_set_inode_last_trans()
+	 *
+	 * So we are sure that last_trans is up to date and can do this check to
+	 * bail out safely. For the fast path, when the full sync flag is not
+	 * set in our inode, we can not do it because we start only our ordered
+	 * extents and don't wait for them to complete (that is when
+	 * btrfs_finish_ordered_io runs), so here at this point their last_trans
+	 * value might be less than or equals to fs_info->last_trans_committed,
+	 * and setting a speculative last_trans for an inode when a buffered
+	 * write is made (such as fs_info->generation + 1 for example) would not
+	 * be reliable since after setting the value and before fsync is called
+	 * any number of transactions can start and commit (transaction kthread
+	 * commits the current transaction periodically), and a transaction
+	 * commit does not start nor waits for ordered extents to complete.
 	 */
 	smp_mb();
 	if (btrfs_inode_in_log(inode, root->fs_info->generation) ||
-	    BTRFS_I(inode)->last_trans <=
-	    root->fs_info->last_trans_committed) {
-		BTRFS_I(inode)->last_trans = 0;
-
+	    (full_sync && BTRFS_I(inode)->last_trans <=
+	     root->fs_info->last_trans_committed)) {
 		/*
 		 * We'v had everything committed since the last time we were
 		 * modified so clear this flag in case it was set for whatever
@@ -2275,6 +2275,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	bool same_page;
 	bool no_holes = btrfs_fs_incompat(root->fs_info, NO_HOLES);
 	u64 ino_size;
+	bool truncated_page = false;
+	bool updated_inode = false;
 
 	ret = btrfs_wait_ordered_range(inode, offset, len);
 	if (ret)
@@ -2306,13 +2308,18 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	 * entire page.
 	 */
 	if (same_page && len < PAGE_CACHE_SIZE) {
-		if (offset < ino_size)
+		if (offset < ino_size) {
+			truncated_page = true;
 			ret = btrfs_truncate_page(inode, offset, len, 0);
+		} else {
+			ret = 0;
+		}
 		goto out_only_mutex;
 	}
 
 	/* zero back part of the first page */
 	if (offset < ino_size) {
+		truncated_page = true;
 		ret = btrfs_truncate_page(inode, offset, 0, 0);
 		if (ret) {
 			mutex_unlock(&inode->i_mutex);
@@ -2348,6 +2355,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 		if (!ret) {
 			/* zero the front end of the last page */
 			if (tail_start + tail_len < ino_size) {
+				truncated_page = true;
 				ret = btrfs_truncate_page(inode,
 						tail_start + tail_len, 0, 1);
 				if (ret)
@@ -2357,8 +2365,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	}
 
 	if (lockend < lockstart) {
-		mutex_unlock(&inode->i_mutex);
-		return 0;
+		ret = 0;
+		goto out_only_mutex;
 	}
 
 	while (1) {
@@ -2506,6 +2514,7 @@ out_trans:
 
 	trans->block_rsv = &root->fs_info->trans_block_rsv;
 	ret = btrfs_update_inode(trans, root, inode);
+	updated_inode = true;
 	btrfs_end_transaction(trans, root);
 	btrfs_btree_balance_dirty(root);
 out_free:
@@ -2515,6 +2524,22 @@ out:
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			     &cached_state, GFP_NOFS);
 out_only_mutex:
+	if (!updated_inode && truncated_page && !ret && !err) {
+		/*
+		 * If we only end up zeroing part of a page, we still need to
+		 * update the inode item, so that all the time fields are
+		 * updated as well as the necessary btrfs inode in memory fields
+		 * for detecting, at fsync time, if the inode isn't yet in the
+		 * log tree or it's there but not up to date.
+		 */
+		trans = btrfs_start_transaction(root, 1);
+		if (IS_ERR(trans)) {
+			err = PTR_ERR(trans);
+		} else {
+			err = btrfs_update_inode(trans, root, inode);
+			ret = btrfs_end_transaction(trans, root);
+		}
+	}
 	mutex_unlock(&inode->i_mutex);
 	if (ret && !err)
 		err = ret;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a85c23dfcddb..da828cf5e8f8 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7285,7 +7285,6 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	    ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
 	     em->block_start != EXTENT_MAP_HOLE)) {
 		int type;
-		int ret;
 		u64 block_start, orig_start, orig_block_len, ram_bytes;
 
 		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 534544e08f76..157cc54fc634 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -452,9 +452,7 @@ void btrfs_get_logged_extents(struct inode *inode,
 			continue;
 		if (entry_end(ordered) <= start)
 			break;
-		if (!list_empty(&ordered->log_list))
-			continue;
-		if (test_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
+		if (test_and_set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
 			continue;
 		list_add(&ordered->log_list, logged_list);
 		atomic_inc(&ordered->refs);
@@ -511,8 +509,7 @@ void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans,
 		wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE,
 						   &ordered->flags));
 
-		if (!test_and_set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
-			list_add_tail(&ordered->trans_list, &trans->ordered);
+		list_add_tail(&ordered->trans_list, &trans->ordered);
 		spin_lock_irq(&log->log_extents_lock[index]);
 	}
 	spin_unlock_irq(&log->log_extents_lock[index]);
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index fe5857223515..d6033f540cc7 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -230,6 +230,7 @@ struct pending_dir_move {
 	u64 parent_ino;
 	u64 ino;
 	u64 gen;
+	bool is_orphan;
 	struct list_head update_refs;
 };
 
@@ -2984,7 +2985,8 @@ static int add_pending_dir_move(struct send_ctx *sctx,
 				u64 ino_gen,
 				u64 parent_ino,
 				struct list_head *new_refs,
-				struct list_head *deleted_refs)
+				struct list_head *deleted_refs,
+				const bool is_orphan)
 {
 	struct rb_node **p = &sctx->pending_dir_moves.rb_node;
 	struct rb_node *parent = NULL;
@@ -2999,6 +3001,7 @@ static int add_pending_dir_move(struct send_ctx *sctx,
 	pm->parent_ino = parent_ino;
 	pm->ino = ino;
 	pm->gen = ino_gen;
+	pm->is_orphan = is_orphan;
 	INIT_LIST_HEAD(&pm->list);
 	INIT_LIST_HEAD(&pm->update_refs);
 	RB_CLEAR_NODE(&pm->node);
@@ -3131,16 +3134,20 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
 	rmdir_ino = dm->rmdir_ino;
 	free_waiting_dir_move(sctx, dm);
 
-	ret = get_first_ref(sctx->parent_root, pm->ino,
-			    &parent_ino, &parent_gen, name);
-	if (ret < 0)
-		goto out;
-
-	ret = get_cur_path(sctx, parent_ino, parent_gen,
-			   from_path);
-	if (ret < 0)
-		goto out;
-	ret = fs_path_add_path(from_path, name);
+	if (pm->is_orphan) {
+		ret = gen_unique_name(sctx, pm->ino,
+				      pm->gen, from_path);
+	} else {
+		ret = get_first_ref(sctx->parent_root, pm->ino,
+				    &parent_ino, &parent_gen, name);
+		if (ret < 0)
+			goto out;
+		ret = get_cur_path(sctx, parent_ino, parent_gen,
+				   from_path);
+		if (ret < 0)
+			goto out;
+		ret = fs_path_add_path(from_path, name);
+	}
 	if (ret < 0)
 		goto out;
 
@@ -3150,7 +3157,8 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
 		LIST_HEAD(deleted_refs);
 		ASSERT(ancestor > BTRFS_FIRST_FREE_OBJECTID);
 		ret = add_pending_dir_move(sctx, pm->ino, pm->gen, ancestor,
-					   &pm->update_refs, &deleted_refs);
+					   &pm->update_refs, &deleted_refs,
+					   pm->is_orphan);
 		if (ret < 0)
 			goto out;
 		if (rmdir_ino) {
@@ -3283,6 +3291,127 @@ out:
 	return ret;
 }
 
+/*
+ * We might need to delay a directory rename even when no ancestor directory
+ * (in the send root) with a higher inode number than ours (sctx->cur_ino) was
+ * renamed. This happens when we rename a directory to the old name (the name
+ * in the parent root) of some other unrelated directory that got its rename
+ * delayed due to some ancestor with higher number that got renamed.
+ *
+ * Example:
+ *
+ * Parent snapshot:
+ * .                                       (ino 256)
+ * |---- a/                                (ino 257)
+ * |     |---- file                        (ino 260)
+ * |
+ * |---- b/                                (ino 258)
+ * |---- c/                                (ino 259)
+ *
+ * Send snapshot:
+ * .                                       (ino 256)
+ * |---- a/                                (ino 258)
+ * |---- x/                                (ino 259)
+ *       |---- y/                          (ino 257)
+ *             |----- file                 (ino 260)
+ *
+ * Here we can not rename 258 from 'b' to 'a' without the rename of inode 257
+ * from 'a' to 'x/y' happening first, which in turn depends on the rename of
+ * inode 259 from 'c' to 'x'. So the order of rename commands the send stream
+ * must issue is:
+ *
+ * 1 - rename 259 from 'c' to 'x'
+ * 2 - rename 257 from 'a' to 'x/y'
+ * 3 - rename 258 from 'b' to 'a'
+ *
+ * Returns 1 if the rename of sctx->cur_ino needs to be delayed, 0 if it can
+ * be done right away and < 0 on error.
+ */
+static int wait_for_dest_dir_move(struct send_ctx *sctx,
+				  struct recorded_ref *parent_ref,
+				  const bool is_orphan)
+{
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	struct btrfs_key di_key;
+	struct btrfs_dir_item *di;
+	u64 left_gen;
+	u64 right_gen;
+	int ret = 0;
+
+	if (RB_EMPTY_ROOT(&sctx->waiting_dir_moves))
+		return 0;
+
+	path = alloc_path_for_send();
+	if (!path)
+		return -ENOMEM;
+
+	key.objectid = parent_ref->dir;
+	key.type = BTRFS_DIR_ITEM_KEY;
+	key.offset = btrfs_name_hash(parent_ref->name, parent_ref->name_len);
+
+	ret = btrfs_search_slot(NULL, sctx->parent_root, &key, path, 0, 0);
+	if (ret < 0) {
+		goto out;
+	} else if (ret > 0) {
+		ret = 0;
+		goto out;
+	}
+
+	di = btrfs_match_dir_item_name(sctx->parent_root, path,
+				       parent_ref->name, parent_ref->name_len);
+	if (!di) {
+		ret = 0;
+		goto out;
+	}
+	/*
+	 * di_key.objectid has the number of the inode that has a dentry in the
+	 * parent directory with the same name that sctx->cur_ino is being
+	 * renamed to. We need to check if that inode is in the send root as
+	 * well and if it is currently marked as an inode with a pending rename,
+	 * if it is, we need to delay the rename of sctx->cur_ino as well, so
+	 * that it happens after that other inode is renamed.
+	 */
+	btrfs_dir_item_key_to_cpu(path->nodes[0], di, &di_key);
+	if (di_key.type != BTRFS_INODE_ITEM_KEY) {
+		ret = 0;
+		goto out;
+	}
+
+	ret = get_inode_info(sctx->parent_root, di_key.objectid, NULL,
+			     &left_gen, NULL, NULL, NULL, NULL);
+	if (ret < 0)
+		goto out;
+	ret = get_inode_info(sctx->send_root, di_key.objectid, NULL,
+			     &right_gen, NULL, NULL, NULL, NULL);
+	if (ret < 0) {
+		if (ret == -ENOENT)
+			ret = 0;
+		goto out;
+	}
+
+	/* Different inode, no need to delay the rename of sctx->cur_ino */
+	if (right_gen != left_gen) {
+		ret = 0;
+		goto out;
+	}
+
+	if (is_waiting_for_move(sctx, di_key.objectid)) {
+		ret = add_pending_dir_move(sctx,
+					   sctx->cur_ino,
+					   sctx->cur_inode_gen,
+					   di_key.objectid,
+					   &sctx->new_refs,
+					   &sctx->deleted_refs,
+					   is_orphan);
+		if (!ret)
+			ret = 1;
+	}
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
 static int wait_for_parent_move(struct send_ctx *sctx,
 				struct recorded_ref *parent_ref)
 {
@@ -3349,7 +3478,8 @@ out:
 					   sctx->cur_inode_gen,
 					   ino,
 					   &sctx->new_refs,
-					   &sctx->deleted_refs);
+					   &sctx->deleted_refs,
+					   false);
 		if (!ret)
 			ret = 1;
 	}
@@ -3372,6 +3502,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 	int did_overwrite = 0;
 	int is_orphan = 0;
 	u64 last_dir_ino_rm = 0;
+	bool can_rename = true;
 
 verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino);
 
@@ -3490,12 +3621,22 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino);
 			}
 		}
 
+		if (S_ISDIR(sctx->cur_inode_mode) && sctx->parent_root) {
+			ret = wait_for_dest_dir_move(sctx, cur, is_orphan);
+			if (ret < 0)
+				goto out;
+			if (ret == 1) {
+				can_rename = false;
+				*pending_move = 1;
+			}
+		}
+
 		/*
 		 * link/move the ref to the new place. If we have an orphan
 		 * inode, move it and update valid_path. If not, link or move
 		 * it depending on the inode mode.
 		 */
-		if (is_orphan) {
+		if (is_orphan && can_rename) {
 			ret = send_rename(sctx, valid_path, cur->full_path);
 			if (ret < 0)
 				goto out;
@@ -3503,7 +3644,7 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino);
 			ret = fs_path_copy(valid_path, cur->full_path);
 			if (ret < 0)
 				goto out;
-		} else {
+		} else if (can_rename) {
 			if (S_ISDIR(sctx->cur_inode_mode)) {
 				/*
 				 * Dirs can't be linked, so move it. For moved
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 7e80f32550a6..88e51aded6bd 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1052,9 +1052,6 @@ static int update_cowonly_root(struct btrfs_trans_handle *trans,
 		ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
 		if (ret)
 			return ret;
-		ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
-		if (ret)
-			return ret;
 	}
 
 	return 0;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 9a37f8b39bae..c5b8ba37f88e 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1012,7 +1012,7 @@ again:
 		base = btrfs_item_ptr_offset(leaf, path->slots[0]);
 
 		while (cur_offset < item_size) {
-			extref = (struct btrfs_inode_extref *)base + cur_offset;
+			extref = (struct btrfs_inode_extref *)(base + cur_offset);
 
 			victim_name_len = btrfs_inode_extref_name_len(leaf, extref);
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index cd4d1315aaa9..8222f6f74147 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4903,10 +4903,17 @@ static void sort_parity_stripes(struct btrfs_bio *bbio, int num_stripes)
 static struct btrfs_bio *alloc_btrfs_bio(int total_stripes, int real_stripes)
 {
 	struct btrfs_bio *bbio = kzalloc(
+		 /* the size of the btrfs_bio */
 		sizeof(struct btrfs_bio) +
+		/* plus the variable array for the stripes */
 		sizeof(struct btrfs_bio_stripe) * (total_stripes) +
+		/* plus the variable array for the tgt dev */
 		sizeof(int) * (real_stripes) +
-		sizeof(u64) * (real_stripes),
+		/*
+		 * plus the raid_map, which includes both the tgt dev
+		 * and the stripes
+		 */
+		sizeof(u64) * (total_stripes),
 		GFP_NOFS);
 	if (!bbio)
 		return NULL;
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 47b19465f0dc..883b93623bc5 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -111,6 +111,8 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 					name, name_len, -1);
 		if (!di && (flags & XATTR_REPLACE))
 			ret = -ENODATA;
+		else if (IS_ERR(di))
+			ret = PTR_ERR(di);
 		else if (di)
 			ret = btrfs_delete_one_dir_name(trans, root, path, di);
 		goto out;
@@ -127,10 +129,12 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 		ASSERT(mutex_is_locked(&inode->i_mutex));
 		di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode),
 					name, name_len, 0);
-		if (!di) {
+		if (!di)
 			ret = -ENODATA;
+		else if (IS_ERR(di))
+			ret = PTR_ERR(di);
+		if (ret)
 			goto out;
-		}
 		btrfs_release_path(path);
 		di = NULL;
 	}
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 90d1882b306f..5ba029e627cc 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -124,7 +124,7 @@ ecryptfs_get_key_payload_data(struct key *key)
 }
 
 #define ECRYPTFS_MAX_KEYSET_SIZE 1024
-#define ECRYPTFS_MAX_CIPHER_NAME_SIZE 32
+#define ECRYPTFS_MAX_CIPHER_NAME_SIZE 31
 #define ECRYPTFS_MAX_NUM_ENC_KEYS 64
 #define ECRYPTFS_MAX_IV_BYTES 16	/* 128 bits */
 #define ECRYPTFS_SALT_BYTES 2
@@ -237,7 +237,7 @@ struct ecryptfs_crypt_stat {
 	struct crypto_ablkcipher *tfm;
 	struct crypto_hash *hash_tfm; /* Crypto context for generating
 				       * the initialization vectors */
-	unsigned char cipher[ECRYPTFS_MAX_CIPHER_NAME_SIZE];
+	unsigned char cipher[ECRYPTFS_MAX_CIPHER_NAME_SIZE + 1];
 	unsigned char key[ECRYPTFS_MAX_KEY_BYTES];
 	unsigned char root_iv[ECRYPTFS_MAX_IV_BYTES];
 	struct list_head keysig_list;
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index b07731e68c0b..fd39bad6f1bd 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -303,9 +303,22 @@ ecryptfs_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	struct file *lower_file = ecryptfs_file_to_lower(file);
 	long rc = -ENOTTY;
 
-	if (lower_file->f_op->unlocked_ioctl)
+	if (!lower_file->f_op->unlocked_ioctl)
+		return rc;
+
+	switch (cmd) {
+	case FITRIM:
+	case FS_IOC_GETFLAGS:
+	case FS_IOC_SETFLAGS:
+	case FS_IOC_GETVERSION:
+	case FS_IOC_SETVERSION:
 		rc = lower_file->f_op->unlocked_ioctl(lower_file, cmd, arg);
-	return rc;
+		fsstack_copy_attr_all(file_inode(file), file_inode(lower_file));
+
+		return rc;
+	default:
+		return rc;
+	}
 }
 
 #ifdef CONFIG_COMPAT
@@ -315,9 +328,22 @@ ecryptfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	struct file *lower_file = ecryptfs_file_to_lower(file);
 	long rc = -ENOIOCTLCMD;
 
-	if (lower_file->f_op->compat_ioctl)
+	if (!lower_file->f_op->compat_ioctl)
+		return rc;
+
+	switch (cmd) {
+	case FITRIM:
+	case FS_IOC32_GETFLAGS:
+	case FS_IOC32_SETFLAGS:
+	case FS_IOC32_GETVERSION:
+	case FS_IOC32_SETVERSION:
 		rc = lower_file->f_op->compat_ioctl(lower_file, cmd, arg);
-	return rc;
+		fsstack_copy_attr_all(file_inode(file), file_inode(lower_file));
+
+		return rc;
+	default:
+		return rc;
+	}
 }
 #endif
 
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 917bd5c9776a..6bd67e2011f0 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -891,7 +891,7 @@ struct ecryptfs_parse_tag_70_packet_silly_stack {
 	struct blkcipher_desc desc;
 	char fnek_sig_hex[ECRYPTFS_SIG_SIZE_HEX + 1];
 	char iv[ECRYPTFS_MAX_IV_BYTES];
-	char cipher_string[ECRYPTFS_MAX_CIPHER_NAME_SIZE];
+	char cipher_string[ECRYPTFS_MAX_CIPHER_NAME_SIZE + 1];
 };
 
 /**
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 1895d60f4122..c095d3264259 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -407,7 +407,7 @@ static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options,
 	if (!cipher_name_set) {
 		int cipher_name_len = strlen(ECRYPTFS_DEFAULT_CIPHER);
 
-		BUG_ON(cipher_name_len >= ECRYPTFS_MAX_CIPHER_NAME_SIZE);
+		BUG_ON(cipher_name_len > ECRYPTFS_MAX_CIPHER_NAME_SIZE);
 		strcpy(mount_crypt_stat->global_default_cipher_name,
 		       ECRYPTFS_DEFAULT_CIPHER);
 	}
diff --git a/fs/locks.c b/fs/locks.c
index 365c82e1b3a9..528fedfda15e 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1665,7 +1665,8 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	}
 
 	if (my_fl != NULL) {
-		error = lease->fl_lmops->lm_change(my_fl, arg, &dispose);
+		lease = my_fl;
+		error = lease->fl_lmops->lm_change(lease, arg, &dispose);
 		if (error)
 			goto out;
 		goto out_setup;
@@ -1727,7 +1728,7 @@ static int generic_delete_lease(struct file *filp, void *owner)
 			break;
 		}
 	}
-	trace_generic_delete_lease(inode, fl);
+	trace_generic_delete_lease(inode, victim);
 	if (victim)
 		error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose);
 	spin_unlock(&ctx->flc_lock);
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index f9f4845db989..19874151e95c 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -433,7 +433,7 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
 
 static bool nfs_client_init_is_complete(const struct nfs_client *clp)
 {
-	return clp->cl_cons_state != NFS_CS_INITING;
+	return clp->cl_cons_state <= NFS_CS_READY;
 }
 
 int nfs_wait_client_init_complete(const struct nfs_client *clp)
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index a1f0685b42ff..a6ad68865880 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -181,8 +181,8 @@ void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred,
 			clear_bit(NFS_DELEGATION_NEED_RECLAIM,
 				  &delegation->flags);
 			spin_unlock(&delegation->lock);
-			put_rpccred(oldcred);
 			rcu_read_unlock();
+			put_rpccred(oldcred);
 			trace_nfs4_reclaim_delegation(inode, res->delegation_type);
 		} else {
 			/* We appear to have raced with a delegation return. */
@@ -370,7 +370,10 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
 			delegation = NULL;
 			goto out;
 		}
-		freeme = nfs_detach_delegation_locked(nfsi, 
+		if (test_and_set_bit(NFS_DELEGATION_RETURNING,
+					&old_delegation->flags))
+			goto out;
+		freeme = nfs_detach_delegation_locked(nfsi,
 				old_delegation, clp);
 		if (freeme == NULL)
 			goto out;
@@ -433,6 +436,8 @@ static bool nfs_delegation_need_return(struct nfs_delegation *delegation)
 {
 	bool ret = false;
 
+	if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags))
+		goto out;
 	if (test_and_clear_bit(NFS_DELEGATION_RETURN, &delegation->flags))
 		ret = true;
 	if (test_and_clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags) && !ret) {
@@ -444,6 +449,7 @@ static bool nfs_delegation_need_return(struct nfs_delegation *delegation)
 			ret = true;
 		spin_unlock(&delegation->lock);
 	}
+out:
 	return ret;
 }
 
@@ -471,14 +477,20 @@ restart:
 								super_list) {
 			if (!nfs_delegation_need_return(delegation))
 				continue;
-			inode = nfs_delegation_grab_inode(delegation);
-			if (inode == NULL)
+			if (!nfs_sb_active(server->super))
 				continue;
+			inode = nfs_delegation_grab_inode(delegation);
+			if (inode == NULL) {
+				rcu_read_unlock();
+				nfs_sb_deactive(server->super);
+				goto restart;
+			}
 			delegation = nfs_start_delegation_return_locked(NFS_I(inode));
 			rcu_read_unlock();
 
 			err = nfs_end_delegation_return(inode, delegation, 0);
 			iput(inode);
+			nfs_sb_deactive(server->super);
 			if (!err)
 				goto restart;
 			set_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state);
@@ -809,19 +821,30 @@ restart:
 	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
 		list_for_each_entry_rcu(delegation, &server->delegations,
 								super_list) {
+			if (test_bit(NFS_DELEGATION_RETURNING,
+						&delegation->flags))
+				continue;
 			if (test_bit(NFS_DELEGATION_NEED_RECLAIM,
 						&delegation->flags) == 0)
 				continue;
-			inode = nfs_delegation_grab_inode(delegation);
-			if (inode == NULL)
+			if (!nfs_sb_active(server->super))
 				continue;
-			delegation = nfs_detach_delegation(NFS_I(inode),
-					delegation, server);
+			inode = nfs_delegation_grab_inode(delegation);
+			if (inode == NULL) {
+				rcu_read_unlock();
+				nfs_sb_deactive(server->super);
+				goto restart;
+			}
+			delegation = nfs_start_delegation_return_locked(NFS_I(inode));
 			rcu_read_unlock();
-
-			if (delegation != NULL)
-				nfs_free_delegation(delegation);
+			if (delegation != NULL) {
+				delegation = nfs_detach_delegation(NFS_I(inode),
+					delegation, server);
+				if (delegation != NULL)
+					nfs_free_delegation(delegation);
+			}
 			iput(inode);
+			nfs_sb_deactive(server->super);
 			goto restart;
 		}
 	}
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 9b0c55cb2a2e..c19e16f0b2d0 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -408,14 +408,22 @@ static int xdr_decode(nfs_readdir_descriptor_t *desc,
 	return 0;
 }
 
+/* Match file and dirent using either filehandle or fileid
+ * Note: caller is responsible for checking the fsid
+ */
 static
 int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry)
 {
+	struct nfs_inode *nfsi;
+
 	if (dentry->d_inode == NULL)
 		goto different;
-	if (nfs_compare_fh(entry->fh, NFS_FH(dentry->d_inode)) != 0)
-		goto different;
-	return 1;
+
+	nfsi = NFS_I(dentry->d_inode);
+	if (entry->fattr->fileid == nfsi->fileid)
+		return 1;
+	if (nfs_compare_fh(entry->fh, &nfsi->fh) == 0)
+		return 1;
 different:
 	return 0;
 }
@@ -469,6 +477,10 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 	struct inode *inode;
 	int status;
 
+	if (!(entry->fattr->valid & NFS_ATTR_FATTR_FILEID))
+		return;
+	if (!(entry->fattr->valid & NFS_ATTR_FATTR_FSID))
+		return;
 	if (filename.name[0] == '.') {
 		if (filename.len == 1)
 			return;
@@ -479,6 +491,10 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 
 	dentry = d_lookup(parent, &filename);
 	if (dentry != NULL) {
+		/* Is there a mountpoint here? If so, just exit */
+		if (!nfs_fsid_equal(&NFS_SB(dentry->d_sb)->fsid,
+					&entry->fattr->fsid))
+			goto out;
 		if (nfs_same_file(dentry, entry)) {
 			nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 			status = nfs_refresh_inode(dentry->d_inode, entry->fattr);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 94712fc781fa..e679d24c39d3 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -178,7 +178,7 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
 		iocb->ki_filp,
 		iov_iter_count(to), (unsigned long) iocb->ki_pos);
 
-	result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping);
+	result = nfs_revalidate_mapping_protected(inode, iocb->ki_filp->f_mapping);
 	if (!result) {
 		result = generic_file_read_iter(iocb, to);
 		if (result > 0)
@@ -199,7 +199,7 @@ nfs_file_splice_read(struct file *filp, loff_t *ppos,
 	dprintk("NFS: splice_read(%pD2, %lu@%Lu)\n",
 		filp, (unsigned long) count, (unsigned long long) *ppos);
 
-	res = nfs_revalidate_mapping(inode, filp->f_mapping);
+	res = nfs_revalidate_mapping_protected(inode, filp->f_mapping);
 	if (!res) {
 		res = generic_file_splice_read(filp, ppos, pipe, count, flags);
 		if (res > 0)
@@ -372,6 +372,10 @@ start:
 				 nfs_wait_bit_killable, TASK_KILLABLE);
 	if (ret)
 		return ret;
+	/*
+	 * Wait for O_DIRECT to complete
+	 */
+	nfs_inode_dio_wait(mapping->host);
 
 	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
@@ -619,6 +623,9 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	/* make sure the cache has finished storing the page */
 	nfs_fscache_wait_on_page_write(NFS_I(inode), page);
 
+	wait_on_bit_action(&NFS_I(inode)->flags, NFS_INO_INVALIDATING,
+			nfs_wait_bit_killable, TASK_KILLABLE);
+
 	lock_page(page);
 	mapping = page_file_mapping(page);
 	if (mapping != inode->i_mapping)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 83107be3dd01..d42dff6d5e98 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -556,6 +556,7 @@ EXPORT_SYMBOL_GPL(nfs_setattr);
  * This is a copy of the common vmtruncate, but with the locking
  * corrected to take into account the fact that NFS requires
  * inode->i_size to be updated under the inode->i_lock.
+ * Note: must be called with inode->i_lock held!
  */
 static int nfs_vmtruncate(struct inode * inode, loff_t offset)
 {
@@ -565,14 +566,14 @@ static int nfs_vmtruncate(struct inode * inode, loff_t offset)
 	if (err)
 		goto out;
 
-	spin_lock(&inode->i_lock);
 	i_size_write(inode, offset);
 	/* Optimisation */
 	if (offset == 0)
 		NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_DATA;
-	spin_unlock(&inode->i_lock);
 
+	spin_unlock(&inode->i_lock);
 	truncate_pagecache(inode, offset);
+	spin_lock(&inode->i_lock);
 out:
 	return err;
 }
@@ -585,10 +586,15 @@ out:
  * Note: we do this in the *proc.c in order to ensure that
  *       it works for things like exclusive creates too.
  */
-void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
+void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr,
+		struct nfs_fattr *fattr)
 {
+	/* Barrier: bump the attribute generation count. */
+	nfs_fattr_set_barrier(fattr);
+
+	spin_lock(&inode->i_lock);
+	NFS_I(inode)->attr_gencount = fattr->gencount;
 	if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) {
-		spin_lock(&inode->i_lock);
 		if ((attr->ia_valid & ATTR_MODE) != 0) {
 			int mode = attr->ia_mode & S_IALLUGO;
 			mode |= inode->i_mode & ~S_IALLUGO;
@@ -600,12 +606,13 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
 			inode->i_gid = attr->ia_gid;
 		nfs_set_cache_invalid(inode, NFS_INO_INVALID_ACCESS
 				| NFS_INO_INVALID_ACL);
-		spin_unlock(&inode->i_lock);
 	}
 	if ((attr->ia_valid & ATTR_SIZE) != 0) {
 		nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC);
 		nfs_vmtruncate(inode, attr->ia_size);
 	}
+	nfs_update_inode(inode, fattr);
+	spin_unlock(&inode->i_lock);
 }
 EXPORT_SYMBOL_GPL(nfs_setattr_update_inode);
 
@@ -1028,6 +1035,7 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map
 
 	if (mapping->nrpages != 0) {
 		if (S_ISREG(inode->i_mode)) {
+			unmap_mapping_range(mapping, 0, 0, 0);
 			ret = nfs_sync_mapping(mapping);
 			if (ret < 0)
 				return ret;
@@ -1060,11 +1068,14 @@ static bool nfs_mapping_need_revalidate_inode(struct inode *inode)
 }
 
 /**
- * nfs_revalidate_mapping - Revalidate the pagecache
+ * __nfs_revalidate_mapping - Revalidate the pagecache
  * @inode - pointer to host inode
  * @mapping - pointer to mapping
+ * @may_lock - take inode->i_mutex?
  */
-int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
+static int __nfs_revalidate_mapping(struct inode *inode,
+		struct address_space *mapping,
+		bool may_lock)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 	unsigned long *bitlock = &nfsi->flags;
@@ -1113,7 +1124,12 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
 	nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
 	spin_unlock(&inode->i_lock);
 	trace_nfs_invalidate_mapping_enter(inode);
-	ret = nfs_invalidate_mapping(inode, mapping);
+	if (may_lock) {
+		mutex_lock(&inode->i_mutex);
+		ret = nfs_invalidate_mapping(inode, mapping);
+		mutex_unlock(&inode->i_mutex);
+	} else
+		ret = nfs_invalidate_mapping(inode, mapping);
 	trace_nfs_invalidate_mapping_exit(inode, ret);
 
 	clear_bit_unlock(NFS_INO_INVALIDATING, bitlock);
@@ -1123,6 +1139,29 @@ out:
 	return ret;
 }
 
+/**
+ * nfs_revalidate_mapping - Revalidate the pagecache
+ * @inode - pointer to host inode
+ * @mapping - pointer to mapping
+ */
+int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
+{
+	return __nfs_revalidate_mapping(inode, mapping, false);
+}
+
+/**
+ * nfs_revalidate_mapping_protected - Revalidate the pagecache
+ * @inode - pointer to host inode
+ * @mapping - pointer to mapping
+ *
+ * Differs from nfs_revalidate_mapping() in that it grabs the inode->i_mutex
+ * while invalidating the mapping.
+ */
+int nfs_revalidate_mapping_protected(struct inode *inode, struct address_space *mapping)
+{
+	return __nfs_revalidate_mapping(inode, mapping, true);
+}
+
 static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
@@ -1231,13 +1270,6 @@ static int nfs_ctime_need_update(const struct inode *inode, const struct nfs_fat
 	return timespec_compare(&fattr->ctime, &inode->i_ctime) > 0;
 }
 
-static int nfs_size_need_update(const struct inode *inode, const struct nfs_fattr *fattr)
-{
-	if (!(fattr->valid & NFS_ATTR_FATTR_SIZE))
-		return 0;
-	return nfs_size_to_loff_t(fattr->size) > i_size_read(inode);
-}
-
 static atomic_long_t nfs_attr_generation_counter;
 
 static unsigned long nfs_read_attr_generation_counter(void)
@@ -1249,6 +1281,7 @@ unsigned long nfs_inc_attr_generation_counter(void)
 {
 	return atomic_long_inc_return(&nfs_attr_generation_counter);
 }
+EXPORT_SYMBOL_GPL(nfs_inc_attr_generation_counter);
 
 void nfs_fattr_init(struct nfs_fattr *fattr)
 {
@@ -1260,6 +1293,22 @@ void nfs_fattr_init(struct nfs_fattr *fattr)
 }
 EXPORT_SYMBOL_GPL(nfs_fattr_init);
 
+/**
+ * nfs_fattr_set_barrier
+ * @fattr: attributes
+ *
+ * Used to set a barrier after an attribute was updated. This
+ * barrier ensures that older attributes from RPC calls that may
+ * have raced with our update cannot clobber these new values.
+ * Note that you are still responsible for ensuring that other
+ * operations which change the attribute on the server do not
+ * collide.
+ */
+void nfs_fattr_set_barrier(struct nfs_fattr *fattr)
+{
+	fattr->gencount = nfs_inc_attr_generation_counter();
+}
+
 struct nfs_fattr *nfs_alloc_fattr(void)
 {
 	struct nfs_fattr *fattr;
@@ -1370,7 +1419,6 @@ static int nfs_inode_attrs_need_update(const struct inode *inode, const struct n
 
 	return ((long)fattr->gencount - (long)nfsi->attr_gencount) > 0 ||
 		nfs_ctime_need_update(inode, fattr) ||
-		nfs_size_need_update(inode, fattr) ||
 		((long)nfsi->attr_gencount - (long)nfs_read_attr_generation_counter() > 0);
 }
 
@@ -1460,6 +1508,7 @@ int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	int status;
 
 	spin_lock(&inode->i_lock);
+	nfs_fattr_set_barrier(fattr);
 	status = nfs_post_op_update_inode_locked(inode, fattr);
 	spin_unlock(&inode->i_lock);
 
@@ -1468,7 +1517,7 @@ int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 EXPORT_SYMBOL_GPL(nfs_post_op_update_inode);
 
 /**
- * nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache
+ * nfs_post_op_update_inode_force_wcc_locked - update the inode attribute cache
  * @inode - pointer to inode
  * @fattr - updated attributes
  *
@@ -1478,11 +1527,10 @@ EXPORT_SYMBOL_GPL(nfs_post_op_update_inode);
  *
  * This function is mainly designed to be used by the ->write_done() functions.
  */
-int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr)
+int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr)
 {
 	int status;
 
-	spin_lock(&inode->i_lock);
 	/* Don't do a WCC update if these attributes are already stale */
 	if ((fattr->valid & NFS_ATTR_FATTR) == 0 ||
 			!nfs_inode_attrs_need_update(inode, fattr)) {
@@ -1514,6 +1562,27 @@ int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fa
 	}
 out_noforce:
 	status = nfs_post_op_update_inode_locked(inode, fattr);
+	return status;
+}
+
+/**
+ * nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache
+ * @inode - pointer to inode
+ * @fattr - updated attributes
+ *
+ * After an operation that has changed the inode metadata, mark the
+ * attribute cache as being invalid, then try to update it. Fake up
+ * weak cache consistency data, if none exist.
+ *
+ * This function is mainly designed to be used by the ->write_done() functions.
+ */
+int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr)
+{
+	int status;
+
+	spin_lock(&inode->i_lock);
+	nfs_fattr_set_barrier(fattr);
+	status = nfs_post_op_update_inode_force_wcc_locked(inode, fattr);
 	spin_unlock(&inode->i_lock);
 	return status;
 }
@@ -1715,6 +1784,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
 		nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
 		nfsi->attrtimeo_timestamp = now;
+		/* Set barrier to be more recent than all outstanding updates */
 		nfsi->attr_gencount = nfs_inc_attr_generation_counter();
 	} else {
 		if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) {
@@ -1722,6 +1792,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 				nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode);
 			nfsi->attrtimeo_timestamp = now;
 		}
+		/* Set the barrier to be more recent than this fattr */
+		if ((long)fattr->gencount - (long)nfsi->attr_gencount > 0)
+			nfsi->attr_gencount = fattr->gencount;
 	}
 	invalid &= ~NFS_INO_INVALID_ATTR;
 	/* Don't invalidate the data if we were to blame */
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index b802fb3a2d99..9e6475bc5ba2 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -459,6 +459,7 @@ void nfs_mark_request_commit(struct nfs_page *req,
 			     struct nfs_commit_info *cinfo,
 			     u32 ds_commit_idx);
 int nfs_write_need_commit(struct nfs_pgio_header *);
+void nfs_writeback_update_inode(struct nfs_pgio_header *hdr);
 int nfs_generic_commit_list(struct inode *inode, struct list_head *head,
 			    int how, struct nfs_commit_info *cinfo);
 void nfs_retry_commit(struct list_head *page_list,
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 78e557c3ab87..1f11d2533ee4 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -138,7 +138,7 @@ nfs3_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 	nfs_fattr_init(fattr);
 	status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
 	if (status == 0)
-		nfs_setattr_update_inode(inode, sattr);
+		nfs_setattr_update_inode(inode, sattr, fattr);
 	dprintk("NFS reply setattr: %d\n", status);
 	return status;
 }
@@ -834,7 +834,7 @@ static int nfs3_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 	if (nfs3_async_handle_jukebox(task, inode))
 		return -EAGAIN;
 	if (task->tk_status >= 0)
-		nfs_post_op_update_inode_force_wcc(inode, hdr->res.fattr);
+		nfs_writeback_update_inode(hdr);
 	return 0;
 }
 
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 2a932fdc57cb..53852a4bd88b 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -1987,6 +1987,11 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 		if (entry->fattr->valid & NFS_ATTR_FATTR_V3)
 			entry->d_type = nfs_umode_to_dtype(entry->fattr->mode);
 
+		if (entry->fattr->fileid != entry->ino) {
+			entry->fattr->mounted_on_fileid = entry->ino;
+			entry->fattr->valid |= NFS_ATTR_FATTR_MOUNTED_ON_FILEID;
+		}
+
 		/* In fact, a post_op_fh3: */
 		p = xdr_inline_decode(xdr, 4);
 		if (unlikely(p == NULL))
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 8646af9b11d2..86d6214ea022 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -621,6 +621,9 @@ int nfs41_walk_client_list(struct nfs_client *new,
 	spin_lock(&nn->nfs_client_lock);
 	list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
 
+		if (pos == new)
+			goto found;
+
 		if (pos->rpc_ops != new->rpc_ops)
 			continue;
 
@@ -639,10 +642,6 @@ int nfs41_walk_client_list(struct nfs_client *new,
 			prev = pos;
 
 			status = nfs_wait_client_init_complete(pos);
-			if (pos->cl_cons_state == NFS_CS_SESSION_INITING) {
-				nfs4_schedule_lease_recovery(pos);
-				status = nfs4_wait_clnt_recover(pos);
-			}
 			spin_lock(&nn->nfs_client_lock);
 			if (status < 0)
 				break;
@@ -668,7 +667,7 @@ int nfs41_walk_client_list(struct nfs_client *new,
 		 */
 		if (!nfs4_match_client_owner_id(pos, new))
 			continue;
-
+found:
 		atomic_inc(&pos->cl_count);
 		*result = pos;
 		status = 0;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 88180ac5ea0e..627f37c44456 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -901,6 +901,7 @@ static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo)
 	if (!cinfo->atomic || cinfo->before != dir->i_version)
 		nfs_force_lookup_revalidate(dir);
 	dir->i_version = cinfo->after;
+	nfsi->attr_gencount = nfs_inc_attr_generation_counter();
 	nfs_fscache_invalidate(dir);
 	spin_unlock(&dir->i_lock);
 }
@@ -1552,6 +1553,9 @@ static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, fmode_t fmod
 
 	opendata->o_arg.open_flags = 0;
 	opendata->o_arg.fmode = fmode;
+	opendata->o_arg.share_access = nfs4_map_atomic_open_share(
+			NFS_SB(opendata->dentry->d_sb),
+			fmode, 0);
 	memset(&opendata->o_res, 0, sizeof(opendata->o_res));
 	memset(&opendata->c_res, 0, sizeof(opendata->c_res));
 	nfs4_init_opendata_res(opendata);
@@ -2413,8 +2417,8 @@ static int _nfs4_do_open(struct inode *dir,
 				opendata->o_res.f_attr, sattr,
 				state, label, olabel);
 		if (status == 0) {
-			nfs_setattr_update_inode(state->inode, sattr);
-			nfs_post_op_update_inode(state->inode, opendata->o_res.f_attr);
+			nfs_setattr_update_inode(state->inode, sattr,
+					opendata->o_res.f_attr);
 			nfs_setsecurity(state->inode, opendata->o_res.f_attr, olabel);
 		}
 	}
@@ -2651,7 +2655,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 		case -NFS4ERR_BAD_STATEID:
 		case -NFS4ERR_EXPIRED:
 			if (!nfs4_stateid_match(&calldata->arg.stateid,
-						&state->stateid)) {
+						&state->open_stateid)) {
 				rpc_restart_call_prepare(task);
 				goto out_release;
 			}
@@ -2687,7 +2691,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 	is_rdwr = test_bit(NFS_O_RDWR_STATE, &state->flags);
 	is_rdonly = test_bit(NFS_O_RDONLY_STATE, &state->flags);
 	is_wronly = test_bit(NFS_O_WRONLY_STATE, &state->flags);
-	nfs4_stateid_copy(&calldata->arg.stateid, &state->stateid);
+	nfs4_stateid_copy(&calldata->arg.stateid, &state->open_stateid);
 	/* Calculate the change in open mode */
 	calldata->arg.fmode = 0;
 	if (state->n_rdwr == 0) {
@@ -3288,7 +3292,7 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 
 	status = nfs4_do_setattr(inode, cred, fattr, sattr, state, NULL, label);
 	if (status == 0) {
-		nfs_setattr_update_inode(inode, sattr);
+		nfs_setattr_update_inode(inode, sattr, fattr);
 		nfs_setsecurity(inode, fattr, label);
 	}
 	nfs4_label_free(label);
@@ -4234,7 +4238,7 @@ static int nfs4_write_done_cb(struct rpc_task *task,
 	}
 	if (task->tk_status >= 0) {
 		renew_lease(NFS_SERVER(inode), hdr->timestamp);
-		nfs_post_op_update_inode_force_wcc(inode, &hdr->fattr);
+		nfs_writeback_update_inode(hdr);
 	}
 	return 0;
 }
@@ -6893,9 +6897,13 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
 
 	if (status == 0) {
 		clp->cl_clientid = res.clientid;
-		clp->cl_exchange_flags = (res.flags & ~EXCHGID4_FLAG_CONFIRMED_R);
-		if (!(res.flags & EXCHGID4_FLAG_CONFIRMED_R))
+		clp->cl_exchange_flags = res.flags;
+		/* Client ID is not confirmed */
+		if (!(res.flags & EXCHGID4_FLAG_CONFIRMED_R)) {
+			clear_bit(NFS4_SESSION_ESTABLISHED,
+					&clp->cl_session->session_state);
 			clp->cl_seqid = res.seqid;
+		}
 
 		kfree(clp->cl_serverowner);
 		clp->cl_serverowner = res.server_owner;
@@ -7227,6 +7235,9 @@ static void nfs4_update_session(struct nfs4_session *session,
 		struct nfs41_create_session_res *res)
 {
 	nfs4_copy_sessionid(&session->sess_id, &res->sessionid);
+	/* Mark client id and session as being confirmed */
+	session->clp->cl_exchange_flags |= EXCHGID4_FLAG_CONFIRMED_R;
+	set_bit(NFS4_SESSION_ESTABLISHED, &session->session_state);
 	session->flags = res->flags;
 	memcpy(&session->fc_attrs, &res->fc_attrs, sizeof(session->fc_attrs));
 	if (res->flags & SESSION4_BACK_CHAN)
@@ -7322,8 +7333,8 @@ int nfs4_proc_destroy_session(struct nfs4_session *session,
 	dprintk("--> nfs4_proc_destroy_session\n");
 
 	/* session is still being setup */
-	if (session->clp->cl_cons_state != NFS_CS_READY)
-		return status;
+	if (!test_and_clear_bit(NFS4_SESSION_ESTABLISHED, &session->session_state))
+		return 0;
 
 	status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
 	trace_nfs4_destroy_session(session->clp, status);
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index fc46c7455898..e3ea2c5324d6 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -70,6 +70,7 @@ struct nfs4_session {
 
 enum nfs4_session_state {
 	NFS4_SESSION_INITING,
+	NFS4_SESSION_ESTABLISHED,
 };
 
 extern int nfs4_setup_slot_table(struct nfs4_slot_table *tbl,
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 5ad908e9ce9c..f95e3b58bbc3 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -346,9 +346,23 @@ int nfs41_discover_server_trunking(struct nfs_client *clp,
 	status = nfs4_proc_exchange_id(clp, cred);
 	if (status != NFS4_OK)
 		return status;
-	set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
 
-	return nfs41_walk_client_list(clp, result, cred);
+	status = nfs41_walk_client_list(clp, result, cred);
+	if (status < 0)
+		return status;
+	if (clp != *result)
+		return 0;
+
+	/* Purge state if the client id was established in a prior instance */
+	if (clp->cl_exchange_flags & EXCHGID4_FLAG_CONFIRMED_R)
+		set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state);
+	else
+		set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+	nfs4_schedule_state_manager(clp);
+	status = nfs_wait_client_init_complete(clp);
+	if (status < 0)
+		nfs_put_client(clp);
+	return status;
 }
 
 #endif /* CONFIG_NFS_V4_1 */
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index b09cc23d6f43..c63189acd052 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -139,7 +139,7 @@ nfs_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 	nfs_fattr_init(fattr);
 	status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
 	if (status == 0)
-		nfs_setattr_update_inode(inode, sattr);
+		nfs_setattr_update_inode(inode, sattr, fattr);
 	dprintk("NFS reply setattr: %d\n", status);
 	return status;
 }
@@ -609,10 +609,8 @@ static int nfs_proc_pgio_rpc_prepare(struct rpc_task *task,
 
 static int nfs_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 {
-	struct inode *inode = hdr->inode;
-
 	if (task->tk_status >= 0)
-		nfs_post_op_update_inode_force_wcc(inode, hdr->res.fattr);
+		nfs_writeback_update_inode(hdr);
 	return 0;
 }
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 595d81e354d1..849ed784d6ac 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1377,6 +1377,36 @@ static int nfs_should_remove_suid(const struct inode *inode)
 	return 0;
 }
 
+static void nfs_writeback_check_extend(struct nfs_pgio_header *hdr,
+		struct nfs_fattr *fattr)
+{
+	struct nfs_pgio_args *argp = &hdr->args;
+	struct nfs_pgio_res *resp = &hdr->res;
+
+	if (!(fattr->valid & NFS_ATTR_FATTR_SIZE))
+		return;
+	if (argp->offset + resp->count != fattr->size)
+		return;
+	if (nfs_size_to_loff_t(fattr->size) < i_size_read(hdr->inode))
+		return;
+	/* Set attribute barrier */
+	nfs_fattr_set_barrier(fattr);
+}
+
+void nfs_writeback_update_inode(struct nfs_pgio_header *hdr)
+{
+	struct nfs_fattr *fattr = hdr->res.fattr;
+	struct inode *inode = hdr->inode;
+
+	if (fattr == NULL)
+		return;
+	spin_lock(&inode->i_lock);
+	nfs_writeback_check_extend(hdr, fattr);
+	nfs_post_op_update_inode_force_wcc_locked(inode, fattr);
+	spin_unlock(&inode->i_lock);
+}
+EXPORT_SYMBOL_GPL(nfs_writeback_update_inode);
+
 /*
  * This function is called when the WRITE call is complete.
  */
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index f6b2a09f793f..d2f2c37dc2db 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1638,7 +1638,7 @@ __destroy_client(struct nfs4_client *clp)
 		nfs4_put_stid(&dp->dl_stid);
 	}
 	while (!list_empty(&clp->cl_revoked)) {
-		dp = list_entry(reaplist.next, struct nfs4_delegation, dl_recall_lru);
+		dp = list_entry(clp->cl_revoked.next, struct nfs4_delegation, dl_recall_lru);
 		list_del_init(&dp->dl_recall_lru);
 		nfs4_put_stid(&dp->dl_stid);
 	}
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index b2e3ff347620..ecdbae19a766 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -31,6 +31,8 @@
 #include "alloc.h"
 #include "dat.h"
 
+static void __nilfs_btree_init(struct nilfs_bmap *bmap);
+
 static struct nilfs_btree_path *nilfs_btree_alloc_path(void)
 {
 	struct nilfs_btree_path *path;
@@ -368,6 +370,34 @@ static int nilfs_btree_node_broken(const struct nilfs_btree_node *node,
 	return ret;
 }
 
+/**
+ * nilfs_btree_root_broken - verify consistency of btree root node
+ * @node: btree root node to be examined
+ * @ino: inode number
+ *
+ * Return Value: If node is broken, 1 is returned. Otherwise, 0 is returned.
+ */
+static int nilfs_btree_root_broken(const struct nilfs_btree_node *node,
+				   unsigned long ino)
+{
+	int level, flags, nchildren;
+	int ret = 0;
+
+	level = nilfs_btree_node_get_level(node);
+	flags = nilfs_btree_node_get_flags(node);
+	nchildren = nilfs_btree_node_get_nchildren(node);
+
+	if (unlikely(level < NILFS_BTREE_LEVEL_NODE_MIN ||
+		     level > NILFS_BTREE_LEVEL_MAX ||
+		     nchildren < 0 ||
+		     nchildren > NILFS_BTREE_ROOT_NCHILDREN_MAX)) {
+		pr_crit("NILFS: bad btree root (inode number=%lu): level = %d, flags = 0x%x, nchildren = %d\n",
+			ino, level, flags, nchildren);
+		ret = 1;
+	}
+	return ret;
+}
+
 int nilfs_btree_broken_node_block(struct buffer_head *bh)
 {
 	int ret;
@@ -1713,7 +1743,7 @@ nilfs_btree_commit_convert_and_insert(struct nilfs_bmap *btree,
 
 	/* convert and insert */
 	dat = NILFS_BMAP_USE_VBN(btree) ? nilfs_bmap_get_dat(btree) : NULL;
-	nilfs_btree_init(btree);
+	__nilfs_btree_init(btree);
 	if (nreq != NULL) {
 		nilfs_bmap_commit_alloc_ptr(btree, dreq, dat);
 		nilfs_bmap_commit_alloc_ptr(btree, nreq, dat);
@@ -2294,12 +2324,23 @@ static const struct nilfs_bmap_operations nilfs_btree_ops_gc = {
 	.bop_gather_data	=	NULL,
 };
 
-int nilfs_btree_init(struct nilfs_bmap *bmap)
+static void __nilfs_btree_init(struct nilfs_bmap *bmap)
 {
 	bmap->b_ops = &nilfs_btree_ops;
 	bmap->b_nchildren_per_block =
 		NILFS_BTREE_NODE_NCHILDREN_MAX(nilfs_btree_node_size(bmap));
-	return 0;
+}
+
+int nilfs_btree_init(struct nilfs_bmap *bmap)
+{
+	int ret = 0;
+
+	__nilfs_btree_init(bmap);
+
+	if (nilfs_btree_root_broken(nilfs_btree_get_root(bmap),
+				    bmap->b_inode->i_ino))
+		ret = -EIO;
+	return ret;
 }
 
 void nilfs_btree_init_gc(struct nilfs_bmap *bmap)
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 469086b9f99b..0c3f303baf32 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -1907,6 +1907,7 @@ static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci,
 					     struct the_nilfs *nilfs)
 {
 	struct nilfs_inode_info *ii, *n;
+	int during_mount = !(sci->sc_super->s_flags & MS_ACTIVE);
 	int defer_iput = false;
 
 	spin_lock(&nilfs->ns_inode_lock);
@@ -1919,10 +1920,10 @@ static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci,
 		brelse(ii->i_bh);
 		ii->i_bh = NULL;
 		list_del_init(&ii->i_dirty);
-		if (!ii->vfs_inode.i_nlink) {
+		if (!ii->vfs_inode.i_nlink || during_mount) {
 			/*
-			 * Defer calling iput() to avoid a deadlock
-			 * over I_SYNC flag for inodes with i_nlink == 0
+			 * Defer calling iput() to avoid deadlocks if
+			 * i_nlink == 0 or mount is not yet finished.
 			 */
 			list_add_tail(&ii->i_dirty, &sci->sc_iput_queue);
 			defer_iput = true;
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 9a66ff79ff27..d2f97ecca6a5 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -143,7 +143,8 @@ static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark,
 	    !(marks_mask & FS_ISDIR & ~marks_ignored_mask))
 		return false;
 
-	if (event_mask & marks_mask & ~marks_ignored_mask)
+	if (event_mask & FAN_ALL_OUTGOING_EVENTS & marks_mask &
+				 ~marks_ignored_mask)
 		return true;
 
 	return false;
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 8490c64d34fe..460c6c37e683 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -502,7 +502,7 @@ static inline int ocfs2_writes_unwritten_extents(struct ocfs2_super *osb)
 
 static inline int ocfs2_supports_append_dio(struct ocfs2_super *osb)
 {
-	if (osb->s_feature_ro_compat & OCFS2_FEATURE_RO_COMPAT_APPEND_DIO)
+	if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_APPEND_DIO)
 		return 1;
 	return 0;
 }
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 20e37a3ed26f..db64ce2d4667 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -102,11 +102,11 @@
 					 | OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS \
 					 | OCFS2_FEATURE_INCOMPAT_REFCOUNT_TREE \
 					 | OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG	\
-					 | OCFS2_FEATURE_INCOMPAT_CLUSTERINFO)
+					 | OCFS2_FEATURE_INCOMPAT_CLUSTERINFO \
+					 | OCFS2_FEATURE_INCOMPAT_APPEND_DIO)
 #define OCFS2_FEATURE_RO_COMPAT_SUPP	(OCFS2_FEATURE_RO_COMPAT_UNWRITTEN \
 					 | OCFS2_FEATURE_RO_COMPAT_USRQUOTA \
-					 | OCFS2_FEATURE_RO_COMPAT_GRPQUOTA \
-					 | OCFS2_FEATURE_RO_COMPAT_APPEND_DIO)
+					 | OCFS2_FEATURE_RO_COMPAT_GRPQUOTA)
 
 /*
  * Heartbeat-only devices are missing journals and other files.  The
@@ -179,6 +179,11 @@
 #define OCFS2_FEATURE_INCOMPAT_CLUSTERINFO	0x4000
 
 /*
+ * Append Direct IO support
+ */
+#define OCFS2_FEATURE_INCOMPAT_APPEND_DIO	0x8000
+
+/*
  * backup superblock flag is used to indicate that this volume
  * has backup superblocks.
  */
@@ -200,10 +205,6 @@
 #define OCFS2_FEATURE_RO_COMPAT_USRQUOTA	0x0002
 #define OCFS2_FEATURE_RO_COMPAT_GRPQUOTA	0x0004
 
-/*
- * Append Direct IO support
- */
-#define OCFS2_FEATURE_RO_COMPAT_APPEND_DIO	0x0008
 
 /* The byte offset of the first backup block will be 1G.
  * The following will be 4G, 16G, 64G, 256G and 1T.
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index ce615d12fb44..a2e1cb8a568b 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -397,7 +397,8 @@ STATIC int				/* error (positive) */
 xfs_zero_last_block(
 	struct xfs_inode	*ip,
 	xfs_fsize_t		offset,
-	xfs_fsize_t		isize)
+	xfs_fsize_t		isize,
+	bool			*did_zeroing)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		last_fsb = XFS_B_TO_FSBT(mp, isize);
@@ -425,6 +426,7 @@ xfs_zero_last_block(
 	zero_len = mp->m_sb.sb_blocksize - zero_offset;
 	if (isize + zero_len > offset)
 		zero_len = offset - isize;
+	*did_zeroing = true;
 	return xfs_iozero(ip, isize, zero_len);
 }
 
@@ -443,7 +445,8 @@ int					/* error (positive) */
 xfs_zero_eof(
 	struct xfs_inode	*ip,
 	xfs_off_t		offset,		/* starting I/O offset */
-	xfs_fsize_t		isize)		/* current inode size */
+	xfs_fsize_t		isize,		/* current inode size */
+	bool			*did_zeroing)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		start_zero_fsb;
@@ -465,7 +468,7 @@ xfs_zero_eof(
 	 * We only zero a part of that block so it is handled specially.
 	 */
 	if (XFS_B_FSB_OFFSET(mp, isize) != 0) {
-		error = xfs_zero_last_block(ip, offset, isize);
+		error = xfs_zero_last_block(ip, offset, isize, did_zeroing);
 		if (error)
 			return error;
 	}
@@ -525,6 +528,7 @@ xfs_zero_eof(
 		if (error)
 			return error;
 
+		*did_zeroing = true;
 		start_zero_fsb = imap.br_startoff + imap.br_blockcount;
 		ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
 	}
@@ -567,13 +571,15 @@ restart:
 	 * having to redo all checks before.
 	 */
 	if (*pos > i_size_read(inode)) {
+		bool	zero = false;
+
 		if (*iolock == XFS_IOLOCK_SHARED) {
 			xfs_rw_iunlock(ip, *iolock);
 			*iolock = XFS_IOLOCK_EXCL;
 			xfs_rw_ilock(ip, *iolock);
 			goto restart;
 		}
-		error = xfs_zero_eof(ip, *pos, i_size_read(inode));
+		error = xfs_zero_eof(ip, *pos, i_size_read(inode), &zero);
 		if (error)
 			return error;
 	}
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index daafa1f6d260..6163767aa856 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2867,6 +2867,10 @@ xfs_rename(
 	 * Handle RENAME_EXCHANGE flags
 	 */
 	if (flags & RENAME_EXCHANGE) {
+		if (target_ip == NULL) {
+			error = -EINVAL;
+			goto error_return;
+		}
 		error = xfs_cross_rename(tp, src_dp, src_name, src_ip,
 					 target_dp, target_name, target_ip,
 					 &free_list, &first_block, spaceres);
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 86cd6b39bed7..a1cd55f3f351 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -384,10 +384,11 @@ enum xfs_prealloc_flags {
 	XFS_PREALLOC_INVISIBLE	= (1 << 4),
 };
 
-int		xfs_update_prealloc_flags(struct xfs_inode *,
-			enum xfs_prealloc_flags);
-int		xfs_zero_eof(struct xfs_inode *, xfs_off_t, xfs_fsize_t);
-int		xfs_iozero(struct xfs_inode *, loff_t, size_t);
+int	xfs_update_prealloc_flags(struct xfs_inode *ip,
+				  enum xfs_prealloc_flags flags);
+int	xfs_zero_eof(struct xfs_inode *ip, xfs_off_t offset,
+		     xfs_fsize_t isize, bool *did_zeroing);
+int	xfs_iozero(struct xfs_inode *ip, loff_t pos, size_t count);
 
 
 #define IHOLD(ip) \
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index d919ad7b16bf..e53a90331422 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -751,6 +751,7 @@ xfs_setattr_size(
 	int			error;
 	uint			lock_flags = 0;
 	uint			commit_flags = 0;
+	bool			did_zeroing = false;
 
 	trace_xfs_setattr(ip);
 
@@ -794,20 +795,16 @@ xfs_setattr_size(
 		return error;
 
 	/*
-	 * Now we can make the changes.  Before we join the inode to the
-	 * transaction, take care of the part of the truncation that must be
-	 * done without the inode lock.  This needs to be done before joining
-	 * the inode to the transaction, because the inode cannot be unlocked
-	 * once it is a part of the transaction.
+	 * File data changes must be complete before we start the transaction to
+	 * modify the inode.  This needs to be done before joining the inode to
+	 * the transaction because the inode cannot be unlocked once it is a
+	 * part of the transaction.
+	 *
+	 * Start with zeroing any data block beyond EOF that we may expose on
+	 * file extension.
 	 */
 	if (newsize > oldsize) {
-		/*
-		 * Do the first part of growing a file: zero any data in the
-		 * last block that is beyond the old EOF.  We need to do this
-		 * before the inode is joined to the transaction to modify
-		 * i_size.
-		 */
-		error = xfs_zero_eof(ip, newsize, oldsize);
+		error = xfs_zero_eof(ip, newsize, oldsize, &did_zeroing);
 		if (error)
 			return error;
 	}
@@ -817,23 +814,18 @@ xfs_setattr_size(
 	 * any previous writes that are beyond the on disk EOF and the new
 	 * EOF that have not been written out need to be written here.  If we
 	 * do not write the data out, we expose ourselves to the null files
-	 * problem.
-	 *
-	 * Only flush from the on disk size to the smaller of the in memory
-	 * file size or the new size as that's the range we really care about
-	 * here and prevents waiting for other data not within the range we
-	 * care about here.
+	 * problem. Note that this includes any block zeroing we did above;
+	 * otherwise those blocks may not be zeroed after a crash.
 	 */
-	if (oldsize != ip->i_d.di_size && newsize > ip->i_d.di_size) {
+	if (newsize > ip->i_d.di_size &&
+	    (oldsize != ip->i_d.di_size || did_zeroing)) {
 		error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
 						      ip->i_d.di_size, newsize);
 		if (error)
 			return error;
 	}
 
-	/*
-	 * Wait for all direct I/O to complete.
-	 */
+	/* Now wait for all direct I/O to complete. */
 	inode_dio_wait(inode);
 
 	/*
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index 4b33ef112400..365dd57ea760 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -300,8 +300,10 @@ xfs_fs_commit_blocks(
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
 	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
-	if (error)
+	if (error) {
+		xfs_trans_cancel(tp, 0);
 		goto out_drop_iolock;
+	}
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 53cc2aaf8d2b..fbbb9e62e274 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -836,6 +836,11 @@ xfs_qm_reset_dqcounts(
 		 */
 		xfs_dqcheck(mp, ddq, id+j, type, XFS_QMOPT_DQREPAIR,
 			    "xfs_quotacheck");
+		/*
+		 * Reset type in case we are reusing group quota file for
+		 * project quotas or vice versa
+		 */
+		ddq->d_flags = type;
 		ddq->d_bcount = 0;
 		ddq->d_icount = 0;
 		ddq->d_rtbcount = 0;