15 files changed, 130 insertions, 74 deletions

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index c05f69a8e..542379f8f 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2851,6 +2851,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 
 	if (log_root_tree->log_transid_committed >= root_log_ctx.log_transid) {
 		blk_finish_plug(&plug);
+		list_del_init(&root_log_ctx.list);
 		mutex_unlock(&log_root_tree->log_mutex);
 		ret = root_log_ctx.log_ret;
 		goto out;
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 37c134a13..cc543fea5 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -584,7 +584,8 @@ struct dentry *devpts_pty_new(struct pts_fs_info *fsi, int index, void *priv)
  */
 void *devpts_get_priv(struct dentry *dentry)
 {
-	WARN_ON_ONCE(dentry->d_sb->s_magic != DEVPTS_SUPER_MAGIC);
+	if (dentry->d_sb->s_magic != DEVPTS_SUPER_MAGIC)
+		return NULL;
 	return dentry->d_fsdata;
 }
 
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 28cc41285..64eddc528 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -782,7 +782,13 @@ resizefs_out:
 			goto encryption_policy_out;
 		}
 
+		err = mnt_want_write_file(filp);
+		if (err)
+			goto encryption_policy_out;
+
 		err = ext4_process_policy(&policy, inode);
+
+		mnt_drop_write_file(filp);
 encryption_policy_out:
 		return err;
 #else
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 6cac3dc33..76962a349 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -540,13 +540,13 @@ void fuse_read_fill(struct fuse_req *req, struct file *file, loff_t pos,
 	req->out.args[0].size = count;
 }
 
-static void fuse_release_user_pages(struct fuse_req *req, int write)
+static void fuse_release_user_pages(struct fuse_req *req, bool should_dirty)
 {
 	unsigned i;
 
 	for (i = 0; i < req->num_pages; i++) {
 		struct page *page = req->pages[i];
-		if (write)
+		if (should_dirty)
 			set_page_dirty_lock(page);
 		put_page(page);
 	}
@@ -1331,6 +1331,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 		       loff_t *ppos, int flags)
 {
 	int write = flags & FUSE_DIO_WRITE;
+	bool should_dirty = !write && iter_is_iovec(iter);
 	int cuse = flags & FUSE_DIO_CUSE;
 	struct file *file = io->file;
 	struct inode *inode = file->f_mapping->host;
@@ -1374,7 +1375,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 			nres = fuse_send_read(req, io, pos, nbytes, owner);
 
 		if (!io->async)
-			fuse_release_user_pages(req, !write);
+			fuse_release_user_pages(req, should_dirty);
 		if (req->out.h.error) {
 			err = req->out.h.error;
 			break;
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index e1574008a..2bcb86e6e 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -840,21 +840,35 @@ repeat:
 	mutex_lock(&kernfs_mutex);
 
 	list_for_each_entry(info, &kernfs_root(kn)->supers, node) {
+		struct kernfs_node *parent;
 		struct inode *inode;
-		struct dentry *dentry;
 
+		/*
+		 * We want fsnotify_modify() on @kn but as the
+		 * modifications aren't originating from userland don't
+		 * have the matching @file available.  Look up the inodes
+		 * and generate the events manually.
+		 */
 		inode = ilookup(info->sb, kn->ino);
 		if (!inode)
 			continue;
 
-		dentry = d_find_any_alias(inode);
-		if (dentry) {
-			fsnotify_parent(NULL, dentry, FS_MODIFY);
-			fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE,
-				 NULL, 0);
-			dput(dentry);
+		parent = kernfs_get_parent(kn);
+		if (parent) {
+			struct inode *p_inode;
+
+			p_inode = ilookup(info->sb, parent->ino);
+			if (p_inode) {
+				fsnotify(p_inode, FS_MODIFY | FS_EVENT_ON_CHILD,
+					 inode, FSNOTIFY_EVENT_INODE, kn->name, 0);
+				iput(p_inode);
+			}
+
+			kernfs_put(parent);
 		}
 
+		fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE,
+			 kn->name, 0);
 		iput(inode);
 	}
 
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index a7f2e6e33..52a28311e 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -275,6 +275,7 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv,
 err_socks:
 	svc_rpcb_cleanup(serv, net);
 err_bind:
+	nn->cb_users[minorversion]--;
 	dprintk("NFS: Couldn't create callback socket: err = %d; "
 			"net = %p\n", ret, net);
 	return ret;
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index aaa2e8d3d..8cfa21f40 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -430,11 +430,8 @@ static bool referring_call_exists(struct nfs_client *clp,
 				((u32 *)&rclist->rcl_sessionid.data)[3],
 				ref->rc_sequenceid, ref->rc_slotid);
 
-			spin_lock(&tbl->slot_tbl_lock);
-			status = (test_bit(ref->rc_slotid, tbl->used_slots) &&
-				  tbl->slots[ref->rc_slotid].seq_nr ==
+			status = nfs4_slot_seqid_in_use(tbl, ref->rc_slotid,
 					ref->rc_sequenceid);
-			spin_unlock(&tbl->slot_tbl_lock);
 			if (status)
 				goto out;
 		}
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 0e8018bc9..6da14aedd 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -806,11 +806,14 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
 {
 	struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
 	struct nfs4_pnfs_ds *ds;
+	bool fail_return = false;
 	int idx;
 
 	/* mirrors are sorted by efficiency */
 	for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) {
-		ds = nfs4_ff_layout_prepare_ds(lseg, idx, false);
+		if (idx+1 == fls->mirror_array_cnt)
+			fail_return = true;
+		ds = nfs4_ff_layout_prepare_ds(lseg, idx, fail_return);
 		if (ds) {
 			*best_idx = idx;
 			return ds;
@@ -859,6 +862,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 	struct nfs4_pnfs_ds *ds;
 	int ds_idx;
 
+retry:
 	/* Use full layout for now */
 	if (!pgio->pg_lseg)
 		ff_layout_pg_get_read(pgio, req, false);
@@ -871,10 +875,13 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 
 	ds = ff_layout_choose_best_ds_for_read(pgio->pg_lseg, 0, &ds_idx);
 	if (!ds) {
-		if (ff_layout_no_fallback_to_mds(pgio->pg_lseg))
-			goto out_pnfs;
-		else
+		if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
 			goto out_mds;
+		pnfs_put_lseg(pgio->pg_lseg);
+		pgio->pg_lseg = NULL;
+		/* Sleep for 1 second before retrying */
+		ssleep(1);
+		goto retry;
 	}
 
 	mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx);
@@ -890,12 +897,6 @@ out_mds:
 	pnfs_put_lseg(pgio->pg_lseg);
 	pgio->pg_lseg = NULL;
 	nfs_pageio_reset_read_mds(pgio);
-	return;
-
-out_pnfs:
-	pnfs_set_lo_fail(pgio->pg_lseg);
-	pnfs_put_lseg(pgio->pg_lseg);
-	pgio->pg_lseg = NULL;
 }
 
 static void
@@ -909,6 +910,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	int i;
 	int status;
 
+retry:
 	if (!pgio->pg_lseg) {
 		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 						   req->wb_context,
@@ -940,10 +942,13 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	for (i = 0; i < pgio->pg_mirror_count; i++) {
 		ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, i, true);
 		if (!ds) {
-			if (ff_layout_no_fallback_to_mds(pgio->pg_lseg))
-				goto out_pnfs;
-			else
+			if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
 				goto out_mds;
+			pnfs_put_lseg(pgio->pg_lseg);
+			pgio->pg_lseg = NULL;
+			/* Sleep for 1 second before retrying */
+			ssleep(1);
+			goto retry;
 		}
 		pgm = &pgio->pg_mirrors[i];
 		mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
@@ -956,12 +961,6 @@ out_mds:
 	pnfs_put_lseg(pgio->pg_lseg);
 	pgio->pg_lseg = NULL;
 	nfs_pageio_reset_write_mds(pgio);
-	return;
-
-out_pnfs:
-	pnfs_set_lo_fail(pgio->pg_lseg);
-	pnfs_put_lseg(pgio->pg_lseg);
-	pgio->pg_lseg = NULL;
 }
 
 static unsigned int
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index 0aa36be71..ae5e15fd1 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -379,7 +379,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
 
 	devid = &mirror->mirror_ds->id_node;
 	if (ff_layout_test_devid_unavailable(devid))
-		goto out;
+		goto out_fail;
 
 	ds = mirror->mirror_ds->ds;
 	/* matching smp_wmb() in _nfs4_pnfs_v3/4_ds_connect */
@@ -405,15 +405,16 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
 			mirror->mirror_ds->ds_versions[0].rsize = max_payload;
 		if (mirror->mirror_ds->ds_versions[0].wsize > max_payload)
 			mirror->mirror_ds->ds_versions[0].wsize = max_payload;
-	} else {
-		ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),
-					 mirror, lseg->pls_range.offset,
-					 lseg->pls_range.length, NFS4ERR_NXIO,
-					 OP_ILLEGAL, GFP_NOIO);
-		if (fail_return || !ff_layout_has_available_ds(lseg))
-			pnfs_error_mark_layout_for_return(ino, lseg);
-		ds = NULL;
+		goto out;
 	}
+	ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),
+				 mirror, lseg->pls_range.offset,
+				 lseg->pls_range.length, NFS4ERR_NXIO,
+				 OP_ILLEGAL, GFP_NOIO);
+out_fail:
+	if (fail_return || !ff_layout_has_available_ds(lseg))
+		pnfs_error_mark_layout_for_return(ino, lseg);
+	ds = NULL;
 out:
 	return ds;
 }
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 7796beacd..e2320c643 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7509,12 +7509,20 @@ static int _nfs4_proc_create_session(struct nfs_client *clp,
 	status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
 	trace_nfs4_create_session(clp, status);
 
+	switch (status) {
+	case -NFS4ERR_STALE_CLIENTID:
+	case -NFS4ERR_DELAY:
+	case -ETIMEDOUT:
+	case -EACCES:
+	case -EAGAIN:
+		goto out;
+	};
+
+	clp->cl_seqid++;
 	if (!status) {
 		/* Verify the session's negotiated channel_attrs values */
 		status = nfs4_verify_channel_attrs(&args, &res);
 		/* Increment the clientid slot sequence id */
-		if (clp->cl_seqid == res.seqid)
-			clp->cl_seqid++;
 		if (status)
 			goto out;
 		nfs4_update_session(session, &res);
diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c
index 332d06e64..c1f4c208f 100644
--- a/fs/nfs/nfs4session.c
+++ b/fs/nfs/nfs4session.c
@@ -172,6 +172,39 @@ struct nfs4_slot *nfs4_lookup_slot(struct nfs4_slot_table *tbl, u32 slotid)
 	return ERR_PTR(-E2BIG);
 }
 
+static int nfs4_slot_get_seqid(struct nfs4_slot_table  *tbl, u32 slotid,
+		u32 *seq_nr)
+	__must_hold(&tbl->slot_tbl_lock)
+{
+	struct nfs4_slot *slot;
+
+	slot = nfs4_lookup_slot(tbl, slotid);
+	if (IS_ERR(slot))
+		return PTR_ERR(slot);
+	*seq_nr = slot->seq_nr;
+	return 0;
+}
+
+/*
+ * nfs4_slot_seqid_in_use - test if a slot sequence id is still in use
+ *
+ * Given a slot table, slot id and sequence number, determine if the
+ * RPC call in question is still in flight. This function is mainly
+ * intended for use by the callback channel.
+ */
+bool nfs4_slot_seqid_in_use(struct nfs4_slot_table *tbl, u32 slotid, u32 seq_nr)
+{
+	u32 cur_seq;
+	bool ret = false;
+
+	spin_lock(&tbl->slot_tbl_lock);
+	if (nfs4_slot_get_seqid(tbl, slotid, &cur_seq) == 0 &&
+	    cur_seq == seq_nr && test_bit(slotid, tbl->used_slots))
+		ret = true;
+	spin_unlock(&tbl->slot_tbl_lock);
+	return ret;
+}
+
 /*
  * nfs4_alloc_slot - efficiently look for a free slot
  *
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index 5b51298d1..33cace62b 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -78,6 +78,7 @@ extern int nfs4_setup_slot_table(struct nfs4_slot_table *tbl,
 extern void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl);
 extern struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl);
 extern struct nfs4_slot *nfs4_lookup_slot(struct nfs4_slot_table *tbl, u32 slotid);
+extern bool nfs4_slot_seqid_in_use(struct nfs4_slot_table  *tbl, u32 slotid, u32 seq_nr);
 extern bool nfs4_try_to_lock_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot);
 extern void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot);
 extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 7d992362f..229fa6139 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -876,6 +876,9 @@ void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo)
 static bool
 pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo)
 {
+	/* Serialise LAYOUTGET/LAYOUTRETURN */
+	if (atomic_read(&lo->plh_outstanding) != 0)
+		return false;
 	if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
 		return false;
 	lo->plh_return_iomode = 0;
@@ -1527,6 +1530,7 @@ pnfs_update_layout(struct inode *ino,
 	}
 
 lookup_again:
+	nfs4_client_recover_expired_lease(clp);
 	first = false;
 	spin_lock(&ino->i_lock);
 	lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 806eda192..6a2309840 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1200,27 +1200,6 @@ free_ol_stateid_reaplist(struct list_head *reaplist)
 	}
 }
 
-static void release_lockowner(struct nfs4_lockowner *lo)
-{
-	struct nfs4_client *clp = lo->lo_owner.so_client;
-	struct nfs4_ol_stateid *stp;
-	struct list_head reaplist;
-
-	INIT_LIST_HEAD(&reaplist);
-
-	spin_lock(&clp->cl_lock);
-	unhash_lockowner_locked(lo);
-	while (!list_empty(&lo->lo_owner.so_stateids)) {
-		stp = list_first_entry(&lo->lo_owner.so_stateids,
-				struct nfs4_ol_stateid, st_perstateowner);
-		WARN_ON(!unhash_lock_stateid(stp));
-		put_ol_stateid_locked(stp, &reaplist);
-	}
-	spin_unlock(&clp->cl_lock);
-	free_ol_stateid_reaplist(&reaplist);
-	nfs4_put_stateowner(&lo->lo_owner);
-}
-
 static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp,
 				       struct list_head *reaplist)
 {
@@ -5976,6 +5955,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
 	__be32 status;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 	struct nfs4_client *clp;
+	LIST_HEAD (reaplist);
 
 	dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n",
 		clid->cl_boot, clid->cl_id);
@@ -6006,9 +5986,23 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
 		nfs4_get_stateowner(sop);
 		break;
 	}
+	if (!lo) {
+		spin_unlock(&clp->cl_lock);
+		return status;
+	}
+
+	unhash_lockowner_locked(lo);
+	while (!list_empty(&lo->lo_owner.so_stateids)) {
+		stp = list_first_entry(&lo->lo_owner.so_stateids,
+				       struct nfs4_ol_stateid,
+				       st_perstateowner);
+		WARN_ON(!unhash_lock_stateid(stp));
+		put_ol_stateid_locked(stp, &reaplist);
+	}
 	spin_unlock(&clp->cl_lock);
-	if (lo)
-		release_lockowner(lo);
+	free_ol_stateid_reaplist(&reaplist);
+	nfs4_put_stateowner(&lo->lo_owner);
+
 	return status;
 }
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index dea2afd9d..86397c48b 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1552,18 +1552,13 @@ static const struct file_operations proc_pid_set_comm_operations = {
 static int proc_exe_link(struct dentry *dentry, struct path *exe_path)
 {
 	struct task_struct *task;
-	struct mm_struct *mm;
 	struct file *exe_file;
 
 	task = get_proc_task(d_inode(dentry));
 	if (!task)
 		return -ENOENT;
-	mm = get_task_mm(task);
+	exe_file = get_task_exe_file(task);
 	put_task_struct(task);
-	if (!mm)
-		return -ENOENT;
-	exe_file = get_mm_exe_file(mm);
-	mmput(mm);
 	if (exe_file) {
 		*exe_path = exe_file->f_path;
 		path_get(&exe_file->f_path);