Merge tag 'nfs-for-4.16-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

  Stable bugfixes:

   - Fix breakages in the nfsstat utility due to the inclusion of the
     NFSv4 LOOKUPP operation

   - Fix a NULL pointer dereference in nfs_idmap_prepare_pipe_upcall()
     due to nfs_idmap_legacy_upcall() being called without an 'aux'
     parameter

   - Fix a refcount leak in the standard O_DIRECT error path

   - Fix a refcount leak in the pNFS O_DIRECT fallback to MDS path

   - Fix CPU latency issues with nfs_commit_release_pages()

   - Fix the LAYOUTUNAVAILABLE error case in the file layout type

   - NFS: Fix a race between mmap() and O_DIRECT

  Features:

   - Support the statx() mask and query flags to enable optimisations
     when the user is requesting only attributes that are already up to
     date in the inode cache, or is specifying the AT_STATX_DONT_SYNC
     flag

   - Add a module alias for the SCSI pNFS layout type

  Bugfixes:

   - Automounting when resolving a NFSv4 referral should preserve the
     RDMA transport protocol settings

   - Various other RDMA bugfixes from Chuck

   - pNFS block layout fixes

   - Always set NFS_LOCK_LOST when a lock is lost"

* tag 'nfs-for-4.16-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (69 commits)
  NFS: Fix a race between mmap() and O_DIRECT
  NFS: Remove a redundant call to unmap_mapping_range()
  pnfs/blocklayout: Ensure disk address in block device map
  pnfs/blocklayout: pnfs_block_dev_map uses bytes, not sectors
  lockd: Fix server refcounting
  SUNRPC: Fix null rpc_clnt dereference in rpc_task_queued tracepoint
  SUNRPC: Micro-optimize __rpc_execute
  SUNRPC: task_run_action should display tk_callback
  sunrpc: Format RPC events consistently for display
  SUNRPC: Trace xprt_timer events
  xprtrdma: Correct some documenting comments
  xprtrdma: Fix "bytes registered" accounting
  xprtrdma: Instrument allocation/release of rpcrdma_req/rep objects
  xprtrdma: Add trace points to instrument QP and CQ access upcalls
  xprtrdma: Add trace points in the client-side backchannel code paths
  xprtrdma: Add trace points for connect events
  xprtrdma: Add trace points to instrument MR allocation and recovery
  xprtrdma: Add trace points to instrument memory invalidation
  xprtrdma: Add trace points in reply decoder path
  xprtrdma: Add trace points to instrument memory registration
  ..

21 files changed, 260 insertions, 106 deletions

diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 995d707537da..7cb5c38c19e4 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -137,6 +137,11 @@ bl_alloc_init_bio(int npg, struct block_device *bdev, sector_t disk_sector,
 	return bio;
 }
 
+static bool offset_in_map(u64 offset, struct pnfs_block_dev_map *map)
+{
+	return offset >= map->start && offset < map->start + map->len;
+}
+
 static struct bio *
 do_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect,
 		struct page *page, struct pnfs_block_dev_map *map,
@@ -156,8 +161,8 @@ do_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect,
 
 	/* translate to physical disk offset */
 	disk_addr = (u64)isect << SECTOR_SHIFT;
-	if (disk_addr < map->start || disk_addr >= map->start + map->len) {
-		if (!dev->map(dev, disk_addr, map))
+	if (!offset_in_map(disk_addr, map)) {
+		if (!dev->map(dev, disk_addr, map) || !offset_in_map(disk_addr, map))
 			return ERR_PTR(-EIO);
 		bio = bl_submit_bio(bio);
 	}
@@ -184,6 +189,29 @@ retry:
 	return bio;
 }
 
+static void bl_mark_devices_unavailable(struct nfs_pgio_header *header, bool rw)
+{
+	struct pnfs_block_layout *bl = BLK_LSEG2EXT(header->lseg);
+	size_t bytes_left = header->args.count;
+	sector_t isect, extent_length = 0;
+	struct pnfs_block_extent be;
+
+	isect = header->args.offset >> SECTOR_SHIFT;
+	bytes_left += header->args.offset - (isect << SECTOR_SHIFT);
+
+	while (bytes_left > 0) {
+		if (!ext_tree_lookup(bl, isect, &be, rw))
+				return;
+		extent_length = be.be_length - (isect - be.be_f_offset);
+		nfs4_mark_deviceid_unavailable(be.be_device);
+		isect += extent_length;
+		if (bytes_left > extent_length << SECTOR_SHIFT)
+			bytes_left -= extent_length << SECTOR_SHIFT;
+		else
+			bytes_left = 0;
+	}
+}
+
 static void bl_end_io_read(struct bio *bio)
 {
 	struct parallel_io *par = bio->bi_private;
@@ -194,6 +222,7 @@ static void bl_end_io_read(struct bio *bio)
 		if (!header->pnfs_error)
 			header->pnfs_error = -EIO;
 		pnfs_set_lo_fail(header->lseg);
+		bl_mark_devices_unavailable(header, false);
 	}
 
 	bio_put(bio);
@@ -323,6 +352,7 @@ static void bl_end_io_write(struct bio *bio)
 		if (!header->pnfs_error)
 			header->pnfs_error = -EIO;
 		pnfs_set_lo_fail(header->lseg);
+		bl_mark_devices_unavailable(header, true);
 	}
 	bio_put(bio);
 	put_parallel(par);
@@ -552,6 +582,31 @@ static int decode_sector_number(__be32 **rp, sector_t *sp)
 	return 0;
 }
 
+static struct nfs4_deviceid_node *
+bl_find_get_deviceid(struct nfs_server *server,
+		const struct nfs4_deviceid *id, struct rpc_cred *cred,
+		gfp_t gfp_mask)
+{
+	struct nfs4_deviceid_node *node;
+	unsigned long start, end;
+
+retry:
+	node = nfs4_find_get_deviceid(server, id, cred, gfp_mask);
+	if (!node)
+		return ERR_PTR(-ENODEV);
+
+	if (test_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags) == 0)
+		return node;
+
+	end = jiffies;
+	start = end - PNFS_DEVICE_RETRY_TIMEOUT;
+	if (!time_in_range(node->timestamp_unavailable, start, end)) {
+		nfs4_delete_deviceid(node->ld, node->nfs_client, id);
+		goto retry;
+	}
+	return ERR_PTR(-ENODEV);
+}
+
 static int
 bl_alloc_extent(struct xdr_stream *xdr, struct pnfs_layout_hdr *lo,
 		struct layout_verification *lv, struct list_head *extents,
@@ -573,16 +628,18 @@ bl_alloc_extent(struct xdr_stream *xdr, struct pnfs_layout_hdr *lo,
 	memcpy(&id, p, NFS4_DEVICEID4_SIZE);
 	p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
 
-	error = -EIO;
-	be->be_device = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), &id,
+	be->be_device = bl_find_get_deviceid(NFS_SERVER(lo->plh_inode), &id,
 						lo->plh_lc_cred, gfp_mask);
-	if (!be->be_device)
+	if (IS_ERR(be->be_device)) {
+		error = PTR_ERR(be->be_device);
 		goto out_free_be;
+	}
 
 	/*
 	 * The next three values are read in as bytes, but stored in the
 	 * extent structure in 512-byte granularity.
 	 */
+	error = -EIO;
 	if (decode_sector_number(&p, &be->be_f_offset) < 0)
 		goto out_put_deviceid;
 	if (decode_sector_number(&p, &be->be_length) < 0)
@@ -692,11 +749,16 @@ out_free_scratch:
 	__free_page(scratch);
 out:
 	dprintk("%s returns %d\n", __func__, status);
-	if (status) {
+	switch (status) {
+	case -ENODEV:
+		/* Our extent block devices are unavailable */
+		set_bit(NFS_LSEG_UNAVAILABLE, &lseg->pls_flags);
+	case 0:
+		return lseg;
+	default:
 		kfree(lseg);
 		return ERR_PTR(status);
 	}
-	return lseg;
 }
 
 static void
@@ -798,6 +860,13 @@ bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 	}
 
 	pnfs_generic_pg_init_read(pgio, req);
+
+	if (pgio->pg_lseg &&
+		test_bit(NFS_LSEG_UNAVAILABLE, &pgio->pg_lseg->pls_flags)) {
+		pnfs_error_mark_layout_for_return(pgio->pg_inode, pgio->pg_lseg);
+		pnfs_set_lo_fail(pgio->pg_lseg);
+		nfs_pageio_reset_read_mds(pgio);
+	}
 }
 
 /*
@@ -853,6 +922,14 @@ bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 		wb_size = nfs_dreq_bytes_left(pgio->pg_dreq);
 
 	pnfs_generic_pg_init_write(pgio, req, wb_size);
+
+	if (pgio->pg_lseg &&
+		test_bit(NFS_LSEG_UNAVAILABLE, &pgio->pg_lseg->pls_flags)) {
+
+		pnfs_error_mark_layout_for_return(pgio->pg_inode, pgio->pg_lseg);
+		pnfs_set_lo_fail(pgio->pg_lseg);
+		nfs_pageio_reset_write_mds(pgio);
+	}
 }
 
 /*
@@ -887,6 +964,7 @@ static struct pnfs_layoutdriver_type blocklayout_type = {
 	.name				= "LAYOUT_BLOCK_VOLUME",
 	.owner				= THIS_MODULE,
 	.flags				= PNFS_LAYOUTRET_ON_SETATTR |
+					  PNFS_LAYOUTRET_ON_ERROR |
 					  PNFS_READ_WHOLE_PAGE,
 	.read_pagelist			= bl_read_pagelist,
 	.write_pagelist			= bl_write_pagelist,
@@ -910,6 +988,7 @@ static struct pnfs_layoutdriver_type scsilayout_type = {
 	.name				= "LAYOUT_SCSI",
 	.owner				= THIS_MODULE,
 	.flags				= PNFS_LAYOUTRET_ON_SETATTR |
+					  PNFS_LAYOUTRET_ON_ERROR |
 					  PNFS_READ_WHOLE_PAGE,
 	.read_pagelist			= bl_read_pagelist,
 	.write_pagelist			= bl_write_pagelist,
@@ -967,6 +1046,7 @@ static void __exit nfs4blocklayout_exit(void)
 }
 
 MODULE_ALIAS("nfs-layouttype4-3");
+MODULE_ALIAS("nfs-layouttype4-5");
 
 module_init(nfs4blocklayout_init);
 module_exit(nfs4blocklayout_exit);
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index efc007f00742..716bc75e9ed2 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -92,10 +92,9 @@ struct pnfs_block_volume {
 };
 
 struct pnfs_block_dev_map {
-	sector_t			start;
-	sector_t			len;
-
-	sector_t			disk_offset;
+	u64			start;
+	u64			len;
+	u64			disk_offset;
 	struct block_device		*bdev;
 };
 
diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c
index 95f74bd2c067..a7efd83779d2 100644
--- a/fs/nfs/blocklayout/dev.c
+++ b/fs/nfs/blocklayout/dev.c
@@ -533,14 +533,11 @@ bl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 		goto out_free_volumes;
 
 	ret = bl_parse_deviceid(server, top, volumes, nr_volumes - 1, gfp_mask);
-	if (ret) {
-		bl_free_device(top);
-		kfree(top);
-		goto out_free_volumes;
-	}
 
 	node = &top->node;
 	nfs4_init_deviceid_node(node, server, &pdev->dev_id);
+	if (ret)
+		nfs4_mark_deviceid_unavailable(node);
 
 out_free_volumes:
 	kfree(volumes);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index d2972d537469..8c10b0562e75 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -775,10 +775,8 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 
 	spin_lock(&dreq->lock);
 
-	if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) {
-		dreq->flags = 0;
+	if (test_bit(NFS_IOHDR_ERROR, &hdr->flags))
 		dreq->error = hdr->error;
-	}
 	if (dreq->error == 0) {
 		nfs_direct_good_bytes(dreq, hdr);
 		if (nfs_write_need_commit(hdr)) {
diff --git a/fs/nfs/export.c b/fs/nfs/export.c
index 83fd09fc8f77..ab5de3246c5c 100644
--- a/fs/nfs/export.c
+++ b/fs/nfs/export.c
@@ -48,10 +48,6 @@ nfs_encode_fh(struct inode *inode, __u32 *p, int *max_len, struct inode *parent)
 		*max_len = len;
 		return FILEID_INVALID;
 	}
-	if (IS_AUTOMOUNT(inode)) {
-		*max_len = FILEID_INVALID;
-		goto out;
-	}
 
 	p[FILEID_HIGH_OFF] = NFS_FILEID(inode) >> 32;
 	p[FILEID_LOW_OFF] = NFS_FILEID(inode);
@@ -59,7 +55,6 @@ nfs_encode_fh(struct inode *inode, __u32 *p, int *max_len, struct inode *parent)
 	p[len - 1] = 0; /* Padding */
 	nfs_copy_fh(clnt_fh, server_fh);
 	*max_len = len;
-out:
 	dprintk("%s: result fh fileid %llu mode %u size %d\n",
 		__func__, NFS_FILEID(inode), inode->i_mode, *max_len);
 	return *max_len;
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 4e54d8b5413a..d175724ff566 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -895,9 +895,7 @@ fl_pnfs_update_layout(struct inode *ino,
 
 	lseg = pnfs_update_layout(ino, ctx, pos, count, iomode, strict_iomode,
 				  gfp_flags);
-	if (!lseg)
-		lseg = ERR_PTR(-ENOMEM);
-	if (IS_ERR(lseg))
+	if (IS_ERR_OR_NULL(lseg))
 		goto out;
 
 	lo = NFS_I(ino)->layout;
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 93552c482992..ceeaf0fb6657 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -735,12 +735,20 @@ int nfs_getattr(const struct path *path, struct kstat *stat,
 		u32 request_mask, unsigned int query_flags)
 {
 	struct inode *inode = d_inode(path->dentry);
-	int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME;
+	struct nfs_server *server = NFS_SERVER(inode);
+	unsigned long cache_validity;
 	int err = 0;
+	bool force_sync = query_flags & AT_STATX_FORCE_SYNC;
+	bool do_update = false;
 
 	trace_nfs_getattr_enter(inode);
+
+	if ((query_flags & AT_STATX_DONT_SYNC) && !force_sync)
+		goto out_no_update;
+
 	/* Flush out writes to the server in order to update c/mtime.  */
-	if (S_ISREG(inode->i_mode)) {
+	if ((request_mask & (STATX_CTIME|STATX_MTIME)) &&
+			S_ISREG(inode->i_mode)) {
 		err = filemap_write_and_wait(inode->i_mapping);
 		if (err)
 			goto out;
@@ -757,24 +765,42 @@ int nfs_getattr(const struct path *path, struct kstat *stat,
 	 */
 	if ((path->mnt->mnt_flags & MNT_NOATIME) ||
 	    ((path->mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)))
-		need_atime = 0;
-
-	if (need_atime || nfs_need_revalidate_inode(inode)) {
-		struct nfs_server *server = NFS_SERVER(inode);
-
+		request_mask &= ~STATX_ATIME;
+
+	/* Is the user requesting attributes that might need revalidation? */
+	if (!(request_mask & (STATX_MODE|STATX_NLINK|STATX_ATIME|STATX_CTIME|
+					STATX_MTIME|STATX_UID|STATX_GID|
+					STATX_SIZE|STATX_BLOCKS)))
+		goto out_no_revalidate;
+
+	/* Check whether the cached attributes are stale */
+	do_update |= force_sync || nfs_attribute_cache_expired(inode);
+	cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
+	do_update |= cache_validity &
+		(NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL);
+	if (request_mask & STATX_ATIME)
+		do_update |= cache_validity & NFS_INO_INVALID_ATIME;
+	if (request_mask & (STATX_CTIME|STATX_MTIME))
+		do_update |= cache_validity & NFS_INO_REVAL_PAGECACHE;
+	if (do_update) {
+		/* Update the attribute cache */
 		if (!(server->flags & NFS_MOUNT_NOAC))
 			nfs_readdirplus_parent_cache_miss(path->dentry);
 		else
 			nfs_readdirplus_parent_cache_hit(path->dentry);
 		err = __nfs_revalidate_inode(server, inode);
+		if (err)
+			goto out;
 	} else
 		nfs_readdirplus_parent_cache_hit(path->dentry);
-	if (!err) {
-		generic_fillattr(inode, stat);
-		stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode));
-		if (S_ISDIR(inode->i_mode))
-			stat->blksize = NFS_SERVER(inode)->dtsize;
-	}
+out_no_revalidate:
+	/* Only return attributes that were revalidated. */
+	stat->result_mask &= request_mask;
+out_no_update:
+	generic_fillattr(inode, stat);
+	stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode));
+	if (S_ISDIR(inode->i_mode))
+		stat->blksize = NFS_SERVER(inode)->dtsize;
 out:
 	trace_nfs_getattr_exit(inode, err);
 	return err;
@@ -1144,7 +1170,6 @@ 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;
diff --git a/fs/nfs/io.c b/fs/nfs/io.c
index 20fef85d2bb1..9034b4926909 100644
--- a/fs/nfs/io.c
+++ b/fs/nfs/io.c
@@ -99,7 +99,7 @@ static void nfs_block_buffered(struct nfs_inode *nfsi, struct inode *inode)
 {
 	if (!test_bit(NFS_INO_ODIRECT, &nfsi->flags)) {
 		set_bit(NFS_INO_ODIRECT, &nfsi->flags);
-		nfs_wb_all(inode);
+		nfs_sync_mapping(inode->i_mapping);
 	}
 }
 
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 65a7e5da508c..04612c24d394 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -861,6 +861,7 @@ static int nfs4_set_client(struct nfs_server *server,
 		set_bit(NFS_CS_MIGRATION, &cl_init.init_flags);
 	if (test_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status))
 		set_bit(NFS_CS_TSM_POSSIBLE, &cl_init.init_flags);
+	server->port = rpc_get_port(addr);
 
 	/* Allocate or find a client reference we can use */
 	clp = nfs_get_client(&cl_init);
@@ -1123,19 +1124,36 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
 	/* Initialise the client representation from the parent server */
 	nfs_server_copy_userdata(server, parent_server);
 
-	/* Get a client representation.
-	 * Note: NFSv4 always uses TCP, */
+	/* Get a client representation */
+#ifdef CONFIG_SUNRPC_XPRT_RDMA
+	rpc_set_port(data->addr, NFS_RDMA_PORT);
 	error = nfs4_set_client(server, data->hostname,
 				data->addr,
 				data->addrlen,
 				parent_client->cl_ipaddr,
-				rpc_protocol(parent_server->client),
+				XPRT_TRANSPORT_RDMA,
+				parent_server->client->cl_timeout,
+				parent_client->cl_mvops->minor_version,
+				parent_client->cl_net);
+	if (!error)
+		goto init_server;
+#endif	/* CONFIG_SUNRPC_XPRT_RDMA */
+
+	rpc_set_port(data->addr, NFS_PORT);
+	error = nfs4_set_client(server, data->hostname,
+				data->addr,
+				data->addrlen,
+				parent_client->cl_ipaddr,
+				XPRT_TRANSPORT_TCP,
 				parent_server->client->cl_timeout,
 				parent_client->cl_mvops->minor_version,
 				parent_client->cl_net);
 	if (error < 0)
 		goto error;
 
+#ifdef CONFIG_SUNRPC_XPRT_RDMA
+init_server:
+#endif
 	error = nfs_init_server_rpcclient(server, parent_server->client->cl_timeout, data->authflavor);
 	if (error < 0)
 		goto error;
diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c
index 30426c1a1bbd..22dc30a679a0 100644
--- a/fs/nfs/nfs4idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -568,9 +568,13 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons,
 	struct idmap_msg *im;
 	struct idmap *idmap = (struct idmap *)aux;
 	struct key *key = cons->key;
-	int ret = -ENOMEM;
+	int ret = -ENOKEY;
+
+	if (!aux)
+		goto out1;
 
 	/* msg and im are freed in idmap_pipe_destroy_msg */
+	ret = -ENOMEM;
 	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		goto out1;
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 8c3f327d858d..24f06dcc2b08 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -270,8 +270,6 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
 		if (mountdata->addrlen == 0)
 			continue;
 
-		rpc_set_port(mountdata->addr, NFS_PORT);
-
 		memcpy(page2, buf->data, buf->len);
 		page2[buf->len] = '\0';
 		mountdata->hostname = page2;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 17a03f2c4330..47f3c273245e 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2020,7 +2020,7 @@ static int nfs4_open_reclaim(struct nfs4_state_owner *sp, struct nfs4_state *sta
 	return ret;
 }
 
-static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct nfs4_state *state, const nfs4_stateid *stateid, int err)
+static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct nfs4_state *state, const nfs4_stateid *stateid, struct file_lock *fl, int err)
 {
 	switch (err) {
 		default:
@@ -2067,7 +2067,11 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct
 			return -EAGAIN;
 		case -ENOMEM:
 		case -NFS4ERR_DENIED:
-			/* kill_proc(fl->fl_pid, SIGLOST, 1); */
+			if (fl) {
+				struct nfs4_lock_state *lsp = fl->fl_u.nfs4_fl.owner;
+				if (lsp)
+					set_bit(NFS_LOCK_LOST, &lsp->ls_flags);
+			}
 			return 0;
 	}
 	return err;
@@ -2103,7 +2107,7 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx,
 		err = nfs4_open_recover_helper(opendata, FMODE_READ);
 	}
 	nfs4_opendata_put(opendata);
-	return nfs4_handle_delegation_recall_error(server, state, stateid, err);
+	return nfs4_handle_delegation_recall_error(server, state, stateid, NULL, err);
 }
 
 static void nfs4_open_confirm_prepare(struct rpc_task *task, void *calldata)
@@ -3150,6 +3154,11 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 	struct nfs4_state *state = calldata->state;
 	struct nfs_server *server = NFS_SERVER(calldata->inode);
 	nfs4_stateid *res_stateid = NULL;
+	struct nfs4_exception exception = {
+		.state = state,
+		.inode = calldata->inode,
+		.stateid = &calldata->arg.stateid,
+	};
 
 	dprintk("%s: begin!\n", __func__);
 	if (!nfs4_sequence_done(task, &calldata->res.seq_res))
@@ -3215,7 +3224,9 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 		case -NFS4ERR_BAD_STATEID:
 			break;
 		default:
-			if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN)
+			task->tk_status = nfs4_async_handle_exception(task,
+					server, task->tk_status, &exception);
+			if (exception.retry)
 				goto out_restart;
 	}
 	nfs_clear_open_stateid(state, &calldata->arg.stateid,
@@ -5759,6 +5770,10 @@ struct nfs4_delegreturndata {
 static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_delegreturndata *data = calldata;
+	struct nfs4_exception exception = {
+		.inode = data->inode,
+		.stateid = &data->stateid,
+	};
 
 	if (!nfs4_sequence_done(task, &data->res.seq_res))
 		return;
@@ -5820,10 +5835,11 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
 		}
 		/* Fallthrough */
 	default:
-		if (nfs4_async_handle_error(task, data->res.server,
-					    NULL, NULL) == -EAGAIN) {
+		task->tk_status = nfs4_async_handle_exception(task,
+				data->res.server, task->tk_status,
+				&exception);
+		if (exception.retry)
 			goto out_restart;
-		}
 	}
 	data->rpc_status = task->tk_status;
 	return;
@@ -6061,6 +6077,10 @@ static void nfs4_locku_release_calldata(void *data)
 static void nfs4_locku_done(struct rpc_task *task, void *data)
 {
 	struct nfs4_unlockdata *calldata = data;
+	struct nfs4_exception exception = {
+		.inode = calldata->lsp->ls_state->inode,
+		.stateid = &calldata->arg.stateid,
+	};
 
 	if (!nfs4_sequence_done(task, &calldata->res.seq_res))
 		return;
@@ -6084,8 +6104,10 @@ static void nfs4_locku_done(struct rpc_task *task, void *data)
 				rpc_restart_call_prepare(task);
 			break;
 		default:
-			if (nfs4_async_handle_error(task, calldata->server,
-						    NULL, NULL) == -EAGAIN)
+			task->tk_status = nfs4_async_handle_exception(task,
+					calldata->server, task->tk_status,
+					&exception);
+			if (exception.retry)
 				rpc_restart_call_prepare(task);
 	}
 	nfs_release_seqid(calldata->arg.seqid);
@@ -6741,7 +6763,7 @@ int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state,
 	if (err != 0)
 		return err;
 	err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW);
-	return nfs4_handle_delegation_recall_error(server, state, stateid, err);
+	return nfs4_handle_delegation_recall_error(server, state, stateid, fl, err);
 }
 
 struct nfs_release_lockowner_data {
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index e4f4a09ed9f4..91a4d4eeb235 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1482,6 +1482,7 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
 	struct inode *inode = state->inode;
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct file_lock *fl;
+	struct nfs4_lock_state *lsp;
 	int status = 0;
 	struct file_lock_context *flctx = inode->i_flctx;
 	struct list_head *list;
@@ -1522,7 +1523,9 @@ restart:
 		case -NFS4ERR_DENIED:
 		case -NFS4ERR_RECLAIM_BAD:
 		case -NFS4ERR_RECLAIM_CONFLICT:
-			/* kill_proc(fl->fl_pid, SIGLOST, 1); */
+			lsp = fl->fl_u.nfs4_fl.owner;
+			if (lsp)
+				set_bit(NFS_LOCK_LOST, &lsp->ls_flags);
 			status = 0;
 		}
 		spin_lock(&flctx->flc_lock);
diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c
index 0d91d84e5822..c394e4447100 100644
--- a/fs/nfs/nfs4sysctl.c
+++ b/fs/nfs/nfs4sysctl.c
@@ -32,7 +32,7 @@ static struct ctl_table nfs4_cb_sysctls[] = {
 		.data = &nfs_idmap_cache_timeout,
 		.maxlen = sizeof(int),
 		.mode = 0644,
-		.proc_handler = proc_dointvec_jiffies,
+		.proc_handler = proc_dointvec,
 	},
 	{ }
 };
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 77c6729e57f0..65c9c4175145 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7678,6 +7678,22 @@ nfs4_stat_to_errno(int stat)
 	.p_name = #proc,	\
 }
 
+#if defined(CONFIG_NFS_V4_1)
+#define PROC41(proc, argtype, restype)				\
+	PROC(proc, argtype, restype)
+#else
+#define PROC41(proc, argtype, restype)				\
+	STUB(proc)
+#endif
+
+#if defined(CONFIG_NFS_V4_2)
+#define PROC42(proc, argtype, restype)				\
+	PROC(proc, argtype, restype)
+#else
+#define PROC42(proc, argtype, restype)				\
+	STUB(proc)
+#endif
+
 const struct rpc_procinfo nfs4_procedures[] = {
 	PROC(READ,		enc_read,		dec_read),
 	PROC(WRITE,		enc_write,		dec_write),
@@ -7698,7 +7714,6 @@ const struct rpc_procinfo nfs4_procedures[] = {
 	PROC(ACCESS,		enc_access,		dec_access),
 	PROC(GETATTR,		enc_getattr,		dec_getattr),
 	PROC(LOOKUP,		enc_lookup,		dec_lookup),
-	PROC(LOOKUPP,		enc_lookupp,		dec_lookupp),
 	PROC(LOOKUP_ROOT,	enc_lookup_root,	dec_lookup_root),
 	PROC(REMOVE,		enc_remove,		dec_remove),
 	PROC(RENAME,		enc_rename,		dec_rename),
@@ -7717,33 +7732,30 @@ const struct rpc_procinfo nfs4_procedures[] = {
 	PROC(RELEASE_LOCKOWNER,	enc_release_lockowner,	dec_release_lockowner),
 	PROC(SECINFO,		enc_secinfo,		dec_secinfo),
 	PROC(FSID_PRESENT,	enc_fsid_present,	dec_fsid_present),
-#if defined(CONFIG_NFS_V4_1)
-	PROC(EXCHANGE_ID,	enc_exchange_id,	dec_exchange_id),
-	PROC(CREATE_SESSION,	enc_create_session,	dec_create_session),
-	PROC(DESTROY_SESSION,	enc_destroy_session,	dec_destroy_session),
-	PROC(SEQUENCE,		enc_sequence,		dec_sequence),
-	PROC(GET_LEASE_TIME,	enc_get_lease_time,	dec_get_lease_time),
-	PROC(RECLAIM_COMPLETE,	enc_reclaim_complete,	dec_reclaim_complete),
-	PROC(GETDEVICEINFO,	enc_getdeviceinfo,	dec_getdeviceinfo),
-	PROC(LAYOUTGET,		enc_layoutget,		dec_layoutget),
-	PROC(LAYOUTCOMMIT,	enc_layoutcommit,	dec_layoutcommit),
-	PROC(LAYOUTRETURN,	enc_layoutreturn,	dec_layoutreturn),
-	PROC(SECINFO_NO_NAME,	enc_secinfo_no_name,	dec_secinfo_no_name),
-	PROC(TEST_STATEID,	enc_test_stateid,	dec_test_stateid),
-	PROC(FREE_STATEID,	enc_free_stateid,	dec_free_stateid),
+	PROC41(EXCHANGE_ID,	enc_exchange_id,	dec_exchange_id),
+	PROC41(CREATE_SESSION,	enc_create_session,	dec_create_session),
+	PROC41(DESTROY_SESSION,	enc_destroy_session,	dec_destroy_session),
+	PROC41(SEQUENCE,	enc_sequence,		dec_sequence),
+	PROC41(GET_LEASE_TIME,	enc_get_lease_time,	dec_get_lease_time),
+	PROC41(RECLAIM_COMPLETE,enc_reclaim_complete,	dec_reclaim_complete),
+	PROC41(GETDEVICEINFO,	enc_getdeviceinfo,	dec_getdeviceinfo),
+	PROC41(LAYOUTGET,	enc_layoutget,		dec_layoutget),
+	PROC41(LAYOUTCOMMIT,	enc_layoutcommit,	dec_layoutcommit),
+	PROC41(LAYOUTRETURN,	enc_layoutreturn,	dec_layoutreturn),
+	PROC41(SECINFO_NO_NAME,	enc_secinfo_no_name,	dec_secinfo_no_name),
+	PROC41(TEST_STATEID,	enc_test_stateid,	dec_test_stateid),
+	PROC41(FREE_STATEID,	enc_free_stateid,	dec_free_stateid),
 	STUB(GETDEVICELIST),
-	PROC(BIND_CONN_TO_SESSION,
+	PROC41(BIND_CONN_TO_SESSION,
 			enc_bind_conn_to_session, dec_bind_conn_to_session),
-	PROC(DESTROY_CLIENTID,	enc_destroy_clientid,	dec_destroy_clientid),
-#endif /* CONFIG_NFS_V4_1 */
-#ifdef CONFIG_NFS_V4_2
-	PROC(SEEK,		enc_seek,		dec_seek),
-	PROC(ALLOCATE,		enc_allocate,		dec_allocate),
-	PROC(DEALLOCATE,	enc_deallocate,		dec_deallocate),
-	PROC(LAYOUTSTATS,	enc_layoutstats,	dec_layoutstats),
-	PROC(CLONE,		enc_clone,		dec_clone),
-	PROC(COPY,		enc_copy,		dec_copy),
-#endif /* CONFIG_NFS_V4_2 */
+	PROC41(DESTROY_CLIENTID,enc_destroy_clientid,	dec_destroy_clientid),
+	PROC42(SEEK,		enc_seek,		dec_seek),
+	PROC42(ALLOCATE,	enc_allocate,		dec_allocate),
+	PROC42(DEALLOCATE,	enc_deallocate,		dec_deallocate),
+	PROC42(LAYOUTSTATS,	enc_layoutstats,	dec_layoutstats),
+	PROC42(CLONE,		enc_clone,		dec_clone),
+	PROC42(COPY,		enc_copy,		dec_copy),
+	PROC(LOOKUPP,		enc_lookupp,		dec_lookupp),
 };
 
 static unsigned int nfs_version4_counts[ARRAY_SIZE(nfs4_procedures)];
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 610d89d8942e..bd60f8d1e181 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -797,15 +797,15 @@ TRACE_EVENT(nfs_readpage_done,
 		)
 );
 
-/*
- * XXX: I tried using NFS_UNSTABLE and friends in this table, but they
- * all evaluate to 0 for some reason, even if I include linux/nfs.h.
- */
+TRACE_DEFINE_ENUM(NFS_UNSTABLE);
+TRACE_DEFINE_ENUM(NFS_DATA_SYNC);
+TRACE_DEFINE_ENUM(NFS_FILE_SYNC);
+
 #define nfs_show_stable(stable) \
 	__print_symbolic(stable, \
-			{ 0, " (UNSTABLE)" }, \
-			{ 1, " (DATA_SYNC)" }, \
-			{ 2, " (FILE_SYNC)" })
+			{ NFS_UNSTABLE, "UNSTABLE" }, \
+			{ NFS_DATA_SYNC, "DATA_SYNC" }, \
+			{ NFS_FILE_SYNC, "FILE_SYNC" })
 
 TRACE_EVENT(nfs_initiate_write,
 		TP_PROTO(
@@ -838,12 +838,12 @@ TRACE_EVENT(nfs_initiate_write,
 
 		TP_printk(
 			"fileid=%02x:%02x:%llu fhandle=0x%08x "
-			"offset=%lld count=%lu stable=%d%s",
+			"offset=%lld count=%lu stable=%s",
 			MAJOR(__entry->dev), MINOR(__entry->dev),
 			(unsigned long long)__entry->fileid,
 			__entry->fhandle,
 			__entry->offset, __entry->count,
-			__entry->stable, nfs_show_stable(__entry->stable)
+			nfs_show_stable(__entry->stable)
 		)
 );
 
@@ -882,13 +882,13 @@ TRACE_EVENT(nfs_writeback_done,
 
 		TP_printk(
 			"fileid=%02x:%02x:%llu fhandle=0x%08x "
-			"offset=%lld status=%d stable=%d%s "
+			"offset=%lld status=%d stable=%s "
 			"verifier 0x%016llx",
 			MAJOR(__entry->dev), MINOR(__entry->dev),
 			(unsigned long long)__entry->fileid,
 			__entry->fhandle,
 			__entry->offset, __entry->status,
-			__entry->stable, nfs_show_stable(__entry->stable),
+			nfs_show_stable(__entry->stable),
 			__entry->verifier
 		)
 );
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index d0543e19098a..18a7626ac638 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -537,7 +537,7 @@ EXPORT_SYMBOL_GPL(nfs_pgio_header_free);
  * @cinfo: Commit information for the call (writes only)
  */
 static void nfs_pgio_rpcsetup(struct nfs_pgio_header *hdr,
-			      unsigned int count, unsigned int offset,
+			      unsigned int count,
 			      int how, struct nfs_commit_info *cinfo)
 {
 	struct nfs_page *req = hdr->req;
@@ -546,10 +546,10 @@ static void nfs_pgio_rpcsetup(struct nfs_pgio_header *hdr,
 	 * NB: take care not to mess about with hdr->commit et al. */
 
 	hdr->args.fh     = NFS_FH(hdr->inode);
-	hdr->args.offset = req_offset(req) + offset;
+	hdr->args.offset = req_offset(req);
 	/* pnfs_set_layoutcommit needs this */
 	hdr->mds_offset = hdr->args.offset;
-	hdr->args.pgbase = req->wb_pgbase + offset;
+	hdr->args.pgbase = req->wb_pgbase;
 	hdr->args.pages  = hdr->page_array.pagevec;
 	hdr->args.count  = count;
 	hdr->args.context = get_nfs_open_context(req->wb_context);
@@ -789,7 +789,7 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc,
 		desc->pg_ioflags &= ~FLUSH_COND_STABLE;
 
 	/* Set up the argument struct */
-	nfs_pgio_rpcsetup(hdr, mirror->pg_count, 0, desc->pg_ioflags, &cinfo);
+	nfs_pgio_rpcsetup(hdr, mirror->pg_count, desc->pg_ioflags, &cinfo);
 	desc->pg_rpc_callops = &nfs_pgio_common_ops;
 	return 0;
 }
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index d602fe9e1ac8..c13e826614b5 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -655,7 +655,7 @@ pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 		return 0;
 	list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
 		if (pnfs_match_lseg_recall(lseg, recall_range, seq)) {
-			dprintk("%s: freeing lseg %p iomode %d seq %u"
+			dprintk("%s: freeing lseg %p iomode %d seq %u "
 				"offset %llu length %llu\n", __func__,
 				lseg, lseg->pls_range.iomode, lseg->pls_seq,
 				lseg->pls_range.offset, lseg->pls_range.length);
@@ -2255,7 +2255,7 @@ pnfs_write_through_mds(struct nfs_pageio_descriptor *desc,
 		nfs_pageio_reset_write_mds(desc);
 		mirror->pg_recoalesce = 1;
 	}
-	hdr->release(hdr);
+	hdr->completion_ops->completion(hdr);
 }
 
 static enum pnfs_try_status
@@ -2378,7 +2378,7 @@ pnfs_read_through_mds(struct nfs_pageio_descriptor *desc,
 		nfs_pageio_reset_read_mds(desc);
 		mirror->pg_recoalesce = 1;
 	}
-	hdr->release(hdr);
+	hdr->completion_ops->completion(hdr);
 }
 
 /*
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 8d507c361d98..daf6cbf5c15f 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -40,6 +40,7 @@ enum {
 	NFS_LSEG_ROC,		/* roc bit received from server */
 	NFS_LSEG_LAYOUTCOMMIT,	/* layoutcommit bit set for layoutcommit */
 	NFS_LSEG_LAYOUTRETURN,	/* layoutreturn bit set for layoutreturn */
+	NFS_LSEG_UNAVAILABLE,	/* unavailable bit set for temporary problem */
 };
 
 /* Individual ip address */
@@ -86,6 +87,7 @@ enum pnfs_try_status {
  */
 #define NFS4_DEF_DS_TIMEO   600 /* in tenths of a second */
 #define NFS4_DEF_DS_RETRANS 5
+#define PNFS_DEVICE_RETRY_TIMEOUT (120*HZ)
 
 /* error codes for internal use */
 #define NFS4ERR_RESET_TO_MDS   12001
@@ -524,8 +526,10 @@ static inline int pnfs_return_layout(struct inode *ino)
 	struct nfs_inode *nfsi = NFS_I(ino);
 	struct nfs_server *nfss = NFS_SERVER(ino);
 
-	if (pnfs_enabled_sb(nfss) && nfsi->layout)
+	if (pnfs_enabled_sb(nfss) && nfsi->layout) {
+		set_bit(NFS_LAYOUT_RETURN_REQUESTED, &nfsi->layout->plh_flags);
 		return _pnfs_return_layout(ino);
+	}
 
 	return 0;
 }
diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c
index 2961fcd7a2df..e8a07b3f9aaa 100644
--- a/fs/nfs/pnfs_dev.c
+++ b/fs/nfs/pnfs_dev.c
@@ -43,7 +43,6 @@
 #define NFS4_DEVICE_ID_HASH_SIZE	(1 << NFS4_DEVICE_ID_HASH_BITS)
 #define NFS4_DEVICE_ID_HASH_MASK	(NFS4_DEVICE_ID_HASH_SIZE - 1)
 
-#define PNFS_DEVICE_RETRY_TIMEOUT (120*HZ)
 
 static struct hlist_head nfs4_deviceid_cache[NFS4_DEVICE_ID_HASH_SIZE];
 static DEFINE_SPINLOCK(nfs4_deviceid_lock);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 12b2d477836b..7428a669d7a7 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1835,6 +1835,8 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 		set_bit(NFS_CONTEXT_RESEND_WRITES, &req->wb_context->flags);
 	next:
 		nfs_unlock_and_release_request(req);
+		/* Latency breaker */
+		cond_resched();
 	}
 	nfss = NFS_SERVER(data->inode);
 	if (atomic_long_read(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)