Merge branch 'overlayfs-current' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs into for-linus

"The biggest change is to rename the filesystem from "overlayfs" to "overlay".
This will allow legacy overlayfs to be easily carried by distros alongside the
new mainline one.  Also fix a couple of copy-up races and allow escaping comma
character in filenames."

The last bit is about commas in pathname mount options...

28 files changed, 400 insertions, 347 deletions

diff --git a/fs/Makefile b/fs/Makefile
index 34a1b9dea6dd..da0bbb456d3f 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -104,7 +104,7 @@ obj-$(CONFIG_QNX6FS_FS)		+= qnx6/
 obj-$(CONFIG_AUTOFS4_FS)	+= autofs4/
 obj-$(CONFIG_ADFS_FS)		+= adfs/
 obj-$(CONFIG_FUSE_FS)		+= fuse/
-obj-$(CONFIG_OVERLAYFS_FS)	+= overlayfs/
+obj-$(CONFIG_OVERLAY_FS)	+= overlayfs/
 obj-$(CONFIG_UDF_FS)		+= udf/
 obj-$(CONFIG_SUN_OPENPROMFS)	+= openpromfs/
 obj-$(CONFIG_OMFS_FS)		+= omfs/
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 783a94355efd..84a2d1868271 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -413,7 +413,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 	ret = 0;
 fail:
 	while (ret < 0 && !list_empty(&tmplist)) {
-		sums = list_entry(&tmplist, struct btrfs_ordered_sum, list);
+		sums = list_entry(tmplist.next, struct btrfs_ordered_sum, list);
 		list_del(&sums->list);
 		kfree(sums);
 	}
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 659f2ea9e6f7..cefca661464b 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2638,7 +2638,7 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
 
 	for (i = 0; i < CEPH_CAP_BITS; i++)
 		if ((dirty & (1 << i)) &&
-		    flush_tid == ci->i_cap_flush_tid[i])
+		    (u16)flush_tid == ci->i_cap_flush_tid[i])
 			cleaned |= 1 << i;
 
 	dout("handle_cap_flush_ack inode %p mds%d seq %d on %s cleaned %s,"
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 5228f201d3d5..4f46f7a05289 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -378,7 +378,7 @@ bl_write_pagelist(struct nfs_pgio_header *header, int sync)
 	loff_t offset = header->args.offset;
 	size_t count = header->args.count;
 	struct page **pages = header->args.pages;
-	int pg_index = pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT;
+	int pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT;
 	unsigned int pg_len;
 	struct blk_plug plug;
 	int i;
diff --git a/fs/nfs/blocklayout/rpc_pipefs.c b/fs/nfs/blocklayout/rpc_pipefs.c
index e966c023b1b7..acbf9ca4018c 100644
--- a/fs/nfs/blocklayout/rpc_pipefs.c
+++ b/fs/nfs/blocklayout/rpc_pipefs.c
@@ -65,17 +65,18 @@ bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b,
 
 	dprintk("%s CREATING PIPEFS MESSAGE\n", __func__);
 
+	mutex_lock(&nn->bl_mutex);
 	bl_pipe_msg.bl_wq = &nn->bl_wq;
 
 	b->simple.len += 4;	/* single volume */
 	if (b->simple.len > PAGE_SIZE)
-		return -EIO;
+		goto out_unlock;
 
 	memset(msg, 0, sizeof(*msg));
 	msg->len = sizeof(*bl_msg) + b->simple.len;
 	msg->data = kzalloc(msg->len, gfp_mask);
 	if (!msg->data)
-		goto out;
+		goto out_free_data;
 
 	bl_msg = msg->data;
 	bl_msg->type = BL_DEVICE_MOUNT,
@@ -87,7 +88,7 @@ bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b,
 	rc = rpc_queue_upcall(nn->bl_device_pipe, msg);
 	if (rc < 0) {
 		remove_wait_queue(&nn->bl_wq, &wq);
-		goto out;
+		goto out_free_data;
 	}
 
 	set_current_state(TASK_UNINTERRUPTIBLE);
@@ -97,12 +98,14 @@ bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b,
 	if (reply->status != BL_DEVICE_REQUEST_PROC) {
 		printk(KERN_WARNING "%s failed to decode device: %d\n",
 			__func__, reply->status);
-		goto out;
+		goto out_free_data;
 	}
 
 	dev = MKDEV(reply->major, reply->minor);
-out:
+out_free_data:
 	kfree(msg->data);
+out_unlock:
+	mutex_unlock(&nn->bl_mutex);
 	return dev;
 }
 
@@ -232,6 +235,7 @@ static int nfs4blocklayout_net_init(struct net *net)
 	struct nfs_net *nn = net_generic(net, nfs_net_id);
 	struct dentry *dentry;
 
+	mutex_init(&nn->bl_mutex);
 	init_waitqueue_head(&nn->bl_wq);
 	nn->bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0);
 	if (IS_ERR(nn->bl_device_pipe))
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 5853f53db732..7f3f60641344 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -125,6 +125,8 @@ again:
 			continue;
 		if (!test_bit(NFS_DELEGATED_STATE, &state->flags))
 			continue;
+		if (!nfs4_valid_open_stateid(state))
+			continue;
 		if (!nfs4_stateid_match(&state->stateid, stateid))
 			continue;
 		get_nfs_open_context(ctx);
@@ -193,7 +195,11 @@ static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *
 {
 	int res = 0;
 
-	res = nfs4_proc_delegreturn(inode, delegation->cred, &delegation->stateid, issync);
+	if (!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
+		res = nfs4_proc_delegreturn(inode,
+				delegation->cred,
+				&delegation->stateid,
+				issync);
 	nfs_free_delegation(delegation);
 	return res;
 }
@@ -380,11 +386,13 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation
 {
 	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
 	struct nfs_inode *nfsi = NFS_I(inode);
-	int err;
+	int err = 0;
 
 	if (delegation == NULL)
 		return 0;
 	do {
+		if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
+			break;
 		err = nfs_delegation_claim_opens(inode, &delegation->stateid);
 		if (!issync || err != -EAGAIN)
 			break;
@@ -605,10 +613,23 @@ static void nfs_client_mark_return_unused_delegation_types(struct nfs_client *cl
 	rcu_read_unlock();
 }
 
+static void nfs_revoke_delegation(struct inode *inode)
+{
+	struct nfs_delegation *delegation;
+	rcu_read_lock();
+	delegation = rcu_dereference(NFS_I(inode)->delegation);
+	if (delegation != NULL) {
+		set_bit(NFS_DELEGATION_REVOKED, &delegation->flags);
+		nfs_mark_return_delegation(NFS_SERVER(inode), delegation);
+	}
+	rcu_read_unlock();
+}
+
 void nfs_remove_bad_delegation(struct inode *inode)
 {
 	struct nfs_delegation *delegation;
 
+	nfs_revoke_delegation(inode);
 	delegation = nfs_inode_detach_delegation(inode);
 	if (delegation) {
 		nfs_inode_find_state_and_recover(inode, &delegation->stateid);
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 5c1cce39297f..e3c20a3ccc93 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -31,6 +31,7 @@ enum {
 	NFS_DELEGATION_RETURN_IF_CLOSED,
 	NFS_DELEGATION_REFERENCED,
 	NFS_DELEGATION_RETURNING,
+	NFS_DELEGATION_REVOKED,
 };
 
 int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 06e8cfcbb670..6e62155abf26 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1527,6 +1527,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		case -ENOENT:
 			d_drop(dentry);
 			d_add(dentry, NULL);
+			nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 			break;
 		case -EISDIR:
 		case -ENOTDIR:
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 20cffc830468..10bf07280f4a 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -266,6 +266,7 @@ static void nfs_direct_req_free(struct kref *kref)
 {
 	struct nfs_direct_req *dreq = container_of(kref, struct nfs_direct_req, kref);
 
+	nfs_free_pnfs_ds_cinfo(&dreq->ds_cinfo);
 	if (dreq->l_ctx != NULL)
 		nfs_put_lock_context(dreq->l_ctx);
 	if (dreq->ctx != NULL)
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 46fab1cb455a..7afb52f6a25a 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -145,9 +145,6 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 	case -NFS4ERR_DELEG_REVOKED:
 	case -NFS4ERR_ADMIN_REVOKED:
 	case -NFS4ERR_BAD_STATEID:
-		if (state == NULL)
-			break;
-		nfs_remove_bad_delegation(state->inode);
 	case -NFS4ERR_OPENMODE:
 		if (state == NULL)
 			break;
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 6388a59f2add..00689a8a85e4 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -626,7 +626,7 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 {
 	struct inode *inode = dentry->d_inode;
 	int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME;
-	int err;
+	int err = 0;
 
 	trace_nfs_getattr_enter(inode);
 	/* Flush out writes to the server in order to update c/mtime.  */
diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h
index ef221fb8a183..f0e06e4acbef 100644
--- a/fs/nfs/netns.h
+++ b/fs/nfs/netns.h
@@ -19,6 +19,7 @@ struct nfs_net {
 	struct rpc_pipe *bl_device_pipe;
 	struct bl_dev_msg bl_mount_reply;
 	wait_queue_head_t bl_wq;
+	struct mutex bl_mutex;
 	struct list_head nfs_client_list;
 	struct list_head nfs_volume_list;
 #if IS_ENABLED(CONFIG_NFS_V4)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 405bd95c1f58..69dc20a743f9 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -370,11 +370,6 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
 		case -NFS4ERR_DELEG_REVOKED:
 		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_BAD_STATEID:
-			if (inode != NULL && nfs4_have_delegation(inode, FMODE_READ)) {
-				nfs_remove_bad_delegation(inode);
-				exception->retry = 1;
-				break;
-			}
 			if (state == NULL)
 				break;
 			ret = nfs4_schedule_stateid_recovery(server, state);
@@ -1654,7 +1649,7 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct
 			nfs_inode_find_state_and_recover(state->inode,
 					stateid);
 			nfs4_schedule_stateid_recovery(server, state);
-			return 0;
+			return -EAGAIN;
 		case -NFS4ERR_DELAY:
 		case -NFS4ERR_GRACE:
 			set_bit(NFS_DELEGATED_STATE, &state->flags);
@@ -2109,46 +2104,60 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta
 	return ret;
 }
 
+static void nfs_finish_clear_delegation_stateid(struct nfs4_state *state)
+{
+	nfs_remove_bad_delegation(state->inode);
+	write_seqlock(&state->seqlock);
+	nfs4_stateid_copy(&state->stateid, &state->open_stateid);
+	write_sequnlock(&state->seqlock);
+	clear_bit(NFS_DELEGATED_STATE, &state->flags);
+}
+
+static void nfs40_clear_delegation_stateid(struct nfs4_state *state)
+{
+	if (rcu_access_pointer(NFS_I(state->inode)->delegation) != NULL)
+		nfs_finish_clear_delegation_stateid(state);
+}
+
+static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
+{
+	/* NFSv4.0 doesn't allow for delegation recovery on open expire */
+	nfs40_clear_delegation_stateid(state);
+	return nfs4_open_expired(sp, state);
+}
+
 #if defined(CONFIG_NFS_V4_1)
-static void nfs41_clear_delegation_stateid(struct nfs4_state *state)
+static void nfs41_check_delegation_stateid(struct nfs4_state *state)
 {
 	struct nfs_server *server = NFS_SERVER(state->inode);
-	nfs4_stateid *stateid = &state->stateid;
+	nfs4_stateid stateid;
 	struct nfs_delegation *delegation;
-	struct rpc_cred *cred = NULL;
-	int status = -NFS4ERR_BAD_STATEID;
-
-	/* If a state reset has been done, test_stateid is unneeded */
-	if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0)
-		return;
+	struct rpc_cred *cred;
+	int status;
 
 	/* Get the delegation credential for use by test/free_stateid */
 	rcu_read_lock();
 	delegation = rcu_dereference(NFS_I(state->inode)->delegation);
-	if (delegation != NULL &&
-	    nfs4_stateid_match(&delegation->stateid, stateid)) {
-		cred = get_rpccred(delegation->cred);
-		rcu_read_unlock();
-		status = nfs41_test_stateid(server, stateid, cred);
-		trace_nfs4_test_delegation_stateid(state, NULL, status);
-	} else
+	if (delegation == NULL) {
 		rcu_read_unlock();
+		return;
+	}
+
+	nfs4_stateid_copy(&stateid, &delegation->stateid);
+	cred = get_rpccred(delegation->cred);
+	rcu_read_unlock();
+	status = nfs41_test_stateid(server, &stateid, cred);
+	trace_nfs4_test_delegation_stateid(state, NULL, status);
 
 	if (status != NFS_OK) {
 		/* Free the stateid unless the server explicitly
 		 * informs us the stateid is unrecognized. */
 		if (status != -NFS4ERR_BAD_STATEID)
-			nfs41_free_stateid(server, stateid, cred);
-		nfs_remove_bad_delegation(state->inode);
-
-		write_seqlock(&state->seqlock);
-		nfs4_stateid_copy(&state->stateid, &state->open_stateid);
-		write_sequnlock(&state->seqlock);
-		clear_bit(NFS_DELEGATED_STATE, &state->flags);
+			nfs41_free_stateid(server, &stateid, cred);
+		nfs_finish_clear_delegation_stateid(state);
 	}
 
-	if (cred != NULL)
-		put_rpccred(cred);
+	put_rpccred(cred);
 }
 
 /**
@@ -2192,7 +2201,7 @@ static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *st
 {
 	int status;
 
-	nfs41_clear_delegation_stateid(state);
+	nfs41_check_delegation_stateid(state);
 	status = nfs41_check_open_stateid(state);
 	if (status != NFS_OK)
 		status = nfs4_open_expired(sp, state);
@@ -2231,19 +2240,8 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 	seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
 
 	ret = _nfs4_proc_open(opendata);
-	if (ret != 0) {
-		if (ret == -ENOENT) {
-			dentry = opendata->dentry;
-			if (dentry->d_inode)
-				d_delete(dentry);
-			else if (d_unhashed(dentry))
-				d_add(dentry, NULL);
-
-			nfs_set_verifier(dentry,
-					 nfs_save_change_attribute(opendata->dir->d_inode));
-		}
+	if (ret != 0)
 		goto out;
-	}
 
 	state = nfs4_opendata_to_nfs4_state(opendata);
 	ret = PTR_ERR(state);
@@ -4841,9 +4839,6 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 		case -NFS4ERR_DELEG_REVOKED:
 		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_BAD_STATEID:
-			if (state == NULL)
-				break;
-			nfs_remove_bad_delegation(state->inode);
 		case -NFS4ERR_OPENMODE:
 			if (state == NULL)
 				break;
@@ -8341,7 +8336,7 @@ static const struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = {
 static const struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = {
 	.owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE,
 	.state_flag_bit	= NFS_STATE_RECLAIM_NOGRACE,
-	.recover_open	= nfs4_open_expired,
+	.recover_open	= nfs40_open_expired,
 	.recover_lock	= nfs4_lock_expired,
 	.establish_clid = nfs4_init_clientid,
 };
@@ -8408,8 +8403,7 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
 		| NFS_CAP_CHANGE_ATTR
 		| NFS_CAP_POSIX_LOCK
 		| NFS_CAP_STATEID_NFSV41
-		| NFS_CAP_ATOMIC_OPEN_V1
-		| NFS_CAP_SEEK,
+		| NFS_CAP_ATOMIC_OPEN_V1,
 	.init_client = nfs41_init_client,
 	.shutdown_client = nfs41_shutdown_client,
 	.match_stateid = nfs41_match_stateid,
@@ -8431,7 +8425,8 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
 		| NFS_CAP_CHANGE_ATTR
 		| NFS_CAP_POSIX_LOCK
 		| NFS_CAP_STATEID_NFSV41
-		| NFS_CAP_ATOMIC_OPEN_V1,
+		| NFS_CAP_ATOMIC_OPEN_V1
+		| NFS_CAP_SEEK,
 	.init_client = nfs41_init_client,
 	.shutdown_client = nfs41_shutdown_client,
 	.match_stateid = nfs41_match_stateid,
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 12493846a2d3..f83b02dc9166 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -715,8 +715,6 @@ static void nfs_inode_remove_request(struct nfs_page *req)
 
 	if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags))
 		nfs_release_request(req);
-	else
-		WARN_ON_ONCE(1);
 }
 
 static void
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 9d3e9c50066a..89326acd4561 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -229,8 +229,16 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
 					      &fsnotify_mark_srcu);
 	}
 
+	/*
+	 * We need to merge inode & vfsmount mark lists so that inode mark
+	 * ignore masks are properly reflected for mount mark notifications.
+	 * That's why this traversal is so complicated...
+	 */
 	while (inode_node || vfsmount_node) {
-		inode_group = vfsmount_group = NULL;
+		inode_group = NULL;
+		inode_mark = NULL;
+		vfsmount_group = NULL;
+		vfsmount_mark = NULL;
 
 		if (inode_node) {
 			inode_mark = hlist_entry(srcu_dereference(inode_node, &fsnotify_mark_srcu),
@@ -244,21 +252,19 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
 			vfsmount_group = vfsmount_mark->group;
 		}
 
-		if (inode_group > vfsmount_group) {
-			/* handle inode */
-			ret = send_to_group(to_tell, inode_mark, NULL, mask,
-					    data, data_is, cookie, file_name);
-			/* we didn't use the vfsmount_mark */
-			vfsmount_group = NULL;
-		} else if (vfsmount_group > inode_group) {
-			ret = send_to_group(to_tell, NULL, vfsmount_mark, mask,
-					    data, data_is, cookie, file_name);
-			inode_group = NULL;
-		} else {
-			ret = send_to_group(to_tell, inode_mark, vfsmount_mark,
-					    mask, data, data_is, cookie,
-					    file_name);
+		if (inode_group && vfsmount_group) {
+			int cmp = fsnotify_compare_groups(inode_group,
+							  vfsmount_group);
+			if (cmp > 0) {
+				inode_group = NULL;
+				inode_mark = NULL;
+			} else if (cmp < 0) {
+				vfsmount_group = NULL;
+				vfsmount_mark = NULL;
+			}
 		}
+		ret = send_to_group(to_tell, inode_mark, vfsmount_mark, mask,
+				    data, data_is, cookie, file_name);
 
 		if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS))
 			goto out;
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
index 9c0898c4cfe1..3b68b0ae0a97 100644
--- a/fs/notify/fsnotify.h
+++ b/fs/notify/fsnotify.h
@@ -12,6 +12,10 @@ extern void fsnotify_flush_notify(struct fsnotify_group *group);
 /* protects reads of inode and vfsmount marks list */
 extern struct srcu_struct fsnotify_mark_srcu;
 
+/* compare two groups for sorting of marks lists */
+extern int fsnotify_compare_groups(struct fsnotify_group *a,
+				   struct fsnotify_group *b);
+
 extern void fsnotify_set_inode_mark_mask_locked(struct fsnotify_mark *fsn_mark,
 						__u32 mask);
 /* add a mark to an inode */
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index e8497144b323..dfbf5447eea4 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -194,6 +194,7 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 {
 	struct fsnotify_mark *lmark, *last = NULL;
 	int ret = 0;
+	int cmp;
 
 	mark->flags |= FSNOTIFY_MARK_FLAG_INODE;
 
@@ -219,11 +220,8 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 			goto out;
 		}
 
-		if (mark->group->priority < lmark->group->priority)
-			continue;
-
-		if ((mark->group->priority == lmark->group->priority) &&
-		    (mark->group < lmark->group))
+		cmp = fsnotify_compare_groups(lmark->group, mark->group);
+		if (cmp < 0)
 			continue;
 
 		hlist_add_before_rcu(&mark->i.i_list, &lmark->i.i_list);
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index d90deaa08e78..34c38fabf514 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -210,6 +210,42 @@ void fsnotify_set_mark_ignored_mask_locked(struct fsnotify_mark *mark, __u32 mas
 }
 
 /*
+ * Sorting function for lists of fsnotify marks.
+ *
+ * Fanotify supports different notification classes (reflected as priority of
+ * notification group). Events shall be passed to notification groups in
+ * decreasing priority order. To achieve this marks in notification lists for
+ * inodes and vfsmounts are sorted so that priorities of corresponding groups
+ * are descending.
+ *
+ * Furthermore correct handling of the ignore mask requires processing inode
+ * and vfsmount marks of each group together. Using the group address as
+ * further sort criterion provides a unique sorting order and thus we can
+ * merge inode and vfsmount lists of marks in linear time and find groups
+ * present in both lists.
+ *
+ * A return value of 1 signifies that b has priority over a.
+ * A return value of 0 signifies that the two marks have to be handled together.
+ * A return value of -1 signifies that a has priority over b.
+ */
+int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b)
+{
+	if (a == b)
+		return 0;
+	if (!a)
+		return 1;
+	if (!b)
+		return -1;
+	if (a->priority < b->priority)
+		return 1;
+	if (a->priority > b->priority)
+		return -1;
+	if (a < b)
+		return 1;
+	return -1;
+}
+
+/*
  * Attach an initialized mark to a given group and fs object.
  * These marks may be used for the fsnotify backend to determine which
  * event types should be delivered to which group.
diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c
index ac851e8376b1..faefa72a11eb 100644
--- a/fs/notify/vfsmount_mark.c
+++ b/fs/notify/vfsmount_mark.c
@@ -153,6 +153,7 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
 	struct mount *m = real_mount(mnt);
 	struct fsnotify_mark *lmark, *last = NULL;
 	int ret = 0;
+	int cmp;
 
 	mark->flags |= FSNOTIFY_MARK_FLAG_VFSMOUNT;
 
@@ -178,11 +179,8 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
 			goto out;
 		}
 
-		if (mark->group->priority < lmark->group->priority)
-			continue;
-
-		if ((mark->group->priority == lmark->group->priority) &&
-		    (mark->group < lmark->group))
+		cmp = fsnotify_compare_groups(lmark->group, mark->group);
+		if (cmp < 0)
 			continue;
 
 		hlist_add_before_rcu(&mark->m.m_list, &lmark->m.m_list);
diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig
index e60125976873..34355818a2e0 100644
--- a/fs/overlayfs/Kconfig
+++ b/fs/overlayfs/Kconfig
@@ -1,4 +1,4 @@
-config OVERLAYFS_FS
+config OVERLAY_FS
 	tristate "Overlay filesystem support"
 	help
 	  An overlay filesystem combines two filesystems - an 'upper' filesystem
diff --git a/fs/overlayfs/Makefile b/fs/overlayfs/Makefile
index 8f91889480d0..900daed3e91d 100644
--- a/fs/overlayfs/Makefile
+++ b/fs/overlayfs/Makefile
@@ -2,6 +2,6 @@
 # Makefile for the overlay filesystem.
 #
 
-obj-$(CONFIG_OVERLAYFS_FS) += overlayfs.o
+obj-$(CONFIG_OVERLAY_FS) += overlay.o
 
-overlayfs-objs := super.o inode.o dir.o readdir.o copy_up.o
+overlay-objs := super.o inode.o dir.o readdir.o copy_up.o
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 15cd91ad9940..8ffc4b980f1b 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -284,8 +284,7 @@ out:
 	return ERR_PTR(err);
 }
 
-static struct dentry *ovl_check_empty_and_clear(struct dentry *dentry,
-						enum ovl_path_type type)
+static struct dentry *ovl_check_empty_and_clear(struct dentry *dentry)
 {
 	int err;
 	struct dentry *ret = NULL;
@@ -294,8 +293,17 @@ static struct dentry *ovl_check_empty_and_clear(struct dentry *dentry,
 	err = ovl_check_empty_dir(dentry, &list);
 	if (err)
 		ret = ERR_PTR(err);
-	else if (type == OVL_PATH_MERGE)
-		ret = ovl_clear_empty(dentry, &list);
+	else {
+		/*
+		 * If no upperdentry then skip clearing whiteouts.
+		 *
+		 * Can race with copy-up, since we don't hold the upperdir
+		 * mutex.  Doesn't matter, since copy-up can't create a
+		 * non-empty directory from an empty one.
+		 */
+		if (ovl_dentry_upper(dentry))
+			ret = ovl_clear_empty(dentry, &list);
+	}
 
 	ovl_cache_free(&list);
 
@@ -487,8 +495,7 @@ out:
 	return err;
 }
 
-static int ovl_remove_and_whiteout(struct dentry *dentry,
-				   enum ovl_path_type type, bool is_dir)
+static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir)
 {
 	struct dentry *workdir = ovl_workdir(dentry);
 	struct inode *wdir = workdir->d_inode;
@@ -500,7 +507,7 @@ static int ovl_remove_and_whiteout(struct dentry *dentry,
 	int err;
 
 	if (is_dir) {
-		opaquedir = ovl_check_empty_and_clear(dentry, type);
+		opaquedir = ovl_check_empty_and_clear(dentry);
 		err = PTR_ERR(opaquedir);
 		if (IS_ERR(opaquedir))
 			goto out;
@@ -515,9 +522,10 @@ static int ovl_remove_and_whiteout(struct dentry *dentry,
 	if (IS_ERR(whiteout))
 		goto out_unlock;
 
-	if (type == OVL_PATH_LOWER) {
+	upper = ovl_dentry_upper(dentry);
+	if (!upper) {
 		upper = lookup_one_len(dentry->d_name.name, upperdir,
-					   dentry->d_name.len);
+				       dentry->d_name.len);
 		err = PTR_ERR(upper);
 		if (IS_ERR(upper))
 			goto kill_whiteout;
@@ -529,7 +537,6 @@ static int ovl_remove_and_whiteout(struct dentry *dentry,
 	} else {
 		int flags = 0;
 
-		upper = ovl_dentry_upper(dentry);
 		if (opaquedir)
 			upper = opaquedir;
 		err = -ESTALE;
@@ -648,7 +655,7 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir)
 		cap_raise(override_cred->cap_effective, CAP_CHOWN);
 		old_cred = override_creds(override_cred);
 
-		err = ovl_remove_and_whiteout(dentry, type, is_dir);
+		err = ovl_remove_and_whiteout(dentry, is_dir);
 
 		revert_creds(old_cred);
 		put_cred(override_cred);
@@ -781,7 +788,7 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 	}
 
 	if (overwrite && (new_type == OVL_PATH_LOWER || new_type == OVL_PATH_MERGE) && new_is_dir) {
-		opaquedir = ovl_check_empty_and_clear(new, new_type);
+		opaquedir = ovl_check_empty_and_clear(new);
 		err = PTR_ERR(opaquedir);
 		if (IS_ERR(opaquedir)) {
 			opaquedir = NULL;
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index af2d18c9fcee..07d74b24913b 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -235,26 +235,36 @@ out:
 	return err;
 }
 
+static bool ovl_need_xattr_filter(struct dentry *dentry,
+				  enum ovl_path_type type)
+{
+	return type == OVL_PATH_UPPER && S_ISDIR(dentry->d_inode->i_mode);
+}
+
 ssize_t ovl_getxattr(struct dentry *dentry, const char *name,
 		     void *value, size_t size)
 {
-	if (ovl_path_type(dentry->d_parent) == OVL_PATH_MERGE &&
-	    ovl_is_private_xattr(name))
+	struct path realpath;
+	enum ovl_path_type type = ovl_path_real(dentry, &realpath);
+
+	if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name))
 		return -ENODATA;
 
-	return vfs_getxattr(ovl_dentry_real(dentry), name, value, size);
+	return vfs_getxattr(realpath.dentry, name, value, size);
 }
 
 ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
 {
+	struct path realpath;
+	enum ovl_path_type type = ovl_path_real(dentry, &realpath);
 	ssize_t res;
 	int off;
 
-	res = vfs_listxattr(ovl_dentry_real(dentry), list, size);
+	res = vfs_listxattr(realpath.dentry, list, size);
 	if (res <= 0 || size == 0)
 		return res;
 
-	if (ovl_path_type(dentry->d_parent) != OVL_PATH_MERGE)
+	if (!ovl_need_xattr_filter(dentry, type))
 		return res;
 
 	/* filter out private xattrs */
@@ -279,17 +289,16 @@ int ovl_removexattr(struct dentry *dentry, const char *name)
 {
 	int err;
 	struct path realpath;
-	enum ovl_path_type type;
+	enum ovl_path_type type = ovl_path_real(dentry, &realpath);
 
 	err = ovl_want_write(dentry);
 	if (err)
 		goto out;
 
-	if (ovl_path_type(dentry->d_parent) == OVL_PATH_MERGE &&
-	    ovl_is_private_xattr(name))
+	err = -ENODATA;
+	if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name))
 		goto out_drop_write;
 
-	type = ovl_path_real(dentry, &realpath);
 	if (type == OVL_PATH_LOWER) {
 		err = vfs_getxattr(realpath.dentry, name, NULL, 0);
 		if (err < 0)
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 2a7ef4f8e2a6..ab1e3dcbed95 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -274,11 +274,11 @@ static int ovl_dir_mark_whiteouts(struct dentry *dir,
 	return 0;
 }
 
-static inline int ovl_dir_read_merged(struct path *upperpath,
-				      struct path *lowerpath,
-				      struct list_head *list)
+static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list)
 {
 	int err;
+	struct path lowerpath;
+	struct path upperpath;
 	struct ovl_readdir_data rdd = {
 		.ctx.actor = ovl_fill_merge,
 		.list = list,
@@ -286,25 +286,28 @@ static inline int ovl_dir_read_merged(struct path *upperpath,
 		.is_merge = false,
 	};
 
-	if (upperpath->dentry) {
-		err = ovl_dir_read(upperpath, &rdd);
+	ovl_path_lower(dentry, &lowerpath);
+	ovl_path_upper(dentry, &upperpath);
+
+	if (upperpath.dentry) {
+		err = ovl_dir_read(&upperpath, &rdd);
 		if (err)
 			goto out;
 
-		if (lowerpath->dentry) {
-			err = ovl_dir_mark_whiteouts(upperpath->dentry, &rdd);
+		if (lowerpath.dentry) {
+			err = ovl_dir_mark_whiteouts(upperpath.dentry, &rdd);
 			if (err)
 				goto out;
 		}
 	}
-	if (lowerpath->dentry) {
+	if (lowerpath.dentry) {
 		/*
 		 * Insert lowerpath entries before upperpath ones, this allows
 		 * offsets to be reasonably constant
 		 */
 		list_add(&rdd.middle, rdd.list);
 		rdd.is_merge = true;
-		err = ovl_dir_read(lowerpath, &rdd);
+		err = ovl_dir_read(&lowerpath, &rdd);
 		list_del(&rdd.middle);
 	}
 out:
@@ -329,8 +332,6 @@ static void ovl_seek_cursor(struct ovl_dir_file *od, loff_t pos)
 static struct ovl_dir_cache *ovl_cache_get(struct dentry *dentry)
 {
 	int res;
-	struct path lowerpath;
-	struct path upperpath;
 	struct ovl_dir_cache *cache;
 
 	cache = ovl_dir_cache(dentry);
@@ -347,10 +348,7 @@ static struct ovl_dir_cache *ovl_cache_get(struct dentry *dentry)
 	cache->refcount = 1;
 	INIT_LIST_HEAD(&cache->entries);
 
-	ovl_path_lower(dentry, &lowerpath);
-	ovl_path_upper(dentry, &upperpath);
-
-	res = ovl_dir_read_merged(&upperpath, &lowerpath, &cache->entries);
+	res = ovl_dir_read_merged(dentry, &cache->entries);
 	if (res) {
 		ovl_cache_free(&cache->entries);
 		kfree(cache);
@@ -452,10 +450,10 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end,
 	/*
 	 * Need to check if we started out being a lower dir, but got copied up
 	 */
-	if (!od->is_upper && ovl_path_type(dentry) == OVL_PATH_MERGE) {
+	if (!od->is_upper && ovl_path_type(dentry) != OVL_PATH_LOWER) {
 		struct inode *inode = file_inode(file);
 
-		realfile =lockless_dereference(od->upperfile);
+		realfile = lockless_dereference(od->upperfile);
 		if (!realfile) {
 			struct path upperpath;
 
@@ -538,14 +536,9 @@ const struct file_operations ovl_dir_operations = {
 int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list)
 {
 	int err;
-	struct path lowerpath;
-	struct path upperpath;
 	struct ovl_cache_entry *p;
 
-	ovl_path_upper(dentry, &upperpath);
-	ovl_path_lower(dentry, &lowerpath);
-
-	err = ovl_dir_read_merged(&upperpath, &lowerpath, list);
+	err = ovl_dir_read_merged(dentry, list);
 	if (err)
 		return err;
 
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 08b704cebfc4..f16d318b71f8 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -24,7 +24,7 @@ MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
 MODULE_DESCRIPTION("Overlay filesystem");
 MODULE_LICENSE("GPL");
 
-#define OVERLAYFS_SUPER_MAGIC 0x794c764f
+#define OVERLAYFS_SUPER_MAGIC 0x794c7630
 
 struct ovl_config {
 	char *lowerdir;
@@ -84,12 +84,7 @@ enum ovl_path_type ovl_path_type(struct dentry *dentry)
 
 static struct dentry *ovl_upperdentry_dereference(struct ovl_entry *oe)
 {
-	struct dentry *upperdentry = ACCESS_ONCE(oe->__upperdentry);
-	/*
-	 * Make sure to order reads to upperdentry wrt ovl_dentry_update()
-	 */
-	smp_read_barrier_depends();
-	return upperdentry;
+	return lockless_dereference(oe->__upperdentry);
 }
 
 void ovl_path_upper(struct dentry *dentry, struct path *path)
@@ -462,11 +457,34 @@ static const match_table_t ovl_tokens = {
 	{OPT_ERR,			NULL}
 };
 
+static char *ovl_next_opt(char **s)
+{
+	char *sbegin = *s;
+	char *p;
+
+	if (sbegin == NULL)
+		return NULL;
+
+	for (p = sbegin; *p; p++) {
+		if (*p == '\\') {
+			p++;
+			if (!*p)
+				break;
+		} else if (*p == ',') {
+			*p = '\0';
+			*s = p + 1;
+			return sbegin;
+		}
+	}
+	*s = NULL;
+	return sbegin;
+}
+
 static int ovl_parse_opt(char *opt, struct ovl_config *config)
 {
 	char *p;
 
-	while ((p = strsep(&opt, ",")) != NULL) {
+	while ((p = ovl_next_opt(&opt)) != NULL) {
 		int token;
 		substring_t args[MAX_OPT_ARGS];
 
@@ -554,15 +572,34 @@ out_dput:
 	goto out_unlock;
 }
 
+static void ovl_unescape(char *s)
+{
+	char *d = s;
+
+	for (;; s++, d++) {
+		if (*s == '\\')
+			s++;
+		*d = *s;
+		if (!*s)
+			break;
+	}
+}
+
 static int ovl_mount_dir(const char *name, struct path *path)
 {
 	int err;
+	char *tmp = kstrdup(name, GFP_KERNEL);
+
+	if (!tmp)
+		return -ENOMEM;
 
-	err = kern_path(name, LOOKUP_FOLLOW, path);
+	ovl_unescape(tmp);
+	err = kern_path(tmp, LOOKUP_FOLLOW, path);
 	if (err) {
-		pr_err("overlayfs: failed to resolve '%s': %i\n", name, err);
+		pr_err("overlayfs: failed to resolve '%s': %i\n", tmp, err);
 		err = -EINVAL;
 	}
+	kfree(tmp);
 	return err;
 }
 
@@ -776,11 +813,11 @@ static struct dentry *ovl_mount(struct file_system_type *fs_type, int flags,
 
 static struct file_system_type ovl_fs_type = {
 	.owner		= THIS_MODULE,
-	.name		= "overlayfs",
+	.name		= "overlay",
 	.mount		= ovl_mount,
 	.kill_sb	= kill_anon_super,
 };
-MODULE_ALIAS_FS("overlayfs");
+MODULE_ALIAS_FS("overlay");
 
 static int __init ovl_init(void)
 {
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 92e8f99a5857..281002689d64 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1338,7 +1338,10 @@ xfs_free_file_space(
 	goto out;
 }
 
-
+/*
+ * Preallocate and zero a range of a file. This mechanism has the allocation
+ * semantics of fallocate and in addition converts data in the range to zeroes.
+ */
 int
 xfs_zero_file_space(
 	struct xfs_inode	*ip,
@@ -1346,65 +1349,30 @@ xfs_zero_file_space(
 	xfs_off_t		len)
 {
 	struct xfs_mount	*mp = ip->i_mount;
-	uint			granularity;
-	xfs_off_t		start_boundary;
-	xfs_off_t		end_boundary;
+	uint			blksize;
 	int			error;
 
 	trace_xfs_zero_file_space(ip);
 
-	granularity = max_t(uint, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
+	blksize = 1 << mp->m_sb.sb_blocklog;
 
 	/*
-	 * Round the range of extents we are going to convert inwards.  If the
-	 * offset is aligned, then it doesn't get changed so we zero from the
-	 * start of the block offset points to.
+	 * Punch a hole and prealloc the range. We use hole punch rather than
+	 * unwritten extent conversion for two reasons:
+	 *
+	 * 1.) Hole punch handles partial block zeroing for us.
+	 *
+	 * 2.) If prealloc returns ENOSPC, the file range is still zero-valued
+	 * by virtue of the hole punch.
 	 */
-	start_boundary = round_up(offset, granularity);
-	end_boundary = round_down(offset + len, granularity);
-
-	ASSERT(start_boundary >= offset);
-	ASSERT(end_boundary <= offset + len);
-
-	if (start_boundary < end_boundary - 1) {
-		/*
-		 * Writeback the range to ensure any inode size updates due to
-		 * appending writes make it to disk (otherwise we could just
-		 * punch out the delalloc blocks).
-		 */
-		error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
-				start_boundary, end_boundary - 1);
-		if (error)
-			goto out;
-		truncate_pagecache_range(VFS_I(ip), start_boundary,
-					 end_boundary - 1);
-
-		/* convert the blocks */
-		error = xfs_alloc_file_space(ip, start_boundary,
-					end_boundary - start_boundary - 1,
-					XFS_BMAPI_PREALLOC | XFS_BMAPI_CONVERT);
-		if (error)
-			goto out;
-
-		/* We've handled the interior of the range, now for the edges */
-		if (start_boundary != offset) {
-			error = xfs_iozero(ip, offset, start_boundary - offset);
-			if (error)
-				goto out;
-		}
-
-		if (end_boundary != offset + len)
-			error = xfs_iozero(ip, end_boundary,
-					   offset + len - end_boundary);
-
-	} else {
-		/*
-		 * It's either a sub-granularity range or the range spanned lies
-		 * partially across two adjacent blocks.
-		 */
-		error = xfs_iozero(ip, offset, len);
-	}
+	error = xfs_free_file_space(ip, offset, len);
+	if (error)
+		goto out;
 
+	error = xfs_alloc_file_space(ip, round_down(offset, blksize),
+				     round_up(offset + len, blksize) -
+				     round_down(offset, blksize),
+				     XFS_BMAPI_PREALLOC);
 out:
 	return error;
 
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index f1deb961a296..894924a5129b 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -236,8 +236,10 @@ xfs_bulkstat_grab_ichunk(
 	XFS_WANT_CORRUPTED_RETURN(stat == 1);
 
 	/* Check if the record contains the inode in request */
-	if (irec->ir_startino + XFS_INODES_PER_CHUNK <= agino)
-		return -EINVAL;
+	if (irec->ir_startino + XFS_INODES_PER_CHUNK <= agino) {
+		*icount = 0;
+		return 0;
+	}
 
 	idx = agino - irec->ir_startino + 1;
 	if (idx < XFS_INODES_PER_CHUNK &&
@@ -262,75 +264,76 @@ xfs_bulkstat_grab_ichunk(
 
 #define XFS_BULKSTAT_UBLEFT(ubleft)	((ubleft) >= statstruct_size)
 
+struct xfs_bulkstat_agichunk {
+	char		__user **ac_ubuffer;/* pointer into user's buffer */
+	int		ac_ubleft;	/* bytes left in user's buffer */
+	int		ac_ubelem;	/* spaces used in user's buffer */
+};
+
 /*
  * Process inodes in chunk with a pointer to a formatter function
  * that will iget the inode and fill in the appropriate structure.
  */
-int
+static int
 xfs_bulkstat_ag_ichunk(
 	struct xfs_mount		*mp,
 	xfs_agnumber_t			agno,
 	struct xfs_inobt_rec_incore	*irbp,
 	bulkstat_one_pf			formatter,
 	size_t				statstruct_size,
-	struct xfs_bulkstat_agichunk	*acp)
+	struct xfs_bulkstat_agichunk	*acp,
+	xfs_agino_t			*last_agino)
 {
-	xfs_ino_t			lastino = acp->ac_lastino;
 	char				__user **ubufp = acp->ac_ubuffer;
-	int				ubleft = acp->ac_ubleft;
-	int				ubelem = acp->ac_ubelem;
-	int				chunkidx, clustidx;
+	int				chunkidx;
 	int				error = 0;
-	xfs_agino_t			agino;
+	xfs_agino_t			agino = irbp->ir_startino;
 
-	for (agino = irbp->ir_startino, chunkidx = clustidx = 0;
-	     XFS_BULKSTAT_UBLEFT(ubleft) &&
-	     irbp->ir_freecount < XFS_INODES_PER_CHUNK;
-	     chunkidx++, clustidx++, agino++) {
-		int		fmterror;	/* bulkstat formatter result */
+	for (chunkidx = 0; chunkidx < XFS_INODES_PER_CHUNK;
+	     chunkidx++, agino++) {
+		int		fmterror;
 		int		ubused;
-		xfs_ino_t	ino = XFS_AGINO_TO_INO(mp, agno, agino);
 
-		ASSERT(chunkidx < XFS_INODES_PER_CHUNK);
+		/* inode won't fit in buffer, we are done */
+		if (acp->ac_ubleft < statstruct_size)
+			break;
 
 		/* Skip if this inode is free */
-		if (XFS_INOBT_MASK(chunkidx) & irbp->ir_free) {
-			lastino = ino;
+		if (XFS_INOBT_MASK(chunkidx) & irbp->ir_free)
 			continue;
-		}
-
-		/*
-		 * Count used inodes as free so we can tell when the
-		 * chunk is used up.
-		 */
-		irbp->ir_freecount++;
 
 		/* Get the inode and fill in a single buffer */
 		ubused = statstruct_size;
-		error = formatter(mp, ino, *ubufp, ubleft, &ubused, &fmterror);
-		if (fmterror == BULKSTAT_RV_NOTHING) {
-			if (error && error != -ENOENT && error != -EINVAL) {
-				ubleft = 0;
-				break;
-			}
-			lastino = ino;
-			continue;
-		}
-		if (fmterror == BULKSTAT_RV_GIVEUP) {
-			ubleft = 0;
+		error = formatter(mp, XFS_AGINO_TO_INO(mp, agno, agino),
+				  *ubufp, acp->ac_ubleft, &ubused, &fmterror);
+
+		if (fmterror == BULKSTAT_RV_GIVEUP ||
+		    (error && error != -ENOENT && error != -EINVAL)) {
+			acp->ac_ubleft = 0;
 			ASSERT(error);
 			break;
 		}
-		if (*ubufp)
-			*ubufp += ubused;
-		ubleft -= ubused;
-		ubelem++;
-		lastino = ino;
+
+		/* be careful not to leak error if at end of chunk */
+		if (fmterror == BULKSTAT_RV_NOTHING || error) {
+			error = 0;
+			continue;
+		}
+
+		*ubufp += ubused;
+		acp->ac_ubleft -= ubused;
+		acp->ac_ubelem++;
 	}
 
-	acp->ac_lastino = lastino;
-	acp->ac_ubleft = ubleft;
-	acp->ac_ubelem = ubelem;
+	/*
+	 * Post-update *last_agino. At this point, agino will always point one
+	 * inode past the last inode we processed successfully. Hence we
+	 * substract that inode when setting the *last_agino cursor so that we
+	 * return the correct cookie to userspace. On the next bulkstat call,
+	 * the inode under the lastino cookie will be skipped as we have already
+	 * processed it here.
+	 */
+	*last_agino = agino - 1;
 
 	return error;
 }
@@ -353,45 +356,33 @@ xfs_bulkstat(
 	xfs_agino_t		agino;	/* inode # in allocation group */
 	xfs_agnumber_t		agno;	/* allocation group number */
 	xfs_btree_cur_t		*cur;	/* btree cursor for ialloc btree */
-	int			end_of_ag; /* set if we've seen the ag end */
-	int			error;	/* error code */
-	int                     fmterror;/* bulkstat formatter result */
-	int			i;	/* loop index */
-	int			icount;	/* count of inodes good in irbuf */
 	size_t			irbsize; /* size of irec buffer in bytes */
-	xfs_ino_t		ino;	/* inode number (filesystem) */
-	xfs_inobt_rec_incore_t	*irbp;	/* current irec buffer pointer */
 	xfs_inobt_rec_incore_t	*irbuf;	/* start of irec buffer */
-	xfs_inobt_rec_incore_t	*irbufend; /* end of good irec buffer entries */
-	xfs_ino_t		lastino; /* last inode number returned */
 	int			nirbuf;	/* size of irbuf */
-	int			rval;	/* return value error code */
-	int			tmp;	/* result value from btree calls */
 	int			ubcount; /* size of user's buffer */
-	int			ubleft;	/* bytes left in user's buffer */
-	char			__user *ubufp;	/* pointer into user's buffer */
-	int			ubelem;	/* spaces used in user's buffer */
+	struct xfs_bulkstat_agichunk ac;
+	int			error = 0;
 
 	/*
 	 * Get the last inode value, see if there's nothing to do.
 	 */
-	ino = (xfs_ino_t)*lastinop;
-	lastino = ino;
-	agno = XFS_INO_TO_AGNO(mp, ino);
-	agino = XFS_INO_TO_AGINO(mp, ino);
+	agno = XFS_INO_TO_AGNO(mp, *lastinop);
+	agino = XFS_INO_TO_AGINO(mp, *lastinop);
 	if (agno >= mp->m_sb.sb_agcount ||
-	    ino != XFS_AGINO_TO_INO(mp, agno, agino)) {
+	    *lastinop != XFS_AGINO_TO_INO(mp, agno, agino)) {
 		*done = 1;
 		*ubcountp = 0;
 		return 0;
 	}
 
 	ubcount = *ubcountp; /* statstruct's */
-	ubleft = ubcount * statstruct_size; /* bytes */
-	*ubcountp = ubelem = 0;
+	ac.ac_ubuffer = &ubuffer;
+	ac.ac_ubleft = ubcount * statstruct_size; /* bytes */;
+	ac.ac_ubelem = 0;
+
+	*ubcountp = 0;
 	*done = 0;
-	fmterror = 0;
-	ubufp = ubuffer;
+
 	irbuf = kmem_zalloc_greedy(&irbsize, PAGE_SIZE, PAGE_SIZE * 4);
 	if (!irbuf)
 		return -ENOMEM;
@@ -402,9 +393,13 @@ xfs_bulkstat(
 	 * Loop over the allocation groups, starting from the last
 	 * inode returned; 0 means start of the allocation group.
 	 */
-	rval = 0;
-	while (XFS_BULKSTAT_UBLEFT(ubleft) && agno < mp->m_sb.sb_agcount) {
-		cond_resched();
+	while (agno < mp->m_sb.sb_agcount) {
+		struct xfs_inobt_rec_incore	*irbp = irbuf;
+		struct xfs_inobt_rec_incore	*irbufend = irbuf + nirbuf;
+		bool				end_of_ag = false;
+		int				icount = 0;
+		int				stat;
+
 		error = xfs_ialloc_read_agi(mp, NULL, agno, &agbp);
 		if (error)
 			break;
@@ -414,10 +409,6 @@ xfs_bulkstat(
 		 */
 		cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno,
 					    XFS_BTNUM_INO);
-		irbp = irbuf;
-		irbufend = irbuf + nirbuf;
-		end_of_ag = 0;
-		icount = 0;
 		if (agino > 0) {
 			/*
 			 * In the middle of an allocation group, we need to get
@@ -427,22 +418,23 @@ xfs_bulkstat(
 
 			error = xfs_bulkstat_grab_ichunk(cur, agino, &icount, &r);
 			if (error)
-				break;
+				goto del_cursor;
 			if (icount) {
 				irbp->ir_startino = r.ir_startino;
 				irbp->ir_freecount = r.ir_freecount;
 				irbp->ir_free = r.ir_free;
 				irbp++;
-				agino = r.ir_startino + XFS_INODES_PER_CHUNK;
 			}
 			/* Increment to the next record */
-			error = xfs_btree_increment(cur, 0, &tmp);
+			error = xfs_btree_increment(cur, 0, &stat);
 		} else {
 			/* Start of ag.  Lookup the first inode chunk */
-			error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &tmp);
+			error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &stat);
+		}
+		if (error || stat == 0) {
+			end_of_ag = true;
+			goto del_cursor;
 		}
-		if (error)
-			break;
 
 		/*
 		 * Loop through inode btree records in this ag,
@@ -451,10 +443,10 @@ xfs_bulkstat(
 		while (irbp < irbufend && icount < ubcount) {
 			struct xfs_inobt_rec_incore	r;
 
-			error = xfs_inobt_get_rec(cur, &r, &i);
-			if (error || i == 0) {
-				end_of_ag = 1;
-				break;
+			error = xfs_inobt_get_rec(cur, &r, &stat);
+			if (error || stat == 0) {
+				end_of_ag = true;
+				goto del_cursor;
 			}
 
 			/*
@@ -469,77 +461,79 @@ xfs_bulkstat(
 				irbp++;
 				icount += XFS_INODES_PER_CHUNK - r.ir_freecount;
 			}
-			/*
-			 * Set agino to after this chunk and bump the cursor.
-			 */
-			agino = r.ir_startino + XFS_INODES_PER_CHUNK;
-			error = xfs_btree_increment(cur, 0, &tmp);
+			error = xfs_btree_increment(cur, 0, &stat);
+			if (error || stat == 0) {
+				end_of_ag = true;
+				goto del_cursor;
+			}
 			cond_resched();
 		}
+
 		/*
-		 * Drop the btree buffers and the agi buffer.
-		 * We can't hold any of the locks these represent
-		 * when calling iget.
+		 * Drop the btree buffers and the agi buffer as we can't hold any
+		 * of the locks these represent when calling iget. If there is a
+		 * pending error, then we are done.
 		 */
+del_cursor:
 		xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
 		xfs_buf_relse(agbp);
+		if (error)
+			break;
 		/*
-		 * Now format all the good inodes into the user's buffer.
+		 * Now format all the good inodes into the user's buffer. The
+		 * call to xfs_bulkstat_ag_ichunk() sets up the agino pointer
+		 * for the next loop iteration.
 		 */
 		irbufend = irbp;
 		for (irbp = irbuf;
-		     irbp < irbufend && XFS_BULKSTAT_UBLEFT(ubleft); irbp++) {
-			struct xfs_bulkstat_agichunk ac;
-
-			ac.ac_lastino = lastino;
-			ac.ac_ubuffer = &ubuffer;
-			ac.ac_ubleft = ubleft;
-			ac.ac_ubelem = ubelem;
+		     irbp < irbufend && ac.ac_ubleft >= statstruct_size;
+		     irbp++) {
 			error = xfs_bulkstat_ag_ichunk(mp, agno, irbp,
-					formatter, statstruct_size, &ac);
+					formatter, statstruct_size, &ac,
+					&agino);
 			if (error)
-				rval = error;
-
-			lastino = ac.ac_lastino;
-			ubleft = ac.ac_ubleft;
-			ubelem = ac.ac_ubelem;
+				break;
 
 			cond_resched();
 		}
+
 		/*
-		 * Set up for the next loop iteration.
+		 * If we've run out of space or had a formatting error, we
+		 * are now done
 		 */
-		if (XFS_BULKSTAT_UBLEFT(ubleft)) {
-			if (end_of_ag) {
-				agno++;
-				agino = 0;
-			} else
-				agino = XFS_INO_TO_AGINO(mp, lastino);
-		} else
+		if (ac.ac_ubleft < statstruct_size || error)
 			break;
+
+		if (end_of_ag) {
+			agno++;
+			agino = 0;
+		}
 	}
 	/*
 	 * Done, we're either out of filesystem or space to put the data.
 	 */
 	kmem_free(irbuf);
-	*ubcountp = ubelem;
+	*ubcountp = ac.ac_ubelem;
+
 	/*
-	 * Found some inodes, return them now and return the error next time.
+	 * We found some inodes, so clear the error status and return them.
+	 * The lastino pointer will point directly at the inode that triggered
+	 * any error that occurred, so on the next call the error will be
+	 * triggered again and propagated to userspace as there will be no
+	 * formatted inodes in the buffer.
 	 */
-	if (ubelem)
-		rval = 0;
-	if (agno >= mp->m_sb.sb_agcount) {
-		/*
-		 * If we ran out of filesystem, mark lastino as off
-		 * the end of the filesystem, so the next call
-		 * will return immediately.
-		 */
-		*lastinop = (xfs_ino_t)XFS_AGINO_TO_INO(mp, agno, 0);
+	if (ac.ac_ubelem)
+		error = 0;
+
+	/*
+	 * If we ran out of filesystem, lastino will point off the end of
+	 * the filesystem so the next call will return immediately.
+	 */
+	*lastinop = XFS_AGINO_TO_INO(mp, agno, agino);
+	if (agno >= mp->m_sb.sb_agcount)
 		*done = 1;
-	} else
-		*lastinop = (xfs_ino_t)lastino;
 
-	return rval;
+	return error;
 }
 
 int
diff --git a/fs/xfs/xfs_itable.h b/fs/xfs/xfs_itable.h
index aaed08022eb9..6ea8b3912fa4 100644
--- a/fs/xfs/xfs_itable.h
+++ b/fs/xfs/xfs_itable.h
@@ -30,22 +30,6 @@ typedef int (*bulkstat_one_pf)(struct xfs_mount	*mp,
 			       int		*ubused,
 			       int		*stat);
 
-struct xfs_bulkstat_agichunk {
-	xfs_ino_t	ac_lastino;	/* last inode returned */
-	char		__user **ac_ubuffer;/* pointer into user's buffer */
-	int		ac_ubleft;	/* bytes left in user's buffer */
-	int		ac_ubelem;	/* spaces used in user's buffer */
-};
-
-int
-xfs_bulkstat_ag_ichunk(
-	struct xfs_mount		*mp,
-	xfs_agnumber_t			agno,
-	struct xfs_inobt_rec_incore	*irbp,
-	bulkstat_one_pf			formatter,
-	size_t				statstruct_size,
-	struct xfs_bulkstat_agichunk	*acp);
-
 /*
  * Values for stat return value.
  */